Neuromorphic Continual Learning for Sequential Deployment of Nuclear Plant Monitoring Systems

2026-04-13

AI Summary

This study addresses the critical challenge of catastrophic forgetting in conventional neural networks when incrementally deploying monitoring subsystems in nuclear power plant industrial control systems, which compromises reliable anomaly detection and poses severe safety risks. To overcome this, the work proposes the first integration of spiking neural networks (SNNs) with continual learning, introducing a delta-based sparse spiking encoding scheme that enables asynchronous multi-source sensor fusion. The approach synergistically combines Elastic Weight Consolidation (EWC), synaptic intelligence, and experience replay strategies. Evaluated on the HAI 21.03 dataset, the system achieves an average F1 score of 0.979, near-zero forgetting rate (0.035 ± 0.039), a 12.6-fold reduction in computational load, 2.5× lower energy consumption, and an attack detection latency of only 0.6 seconds, substantially enhancing both energy efficiency and operational reliability.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Neuro-Symbolic Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Anomaly detection in nuclear industrial control systems (ICS) requires continuous, energy-efficient monitoring across multiple subsystems that are often deployed at different stages of plant commissioning. When a conventional neural network is sequentially trained to monitor new subsystems, it catastrophically forgets previously learned anomaly patterns, a safety-critical failure mode. We present the first spiking neural network (SNN)-based anomaly detection system with continual learning for nuclear ICS, addressing both challenges simultaneously. Our approach introduces spike-encoded asynchronous sensor fusion, a delta-based encoding that converts heterogeneous sensor streams into sparse spike trains at rates dictated by each sensor's natural dynamics, achieving 92.7% input sparsity. We evaluate five continual learning strategies, including sequential fine-tuning, Elastic Weight Consolidation (EWC), Synaptic Intelligence (SI), experience replay, and a hybrid EWC+Replay approach, on the HAI 21.03 nuclear ICS security dataset across three sequentially deployed subsystems (boiler, turbine, water treatment). The hybrid EWC+Replay method achieves an average F1 score of 0.979 with near-zero average forgetting (AF = 0.000 single seed; 0.035 +/- 0.039 across three seeds), while requiring 12.6x fewer operations (an estimated 2.5x in energy based on published hardware specifications) than an equivalent artificial neural network. The system detects all tested attacks with a mean latency of 0.6 seconds. These results demonstrate that neuromorphic computing offers a viable path toward always-on, energy-efficient, and adaptable safety monitoring for next-generation nuclear facilities.

Problem

• continual learning
• catastrophic forgetting
• anomaly detection
• nuclear ICS
• sequential deployment

Innovation

• Spiking Neural Network
• Continual Learning
• Anomaly Detection
• Neuromorphic Computing
• Sensor Fusion