[1]裴文龙,徐塑哲,张佰庆,等.面向支柱绝缘子清洗的机器人多模式自适应决策与智能控制方法研究[J].机械与电子,2026,44(09):44-56.
　PEI Wenlong,XU Suzhe,ZHANG Baiqing,et al.Research on Multi-mode Adaptive Decision making and Intelligent Control Method for Insulator Cleaning Robots[J].Machinery & Electronics,2026,44(09):44-56.
点击复制

面向支柱绝缘子清洗的机器人多模式自适应决策与智能控制方法研究()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
44
期数:
2026年09期
页码:
44-56
栏目:
机器人技术
出版日期:
2026-09-25

文章信息/Info

Title:
Research on Multi-mode Adaptive Decision making and Intelligent Control Method for Insulator Cleaning Robots
文章编号:
1001-2257(2026)09-0044-13
作者:
裴文龙1; 徐塑哲1; 张佰庆1; 衡 可1; 郭明鑫1; 季洪鑫2
1.国网徐州供电公司,江苏 徐州221000;
2.中国矿业大学电气工程学院,江苏 徐州 221116
Author(s):
PEI Wenlong1; XU Suzhe1; ZHANG Baiqing1; HENG Ke1; GUO Mingxin1; JI Hongxin2
(1.State Grid Xuzhou Power Supply Company,Xuzhou 221000,China;
2.School of Electrical Engineering,China University of Mining and Technology,Xuzhou 221116,China)
关键词:
绝缘子清洗机器人; 模糊贝叶斯决策; 深度强化学习; 自适应控制; 扰动观测器
Keywords:
insulator cleaning robot; fuzzy-Bayesian decision; deep reinforcement learning; adaptive control; disturbance observer
分类号:
TP242
文献标志码:
A
摘要:
针对绝缘子清洗机器人在高空支柱绝缘子清洗作业中存在的作业模式僵化与参数控制静态化问题,提出一种融合感知决策与自适应控制的智能清洗方法。首先,构建基于多维度视觉的污秽特征提取模型,实现对污秽类型、覆盖率、曲率、湿润度与厚度的精准感知;在此基础上,提出一种模糊贝叶斯决策机制,实现干刷、水洗与混合洗3种作业模式的鲁棒自主选择。进一步,设计基于深度强化学习的双层清洗参数自适应控制架构,上层通过离线学习全局优化策略,下层结合实时反馈进行局部补偿,实现清洗参数的动态实时优化。同时,引入基于扰动观测器的本体抗扰控制器,保障绝缘子清洗机器人在清洗扰动下的本体稳定。仿真结果表明,所提方法在清洗清洁率、能量效率、模式适应性和运动稳定性方面均显著优于传统固定策略与单一智能控制方法,平均清洁率达92.1%,能耗降低36.6%,验证了其在复杂动态环境中具备良好的自适应能力和工程应用潜力。
Abstract:
To address the problems of rigid operation modes and static parameter control in existing robotic cleaning systems for high-altitude post insulators,this paper proposes an intelligent cleaning framework that integrates perceptual decision-making with adaptive control.First,a multi-dimensional vision-based contamination feature extraction model is constructed to achieve accurate perception of contamination type,coverage rate,surface curvature,wettability,and layer thickness.On this basis,a fuzzy-Bayesian decision mechanism is developed to enable robust autonomous selection among three cleaning modes:dry brushing,water washing,and hybrid cleaning.Furthermore,a dual-layer adaptive parameter control architecture based on the Deep Deterministic Policy Gradient (DDPG) algorithm is designed,where the upper-layer learns global optimization strategies through offline learning,and the lower layer performs real-time local compensation using feedback signals,thereby enabling dynamic and online optimization of cleaning parameters.Concurrently,a disturbance-observer-based anti-disturbance controller is intro-duced to maintain the body stability of the robot under cleaning-induced disturbances.Simulation results demonstrate that the proposed method significantly outperforms conventional fixed strategies and single intelligent control methods in terms of cleaning efficiency,energy consumption,mode adaptability,and motion stability,achieving an average cleaning rate of 92.1% and a 36.6% reduction in energy consumption. These results validate its strong adaptive capability and promising engineering application potential in complex dynamic environments.

参考文献/References:

[1] 李静,刘航,于龙滨,等.环境因素对复合绝缘子积污特性的影响[J].科学技术与工程,2023,23(18):7772-7778.

