Real-Time Artificial Neural Network Fault Diagnosis for Uninterrupted Power in Intensive Care Units

Authors

  • Marino A Department of Biomedical Engineering, Sapienza University of Rome, Rome, Italy Author
  • Rousseau C Department of Electrical Engineering, University of Lyon, Lyon, France Author
  • Papadopoulos K Department of Intensive Care Medicine, National and Kapodistrian University of Athens, Athens, Greece Author

DOI:

https://doi.org/10.5281/zenodo.22643993

Keywords:

real-time artificial neural network fault diagnosis, uninterruptible power supply reliability, intensive care unit power continuity, hospital microgrid resilience, hardware-in-the-loop fault detection

Abstract

Background: Intensive care units depend on an unbroken chain of electrical protection-spanning the utility-to-generator
automatic transfer switch, the standby generator and its power-electronic interface, the uninterruptible power supply (UPS)
rectifier-inverter-battery stage, and the downstream critical-care distribution feeder-in which a fault at any stage must be
detected, classified, and cleared before it reaches life-supporting equipment. Fixed-threshold overcurrent and undervoltage
protection struggles to discriminate the variable-impedance, power-electronically shaped fault signatures produced by modern
multi-source backup architectures, motivating growing use of artificial neural network (ANN) and deep-learning-based fault
diagnosis validated for real-time or near-real-time operation. Objective: This case study uses the illustrative electrical supply chain
feeding a hospital intensive care unit as an analytical frame for examining what published, individually verified real-time and
hardware-in-the-loop-validated ANN fault-diagnosis studies would contribute at each stage of that chain, and what gaps remain
before such diagnosis could be considered dependable for life-critical loads. Methods: A narrative case-analysis approach, rather
than a systematic review protocol, was used to identify and individually verify twenty peer-reviewed studies of ANN and
deep-learning fault diagnosis in microgrids, power-electronic converters and inverters, and UPS control systems, prioritizing
studies with real-time, online, or hardware-in-the-loop validation, which were then mapped onto four stages of the illustrative ICU
power-chain case and read against a separate hospital microgrid resilience literature. Findings: Real-time or
hardware-in-the-loop-validated ANN architectures-including feedforward networks validated on RT-LAB simulators,
hardware-in-the-loop-validated inverter fault-tolerant control schemes, wavelet-plus-ANN feeder classifiers, and CNN-LSTM and
protective-agent deep networks-achieved fault detection and classification accuracies generally exceeding 95%, and frequently
exceeding 99%, under nominal test conditions across every stage of the ICU power chain examined, but a smaller subset of these
studies documented accuracy falling to roughly 95.5-96% under adverse fault-parameter combinations and to 95.9% under
independent out-of-sample simulation. Separately, hospital microgrid resilience optimization studies achieving near-complete
critical-load service in outage scenarios uniformly modeled fault detection and clearing as instantaneous, omitting this
documented detection latency and residual misclassification risk, while UPS-specific sensor-fault diagnosis has not been revisited
with contemporary deep architectures since early fuzzy-neural approaches. Conclusions: Real-time ANN fault diagnosis has
matured across the individual components of the hospital ICU power chain, but integrating its documented accuracy, latency, and
robustness characteristics into hospital-representative resilience models, and revisiting UPS sensor-fault diagnosis with modern
deep architectures, are necessary next steps for translating this diagnostic capability into dependable, continuous power supply for
critical care.

References

Hubner RU, Kusel C, Oestmann JW (2023) Resilience of the critical infrastructure in hospitals: categorization and quantification as a basis for optimization. Die Anaesthesiologie, 72(10):710-718, DOI:10.1007/s00101-023-01318-9.

Khalil M, Ravaghi H, Samhouri D, Abo J, Ali A, Sakr H, Camacho A (2022) What is "hospital resilience"? A scoping review on conceptualization, operationalization, and evaluation. Frontiers in Public Health, 10:1009400, DOI:10.3389/fpubh.2022.1009400.

Zaben MM, Worku MY, Hassan MA, Abido MA (2024) Machine learning methods for fault diagnosis in AC microgrids: a systematic review. IEEE Access, 12:20260-20298, DOI:10.1109/ACCESS.2024.3360330.

Niharika, Mathew L (2023) Real time analysis of artificial neural network-based fault detection and fault location in the AC microgrid. In: Soft Computing for Security Applications, Advances in Intelligent Systems and Computing, vol 1428. Springer, Singapore, DOI:10.1007/978-981-19-3590-9_25.

