An intelligent fault diagnosis framework based on piecewise aggregate approximation, statistical moments, and sparse autoencoder

Abstract

Rotating machines (RMs) have vast applicability in almost all the industries in mechanical domain. Rolling element bearings (RBs) are the key elements to ensure that the RMs perform efficiently. RBs are highly prone to wear and tear which could have devastating consequences such as massive economic losses and accidents. In the past, many time-domain based condition-indicators such as root mean square (RMS), skewness and kurtosis, etc. have been proposed by researchers to diagnose the bearing faults and prevent RM failures. However, they are often insensitive to early stage faults, affected by outliers and possess poor degradation tracking characteristics. To overcome these shortcomings, this paper proposes a novel statistical feature extraction technique called as multiscale statistical moment (MSM) analysis, in combination with sparse autoencoder to detect the incipient faults as well as track the progression of wear. Firstly, the vibration signal are acquired from the bearings to be monitored. Secondly, the MSM features are extracted from the vibration signals. Thirdly, the MSM features corresponding to normal conditions are utilized to train the sparse autoencoder network. Fourthly, the MSM features corresponding to test conditions are supplied to the pre-trained sparse autoencoder model. The MSM technique offers the advantage that it extracts the fault properties contained in multiple time-scales of the vibration signals instead of a single time-scale only. Finally, the dissimilarity between the actual and predicted output is measured to obtain the bearing health indicator (BHI). The experimental results demonstrate that the suggested BHI detects the faults at early stages, possess better sensitivity and trends the bearing degradation more accurately as compared to the traditional techniques such as RMS, kurtosis, and BHI obtained with statistical moment features at single-scale only.

Gear fault diagnosis based on complex network theory and error-correcting output codes: Multi class support vector machine

“…While training, the hyperparameters (P and s) of the ECOC-MSVM model are tuned using 10-fold cross-validation. The objective function is set to the classification error measure given by equation (15). The tuning process ends when the lowest cross-validation classification error is achieved.…”

“…Although these methods have been used extensively in recognizing the gear faults, each of them suffers from one or other demerit such as low sensitivity to premature faults, inherent stationary nature, requirement of prior fault knowledge, need to predefine analytical functions and spectral smearing. [13][14][15] Thus, continuous innovation and development of new fault feature extraction techniques becomes a prerequisite to further improve the fault diagnosis accuracy.…”