Motor Bearing Fault Detection Research Articles

A computationally efficient method for induction motor bearing fault detection based on parallel convolutions and semi-supervised GAN

ABSTRACT Accurate and timely bearing fault detection is imperative for optimal system functioning and the implementation of preventative maintenance measures. Deep learning models provide viable solutions to these malfunctions, however, the lack of labelled data makes the training both expensive and cumbersome. To remedy this, various semi-supervised approaches have surfaced in the last decade, significantly mitigating the need for extensive labelled data but with added computational cost. This study proposes one such approach by leveraging generative adversarial networks (GAN) trained on a time-frequency based representation. The proposed Parallel Convolutions Semi-Supervised GAN, namely PC-SSGAN, uses bottleneck parallel convolutions blocks to capture multi-scale features in both local and global contexts, lacing both the generator and discriminator with enhanced feature extraction capabilities and simultaneously reducing the parameters and training time. The Proposed framework is evaluated on two distinct open-source datasets. The classification accuracy for both models exceeded 99.50%. Moreover, the proposed parallel convolutions-based architecture spent approximately 33% less time on training than the normal convolutional layers. It has been foreseen that the proposed fault detection system can be integrated into the motor fault tolerant control system to produce a unified framework that can make informed decisions to handle the bearing faults effectively.

Multidomain Features-Based GA Optimized Artificial Immune System for Bearing Fault Detection

This paper proposes a novel multidomain features-based genetic algorithm (GA) optimized artificial immune system (AIS) framework for fault detection in real systems. Different from native real-valued negative selection algorithm (RNSA) that operates in original data space, this algorithm utilizes feature space transformation and diversity factor-based GA for optimized detector distribution in nonself feature space. The proposed framework comprises three stages namely; feature extraction, unsupervised feature selection, and GA optimized AIS. In the first stage, signal processing methods are applied to extract multidomain features (time-domain statistical, frequency domain statistical, and special features) of the system. In the second stage, two unsupervised methods namely, ${k}$ -NN clustering and pretraining using deep learning neural network are proposed for dominant fault-characterizing feature selection. Finally, in the third stage, the fault-characterizing feature vectors are used for system status categorization (i.e., normal, fault) using selected (fault-characterizing) features-based AIS method. The efficacy of the proposed framework is verified through experiments on motor bearing fault detection using vibration signal. The major accomplishment of the proposed combination of space transformation, feature selection and AIS (anomaly classification) techniques is the alleviation of computational burden on RNSA implementation. Moreover, GA optimized AIS fault diagnosis based on well-established features gives improved detection performance.

Motor Bearing Fault Detection Using Spectral Kurtosis-Based Feature Extraction Coupled With K-Nearest Neighbor Distance Analysis

Bearing faults are the main contributors to the failure of electric motors. Although a number of vibration analysis methods have been developed for the detection of bearing faults, false alarms still result in losses. This paper presents a method that detects bearing faults and monitors the degradation of bearings in electric motors. Based on spectral kurtosis (SK) and cross correlation, the method extracts fault features that represent different faults, and the features are then combined to form a health index using principal component analysis (PCA) and a semisupervised k-nearest neighbor (KNN) distance measure. The method was validated by experiments using a machinery fault simulator and a computer cooling fan motor bearing. The method is able to detect incipient faults and diagnose the locations of faults under masking noise. It also provides a health index that tracks the degradation of faults without missing intermittent faults. Moreover, faulty reference data are not required.

Periodic Sparsity Oriented Super-wavelet Analysis with Application to Motor Bearing Fault Detection of Wind Turbine

Periodic Sparsity Oriented Super-wavelet Analysis with Application to Motor Bearing Fault Detection of Wind Turbine

A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM

This paper presents a novel hybrid model for fault detection and classification of motor bearing. In the proposed model, permutation entropy (PE) of the vibration signal is calculated to detect the malfunctions of the bearing. If the bearing has faults, the vibration signal is decomposed into a set of intrinsic mode functions (IMFs) by ensemble empirical mode decomposition (EEMD). The PE values of the first several IMFs (IMF-PE) are calculate to reveal the multi-scale intrinsic characteristics of the vibration signal. Then, support vector machines (SVM) optimized by inter-cluster distance (ICD) in the feature space (ICDSVM) is used to classify the fault type as well as fault severity. Finally, the proposed model is fully evaluated by experiments and comparative studies. The results demonstrate its effectiveness and robustness for motor bearing fault detection and classification.

Recent Patents on Fault Pattern Recognition for Motor Bearing by Multi-layer Relevance Vector Machine Classifier

Fault diagnosis for motor bearing has a great economic and social significance, the patents on motor bearing fault detection and diagnosis method have been presented in the past years. However, there are some shortcomings including local extremum or over-fitting in the fault diagnosis method of these patents. Relevance vector machine (RVM), requires much fewer kernel functions compared with support vector machine (SVM), and provides the posterior distributions rather than just a point estimate. Thus, fault pattern recognition for motor bearing based on multi-layer RVM classifier was proposed in the paper, and two multi-class combination patterns of RVM classifiers including ‘binary tree’ and ‘one-against-one’ were used, among which ‘binary tree’ pattern is used to distinguish the fault state from the normal state, ‘one-against-one’ pattern was used to recognize the fault types. The fault pattern recognition results for motor bearing among RVM classifier, SVM classifier and RBF neural network (ANN) classifier were analyzed, and the experimental results indicate that RVM classifier has the better fault pattern recognition ability than SVM classifier or RBFNN classifier. Keywords: fault diagnosis, multi-class combination pattern, motor bearing, pattern recognition, RVM.

Stator Current-Based Locomotive Traction Motor Bearing Fault Detection

Rolling-element bearings are critical components in locomotive traction motors. A reliable online bearing fault-diagnostic technique is critically needed to prevent motor systems performance degradation and malfunction. Motor bearing failure induces vibration, resulting in the modulation of the stator current. Compared with conventional monitoring techniques such as vibration monitoring or temperature monitoring, stator current-based monitoring offers significant economic benefits and implementation advantages. In this paper, a novel approach to locomotive traction motor current signature analysis based on wavelet packet decomposition (WPD) of stator current is presented. The effectiveness and practicability of the proposed method is verified by locomotive running tests.

Asynchronous Motor Bearing Fault Detection Methods

Bearing, asynchronous deep groove ball bearings are widely used in induction motor field. Motor bearing failure probability is as high as 40% in asynchronous motor. It accounts for the largest proportion of failures in the motor. Therefore, people have been on studying motor bearing fault detection methods for further research. So far, people have studied a variety of modern detection methods.

Diagnosis Tool for Motor Condition Monitoring

In the modern industrial environment there is increasing demand for automatic condition monitoring. With reliable condition monitoring, faults such as mechanical motor failures could be identified in their early stages and further damage to the system could be prevented. Successful monitoring is a complex and application-specific problem, but a generic tool would be useful in preliminary analysis of new signals and in verification of known theories. A generic condition diagnosis tool is introduced in this paper. The tool is based on discriminative energy functions which reveal discriminative frequency-domain regions where failures can be identified. The tool was applied to induction motor bearing fault detection and succeeded in finding characteristic frequencies which allow accurate detection of bearing faults.