Cooperative Control of Source Characteristic, Wire Feed and Torch Motion in V Narrow Gap Pulsed MIG/MAG Welding INAMASA Keisuke; KANEKO Yasuyoshi; YAMANE Satoshi; OHSHIMA Kenji; YAMAMOTO Hikaru
Preprints of the National Meeting of JWS,
Volume：91,
First page：58,
Last page：59, Sep. 2012
厚板溶接の生産性を向上させるために，狭開先パルスMIG/MAG溶接におけるトーチモーションと電源特性の協調制御を提案する．すなわち、ウィービングに合わせて非線形特性電源の特性を切り替える溶接制御法について数値実験と溶接実験により有効性を示す。
JAPAN WELDING SOCIETY, Japanese
DOI：https://doi.org/10.14920/jwstaikai.2012f.0.58.0DOI ID：10.14920/jwstaikai.2012f.0.58.0,
CiNii Articles ID：10030687597,
CiNii Books ID：AN10273925 NUMERICAL SIMULATION OF MIG WELD POOL IN SWITCHBACK WELDING
Y. Kaneko; S. Yamane; K. Oshima
WELDING IN THE WORLD, Volume：53, Number：11-12, First page：R333, Last page：R341, Nov. 2009, [Reviewed]
The authors proposed a switchback welding method to make stable back beads in the first layer weld during one-side multi-layer welding. In the proposed welding method, a welding torch is moved backwards and forwards like a switchback. The torch motion is important in the control of the weld pool. In this paper, the influence of the torch motion on the weld pool shape is investigated in order to find the optimum welding parameters. Firstly, fundamental welding experiments were carried out in thin plate one-side butt welding to determine the parameters of numerical simulation. Secondly, a simple numerical model for switchback welding was constructed and a heat conduction analysis was carried out, to investigate the effect of the travel speed and backward stroke distance of the torch on the weld pool. When the travel speed of the forward stroke was faster than that of the backward stroke, the weld pool length became shorter than a constant travel speed. On the other hand, if the backward stroke distance became longer than half of the forward stroke distance, continuous back beads could be obtained, regardless of such a disturbance as fluctuation of the arc length. The validity of the switchback welding method was verified by numerical simulation and fundamental experiments.
INT INST WELDING, English, Scientific journal
ISSN：0043-2288, Web of Science ID：WOS:000274740300007
4-3 Health and Safety for Welding and Thermal Cutting(Chapter 4 Quality Control in Welded Fabrication,Lecture Note -A Class in Joining & Welding-) KOHYAMA Norihiko; HATANO Isao; YAMADA Hiroshi; OKUNO Tsutomu; YAMANE Satoshi; MIYAZAKI Kuniaki
Journal of the Japan Welding Society,
Volume：77,
Number：8,
First page：752,
Last page：760, Dec. 2008
Japan Welding Society, Japanese
DOI：https://doi.org/10.2207/jjws.77.752DOI ID：10.2207/jjws.77.752,
ISSN：0021-4787,
CiNii Articles ID：110007028544,
CiNii Books ID：AN00246019 Adaptation of robotic welding by the neural network Koizumi Manabu; Yamane Satoshi; Kaneko Yasuyoshi; Ohshima Kenji
Preprints of the National Meeting of JWS,
Volume：2008,
First page：15,
Last page：15, 2008
By presuming welding voltage using a neural network, unusual voltage decreases sputter generated owing to, and aims at performing quality welding.
JAPAN WELDING SOCIETY, Japanese
DOI：https://doi.org/10.14920/jwstaikai.2008s.0.15.0DOI ID：10.14920/jwstaikai.2008s.0.15.0,
CiNii Articles ID：130005045387 Numerical Simulation of Weld Pool in Narrow Gap Welding Yamane Satoshi; Takahashi Yusuke; Kaneko Yasuyoshi; Ohshima Kenji
Preprints of the National Meeting of JWS,
Volume：2006,
First page：59,
Last page：59, 2006
In order to get high quality of welding,it is necessary to make a stable back bead and to make weld pool to get the desired bead height.In order to improve this problem,the switch back welding method was proposed.
JAPAN WELDING SOCIETY
DOI：https://doi.org/10.14920/jwstaikai.2006f.0.59.0DOI ID：10.14920/jwstaikai.2006f.0.59.0,
CiNii Articles ID：130005045198 406 Seam Tracking of Welding Line in Switch Back Welding. YUZAWA Hiroki; KANEKO Yasuyoshi; YAMANE Satoshi; YAMAMOTO Hikaru; HIRAKAWA Manabu; OSHIMA Kenji
Pre-Prints of the National Meeting of JWS,
Number：76,
First page：170,
Last page：171, Mar. 2005
片面多層盛溶接におけるスイッチバック溶接法の実用化に対する問題点を検討するために，直線のみならず円周部分の裏当て材なしでの裏ビード形成，およびギャップ変動に対する溶接条件の適応制御技術の確立を目的としている．
Japan Welding Society, Japanese
DOI：https://doi.org/10.14920/jwstaikai.2005s.0.77.0DOI ID：10.14920/jwstaikai.2005s.0.77.0,
CiNii Articles ID：110004541029,
CiNii Books ID：AN10273925 Neural Network Model of Weld Pool in Pulsed MIG Welding HIRAI Akira; KANEKO Yasuyoshi; NAGASAWA Kazuya; YAMANE Satoshi; OSHIMA Kenji
quarterly journal of the Japan Welding Society,
Volume：21,
Number：2,
First page：227,
Last page：233, May 2003
This paper deals with the problem concerning the modeling and sensing of the weld pool. In order to obtain the high quality of the welding result, it is important to measure and control the penetration depth in the robotic welding. Since it is difficult to directly measure the penetration depth and the relationship among the penetration depth, the welding current and other weld pool parameters such as the surface shape of the weld pool and the gap width, is non-liner, the weld pool model is constructed by neural network to estimate the penetration depth. The input and output variables of neural network model are determined from the information of the deferential equation for the penetration depth and the weld pool widths. Some steady state data and a transient response data of the fundamental experiment result are used as the training data of neural network model. The neural network model with less error can be learned by using these training data. When the experimental data of the weld pool widths and the gap width are input to the neural network model, this model is performed as the sensor to estimate the penetration depth. The validity of the neural network model was verified by the welding experiment.
Japan Welding Society, Japanese
DOI：https://doi.org/10.2207/qjjws.21.227DOI ID：10.2207/qjjws.21.227,
ISSN：0288-4771,
CiNii Articles ID：110003422344,
CiNii Books ID：AN1005067X Intelligent cooperative control system in visual welding robot
LH Sharif; S Yamane; T Sugimoto; K Oshima
IECON'01: 27TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOLS 1-3, First page：439, Last page：443, 2001, [Reviewed]
Quality of a multi-layer welding depends on a welding in first layer. In order to get a high quality of the welding, it is necessary to make a stable back bead and to melt the base metals. In narrow, gap welding, it is difficult to control the bead height(deposited metal) and the back bead(the melted area of the backside) by using conventional welding, simultaneously. To improve this situation, authors propose a cooperative control of the welding equipments including the welding power source, the electrode wire feeder and the welding robot, i.e., the welding torch is not only oscillating on the groove, but also moving hack and forth. To control the heat input, the power source is controlled according to the torch motion( robot motion), too. In the forward process, the arc (the heat) is given to the root edges to get a wide back bead. In backward process, the suitable bead height is obtained. The idea of its robot motion comes from the knowledge of the skill welding works. The arc length must be kept short during the welding regardless of the unexpected disturbances. Therefore, Weld pool and the arc position are observed by using a CCD camera. A personal computer processes image and adjusts the welding current and the torch motion. The welding experiments are carried out to verify the validity of the cooperative control method.
IEEE, English, International conference proceedings
ISSN：1553-572X, Web of Science ID：WOS:000178186000078
Control in Welding System. OSHIMA Kenji; YAMANE Satoshi
QUARTERLY JOURNAL OF THE JAPAN WELDING SOCIETY,
Volume：67,
Number：1,
First page：53,
Last page：59, 1998
JAPAN WELDING SOCIETY, Japanese
DOI：https://doi.org/10.2207/qjjws1943.67.53DOI ID：10.2207/qjjws1943.67.53,
ISSN：0021-4787,
CiNii Articles ID：130003764093 Back bead control of the one-side robotic welding with visual sensor - Cooperative control of current-waveform and torch motion for change of gap and welding position
K Eguchi; S Yamane; H Sugi; T Kubota; K Oshima
IECON '98 - PROCEEDINGS OF THE 24TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOLS 1-4, First page：1182, Last page：1185, 1998, [Reviewed]
Control of the weld pool in a first layer of the one-side multi-layer welding is important to obtain a good quality of the welding. For this purpose, the authors propose a new method, the switch back welding method, to get the stable back be;ld. In the forward stroke, visual robot observes the groove shape and the root gap. In the backward process, it observes the surface of the weld pool every half cycle of the weaving to investigate whether the pulsed droplet is deposited to the root edge of the base metals :and whether the deposited metal bridges the gap between the both base metal or not. The welding speed, the current waveform anti the distance of the backward forward stroke are obtained by using the fuzzy inference to get the stable and wide back bead.
IEEE, English, International conference proceedings
ISSN：1553-572X, Web of Science ID：WOS:000077035900220
Application of neural network to detection of arc length, extension length and root gap in robotic welding
K Eguchi; S Yamane; H Sugi; T Kubota; K Oshima
IECON '98 - PROCEEDINGS OF THE 24TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOLS 1-4, First page：1131, Last page：1135, 1998, [Reviewed]
Full penetration control of the weld pool in a first layer of the one-side multilayer welding is important to obtain a good duality of welding. For this purpose, tbe authors propose a new method, the switch back welding method, to get the stable back bead. A welding torch is not only oscillated in the groove, but also moved backward and forward. Both voltage and current are entered to neural networks (N.N.) to estimate the wire extension and the are length. Moreover, the gap and the deviation of the oscillation center from gap center are estimated. Training data are made from experimental results. Performance of the are sensor is examined by giving testing data to the neural networks.
