摘要
针对故障诊断对象的多故障特性 ,为使系统在诊断对象的各子故障域的诊断精度达到最高 ,给出了可以适合于在多故障情况下找到一个最优联盟结构的算法 .首先 ,给出了各个诊断方法代理和代理联盟的诊断能力的定义 ,并且提出将联盟的诊断能力作为评判标准 ;然后 ,在各子故障域同时进行联盟结构的搜索 ,寻找出具有最高联盟诊断能力的结构形式 ,并改变联盟矩阵中相应单元的值 ;最后 ,根据联盟矩阵确定各子故障域的联盟结构 。
In allusion to the multi-fault characteristic of the object, to get the maximum diagnosis precision in every fault region, an algorithm is presented that can search an optimal coalition structure which is fit for multi fault diagnosis. Firstly, the definitions of the diagnosis abilities of a diagnosis agent and a coalition are given, and the diagnosis ability of a coalition is regarded as a criterion in judging the coalition; then searching in each fault region, to find out the coalition formation having the highest diagnosis ability, and have the value of the coalition matrix changed accordingly; Finally, according to the coalition matrix, the coalition structure in each fault region is determined, and the coalition of the object is formed.
出处
《东南大学学报(自然科学版)》
EI
CAS
CSCD
北大核心
2003年第1期49-52,共4页
Journal of Southeast University:Natural Science Edition
基金
国家自然科学基金资助项目 (5990 50 0 5)
国家高技术研究发展计划 ( 86 3计划 )经费资助项目( 2 0 0 1AA4 2 32 4 0 )