Rolling-Element Bearing Fault Diagnosis Using Advanced Machine Learning-Based Observer

Abstract

Rotating machines represent a class of nonlinear, uncertain, and multiple-degrees-of-freedom systems that are used in various applications. The complexity of the system’s dynamic behavior and uncertainty result in substantial challenges for fault estimation, detection, and identification in rotating machines. To address the aforementioned challenges, this paper proposes a novel technique for fault diagnosis of a rolling-element bearing (REB), founded on a machine-learning-based advanced fuzzy sliding mode observer. First, an ARX-Laguerre algorithm is presented to model the bearing in the presence of noise and uncertainty. In addition, a fuzzy algorithm is applied to the ARX-Laguerre technique to increase the system’s modeling accuracy. Next, the conventional sliding mode observer is applied to resolve the problems of fault estimation in a complex system with a high degree of uncertainty, such as rotating machinery. To address the problem of chattering that is inherent in the conventional sliding mode observer, the higher-order super-twisting (advanced) technique is introduced in this study. In addition, the fuzzy method is applied to the advanced sliding mode observer to improve the accuracy of fault estimation in uncertain conditions. As a result, the advanced fuzzy sliding mode observer adaptively improves the reliability, robustness, and estimation accuracy of rolling-element bearing fault estimation. Then, the residual signal delivered by the proposed methodology is split in the windows and each window is characterized by a numerical parameter. Finally, a machine learning technique, called a decision tree, adaptively derives the threshold values that are used for problems of fault detection and fault identification in this study. The effectiveness of the proposed algorithm is validated using a publicly available vibration dataset of Case Western Reverse University. The experimental results show that the machine learning-based advanced fuzzy sliding mode observation methodology significantly improves the reliability and accuracy of the fault estimation, detection, and identification of rolling element bearing faults under variable crack sizes and load conditions.

Deep Learning-Based Adaptive Neural-Fuzzy Structure Scheme for Bearing Fault Pattern Recognition and Crack Size Identification

“…The challenge of vibration signal modeling can be addressed by the mathematical-based system modeling five degrees of freedom vibration bearing modeling. Mathematical-based system modeling (such as five degrees of freedom vibration bearing modeling) is reliable but has some drawbacks, such as the lack of complexity and uncertainty related to modeling [ 13 , 14 , 15 ]. Linear-based system identification techniques (such as the combination of autoregressive with external inputs, and autoregressive with external inputs and Laguerre technique) have been used to address the above challenges [ 15 , 16 , 17 , 18 , 19 ].…”

“…The variable structure technique is a robust observer for signal estimation. Based on Equations (13) and (14), and [ 14 ], the state-space equation for variable structure observer is defined using the following equations. …”

“…To detect anomalies using the model-based technique, modeling is the critical step. System modeling is categorized into two principal groups: (a) mathematical-based system modeling, such as Newton–Euler, Lagrange, and finite element methods, and (b) system identification approaches, such as autoregressive (AR), autoregressive with external input (ARX), ARX–Laguerre techniques, neural network approach, and fuzzy logic methods [ 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 ]. To improve the accuracy of signal approximation in nonlinear and nonstationary signals, we propose a combination of autoregressive techniques, namely the Laguerre technique with support vector regression (SVR), which will henceforth be called the support vector autoregressive–Laguerre (SVAL).…”

A Deep Neural Network-Based Feature Fusion for Bearing Fault Diagnosis

“…Presently, among existing methods, the intelligent signal-based fault diagnosis is considered to be the most popular approach. In this approach, the task of signal-based fault diagnosis is treated as a pattern classification problem, which consists of four main steps: signal acquisition, feature extraction, feature selection, and feature classification [2]. In the first step, signals are measured by different types of sensors attached to the machine.…”

A Low-Cost, Small-Size, and Bluetooth-Connected Module to Detect Faults in Rolling Bearings

“…A comprehensive review of such processing methods can be found in [2][3][4]. More recently, approaches based on machine learning, as those shown in [5], were applied to a vibration dataset in order to identify faulty bearings. Further investigations on such topics regard the enhancement of the fault detection in the presence of noise, as in [6][7][8].…”