Keywords
causal fault attribution
multivariate time series
cooling system anomaly
counterfactual residuals
root-cause localization
safety-critical process monitoring
Abstract
Nuclear power plants rely on continuous monitoring of cooling loops, auxiliary pumps, heat exchangers, pressure vessels, valve positions, coolant temperature, flow rate, vibration, and radiation-related process indicators. These variables are highly coupled through thermal transfer, hydraulic balance, safety-control logic, and delayed feedback mechanisms. A minor deviation in pump efficiency, valve response, or heat-exchanger performance may propagate through several subsystems before triggering system-level alarms. This study proposes a causal fault attribution method for multivariate time series from nuclear plant cooling and auxiliary systems. The method constructs a time-lagged causal graph using conditional independence testing, physical safety constraints, and control-loop dependency rules. A counterfactual residual module estimates expected variable trajectories under normal thermal-hydraulic behavior. Root-cause variables are then ranked according to their causal contribution to downstream deviations. Experiments are conducted on a nuclear plant simulation and monitoring dataset containing 12 cooling-loop subsystems, 146 process variables, and 1-second measurements collected across 9,800 simulated operating cycles and 14 months of auxiliary-system logs. The dataset contains 428 million timestamped records and 1,260 expert-reviewed abnormal episodes, including coolant flow degradation, auxiliary pump instability, valve-response delay, heat-exchanger fouling, sensor drift, and abnormal pressure oscillation. The proposed method reduces median root-cause localization time from 33.8 minutes to 8.6 minutes compared with a temporal reconstruction baseline. The mean reciprocal rank for initiating-variable identification reaches 0.851. Causal path analysis assigns 980 abnormal episodes to interpretable thermal-hydraulic propagation chains, while unnecessary subsystem inspection tickets decrease from 760 to 284. Median inference latency remains 37 ms per monitoring window. The results indicate that causal fault attribution can improve fine-grained anomaly diagnosis in safety-critical nuclear plant monitoring systems.
References
Soppelsa, A., Fedrizzi, R., & Pipiciello, M. (2026). A Two-Degree-of-Freedom Controller with Transport Delay Compensation for Application in Thermo-Hydraulic Circuits. Energies, 19(9), 2128.
Yang, J. (2026). Computational Analysis of How Digital Non-Clinical Communication Tools Influence Social Participation Among Older Adults in Community-Based Elderly Care. Available at SSRN 6682838.
Zhang, Z. (2026). A Study on the Identification of Manipulative Design in Subscription and Payment Interfaces of Digital Consumer Platforms and Its Behavioral Effects. Available at SSRN 6734760.
Kabir, T. (2026). Intelligent Condition Monitoring and Fault Diagnosis of Electrical Power and Control Systems Using Machine Learning–Based Predictive Analytics. American Journal of Interdisciplinary Studies, 7(01), 177-222.
Chen, X., Xiao, H., Zeng, Z., Zhang, S., & Xiao, R. (2025). Fine-Grained Multivariate Time Series Anomaly Detection via Causal Inference. Knowledge-Based Systems, 114765.
Suliman, A., Eftekhari, M., Dimitriou, V., & Ali, Y. (2025). Quantification and diagnostics of Corrosion-driven energy degradation in closed loop hydronic heating systems. Engineering Failure Analysis, 110349.
Fu, Y., Gui, H., Li, W., & Wang, Z. (2020, August). Virtual Material Modeling and Vibration Reduction Design of Electron Beam Imaging System. In 2020 IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA) (pp. 1063-1070). IEEE.
Liang, R., Feifan, F. N. U., Liang, Y., & Ye, Z. (2025). Emotion-Aware Interface Adaptation in Mobile Applications Based on Color Psychology and Multimodal User State Recognition. Frontiers in Artificial Intelligence Research, 2(1), 51-57.
Khosravinia, P., Gama, J., & Veloso, B. (2026). Causally-Constrained Probabilistic Forecasting for Time-Series Anomaly Detection. arXiv preprint arXiv:2604.17998.
Yang, M., Wu, J., Tong, L., & Shi, J. (2025). Design of Advertisement Creative Optimization and Performance Enhancement System Based on Multimodal Deep Learning.
Wu, C., & Chen, H. (2025). Research on system service convergence architecture for AR/VR system.
Sayed, E., Ali, A. M., Alrashdi, I., Sallam, K. M., Abdel-Basset, M., & Ismail, M. M. (2026). Sustainable diagnostic accuracy in healthcare 4.0: a comparative study of machine learning models with association rule-based feature reduction. Cluster Computing, 29(4), 224.
