Medical electronic equipment switching power supply fault diagnosis method based on multi-dimensional feature fusion

The invention relates to a medical electronic equipment switching power supply fault diagnosis method based on multi-dimensional feature fusion, and belongs to the field of medical electronic equipment fault diagnosis. The method comprises the steps of acquiring electric signal data of a plurality of key test points of the medical electronic equipment switching power supply in different fault states by using a multi-channel data acquisition card; respectively extracting different features of a spatial dimension and a time dimension by utilizing a one-dimensional convolutional neural network and a bidirectional long-short-term memory network, fusing the features of different dimensions in an equal-proportion feature graph addition mode, establishing a multi-dimensional feature fusion faultdiagnosis model, and finally optimizing model parameters by using an Adam algorithm to realize intelligent drawing-free chip-level fault diagnosis of the medical electronic equipment switching power supply. According to the i