Motor Fault Detection Using Vibration and Current

Abstract

Induction motors are widely used in industries because of their high efficiency, reliability, and simple construction. They are commonly used in machines such as pumps, compressors, and conveyors. However, due to continuous operation and harsh working conditions, induction motors can develop different types of faults. These faults may be mechanical, such as bearing damage and misalignment, or electrical, such as unbalanced voltage and single phasing. If these faults are not detected early, they can lead to serious damage and unexpected system failure. In this project, motor fault detection is carried out using vibration analysis and current analysis. A vibration sensor measures the mechanical vibrations of the motor, while a current sensor monitors the electrical current drawn by the motor. The collected signals are processed and analyzed to identify abnormal conditions in the motor. This method helps in detecting faults at an early stage and improving the reliability of the motor system. This system helps in condition monitoring and predictive maintenance, which reduces maintenance cost and prevents unexpected breakdowns in industrial applications.

Introduction

Induction motors are widely used in industry for their efficiency, reliability, and simplicity, but they are prone to faults such as bearing defects, rotor/stator issues, and electrical imbalances. Early detection of these faults is critical to prevent damage, reduce maintenance costs, and avoid unexpected downtime.

This project employs vibration analysis and current signature analysis (MCSA) using sensors connected to an ESP32 microcontroller to monitor motor health. Signal processing and feature extraction identify abnormal conditions, and detected faults are displayed on an OLED and sent to a cloud server for remote monitoring. Machine learning and deep learning approaches enhance fault classification accuracy, while combined vibration and current monitoring improves detection of both mechanical and electrical faults.

The proposed system offers several advantages: early fault detection, improved reliability, reduced maintenance costs, minimized downtime, enhanced safety, and extended motor lifespan. Experimental results confirm accurate detection of bearing faults, stator winding issues, and supply abnormalities, ensuring stable motor performance and higher industrial productivity.

Conclusion

In conclusion, the proposed fault diagnosis and fault-tolerant control methodology provides an effective solution for improving the reliability and performance of induction motor drive systems. The system is capable of detecting common faults such as bearing failures, stator winding defects, and supply voltage disturbances at an early stage using advanced monitoring techniques like vibration analysis, current signature analysis, and temperature monitoring. The implementation of fault-tolerant control strategies helps maintain stable motor operation even under faulty conditions, thereby reducing performance degradation. Furthermore, the methodology contributes to minimizing unexpected breakdowns, reducing maintenance costs, and improving overall operational safety. By enabling condition-based maintenance and continuous monitoring, the proposed approach enhances motor efficiency, increases service life, and supports uninterrupted industrial productivity. Hence, this method can be considered a reliable and practical solution for modern induction motor fault detection and protection systems.

References

[1] Ahad, M. F., Khan, M. A., Uzair, M., Iqbal, J., & Khan, M. A. (2022). IoT-based Machine Induction Motor Fault Detection System Using ESP32. Sensors, 22(12), 4587 [2] Kumar, S. S., & Kumar, R. D. (2021). IoT-based Machine Induction Motor Fault Detection Using Raspberry Pi. International Journal of Engineering Research & Technology (IJERT), 10(01), 119-125. [3] Patel, S., & Patel, D. (2020). IoT-based Machine Induction Motor Fault Detection Using Arduino. International Journal of Engineering Research & Technology (IJERT), 9(12), 957-962. [4] Krishna, M.S.R.; Seshadrinath, J. Model Based Stator Interturn Fault Analysis in Synchronous Reluctance Motor Drives. IEEE Trans. Ind. Appl. 2024, 60, 8878–8887 [5] L. Deng, A. Zhang, and R. Zhao, “Intelligent identification of incipient rolling bearing faults based on VMD and PCA-SVM,” Adv. Mech. Eng., vol. 14, no. 1, pp. 1–18, (2022). [6] Henriques, K.; Laadjal, K.; Cardoso, A.J.M. Inter-Turn Short-Circuit Fault Detection in Synchronous Reluctance Machines, Based on Current Analysis. Eng. Proc. 2022, 24, 23. [7] Khan, M. A., Khan, N. U., Iqbal, J., & Ahad, M. F. (2019). Machine Induction Motor Fault Detection Using Cloud Computing and Machine Learning. IEEE Transactions on Industrial Electronics, 67(5), 4144-4154. [8] Singh, P., Kumar, R. D., & Kumar, S. S. (2018). IoT-based Machine Induction Motor Fault Detection System Using Blynk. International Journal of Engineering Research & Technology (IJERT), 7(12), 148-152. [9] Krishna, M.S.R.; Seshadrinath, J. Model Based Stator Interturn Fault Analysis in Synchronous Reluctance Motor Drives. IEEE Trans. Ind. Appl. 2024, 60, 8878–8887. [Google Scholar] [CrossRef]

Copyright

Copyright © 2026 Ms. Sonali Sangole, Mr. Akshay Nimje, Ms. Shreya Mate, Mr. Nagendra Narmalwar, Mr. Abhishek Bhakre, Mr. Anmol Shende. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.