EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimization of Welding Parameters Using an Improved Hill-Climbing Algorithm Based on BP Neural Network for Multi-Bead Weld Smoothness Control

Ying Tong, Guo-Zheng Quan, Hai-Tao Wang, Wei Xiong iD

Materials · 31.08.2025 · 18 (17) · 4084

DOI: 10.3390/ma18174084 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 31.08.2025. Verfasst von Ying Tong und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Intelligent Manufacturing and Automotive, Chongqing Polytechnic University of Electronic Technology, Chongqing 401331, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sichuan Science and Technology Program, Sichuan Provincial Special Project for Industrial Development of Key Technical Equipment.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In multi-pass welding processes, achieving a uniform and smooth weld surface is crucial for mechanical performance and dimensional accuracy. However, the complex nonlinear relationships between welding parameters and weld bead geometry present significant challenges for traditional optimization methods. This study proposes an intelligent prediction and optimization framework that integrates a backpropagation (BP) neural network with an improved hill-climbing algorithm to enhance weld surface smoothness in automated multi-bead overlay welding. Experimental data collected under varying arc voltages, wire feed rates, and welding speeds were used to train the neural network. The improved hill-climbing algorithm adaptively adjusts weights and biases in the BP model to overcome issues of local minima and slow convergence. Comparative results demonstrate that the proposed method significantly outperforms conventional BP approaches in terms of prediction accuracy and convergence efficiency. Furthermore, optimal welding parameters identified by the model yield smoother weld surfaces, reducing the need for post-processing. This work provides a novel solution for intelligent control and real-time optimization in advanced welding systems.

Schlagwörter

Stichwörter der Autor:innen

BP neural networkautomated overlay weldinghill-climbing algorithmsurface smoothness predictionweld bead morphologywelding parameter optimization

Autor:innen und Institutionen

  • College of Intelligent Manufacturing and Automotive, Chongqing Polytechnic University of Electronic Technology, Chongqing 401331, China.
  • Chongqing Key Laboratory of Advanced Mold Intelligent Manufacturing, School of Material Science and Engineering, Chongqing University, Chongqing 400044, China.
  • Key Laboratory of Advanced Reactor Engineering and Safety, Ministry of Education, Collaborative Innovation Center of Advanced Nuclear Energy Technology, Institute of Nuclear and New Energy Technology, Tsinghua Universit…

ORCID-Profile: Wei Xiong

Förderung

  • Sichuan Science and Technology Program
  • Sichuan Provincial Special Project for Industrial Development of Key Technical Equipment

Zitieren

APA

Tong, Y., Quan, G. Z., Wang, H. T., & Xiong, W. (2025). Optimization of Welding Parameters Using an Improved Hill-Climbing Algorithm Based on BP Neural Network for Multi-Bead Weld Smoothness Control. Materials, 18(17), 4084. https://doi.org/10.3390/ma18174084

Vancouver

Tong Y, Quan GZ, Wang HT, Xiong W. Optimization of Welding Parameters Using an Improved Hill-Climbing Algorithm Based on BP Neural Network for Multi-Bead Weld Smoothness Control. Materials. 2025;18(17):4084. doi:10.3390/ma18174084

BibTeX
@article{Tong2025,
  author = {Tong, Ying and Quan, Guo-Zheng and Wang, Hai-Tao and Xiong, Wei},
  title = {Optimization of Welding Parameters Using an Improved Hill-Climbing Algorithm Based on BP Neural Network for Multi-Bead Weld Smoothness Control},
  journal = {Materials},
  year = {2025},
  volume = {18},
  number = {17},
  pages = {4084},
  doi = {10.3390/ma18174084}
}
Kostenlos starten →