IEEE, English, International conference proceedings
ISSN：1553-572X, Web of Science ID：WOS:000077035900211
Sensing of groove gap and torch position using neural network in pulsed MIG welding
K Eguchi; S Yamane; S Horinaka; T Kubota; K Oshima
IECON '97 - PROCEEDINGS OF THE 23RD INTERNATIONAL CONFERENCE ON INDUSTRIAL ELECTRONICS, CONTROL, AND INSTRUMENTATION, VOLS. 1-4, First page：1409, Last page：1414, 1997, [Reviewed]
It is important to realize intelligent welding robots to obtain a good quality of the welding. For this purpose, it is required to detect root gap of groove and deviation from center of gap to center of the weaving. In order to simultaneously detect those, the authors propose an are sensor using neural networks (N.N.). Both are length and wire extension are found by N.N. The root edges of the groove and its center is estimated geometrically. Training data are made from experimental results. Performance of the are sensor is examined by giving testing data to the neural networks.
IEEE, English, International conference proceedings
ISSN：1553-572X, Web of Science ID：WOS:000073933000251
Application of multilayered fuzzy inference to the tracking of the orbit on a two dimensional plane using industrial robot
S Yamane; K Eguchi; M Numakura; K Oshima
PROCEEDINGS OF THE 1996 IEEE IECON - 22ND INTERNATIONAL CONFERENCE ON INDUSTRIAL ELECTRONICS, CONTROL, AND INSTRUMENTATION, VOLS 1-3, First page：1832, Last page：1837, 1996, [Reviewed]
This paper deals with the problem concerning the tracking of the orbit on the two dimensional plane with an arm type welding robot. New methods with a multilayered fuzzy controller are proposed for solving this problem. The performance of a fuzzy controller depends on the fuzzy variables and the control rules. Control rules are constructed from the knowledge of the robot operator. The fuzzy variables can be adjusted owing to the shape of the orbit obtained by using a CCD camera.
IEEE, English, International conference proceedings
ISSN：1553-572X, Web of Science ID：WOS:A1996BG90S00316
NEURAL CONTROL OF WELD POOL IN THE ROBOTIC WELDING
Y KANEKO; S YAMANE; K KUGAI; K OHSHIMA
IAS '94 - CONFERENCE RECORD OF THE 1994 INDUSTRY APPLICATIONS CONFERENCE/TWENTY-NINTH IAS ANNUAL MEETING, VOLS 1-3, First page：1914, Last page：1919, 1994, [Reviewed]
I E E E, English, International conference proceedings
ISSN：0197-2618, Web of Science ID：WOS:A1994BB96H00262
FUZZY CONTROL IN SEAM TRACKING OF THE WELDING ROBOTS USING SENSOR FUSION
S YAMANE; Y KANEKO; A HIRAI; K OHSHIMA
IAS '94 - CONFERENCE RECORD OF THE 1994 INDUSTRY APPLICATIONS CONFERENCE/TWENTY-NINTH IAS ANNUAL MEETING, VOLS 1-3, First page：1741, Last page：1747, 1994, [Reviewed]
I E E E, English, International conference proceedings
ISSN：0197-2618, Web of Science ID：WOS:A1994BB96H00238
NEURAL-NETWORK AND FUZZY CONTROL IN THE WELDING ROBOTS USING CCD CAMERA AND TOUCH SENSOR
Y KANEKO; S YAMANE; T KUBOTA; K OHSHIMA
IJCNN '93-NAGOYA : PROCEEDINGS OF 1993 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, First page：677, Last page：680, 1993, [Reviewed]
I E E E, English, International conference proceedings
Web of Science ID：WOS:A1993BA47B00161
NEURAL-NETWORK AND FUZZY CONTROL OF WELD POOL WITH WELDING ROBOT
S YAMANE; Y KANEKO; N KITAHARA; K OHSHIMA; M YAMAMOTO
IAS 93, PTS 1-3, First page：2175, Last page：2180, 1993, [Reviewed]
I E E E, English, International conference proceedings
Web of Science ID：WOS:A1993BZ56X00292
Tracking of the welding line using image processing
山根 敏
Volume：27, Number：9, First page：44, Last page：51, Sep. 2016
Japanese
ISSN：0915-6755, CiNii Articles ID：40020956333, CiNii Books ID：AN10164169
Examination concerning Automation of Titanium Welding
金子 裕良; 山根 敏
Volume：60, Number：1, First page：58, Last page：62, Jan. 2012
Japanese
ISSN：1341-1713, CiNii Articles ID：40019187683, CiNii Books ID：AN10468673
Application of MIG Switch Back Welding to thin Titanium Welding
YAMANE S; UJI K; HONDA N; KANEKO Y
Volume：29, Number：1, First page：61, Last page：66, 31 Dec. 2011
Japanese
ISSN：0288-4771, CiNii Articles ID：10030150603, CiNii Books ID：AN1005067X
Application of co-operative welding system to titanium welding
UJI Katsumasa; YAMANE Satoshi; KANEKO Yasuyoshi; OSHIMA Kenji
Volume：87, First page：158, Last page：159, 18 Aug. 2010
Japanese
CiNii Articles ID：10026559167, CiNii Books ID：AN10273925
High-quality thin plate welding of magnesium in TIG welding
TAKADA Taro; KANEKO Yasuyoshi; YAMANE Satoshi; OHSHIMA Kenji
Volume：87, First page：156, Last page：157, 18 Aug. 2010
Japanese
CiNii Articles ID：10026559163, CiNii Books ID：AN10273925
Estimation of Welding Voltage Using Neural Network in GMA Welding
YAMANE Satoshi; KOIZUMI Manabu; IMAI Yuusuke; KANEKO Yasuyoshi; OSHIMA Kenji
Volume：27, Number：2, First page：27s, Last page：31s, 20 Jan. 2010
English
ISSN：0288-4771, CiNii Articles ID：10030148834, CiNii Books ID：AN1005067X
423 Control of Weld Pool By Switchback Welding
Miyashita Ken; Kaneko Yasuyoshi; Yamane Satoshi; Ohshima Kenji
Pre-Prints of the National Meeting of JWS, Number：83, First page：358, Last page：359, 20 Aug. 2008
Japan Welding Society, Japanese
CiNii Articles ID：110007059682, CiNii Books ID：AN10273925
【スイッチバック溶接のバッキングレスV開先溶接に関する一連の研究】 : 「スイッチバック溶接のバッキングレスV開先円周溶接への適用」「V開先片面裏あてなしスイッチバック溶接におけるトーチ揺動方法および裏ビードのフィードフォワード制御」
山根 敏; 山本 光; 金子 裕良; 大嶋 健司
Volume：77, Number：5, First page：385, Last page：386, 05 Jul. 2008
Japanese
ISSN：0021-4787, CiNii Articles ID：10021827568, CiNii Books ID：AN00246019
116 High quality welding using cooperative control system
YOSHIDA Tetsuo; YAMANE Satoshi; YAMAMOTO Hikaru; NAKASHIMA Toru; KANEKO Yasuyoshi; OSHIMA Kenji
Pre-Prints of the National Meeting of JWS, Number：82, First page：34, Last page：35, 17 Mar. 2008
Japan Welding Society, Japanese
CiNii Articles ID：110006806036, CiNii Books ID：AN10273925
115 Adaptation of the Neural Network to Robotic Welding
KOIZUMI Manabu; YAMANE Satoshi; KANEKO Yasuyoshi; OSHIMA Kenji
Pre-Prints of the National Meeting of JWS, Number：82, First page：32, Last page：33, 17 Mar. 2008
Japan Welding Society, Japanese
CiNii Articles ID：110006806035, CiNii Books ID：AN10273925
114 Numerical Simulation of Weld Pool in High Efficient Robotic Weiding
Yoshiyama Kensuke; Yamane Satoshi; Kaneko Yasuyoshi; Ohshima Kenzi; HOSOYA Kazumichi; NAKAJIMA Toru; YAMAMOTO Hikaru
Pre-Prints of the National Meeting of JWS, Number：82, First page：30, Last page：31, 17 Mar. 2008
Japan Welding Society, Japanese
CiNii Articles ID：110006806034, CiNii Books ID：AN10273925
V開先溶接裏当てなしスイッチバック溶接におけるトーチ揺動方法および裏ビードのフィードフォワード制御
中嶋徹; 山本光; 山根敏; 大嶋健司
First page：II 293-297, 2008
バッキングV開先溶接におけるギャップセンシングと溶融池の制御
中嶋徹; 山本光; 山根敏; 大嶋健司
First page：II 288-292, 2008
協調溶接システムを用いた溶融池制御
山根敏; 吉田哲夫; 山本光; 中嶋徹; 大嶋健司
2008
ニューラルネットワークによるパルスMIG 溶接における突出し長さの推定
山根敏; 吉田哲夫; 金子裕良; 山本光; 大嶋健司
First page：II 263-267, 2008
高能率溶接における溶融池の数値シミュレーション
山根敏; 吉山健介; 高橋祐介; 大嶋健司
First page：II 258-262, 2008
スイッチバック溶接における溶接溶融池の数値シミュレーション
山根敏; 田中彬人; 金子裕良; 山本光; 大嶋健司
First page：II 268-272, 2008
２電極溶接方法における溶融池の数値シミュレーション
山根敏; 田中彩人; 中嶋徹; 山本光; 金子裕良; 大嶋健司
2008
ロボットおよび溶接電源の協調制御
山根敏; 石川智也; 中嶋徹; 山本光; 金子裕良; 大嶋健司
2008
電気溶接作業環境における低周波磁界の測定と解析
山根敏; 山本恭子; 安川卓也; 神戸勇貴; 大嶋健司
2008
アーク溶接作業環境における電磁界（ELF）の測定および解析
山根敏; 山本恭子; 安川卓也; 神戸勇貴
2008
電気溶接作業環境における電磁界（ELF）の測定および解析
山根敏; 山本恭子; 安川卓也; 神戸勇貴
2008
Estimation of wire extension length using neural network in MIG welding Satoshi Yamane; Tetsuo Yoshida; Yasuyoshi Kaneko; Hikaru Yamamoto; Kenji Oshima
Yosetsu Gakkai Ronbunshu/Quarterly Journal of the Japan Welding Society,
Volume：26,
Number：1,
First page：31,
Last page：36, 2008
Measuring of arc length is important to obtain good welding quality in spite of variation of torch height. Therefore, it is necessary to detect arc behavior in the transient state in addition to the steady state. For this purpose, this paper proposes neural network models which output the present wire extension from the data relating to wire melting, such as welding current, current pickup voltage and wire feed rate in every sampling period. Since performance of the neural network model depends on threshold functions, authors investigate the performance of the neural network models based on both sigmoid function and radial base function. To confirm the validity of these systems, fundamental experiments were carried out. The arc was directly observed and recorded as image data using a high speed camera. The output data from the neural network were compared with the measured data which were obtained from every captured image. It was found that the neural network model based on the radial base function is useful than the sigmoid function to estimate the wire extension length in MIG welding because of better responses in the transient state and smaller steady state error.
