Laser welding method and device and storage medium thereof

Abstract

The invention discloses a laser welding method and device and a storage medium thereof. The method comprises the steps that a bad factor sample set in the laser welding process is collected as a target data set; an existing sample set with the highest similarity with the target data set is determined as a source data set; pre-training is continuously conducted on a deep learning model by using thesource data set to obtain a first pre-training model; structure adjustment is performed on the first pre-training model by using the target data set to obtain a second pre-training model; and parameters of the first pre-training model are migrated to the second pre-training model to obtain a final model. The source data set which has the highest similarity with and is matched with the target dataset can be confirmed, and negative migration is avoided; and the defect that a small amount of sample data is prone to over-fitting is overcome in a transfer learning mode, and the model convergencespeed is increased.

Description

technical field [0001] The invention relates to the field of laser welding, in particular to a laser welding method, device and storage medium thereof. Background technique [0002] Laser welding technology is widely and deeply used in the fields of aerospace, automobile manufacturing and consumer electronics. However, there are various unfavorable factors in the laser welding process, such as material surface impurities and wear, wrong process parameters, human error factors, etc. The appearance of unfavorable factors will lead to continuous defects with a high probability. The laser welding process is accompanied by the release of a large number of sound, light, electricity, and heat signals. Depending on a variety of sensors, the monitoring of this series of signals can be realized. In the monitoring process, the use of deep learning technology can establish the correlation between signal strength changes and various adverse factors. Deep learning technology requires a ...

AI Technical Summary

Problems solved by technology

Deep learning technology requires a large amount of sample data to achieve better performance, but in some laser welding processing environments, the collection of sample data is very difficult, and it is necessary to resort to manual sampling and destructive collection methods to achieve collection of bad samples , the acquisition of bad samples always requires a lot of manpower and cost, which makes it difficult to obtain a large number of sample data

In the case of relatively small sample data, the monitoring effect of existing deep learning models for laser welding will be greatly limited

Images