Bearing Fault Diagnosis Using Grad-CAM and Acoustic Emission Signals

Abstract

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. of convolutional neural network (CNN) and DNN-based approaches. From these papers we could conclude that the CNN-based techniques are much better than DNN-based methods in terms of fault diagnosis performance [3,12,15,16]. Although DNN or CNN-based methods have achieved high classification accuracy, there are still two issues that must be resolved to make these methods highly applicable to real applications. The first issue is that the trained neural network, in general, can be only reliable on the specific machine since the patterns of the raw signals strongly depend on the operating conditions of the machinery such as load, installation, external vibration, etc. The second concern is that the trained feature representation is uninterpretable due to the black box-like operation of the neural networks.This paper proposes a new CNN-based rolling element bearing fault diagnosis approach to resolve the aforementioned problems. To address the first issue, the proposed method utilizes the normalized bearing characteristic components (NBCC) as the input data of CNN rather than raw AE signal itself. Since the bearing characteristic frequencies are induced by appearing bearing failures, NBCC is a more effective representation for diagnosing the bearing failure symptoms. To resolve the second issue, this paper applies the gradient-weighted class activation mapping (Grad-CAM) to visualize important regions in NBCC. According to the literature, Grad-CAM is a promising method that provides visual explanations of the classification result of a CNN in object detection and recognition [17].The remainder of this paper is organized as follows. Section 2 introduces the proposed methodology for diagnosing rolling element bearing faults using AE signals. In Section 3 the bearing fault simulator used for collecting AE signals is presented. The fault diagnosis results demonstrated and discussed in Section 4. Finally, Section 5 contains the concluding remarks. Proposed...

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

“…Thus, to increase the depth of the network architecture for better learning of the parameters, several convolutions and pooling layers are stacked together. Finally, the outputs of these layers are flattened and connected with some fully connected layers, which alter the resultant matrix into columns [ 54 , 55 ]. The last fully connected layer is denoted as the output layer, from which the output probability is obtained by using activation functions.…”

VODCA: Verification of Diagnosis Using CAM-Based Approach for Explainable Process Monitoring

“…Moreover, the CAM and Grad-CAM have been used in several fields to improve the explanatory power of deep-learning models. In addition, in FDD, the CAM or Grad-CAM can be used for a visual explanation [8].…”

“…Among them, representative methods are the Class Activation Map (CAM) [6] proposed in the convolutional neural network (CNN)-based architecture and attention mechanism [7]. By means of these methods, studies to explain the decisions made by deep-learning models are being conducted in various applications, and studies for fault diagnosis are also being proposed in manufacturing applications [8].…”

Novel Bearing Fault Diagnosis Using Gaussian Mixture Model-Based Fault Band Selection

“…A major advantage of MSCA is that it does not require mounting external sensors for data collection. Another type of data, Acoustic Emission (AE), has been receiving attention due to its ability to detect low-energy signals from low rotation speed bearings with early-stage failure; however, usage of AE data requires working with tremendous amounts of data, which requires a lot of time and computational resources for analysis [ 18 ]. Audible sound data have an advantage in collection simplicity due to noncontact sensor installation and are used in research works by Nakamura et al [ 19 ] and Lu et al [ 20 ].…”