Physics-Informed Deep Sequential Learning and Non-Parametric Adaptive Thresholding for Integrated Microgrid Fault Detection

DOI: https://doi.org/10.33650/jeecom.v8i2.17123
Authors

(1)  Muhammad Akbar Barrinaya   (Universitas Pertamina)  
        Indonesia
(2) * Herminarto Akbar Nugroho   (Universitas Pertamina)  
        Indonesia
(*) Corresponding Author

Abstract


The rapid proliferation of clean energy microgrids—integrating solar photovoltaic (PV) generation, bidirectional power converters, and battery energy storage systems (BESS)—requires robust fault detection and isolation (FDI) to guarantee continuous operational stability. However, non-Gaussian residual profiles caused by severe irradiance intermittency and dynamic switching transients compromise traditional fixed-threshold strategies, resulting in elevated false alarm and missed detection rates. To address this challenge, this study presents a hybrid FDI framework combining physics-guided deep sequential forecasting with non-parametric adaptive thresholding. A Temporal Convolutional Network integrated with Long Short-Term Memory (TCN-LSTM), constrained by equivalent circuit and DC bus power balance equations, is developed to forecast multi-modal nominal trajectories and extract reliable diagnostic residuals. Raw electrical streams sampled at 10 kHz are down sampled via moving-window averaging to 10-second intervals to accommodate prognostic forecasting horizons. Non-parametric Kernel Density Estimation (KDE) is subsequently implemented to dynamically compute adaptive threshold boundaries from empirical non-Gaussian residual distributions. Simulation experiments under stochastic irradiance profiles and dynamic load cycles confirm that the proposed TCN-LSTM architecture achieves nominal forecasting RMSE values of 0.007 V for cell voltage and 0.306 °C for temperature, reducing the missed detection rate of PV shading mismatches and critical sensor biases compared to static thresholding. Furthermore, integration with a Local Outlier Factor (LOF) anomaly detector provides early warning margins of 83.5 minutes for micro-short circuit voltage dips and 24.6 minutes for thermal runaway precursors prior to hard-limit BMS alarms.

Keywords

Fault Detection and Isolation; Integrated Microgrids; Solar Photovoltaic Systems; Deep Learning; Kernel Density Estimation



Full Text: PDF



References


S. V. R. Naik and P. N. Rao, “Intelligent Fault Detection in PSO-MPPT based Photovoltaic and Electric Vehicle Integrated System Under Partial Shading Conditions,” Indian Journal of Pure and Applied Physics, vol. 64, no. 2, pp. 197–208, 2026, doi: 10.56042/ijpap.v64i2.25940.

C. Huang and D. Ma, “Actuator and sensor fault tolerant control for Steer-by-Wire systems: Recent Advances,” in Proceedings - 2022 Chinese Automation Congress, CAC 2022, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 1606–1610. doi: 10.1109/CAC57257.2022.10055044.

M. P. Kumar, S. Velpula, and C. Saiprakash, “Fault diagnosis and predictive maintenance of electric vehicle powertrain using artificial intelligence techniques: A review,” Results in Engineering, vol. 30, 2026, doi: 10.1016/j.rineng.2026.110857.

L. Wang, “Fault Diagnosis and Optimization Technology for New Energy Vehicle Powertrain Systems,” in Frontiers in Artificial Intelligence and Applications, 2026, pp. 1156–1164. doi: 10.3233/FAIA260159.

M. A. Rezaei et al., “Adaptation of a Real-Time Deep Learning Approach with an Analog Fault Detection Technique for Reliability Forecasting of Capacitor Banks Used in Mobile Vehicles,” IEEE Access, vol. 10, pp. 132271–132287, 2022, doi: 10.1109/ACCESS.2022.3228916.

G. Wójcik and P. Przystałka, “Towards Safer Electric Vehicles: Autoencoder-Based Fault Detection Method for High-Voltage Lithium-Ion Battery Packs,” Sensors, vol. 25, no. 5, 2025, doi: 10.3390/s25051369.

M. Sharawy, A. El-Nahas, M. A. Alahmar, F. A. Banakhr, M. I. Mosaad, and M. Selmy, “Machine learning framework for multi-fault diagnosis within three-phase induction motor in Electric Vehicle applications,” Results in Engineering, vol. 30, 2026, doi: 10.1016/j.rineng.2026.110933.

K. Zhang et al., “A model-data fusion approach utilizing residual subset selection and adaptive thresholding for hybrid electric vehicle fault diagnosis,” Expert Syst. Appl., vol. 300, 2026, doi: 10.1016/j.eswa.2025.130376.

X. Han, X. Zhou, F. Lu, and J. Huang, “Data model-based sensor fault diagnosis algorithm for closed-loop control systems,” Measurement, vol. 246, p. 116715, 2025.