Japanese
DOI：https://doi.org/10.2207/qjjws.26.31DOI ID：10.2207/qjjws.26.31,
ISSN：0288-4771,
CiNii Articles ID：80017947351,
SCOPUS ID：70449396799 ビジュアル情報を利用したアーク溶接プロセスの自動化システム
山根敏
First page：I 88-90, 2008
ニューラルネットワークによるアーク溶接プロセスの最適化 山根敏
Volume：77,
Number：1,
First page：34,
Last page：39, 2008
DOI：https://doi.org/10.2207/jjws.77.34DOI ID：10.2207/jjws.77.34,
ISSN：0021-4787,
CiNii Articles ID：110006572103 V開先溶接裏当てなしスイッチバック溶接におけるトーチ揺動方法および裏ビードのフィードフォワード制御
中嶋徹; 山本光; 山根敏; 大嶋健司
溶接法ガイドブック6 溶接学会,溶接法研究委員会編, First page：II 293-297, 2008
バッキングV開先溶接におけるギャップセンシングと溶融池の制御
中嶋徹; 山本光; 山根敏; 大嶋健司
溶接法ガイドブック6 溶接学会,溶接法研究委員会編, First page：II 288-292, 2008
協調溶接システムを用いた溶融池制御
山根敏; 吉田哲夫; 山本光; 中嶋徹; 大嶋健司
溶接学会溶接法研究委員会資料, 2008
ニューラルネットワークによるパルスMIG 溶接における突出し長さの推定
山根敏; 吉田哲夫; 金子裕良; 山本光; 大嶋健司
溶接法ガイドブック6 溶接学会,溶接法研究委員会編, First page：II 263-267, 2008
高能率溶接における溶融池の数値シミュレーション
山根敏; 吉山健介; 高橋祐介; 大嶋健司
溶接法ガイドブック6 溶接学会,溶接法研究委員会編, First page：II 258-262, 2008
スイッチバック溶接における溶接溶融池の数値シミュレーション
山根敏; 田中彬人; 金子裕良; 山本光; 大嶋健司
溶接法ガイドブック6 溶接学会,溶接法研究委員会編, First page：II 268-272, 2008
２電極溶接方法における溶融池の数値シミュレーション
山根敏; 田中彩人; 中嶋徹; 山本光; 金子裕良; 大嶋健司
日本溶接協会ロボット溶接研究委員会資料, 2008
ロボットおよび溶接電源の協調制御
山根敏; 石川智也; 中嶋徹; 山本光; 金子裕良; 大嶋健司
日本溶接協会ロボット溶接研究委員会資料, 2008
電気溶接作業環境における低周波磁界の測定と解析
山根敏; 山本恭子; 安川卓也; 神戸勇貴; 大嶋健司
日本溶接協会ロボット溶接研究委員会資料, 2008
アーク溶接作業環境における電磁界（ELF）の測定および解析
山根敏; 山本恭子; 安川卓也; 神戸勇貴
溶接学会溶接法研究委員会資料, 2008
電気溶接作業環境における電磁界（ELF）の測定および解析
山根敏; 山本恭子; 安川卓也; 神戸勇貴
日本溶接協会安全衛生・環境委員会資料, 2008
Estimation of wire extension length using neural network in MIG welding Satoshi Yamane; Tetsuo Yoshida; Yasuyoshi Kaneko; Hikaru Yamamoto; Kenji Oshima
Yosetsu Gakkai Ronbunshu/Quarterly Journal of the Japan Welding Society,
Volume：26,
Number：1,
First page：31,
Last page：36, 2008
Measuring of arc length is important to obtain good welding quality in spite of variation of torch height. Therefore, it is necessary to detect arc behavior in the transient state in addition to the steady state. For this purpose, this paper proposes neural network models which output the present wire extension from the data relating to wire melting, such as welding current, current pickup voltage and wire feed rate in every sampling period. Since performance of the neural network model depends on threshold functions, authors investigate the performance of the neural network models based on both sigmoid function and radial base function. To confirm the validity of these systems, fundamental experiments were carried out. The arc was directly observed and recorded as image data using a high speed camera. The output data from the neural network were compared with the measured data which were obtained from every captured image. It was found that the neural network model based on the radial base function is useful than the sigmoid function to estimate the wire extension length in MIG welding because of better responses in the transient state and smaller steady state error.
Japanese
DOI：https://doi.org/10.2207/qjjws.26.31DOI ID：10.2207/qjjws.26.31,
ISSN：0288-4771,
CiNii Articles ID：80017947351,
SCOPUS ID：70449396799 ビジュアル情報を利用したアーク溶接プロセスの自動化システム
山根敏
溶接法ガイドブック6 溶接学会,溶接法研究委員会編, First page：I 88-90, 2008
ニューラルネットワークによるアーク溶接プロセスの最適化
山根敏
溶接学会誌, Volume：77, Number：1, First page：34, Last page：39, 2008
Japan Welding Society, Japanese
DOI ID：10.2207/jjws.77.34, ISSN：0021-4787, CiNii Articles ID：110006572103, CiNii Books ID：AN00246019
Cooperative control of robotic welding system in one side backingless V groove welding
Satoshi Yamane; Toru Nakajima; Hikaru Yamamoto; Yasuyoshi Kaneko; Kenji Oshima
ADVANCED WELDING AND MICRO JOINING / PACKAGING FOR THE 21ST CENTURY, Volume：580-582, First page：339, Last page：+, 2008
The formation of stable back beads in the first layer weld during one side multilayer welding is important to achieve high quality welded metal joints. The authors thus employed the switch back welding method for the welding of V groove joints Without backing plates. In this method, the personal computers control a welding robot, a digital welding power source and a wire feeder, simultaneously. Each unit is connected together with Ethernet and UDP (User Datagram Protocol). The personal computer for controlling the welding robot is synchronized with other Computers. The suitability of the welding conditions for each loot gap was verified by observation of the are, molten pool and external appearance of back beads.
TRANS TECH PUBLICATIONS LTD, English
ISSN：0255-5476, Web of Science ID：WOS:000258372000080
112 Numerical Simulation of Weld Pool on Double-electrode Welding Process
TANAKA Akito; YAMANE Satoshi; YAMAMOTO Hikaru; NAKAJIMA Toru; KANEKO Yasuyoshi; OSHIMA Kenji
Pre-Prints of the National Meeting of JWS, Number：81, First page：26, Last page：27, 01 Sep. 2007
Japan Welding Society, Japanese
CiNii Articles ID：110006427436, CiNii Books ID：AN10273925
110 Torch Weaving and Feed-forward Control of Back Bead in One Side Backing less V Groove Welding by using Switch Back Welding
ISHIKAWA Tomoya; YAMANE Satoshi; YAMAMOTO Hikaru; NAKASHIMA Toru; KANEKO Yasuyoshi; OSHIMA Kenji
Pre-Prints of the National Meeting of JWS, Number：80, First page：22, Last page：23, 19 Mar. 2007
Japan Welding Society, Japanese
CiNii Articles ID：110006295606, CiNii Books ID：AN10273925
101 Numerical Simulation of Weld Pool on Double-electrode Welding Process
TANAKA Akito; YAMANE Satoshi; YAMAMOTO Hikaru; NAKAJIMA Toru; KANEKO Yasuyoshi; OSHIMA Kenji
Pre-Prints of the National Meeting of JWS, Number：80, First page：4, Last page：5, 19 Mar. 2007
Japan Welding Society, Japanese
CiNii Articles ID：110006295597, CiNii Books ID：AN10273925
102 Control of Weld Pool by using Switch Back Welding
Maekawa Y.; Oshima K.; Yamane S.; Kaneko Y.
Pre-Prints of the National Meeting of JWS, Number：80, First page：6, Last page：7, 19 Mar. 2007
Japan Welding Society, Japanese
CiNii Articles ID：110006295598, CiNii Books ID：AN10273925
高効率溶接方法における溶融池の数値シミュレーション
山根敏; 田中彩人; 山本光; 中嶋徹; 大嶋健司
2007
開先片面裏当てなしスイッチバック溶接のバッキングレスV開先円周溶接への適用
山根敏; 田中彬人; 山本光; 金子裕良; 大嶋健司
Volume：25, Number：1, First page：86, Last page：94, 2007
Torch Weaving and Feed-forward Control of Back Bead in One Side Backing less V Groove Welding by using Switch Back Welding
YAMANE Satoshi; ISHIKAWA Tomoya; NAKAJIMA Toru; YAMAMOTO Hikaru; KANEKO Yasuyoshi; OSHIMA Kenji
Volume：25, Number：1, First page：159, Last page：164, 2007
Japanese
ISSN：0288-4771, CiNii Articles ID：10030884371, CiNii Books ID：AN1005067X
アーク溶接プロセスの自動化システムの展開
山根敏
2007
Analysis and development in advanced welding technologies
山根敏; 中嶋徹; 山本光
Volume：8, Number：8, First page：83, Last page：86, 2007
The formation of stable back beads in the first layer weld during one side multilayer welding is important to achieve high quality welded metal joints. The authors thus employed the switch back welding method for welding V groove joints, with 4mm root gap, without using backing plates. In this method, the power source, wire feed motor, and robot manipulators are the computer based cooperative control. In this robotic welding system, there are 4 personal computers. In order to achieve the good quality of the welding, it is important to trace the welding line. The personal computer for controlling of the robot is synchronized with other computers, i.e., the computer controls other units. The suitability of the welding conditions for each root gap was verified by observation of the arc, molten pool and external appearance of back beads.
