Optimizing the Validation Process of Resistance Spot Welds in the Automotive Industry Using TOPSIS and K-fold Cross-Validation

EasyChair Preprint 14107

Abstract

In a complex and constantly evolving environment, decision-making has become a major challenge for organizations, governments, and individuals. Faced with this complexity, Multi-Criteria Decision Making (MCDM) methods have proven to be valuable tools. Among them, the TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) technique stands out for its ability to provide informed and justified decisions. This issue is particularly relevant in the automotive industry, where resistance spot welding plays a critical role in the assembly of car bodies. However, the choice of optimal welding parameters requires taking into account many conflicting criteria. In this conference paper, we will present the results of training an artificial neural network, with the objective of classifying and validating weld spots according to their dimensions, indentations, and sheet thicknesses. This innovative approach aims to optimize the resistance spot welding process in the automotive industry, leveraging the advancements in artificial intelligence.

Keyphrases: ANN, IA, K-Fold, MCDM, Quality, RWS, TOPSIS

@booklet{EasyChair:14107,
  author    = {Adil Nabih and Imane Moufid and Labiba Bousmaki and Driss Serrou and Ismail Lagrat and Oussama Bouazaoui},
  title     = {Optimizing the Validation Process of Resistance Spot Welds in the Automotive Industry Using TOPSIS and K-fold Cross-Validation},
  howpublished = {EasyChair Preprint 14107},
  year      = {EasyChair, 2024}}