Gear fault monitoring based on unsupervised feature dimensional reduction and optimized LSSVM-BSOA machine learning model

Abstract

In the trend of Industry 4.0 development, the big data of system operation is significant for analyzing, predicting, or identifying any possible problem. This study proposes a new diagnosis technique for identifying the vibration signal, which combines the feature dimensional reduction method and optimized classifier. Firstly, an auto-encoder feature dimensional reduction (AE-FDR) method is constructed with the bottleneck hidden layer to extract the low-dimensional feature. Secondly, a supervised classifier is formed to carry out fine-turning and classification. The least square-support vector machine (LSSVM) classifier is used as basic with an optimized parameter exploited by the backtracking search optimisation algorithm (BSOA). This LSSVM-BSOA is used to identify the gear fault based on the original vibration data. The proposed AE-FDR-LSSVM-BSOA diagnosis technique shows good ability for identifying the gear fault. A helical gear is experimented with three fault status for evaluate this method. The diagnosis result achieves a high accuracy of 93.3%.

Planetary gearbox fault diagnosis based on FDKNN-DGAT with few labeled data

“…Planetary gearbox failure sample data as a one-dimensional vibration signal. Since the fault samples are sparse and the original vibration signal is more complex and contains faultindependent information such as noise, the fast Fourier transform (FFT) [32] is used to transform the original signal into spectral samples and reduce the overall computational cost of the model. The transformed samples are used as graph nodes to construct the KNN graph and determine the adjacency matrix A.…”