[2] 祝永坤,王军亮,李硕,等.复合绝缘子闪络故障原因分析及防范措施[J].内蒙古电力技术,2021,39(6):82-86.
[3] 李特,王尧平,李响,等.±500 kV 葛南线绝缘子自然积污特性研究[J].浙江电力,2023,42(6):98-104.
[4] 刘杰.重污染区复合外绝缘长期防污闪能力提升关键技术及应用[J].河北电力技术,2021,40(6):67.
[5] 许致远,吴波,陈顺宝,等.绝缘子清洗技术发展现状[J].电瓷避雷器,2026(2):101-107.
[6] Aghanasiri P,Raeisi A,Zarafshan P,et al.Modeling and control of a robot for power transmission insulator cleaning[C]∥2025 12th Iranian Conference on Renewable Energies and Distributed Generation (ICREDG).New York:IEEE,2025:1-6.
[7] Lei Ting,Xie Zhiwen,Wang Ke,et al.Control and application of ultra-high voltage insulator cleaning and detecting robot[C]∥Journal of Physics:Conference Series,2021,2087(1):012044.
[8] 宋伟,姜红建,王滔,等.爬壁机器人磁吸附组件优化设计与试验研究[J].浙江大学学报(工学版),2018,52(10):1837-1844.
[9] 蒋怡蔚,侯宇,李浩男,等.永磁吸附履带式管外爬行机器人的力学分析及运动仿真[J].机床与液压,2023,51(21):7-15.
[10] Alhassan A B,Zhang Xiaodong,Shen Haiming,et al.Investigation of aerodynamic stability of a lightweight dual-arm power transmission line inspection robot under the influence of wind[J].Mathematical Problems in Engineering,2019,2019:2139462.
[11] 何玉灵,庞子旺,代德瑞,等.基于弹性压紧与改进轮槽的线路巡检机器人抗风性优化设计[J].机械强度,2025,47(9):205-212.
[12] Cheng Hao,Wang Xuejun.Research on stability control strategy of adjustable pressure wall-climbing robot based on adsorption identification[J].Proceedings of the Institution of Mechanical Engineers,Part C: Journal of Mechanical Engineering Science,2024,238(5):1590-1602.
[13] Lou Shengjie,Wei Zhong,Guo Jinlin,et al.Current status and trends of wall-climbing robots research[J].Machines,2025,13(6):521.
[14] Bisht R S,Pathak P M,Panigrahi S K.Modelling,simulation and experimental validation of wheel and arm locomotion based wall-climbing robot[J].Robotica, 2023,41(2):433-469.
[15] 方永忠.基于热流固耦合的接触网绝缘子低温清洗技术研究[J].应用物理,2024(10):680-691.
[16] Zhang Yaqi,Xie Weiyi,Ma Renjie.Disturbance observer-based terminal sliding mode control for the training safety improvement in robot-assisted rehabilitation[J].Intelligence & Robotics,2025,5(2):333-354.
[17] Wen Xinyu,Guo Lei,Yan Peng,et al.Composite hierarchical anti-disturbance control for robotic systems with multiple disturbances[J].International Journal of Control,Automation and Systems,2022,12 (3):541-551.
[18] 梁旭,苏婷婷,侯增广,等.基于变阻抗控制的冗余驱动并联机器人多目标内力优化[J].自动化学报,2023,49(5):1099-1115.
[19] 张秀丽,王琪,黄森威,等.一种多模型融合的仿猎豹四足机器人复杂运动控制方法[J].机器人,2022,44(6):682-693.
[20] 曹潜.基于改进落足点的四足机器人爬楼梯 MPC 控制算法研究[J].建模与仿真,2025,14(1):474-482.
[21] Farghdani S,Abdelrahman O,Chhabra R.Fast and modular whole-body lagrangian dynamics of legged robots with changing morphology[PP/OL].arXiv(2025-04-23)[2026-05-05].https:∥arxiv.org/abs/2504.16383.

备注/Memo

备注/Memo:
收稿日期:2026-06-05
基金项目:国网江苏省电力有限公司科技项目资助(J2025150)
作者简介:裴文龙 (1989-),男,江苏徐州人,硕士研究生,研究方向为变电一次设备故障诊断及数据分析;季洪鑫 (1988-),男,江苏徐州人,博士,硕士研究生导师,研究方向为高电压绝缘检测与故障诊断,通信作者,E-mail:jihongx816@163.com。
更新日期/Last Update: 2026-10-12