基于改进离散粒子群算法的传感器优化配置  

Optimal Sensor Placement Based on Improved Discrete PSO Algorithm

作　　者：马羚[1] 李海军[1] 王成刚[2] 李国峰[3] 

机构地区：[1]海军航空工程学院兵器科学与技术系 [2]海军航空工程学院基础实验部 [3]中国人民解放军92154部队导弹技术队

出　　处：《电子学报》2015年第12期2408-2413,共6页Acta Electronica Sinica

基　　金：国家部委"十二五"预先研究项目(No.51319040102)

摘　　要：传感器优化配置是实现航空设备故障预测与健康管理(Prognostics and Health Management,PHM)系统设计的基础和保证.本文首先对系统的故障-传感器相关性矩阵进行了改进,在此基础上根据系统测试性指标要求建立了考虑传感器故障率的约束优化模型,并采用一种改进的离散粒子群算法求解.算法根据传感器优化配置的特点设计了粒子个体适应度计算方法,惯性权重则基于群体早熟程度自适应调整.仿真实例验证了本文方法的有效性,优化结果满足系统各项测试性指标要求,可为航空设备PHM系统的传感器优化配置提供有效指导.Optimal sensor placement is foundation and guarantee for design of（Prognostics and Health Management,PHM）system for avionics.The fault-sensor dependency matrix is improved which considers the failure probability of the sensors firstly.Based on this,the constraint optimization model is established and the improved discrete PSO algorithm is used to solve the problem.The algorithm designs the fitness function by the characteristics of optimal sensor placement,and the inertia weight is adjusted adaptively based on the swarm＇s premature degree which can avoid algorithm limits to local extremum and accelerate the convergence speed.The simulation examples demonstrate that the proposed method is effective,and the optimization results meet all the testability index requirements of system,and it can provide effective direction to the optimal sensor placement of PHM system for avionics.

关 键 词：传感器优化配置 测试性指标 传感器故障率 离散粒子群算法 

分 类 号：TN432[电子电信—微电子学与固体电子学]