Image processing method for automatic tracking of the weld line in plasma robotic welding

Wang, Weixi; Yamane, Satoshi; Koike, Tomoyuki; Touma, Jiro; Hosoya, Kazumichi; Nakajima, Takashi; Yamamoto, Hiroyuki

doi:10.1007/s00170-015-8311-8

Cited by 13 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…19) If there is no gap in the workpieces with the groove, the quality of PAW will depend on the tracking of the welding line. 21) Due to heat distortion, the gap occurs in the fabrication of the thick plates. Thus, to get a high quality, it is required to adjust the welding parameters according to the gap.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Control by Convolutional Neural Network in Plasma Arc Welding System

Yamane

Matsuo

2020

ISIJ Int.

Self Cite

View full text Add to dashboard Cite

Plasma arc welding (PAW) was employed in joining thick materials with groove. Due to the high-density plasma arc, keyhole welding was used in the butt welding. The gap might be taken in places due to the heat distortion during the welding. To achieve a high-quality welding, the adaptive control is required according to the gap. The authors tried to apply CMOS camera to obtain information from the top surface and achieve synchronization between the camera shutter and welding current. Thus, a clear image of the weld pool with the keyhole and the gap was taken. The brightness distribution in the front of the weld pool becomes uneven due to the plasma arc. To classify the gap and select the welding conditions, such as the welding current and the plasma gas flow rate, the authors used one of the deep learning algorithms, convolutional neural network (CNN). In the training and testing data, the performance of the CNN was found to be satisfactory. However, if the plasma torch does not trace the welding line, the pool image will be different from the training image. Hence, the CNN will not be able to estimate the correct gap. To avoid this, the authors detected the welding line from the pool image and selected the image area near the welding line as the input of the CNN, i.e., the input area is selected based on the image obtained during the welding. The validity of the proposed method was verified by the welding experiments.

show abstract

Section: Introductionmentioning

confidence: 99%

Adaptive Control by Convolutional Neural Network in Plasma Arc Welding System

Yamane

Matsuo

2020

ISIJ Int.

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, these methods have limitations due to the difficulty placing additional sensors within the vacuum chamber, which creates complications when used in industrial conditions. Moreover, a number of studies indicate that electron beam welding is accompanied by high-frequency processes [1][2][3][4] that often carry the most information about the thermal characteristics of the electron beam's interaction with the metal in the penetration channel. Frequencies up to 20 kHz are inherent to these processes, which makes it possible to study them using X-ray radiation sensors.…”

Section: Introductionmentioning

confidence: 99%

“…Methods based on registration of the secondary plasma current originating above the welding zone [5] are promising. Several methods have been developed to study and control electron beam welding [1][2][3][4][5] processes. Similar works in the area of laser welding have been widely conducted recently.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modeling the Influence of the Penetration Channel’s Shape on Plasma Parameters When Handling Highly Concentrated Energy Sources

Трушников

Саломатова

Bezukladnikov

et al. 2017

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

In our work to formulate a scientific justification for process control methods when processing materials using concentrated energy sources, we develop a model that can calculate plasma parameters and the magnitude of the secondary waveform of a current from a non-self-sustained discharge in plasma as a function of the geometry of the penetration channel, thermal fields, and the beam's position within the penetration channel. We present the method and a numeric implementation whose first stage involves the use of a two-dimensional model to calculate the statistical probability of the secondary electrons' passage through the penetration channel as a function of the interaction zone's depth. Then, the discovered relationship is used to numerically calculate how the secondary current changes as a distributed beam moves along a three-dimensional penetration channel. We demonstrate that during oscillating electron beam welding the waveform has the greatest magnitude during interaction with the upper areas of the penetration channel and diminishes with increasing penetration channel depth in a way that depends on the penetration channel's shape. When the surface of the penetration channel is approximated with a Gaussian function, the waveform decreases nearly exponentially.

show abstract

“…Adaptive control makes it possible to ensure consistent quality during welding and related processes [11][12][13][14][15][16]. Its measures can reduce the size of allowances in subsequent mechanical processing, leading to a reduction in the cost of production and improving the energy-efficiency of the process.…”

Section: Introductionmentioning

confidence: 99%

Use of a Secondary Current Sensor in Plasma during Electron-Beam Welding with Focus Scanning for Process Control

2016

View full text Add to dashboard Cite

We consider questions of building a closed-loop focus control system for electron-beam welding. As a feedback signal, we use the secondary current in the plasma that forms above the welding zone. This article presents a model of a secondary current sensor in plasma during electron-beam welding with focus scanning. A comparison of modeled results with experimental data confirms the adequacy of the model. We show that the best results for focus control are obtained when using phase relationships rather than amplitude relationships. We outline the principles for building an EBW focus control system based on parameters of the secondary current in plasma. We simulate the work of a control system’s circuits and demonstrate the stability of the synthesized system. We have conducted pilot tests on an experimental prototype.

show abstract

Image processing method for automatic tracking of the weld line in plasma robotic welding

Cited by 13 publications

References 16 publications

Adaptive Control by Convolutional Neural Network in Plasma Arc Welding System

Adaptive Control by Convolutional Neural Network in Plasma Arc Welding System

Modeling the Influence of the Penetration Channel’s Shape on Plasma Parameters When Handling Highly Concentrated Energy Sources

Use of a Secondary Current Sensor in Plasma during Electron-Beam Welding with Focus Scanning for Process Control

Contact Info

Product

Resources

About