改进Q-Learning输电线路超声驱鸟设备参数优化研究
徐浩，房旭，张浩，王爱军，周洪益，宋钰
(国网江苏省电力有限公司盐城供电分公司，江苏 盐城 224000)
摘 要：超声波驱鸟是一种解决输电设备鸟害的重要手段，但现场使用超声波驱鸟器工作模式较单一，易产生鸟类适应问题。提出了一种改进 Q-Learning 输电线路超声驱鸟设备参数优化方法，针对涉鸟故障历史数据量少以及鸟类的适应性问题，将强化学习算法应用于输电线路超声驱鸟设备参数优化；针对传统强化学习算法在设备终端应用中存在收敛慢、耗时长的缺点，提出一种基于动态学习率的改进 Q-Learning 算法，对不同频段超声波的权重进行自适应优化。实验结果显示，改进 Q-Learning 算法最优参数的迭代收敛速度大幅提高，优化后驱鸟设备的驱鸟成功率达到了76%，优于传统强化学习算法模式，较好地解决了鸟类适应性问题。
关键词： 改进Q-Learning ；超声波驱鸟；参数优化；适应性
中图分类号：TM726 ；P631.5 文献标识码：B 文章编号：1007-3175(2024)05-0053-05
Research on Parameter Optimization of Improved Q-Learning Ultrasonic
Bird Repellent Equipment for Transmission Lines
XU Hao, FANG Xu, ZHANG Hao, WANG Ai-jun, ZHOU Hong-yi, SONG Yu
（Yancheng Power Supply Company of State Grid Jiangsu Electric Power Co., Ltd, Yancheng 224000, China）
Abstract: Ultrasonic bird repellent is an important method to solve the problem of bird damage in power transmission equipment, but the sole mode of operation that ultrasonic bird repellent was used in the field caused problems of the adaptability of birds. This paper presented an improved parameter optimization method for ultrasonic bird repellent equipment of Q-Learning transmission line, and the reinforcement learning algorithm is applied to the parameter optimization of ultrasonic bird drive equipment of transmission lines in order to solve the problem of little historical data of birds-related faults and the adaptability of birds. In view of the shortcomings of traditional reinforcement learning algorithms in device terminal applications, which have slow convergence and long time-consuming, an improved Q-Learning algorithm based on dynamic learning rate was proposed, which adaptively optimized the weights of ultrasound in different frequency bands. The experimental results showed that the iterative convergence speed of the optimal parameters of the improved Q-Learning algorithm was greatly improved, and the success rate of bird repellent equipment after optimization was 76%, which is better than the traditional reinforcement learning algorithm mode, and can better solve the adaptability problem of birds.
Key words: improved Q-Learning; ultrasonic bird repellent; parameter optimization; adaptability
参考文献
[1] 李帆，李阳林，张宇，等. 架空输电线路涉鸟故障分析与防范[J]. 中国电力，2019，52(10) ：92-99．
[2] 李阳林，张宇，郭志锋，等. 架空输电线路涉鸟故障防治[M]. 北京：中国电力出版社，2018．
[3] 唐子峰，袁翔，廖志雄，等. 广东韶关电网鸟害跳闸故障统计分析及防护[J]. 电瓷避雷器，2018(2) ：20-24.
[4] 中国电力企业联合会. 架空输电线路涉鸟故障防治技术导则：GB/T 35695—2017[S] . 中国标准出版社，2017 ：15-29.
[5] 盛从兵， 赵庆喜， 李辉杰， 等. 基于鸟类生物特性的智能型声波驱鸟装置研究[J] . 电源技术应用，2013(12) ：382.
[6] 聂兴成，张荣浩，王爱玉，等. 杆塔智能超声波驱鸟系统设计[J]. 电工电气，2015(10) ：21-23.
[7] 余鹏，田杰，陈硕. 变电站电子爆鸣驱鸟系统设计[J].电子设计工程，2017，25(24) ：134-137.
[8] 王彦. 基于超声参量阵的变电站驱鸟系统设计与算法研究[D]. 青岛：山东科技大学，2019.
[9] 汤瀚博，蒋旭，李海波，等. 基于物联网技术的输电线路智慧驱鸟系统设计[J] . 现代电子技术，2023，46(21) ：154-159.
[10] 李睿. 多模式超声波驱鸟器的研制[J] . 电工电气，2021(3) ：35-40.
