CPSO-NP优化算法及其在TE过程中应用  

Chaotic Particle Swarm Optimization with Natural Selection and Predatory Search(CPSO-NP) and Its Application in TE Process

作　　者：周乐 刘昕明[1] 周鹤龄 ZHOU Le;LIU Xin-ming;ZHOU He-ling(School of Electrical and Control Engineering, Liaoning Technical University,Huludao 125105,China;Kreal Technology Co., Ltd.,Suzhou 215200,China)

机构地区：[1]辽宁工程技术大学电气与控制工程学院,辽宁葫芦岛125105 [2]苏州卡瑞电子科技公司,江苏苏州215200

出　　处：《测控技术》2018年第7期32-36,41,共6页Measurement & Control Technology

基　　金：国家自然科学基金资助项目(51274118);辽宁省教育厅科学研究一般项目(LJYL013);辽宁省创新团队基金项目(LT2010047)

摘　　要：为有效平衡粒子群算法的探索和开发能力,解决粒子群局部最优、收敛速度慢等问题,提出了基于捕食搜索和自然选择的混沌粒子群算法。该算法借鉴自然选择中适者生存的进化机制以提高算法的收敛速度;且捕食搜索策略调节限制级别平衡全局搜索和局部搜索,优化搜索性能;通过函数测试和化工TE的故障诊断,结果表明:所提算法计算精度高、收敛速度快,能准确地对SVM的参数进行寻优,提高了故障诊断的准确性。In order to effectively balance the exploration and development capabilities and overcome the shortcomings of local minima and low convergence in particle swarm optimization（PSO）, a Chaotic PSO algorithm with natural selection and predatory search（CPSO-NP） is proposed. The evolutionary mechanism of survival of the fittest in natural selection was employed to improve the convergence rate of the algorithm, and the predatory search can balance the global search and the local search by adjusting the level of restriction so as to optimize the search performance. The results of functional tests and chemical TE fault diagnosis show that the CPSO-NP algorithm can search the optimal parameters of SVM accurately with high precision and fast convergence, and improve the accuracy of fault diagnosis.

关 键 词：粒子群算法 混沌 自然选择 捕食搜索 故障诊断 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]