改进PSO算法及其无人机电力巡线规划应用
|
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.
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.
引文
[1]葛黄徐.输电线路智能巡检系统的应用分析[J].通讯世界,2018,334(3):248-249.
[2]邓元婧,汪从敏,夏开全,等.架空输电线路通道环境的巡视技术与应用[J].浙江电力,2014(8):28-31.
[3]施孟佶,秦开宇,李凯,等.高压输电线路多无人机自主协同巡线设计与测试[J].电力系统自动化,2017,41(10):117-122.
[4]钱红昇,葛文锋,钟鸣,等.基于分层的改进[A*]算法在路径规划中的应用[J].计算机工程与应用,2014,50(7):225-229.
[5]赵晓,王铮,黄程侃,等.基于改进A*算法的移动机器人路径规划[J].机器人,2018,40(6):137-144.
[6]游晓明,刘升,吕金秋.一种动态搜索策略的蚁群算法及其在机器人路径规划中的应用[J].控制与决策,2017(3):552-556.
[7]DAS P K,BEHERA H S,TRIPATHY H K,et al.Ahybrid improved PSO-DV algorithm for multi-robot path planning in a clutter environment[J].Neurocomputing,2016,207:735-753.
[8]OLEIWI B K,ROTH H,KAZEM B I.A hybrid approach based on ACO and GA for multi objective mobile robot path planning[J].Applied mechanics and materials,2014,527:203-212.
[9]CHEN X,KONG Y,FANG X,et al.A fast two-stage ACO algorithm for robotic path planning[J].Neural computing and applications,2013,22(2):313-319.
[10]HUANG H C,TSAI C C.Global path planning for autonomous robot navigation using hybrid metaheuristic GA-PSO algorithm[C]//Proceeding of SICE Annual Conference.Tokyo,Japan:IEEE,2011:1338-1343.
[11]GENG N,GONG D,ZHANG Y.Robot path planning in an environment with many terrains based on interval multi-objective PSO[J].International journal of robotics&automation,2016,31(2):100-110.
[12]MAZINAN A H,SAGHARICHIHA F.A novel hybrid PSO-ACO approach with its application to SPP[J].Evolving systems,2015,6(4):293-302.
[13]Lamini C,Benhlima S,Elbekri A.Genetic Algorithm Based Approach for Autonomous Mobile Robot Path Planning[J].Procedia computer science,2018,127:180-189.
[14]YONGBO C,YUESONG M,JIANQIAO Y,et al.Threedimensional unmanned aerial vehicle path planning using modified wolf pack search algorithm[J].Neurocomputing,2017:S0925231217309220.
[15]YE B,TANG Q,YAO J,et al.Collision-free path planning and delivery sequence optimization in noncoplanar radiation therapy[J].IEEE transactions on cybernetics,2017:1-14.
[16]魏民,杨明磊,钱锋.带有精英保留机制的混合差分化学反应算法[J].化工学报,2015,66(1):316-325.
[17]徐华东,王世勇,杨轻,等.基于柱状空间和改进A*算法的无人机规避方法[J].测控技术,2014,33(7):132-135.
[2]邓元婧,汪从敏,夏开全,等.架空输电线路通道环境的巡视技术与应用[J].浙江电力,2014(8):28-31.
[3]施孟佶,秦开宇,李凯,等.高压输电线路多无人机自主协同巡线设计与测试[J].电力系统自动化,2017,41(10):117-122.
[4]钱红昇,葛文锋,钟鸣,等.基于分层的改进[A*]算法在路径规划中的应用[J].计算机工程与应用,2014,50(7):225-229.
[5]赵晓,王铮,黄程侃,等.基于改进A*算法的移动机器人路径规划[J].机器人,2018,40(6):137-144.
[6]游晓明,刘升,吕金秋.一种动态搜索策略的蚁群算法及其在机器人路径规划中的应用[J].控制与决策,2017(3):552-556.
[7]DAS P K,BEHERA H S,TRIPATHY H K,et al.Ahybrid improved PSO-DV algorithm for multi-robot path planning in a clutter environment[J].Neurocomputing,2016,207:735-753.
[8]OLEIWI B K,ROTH H,KAZEM B I.A hybrid approach based on ACO and GA for multi objective mobile robot path planning[J].Applied mechanics and materials,2014,527:203-212.
[9]CHEN X,KONG Y,FANG X,et al.A fast two-stage ACO algorithm for robotic path planning[J].Neural computing and applications,2013,22(2):313-319.
[10]HUANG H C,TSAI C C.Global path planning for autonomous robot navigation using hybrid metaheuristic GA-PSO algorithm[C]//Proceeding of SICE Annual Conference.Tokyo,Japan:IEEE,2011:1338-1343.
[11]GENG N,GONG D,ZHANG Y.Robot path planning in an environment with many terrains based on interval multi-objective PSO[J].International journal of robotics&automation,2016,31(2):100-110.
[12]MAZINAN A H,SAGHARICHIHA F.A novel hybrid PSO-ACO approach with its application to SPP[J].Evolving systems,2015,6(4):293-302.
[13]Lamini C,Benhlima S,Elbekri A.Genetic Algorithm Based Approach for Autonomous Mobile Robot Path Planning[J].Procedia computer science,2018,127:180-189.
[14]YONGBO C,YUESONG M,JIANQIAO Y,et al.Threedimensional unmanned aerial vehicle path planning using modified wolf pack search algorithm[J].Neurocomputing,2017:S0925231217309220.
[15]YE B,TANG Q,YAO J,et al.Collision-free path planning and delivery sequence optimization in noncoplanar radiation therapy[J].IEEE transactions on cybernetics,2017:1-14.
[16]魏民,杨明磊,钱锋.带有精英保留机制的混合差分化学反应算法[J].化工学报,2015,66(1):316-325.
[17]徐华东,王世勇,杨轻,等.基于柱状空间和改进A*算法的无人机规避方法[J].测控技术,2014,33(7):132-135.