An aero-generator fault feature extraction method based on iSDAE

Abstract

The invention discloses an aero-generator fault feature extraction method based on iSDAE (improved Stacked Denoising Auto-Encoderes), and is mainly to solve the problem of not high diagnosis accuracy since the existing fault diagnosis technology is limited by artificial feature extraction. The method has the following specific steps: 1) fault analysis; 2) data acquisition; 3) data pre-processing; 4) training of the iSDAE (improved Stacked Denoising Auto-Encoderes); and 5) feature output. The method can learn data features automatically and obtains distributed feature representations of original data, has a certain noise immunity and good robustness and effectively improves aero-generator fault diagnosis correct rate.

Description

technical field [0001] The invention relates to an iSDAE (improved Stacked Denoising Autoencoders, improved stack denoising autoencoder)-based method for extracting fault features of an aero-generator, belonging to the technical field of generator state monitoring and fault diagnosis. Background technique [0002] The aviation generator is an important part of the main power supply of the aircraft. It is responsible for providing power for the instruments, meters, radar, lighting, radio communications and various control systems on the aircraft. Failure of any part of the aero-generator will not only affect its normal operation, but also may cause the aircraft to fail to fly normally, and even cause major aviation accidents in severe cases. Therefore, it has extremely important practical significance and huge economic benefits to carry out in-depth research on the fault diagnosis technology of aero-generators, make timely, accurate and rapid judgments on possible faults of a...

AI Technical Summary

Problems solved by technology

However, the current feature extraction methods generally rely on manual extraction, which is time-consuming and labor-intensive, is greatly affected by noise interference, and is not universal. In view of the limitation of manual extraction features in the existing fault diagnosis technology, the diagnostic accuracy is not high. High problem, the present invention proposes an iSDAE-based aviation generator fault feature extraction method, the method can automatically learn the data features, obtain the distributed feature representation of the original data, and has a certain anti-noise ability, has a very Good robustness, effectively improving the accuracy of aircraft generator fault diagnosis

Images