A Comparative Study between Machine Learning Algorithm and Artificial Intelligence Neural Network in Detecting Minor Bearing Fault of Induction Motors

Abstract

Most of the mechanical systems in industries are made to run through induction motors (IM). To maintain the performance of the IM, earlier detection of minor fault and continuous monitoring (CM) are required. Among IM faults, bearing faults are considered as indispensable because of its high probability incidence nature. CM mainly depends upon signal processing and fault detection techniques. In recent decades, various methods have been involved in detecting the bearing fault using machine learning (ML) algorithms. Additionally, the role of artificial intelligence (AI), a growing technology, has also been used in fault diagnosis of IM. Taking the necessity of minor fault detection and the detailed study about the role of ML and AI to detect the bearing fault, the present study is performed. A comprehensive study is conducted by considering various diagnosis methods from ML and AI for detecting a minor bearing fault (hole and scratch). This study helps in understanding the difference between the diagnosis approach and their effectiveness in detecting an IM bearing fault. It is accomplished through FFT (fast Fourier transform) analysis of the load current and the extracted features are used to train the algorithm. The application is extended by comparing the result of ML and AI, and then explaining the specific purpose of use.

Induction machine stator short-circuit fault detection using support vector machine

“…In particular, thanks to advancements in machine learning algorithms (MLAs), the automatic diagnosis has made considerable progress in IMFD (Filippetti et al, 2000;Siddique et al, 2003;Choudhary et al, 2019;Liu et al, 2018;Esakimuthu Pandarakone et al, 2019;Ali et al, 2019;Martin-Diaz et al, 2018). The most widely used MLAs in IMFD are the following: support vector machines (SVMs) (Konar and Chattopadhyay, 2011;Widodo and Yang, 2007;Esakimuthu Pandarakone et al, 2019;Ali et al, 2019;Martin-Diaz et al, 2018), adaptive neural fuzzy inference system (ANFIS) (Ballal et al, 2007), fuzzy logic (Rodríguez et al, 2008), artificial neural networks (ANNs) (Bouzid et al, 2008;Esakimuthu Pandarakone et al, 2019;Glowacz and Glowacz, 2017;Martin-Diaz et al, 2018), genetic algorithms (Razik, de Rossiter Correa and Da Silva, 2009), extreme learning machine (ELM) (Coelho et al, 2014) and K-nearest neighbors (KNN) (Ali et al, 2019;Esakimuthu Pandarakone et al, 2019;Glowacz and Glowacz, 2017;Martin-Diaz et al, 2018). The main advantage of MLAs is that no mathematical model is needed for the system monitoring.…”

Deep learning and reinforcement learning approach on microgrid

“…The bearing fault analysis is carried out by fast Fourier transform (FFT) to train the DL algorithm using a feature extraction technique in load current. 91 The fault section is estimated in paper 92 using neural network models. Collective information on protective devices and circuit breakers helps to analysis.…”

“…The bearing is analyzed by vibration frequency in a motor using a neural network to predict fault. The bearing fault analysis is carried out by fast Fourier transform (FFT) to train the DL algorithm using a feature extraction technique in load current 91 . The fault section is estimated in paper 92 using neural network models.…”

Rotating blade faults classification of a rotor-disk-blade system using artificial neural network

“…In addition to the application of ANN to diagnose specific rotating machine faults, some previous works are reported here identifying rotor-bearing system faults using multi-layer BP neural network [18], rolling element bearing faults using time-domain features in ANN [19], minor faults such as scratch and hole in the bearings of induction motors using five machine learning algorithms and convolutional neural network [20], and compound bearing defects such as inner race, outer race and roller defect for embedded systems under varying rotational speeds using MobileNet-v2; a light state-of-the-art convolutional neural network model [21]. In addition, two articles related to rotating shafts addressed the the detection of ball bearing faults producing vibrations in Rotating shafts using multi-layer feed forward neural network [22] and induction motor shaft misalignments using multi-scale entropy (MSE) coupled with back-propagation neural network [23].…”