An Information Fusion Fault Diagnosis Method Based on Dimensionless Indicators With Static Discounting Factor and KNN

For petrochemical rotating machinery and equipment, the reliability of the diagnostic evidence is affected by uncertain factors, causing conflicts between evidence provided by the various information sources, and thus affecting the validity of the fault diagnosis. This paper presents an information fusion fault diagnosis method that is based on a static discounting factor and combines K-nearest neighbors (KNNs) with dimensionless indicators. The method uses evidence reasoning to process the uncertainty and accuracy of the information through the KNN algorithm and dimensionless indicators to turn petrochemical machinery sensor input signals into the reliability of structure framework, according to the static discount factor, after correction evidence and evidence theory formula was used to fusion and, based on the fusion result, the fault type diagnosis decision-making. Experimental results show that the method can effectively reduce the influence of unreliable factors on the fusion results, thus allowing more accurate decision making.