基于粒子群-差分进化算法的测试优化选择方法  

Test Optimization Selection Method Based on Particle Swarm Optimization-differential Evolution Algorithm

作　　者：丁善婷[1,2] 蔡胜玲 谭梦颖 董正琼 蒋成昭 DING Shanting;CAI Shengling;TAN Mengying;DONG Zhengqiong;JIANG Chengzhao(School of Mechanical Engineering,Hubei Univ.of Tech.,Wuhan 430068,China;Hubei Key Laboratory of Modern Manufacturing Quality Engineering,Wuhan 430068,China)

机构地区：[1]湖北工业大学机械工程学院,湖北武汉430068 [2]湖北省现代制造质量工程重点实验室,湖北武汉430068

出　　处：《湖北工业大学学报》2024年第4期12-17,共6页Journal of Hubei University of Technology

基　　金：湖北工业大学博士科研启动基金(BSQD2020006);现代制造质量工程湖北省重点实验室开放基金(KFJJ-2021015)。

摘　　要：测试优化选择是装备测试性设计中关键的一步。针对其易陷入局部最优的问题,提出一种添加信息交换机制的粒子群-差分进化算法(PSO-DE)优化方法。通过融合多信号流图与贝叶斯网络,建立多维空间测试性模型后,利用PSO-DE算法实现快速精确求解。电源系统分析表明:该方法在满足测试性设计要求的前提下,搜索到的测试集合使得系统各测试性指标综合最优且收敛速度最快。相较于其它优化算法,具有收敛速度快、能收敛到全局最优等优点,由此验证了方法的可行性。Test optimization selection is a key step in equipment testability design.To avoid falling into local optima,the particle swarm optimization-differential evolutionary algorithm(PSO-DE)optimization method with added information exchange mechanism is proposed.After establishing a multi-dimensional spatial testability model by fusing multi-signal flow graph with Bayesian network,the PSO DE algorithm is used to achieve a fast and accurate solution.The analysis of the power supply system shows that the method satisfies the testability design requirements,and the searched test set makes the system optimal in terms of testability indexes and the fastest convergence rate.Compared with other optimization algorithms,it has the advantages of fast convergence to the global optimum,thus verifying the feasibility of the method.

关 键 词：测试性模型 测试优化选择 PSO-DE算法 

分 类 号：TP206[自动化与计算机技术—检测技术与自动化装置]