Japanese
ISSN：1347-4758, CiNii Articles ID：120001371283, CiNii Books ID：AA11808968
高品質・高効率ロボット溶接システムの開発に関する研究
山根敏
Volume：5 (18年度), First page：177, Last page：178, 2007
Numerical simulation of MIG weld pool in switch back welding Kaneko Yasuyoshi; Maekawa Yasuyuki; Yamane Satoshi; Oshima Kenji
Yosetsu Gakkai Ronbunshu/Quarterly Journal of the Japan Welding Society,
Volume：25,
Number：2,
First page：372,
Last page：380, 2007
The authors proposed the switch back welding method to make the stable back beads in the first layer weld during one side multilayer welding. In the proposed welding method, the torch motion is important to control the weld pool, i.e., the welding torch is moved backward and forward like switch back. It is important to investigate the behavior of the weld pool to get the optimum welding parameters such as the traveling speed, the forward distance, the backward distance, the welding current and so on. There are many welding parameters. In order to find the optimum, welding parameters, the numerical simulations are useful, method instead of the welding experiments. Since the deposited metal is considered in the numerical models of the welding in the thick plates, the numerical analysis becomes complicated. In order to simplify the analysis, the authors discussed the numerical simulations of the welding in the thin metal plates because the effect of the deposited metal can be minimized. First, the fundamental welding experiments were carried out in MIG welding. By using the experimental results, the numerical models in the switch back welding are determined. Next, the behaviors of the temperature are investigated under the change of the traveling speed and the backward distance. If the traveling speed is constant in the switch back welding, the weld, pool size may sometimes become big. In this case, the burn trough may take place due to the flow in the weld pool. When the traveling speed, of the forward movement is faster than backward movement, the weld pool, length becomes shorter than the case of the constant traveling speed. Moreover, if the backward distance is longer than, half of the forward distance of the switch back welding, the authors can obtain continuous back bead regardless of the disturbance such as the variation of the arc length, i.e., the stability of the weld pool is increased. The switch back welding method is useful to make the stable back bead in the MIG welding.
Japanese
DOI：https://doi.org/10.2207/qjjws.25.372DOI ID：10.2207/qjjws.25.372,
ISSN：0288-4771,
CiNii Articles ID：80020745129,
SCOPUS ID：70449624187 高効率溶接方法における溶融池の数値シミュレーション
山根敏; 田中彩人; 山本光; 中嶋徹; 大嶋健司
溶接学会溶接法研究委員会資料, 2007
開先片面裏当てなしスイッチバック溶接のバッキングレスV開先円周溶接への適用
山根敏; 田中彬人; 山本光; 金子裕良; 大嶋健司
溶接学会論文集, Volume：25, Number：1, First page：86, Last page：94, 2007
開先片面裏当てなしスイッチバック溶接におけるトーチ揺動方法および裏ビードのフィードフォワード制御
山根敏; 石川智也; 中嶋徹; 山本光; 金子裕良; 大嶋健司
溶接学会論文集, Volume：25, Number：1, First page：159, Last page：164, 2007
Japanese
ISSN：0288-4771, CiNii Articles ID：10030884371, CiNii Books ID：AN1005067X
アーク溶接プロセスの自動化システムの展開
山根敏
溶接学会溶接法研究委員会資料, 2007
次世代溶接技術の現象解明及び適用検討に関する研究
山根敏; 中嶋徹; 山本光
埼玉大学地域共同研究センター紀要, Volume：8, Number：8, First page：83, Last page：86, 2007
The formation of stable back beads in the first layer weld during one side multilayer welding is important to achieve high quality welded metal joints. The authors thus employed the switch back welding method for welding V groove joints, with 4mm root gap, without using backing plates. In this method, the power source, wire feed motor, and robot manipulators are the computer based cooperative control. In this robotic welding system, there are 4 personal computers. In order to achieve the good quality of the welding, it is important to trace the welding line. The personal computer for controlling of the robot is synchronized with other computers, i.e., the computer controls other units. The suitability of the welding conditions for each root gap was verified by observation of the arc, molten pool and external appearance of back beads.
Japanese
ISSN：1347-4758, CiNii Articles ID：120001371283, CiNii Books ID：AA11808968
高品質・高効率ロボット溶接システムの開発に関する研究
山根敏
総合研究機構研究プロジェクト研究成果報告書, Volume：5 (18年度), First page：177, Last page：178, 2007
Numerical simulation of MIG weld pool in switch back welding Kaneko Yasuyoshi; Maekawa Yasuyuki; Yamane Satoshi; Oshima Kenji
Yosetsu Gakkai Ronbunshu/Quarterly Journal of the Japan Welding Society,
Volume：25,
Number：2,
First page：372,
Last page：380, 2007
The authors proposed the switch back welding method to make the stable back beads in the first layer weld during one side multilayer welding. In the proposed welding method, the torch motion is important to control the weld pool, i.e., the welding torch is moved backward and forward like switch back. It is important to investigate the behavior of the weld pool to get the optimum welding parameters such as the traveling speed, the forward distance, the backward distance, the welding current and so on. There are many welding parameters. In order to find the optimum, welding parameters, the numerical simulations are useful, method instead of the welding experiments. Since the deposited metal is considered in the numerical models of the welding in the thick plates, the numerical analysis becomes complicated. In order to simplify the analysis, the authors discussed the numerical simulations of the welding in the thin metal plates because the effect of the deposited metal can be minimized. First, the fundamental welding experiments were carried out in MIG welding. By using the experimental results, the numerical models in the switch back welding are determined. Next, the behaviors of the temperature are investigated under the change of the traveling speed and the backward distance. If the traveling speed is constant in the switch back welding, the weld, pool size may sometimes become big. In this case, the burn trough may take place due to the flow in the weld pool. When the traveling speed, of the forward movement is faster than backward movement, the weld pool, length becomes shorter than the case of the constant traveling speed. Moreover, if the backward distance is longer than, half of the forward distance of the switch back welding, the authors can obtain continuous back bead regardless of the disturbance such as the variation of the arc length, i.e., the stability of the weld pool is increased. The switch back welding method is useful to make the stable back bead in the MIG welding.
Japanese
DOI：https://doi.org/10.2207/qjjws.25.372DOI ID：10.2207/qjjws.25.372,
ISSN：0288-4771,
CiNii Articles ID：80020745129,
SCOPUS ID：70449624187 Sensing and seam tracking of welding line in backingless V groove welding S. Yamane; H. Yamamoto; Y. Kaneko; K. Oshima
SCIENCE AND TECHNOLOGY OF WELDING AND JOINING,
Volume：11,
Number：5,
First page：586,
Last page：592, Sep. 2006
The formation of stable back beads in the first layer weld during one side multilayer welding is important to achieve high quality welded metal joints. The authors tried to apply the switch back welding method to butt welding to join discs with flat metal plates without backing plates. During the welding, the gap was detected by processing the weld pool image taken with a CCD camera. Moreover, the tip of the electrode wire is changing owing to a curve of its wire extension in accordance with a rotation of the torch axis. Even though teaching is achieved before the welding, the weaving centre is shifted from the gap centre. The controller of the seam tracking was designed to prevent any steady state error.
MANEY PUBLISHING, English
DOI：https://doi.org/10.1179/174329306X150153DOI ID：10.1179/174329306X150153,
ISSN：1362-1718,
Web of Science ID：WOS:000243639700016 309 Numerical Simulation of Weld Pool in Switch Back Welding TAKAHASHI Yusuke; YAMANE Satoshi; YAMAMOTO Hikaru; KANEKO Yasuyoshi; OSHIMA Kenji
Pre-Prints of the National Meeting of JWS,
Number：78,
First page：138,
Last page：139, 2006
片面多層盛溶接におけるスイッチバック溶接法の実用化に対する問題点として、直線だけでなく円周部分の裏当て材無しでの裏ビードを形成すること等が挙げられる。そこで良好な溶接結果を得るために、数値シミュレーションを行い最適な溶接条件を求めることを目的としている。
Japan Welding Society, Japanese
DOI：https://doi.org/10.14920/jwstaikai.2006s.0.64.0DOI ID：10.14920/jwstaikai.2006s.0.64.0,
CiNii Articles ID：110005857315,
CiNii Books ID：AN10273925 溶接作業環境における電磁界（EMF）について
山根敏; 内田潤; 山本泰子; 大嶋健司
2006
スイッチバック溶接における数値シミュレーション 山根敏; 田中彩人; 高橋祐介; 金子裕良; 山本光; 大嶋健司
溶接学会溶接アーク物理研究委員会資料,
Number：78,
First page：138,
Last page：139, 2006
片面多層盛溶接におけるスイッチバック溶接法の実用化に対する問題点として、直線だけでなく円周部分の裏当て材無しでの裏ビードを形成すること等が挙げられる。そこで良好な溶接結果を得るために、数値シミュレーションを行い最適な溶接条件を求めることを目的としている。
Japan Welding Society, Japanese
DOI：https://doi.org/10.14920/jwstaikai.2006s.0.64.0DOI ID：10.14920/jwstaikai.2006s.0.64.0,
CiNii Articles ID：110005857315,
CiNii Books ID：AN10273925 溶接作業環境における電磁界（EMF）について
山根敏; 内田潤; 山本泰子; 大嶋健司
溶接学会溶接アーク物理研究委員会資料, 2006
238 Sensing and Seam Tracking of Welding Line in Robot Welding
YUZAWA Hiroki; YAMANE Satoshi; YAMAMOTO Hikaru; HIRAKAWA Manabu; OSHIMA Kenji; KANEKO Yasuyoshi
Pre-Prints of the National Meeting of JWS, Number：77, First page：148, Last page：149, 20 Aug. 2005
Japan Welding Society, Japanese
CiNii Articles ID：110004557159, CiNii Books ID：AN10273925
240 Control of Weld Pool in Thin Plate Welding by using Switch Back Welding.
Nakashima Y.; Kaneko Y.; Yamane S.; Oshima K.
Pre-Prints of the National Meeting of JWS, Number：77, First page：152, Last page：153, 20 Aug. 2005
Japan Welding Society, Japanese
CiNii Articles ID：110004557161, CiNii Books ID：AN10273925
Effect of power source characteristic on CO2 short circuiting arc welding S Yamane; S Xiang; Y Kaneko; K Oshima
SCIENCE AND TECHNOLOGY OF WELDING AND JOINING,
Volume：10,
Number：3,
First page：281,
Last page：286, Jun. 2005
Some problems are reported concerning the observation of the weld pool and effects of the power source characteristic on arc stability in CO2 short circuiting arc welding. First, the effect of a power source with a constant voltage characteristic on CO2 short circuiting arc welding is investigated by analysing the behaviour of the voltage and the current. From the results of this analysis, the cause of spatter generation is identified. A new power source characteristic is then proposed to improve the stability and the self-regulation of the arc. By adjusting the power source characteristic, the metal transfer can be stabilised in the CO2 short circuiting arc welding process, i.e. the present authors have developed a power source having a non-linear characteristic. Its performance is verified by carrying out experiments.
