多传感器信息融合的智能故障诊断

针对传统故障诊断方法只利用单一参数对复杂系统进行诊断具有信息不完备和不确定性的问题,提出了一种基于PCA和D-S证据理论的多传感器信息融合故障诊断方法.该方法基于PCA对信息融合的多维数据进行降维处理,并利用证据理论实现对非精确信息的正确推理,解决了信息融合数据的组合爆炸问题,从而得到精确的诊断结果.将该方法应用于火电机组的汽包锅炉给水控制系统故障诊断中,实现了对控制系统中主要参数的故障检测,有效提高了控制系统工作的可靠性.

Intelligent fault diagnosis strategy of multi-sensor data fusion

According to the problem of multi-sensor information fusion of complex systems,an intelligent fault diagnosis method based on PCA and DS evidence theory is proposed.Then,the characteristic of data dimension reduction of PCA and the completeness of fault diagnosis,the advantage of presenting and reasoning inaccurate information of evidence theory are utilized,the problem of nonuniqueness of fault isolation of PCA and combination explosion of evidence theory is solved.Furthermore,the capability of fault detection and separation is improved significantly.