A Solder Joint Quality Evaluation Method Based on Indentation Feature Image Recognition

Abstract

The invention relates to a method for evaluating the quality of solder joints, in particular to a method for evaluating the quality of solder joints based on indentation feature image recognition. The method includes the following steps: S1 obtains the indentation image and the nugget diameter of the corresponding solder joint; S2 preprocesses the indentation image to eliminate noise, highlight the boundary, and fill holes; S3 designs a feature extraction algorithm based on the preprocessed image to obtain Solder joint indentation average axial length, pitting area, and Hog features; S4 draws average axial length-nucleus diameter, pitting area-nucleus diameter curves, and finds the first feature point and the second feature point; S5 according to the extracted features Compare with the first characteristic point, the second characteristic point or use SVM to evaluate the solder joint quality. The invention integrates multiple image processing algorithms, extracts multiple features representing indentation, solves the problems of difficult feature extraction of solder joints and electrodes, and difficult evaluation of solder joint quality, and provides a new idea for automatic welding quality monitoring. The classification of solder joints provides a reference.

Description

technical field [0001] The invention relates to a method for evaluating the quality of solder joints, in particular to a method for evaluating the quality of solder joints based on indentation characteristic image recognition, and belongs to the field of welding technology. Background technique [0002] Resistance spot welding is widely used in the connection of plates in industrial production due to its simple operation, high production efficiency and low cost. However, the resistance spot welding has the characteristics of complex process, rapid temperature change, and strong coupling between stages in the welding process, which makes it difficult to extract the state information of the solder joints. At present, the methods for evaluating the quality of solder joints mainly include manual visual inspection and destructive testing. Among them, the manual visual inspection method is time-consuming and laborious, and has high requirements for technical personnel, and the in...

AI Technical Summary

Problems solved by technology

Although this method can effectively reduce human influence and identify solder joints, it cannot identify common defects such as pitting and spattering.

[0004] Galvanized high-strength steel sheet is a kind of high-strength steel that has emerged in recent years. Compared with traditional steel sheets, it has problems such as significant changes in pitting wear characteristics, serious electrode wear, and poor welding processability during spot welding. It will have a serious impact on the quality of solder joints, and the pitting characteristics are difficult to obtain by traditional non-destructive testing methods. Therefore, the evaluation of spot welding quality of high-strength steel is a technical problem that needs to be solved urgently

At the same time, it is difficult to accurately evaluate the quality of solder joints by traditionally extracting single solder joint status information, while the feature extraction method based on electrode indentation images has the advantages of easy acquisition, stable feature changes, and the ability to simultaneously extract multiple features on the surface of electrodes and solder joints.

Images