Sustainable Energy and Artificial Intelligence

Reinforcement Learning-Optimized Data-Driven Fractional-Order Sliding Mode Observer for Sensor Fault Detection

Document Type : Original Article

Authors

Mohsen Shiri 1
Hadi Delavari 2
Younes Solgi 1

1 Department of Electrical Engineering, Faculty of Engineering, Bu-Ali Sina University, Hamedan, Iran.

2 Department of Electrical Engineering, Hamedan University of Technology, Hamedan, Iran.

https://doi.org/10.66224/seai.2602-1049
Abstract
This paper addresses the problem of model-free control and sensor fault detection for discrete-time nonlinear systems by proposing an intelligent proportional–integral–derivative controller in conjunction with a fractional-order sliding mode observer. The proposed method eliminates the need for an explicit mathematical model and relies solely on input and output signals. By integrating sliding mode observation with fractional calculus, the proposed fault detection scheme benefits from enhanced memory characteristics and increased degrees of freedom in the observer design. This integration enables an effective trade-off between detection accuracy and convergence speed, thereby improving the overall performance of the fault detection mechanism. Enhancing the fault detection mechanism significantly reduces false alarm rates, thereby improving operational reliability and yielding tangible benefits in terms of economic efficiency. To intelligently tune the controller and observer parameters, a Reinforcement Learning–based optimization strategy is employed. This learning mechanism enables the adaptive tuning of controller and observer design parameters to achieve enhanced tracking accuracy while simultaneously improving the precision of residual generation for reliable fault detection within the system. The stability of the resulting closed-loop system is rigorously established using Lyapunov theory. The effectiveness and superiority of the proposed approach are validated through comprehensive simulation studies conducted on a data-driven, model-free nonlinear discrete-time system. The simulation results demonstrate significant improvements in tracking performance, robustness, and fault estimation accuracy compared to conventional approaches.

