Multi-Sensor Fusion and Data Analytics for Power Cable Condition Monitoring and Predictive Maintenance

Power cables are critical infrastructure for electric power transmission, and their reliability directly affects supply security. The expansion of cable deployment has increased the difficulty of condition monitoring, while more complex operating environments intensify the challenge of early identification of insulation aging and latent defects. This paper systematically analyzes power-cable condition-monitoring and intelligent operation-and-maintenance (O&M) technologies, comparing electrical monitoring methods—such as partial discharge, sheath current, and dielectric loss—with non-electrical parameter monitoring of temperature, humidity, and strain, thereby clarifying the performance characteristics and applicable scopes of each approach. We also examine O&M methods including intelligent inspection, supervisory control and data acquisition (SCADA) system integration, and data-fusion algorithms. The results show that establishing a multi-parameter collaborative sensing framework, platform-based integration, and an artificial intelligence (AI)-driven O&M system enables accurate condition assessment and predictive maintenance of cables. This study provides a technical pathway for transitioning power-cable O&M from periodic maintenance to predictive maintenance and offers practical value for enhancing grid reliability.