Advanced asset analytic via thermal & partial discharge sensors on primary equipment in TNB distribution network

This paper presents a case study on the integration of advanced asset analytics for primary equipment in power distribution networks, focusing on switchgear and transformers. The deployment utilizes real-time monitoring systems equipped with Surface Acoustic Wave (SAW) technology and wired sensors to track critical parameters such as thermal variations and partial discharge levels. These parameters provide insights into the operational health of equipment, enabling predictive maintenance, optimizi ng performance, and reducing unplanned outages. The monitoring system leverages passive thermal sensors to monitor temperature changes and wired partial discharge sensors to detect electrical discharge activity. Data is aggregated at a local concentrat or and transmitted to Tenaga Nasional Berhad's (TNB) cloud-based data lake via cellular or fibre optic networks. Real-time alerts are triggered when temperature or discharge metrics exceed predefined thresholds, allowing operators to address potential issues promptly and prevent equipment failures. As the system evolves, machine learning algorithms will be integrated to enhance predictive capabilities. By analysing historical data and identifying patterns, these algorithms will provide advanced warnings of equipment degradation, enabling more efficient maintenance scheduling and extending the lifespan of critical assets. This study demonstrates the potential of combining real-time sensor data, robust data transmission, and machine learning analytics to transition from reactive to predictive maintenance strategies. The results underscore the system's ab ility to improve equipment reliability, enhance performance, and achieve significant operational cost savings, making it a scalable solution for modern utility networks.