STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Instrumentation Technology & Innovations Review Article

TinyML-Based Real-Time Industrial Fault Detection Using Vibration Signals

  1. Sarvesh Mahimkar Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur
  2. Bhakti Gavali Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur
  3. Aditi Gavali Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur
  4. Jyoti Ghadage Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur
  5. Vaibhav Godase Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Pandharpur

Abstract

Industrial rotating machinery is commonly monitored through vibration measurements because changes in bearing condition can alter signal amplitude, impulsiveness, and spectral distribution. Cloud-centred analytics may introduce communication dependence, bandwidth demand, and response delay. Tiny Machine Learning (TinyML) offers a complementary approach by executing compact inference locally on resource-constrained edge hardware. This paper presents a reproducible, deployment-oriented workflow for vibration-based machine-state classification using statistical and spectral features with small classifiers suitable for edge deployment. A synthetic three-class vibration benchmark was constructed to represent healthy operation, inner-race-like impulsive behavior, and outer-race-like impulsive behavior under multiple rotational speeds (900–1,800 rpm). Twelve features—seven time- domain/statistical and five spectral-band energy fractions were extracted from 1,800 windows of 1,024 samples each, and a stratified 75:25 train–test split (1,350/450 windows) was used to evaluate a small multilayer perceptron (MLP) with one hidden layer of 16 ReLU units, a constrained random forest, and an extra-trees classifier. On the held-out synthetic test set, the MLP achieved 99.78% accuracy (macro F1 = 0.998), while both three ensembles reached 100% accuracy (macro F1 = 1.000). Host-side inference timing ranged from 0.001 ms/window for the MLP to 0.052 ms/window for the random forest, though these are desktop Python benchmarks, not microcontroller measurements. The paper explicitly separates simulation results from field validation and discusses memory, latency, quantity, data leakage, and fail-safe considerations that must be addressed before deployment on a microcontroller. Since the benchmark is synthetic and the random split does not model recording-level dependence, the results demonstrate pipeline feasibility and methodological transparency rather than industrial diagnostic validity. Validation on recording-level splits of public datasets (CWRU, Paderborn) and subsequent on-device profiling with a real accelerometer are required before operational use.

Keywords

References (26)

