Performance Assessment and Optimization of Bird Prevention Devices for Transmission Lines Based on Internet of Things Technology

Birds nest, inhabit and fly near transmission lines, which may cause serious power accidents. Aiming at the problems of false alarm, false alarm and insufficient system stability in traditional bird prevention devices, a new bird prevention device scheme combining deep learning and Internet of Things (IOT) technology is proposed in this study. Methods: In this study, firstly, the convolutional neural network (CNN) algorithm based on deep learning is used to recognize bird images, and the recognition accuracy is improved by training a large number of samples. In addition, multi-sensor fusion and real-time data transmission are realized by using IOT technology, which enhances the intelligence and remote monitoring ability of the system. The results show that the optimized bird prevention device has significantly improved the accuracy of bird detection, recall and system stability. Compared with the traditional algorithm, the false alarm rate and false alarm rate are greatly reduced, and the processing speed of the system is accelerated, and it can keep stable operation for a long time. This achievement provides a strong support for the safety protection of electric power system (EPS), and also provides a new idea for the research and development of bird prevention devices in the future.