Conceptualization of An Intelligent Decision Framework for Control Factors and Weld Quality Prediction

Open Access

Year : 2023 | Volume :11 | Special Issue : 06 | Page : 10-19
By

Pradeep Kumar Singh

Abstract

To improve the robot’s welding quality, control welding precision, optimize welding parameters, realize continuous welding quality database optimization, and increase welding defect detection, a fuzzy neural network-based intelligent decision-making system must be built. This study demonstrates how fuzzy control theory and BP neural networks may be used to identify welding issues and enhance process variables. The experimental findings indicate that, with seam classification accuracy close to 90%, enhancing welding parameters and performance is feasible and achievable. Neural networks, fuzzy controls, and expert systems are all used to describe welding process control. Utilizing intelligent welding controllers. Systems with intelligence can identify surface, volume, and linear welding faults. morphological (pits, undercuts, welds, surface cracks), volumetric (voids), or linear (such as slag, partial penetration, unfused, and fractures). Destructive testing benefits from data storage and visibility. Design and demand changes complicate production decisions. AI approaches like neural networks make online decisions. This article uses neural networks to predict SAW weld quality (SAW). Taguchi’s principles are applied in experiments and equations. The use of experimental data and regression analysis in the development of neural network models. Considering the relative speeds and precisions of the models. NNPSO performs better than BPNN, RBFNN, and GA combined (NNGA). The created weld quality prediction technique contains online monitoring, and it is customizable, competent, and accurate. Additionally, the scheme is competent. Models are tested. The strategy that has been presented and developed will assist people in protecting themselves from robot risks.

Keywords: Welding quality, intelligent decision-making system, welding quality, welding precision, optimized welding parameters, fuzzy neural network

[This article belongs to Special Issue under section in Journal of Polymer and Composites(jopc)]

How to cite this article: Pradeep Kumar Singh. Conceptualization of An Intelligent Decision Framework for Control Factors and Weld Quality Prediction. Journal of Polymer and Composites. 2023; 11(06):10-19.
How to cite this URL: Pradeep Kumar Singh. Conceptualization of An Intelligent Decision Framework for Control Factors and Weld Quality Prediction. Journal of Polymer and Composites. 2023; 11(06):10-19. Available from: https://journals.stmjournals.com/jopc/article=2023/view=119388

Full Text PDF Download

Browse Figures

References

1.
Lihong Zhu, Zhihong Chen. “Intelligent control of fuzzy adaptive PID pulse welding power supply,” Welding, pp. 65–68, 2016.
2.
Weilin Zhou, “Research on laser vision weld detection and tracking system based on deep layered features,” South China University of Technology, 2018.
3.
Y. Bao, H. Liao, J. Zhang, J. Zhang, K. Yang, and Y. Jiang, “Online analysis system for short-cycle arc stud welding,” Electric welding machine, pp. 17–25, 2017.
4.
Zhihao Chen, “Application of fuzzy neural network in intelligent identification of welding defects,” China Strategic Emerging Industry, p. 137, 2017.
5.
K. He and X. Li, “A quantitative estimation technique for welding quality using local mean decomposition and support vector machine,” Journal of Intelligent Manufacturing, vol. 27, pp. 525–533, 2016.
6.
Weijia Lu, Xiangdong Gao, Nanfeng Zhang, et al, “Application of fuzzy control technology in automatic tracking of arc welding seams,” Manufacturing Technology and Machine Tools, pp. 50–54, 2017.
7.
Dejin Xu, “Design of big data analysis system based on cloud intelligent welding control,” Electric Welding Machine, pp. 21–25, 2018.
8.
S. B. Chen, Z. Ye and G. Fang, “Intelligentized Technologies for Welding Manufacturing,” Materials Science Forum, vol. 773–774, pp. 725–731, 2015.
9.
Y. Zou, L. Fang, Z. Hui, and K. Miao, “Research on quality inspection for backside weld of tailored blank laser welding based on texture feature,” in Intelligent Control & Automation, 2015.

10.
T. M. Lubecki and F. Bai, “Weld quality assessment based on arc sensing for robotic welding,” in IEEE International Conference on Advanced Intelligent Mechatronics, 2015.
11.
L. Sheng, X. Tang, H. Peng, J. Pan, Y. Pei, and H. Zhu, “Research of on-line inspection of laser welding seam quality of cold rolled strips,” Laser Technology, vol. 39, pp. 437–442, 2015.
12.
Haipeng Deng, “Integration and application of intelligent manufacturing and robot welding technology,” Electromechanical Information, pp. 105–106, 2018.
13.
Y. Xu, L. Na, F. Gu, L. Tao, H. Chen, S. Chen, and H. Yu, Sensing Technology for Intelligentized Robotic Welding in Arc Welding Processes, 2015.
14.
Turichin, G. Velichko, O. Kuznetsov, A. Pevzner, J. Grinin, “Design of mobile hybrid laser-arc welding system on the base of 20 kW fiber laser,” Laser Optics, 2014 International Conference, 2014.
15.
Yachao Yang, Huimin Quan, Linfeng Deng, et al, “Prediction method of welding machine parameters based on neural network,” Transactions of the China Welding Society, pp. 32–36, 2018.
16.
Guangxue Dong, Junjie He, Liangyu Li, et al, “Improvement of arc sensing integral difference method based on BP neural network,” Welding Technology, pp. 31–35, 2016.
17.
Yinbo Wang, Zhonglin Yang, Yanli Xu, “Intelligent management system for networked welding data,” Electric Welding Machine, pp. 125–129, 2018.
18.
D. T. Thao, I. S. Kim, H. H. Na, S. M. Jung, and J. Y. Shim, “Development of mathematical model with a genetic algorithm for automatic GMA welding process,” International Journal of Advanced Manufacturing Technology, vol. 73, pp. 837–847, 2014.
19.
Sugawara Mai, et al, “Control system for reducing weld spatter during the welding process by using high-speed visual sensing,” Mechanical Engineering Letters, March 2017.
20.
Hirata Ichiro, Tsurumarun ataka, Goto Yasunori, “Application of Generic System Design Process Case Study of a Welding Torch Handle Design,” Special issue of Japanese Society for the Science of Design, 2015.
21.
N. Ravinder, Reddy, V.V. Satyanarayana, M. Prashanthi, N. Suguna, “Application of triz methodology in diffusion welding system optimization,” Management Systems in Production Engineering, 2017.
22.
Y. J. Jeong, H. H. Kim, R. R. Chand, H. H. Na, H. L. Ji, and I. S. Kim, “A Smart System to Determine and Control for the Process Parameters in Pipeline Welding,” Materials Science Forum, vol. 773–774, pp. 750–758, 2014.
23.
I. S. Kim, J. H. Lee, J. Malekani, and P. K. D. V. Yarlagadda, “Prediction of GMA Welding Characteristic Parameter by Artificial Neural Network System,” Advanced Materials Research, vol. 1061–1062, p. 11, 2014.
24.
Ke Qin, “Internet-of-Things Monitoring System of Robot Welding Based on Software Defined Networking,” IEEE, Huazhong Normal University, Proceedings of 2016 First IEEE International Conference on Computer Communication and the Internet (ICCCI 2016), IEEE BEIJING SECTION, June 2016.
25.
Qin Yang, “Design of Welding Control System Based on Robot,” Science and Engineering Research Center, Proceedings of 2016 International Conference on Electrical Engineering and Automation (ICEEA2016) Science and Engineering Research Center, Science and Engineering R

Special Issue Open Access Original Research
Volume 11
Special Issue 06
Received June 21, 2023
Accepted August 29, 2023
Published September 29, 2023
Views: 219