MANEY PUBLISHING, English
DOI：https://doi.org/10.1179/174329305X39310DOI ID：10.1179/174329305X39310,
ISSN：1362-1718,
Web of Science ID：WOS:000234387500003 Image processing and control of weld pool in switch back welding without backing plate Satoshi Yamane; Hiroki Yuzawa; Yasuyoshi Kaneko; Hikaru Yamamoto; Manabu Hirakawa; Kenji Oshima
Yosetsu Gakkai Ronbunshu/Quarterly Journal of the Japan Welding Society,
Volume：23,
Number：1,
First page：65,
Last page：70, Feb. 2005
The formation of stable back beads in the first layer weld during one side multilayer welding is important to achieve high quality welded metal joints. The authors thus employed the switch back welding method for V groove joints without backing plates. In this method, the power source, wire feed motor, and robot manipulators were controlled by the computer based cooperative control. The torch is moved backward and forward like switch back. First, the torch is moved forward with high speed. The arc is discharged to the each root edge of the groove. The droplet is deposited to each root edge, too. After that, the torch is moved backward with the same high speed. During the backward motion, the deposited metal makes the bridge between the both edges due to the surface tension. Next, the torch is moved forward with slow speed to form the bead. The mentioned torch motion is repeated. When constant welding conditions are used, the back bead becomes unstable by affection of the disturbances such as gap variations due to the welding distortion. In this method, it is important to measure the gap. The authors discuss a method to detect the gap and to get the stable back bead by using a visual sensor, the CCD camera. During the slow forward torch motion, the weld pool can be observed. The shape in the front part of the weld pool depends on the gap. It can be detected by processing the weld pool images. The authors investigate the method to take the gap from the weld pool image. The use of feed-forward control of back beads to compensate for variations of root gaps was also tested. In order to verify the performance of the feed forward controller, the gap is changing from 4.6 mm to 2.5 mm without the tack welding.
Japanese
DOI：https://doi.org/10.2207/qjjws.23.65DOI ID：10.2207/qjjws.23.65,
ISSN：0288-4771,
CiNii Articles ID：110003423069,
SCOPUS ID：18344396060 Image processing and control of weld pool in switch back welding without backing plate Satoshi Yamane; Hiroki Yuzawa; Yasuyoshi Kaneko; Hikaru Yamamoto; Manabu Hirakawa; Kenji Oshima
Yosetsu Gakkai Ronbunshu/Quarterly Journal of the Japan Welding Society,
Volume：23,
Number：1,
First page：65,
Last page：70, Feb. 2005
The formation of stable back beads in the first layer weld during one side multilayer welding is important to achieve high quality welded metal joints. The authors thus employed the switch back welding method for V groove joints without backing plates. In this method, the power source, wire feed motor, and robot manipulators were controlled by the computer based cooperative control. The torch is moved backward and forward like switch back. First, the torch is moved forward with high speed. The arc is discharged to the each root edge of the groove. The droplet is deposited to each root edge, too. After that, the torch is moved backward with the same high speed. During the backward motion, the deposited metal makes the bridge between the both edges due to the surface tension. Next, the torch is moved forward with slow speed to form the bead. The mentioned torch motion is repeated. When constant welding conditions are used, the back bead becomes unstable by affection of the disturbances such as gap variations due to the welding distortion. In this method, it is important to measure the gap. The authors discuss a method to detect the gap and to get the stable back bead by using a visual sensor, the CCD camera. During the slow forward torch motion, the weld pool can be observed. The shape in the front part of the weld pool depends on the gap. It can be detected by processing the weld pool images. The authors investigate the method to take the gap from the weld pool image. The use of feed-forward control of back beads to compensate for variations of root gaps was also tested. In order to verify the performance of the feed forward controller, the gap is changing from 4.6 mm to 2.5 mm without the tack welding.
Japanese
DOI：https://doi.org/10.2207/qjjws.23.65DOI ID：10.2207/qjjws.23.65,
ISSN：0288-4771,
CiNii Articles ID：110003423069,
SCOPUS ID：18344396060 スイッチバック溶接における溶接線検出・追跡制御
山根敏
2005
スイッチバック溶接における溶接線検出・追跡制御
山根敏
溶接学会溶接アーク物理研究委員会資料, 2005
Feed forward control of back bead and bead height in narrow gap robotic welding S Yamane; LH Sharif; S Zeniya; K Oshima
SCIENCE AND TECHNOLOGY OF WELDING AND JOINING,
Volume：10,
Number：1,
First page：23,
Last page：26, 2005
For high quality welding, it is necessary to form a stable back bead and to melt metal plates. In narrow gap welding, it is difficult to control the bead height and the back bead simultaneously using conventional welding. In order to solve this problem, a switch back welding method is proposed in which the welding torch is moved back and forth along the welding line. In the forward movement of the torch, the arc heat is given to the root edges to obtain a wide back bead. In the backward movement, suitable bead height is formed. From the fundamental experimental results, a numerical model was prepared for this type of welding. Using this model, the optimum stroke length was found. Its validity was verified by carrying out welding experiments.
MANEY PUBLISHING, English
DOI：https://doi.org/10.1179/174329305X19367DOI ID：10.1179/174329305X19367,
ISSN：1362-1718,
Web of Science ID：WOS:000228445100004 226 Sensing and Control of Weld Pool in Backingless V Groove Welding
TSUKIGAWA Makoto; KANEKO Yasuyoshi; YAMANE Satoshi; YAMAMOTO Hikaru; HIRAKAWA Manabu; OSHIMA Kenji
Pre-Prints of the National Meeting of JWS, Number：75, First page：116, Last page：117, 20 Aug. 2004
Japan Welding Society, Japanese
CiNii Articles ID：110003432089, CiNii Books ID：AN10273925
Adaptive control of back bead in V groove welding without backing plate S Yamane; H Yamamoto; T Ishihara; T Kubota; K Eguchi; K Oshima
SCIENCE AND TECHNOLOGY OF WELDING AND JOINING,
Volume：9,
Number：2,
First page：138,
Last page：148, Apr. 2004
The formation of stable back beads in the first layer weld during one side multilayer welding is important to achieve high quality welded metal joints. The authors thus employed the switch back welding method for welding V groove joints without using backing plates. Moreorer, in the field work, there is misalignment of both metal plates during set-up. The suitability of the welding conditions for each root gap and the misalignment were verified by observation of the arc, molten pool and external appearance of back beads. Welding conditions, namely, welding current, wire feedrate, weaving width forward/backward stroke of switch back motion and welding speed, were controlled continuously according to root gap variations. Stable back beady were obtained for root gaps between 4.9 and 2.3 mm and and misalignments between 0.1 and 2.8 mm.
MANEY PUBLISHING, English
DOI：https://doi.org/10.1179/136217104225017044DOI ID：10.1179/136217104225017044,
ISSN：1362-1718,
CiNii Articles ID：30002225316,
Web of Science ID：WOS:000222194800006 溶接溶融池のニューラルネットワークモデル
金子 裕良; 長澤 和哉; 山根 敏
Number：37, First page：9, Last page：14, Mar. 2004
Japanese
ISSN：0916-6394, CiNii Articles ID：40006332165, CiNii Books ID：AN00095740
ロボット溶接における知的情報処理・制御
山根敏; 大嶋健司
2004
ロボット溶接における知的情報処理・制御
山根敏; 大嶋健司
日本溶接協会ロボット溶接研究委員会資料, 2004
Feed-Forward Control of Back Bead for Root Gap Variation in V Groove Welding without Backing Plate
YAMAMOTO Hikaru; ISHIHARA Toshihiko; TAKANO Yutaka; EGUCHI Kazuhiko; YAMANE Satoshi; OSHIMA Kenji
quarterly journal of the Japan Welding Society, Volume：20, Number：4, First page：499, Last page：505, 05 Nov. 2002
The stable back bead in a first layer of the one-side multilayer welding is important to obtain a good quality of welding. For this purpose, the switch back welding method was applied for the root gap from 1 mm to 5 mm in V groove welding without the backing plate. This method requires the cooperative control of power source, wire feed motor and robot manipulator by the personal computers. The validity of welding conditions for each root gap were confirmed by observing the arc and the weld pool, and the back bead appearance. Next, the feed-forward control of the back bead for the root gap variation was discussed. The root gap on start and end points of welding were detected by using the spot laser sensor. The welding conditions, welding current, wire feed rate, weaving width, forward/backward stroke of the switch back motion and stroke speed, were continuously controlled corresponding to the root gap variation, and the stable back bead was obtained by the fundamental experiment regardless of changing the root gap from 4.4 mm to 1.9 mm.
Japan Welding Society, Japanese
ISSN：0288-4771, CiNii Articles ID：110003422306, CiNii Books ID：AN1005067X
Adaptive Control for Gap Variation in Narrow Robotic Welding
SHARIF Leila H.; YAMANE Satoshi; SUGIMOTO Tomotaka; OSHIMA Kenji
quarterly journal of the Japan Welding Society, Volume：20, Number：4, First page：506, Last page：516, 05 Nov. 2002
Quality of a multi-layer welding depends on a welding in first layer. In order to get a high quality of the welding, it is necessary to make a stable back bead and to melt the base metals. In narrow gap welding, it is difficult to control the bead height (deposited metal) and the back bead (the melted area of the backside) simultaneously by using conventional welding. To improve this problem, authors propose a cooperative control of the welding equipments including the welding power source, the electrode wire feeder and the welding robot, i.e., the welding torch is not only oscillating on the groove, but also moving back and forth. To control the heat input, the power source is controlled according to the torch motion (robot motion), too. In the forward process, the arc (the heat) is given to the root edges to get a wide back bead. In the backward process, the suitable bead height is obtained. The idea of its robot motion comes from the knowledge of the skilled welding workers. Since the arc length must be kept short during the welding, the power source with a nonlinear power source characteristic is used. Welding conditions are investigated for 4 mm root gap, 5 mm root gap and 6 mm root gap by observing arc position with a high speed motion video camera, and observing the weld pool with a CCD camera. The welding conditions are stored in a database. Before the welding, the root gap at the beginning and at the end on the base metal is detected by a slit laser light and the CCD camera, and is stored into a memory in the personal computer. During the welding, the personal computer detects the torch position from the encoder pulses of the welding robot, finds the root gap at the torch position and calculates the welding conditions by using the data base, i.e., the adaptive control for the gap variation is applied. The welding experiment under the root gap variation from 6 mm to 4 mm is carried out to verify the validity of the cooperative control method.
Japan Welding Society, Japanese
ISSN：0288-4771, CiNii Articles ID：110003422307, CiNii Books ID：AN1005067X
Neural Network Model and Fuzzy Control of Weld Pool in Pulsed MIG Welding
Hirai A.; Hosoda T.; Nagasawa K.; Kaneko Y.; Yamane S.; Oshima K.