Sivapriya A, Kalaiarasi N, Vishnuram P, Abou Houran M, Bajaj M, Pushkarna M, Kamel S (2023) Real-time hardware-in-loop based open circuit fault diagnosis and fault tolerant control approach for cascaded multilevel inverter using artificial neural network. Frontiers in Energy Research, 10:1083662, DOI:10.3389/fenrg.2022.1083662.

Rahmanian Koushkaki E, Rajaei A (2026) A real-time ANN for estimation of digital twin parameters used in health indication of flyback converter. Journal of Electrical Systems and Information Technology, 13:18, DOI:10.1186/s43067-026-00320-6.

Bhagwat A, Dutta S, Jadoun VK, Veerendra AS, Sahu SK (2024) A customised artificial neural network for power distribution system fault detection. IET Generation, Transmission & Distribution, 18(11), DOI:10.1049/gtd2.13186.

Pradhan R, Mishra S, Mahapatra A, Chhotaray A (2025) Advanced fault detection and classification via fully connected neural network using multilayer perceptron in AC microgrid. Sadhana, 50:146, DOI:10.1007/s12046-025-02835-6.

Taheri B, Hosseini SA, Hashemi-Dezaki H (2025) Enhanced fault detection and classification in AC microgrids through a combination of data processing techniques and deep neural networks. Sustainability, 17(4):1514, DOI:10.3390/su17041514.

Teta A, Korich B, Bakria D, Hadroug N, Rabehi A, Alsharef M, Bajaj M, Zaitsev I, Ghoneim SSM (2024) Fault detection and diagnosis of grid-connected photovoltaic systems using energy valley optimizer based lightweight CNN and wavelet transform. Scientific Reports, 14:18907, DOI:10.1038/s41598-024-69890-7.

Yang Y, Tu F, Huang S, Tu Y, Liu T (2023) Research on CNN-LSTM DC power system fault diagnosis and differential protection strategy based on reinforcement learning. Frontiers in Energy Research, 11:1258549, DOI:10.3389/fenrg.2023.1258549.

Chen Q, Xu T, Zhou C, Wang Y (2026) Enhancing intelligent fault detection and classification in power grid engineering using LSTM neural networks. Distributed Generation & Alternative Energy Journal, 41(4):857-898, DOI:10.13052/dgaej2156-3306.4142.

Esmaeilbeigi S, Kazemi Karegar H, Najar A (2025) A fault classification scheme based on protective agents for microgrid with parameters impact analysis. Scientific Reports, 15:44316, DOI:10.1038/s41598-025-28178-0.

Sahu R, Panigrahi PK, Lal DK, Pradhan R, Mahanty C (2026) Robust deep learning for multiclass power system fault diagnosis using edge deployment. Algorithms, 19(4):299, DOI:10.3390/a19040299.

Jayasinghe JARR, Malindi JHE, Rajapaksha RMAM, Logeeshan V, Wanigasekara C (2024) Classification and localization of faults in AC microgrids through discrete wavelet transform and artificial neural networks. IEEE Open Access Journal of Power and Energy, 11:303-313, DOI:10.1109/OAJPE.2024.3422387.

Taniguchi S, Dote Y (2001) Sensor fault detection for uninterruptible power supply (UPS) control system using fast fuzzy-neural network and immune network. In: 2001 IEEE International Conference on Systems, Man and Cybernetics, Vol. 1:99-104, DOI:10.1109/ICSMC.2001.969795.

Hervas-Zaragoza J, Colmenar-Santos A, Rosales-Asensio E, Colmenar-Fernandez L (2022) Microgrids as a mechanism for improving energy resilience during grid outages: a post COVID-19 case study for hospitals. Renewable Energy, 199:308-319, DOI:10.1016/j.renene.2022.08.132.

Eissa MA, Samy MM, Said M (2026) Techno-economic analysis and resilience enhancement of a hospital microgrid under grid outage scenarios. Scientific Reports, 16:18358, DOI:10.1038/s41598-026-56638-8.

Nazartalab P, Alavi-Rad H (2026) Resilience-oriented optimization of hospital microgrids with critical load support using ESS and PV under grid outage conditions. Scientific Reports, 16:5475, DOI:10.1038/s41598-026-34992-x.

Zidane TEK, Muis ZA, Ho WS, Zahraoui Y, Aziz AS, Su CL, Mekhilef S, Elia Campana P (2025) Power systems and microgrids resilience enhancement strategies: a review. Renewable and Sustainable Energy Reviews, 207:114953, DOI:10.1016/j.rser.2024.114953.

Downloads

Published

2026-06-06