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

Shrinathan Esakimuthu Pandarakone,Hisahide Nakamura,Yukio Mizuno

doi:10.3390/en12112105

Shrinathan Esakimuthu Pandarakone, Hisahide Nakamura + Show 1 more

Open Access

https://doi.org/10.3390/en12112105

Copy DOI

Journal: Energies	Publication Date: Jun 1, 2019
Citations: 49	License type: CC BY 4.0

Affiliation: Nagoya Institute of Technology

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.

Highlights

In recent decades, induction motor (IM) applications have been extended to various fields in industry due to their numerous advantages, such as low cost, less maintenance, simple and robust construction, high efficiency with good reliability in operation than any other motors available
Many studies [3,4] keep on suggesting the importance of condition monitoring (CM) and fault diagnosis of IM, which is more recommended to avoid the production blockage for diagnosing the IM
The diagnosis results of all machine learning (ML) algorithms belong to the same range, yet support vector machine (SVM) and k-nearest neighbor (k-NN) have

Summary

Introduction

Induction motor (IM) applications have been extended to various fields in industry due to their numerous advantages, such as low cost, less maintenance, simple and robust construction, high efficiency with good reliability in operation than any other motors available. Some industries have started performing maintenance to safeguard the equipment by detecting the faults at the earliest. Maintenance may lead to a production blockage in the industry by consuming more time for diagnosis. Many studies [3,4] keep on suggesting the importance of condition monitoring (CM) and fault diagnosis of IM, which is more recommended to avoid the production blockage for diagnosing the IM. CM deals with continuous monitoring of the failure progress of respective equipment, and indicates the significant changes observed above the critical level. The online surveillance of IM progressively cuts down the scheduled maintenance cost and automatically increases the production rate by reducing the diagnosis time

Methods

Findings

Discussion

Conclusion