As a crucial method for defect elimination in transmission lines, live-line work plays a key role in improving power supply reliability and reducing operation costs. However, it also faces numerous challenges due to its high risks and strict requirements on the professional skills of operators. Currently, the defect elimination process relies on full-time supervisors conducting ground monitoring under the tower. This approach, restricted by viewing angles and distances, struggles to effectively control sudden operational risks. This paper proposes an intelligent management and control method for live-line work based on high-precision position information. The method collects high-precision positioning data and acceleration data of various parts of the operators through intelligent wearable devices. By integrating this data with the intelligent recognition model of the background analysis system, it enables automatic identification of non-compliant operations, insufficient electrical distances, and operational standardization, as well as scientific evaluation of operators' skill levels. This method overcomes issues such as algorithm limitations, false alarms, missed alarms, and line-of-sight obstructions existing in the current artificial intelligence-based image recognition technology. It achieves real-time accurate mapping and quantitative analysis of the operation process, providing strong support for the safety management and control of live-line work and the training of operators.
Ye-fei et al. (Fri,) studied this question.