<abstract xmlns="http://www.w3.org/1999/xhtml">

A method has been proposed for welding penetration status prediction in the paper. First, an experimental system was set up and welding experiments were performed. Some groups of welding images could been obtained. A composite filtering system composed of a neutral light reduction filter and a narrow band filter was developed to filter the weld arc disturbance. Some operations were performed to the images, namely the median filter and gray transformation. Then a neural network was setup, containing three layers. The inner widths of pool <italic>xn</italic>, the outer widths of pool <italic>xw</italic>, the width difference values <italic>e</italic> between the inner and outer of pool, ratios of inner pool widths <italic>Rn</italic> and ratios of outer pool widths <italic>Rw</italic> between two adjacent images were determined to be the input parameters. The penetration parameter <italic>p</italic> was chosen to be the output. Based on the images, groups of pool parameter data have been obtained and used to train the network. In this way, the weld penetration prediction model can be deduced. Finally, verification tests have been done. It showed that weld penetration situation predicted by the model is fit to its real condition. The accuracy rate is up to 96%, which affords a new way for penetration detection.
</abstract>

A method has been proposed for welding penetration status prediction in the paper. First, an experimental system was set up and welding experiments were performed. Some groups of welding images could been obtained. A composite filtering system composed of a neutral light reduction filter and a narrow band filter was developed to filter the weld arc disturbance. Some operations were performed to the images, namely the median filter and gray transformation. Then a neural network was setup, containing three layers. The inner widths of pool xn, the outer widths of pool xw, the width difference values e between the inner and outer of pool, ratios of inner pool widths Rn and ratios of outer pool widths Rw between two adjacent images were determined to be the input parameters. The penetration parameter p was chosen to be the output. Based on the images, groups of pool parameter data have been obtained and used to train the network. In this way, the weld penetration prediction model can be deduced. Finally, verification tests have been done. It showed that weld penetration situation predicted by the model is fit to its real condition. The accuracy rate is up to 96%, which affords a new way for penetration detection.

Research of neural network for weld penetration control

Department of Electronic Information, Dongguan Polytechnic

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

{"article-title":"Research of neural network for weld penetration control"}

A method has been proposed for welding penetration status prediction in the paper. First, an experimental system was set up and welding experiments were...

Item	Numerical value

Scale	1/3″
Focal length	5~50 mm
Aperture	F1.3-C
Angle of view	51.8–56°
Nearest object distance	0.8 m

Research of neural network for weld penetration control

Online veröffentlicht: 31. März 2022

Seitenbereich: 849 - 860

Eingereicht: 22. Juli 2021

Akzeptiert: 06. Dez. 2021

DOI: https://doi.org/10.2478/amns.2021.2.00169

Schlüsselwörter
weld, weld pool image, weld penetration control, neural network modelling

© 2021 Dukun Ding, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Fig. 9

Fig. 10

Fig. 11

Fig. 12

Fig. 13

Welding experiment conditions

Size of T10Z0513CS lens

Weld penetration status

Research of neural network for weld penetration control

Online veröffentlicht: 31. März 2022

Seitenbereich: 849 - 860

Eingereicht: 22. Juli 2021

Akzeptiert: 06. Dez. 2021

DOI: https://doi.org/10.2478/amns.2021.2.00169

Schlüsselwörterweld, weld pool image, weld penetration control, neural network modelling

© 2021 Dukun Ding, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Fig. 9

Fig. 10

Fig. 11

Fig. 12

Fig. 13

Welding experiment conditions

Size of T10Z0513CS lens

Weld penetration status

Schlüsselwörter
weld, weld pool image, weld penetration control, neural network modelling