Laser welding process monitoring method and system based on multi-source data fusion and medium

The invention belongs to the technical field of laser welding, and particularly relates to a laser welding process monitoring method and system based on multi-source data fusion, and the method comprises the following steps: S1, obtaining multi-source data obtained by collecting multi-source signals in the laser welding process by multiple types of sensors; s2, performing preprocessing and feature extraction on the multi-source data to obtain feature data of laser welding; s3, a neural network algorithm is applied to the feature data to calculate monitoring results and probability distribution corresponding to each type of sensors; s4, probability distribution and a monitoring result of the fused multi-source data are calculated through a fusion decision algorithm so as to evaluate the welding quality in the laser welding process, and a welding seam image is output; according to the method, feature analysis is carried out on data collected by different types of sensors respectively, feature analysis results a