Hybrid Model and Data Driven Fault Diagnosis and Self-Recovery Control of Integrated Energy Systems

DOI: https://doi.org/10.62517/jes.202502404

Author(s)

Siying Lyu, Lyujun He

Affiliation(s)

Guangzhou College of Commerce, Guangzhou, Guangdong, China

Abstract

In view of the common actuator faults, sensor faults and cyber attacks in the operation of integrated energy systems, this paper proposes a hybrid model and data driven fault diagnosis and self-recovery control method based on model-based fault observer and data-based deep learning technology, so as to improve the safety and reliability of integrated energy systems. This project will establish a fault testing model for a multi-energy complementary integrated energy system, applying the proposed hybrid model and data driven algorithm, researching robust and accurate diagnosis of multi-type complex faults and continuous fault-tolerant operation in integrated energy systems. The research results will provide new insights for the design of robust observers and the study of fault diagnosis and self-recovery control in complex systems.

Keywords

Integrated Energy Systems; Actuator Fault; Sensor Fault; Cyber Attacks; Fault Observer; Deep Learning

References

[1]Kong X, Lu Z, Guo X, et al. Resilience evaluation of cyber-physical power system considering cyber attacks. IEEE Transactions on Reliability, 2024, 73(1): 245-256. [2]Lund H, Werner S, Wiltshire R, et al. 4th Generation district heating (4GDH): integrating smart thermal grids into future sustainable energy systems. Energy, 2014, 68: 1-11. [3]Zhou M, Liu C, Jahromi A, et al. Revealing vulnerability of N-1 secure power systems to coordinated cyber-physical attacks. IEEE Transactions on Power Systems, 2023, 38(2): 1044 -1057. [4]Li J, Wang Y, Li H, et al. Adaptive dual control law sliding mode observer to reconstruct cyber attack and compensate power in cyber physical power system. IEEE Transactions on Power Systems, 2025, 40(4): 3198-3210. [5]Addel-Geliel M, Zakzouk S, El Sengaby M. Application of model-based fault detection for an industrial boiler//Control & Automation (MED), 2012 20th Mediterranean Conference on. IEEE, 2012: 98-103. [6]Escobar R F, Astorga-Zaragoza C M, Téllez-Anguiano A C, et al. Sensor fault detection and isolation via high-gain observers: Application to a double-pipe heat exchanger. ISA transactions, 2011, 50(3): 480-486. [7]Kiasi F, Prakash J, Shah S L. Detection and diagnosis of incipient faults in sensors of an LTI system using a modified GLR-based approach. Journal of Process Control, 2015, 33: 77-89. [8]Khoshnevisan L, Momeni H R, Ashraf-Modarres A. Introduction of a robust fault detection filter model based on continuous Kalman filter for a real drum boiler system. International Journal of Modeling and Optimization, 2012, 2(4): 539. [9]Rahme S, Meskin N. Adaptive sliding mode observer for sensor fault diagnosis of an industrial gas turbine. Control Engineering Practice, 2015, 38: 57-74. [10][Khoshnevisan L, Momeni H R, Ashraf-Modarres A. Implementation of an innovative simplified sliding mode observer-based robust fault detection in a drum boiler system//Proc. 2011 WASET Conference, Dubai, UAE. 2011: 340-344. [11]Gao D, Wang S, Shan K, et al. A system-level fault detection and diagnosis method for low delta-T syndrome in the complex HVAC systems. Applied energy, 2016, 164: 1028-1038. [12]Madrigal-Espinosa G, Osorio-Gordillo G L, Astorga-Zaragoza C M, et al. Fault detection and isolation system for boiler-turbine unit of a thermal power plant. Electric Power Systems Research, 2017, 148: 237-244. [13]Wang Y, Yin X, Wang B. A method of diagnosing leakage of boiler steam and water pipes based on genetic neural network//Intelligent Control and Automation (WCICA), 2016 12th World Congress on. IEEE, 2016: 2829-2833. [14]Rostek K, Morytko Ł, Jankowska A. Early detection and prediction of leaks in fluidized-bed boilers using artificial neural networks. Energy, 2015, 89: 914-923. [15]Rahman A, Sun W, Haggi H. Cybersecurity for hydrogen integrated power systems: vulnerability identification and impact analysis with attack defense strategy. IEEE Transactions on Power Systems, 2025, Early Access.