伪证据识别在机械故障诊断中的研究

False Evidence Identification in Mechanical Fault Diagnosis

针对多传感器信息在故障诊断中可能存在伪证据,造成证据间剧烈冲突使经典证据理论合成规则失效的问题,利用Dempster-Shafer合成规则中一致证据的聚焦性,提出一种新的伪证据识别方法,构造出新证据取代原来的伪证据进行证据合成,削弱了伪证据的不良影响。在构建的基于多传感器信息融合的故障诊断识别框架中,运用改进的证据合成方法对发动机的故障进行诊断,将此诊断结论与其他证据理论的诊断结论进行了比较。结果表明,该方法可有效提高机械故障诊断的准确率,验证了此方法的可靠性和优越性。

The high evidence conflict is caused by the false evidence in multi-sensor systems, and it can make the classical evidence combination rule out of action. To reduce the negative impact of the false evidence, a new false evidence identification method is proposed, which is based on the fact that the more evidences a decision is supported by, the higher degree it has. A new evidence is restructured to take the place of the false evidence and weaken the influence of the false evidence effectively. A multi-sensor fault diagnosis system is built for engine fault diagnosis. Comparing the diagnosis result of the proposed method with the diagnosis results of other different combination rules, the diagnosis result of the proposed method turns out to be more accurate. The new false evidence identification method is proved to be credible and excellent.