Development of an AI Based AC Motor Fault Prediction Model

Tanaka Mutsvangwa; Didymus T Makusha

doi:10.71097/IJSAT.v16.i2.6083

Development of an AI Based AC Motor Fault Prediction Model

Author(s)	Tanaka Mutsvangwa, Didymus T Makusha
Country	Zimbabwe
Abstract	Abstract Maintaining industrial motors is critical in the manufacturing and mining industries, because motor faults can cause financial losses, including delays and downtime during production. This paper is going to investigate the development of an AC motor fault predictive AI model applicable in industrial settings. AI representing artificial intelligence. The model is trained on data that focus on nature, type and cause of faults in AC motors [6]. The structure and main components of the AC motor will be described separately with their purpose stated, the components are: rotor, stator and bearing, fan blade, wiring cover, end bell and motor frame. The investigation will name and classify types of faults commonly found in AC motors and will analyse current strategies used to resolve these problems of faults in motors including reactive and scheduled maintenance approaches. The motor faults are classified into two types which are electrical faults and mechanical faults [3]. There are two sub classes of electrical faults which are stator faults and rotor faults. Mechanical faults include bearing faults and eccentricity related faults, mainly caused by intense thermal, mechanical and environmental stress [4]. This work shows how the AI model was developed and tested to detect these faults. Most of these faults are really progressive faults which continue to occur on different random occasions. However, the work also demonstrated that while use of AI to solve this problem offers promise it still has a lot of development and innovation work needed. The study shows that the bigger the training dataset, the more accurate and useful the model. In contrast traditional approaches will be still remain costly than the produced model. The dataset is used to train AI algorithms such as Linear Regression, Random Forest Regression and Long Short-Term Memory (LSTM) a deep learning algorithm [7]. The data used consists of stator currents, input power, slip, rotor speed, rotor currents and efficiency. After training, the model will be able to predict the fault to be experienced by the motor, and also provide the estimate of probable predicted time the fault is most likely to occur. Also discussed in this article are the signal processing techniques applied to prepare the data to be used in training the model. The article also outlines the types of signal processing methods used when collecting parameters which are essential for error detection. The signal processing technique we used to monitor the condition of the motor is the FFT (Fast Fourier transform) [8]. The resulting dataset is also suitable to be used for training other machine learning models. This study focuses on data processing, feature generation and model training, contributing accuracy and reliability to maintenance engineering through an AI based AC motor fault prediction model.
Keywords	Keywords: AC, AI, IOT, Deep Machine Learning, Motor Fault, FFT
Field	Engineering
Published In	Volume 16, Issue 2, April-June 2025
Published On	2025-06-10
DOI	https://doi.org/10.71097/IJSAT.v16.i2.6083
Short DOI	https://doi.org/g9pz8t

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 15 Isu 4 Cover Page Vol 15 Isu 3 Cover Page Vol 15 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Development of an AI Based AC Motor Fault Prediction Model

Share this