J. Shen et al., “Timely multi-fault diagnosis and prognostics for lithium-ion batteries of electric vehicles based on hybrid neural network and anomaly detection,” J. Energy Storage, vol. 150, 2026, doi: 10.1016/j.est.2025.120026.

E. V. H. Udoka, K. U. Umaru, E. Edozie, R. Nafuna, and N. Yudaya, “The differences between single diode model and double diode models of a solar photovoltaic cells: systematic review,” Journal of Engineering, Technology, and Applied Science (JETAS), vol. 5, no. 2, pp. 57–66, 2023.

F. M. Petcut, “Comparative Analysis of Single-Diode and Two-Diode Models of Photovoltaic Panels,” in 2025 18th International Conference on Engineering of Modern Electric Systems (EMES), IEEE, 2025, pp. 1–6.

D. S. Pillai, F. Blaabjerg, and N. Rajasekar, “A comparative evaluation of advanced fault detection approaches for PV systems,” IEEE J. Photovolt., vol. 9, no. 2, pp. 513–527, 2019.

A. Triki-Lahiani, A. B.-B. Abdelghani, and I. Slama-Belkhodja, “Fault detection and monitoring systems for photovoltaic installations: A review,” Renewable and Sustainable Energy Reviews, vol. 82, pp. 2680–2692, 2018.

D. Saadaoui et al., “Parameters extraction of single diode and double diode models using analytical and numerical approach: A comparative study,” International Journal of Modelling and Simulation, vol. 45, no. 2, pp. 569–598, 2025.

C. Yang et al., “A Survey of Photovoltaic Panel Overlay and Fault Detection Methods†.,” Energies (Basel)., vol. 17, no. 4, p. NA-NA, 2024.

A. Et-Taleby, Y. Chaibi, M. Benslimane, and M. Boussetta, “Applications of machine learning algorithms for photovoltaic fault detection: a review,” Statistics, Optimization & Information Computing, vol. 11, no. 1, pp. 168–177, 2023.

Q. Wei, S. Gao, L. Shi, S. Gao, K. Wu, and Y. Li, “Nonlinear dual-motor steer-by-wire system cooperative control via fixed-time command-filtered,” ISA Trans., vol. 167, pp. 984–994, Dec. 2025, doi: 10.1016/j.isatra.2025.08.018.

M. H. Elmahdy, E. M. El-Gendy, I. Ismael, and M. M. Saafan, “Advancements in fault diagnosis and fault tolerant control of lithium-ion battery systems for electric vehicles: Theoretical and real-time approaches,” J. Energy Storage, vol. 152, 2026, doi: 10.1016/j.est.2026.120794.

S. Zhang, J. Li, R. Li, and X. Zhang, “Voltage sensor fault detection, isolation and estimation for lithium-ion battery used in electric vehicles via a simple and practical method,” J. Energy Storage, vol. 55, 2022, doi: 10.1016/j.est.2022.105555.

L. He, C.-F. Zong, G.-H. Jiang, H.-Y. Zheng, and G. Li, “SOC estimation and fault tolerant control method of power battery for steering-by-wire system,” Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition), vol. 42, no. SUPPL. 1, pp. 17–21, 2012, [Online]. Available: https://www.scopus.com/pages/publications/84871917916?origin=resultslist

A. Sistani, S. A. Hosseini, V. S. Sadeghi, and B. Taheri, “Providing a fault detection method for the occurrence of faults in DC microgrids, distributed generations, and electrical vehicles,” AUT Journal of Electrical Engineering, vol. 56, no. 2, pp. 325–342, 2024, doi: 10.22060/eej.2024.22866.5565.

L. Jiang, Z. Deng, X. Tang, L. Hu, X. Lin, and X. Hu, “Data-driven fault diagnosis and thermal runaway warning for battery packs using real-world vehicle data,” Energy, vol. 234, 2021, doi: 10.1016/j.energy.2021.121266.

Z. Sun et al., “An Online Data-Driven Fault Diagnosis and Thermal Runaway Early Warning for Electric Vehicle Batteries,” IEEE Trans. Power Electron., vol. 37, no. 10, pp. 12636–12646, 2022, doi: 10.1109/TPEL.2022.3173038.

B. Zhou, C. Yu, Z. Liu, J. Guo, J. Chen, and J. Guo, “Fault diagnosis of hydraulic internal leaks in steering systems of multi-axle heavy vehicle via BO-transformer-LSTM technique,” Measurement (Lond)., vol. 267, 2026, doi: 10.1016/j.measurement.2026.120540.

X. Qin, W. Zhang, S. Gao, X. He, and J. Lu, “Sensor Fault Diagnosis of Autonomous Underwater Vehicle Based on LSTM,” in Chinese Control Conference, CCC, 2018, pp. 6067–6072. doi: 10.23919/ChiCC.2018.8483218.

