AI Powered Fault Detection in DC Motor using STM32

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 17 | 01 | Page :
    By

    Pallavi Kumari V,

  • Samiksha Murthy,

  • Sribhanu Sravya Addaguduri,

  • Anjana Joshi,

  1. Student, Department of Electronics and Instrumentation Engineering, Dayanand Sagar College of Engineering, Bengaluru, India
  2. Student, Department of Electronics and Instrumentation Engineering, Dayanand Sagar College of Engineering, Bengaluru, India
  3. Student, Department of Electronics and Instrumentation Engineering, Dayanand Sagar College of Engineering, Bengaluru, India
  4. Assistant Professor, Department of Electronics and Instrumentation Engineering, Dayanand Sagar College of Engineering, Bengaluru, India

Abstract

This work presents the design and implementation of an embedded artificial intelligence system for real-time fault detection in a direct current (DC) motor using the STM32 Nucleo- F411RE microcontroller. The objective of the study is to develop a low-cost and efficient predictive maintenance solution capable of identifying abnormal motor behavior at an early stage. Vibration and temperature signals are acquired using an MPU6050 sensor and processed directly on the microcontroller without relying on cloud-based computation. Statistical and time-domain features are extracted from the sensor signals and used to train a lightweight anomaly detection model using Nano Edge AI Studio. The trained model is deployed on the STM32 platform to enable on-device inference with minimal memory consumption. Experimental validation is carried out under both normal and induced faulty operating conditions to evaluate classification performance. The system demonstrates high detection reliability with optimized RAM and Flash utilization, making it suitable for resource-constrained embedded environments. The proposed solution reduces latency, enhances data security, and eliminates dependency on external servers. The architecture can be extended to multi-motor industrial systems for scalable predictive maintenance. This approach contributes toward intelligent edge-based monitoring systems that improve equipment reliability, reduce downtime, and support Industry 4.0 applications and demonstrates the potential of compact embedded AI systems to enable intelligent, autonomous, and efficient motor health monitoring in modern industrial environments.

Keywords: STM32 microcontroller, STM32 Cube IDE, Nano Edge, Machine Learning model, Artificial Intelligence.

How to cite this article:
Pallavi Kumari V, Samiksha Murthy, Sribhanu Sravya Addaguduri, Anjana Joshi. AI Powered Fault Detection in DC Motor using STM32. Journal of Control & Instrumentation. 2026; 17(01):-.
How to cite this URL:
Pallavi Kumari V, Samiksha Murthy, Sribhanu Sravya Addaguduri, Anjana Joshi. AI Powered Fault Detection in DC Motor using STM32. Journal of Control & Instrumentation. 2026; 17(01):-. Available from: https://journals.stmjournals.com/joci/article=2026/view=238911


References

[1] De Fabritiis F, Gryllias K. A Self-supervised Learning Approach for Anomaly Detection in Rotating Machinery. InProceedings of the Annual Conference of the PHM Society 2024 2024 Nov 5 (Vol. 16, No. 1). PHM Society.

[2] Mones Z. MEMS accelerometer based condition monitoring and fault detection for induction motor. InThe 7th International Conference on Engineering & MIS 2021 2021 Oct 11 (pp. 1-6).

[3] Liao W. Real time bearing fault diagnosis based on convolutional neural network and STM32 microcontroller. arXiv preprint arXiv:2304.09100. 2023 Apr 14.

[4] Strantzalis K, Gioulekas F, Katsaros P, Symeonidis A. Operational state recognition of a DC motor using edge artificial intelligence. Sensors. 2022 Dec 9;22(24):9658.

[5] Adegbite T, Refaat SS, Farrag M, Mohammed A. Embedded AI-Enabled Fault Detection System for Electric Vehicle Powertrains. In2025 IEEE 4th Industrial Electronics Society Annual On-Line Conference (ONCON) 2025 Dec 11 (pp. 1-6). IEEE.

[6] Ahmad S, Styp-Rekowski K, Nedelkoski S, Kao O. Autoencoder-based condition monitoring and anomaly detection method for rotating machines. In2020 IEEE International Conference on Big Data (Big Data) 2020 Dec 10 (pp. 4093-4102). IEEE.

[7] Liu W, Hao J, Yang Y, Shen G. Research on Motor Fault Diagnosis Based on Improved Convolutional Neural Network of Random Forest under Small Sample Conditions. In2025 International Conference on Equipment Intelligent Operation and Maintenance (ICEIOM) 2025 Aug 1 (pp. 1137-1142). IEEE.

[8] Alasiry AH, Saidya HH, Tamami NA. A Dual-Microcontroller IoT-Based Real-Time Monitoring System for Predictive Maintenance of Induction Motors. In2025 International Electronics Symposium (IES) 2025 Aug 5 (pp. 164-171). IEEE.

[9] Zhao L, Xie T, Wei Y, Liu Y, Qin Y. Overview of digital twin-driven rotating machinery fault diagnosis: status and trends. Measurement Science and Technology. 2025 May 31;36(5):052001.

[10] Bhoomika CJ, Das C, Akshay DR, Subrahmanya KS. Analysis and Implementation of Current Signature Analysis for Fault Detection in Single-Phase Induction Motor. In2025 1st IEEE Uttar Pradesh Section Women in Engineering International Conference on Electrical Electronics and Computer Engineering (UPWIECON) 2025 Oct 30 (pp. 272-277). IEEE.

Ahead of Print Subscription Review Article
Volume 17
01
Received 23/02/2026
Accepted 26/02/2026
Published 20/03/2026
Publication Time 25 Days
59

Login


My IP

PlumX Metrics