Bearing failure generates impulses when the rolling elements pass the cracked surface of the bearing. Over the past decade, acoustic emission (AE) techniques have been used to detect bearing failures operated in low-rotating speeds. However, since the high sampling rates of the AE signals make it difficult to design and extract discriminative fault features, deep neural network-based approaches have been proposed in several recent studies. This paper proposes a convolutional neural network (CNN)-based bearing fault diagnosis technique. In this work, the normalized bearing characteristic component (NBCC) is used as the input of CNN, which is an effective form of representing bearing failure symptoms. In addition, importance-weight is extracted using gradient-weighted class activation mapping (Grad-CAM) for visual explanation of CNN. In the experiment result, the proposed approach achieves high classification accuracy with reasonable visualization, which shows that CNN successfully learned the components of bearing characteristic frequency for each type of bearing failure.

This paper presents a novel method for diagnosing incipient bearing defects under variable operating speeds using convolutional neural networks (CNNs) trained via the stochastic diagonal Levenberg-Marquardt (S-DLM) algorithm. The CNNs utilize the spectral energy maps (SEMs) of the acoustic emission (AE) signals as inputs and automatically learn the optimal features, which yield the best discriminative models for diagnosing incipient bearing defects under variable operating speeds. The SEMs are two-dimensional maps that show the distribution of energy across different bands of the AE spectrum. It is hypothesized that the variation of a bearing’s speed would not alter the overall shape of the AE spectrum rather, it may only scale and translate it. Thus, at different speeds, the same defect would yield SEMs that are scaled and shifted versions of each other. This hypothesis is confirmed by the experimental results, where CNNs trained using the S-DLM algorithm yield significantly better diagnostic performance under variable operating speeds compared to existing methods. In this work, the performance of different training algorithms is also evaluated to select the best training algorithm for the CNNs. The proposed method is used to diagnose both single and compound defects at six different operating speeds.

Spherical storage tanks are used in various industries to store substances like gasoline, oxygen, waste water, and liquefied petroleum gas (LPG). Cracks in the storage tanks are unaccepted defects, as storage tanks can leak or spill the contained substance through these cracks. Leakage from contained hazardous substances storage tanks can contaminate the environment and may lead to fatal accidents. Therefore, the ability to detect cracks from spherical storage tanks is necessary to avoid damage to the environment and to ensure public safety. In this paper, we present a crack detection case study of a spherical tank. The detection was performed using time-domain statistical features and a machine learning algorithm. The proposed method consists of (1) extraction of statistical features from the acoustic emissions (AE) acquired from the spherical tank, and (2) classification of the nonlinear data using a support vector machine (SVM). We evaluate the proposed algorithm with AE data obtained from the spherical tank, demonstrating that the algorithm effectively discriminates between normal and crack conditions. These results show that the proposed algorithm is effective for detecting cracks in spherical storage tanks.

Pressure vessels (PV) are designed to hold liquids, gases, or vapors at high pressures in various industries, but a ruptured pressure vessel can be incredibly dangerous if cracks are not detected in the early stage. This paper proposes a robust crack identification technique for pressure vessels using genetic algorithm (GA)-based feature selection and a deep neural network (DNN) in an acoustic emission (AE) examination. First, hybrid features are extracted from multiple AE sensors that represent diverse symptoms of pressure vessel faults. These features stem from various signal processing domains, such as the time domain, frequency domain, and time-frequency domain. Heterogenous features from various channels ensure a robust feature extraction process but are high-dimensional, so may contain irrelevant and redundant features. This can cause a degraded classification performance. Therefore, we use GA with a new objective function to select the most discriminant features that are highly effective for the DNN classifier when identifying crack types. The potency of the proposed method (GA + DNN) is demonstrated using AE data obtained from a self-designed pressure vessel. The experimental results indicate that the proposed method is highly effective at selecting discriminant features. These features are used as the input of the DNN classifier, achieving a 94.67% classification accuracy.

A new method is established to construct the 2-D fault diagnosis representation of multiple bearing defects from 1-D acoustic emission signals. This technique starts by applying envelope analysis to extract the envelope signal. A novel strategy is propounded for the deployment of the continuous wavelet transform with damage frequency band information to generate the defect signature wavelet image (DSWI), which describes the acoustic emission signal in time-frequency-domain, reduces the nonstationary effect in the signal, shows discriminate pattern visualization for different types of faults, and associates with the defect signature of bearing faults. Using the resultant DSWI, the deep convolution neural network (DCNN) architecture is designed to identify the fault in the bearing. To evaluate the proposed algorithm, the performance of this technique is scrutinized by a series of experimental tests acquired from a self-designed testbed and corresponding to different bearing conditions. The performance from the experimental dataset demonstrates that the suggested methodology outperforms conventional approaches in terms of classification accuracy. The result of combining the DCNN with DSWI input yields an accuracy of 98.79% for classifying multiple bearing defects.

Incipient defects in bearings are traditionally diagnosed either by developing discriminative models for features that are extracted from raw acoustic emission (AE) signals, or by detecting peaks at characteristic defect frequencies in the envelope power spectrum of the AE signals. Under variable speed conditions, however, such methods do not yield the best results. This letter proposes a technique for diagnosing incipient bearing defects under variable speed conditions, by extracting features from different sub-bands of the inherently non-stationary AE signal, and then classifying bearing defects using a weighted committee machine, which is an ensemble of support vector machines and artificial neural networks. The proposed method also improves the generalization performance of the neural networks to enhance their classification accuracy, particularly with limited training data.