论文部分内容阅读
针对单一传感器节点只能采集通风机的部分信息,故障诊断结果具有片面性,提出一种多传感器融合的通风机故障诊断方法。首先采用单个传感器提取其状态信息,并采用小波分析提取通风机状态特征,然后采用神经网络对单一传感器进行通风机故障诊断,然后将每一个诊断结果作为一个证据,采用D-S证据理论进行信息融合,得到最终诊断结果,最后采用仿真实验进行了性能测试和验证。结果表明,本文方法可以在很短时间内得到较高的通风机故障诊断正确率,提高风机故障诊断精度和效率。
For a single sensor node can only collect some of the fan information, fault diagnosis results with one-sidedness, proposed a multi-sensor fusion fan fault diagnosis method. Firstly, a single sensor was used to extract the state information of the ventilator, and the characteristics of the ventilator were extracted by wavelet analysis. Then, a single sensor was diagnosed by using neural network to diagnose the ventilator fault. Then, each diagnostic result was taken as one evidence, and the DS evidence theory was used to fuse information. Get the final diagnosis result, finally use the simulation experiment to carry on the performance test and the verification. The results show that the proposed method can get a higher accuracy of fan fault diagnosis in a very short period of time and improve the accuracy and efficiency of fan fault diagnosis.