关于系统级故障诊断的烟花-反向传播神经网络算法  

A Firewoks Algorithm-Back Propagation Fault Diagnosis Algorithm for System-level Fault Diagnosis

作　　者：归伟夏[1] 陆倩 苏美力 GUI Weixia;LU Qian;SU Meili(School of Computer and Electronics Information,Guangxi University,Nanning 530004,China)

机构地区：[1]广西大学计算机与电子信息学院,南宁530004

出　　处：《电子与信息学报》2020年第5期1102-1109,共8页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(61862003,61862004);广西研究生教育创新计划资助项目(YCSW2019036)。

摘　　要：为了更快速且精确地诊断出大规模多处理器系统中的故障单元,该文首次将改进的烟花算法和反向传播(BP)神经网络相结合,提出一种新的系统级故障诊断算法-烟花-反向传播神经网络故障诊断算法(FWA-BPFD)。首先,在烟花算法中引入双种群策略、协作算子以及最优算子,设计新的适应度函数,优化变异算子、映射规则和选择策略。然后,利用烟花算法全局搜索能力和局部搜索能力的自调节机制,优化BP神经网络中的权值和阈值的寻优过程。仿真实验结果表明,该文算法相较于其他算法不仅有效地降低了迭代次数和训练时间,而且还进一步提高了诊断精度。In order to diagnose fault units in the large-scale multiprocessor systems more quickly and accurately,a system-level fault diagnosis algorithm-FireWorks Algorithm-Back Propagation Fault Diagnosis(FWABPFD) based on fireworks algorithm and Back Propagation(BP) neural network is proposed. Firstly, two population strategy, cooperative operator and optimal operator are introduced into fireworks algorithm. A new fitness function is designed, and the mutation operator, mapping rule and selection strategy are optimized.Then, the optimization process of weight and threshold value in BP neural network is optimized by the selfregulating mechanism of global and local searching ability of fireworks algorithm. Simulation results show that compared with other algorithms, this algorithm not only reduces the number of iterations and training time,but also improves the accuracy of diagnosis.

关 键 词：系统级故障诊断 烟花算法 反向传播神经网络 PMC模型 烟花-反向传播神经网络算法 

分 类 号：TP306[自动化与计算机技术—计算机系统结构]