Pre-Prints of the National Meeting of JWS, Number：70, First page：82, Last page：83, 24 Mar. 2002
Japan Welding Society, Japanese
CiNii Articles ID：110003430375, CiNii Books ID：AN10273925
Neural Network Model and Control of Weld Pool in Pulsed MIG Welding
Hirai A.; Yamane S.; Hosoda T.; Kaneko Y.; Oshima K.
Pre-Prints of the National Meeting of JWS, Number：69, First page：342, Last page：343, 10 Sep. 2001
Japan Welding Society, Japanese
CiNii Articles ID：110003430230, CiNii Books ID：AN10273925
Sensing and control of weld pool by fuzzy-neural network in robotic welding system
A Hirai; Y Kaneko; T Hosoda; S Yamane; K Oshima
IECON'01: 27TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOLS 1-3, First page：238, Last page：242, 2001
It is important to control penetration depth of weld pool during the welding, so as to get a good quality of the welding. But, it may be difficult to directly detect the penetration depth by using a visual sensor. In order to detect the penetration depth, authors propose a penetration depth model based on neural network. During the welding, a fuzzy controller adjusts the welding current so as to get the desired penetration depth. Since performances of the fuzzy controller depend on the fuzzy variables, its tuning can be performed by using the neural network model. The validity of fuzzy - neural network is verified by the welding experiments.
IEEE, English
ISSN：1553-572X, Web of Science ID：WOS:000178186000043
Application of Modern Control Technology to Welding System
OSHIMA Kenji; YAMANE Satoshi
Journal of the Japan Welding Society, Volume：69, Number：4, First page：324, Last page：330, 05 Jun. 2000
Japan Welding Society, Japanese
ISSN：0021-4787, CiNii Articles ID：110003397579, CiNii Books ID：AN00246019
Sensing and digital control of weld pool with visual welding robot LH Sharif; S Yamane; K Eguchi; Y Hino; T Kubota; K Oshima
IECON 2000: 26TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOLS 1-4,
First page：1521,
Last page：1526, 2000
Quality of a multi-layer welding depends on a welding in first layer. In order to get a high quality of the welding, it is necessary to make a stable back bead and to melt the base metals. In narrow gap of which groove angle is over 16, arc discharge from top of an extension wire to surface of the groove and cannot creep up the electrode wire. If the arc length becomes long, heat is given to upper side of the base metal. It is difficult to get the wide back bead. Weaving width is shorter than gap to avoid the creeping of the arc. In order to get a good back bead and suitable bead height, the authors try to carry out cooperative control of the welding power source, a wire feeder unit and a robot manipulator. Weld pool is observed by using a CCD camera. A personal computer processes image of the weld pool. By using the result of the image processing, a simulation model of the welding system is prepared to make a digital controller. Welding speed and wire feed rate are controlled to get the desired bead height and arc position.
IEEE, English
DOI：https://doi.org/10.1109/IECON.2000.972500DOI ID：10.1109/IECON.2000.972500,
ISSN：1553-572X,
Web of Science ID：WOS:000176916400257 Application of neural network to arc sensor
K Eguchi; S Yamane; H Sugi; T Kubota; K Oshima
SCIENCE AND TECHNOLOGY OF WELDING AND JOINING, Volume：4, Number：6, First page：327, Last page：334, 1999
Full penetration control of the weld pool in the first layer of a single side multilayer weldment is important to obtain a good quality weld. For this purpose, a new method, the switchback welding method, is proposed to achieve a stable back bead. A welding torch not only weaves along the groove, but also moves back and forth. Also, a neural network (NN) arc sensor is proposed that estimates the wire extension and the arc length by using measurements of both voltage and current. Moreover; from the output of the NN, the gap and the error (deviation) of the oscillation centre of the torch from the groove centre are estimated. Training data are constructed from experimental results, and performance of the NN arc sensor is examined using test data. Seam tracking is carried out via the output of the NN arc sensors: a good tracking result is obtained.
I O M COMMUNICATIONS LTD INST MATERIALS, English
ISSN：1362-1718, Web of Science ID：WOS:000171720800002
Back Bead Control of the One-side Robotic Welding with Visual Sensor
K.Eguchi; H.Sugi; T.Kubota; K.Oshima
First page：1131, Last page：1135, 1998
Back Bead Control of the One-side Robotic Welding with Visual Sensor
K.Eguchi; H.Sugi; T.Kubota; K.Oshima
Proceedings of 24the Annual Conference of IEEE Industrial Electronics Society, First page：1131, Last page：1135, 1998
Neuro-Fuzzy Control in the Robotic Welding(Key Technologies of the Robotic Welding : State of the Art and Problems to be solved)
Ohshima Kenji; Yamane Satoshi
Journal of the Japan Welding Society, Volume：63, Number：7, First page：516, Last page：522, 05 Oct. 1994
Japan Welding Society, Japanese
ISSN：0021-4787, CiNii Articles ID：110003396109, CiNii Books ID：AN00246019
Tracking of the Orbit using Genetic Algorithm and Fuzzy Control in Robotic Welding
Hatanaka T.; Kaneko Y.; Kobayashi K.; Yamane S.; Ohshima K.
Pre-Prints of the National Meeting of JWS, Number：55, First page：82, Last page：83, 26 Sep. 1994
Japan Welding Society, Japanese
CiNii Articles ID：110003428087, CiNii Books ID：AN10273925
Sensing of the Weld Pool in Pulsed MIG Welding by Multi-layered Fuzzy Inference
Kaneko Y.; Miyazawa M.; Kubota T.; Yamane S.; Ohshima K.
Pre-Prints of the National Meeting of JWS, Number：55, First page：78, Last page：79, 26 Sep. 1994
Japan Welding Society, Japanese
CiNii Articles ID：110003428085, CiNii Books ID：AN10273925
Neuro-Fuzzy Control of Weld Pool in Pulsed MIG Welding
KANEKO Yasuyoshi; IISAKA Tatsuya; YAMANE Satoshi; OHSHIMA Kenji
quarterly journal of the Japan Welding Society, Volume：12, Number：3, First page：374, Last page：378, 05 Aug. 1994
This paper deals with the problem concerning the sensing and the controlling of weld pool. In order to obtain the high quality of the welding result, it is important to control the weld pool depth in the robotic welding regardless of the external disturbance such as an irregular change of the groove gap. The method of controlling the weld pool depth without mathematical model is discussed. Since it is difficult to directly measure the depth, the depth is estimated from the surface shape of the weld pool, the groove gap, and the welding current. A neural network is used to estimate the depth without mathematical model. The weld pool depth is controlled from the output of the neural network by using the fuzzy controller. The validity of the neural network and of the fuzzy controller was verified by the welding experiments.
Japan Welding Society, Japanese
ISSN：0288-4771, CiNii Articles ID：110003423336, CiNii Books ID：AN1005067X
Construction of Fuzzy Model and Fuzzy Control of the Penetration in Pulsed MIG Welding.
Iisaka T.; Miyazawa M.; Kaneko Y.; Kubota T.; Yamane T.; Ohsima K.
Pre-Prints of the National Meeting of JWS, Number：54, First page：160, Last page：161, 13 Mar. 1994
Japan Welding Society, Japanese
CiNii Articles ID：110003427947, CiNii Books ID：AN10273925
Tracking of Orbit with Neuro-Fuzzy Controller and Hopfield Network
金子 裕良; 成嶋 和行; 大嶋 健司; 山根 敏
Volume：47, First page：207, Last page：208, 27 Sep. 1993
本研究では多関節ロボットを用いて3次元構造物上の軌道を追跡する方法について検討する。溶接分野においては、ロボット手先の姿勢が被溶接物および軌道に対して垂直であることが望ましい。しかし被溶接物の形状によってはロボット手先と被溶接物との干渉を避けるために手先姿勢を変化させる必要がある。特に直角の曲がり角を持つ軌道を追跡する場合の手先姿勢の決定は重要な課題である。このために、望ましい溶接姿勢、追跡性能および被溶接物との干渉を考慮し、ホップフィールドネットワークにより手先姿勢を予見的に決定する。軌道はCCDカメラを用いてセンシングし、ニューロ・ファジィ制御により追跡を行う。
Japanese
CiNii Articles ID：110002884630, CiNii Books ID：AN00349328
Fuzzy control of seam tracking and torch posture with arm type robots.
馬 培軍; 里野 光; 金子 裕良; 山根 敏; 大嶋 健司
Volume：47, First page：51, Last page：52, 27 Sep. 1993
平面にパイプを溶接する場合のロボットの知能化について考察する。すなわち、溶接線に対してロボット手先姿勢を一定に保ちながら軌道の追跡を行う。ここではライン状レーザとCCDカメラにより溶接線を検出する。手先の運動方程式は複雑となるので、姿勢制御と溶接線追跡には式を必要としないファジィ制御を用いる。このとき、最適なファジィ変数を求めるためにニューラルネットワークと最急降下法を用いる。追跡実験においてファジィ制御の有効性を確認する。
Japanese
CiNii Articles ID：110002884552, CiNii Books ID：AN00349328
Sensing and Controlling of the Weld Pool by the Fuzzy Inference
Kaneko Y.; yamane S.; Iisaka T.; Kubota T.; Ohshima K.
Pre-Prints of the National Meeting of JWS, Number：53, First page：178, Last page：179, 31 Aug. 1993
Japan Welding Society, Japanese
CiNii Articles ID：110003431644, CiNii Books ID：AN10273925
Application of Neuro-fuzzy Control to the Tracking of the orbit
Ma P.; Narushima K.; Kaneko Y.; Yamane S.; Ohshima K.
Pre-Prints of the National Meeting of JWS, Number：53, First page：182, Last page：183, 31 Aug. 1993
Japan Welding Society, Japanese
CiNii Articles ID：110003431646, CiNii Books ID：AN10273925
Sensing and Neuro-Fuzzy Control in Fillet MIG Welding
Kaneko Yasuyoshi; Kohashi Yoshiaki; Ohshima Kenji; Yamane Satoshi
Pre-Prints of the National Meeting of JWS, Number：52, First page：150, Last page：151, 15 Mar. 1993
Japan Welding Society, Japanese
CiNii Articles ID：110003431504, CiNii Books ID：AN10273925
Fuzzy Control and Neural Network in Tracking of Welding line
Narushima Kazuyuki; Matumoto Haruyuki; Kaneko Yasuyoshi; Ohshima Kenji; Yamane Satoshi; Iizuka Tadayuki
Pre-Prints of the National Meeting of JWS, Number：52, First page：148, Last page：149, 15 Mar. 1993
Japan Welding Society, Japanese
CiNii Articles ID：110003431503, CiNii Books ID：AN10273925
Neuro-Fuzzy Control of Weld Pool in Pulsed MIG Welding
Yamane S.; Kohashi Y.; Kaneko Y.; Kubota T.; Ohshima K.
