Abstract

Effective filtering and noise reduction, feature extraction and fault diagnosis, and prognostics technology are important to Prognostics and Health Management (PHM) of equipment. Therefore, a multifeature fusion fault diagnosis method based on the combination of quadratic filtering and QPSO-KELM algorithm is proposed. In the quadratic filtering, stable filtering can reduce the impact of noise and fast-kurtogram can filtrate fault frequency bands with rich fault information. Then, the time-domain, frequency-domain, and time-frequency parameters of the secondary filter signal are extracted. MSSST was used to analyze the filtered signal, and the time-frequency image was obtained. The time-frequency parameter was extracted from the time-frequency image by 2DPCA, and all the extracted parameters are taken as the fusion fault feature of the gearbox. Finally, the fault feature parameters are taken as the training sample and testing sample of QPSO-KELM for training and testing to achieve the purpose of fault diagnosis. The experimental results show that the proposed method can effectively filter the noise, complete the fault mode identification of gearbox, and improve the fault diagnosis accuracy better than other methods.

Highlights

  • As a key component of mechanical transmission system, gearbox failure will lead to equipment shutdown, economic losses, and even casualties. e earlier the gearbox fault is found and repaired in time, the less the loss will be caused

  • Linear noise reduction algorithm is not suitable for processing complex vibration signals. erefore, the nonlinear filtering noise reduction method is the mainstream noise reduction method in the field of mechanical equipment fault diagnosis. e commonly used technologies include noise reduction method based on empirical mode decomposition (EMD) [1,2,3,4], noise reduction method based on wavelet transform [5,6,7], and noise reduction method based on manifold learning [8,9,10,11]

  • (3) Fault diagnosis: the extracted features are divided into training sample and test sample, which are used as the input of the QPSO-kernel extreme learning machine (KELM) model. e test sample is input into the trained QPSO-KELM, and the result of fault diagnosis can be obtained

Read more

Summary

Introduction

As a key component of mechanical transmission system, gearbox failure will lead to equipment shutdown, economic losses, and even casualties. e earlier the gearbox fault is found and repaired in time, the less the loss will be caused. E algorithm based on QPSO can optimize the structural parameters of KELM with strong global search ability, so as to improve the learning speed and classification accuracy of KELM and improve the accuracy of gearbox fault diagnosis. (1) e effect of signal filtering and noise reduction is not obvious enough, leading to the fault feature extraction which is not obvious enough. (2) e common time-frequency analysis methods have the problems of energy leakage and low resolution, which cannot extract effective two-dimensional features. Erefore, filtering noise reduction, feature extraction, and fault diagnosis technology are the focus of this paper [36]. In order to solve the above problems, denoising, feature extraction, and intelligent fault diagnosis technology are listed as the research priorities in this paper, and the following researches are carried out. (3) Fault diagnosis: the extracted features are divided into training sample and test sample, which are used as the input of the QPSO-KELM model. e test sample is input into the trained QPSO-KELM, and the result of fault diagnosis can be obtained

Basic Theory of the Proposed Method
Experimental Verification and Discussion
Findings
Comparison and Discussion
Conclusion
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