电子部件故障诊断的Dempster-Shafer信息融合算法

Dempster-Shafer information fusion algorithmof electronic equipment fault diagnosis

针对电路故障元件诊断的不确定性问题,给出了光电雷达电子部件故障定位的多传感器Dempster-Shafer(DS)信息融合方法.通过测试电路中的被诊断元件的工作温度和工作电压,得出了DS证据理论中两传感器对各待诊断元件的信度函数分配,再分别利用利用模糊规则和DS联合规则得到融合后的信度函数分配,从而确定故障元件.单传感器诊断与融合诊断的结果比较说明多传感器融合算法具有较高的准确性,而模糊融合算法与DS算法的结果比较则说明DS算法在故障诊断方面更具有优越性.

In order to reduce uncertain problem of circuit fault diagnosis,an information fusion method,which is for photovoltaic radar electronic equipment fault diagnosis based on Dempster_Shafer (DS) evidential theory and fuzzy logical theory,is presented.According to the measurement results of the temperature and the voltage of circuit component,the belief function assignment of two sensors to circuit component,and the fusion belief function assignment was obtained by using DS rule and fuzzy method respectively,then fault component was found.By comparing the diagnosis results based on separate original data and fused date respectively,the latter was proved more accurate;By comparing fuzzy fusion method with DS algorithm,the DS fusion algorithm is more accurate in the circuit fault recognition.