Pre-Prints of the National Meeting of JWS, Number：52, First page：146, Last page：147, 15 Mar. 1993
Japan Welding Society, Japanese
CiNii Articles ID：110003431502, CiNii Books ID：AN10273925
Sensing and Fuzzy Control of Weld Pool in Pulsed MIG Welding
YAMANE Satoshi; OHSHIMA Kenji; KOHASHI Yoshiaki
quarterly journal of the Japan Welding Society, Volume：10, Number：4, First page：46, Last page：51, 05 Nov. 1992
This paper deals with some problems concerning the sensing and controlling of the weld pool. A good quality of the welding result can be obtained by keeping the weld pool shape constant. The system for sensing and controlling the weld pool is proposed. First, authors tried to take an image of the weld pool with a CCD shutter camera. A new method is proposed to clearly take the weld pool. The method is to reduce the welding current as small as possible while the shutter of the CCD camera opens for 1 [ms]. The weld pool shape can be obtained by the image processing. Next, the method is discussed for controlling the weld pool. It may be difficult to describe the state equations of the weld pool shape, since welding phenomena are described by partial differential equations. Therefore, authors control the weld pool shape with the fuzzy controller. In fuzzy control, it is important to determine the control rule and the fuzzy variables. A new method is proposed for designing the fuzzy controller. The weld pool width w (t) for the welding current u (t) is approximated by a first order system with the time delay T : dw (t)/dt=-λw (t)+bu (t-T). In the system with the time delay, when the gain of the conventional fuzzy controller increase, the response of the plant may become unstable. In order to improve the control performance, the fuzzy variables and the control rules are constructed from design knowledge of the controller for the first order system with the time delay. Namely the deviation e [n], its variation Δe [n], the prior manipulating variable Δu [n-1], and the manipulating variable Δu[n] are used as the fuzzy variables. The validity of proposed method was verified by the experiments.
Japan Welding Society, Japanese
ISSN：0288-4771, CiNii Articles ID：110003423185, CiNii Books ID：AN1005067X
Neuro and Fuzzy Control of Weld Pool in Pulsed MIG Welding
Ohshima Kenji; Kaneko Yasuyoshi; Kohashi Yoshiaki; Kubota Takefumi; Yamane Satoshi
Pre-Prints of the National Meeting of JWS, Number：51, First page：354, Last page：355, 01 Sep. 1992
Japan Welding Society, Japanese
CiNii Articles ID：110003427858, CiNii Books ID：AN10273925
Sensing and Fuzzy Control in Fillet MIG Welding
Yamane Satoshi; Ohshima Kenji; Kaneko Yasuyoshi; Kohashi Yoshiaki; Kubota Takefumi
Pre-Prints of the National Meeting of JWS, Number：51, First page：362, Last page：363, 01 Sep. 1992
Japan Welding Society, Japanese
CiNii Articles ID：110003427862, CiNii Books ID：AN10273925
Sensing and Fuzzy Control of Weld Pool Shape
Yamane S.; Ohshima K.; Kaneko Y.; Ikeya H.; Chen Q.
Pre-Prints of the National Meeting of JWS, Number：49, First page：80, Last page：81, 25 Aug. 1991
Japan Welding Society, Japanese
CiNii Articles ID：110003427427, CiNii Books ID：AN10273925
抵抗溶接環境における低周波磁界の計測とシミュレーション
2009
抵抗溶接環境における低周波磁界の計測とシミュレーション
電気学会全国大会講演論文集, 2009
In Process Control of Weld Pool using Weaving Control in Switch Back Welding
2008
Poster presentation
Numerical simulation of weld pool in narrow gap GMA welding
2008
Poster presentation
Estimation of Welding Voltage Using Neural Network in GMA Welding
2008
Poster presentation
スイッチバック溶接における溶融池のセンシングと協調制御
2008
スイッチバック溶接のバッキングレスV開先溶接に関する一連の研究
2008
ニューラルネットワークのロボット溶接への適応
2008
協調制御システムによる高品質溶接
2008
高効率溶接ロボットにおける溶融池の数値シミュレーション
2008
抵抗溶接作業環境における誘導電流の数値解析
2008
抵抗溶接作業環境における低周波磁界の測定
2008
In Process Control of Weld Pool using Weaving Control in Switch Back Welding
2008
Poster presentation
Numerical simulation of weld pool in narrow gap GMA welding
2008
Poster presentation
Estimation of Welding Voltage Using Neural Network in GMA Welding
2008
Poster presentation
スイッチバック溶接における溶融池のセンシングと協調制御
溶接学会全国大会講演概要, 2008
スイッチバック溶接のバッキングレスV開先溶接に関する一連の研究
溶接学会全国大会講演概要, 2008
ニューラルネットワークのロボット溶接への適応
溶接学会全国大会講演概要, 2008
協調制御システムによる高品質溶接
溶接学会全国大会講演概要, 2008
高効率溶接ロボットにおける溶融池の数値シミュレーション
溶接学会全国大会講演概要, 2008
抵抗溶接作業環境における誘導電流の数値解析
電気学会全国大会講演論文集, 2008
抵抗溶接作業環境における低周波磁界の測定
電気学会全国大会講演論文集, 2008
高効率溶接法による溶接溶融池の数値シミュレーション
2007
ニューラルネットワークによるパルスMIG 溶接における突出し長さの推定
2007
Measurement and Numerical Simulation of Electromagnetic Field in Arc Welding
2007
Numerical Simulation of MIG Weld Pool in Switch Back Welding
2007
In Process Control of Weld Pool using Weaving Control in Switch Back Welding
2007
Torch Weaving and Feed-Forward Control of Back Bead in One Side Backing Less V Groove Welding Using Switch Back Welding
2007
Cooperative Control of Robotic Welding System in One Side Backingless V Groove Welding
2007
二電極溶接法における溶接溶融池の数値シミュレーション
2007
スイッチバック溶接による溶接溶融池の制御
2007
V開先片面裏当てなしスイッチバック溶接におけるトーチ揺動方法および裏ビードのフィードフォワード制御
2007
溶接作業環境における低周波磁界の数値解析と実測,電
2007
高効率溶接法による溶接溶融池の数値シミュレーション
溶接学会全国大会講演概要, 2007
ニューラルネットワークによるパルスMIG 溶接における突出し長さの推定
溶接学会全国大会講演概要, 2007
Measurement and Numerical Simulation of Electromagnetic Field in Arc Welding
Proc. of International Institute of Welding Commission XII , IIW Doc. XII-1930-07, 2007
Numerical Simulation of MIG Weld Pool in Switch Back Welding
Proc. of International Institute of Welding Commission XII , IIW Doc. 212-1106-07, 2007
In Process Control of Weld Pool using Weaving Control in Switch Back Welding
Proc. of International Institute of Welding Commission XII , IIW Doc. No. XII-1949-08, 2007
Torch Weaving and Feed-Forward Control of Back Bead in One Side Backing Less V Groove Welding Using Switch Back Welding
Proc. of International Institute of Welding Commission XII , IIW Doc. No. XII-1931-07, 2007
Cooperative Control of Robotic Welding System in One Side Backingless V Groove Welding
Proc. of IWJC-KOREA 2007, 2007
二電極溶接法における溶接溶融池の数値シミュレーション
溶接学会全国大会講演概要, 2007
スイッチバック溶接による溶接溶融池の制御
溶接学会全国大会講演概要, 2007
V開先片面裏当てなしスイッチバック溶接におけるトーチ揺動方法および裏ビードのフィードフォワード制御
溶接学会全国大会講演概要, 2007
溶接作業環境における低周波磁界の数値解析と実測,電
電気学会全国大会講演論文集, 2007
狭開先溶接における溶融池の数値シミュレーション
2006
Numerical Simulation of Electromagnetic Field in Arc welding
2006
Sensing and Control of Welding Pool in Backingless V Groove Welding
2006
Sensing and Seam Tracking of Welding Line in Backingless V Groove Welding
2006
スイッチバック溶接における溶融池の数値シミュレーション
2006
狭開先溶接における溶融池の数値シミュレーション
溶接学会全国大会講演概要, 2006
Numerical Simulation of Electromagnetic Field in Arc welding
Proc. of International Institute of Welding Commission XII, 2006
Sensing and Control of Welding Pool in Backingless V Groove Welding
Proc. of International Institute of Welding Commission XII , IIW Doc. No. XII-1902-06, 2006
Sensing and Seam Tracking of Welding Line in Backingless V Groove Welding
Proc. of International Institute of Welding Commission XII, 2006
スイッチバック溶接における溶融池の数値シミュレーション
溶接学会全国大会講演概要, 2006
ロボット溶接における溶接線の検出と追跡制御，溶接学会全国大会講演概要
2005
スイッチバック溶接による薄板溶接溶融池の制御
2005
スイッチバック溶接における溶接線の検出と追跡制御
2005
ロボット溶接における溶接線の検出と追跡制御，溶接学会全国大会講演概要
溶接学会全国大会講演概要, 2005
スイッチバック溶接による薄板溶接溶融池の制御
溶接学会全国大会講演概要, 2005
スイッチバック溶接における溶接線の検出と追跡制御
溶接学会全国大会講演概要, 2005
バッキングレスV開先溶接におけるセンシングと制御
2004
Control of Back Bead by Visual Robot in V-groove Welding without Backing Plate
2004
スイッチバック溶接における溶融池の画像処理と制御
2004
バッキングレスV開先溶接におけるセンシングと制御
溶接学会全国大会講演概要, 2004
Control of Back Bead by Visual Robot in V-groove Welding without Backing Plate
Proc. of International Institute of Welding Commission XII, 2004
スイッチバック溶接における溶融池の画像処理と制御
溶接学会全国大会講演概要, 2004
A Study on Mag Welding Skill Support System Using Deep Learning and Augmented Reality
Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, Grant-in-Aid for Scientific Research (C), 01 Apr. 2022 - 31 Mar. 2025
Saitama University
Grant amount(Total)：4160000, Direct funding：3200000, Indirect funding：960000
Grant number：22K04709
Control and estimation of weld pool in visual robotic welding using deep learning
Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, Grant-in-Aid for Scientific Research (C), 01 Apr. 2019 - 31 Mar. 2022
Yamane Satoshi, Saitama University
Grant amount(Total)：4290000, Direct funding：3300000, Indirect funding：990000
Deep learning was applied to estimate the molten pool condition in a welding system. In order to do this, it is important to capture clear images of the molten pool. Therefore, we clarified good conditions for capturing images of the molten pool by considering the characteristics of visual sensors and the spectral characteristics of the arc and molten pool. Using this method, the molten pool image was used as an input to Resnet50, a deep learning system, to estimate the molten state of the root of the groove for V-gap welding with gap variation. The boundary between the molten and unmolten areas was estimated from the molten pool image using semantic segmentation, and this was applied to weld line imitation control.