Yin, J., Huang, Y., & Rao, H. (2026). A Study on the Dynamic Evolution of Learning Behavior and Outcome Prediction in Digital Educational Environments. Available at SSRN 6607139.
Hadizadeh, A., Tarighat, A., & Malian, A. (2026). A data-driven framework for structural health monitoring using reinforcement learning and deep autoencoders. Scientific Reports.
Karimi, K., & Ranani, E. M. (2025). A Mathematical Framework for Anomaly Detection in High-Dimensional Data Using Sparse Autoencoders and Mutual Information Filtering. International Journal of Mathematical Modelling & Computations, 15(4).
Yin, L., Tong, Y., Islam, Z. H., Zhang, K., Xie, R., Burger, J., ... & Wang, B. (2024). Targeted NAD+ Delivery for intimal Hyperplasia and Re-endothelialization: a novel anti-restenotic therapy approach. bioRxiv, 2024-02.
Du, Y., Liu, Q., Dong, Y., & Chen, Z. (2026). Cross-Domain Transfer and Few-Shot Recognition of Defect Images in Complex Industrial Settings.
Alagha, N., Khairuddin, A. S. M., Haitaamar, Z. N., Al-Khatib, O., & Kanesan, J. (2025). Artificial intelligence in wind turbine fault detection and diagnosis: Advances and perspectives. Energies, 18(7), 1680.
Xiong, W., Zeng, Y., & Guo, Y. (2026). A Study on the Impact of MEP Space Organization in Large-Scale Commercial Complexes on Investment Efficiency and Its Mechanisms.
Hong, Z., Xu, T., & Chen, H. (2026). A Study on Test Coverage Mapping and Release Risk Prediction in Continuous Delivery of Cloud Services.
Nakti, I., Mansouri, M., Al-Hmouz, R., & Khedher, A. (2025). Artificial intelligence techniques with digital twin for fault diagnosis in interconnected systems: A review. IEEE Access, 13, 91860-91874.
Li, J., Ma, R., & Gu, Y. (2026). From Audit Requirements to Computable Software Architecture: A Rule-Engine and Evidence-Indexing Method for Trusted Digital Infrastructure.
Zhang, Z., Tong, Y., & Gao, Y. (2026). Retrieval-Augmented Generation with Low-Latency Deployment for Vertical Domains Question Answering: A Case Study on Economic Resource Platforms.
Sanjalawe, Y., Fraihat, S., Al-E’mari, S., & Makhadmeh, S. N. (2026). Bridging the gap: A comprehensive survey on AI-driven digital twin networks for future wireless systems. Journal of King Saud University Computer and Information Sciences, 38(3), 113.
Qi, C., & Qiao, X. (2026). Efficient Data Sampling and Feature Selection Algorithms for Scalable Machine Learning Pipelines.
Su, D., & Zhang, H. Developing a Data-Driven Computational Framework for Scalable Special Education Practices for Autism and Intellectual Disabilities in the US Public School System.
Zhang, Y., Gu, W., & Wang, J. (2025, December). Construction of Wind Farm Asset Health Index Based on Multi-Dimensional Indicators and Analytic Hierarchy Process and Its Correlation with Operational Performance. In Proceedings of the 2025 International Conference on Digital Transformation and Management (pp. 317-323).
Longhi, G., Lomonaco, G., Melichar, T., & Mazzini, G. (2026). MSR Fuel and Thermohydraulic: Modeling of Energy Well Experimental Loop in TRACE Code. Energies, 19(4), 1098.
Xu, T., Zhu, W., & Zhang, J. (2026). Stability and Consistency of Explainable Deep Learning Methods in Credit Risk Assessment. Available at SSRN 6893938.
Yin, L., Tong, Y., Xie, R., Zhang, Z., Islam, Z. H., Zhang, K., ... & Wang, B. (2024). Targeted NAD+ repletion via biomimetic nanoparticle enables simultaneous management of intimal hyperplasia and accelerated re-endothelialization: a proof-of-concept study toward next-generation of endothelium-protective, anti-restenotic therapy. Journal of Controlled Release, 376, 806-815.
Fayyaz, Y., Elouataoui, W., Gahi, Y., El-Khatib, K., Harvel, G., & Sankaranarayanan, K. (2026). Natural language processing in the nuclear industry: opportunities and challenges. Nuclear Technology, 212(5), 1143-1163.
Zhang, Y., Wang, J., & Gu, W. (2026, February). Research on the Construction and Effectiveness of a Computer-Aided Systematic Training Framework for Wind Farm O&M Quality Amidst High Personnel Turnover. In Proceedings of the 2nd International Conference on Digital Management and Information Technology (pp. 647-651).