为了获得更多的故障信息,全面了解故障特征,采用多个不同的传感器共同监测是一种有效的方法途径.而实际现场工业设备运行环境非常复杂,使得传感器采集到的信息包含很多来自自然环境或人为的干扰噪声,导致采集到的故障信息冲突.针对这一问题,提出了一种基于多传感器信息融合的故障诊断方法.首先求得各证据之间的证据距离,根据证据距离值的大小再修改证据,然后利用D-S证据理论进行信息融合,提高了诊断的可靠性和准确度.实验验证了该方法切实可行.
In order to obtain more fault information and form a full picture of fault characteristics,using different sensor monitoring is an effective way,but the actual operation environment is very complex.The industrial equipment field makes sensors collect the information containing a lot of noises from the natural environment or artificial interference,which often leads to the conflicts between sensors of the collected fault information.In order to solve this problem,a fault diagnosis method based on multi-sensor information fusion was presented,first of all,the evidence of the distance between various evidences were acquired and modified later according to the size of the evidence distance,and then information fusion was conducted by employing the D-S evidence theory.The reliability and accuracy of the diagnosis were improved,and the feasibility of the method was verified by the experiment as well.