Grant number：19K05076
Fundamental of 3D adaptive model in Robotic welding
Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, Grant-in-Aid for Scientific Research (C), 01 Apr. 2015 - 31 Mar. 2019
YAMANE Satoshi, Saitama University
Grant amount(Total)：4810000, Direct funding：3700000, Indirect funding：1110000
In order to perform three-dimensional modeling using arc welding technology, a method of melting the electrode wire with low heat input is effective. In this study, I proposed the welding method with low heat input under the arc welding using the arc welding robot. For this purpose, I performed high-speed cooperative control between the characteristics of the welding power source and the electrode wire feed rate. Thus, the low heat input welding method was achieved. In addition, I examined a method for observing the melting area using a CMOS camera, and clarified how to construct an optical system.
Grant number：15K06456
Development of Automatic Control System in Plasma-MIG Hybrid Welding
Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, Grant-in-Aid for Scientific Research (C), 2011 - 2013
YAMANE Satoshi, Saitama University
Grant amount(Total)：5200000, Direct funding：4000000, Indirect funding：1200000
The deep penetration can be obtained in plasma welding under inert shielding gas. The good mechanical property can be obtained due to the inert shielding gas, too. But efficiency of the welding is not good. On the other hand, a high efficiency of the welding was achieved by using MIG welding. The arc in MIG welding becomes unstable. In order to improve the arc stability, the hybrid welding system by using plasma and MIG welding was developed. The control circuit was made to synchronize the plasma welding with the MIG welding. Arc phenomena were analyzed by using the circuit and by taking with high speed video camera. The conditions for set up and welding were specified.
Grant number：23560862
Sensing and Control of weld pool in MIG welding with neural network arc sensor
Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, Grant-in-Aid for Scientific Research (C), 2004 - 2005
YAMANE Satoshi, Saitama University
Grant amount(Total)：3300000, Direct funding：3300000
In order to get a high quality of the welding, the stable back bead is required during the welding. By using conventional welding method, the backing plates are needed to support the weld pool. If the enough weld pool can not be obtained into the backing metal plates, there is some notch. If the strong force acts on the notch, the crack takes place. In order to avoid the crack, the control of the weld pool is important and depends on the arc length and the wire extension. For this purpose, the sensing of the arc length and the wire extension are carried out. Since the behavior of the wire extension is nonlinear, it is difficult to describe the differential equation. The neural network is suitable to describe the nonlinear characteristic. The arc length and the wire extension are estimated by using the knowledge of the skill welders and the fundamental experiment result, i.e., the neural network is constructed to estimate the wire extension. If the extension is given, the arc length is calculated by using the relationship between the current and the torch voltage. In order to train the neural network, the pulsed MIG welding is carried out on the flat plate. It is taken by the high speed video camera, every 1ms. The welding current, the voltage and the wire extension are measured, too. These data are used to the training data for the neural network. In the pulsed MIG welding, the melting of the wire depends on the Joule heat, i.e., the effective value of the voltage and the current are related to the wire melting. It depends on the current, wire extension length and the wire feed rate. By using this knowledge, the input variables are determined in the neural network for the estimation of the wire extension. Sampling periods is 10ms. The data during 50ms are used as the training data. The neuron in the input layer is 20. The output is 1. That is, the extension wire is estimated by using the current, the voltage and the wire feed rate. Moreover, the control of the weld pool is considered in the butt welding for the base metal with 12mm thickness and 45 degree groove without the backing plates. By carrying out the fundamental experiments, the welding conditions are investigated. The weld pool was control according to the gap, so as to get the high quality of the welding.
Grant number：16560626
Adaptive Control of Back Bead and Bead Height under Gap Variation in Narrow Gap Robotic Welding
Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, Grant-in-Aid for Scientific Research (C), 2003 - 2004
KANEKO Yasuyoshi; YAMANE Satoshi, Saitama University
Grant amount(Total)：3500000, Direct funding：3500000
If the amount of the deposited metal becomes big in the narrow gap, the bead height becomes high. In this case, the arc heat is given on the weld pool and is not given to the root edge. Lack of fusion takes place and cause the problem concerning the mechanical strength. Therefore, in general, the amount of the deposited metal is determined so that the bead height is less than 4mm. It takes more than three times of the torch traveling from the beginning to the end of the welding line, when the thickness of the metal plates is over 12mm. Moreover, the arc behavior depends on the welding power source characteristic ; the electrode wire feed rate and the welding torch motion. The short arc length is necessary to get a high quality of the welding.
In order to control the bead height and the back bead, authors propose a cooperative control method of the welding equipments including the power source, the electrode wire feeder and the welding robot by using the computer network.
Authors try to not only oscillate the welding torch on the groove at 10 Hz, but also move along the weaving centre back and forth like switch back, i.e., authors propose the switch back welding method.
First, the authors move the weaving centre forward, to pre-heat the root edges of the base metal by the arc. The stable back bead is formed without the lack of fusion. The mentioned welding process is called forward process. Next, the authors move weaving centre backward to deposit droplets to the root edges and to the groove surface, so that the desired bead height is obtained. This is called backward process. If the arc length becomes long, it is difficult to give the heat to the root edge and a lack of fusion in the joint part takes place. In order to observe the weld pool, it is useful to use a CCD camera. But, it is difficult to apply the observation method of the weld pool, which is proposed for thin plate welding, i.e., it is important that the shutter of the CCD camera is synchronized with torch oscillating. In this paper, the shutter of the CCD camera is opened when the torch passes on the centre of the weaving. In the switch back welding, there are many parameters of welding conditions, such as traveling speed of the torch, the current, the wire feed rate and so on. To find the optimum parameters of the welding conditions, the numerical model of the weld pool is described by using an equation of heat conduction. It takes long time to solve the numerical model by applying the finite difference in a numerical analysis. In stead of the numerical model, the fuzzy model of the weld pool is proposed to save the calculation time. Its model is adjusted by using the numerical results. The optimum stroke length is estimated from 4 to 6mm gap. In order to verify the validity of the fuzzy model and the proposed welding method, the experiment is carried out under the variation of the gap. A good result of the welding can be obtained, i.e., the smooth surface bead and wide back bead are obtained.
Grant number：15560621
Seam Tracking and Detection of Groove by using Neural Network in Robotic Welding
Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, Grant-in-Aid for Scientific Research (C), 2000 - 2001
YAMANE Satoshi; KANEKO Yasuyoshi; OSHIMA Kenji, Saitama University
Grant amount(Total)：700000, Direct funding：700000
In this study, where backing plate or backing material are not used, one side back bead welding system is proposed to obtain a good welding result without the variation of the root gap. In the system, the torch is not only oscillated in the groove, but also moved before and behind like the switch back. During the forward process, a heat is given and is melted the base material and its root edge. During backward process, the droplet is deposited at the root edge and the bridge is formed. After that, the torch is moved forward by high-speed before burn through is generated. This torch motion is repeated. Therefore, there is no incomplete fusion and the stable back bead is obtained.
For this purpose,
1) The system is constructed to do the cooperative control of the torch motion (weaving width, welding speed), the wire feed rate and the power source characteristic, i.e., the stable weld pool penetration is kept and the seam tracking is carried out. The pulsed current becomes peak where the torch approaches the root edge. The droplet is deposited on the root edges. The interface circuit between computer and welding robot, the welding power source and the wire feeder was made, and the cooperative control of the wire feed rate and current waveform was carried out according to the torch position.
2) The technique is proposed for enabling the real-time sensing of the arc length and the extension length of the electrode wire in transient response.
3) The neural network models are constructed by using the extension length in the beginning of the welding, and the welding current at each sampling, the wire feed rate. Its model output is the arc length and the extension length.
The transient response is obtained by carrying out the fundamental welding experiment. The validity of this neural network is confirmed by comparing the output of the model with the experimental result. It is shown that the extension length and the arc length from voltage and current can be estimated and the neural network model is applicable as a sensor of the arc length. By using its model, it is possible to detect the groove shape during the forward process in the switch back motion.
Grant number：12650709
Study on Control Of Weld Pool Shape And Cooling Rate By Using Fuzzy-Neural Network
Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research, Grant-in-Aid for Scientific Research (A), 1995 - 1996
OSHIMA Kenji; KANJYOU Yoshihiro; SUGITANI Yuji; KUBOTA Takefumi; KANEKO Yasuyoshi; YAMANE Satoshi, Saitama University
Grant amount(Total)：5000000, Direct funding：5000000
Knowledge based information processing and control of welding robots by using fuzzy neural network is discussed. The authors apply the fuzzy-neural network to estimate weld pool penetration depth and cooling time, and control welding current and cooling time by fuzzy control.
First, images of weld pool surface and gap are taken with CCD cameras, simultaneously. By using image processing, pool surface shape and gap are obtained. Next, the authors made neural networks to estimate the weld pool shape (the penetration depth and the back bead width) and heat input to base metals, which corresponds to the welding current. The penetration depth is detected by using the fuzzy neural network and the information such as the weld pool surface, the gap and the current in case of the variation of the gap. By using multi-layred fuzzy control, the current is controlled to keep the estimated penetration depth the desired value.
Neural networks are constructed to estimate the cooling time by using gap, current and welding speed. Training data of neural network are mede by carrying out numerical simulations concerning heat transfer in the weld pool. Current and welding speed are determined by using neural networks to get the desired cooling rate, and are applied to the welding. A good quality of the welding is obtained.
The authors consider the simulation result and propose switch back welding to get the stable back bead and desired cooling rate. The validity of the one-side back bead welding without backing is verified to carry out simulations and experiments.
Grant number：07555511
各種センサを持つエキスパートロボットによるGMA溶接の全自動化に関する研究
1992 - 1992
Grant amount(Total)：5400000, Direct funding：5400000
Grant number：04452283
