A Diagnosis Method for Rotation Machinery Faults Based on Dimensionless Indexes Combined withK-Nearest Neighbor Algorithm

Abstract

It is difficult to well distinguish the dimensionless indexes between normal petrochemical rotating machinery equipment and those with complex faults. When the conflict of evidence is too big, it will result in uncertainty of diagnosis. This paper presents a diagnosis method for rotation machinery fault based on dimensionless indexes combined withK-nearest neighbor (KNN) algorithm. This method uses aKNN algorithm and an evidence fusion theoretical formula to process fuzzy data, incomplete data, and accurate data. This method can transfer the signals from the petrochemical rotating machinery sensors to the reliability manners using dimensionless indexes andKNN algorithm. The input information is further integrated by an evidence synthesis formula to get the final data. The type of fault will be decided based on these data. The experimental results show that the proposed method can integrate data to provide a more reliable and reasonable result, thereby reducing the decision risk.

Machine learning for fault analysis in rotating machinery: A comprehensive review

“…It is seen in Fig. 5 that the majority of the studies are considered bearing faults [ [71] , [72] , [73] , [74] , [75] ] followed by rotor faults [ [76] , [77] , [78] , [79] , [80] ], gear faults [ [81] , [82] , [83] , [84] , [85] ], shaft faults [ 21 , 46 , 71 , 72 , 86 ], stator [ 7 , 25 , 87 ], and other component faults [ 28 , [88] , [89] , [90] ]. The pie chart shown in Fig.…”

“…Regarding the fault type percentiles shown in Fig. 9 , it is seen that the majority of the studies focused on only four types of bearing faults whereas other faults such as house eccentricity, aging, journal bearing faults, oil issues, wear, and clearance problems are barely investigated [ 6 , 22 , 31 , 72 , 93 , 123 ]. Besides, compound faults are rarely considered [ 10 , 40 , 74 , 106 , 107 ], yet they are essential in FD and FP procedures of rotating machines.…”

Detection of Deterioration of Three-phase Induction Motor using Vibration Signals

“…The next step is the classification of feature vectors. The authors used the NN classifier [27], [28], [29], LDA [30], [31], and SVM [25], [32], [33]. However, other classifiers could be also used, for example neural network [34], [35].…”