S. L. Sreedevi, G. Ramani, B. Parvathi Sangeetha, N. Rishikesh, G. Vasumathi, and N. Janaki, “Sandcat Optimized ANN-LSTM Framework for Advanced Fault Detection in Electric Vehicle Drive Motor,” in 2025 IEEE International Conference on Emerging Trends in Computing and Communication, ETCOM 2025, 2025. doi: 10.1109/ETCOM66606.2025.11436615.

C.-G. Huang, X. Yin, H.-Z. Huang, and Y.-F. Li, “An enhanced deep learning-based fusion prognostic method for RUL prediction,” IEEE Trans. Reliab., vol. 69, no. 3, pp. 1097–1109, 2019.

J. Zhong, Y. Zhang, J. Wang, C. Luo, and Q. Miao, “Unmanned aerial vehicle flight data anomaly detection and recovery prediction based on spatio-temporal correlation,” IEEE Trans. Reliab., vol. 71, no. 1, pp. 457–468, 2021.

K. Yang, S. Zhang, R. Lin, R. Tu, X. Zhou, and R. Zhang, “DC Series Arc Fault Detection in Electric Vehicle Charging Systems Using a Temporal Convolution and Sparse Transformer Network,” Sensors, vol. 26, no. 6, 2026, doi: 10.3390/s26061897.

S. Ai, J. Song, and G. Cai, “A real-time fault diagnosis method for hypersonic air vehicle with sensor fault based on the auto temporal convolutional network,” Aerosp. Sci. Technol., vol. 119, 2021, doi: 10.1016/j.ast.2021.107220.

G. Wójcik and P. Przystałka, “LSTM Model-Based Fault Detection for Electric Vehicle’s Battery Packs,” in Lecture Notes in Networks and Systems, 2023, pp. 217–229. doi: 10.1007/978-3-031-16159-9_18.

L. Dong and Y. Huo, “Research on Fault Diagnosis Method for Autonomous Underwater Vehicles Based on Improved LSTM Under Data Missing Conditions,” Applied Sciences (Switzerland), vol. 15, no. 21, 2025, doi: 10.3390/app152111570.

S. Liu, T. Xu, X. Du, Y. Zhang, and J. Wu, “A hybrid deep learning model based on parallel architecture TCN-LSTM with Savitzky-Golay filter for wind power prediction,” Energy Convers. Manag., vol. 302, p. 118122, 2024.

J. Tian, H. Liu, W. Gan, Y. Zhou, N. Wang, and S. Ma, “Short-term electric vehicle charging load forecasting based on TCN-LSTM network with comprehensive similar day identification,” Appl. Energy, vol. 381, p. 125174, 2025.

C. Hu, F. Cheng, L. Ma, and B. Li, “State of charge estimation for lithium-ion batteries based on TCN-LSTM neural networks,” J. Electrochem. Soc., vol. 169, no. 3, p. 030544, 2022.

H. Huang, J. Mai, W. He, N. Ma, and Y. Cao, “A deep belief rule with backward deduction process for the autonomous underwater vehicle fault diagnosis,” Appl. Soft Comput., vol. 198, 2026, doi: 10.1016/j.asoc.2026.115227.

C. Huang, F. Naghdy, H. Du, and H. Huang, “Fault tolerant steer-by-wire systems: An overview,” Jan. 01, 2019, Elsevier Ltd. doi: 10.1016/j.arcontrol.2019.04.001.

A. Zandieh, I. Han, M. Daliri, and A. Karbasi, “Kdeformer: Accelerating transformers via kernel density estimation,” in International Conference on Machine Learning, PMLR, 2023, pp. 40605–40623.

M. Wahbah, B. Mohandes, T. H. M. EL-Fouly, and M. S. El Moursi, “Unbiased cross-validation kernel density estimation for wind and PV probabilistic modelling,” Energy Convers. Manag., vol. 266, p. 115811, 2022.

J. Li, Y. Fan, and X. Tan, “Electric Vehicle Battery System Voltage Fault Diagnosis and Analysis Based on Kernel Density Estimation and Z-Score,” in 2025 6th International Conference on Mechatronics Technology and Intelligent Manufacturing, ICMTIM 2025, 2025, pp. 645–648. doi: 10.1109/ICMTIM65484.2025.11040815.

K. Zhang, S. Wang, D. Shi, H. Huang, and Y. Shi, “Research on fault diagnosis of multi-mode electromechanical compound transmission system for hybrid electric vehicles based on kernel density estimation,” in 15th Global Reliability and Prognostics and Health Management Conference, PHM-Beijing 2024, 2024. doi: 10.1109/PHM-BEIJING63284.2024.10874632.


Dimensions, PlumX, and Google Scholar Metrics

10.33650/jeecom.v8i2.17123


Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Muhammad Akbar Barrinaya, Herminarto Akbar Nugroho

 
This work is licensed under a Creative Commons Attribution License (CC BY-SA 4.0)

Journal of Electrical Engineering and Computer (JEECOM)
Published by LP3M Nurul Jadid University, Indonesia, Probolinggo, East Java, Indonesia.