Welding spot quality detection method and device based on multi-model fusion and storage medium

Abstract

The invention discloses a welding spot quality detection method and device based on multi-model fusion and a storage medium, and the method comprises the steps: obtaining a welding spot technological parameter data set in a resistance spot welding process, and dividing the welding spot technological parameter data set into a training set and a test set according to a preset proportion; adopting a machine learning algorithm to construct a plurality of single welding spot quality detection models, and inputting the training set into each single welding spot quality detection model for training; evaluating each trained single welding spot quality detection model according to a preset evaluation index, and selecting the single welding spot quality detection model with good evaluation performance as a base classifier; and inputting the test set into each base classifier, and fusing output results of all the base classifiers according to a preset rule to obtain a welding spot quality detection result. According to the embodiment of the invention, the method can effectively prevent the model from being over-fitted, has good generalization capability, improves the robustness of the model, and achieves the improvement of the accuracy and detection efficiency of the quality detection of the welding spots.

Description

technical field [0001] The invention relates to the technical field of resistance spot welding, in particular to a method, device and storage medium for detecting the quality of solder joints based on multi-model fusion. Background technique [0002] At present, the automotive industry mainly uses manual sampling methods such as chisel inspection, full destruction inspection, and ultrasonic inspection to detect the quality of body solder joints. However, the above random inspection methods have problems such as narrow coverage of detected solder joints and low sampling frequency, which may easily cause a large number of unqualified Solder joints flow out, causing safety hazards. In order to solve this problem, the automotive industry is exploring the method of analyzing solder joint process parameters through machine learning to detect the quality of solder joints, so as to realize the full inspection of the quality of solder joints on the body and eliminate the potential sa...

AI Technical Summary

Problems solved by technology

[0002] At present, the automotive industry mainly uses manual sampling methods such as chisel inspection, full destruction inspection, and ultrasonic inspection to detect the quality of body solder joints. However, the above random inspection methods have problems such as narrow coverage of detected solder joints and low sampling frequency, which may easily cause a large number of unqualified Solder joints flow out, causing safety hazards

Images