改進Q-Learning輸電線路超聲驅鳥設備參數優化研究
徐浩，房旭，張浩，王愛軍，周洪益，宋鈺
(國網江蘇省電力有限公司鹽城供電分公司，江蘇 鹽城 224000)
摘 要：超聲波驅鳥是一種解決輸電設備鳥害的重要手段，但現場使用超聲波驅鳥器工作模式較單一，易產生鳥類適應問題。提出了一種改進 Q-Learning 輸電線路超聲驅鳥設備參數優化方法，針對涉鳥故障歷史數據量少以及鳥類的適應性問題，將強化學習算法應用于輸電線路超聲驅鳥設備參數優化；針對傳統強化學習算法在設備終端應用中存在收斂慢、耗時長的缺點，提出一種基于動態學習率的改進 Q-Learning 算法，對不同頻段超聲波的權重進行自適應優化。實驗結果顯示，改進 Q-Learning 算法最優參數的迭代收斂速度大幅提高，優化后驅鳥設備的驅鳥成功率達到了76%，優于傳統強化學習算法模式，較好地解決了鳥類適應性問題。
關鍵詞： 改進Q-Learning ；超聲波驅鳥；參數優化；適應性
中圖分類號：TM726 ；P631.5 文獻標識碼：B 文章編號：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
參考文獻
[1] 李帆，李陽林，張宇，等. 架空輸電線路涉鳥故障分析與防范[J]. 中國電力，2019，52(10) ：92-99．
[2] 李陽林，張宇，郭志鋒，等. 架空輸電線路涉鳥故障防治[M]. 北京：中國電力出版社，2018．
[3] 唐子峰，袁翔，廖志雄，等. 廣東韶關電網鳥害跳閘故障統計分析及防護[J]. 電瓷避雷器，2018(2) ：20-24.
[4] 中國電力企業聯合會. 架空輸電線路涉鳥故障防治技術導則：GB/T 35695—2017[S] . 中國標準出版社，2017 ：15-29.
[5] 盛從兵， 趙慶喜， 李輝杰， 等. 基于鳥類生物特性的智能型聲波驅鳥裝置研究[J] . 電源技術應用，2013(12) ：382.
[6] 聶興成，張榮浩，王愛玉，等. 桿塔智能超聲波驅鳥系統設計[J]. 電工電氣，2015(10) ：21-23.
[7] 余鵬，田杰，陳碩. 變電站電子爆鳴驅鳥系統設計[J].電子設計工程，2017，25(24) ：134-137.
[8] 王彥. 基于超聲參量陣的變電站驅鳥系統設計與算法研究[D]. 青島：山東科技大學，2019.
[9] 湯瀚博，蔣旭，李海波，等. 基于物聯網技術的輸電線路智慧驅鳥系統設計[J] . 現代電子技術，2023，46(21) ：154-159.
[10] 李睿. 多模式超聲波驅鳥器的研制[J] . 電工電氣，2021(3) ：35-40.