  1. Godase V, Pawar P, Nagane S, Kumbhar S. Automatic railway horn system using node MCU. Journal of Control & Instrumentation. 2024 Jan;15(1).
  2. Godase V, Godase J. Diet prediction and feature importance of gut microbiome using machine learning. Evolution in Electrical and Electronic Engineering. 2024 Nov 6;5(2):214-9.
  3. Jamadade VK, Ghodke MG, Katakdhond SS, Godase V. A comprehensive review on scalable Arduino radar platform for real-time object detection and mapping. Journal of Microprocessor and Microcontroller Research. 2025 May;2(2):1-2.
  4. Godase, V. (2025). A comprehensive study of revolutionizing EV charging with solar-powered wireless solutions. Advance Research in Power Electronics and Devices e-ISSN, 3048-7145.
  5. Godase V. Advanced Neural Network Models for Optimal Energy Management in Microgrids with Integrated Electric Vehicles. InProceedings of the International Conference on Trends in Material Science and Inventive Materials (ICTMIM-2025) DVD Part Number: CFP250J1-DVD 2025 Apr 18.
  6. Dange R, Attar E, Ghodake P, Godase V. Smart agriculture automation using ESP8266 NodeMCU. J. Electron. Comput. Netw. Appl. Math,(35). 2023 Jul:1-9.
  7. Godase V. Optimized algorithm for face recognition using Deepface and multi-task cascaded convolutional network (MTCNN). Optimum Science Journal. 2025 May 5(3):66-74.
  8. Bhaganagare S, Chavan S, Gavali S, Godase V. The Vocal Cortex of the Smart Home: A Review of ESP32- Based Control and Automation Architectures. International Journal of Advanced Research in Science, Communication and Technology. 2025 Nov:1071-94.
  9. Godase V. Navigating the digital battlefield: An in-depth analysis of cyber-attacks and cybercrime. International Journal of Data Science, Bioinformatics and Cyber Security. 2025 Jan 17;1(1):16-27.
  10. Godase V, Jagadale A. Three element control using PLC, PID & SCADA interface. International Journal for Scientific Research & Development. 2019;7(2):1105-9.
  11. Godase V. Edge AI for smart surveillance: Real-time human activity recognition on low-power devices. International Journal of AI and Machine Learning Innovations in Electronics and Communication Technology. 2025 Jan 18;1(1):29-46.
  12. Godase V. LoRaEdge-ESP32 synergy: Revolutionizing farm weather data collection with low-power, long- range IoT. Advance Research in Analog and Digital Communications. 2025 Jan 1.
  13. Godase V. Comparative study of ladder logic and structured text programming for PLC. Available at SSRN. 2025 Jul 2.
  14. Godase V, Modi S, Misal V, Kulkarni S. Real-time object detection for autonomous drone navigation using YOLOv8,‖. Advance Research in Communication Engineering and its Innovations. 2025;2(2):17-27.
  15. Godase V. Smart energy management in manufacturing plants using PLC and SCADA. Advance Research in Power Electronics and Devices. 2025 May 8;2(2):14-24. 16. Godase V. IoT-MCU Integrated Framework for Field Pond Surveillance and Water Resource Optimization. International Journal of Emerging IoT Technologies in Smart Electronics and Communication. 2025 Jan 1.
  16. Mehta J, Gupta V, Sivia JS. A Comprehensive Review of Terahertz antennas: Designs, Challenges and Optimization Techniques. Wireless Personal Communications. 2026 Oct 3:1-49.
  17. Godase V, Khiste R, Palimkar V. AI-Optimized reconfigurable antennas for 6G communication systems. Journal of RF and Microwave Communication Technologies. 2025 Aug;2(3):1-2.
  18. Bhaganagare S, Chavan S, Gavali S, Godase VV. Voice-controlled home automation with esp32: A systematic review of iot-based solutions. Journal of Microprocessor and Microcontroller Research. 2025 Sep 1;2(3):1-3.
  19. Jamadade VK, Ghodke MG, Katakdhond SS, Godase V. A comprehensive review on scalable Arduino radar platform for real-time object detection and mapping. Journal of Microprocessor and Microcontroller Research. 2025 May;2(2):1-2.
  20. Godase V. Cross-domain comparative analysis of microwave imaging systems for medical diagnostics and industrial testing. Journal of Microwave Engineering and Technologies. 2025 Aug;12(2):39-48.
  21. Jamadade VK, Ghodke MG, Katakdhond SS, Godase V. A Review on Real-time Substation Feeder Power Line Monitoring and Auditing Systems,”. International Journal of Emerging IoT Technologies in Smart Electronics and Communication. 2025 Sep;1(2):1-6.
  22. Godase VV. VLSI-Integrated Energy Harvesting Architectures for Battery-Free IoT Edge Systems. Journal of Electronics Design and Technology. 2025 Sep;2(3):1-2. 24. Salunkhe A, Pawar V, Pise P, Mule S, Survase A, Godase V, Zambre S. A review on real-time RFID-based smart attendance systems for efficient record management. Advance Research in Analog and Digital Communications. 2025 Aug;2(2):32-46.
  23. Godase VV. A neuromorphic-inspired, low-power VLSI architecture for edge AI in IoT sensor nodes. Journal of Microelectronics and Solid State Devices. 2025;12(2):41-7.
  24. Nagane MS, Pawar MP, Godase PV. Cinematica sentiment analysis. Journal of Image Processing and Intelligent Remote Sensing. 2022 May;2(3):27-32.
  25. Akhtar ZB. Artificial intelligence within medical diagnostics: A multi-disease perspective. Artificial intelligence in Health. 2025 Jan 6;2(3):44-62.
  26. Wang Z, Huang Y, Song D, Ma L, Zhang T. Promptcharm: Text-to-image generation through multi-modal prompting and refinement. InProceedings of the 2024 CHI conference on human factors in computing systems 2024 May 11 (pp. 1-21).

Other papers on this site that share keywords with this one, closest match first.

  1. Journal of Control & Instrumentation

    AI Powered Fault Detection in DC Motor using STM32

    2026

  2. Journal of Artificial Intelligence Research & Advances

    Fault Investigation of Rolling Element Bearing using Soft Computing

    2019

  3. Trends in Mechanical Engineering & Technology

    To Diagnose the Broken Tooth Fault, Signal Processing Techniques and Machine Learning Technique are Applied

    2024

  4. Journal of Aerospace Engineering & Technology

    Industrial Prognostics via Ensemble Machine Learning: An Uncertainty Aware Framework for RUL Estimation on NASA FD004 Telemetry

    2026

  5. Journal of Mechatronics and Automation

    Efficient Machine Defect Detection with Sugeno Fuzzy Membership and GRU Networks for Robust Industrial Automation

    2025

  6. Journal of Industrial Safety Engineering

    Predictive Maintenance Strategies for Safety-critical Mechanical Systems

    2025

Read more of it

Subscribe to one journal or build your own list of several. One invoice, one payment, access for a full year.

Subscribe to journals →

Publish your article

Peer-reviewed journals across every subject, with open access options. Send your manuscript to the right editor today.

Publish with us → Calculate your APC
Support