Keywords

Data-Driven Fault Detection
Sensor Fault
Fractional-Order Sliding Mode Observer
Reinforcement Learning
Discrete-Time System
Subjects
1. Khaki-Sedigh, A. (2023). An Introduction to Data-Driven Control Systems. John Wiley & Sons.
2. Veisi, A., & Delavari, H., (2025). Applied Data Driven Nonlinear Control (Vol. 1): Hamedan University of Technology Press.
3. Ding, S. X. (2014). Data-driven design of fault diagnosis and fault-tolerant control systems (pp. 23-47). London: Springer London.
4. Ding, S. X. (2021). Advanced methods for fault diagnosis and fault-tolerant control (Vol. 184). Berlin: Springer.
5. Gnetchejo, P. J., Essiane, S. N., Ele, P., Dadjé, A., & Chen, Z. (2025). Faults diagnosis in a photovoltaic system based on multivariate statistical analysis. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 47(1), 7383-7404.
6. Antony, A. S. M., Sundaram, K. M., Raman, C. J., & Murthy, G. R. (2026). Intelligent fault detection in battery systems: a machine learning approach with transformer-enhanced multi-modal Sensing. Electric Power Systems Research, 251, 112279.
7. Alrifai, Y., Aguilera-González, A., Vechiu, I., & Becerra-Becerra, G. (2026). Hybrid fault detection and identification strategy for PV systems combining statistical data-driven and Kalman filter algorithms. Electric Power Systems Research, 252, 112381.
8. Allahverdi, F., Ramezani, A., & Forouzanfar, M. (2020). Sensor fault detection and isolation for a class of uncertain nonlinear system using sliding mode observers. Automatika, 61(2), 219-228.
9. Gao, S., Ma, G., & Guo, Y. (2023). Robust sliding‐mode observer‐based multiple‐fault diagnosis scheme. Asian Journal of Control, 25(2), 1555-1576.
10. Veisi, A., Shiri, M., & Delavari, H. (2024). Fractional order sliding mode observer-based control in the presence of faults. Contributions of Science and Technology for Engineering, 1(1), 19-24.
11. Shiri, M., & Delavari, H. (2026). A model-free data-driven intelligent fault diagnosis framework for discrete nonlinear systems using a novel fractional order neural network. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 48(2), 125.
12. Rektemvald, M. P. M. (2025, November). Sensor fault detection scheme for a lithium battery with SMO. In 2025 5th International Conference on Applied Automation and Industrial Diagnostics (ICAAID) (pp. 1-7). IEEE.
13. Bilal, H., Aslam, M. S., Tian, Y., Ullah, I., Ayouni, S., & Vasilakos, A. V. (2025). A consumer electronics-enhanced UAV system for agricultural farm tracking with fuzzy SMO and actuator fault detection control algorithms. IEEE Transactions on Consumer Electronics.
14. Zhong, F., Li, H., & Zhong, S. (2016). State estimation based on fractional order sliding mode observer method for a class of uncertain fractional-order nonlinear systems. Signal Processing, 127, 168-184.
15. Alshammari, M., Alshammari, T. S., Alshammari, S., Alsheekhhussain, Z., Shah, R., Jebran, S., & Al-sawalha, M. M. (2025). Exploring new routes in fractional modeling: analytical solutions of Burgers-type systems via Caputo-Hadamard and ϕ-Caputo derivatives. Boundary Value Problems, 2025(1), 166.
16. Veisi, A., & Delavari, H. (2025). Deep reinforcement learning optimizer based novel Caputo fractional order sliding mode data driven controller. Engineering Applications of Artificial Intelligence, 140, 109725.
17. Veisi, A., & Delavari, H. (2024). Fractional data driven controller based on adaptive neural network optimizer. Expert Systems with Applications, 257, 125077.
18. Veisi, A., Delavari, H., & Shanaghi, F. (2023, February). Maximum power point tracking in a photovoltaic system by optimized fractional nonlinear controller. In 2023 8th International Conference on Technology and Energy Management (ICTEM) (pp. 1-5). IEEE.
19. Liu, D., & Yang, G. H. (2017). Data-driven adaptive sliding mode control of nonlinear discrete-time systems with prescribed performance. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 49(12), 2598-2604.
20. Hou, M., Renming, Y., Li, G., & Han, Y. (2024). Data‐driven integral terminal sliding mode fault‐tolerant control for a collection of discrete‐time nonlinear systems. Asian Journal of Control, 26(2), 946-959.
21. Treesatayapun, C. (2017). Discrete-time adaptive controller based on non-switch reaching condition and compact system dynamic estimator. Journal of the Franklin Institute, 354(15), 6783-6804.
22. Han, K., & Feng, J. (2021). Data-driven robust fault tolerant linear quadratic preview control of discrete-time linear systems with completely unknown dynamics. International Journal of Control, 94(1), 49-59.
23. Veisi, A., & Delavari, H. (2025). Stability of Nonlinear Fractional Order Discrete-Time Systems for Engineering Applications.
24. Delavari, H., & Veisi, A. (2021). Power maximization of wind turbine based on DFIG using fractional order variable structure controller. In seventh international conference on energy technology and management, Ardabil (Vol. 2, p. 022).
25. Han, Y., & Hou, M. (2024). Data-driven second-order sliding mode fault-tolerant control for a class of discrete-time nonlinear systems. European Journal of Control, 76, 100954.
26. Wang, Y., & Wang, Z. (2020). Model free adaptive fault-tolerant tracking control for a class of discrete-time systems. Neurocomputing, 412, 143-151.
27. Shakya, A. K., Pillai, G., & Chakrabarty, S. (2023). Reinforcement learning algorithms: A brief survey. Expert Systems with Applications, 231, 120495.
28. Liang, H., Xie, J., Huang, B., Li, Y., Sun, B., & Yang, C. (2025). A novel sim2real reinforcement learning algorithm for process control. Reliability Engineering & System Safety, 254, 110639.
Sustainable Energy and Artificial Intelligence
Volume 2, Issue 2
Spring 2026
Pages 121-130

  • Receive Date 23 February 2026
  • Revise Date 09 May 2026
  • Accept Date 17 May 2026
  • First Publish Date 17 May 2026

Home

Guide for Authors

Submit Manuscript

Reviewers

Contact Us