Abstract

In a wind turbine, the rolling bearing is the critical component. However, it has a high failure rate. Therefore, the failure analysis and fault diagnosis of wind power rolling bearings are very important to ensure the high reliability and safety of wind power equipment. In this study, the failure form and the corresponding reason for the failure are discussed firstly. Then, the natural frequency and the characteristic frequency are analyzed. The Empirical Mode Decomposition (EMD) algorithm is used to extract the characteristics of the vibration signal of the rolling bearing. Moreover, the eigenmode function is obtained and then filtered by the kurtosis criterion. Consequently, the relationship between the actual fault frequency spectrum and the theoretical fault frequency can be obtained. Then the fault analysis is performed. To enhance the accuracy of fault diagnosis, based on the previous feature extraction and the time-frequency domain feature extraction of the data after EMD decomposition processing, four different classifiers are added to diagnose and classify the fault status of rolling bearings and compare them with four different classifiers.

Highlights

  • With the development of wind power generation, there will be more and more large-capacity large-scale units

  • If it is possible to detect the operation of wind turbines, analyze and diagnose faults, and find the problems in time, it can avoid the faults in time

  • The vibration of rolling bearings can be divided into three categories: (1) Natural vibration; (2) Forced vibration caused by errors in the processing and assembly of parts of each part; (3) The outer and inner ring grooves or the surface of the ball have impact vibration caused by damages such as wear, scratches, pitting and spalling

Read more

Summary

Introduction

With the development of wind power generation, there will be more and more large-capacity large-scale units. The detection, diagnosis, and analysis of the bearing state are beneficial to accurately understand the working condition of the rolling bearing and avoid unnecessary losses caused by unknown accidents. Rolling bearing detection and diagnosis technology have experienced more than sixty years of development [2]. After Cooley and Tukey proposed the Fast Fourier Transform (FFT) algorithm theory in 1965 [5], the bearing diagnosis technology based on spectrum analysis has been developed rapidly [6]. Literature [5] uses the Short-time Fourier Transform (STFT) and generative neural networks methods to diagnose rolling bearing faults. Literature [10] uses the Variational Modal Decomposition Fractional Fourier Transform (VMD-FRFT) method to diagnose rolling bearing faults. Make full use of signal processing methods such as EMD to research feature extraction and failure analysis. A rolling bearing fault analysis method based on EMD K-Nearest Neighbor (EMD-KNN) is given

Rolling Bearing Vibration Mechanism and Characteristic Signal Frequency
Fault Frequency Analysis Based on EMD
Fault Analysis of Rolling Bearing Based on EMD-KNN Method
Conclusions
Full Text
Published version (Free)

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