A multiphysics numerical simulation approach for performance optimization of high-temperature superconducting magnetic energy storage systems

Abstract

This paper presents a novel framework for ground-wire state visualization and real-time diagnosis that integrates multisource sensing, intelligent modeling, and optimization-driven decision-making. By fusing heterogeneous data sources such as tension, vibration, temperature, and electrical measurements, the framework establishes a robust foundation for monitoring dynamic operating conditions in power transmission corridors. A phase-aware segmentation mechanism combined with rule-guided refinement ensures both high detection accuracy and interpretability, while advanced learning-based modules enhance adaptability under noise and domain shifts. Extensive experiments on both field datasets and lab controlled testbeds demonstrate that the proposed method outperforms state-of-the-art baselines in terms of classification accuracy, change-point detection stability, and fault localization precision. The results validate the scalability and efficiency of the framework, providing a practical pathway for intelligent infrastructure monitoring and operational safety in modern power systems.