A Fault Diagnosis Method for Switching Power Supply of Medical Electronic Equipment Based on Multidimensional Feature Fusion

Abstract

The invention relates to a fault diagnosis method for a switching power supply of medical electronic equipment based on multi-dimensional feature fusion, and belongs to the field of fault diagnosis of medical electronic equipment. This method uses a multi-channel data acquisition card to collect the electrical signal data of multiple key test points of the switching power supply of medical electronic equipment under different fault states, and then uses a one-dimensional convolutional neural network and a bidirectional long-short-term memory network to extract the spatial dimension and time dimension respectively. Different features, and different dimensional features are fused by adding equal-scale feature maps to establish a multi-dimensional feature fusion fault diagnosis model. Finally, the Adam algorithm is used to optimize the model parameters to realize chip-level fault intelligence for medical electronic equipment switching power supplies without drawings. diagnosis. The invention effectively overcomes the one-sidedness brought by a single feature to the fault diagnosis result, can accurately identify various common fault types of switching power supplies, and has an accuracy rate better than that of a fault diagnosis method based on a single feature.

Description

technical field [0001] The invention belongs to the field of fault diagnosis of medical electronic equipment, and relates to a fault diagnosis method for switching power supply of medical electronic equipment based on multi-dimensional feature fusion. Background technique [0002] Whether medical electronic equipment can exert its maximum performance is not only directly related to its own technical performance, but also has an extremely important relationship with the quality of power supply. Because the switching power supply is subjected to high voltage and strong current impact for a long time, it causes frequent failures. At the same time, the manufacturer no longer provides detailed circuit diagrams and other information in order to obtain maintenance profits, which makes the maintenance of switching power supplies difficult and expensive. At present, the method based on machine learning has been widely used in the field of fault diagnosis, but there are still some def...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the purpose of the present invention is to provide a deep learning-based fault diagnosis method for switching power supplies of medical electronic equipment without drawings, which does not need to manually extract the electrical signal characteristics of switching power supplies, automatically completes end-to-end chip-level fault diagnosis, and effectively solves the problem of medical electronics. Due to frequent failures and lack of information such as drawings, the switching power supply of equipment is difficult and expensive to maintain

Images