基于信息融合技术的某新型自行火炮发动机电控系统故障诊断

Fault Diagnosis of New Certain Self-propelled Gun's Engine Electric Control System Based on Information Fusion Technology

多传感器故障诊断过程中,由于多方面的原因,如测量噪声的存在、诊断知识的不完全等等,使得故障诊断存在着不确定性,影响到诊断结果的可靠性和准确度;通过分析某新型自行火炮发动机电控系统的故障特点,研究了一种基于BP神经网络及信息融合技术的多传感器故障诊断方法,将该自行火炮发动机电控系统的故障诊断过程分为子系统和系统级两级诊断,子系统采用BP神经网络实现故障模式分类,系统级运用D-S证据理论对整个系统故障进行综合决策评判;应用表明,在某个子神经网络识别存在差异的情况下,采用D-S证据理论进行融合可以有效地提高识别的准确性。

In the multi--sensor failure diagnosis process, as a result of various reasons, such as the existence of measurement noise, diagnosis knowledge incomplete and so on, it makes the fault diagnosis uncertainty and affects the reliability and the accuracy of the diagnosis result. This article according to the analysis of the engine electrically controlled system＇s fault characteristic of a new certain self--propelled gun＇s, proposes a technique based on information fusion fault diagnosis method. The diagnosis process is divided into the subsystem and the system--level, the subsystem uses the BP neural network to classify the fault mode, the system--level uses the D--S evidence theory car- ries on the comprehensive decision judgment for the whole system＇s fault. Application shows if some sub--neural network diagnosis has error, using D--S evidence theory fusion can effectively improve the accuracy of diagnosis.