Non-Mutually Exclusive Deep Neural Network Classifier for Combined Modes of Bearing Fault Diagnosis

Abstract

The simultaneous occurrence of various types of defects in bearings makes their diagnosis more challenging owing to the resultant complexity of the constituent parts of the acoustic emission (AE) signals. To address this issue, a new approach is proposed in this paper for the detection of multiple combined faults in bearings. The proposed methodology uses a deep neural network (DNN) architecture to effectively diagnose the combined defects. The DNN structure is based on the stacked denoising autoencoder non-mutually exclusive classifier (NMEC) method for combined modes. The NMEC-DNN is trained using data for a single fault and it classifies both single faults and multiple combined faults. The results of experiments conducted on AE data collected through an experimental test-bed demonstrate that the DNN achieves good classification performance with a maximum accuracy of 95%. The proposed method is compared with a multi-class classifier based on support vector machines (SVMs). The NMEC-DNN yields better diagnostic performance in comparison to the multi-class classifier based on SVM. The NMEC-DNN reduces the number of necessary data collections and improves the bearing fault diagnosis performance.

A Multitask-Aided Transfer Learning-Based Diagnostic Framework for Bearings under Inconsistent Working Conditions

“…Specifically, when using popular feature extraction methods that analyze features from the time domain, frequency domain, or time-frequency domain, it is very difficult to identify the fault characteristics under variable working conditions [ 15 , 16 , 17 , 18 , 19 , 20 ]. Therefore, research on new and effective methods for the condition monitoring of rolling element bearings has become a challenging and valuable task [ 21 , 22 , 23 , 24 ].…”

Bearing Fault Diagnosis under Variable Rotational Speeds Using Stockwell Transform-Based Vibration Imaging and Transfer Learning

“…These fault diagnosis studies have shown that diagnosis of bearing wear can reduce maintenance expenses and enhance machine reliability [6,[12][13][14][15][16]. Bearing fault diagnosis studies have extensively investigated vibration signals and motor current analysis [17,18]. Multiple signature analysis of vibrations and motor currents has also been researched to improve reliability [19].…”

“…Primarily, bearing faults occur due to localized imperfections, i.e., cracks or spalls. These flaws create shocks and stimulate high-occurrence reverberations of the bearings and machine assembly due to the recurring effect on spinning parts [17]. Time-frequency signal analysis approaches have been employed to solve these issues, such as fast Fourier transform (FFT) and short-term-Fourier transform (STFT), which convert time-domain signals into frequency-domain signals for further analysis [20].…”

“…From these 2D images, the feature selection process is automated by employing a transfer learning (TL)-based convolutional neural network (CNN). Conventional, straightforward neural networks make the feature selection process much easier through their convoluted encoding layers compared to traditional methods [17,31,32]. In [33], Zheng et al introduced a TL-based artificial neural network (ANN) for a bearing's raw vibration signals.…”

A Reliable Health Indicator for Fault Prognosis of Bearings

“…Generally, this involves condition monitoring using appropriate sensors, assessment of the current health status of the machines and predicting their future health by analyzing acquired measurement data, and utilization of this knowledge to improve the overall reliability and availability of the machines [ 1 , 2 , 3 , 4 , 5 , 6 , 7 , 8 , 9 ]. Rolling element bearings are among the most significant contributors to the failure of critical industrial equipment, such as induction motors [ 10 , 11 ]. Consequently, they have received considerable research attention [ 2 , 3 , 4 , 5 , 7 , 8 , 12 , 13 ].…”