(Hz)0.Entropy 2021, 23,12 ofFigure six. Time domain waveform and amplitude spectrum of two
(Hz)0.Entropy 2021, 23,12 ofFigure 6. Time domain waveform and amplitude spectrum of two noise signals (i.e., white noise and 1/f noise).Entropy 2021, 23, x FOR PEER REVIEW5 4 MEDE of white noise MDE of white noise MPE of white noise MSE of white noise4.five 4 Entropy value13 of3.5 Step 2: periodic mode element extraction. Make use of the PAVME process to extract the periMEDE of 1/f noise MDE of WOA odic mode element related to bearing faults, where the1/f noise MCC950 supplier approach is adopted 3 three MPE of 1/f noise to automatically ascertain the optimal combination parameters of VME. MSE of 1/f noise two.five Step 3: fault function extraction. Calculate the MEDE on the extracted periodic mode com2 ponent to construct multiscale fault function vector set. 2 1 Step 4: overall health condition identification. In view of k-nearest neighbor (KNN) has the less parametric15 influence and 1.five faster computing speed than help vector machine 0 5 ten 20 0 5 ten 15 20 (SVM) and artificial neural network (ANN),Scale fatorKNN classifier is chosen within this so the Scale fator step. Concretely, the constructed multiscale fault feature vector set in step three is ran(a) (b) domly divided into the education samples and testing samples, where the training Figure 7. Entropy obtained by different strategies for two two signals: (a) white noise and and (b) obtained by Figure 7. Entropy valuevaluesamples are unique solutions fornoisenoise signals: (a) white noise(b) 1/f noise. into the adopted to train the KNN model and the testing samples is fed 1/f noise. well-trained KNN model to automatically determine unique wellness conditions of 4. Proposed Fault Diagnosis Process rolling bearing. Note that, in the KNN classifier, according to the earlier studies [39], four. Proposed Fault Diagnosis Process To correctly extract function information and facts connected with bearing regional of KNN is definitely the Euclidean distance is adopted and also the variety of nearest neighbors fault and To proficiently extract feature information and facts linked with bearing regional fault and auautomatically realize the identification of bearing overall health status, this paper Chebyshevnew set as 3. Needless to say, in the KNN classifier the Mahalanobis distance, proposes a distomatically comprehend the identification ofmethod based on PAVME and MEDE, which new bearing fault diagnosis bearing overall health status, this paper proposes a also large neighbor tance and also the bigger neighbor quantity is often also adopted, but mostly consists of bearing fault diagnosis technique according to PAVME and MEDE, which primarily consists of four elements (i.e., vibration data collection, periodic mode element Tianeptine sodium salt supplier extraction, fault quantity tends to cause the low identification accuracy. Frequently speaking, the 4 elements (i.e., vibration data collection, periodic mode component Figure eight shows the flowchart from the fault feafeature extractionnearest neighbors needs to be much less than extraction, root in the instruction samnumber of and health condition identification). the square ture extractionproposed approach. Theidentification).in the proposed strategy are summarized as follows: and health situation particular measures Figure 8 shows the flowchart in the ple quantity. proposed process. The distinct actions from the proposed technique are summarized as follows: Step 1: vibration data collection. Collect the original bearing vibration signal by installing the accelerometer around the bearing fault simulation test bench.Entropy valueFigure eight. Flowchart of your proposed strategy for bearing fault identification. Figure 8. Flowchart with the proposed met.