Investigation of Intelligent Substation Inspection Robot by Using Mobile Data

Abstract

Substation equipment inspection is essential for the power industry. The expansion of the smart grid scale improves the transmission capacity and enhances the likelihood of power plant facilities failure. To ensure the safety of the electric power supply, it is essential to inspect substation equipment. Metal commercial equipment can be traversed by remote inspection robots equipped with magnetic wheels. It is possible to use robots like this to examine equipment and pipelines remotely. In many cases, these gadgets are able to scale vertical surfaces and even traverse obstacles with a variety of shapes. Finally, researchers in the field of robotics have indicated that challenges such as restricted onboard battery capacity, undependable line fault detection, electrical insulation, power mechanism, and advanced control techniques for outer wind disruption are highly promising research areas. To build an unmanned, intelligent, and succeeded substation, the substation progressively implements inspection robots instead of physical exertion. Hence, in this paper, the mobile-based Intelligent Tracking Framework (MITF) has been proposed using inspection robots. This inspection robot is autonomous and can be used for various tracking tools: visual, infrared, and partial charge–discharge camera. The robot is integrated with a camera and thermal infrared imager sensors that have been collectively designated as workload. These inspection sensors are used to detect environmental parameters such as reading meters, evaluation thermoelectric temperature. The accurate localization of working loads and the inspection robot electromagnetic interference within substations have been resolved. This mobile robot delivers innovative monitoring and precise detection for the unmanned substation and smart substation. The suggested approach’s effectiveness is verified through experiment results based on the electrical equipment of the substation. The experimental outcome of the proposed method boosts the Meter Reading Analysis (94.19%), Transmission Capacity Analysis (98.5%), Workload Analysis (98.9%), Temperature Analysis (97.6%), and Safety Analysis (95.41%).