Abstract
This paper proposes a bearing fault feature extraction and recognition method based on particle swarm optimization optimization Maximum Correlated Kurtosis Deconvolution (MCKD) and one-dimensional convolutional neural network to solve the non-stationarity of rolling bearing fault signals, Non-linear and complex characteristics, as well as the problems of noise interference and unclear fault characteristics in the process of fault identification. First, the multi-channel signals of the rolling bearing is analyzed, in order to select the signal containing the impact component as the fault feature. Next, the signal containing the fault feature is filtered through MCKD, where the best parameters of MCKD are obtained by improving the particle swarm algorithm to achieve the feature enhancement of the main signal. Finally, a one-dimensional convolutional neural network (One Dimensional Convolutional Neural Network, 1D-CNN) is used to model the characteristic signals under different damage conditions in order to obtain the fault recognition model of the rolling bearing.The experimental results show that the method can effectively extract the main characteristic signals of the faulty bearing, and realize the accurate identification of the bearing fault in the noisy environment.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wiggins RA (1978) Minimum entropy deconvolution. Geoexploration 16(1):21–35
McDonald GL, Zhao Q, Zuo MJ (2012) Maximum correlated kurtosis deconvolution and application on gear tooth chip fault detection. Mech Syst Signal Process 33:237–255
Su L, Hairun H, Li K et al (2019) A method for extracting fault features of rolling bearings based on LCD-MCKD. J Huazhong Univ Sci Technol 47(9):19–24
Xiaoyan Z, Yongjie W (2019) Early fault diagnosis of rolling bearing based on autocorrelation analysis and MCKD. Vibrat Shock 38(24):183–188
Shangkun L, Guiji T, He Y (2016) Teager energy operator combined with MCKD early fault identification of rolling bearings. Vibrat Shock 35(15):98–102
Liyang W, Chong D, Xin W et al (2019) A motor fault diagnosis method based on sparse auto encoder. Noise Vibrat Control (5):197–202,249
Li H, Hydro Z, Xianrong Q, Yuantao S (2018) Bearing fault diagnosis method based on short-time Fourier transform and convolutional neural network. Vibrat Shock 37(19):124–131
Yuxuan Z, Li Q, Bingru Y et al (2019) End-to-end method of bearing fault diagnosis based on LSTM. Noise Vibrat Control 39(6):187–193
Xin W, Dongxing M, Li X (2021) Research on motor fault diagnosis based on acoustic signal and one-dimensional convolutional neural network. Noise Vibrat Control 41(02):125–129
Zhuang Y, Jianbo Y (2020) Gearbox fault diagnosis method based on multi-channel one-dimensional convolutional neural network feature learning. Vibra Shock 39(20):55–66
Haiyan (2019) Rolling bearing fault feature extraction method based on exponential distribution parameters. Automat Technol Applic 38(3):27–30, 42
Pu W, Li T, Xuejin G et al (2019) A composite fault feature extraction method for rolling bearings based on LMD and MSEE. Bearings 3:63–69
Gilles J (2013) Empirical wavelet transform. IEEE Trans Signal Process 61(16):3999–4010
Mohanty GKK, Raju KS (2014) Bearing fault analysis using variational mode decomposition. Int Conf Indust Inf Syst 4(2):1–6
Acknowledgements
This paper is supported by Doctoral Fund of Southwest University of Science and Technology (No.21zx7137).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, Y., Yin, X. (2023). Research on Bearing Fault Recognition Based on PSO-MCKD and 1D-CNN. In: Lee, S., Han, C., Choi, JY., Kim, S., Kim, J.H. (eds) The Proceedings of the 2021 Asia-Pacific International Symposium on Aerospace Technology (APISAT 2021), Volume 1. APISAT 2021. Lecture Notes in Electrical Engineering, vol 912. Springer, Singapore. https://doi.org/10.1007/978-981-19-2689-1_77
Download citation
DOI: https://doi.org/10.1007/978-981-19-2689-1_77
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-2688-4
Online ISBN: 978-981-19-2689-1
eBook Packages: EngineeringEngineering (R0)