Spot welding nugget quality prediction method and equipment based on multi-factor mapping model

Abstract

The invention provides a spot welding nugget quality prediction method and equipment based on a multi-factor mapping model, and the method comprises the steps: carrying out the standardization processing of an original data set of a body in white through a Z-score method, and obtaining the preprocessing data; performing multi-process feature fusion operation on the preprocessed data to obtain three types of data sets, and performing unified expression on the three types of data sets by using a feature selection method to obtain a fused data set; cutting the fused data set into a training set and a verification set according to a set-aside method; inputting the training set into a plurality of machine learning models for iterative training, completing parameter selection of the corresponding machine learning models in combination with a Bayesian optimization algorithm, and verifying whether the trained corresponding machine learning models meet a selected index threshold value or not on the verification set, thereby determining the optimal machine learning model of multi-factor mapping. And predicting the quality index of the nugget by using the model. According to the method, online feasibility analysis of vehicle body shaping in a welding experiment can be effectively carried out, so that the cost is reduced and the efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of automobile body-in-white welding, in particular to a method and equipment for predicting the quality of spot welding nuggets based on a multi-factor mapping model. Background technique [0002] The body-in-white not only needs to provide passengers with a comfortable riding and driving space, but also needs to ensure the personal safety of passengers in sudden accidents, that is, when road conditions such as collisions and rollovers occur. Therefore, the body-in-white must prioritize impact collisions in the development design. In the four main processes of body-in-white (stamping, welding, painting, and final assembly), welding is mainly to heat and press materials such as castings, stamped sheets, and profiles at points, lines, and surfaces, respectively or at the same time. Then the complete body is completed. Usually, a body-in-white contains about 6,000 solder joints. Therefore, the strength and ser...

AI Technical Summary

Problems solved by technology

With the rapid development of computing hardware, the ability to store and collect data has been greatly enhanced, but the ability to process and analyze data is relatively lacking. Traditional industrial database methods can efficiently add, delete, modify and query data throughout the manufacturing process, but it is difficult to find hidden information, idle information is difficult to effectively use

Images