Main speed reducer multi-fault intelligent diagnosis method based on multi-channel data deep mining

Abstract

The invention discloses a main speed reducer multi-fault intelligent diagnosis method based on multi-channel data deep mining, and the method comprises the steps: obtaining a vibration signal of a main speed reducer through a multi-channel sensor, and carrying out the noise reduction of the vibration signal through the combination of a wavelet contraction noise reduction method and a structured sparse method; based on the vibration signal after noise reduction processing, adopting a deep belief network to perform multi-channel deep feature extraction, and fusing multi-channel deep features; and based on a deep feature fusion result, performing online state monitoring and multi-fault intelligent diagnosis on the main speed reducer by adopting a sparse Bayesian extreme learning machine. According to the invention, single-fault and multi-fault modes can be identified at the same time, and quantitative analysis of state monitoring and intelligent fault diagnosis of the main speed reducer is realized.

Description

Technical field [0001] The present invention relates to the technical field of the main reducer fault diagnosis, particularly to a multi-channel data based on the final drive mining depth Multiple Fault diagnosis intelligent. Background technique [0002] As a core component of automobile axle drive system, the status and performance of the final drive has an important impact on vehicle safety, comfort and reliability. Based on this, the car online final drive status monitoring and fault pattern recognition for the protection of vehicle safety, ensure reliable operation and avoid a catastrophic accident is significant. [0003] At present, many domestic and foreign research institutions to carry out research of mechanical fault diagnosis based on vibration signal to obtain reliable sensing data, aspects of vibration signal preprocessing and feature extraction and intelligent recognition failure mode has made a large number of research results . Wuhan University of Technology Tsu ...

AI Technical Summary

Problems solved by technology

[0004] As a research branch of mechanical fault diagnosis, the fault diagnosis of the main reducer of the rear axle of the automobile was mainly conducted by experienced engineers or maintenance personnel in the early stage, according to the sound signal generated by the gear pair meshing inside the main reducer. Judging the operating status, this technology is highly subjective and is easily affected by the noise in the surrounding noisy environment, thus giving wrong diagnostic results

Judging from the research content of domestic and foreign researchers, the existing research mainly revolves around the analysis of the vibration signal of the rear axle main drive, but the research on the multi-fault diagnosis technology for the main drive is not rich, and there are some problems that need to be solved urgently. The key question:

[0007] 2) The utilization rate of multi-channel sensing data is low

[0009] 3) The research on multi-fault mode recognition is relatively weak

[0010] Due to the complex internal assembly of the main reducer, multiple failure modes usually occur simultaneously or cascade before and after, and there is a strong coupling between the failure modes, which increases the difficulty of fault identification

Images