Abstract
Traditional motor bearing fault diagnosis methods lack effective feature extraction and high fault diagnosis accuracy. In this paper, a method for combining wavelet energy entropy and cubic KNN algorithm to motor fault diagnosis was proposed based on the Case Western Reserve University Bearing Data Center's experimental data. The diagnostic results of the cubic KNN algorithm without introducing the vibration signal feature value of motor bearing were compared with that of the cubic KNN algorithm after introducing time-domain features, frequency domain features, and wavelet entropy feature to verify the diagnostic effect of the proposed method. The results showed that the KNN diagnosis error rate of motor bearing equipment fault diagnosis is effectively reduced from 0.22 to 0, the diagnostic accuracy was significantly improved by 94.34 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup> and the method has high application value in the fault diagnosis of motor bearings.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call