摘要
针对电力巡线任务的具体需求,提出一种改进型自适应粒子群算法。该算法通过引入自适应调节算法中的惯性权重,以平衡不同阶段全局搜索和局部搜索能力;加入具有自调整能力的自学习因子和社会学习因子,着重加强算法在运行后期的收敛速度和寻优能力;并针对偶发的大量粒子聚集于某个局部最优值的现象,适时引入驱散操作,对粒子聚集区域加以疏散,使其被分配到更大的空间范围内,以加强算法跳出局部极小的能力。最后,通过典型智能算法测试函数的测试,检验了改进算法在平均最优值、运行时间和成功次数等方面的优势;通过仿真分析,验证了该算法在电力巡线应用的有效性。
An improved adaptive particle swarm optimization algorithm is proposed to meet the specific requirements of power line patrol tasks.By introducing the inertia weight of the adaptive adjustment algorithm,the algorithm balances the global search and local search capabilities at different stages of operation.The self-learning factor and social learning factor with self-adjusting ability are added to enhance the convergence speed and optimization ability of the algorithm in the later stage of operation.In view of the phenomenon that a large number of particles are clustered in a local optimum value,the dispersal operation is introduced in time to evacuate the particle aggregation area,so that it can be allocated to a larger space range,so as to enhance the ability of the algorithm to jump out of the local minimum.Finally,the test results of the intelligent algorithm test function verify the advantages of the improved algorithm in terms of average optimal value,running time and number of successful times,and the effectiveness of the algorithm in power line patrol is verified by simulation analysis.
作者
杨轻
杨忠
许昌亮
徐浩
韩家明
YANG Qing;YANG Zhong;XU Changliang;XU Hao;HAN Jiaming(College of Automation Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China;Key Laboratory of Navigation,Control and Health-Management Technologies of Advanced Aerocraft (Nanjing Univ.of Aeronautics and Astronautics),Ministry of Industry and Information Technology,Nanjing 211106,China)
出处
《应用科技》
CAS
2019年第3期80-85,共6页
Applied Science and Technology
基金
国家自然科学基金项目(61473144)
中国南方电网有限责任公司科技项目(066600KK52170074)
航空科学基金项目(20162852031)
关键词
粒子群算法
电力巡线
多旋翼无人机
兴趣点
自适应
驱散策略
收缩因子
测试函数
PSO
power line patrol
Multi-Rotor UAV
point of interest
self-adaption
dispersion strategy
contractionfactor
test function
