Partial migration fault diagnosis method based on multi-scale weight selection adversarial network

Abstract

The invention relates to a partial migration fault diagnosis method based on a multi-scale weight selection adversarial network, and belongs to the technical field of mechanical fault diagnosis. The method comprises the following steps: S1, collecting original vibration signals of to-be-tested equipment under different working conditions, expanding a fault sample data set, and dividing the fault sample data set into training samples and test samples; s2, constructing an MDAN by using deep learning; s3, constructing a multi-scale weight selection mechanism; s4, combining a multi-scale weight selection mechanism and the MDAN to construct an MWSAN; s5, inputting the training sample in the step S1 into the constructed MWSAN, and performing iterative optimization training on the MWSAN by using a multi-scale classification loss function and a domain discrimination loss function; and S6, inputting the test sample in the step S1 into the trained MWSAN, and carrying out partial migration fault diagnosis on the to-be-tested equipment. According to the invention, the fault diagnosis precision is improved.

Description

technical field [0001] The invention belongs to the technical field of mechanical fault diagnosis, and relates to a partial migration fault diagnosis method based on a multi-scale weight selection confrontation network. Background technique [0002] In recent years, the development of industry has higher and higher requirements for long-term safe and reliable operation of mechanical equipment. In order to avoid major economic losses and personal injuries, the development and application of fault diagnosis technology has become an important means to improve the safety and stability of mechanical systems. Fault diagnosis technology monitors the operating status of equipment to determine the location of the fault and timely investigate potential safety hazards. Therefore, in order to prevent catastrophic accidents, it is particularly important to strengthen the condition monitoring of mechanical equipment and identify faults in a timely and accurate manner. The health status o...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the purpose of the present invention is to provide a partial migration fault diagnosis method based on multi-scale weight selection confrontation network, combined with multi-scale domain confrontation network structure and multi-scale weight selection mechanism, to solve the problem of partial migration during fault diagnosis of mechanical equipment Diagnose problems, thereby improving the accuracy of fault diagnosis

Images