Condition Monitoring of Electrical Rotating Parts Based on Mutual Information Feature Selection and Improved KNN Regression Algorithm

Zhiguo Dong; Jian Feng; Wencheng Zhao; Yu Wang; Haiming Niu

doi:10.6911/WSRJ.202412_10(12).0006

Authors

Zhiguo Dong
Jian Feng
Wencheng Zhao
Yu Wang
Haiming Niu

DOI:

https://doi.org/10.6911/WSRJ.202412_10(12).0006

Keywords:

Rotating parts, Mutual information, KNN regression, Condition monitoring.

Abstract

It is necessary to monitor the on - line status of the rotating parts which can cause the shutdown of the electrical equipment. In order to improve the accuracy of the prediction model, the mutual information is used to select the features of the original data. Aiming at the condition monitoring, the distance measurement formula of KNN regression algorithm is improved, and the prediction accuracy is improved by about 80%. Taking the bearing of a wind turbine as an example, the improved KNN regression algorithm can be used for fault warning three weeks in advance.

Downloads

Download data is not yet available.

References

[1] WANG Rui, CHEN Zhigang.Syudy on centrifugal gas compressor bearing fault character obtaining based on data mining[J]. Oil Field Equipment,2006(05):23-26.

[2] XIONG Zhongjie,QU Yingning,FENG Yanhui,et al. Fault analysis of wind turbine pitch system based on machine learning[J]. Acta Energiae Solaris Sinica,2020,41(05):85-90.

[3] Tautz-Weinert J , Watson S J . Using SCADA data for wind turbine condition monitoring – a review[J]. Iet Renewable Power Generation, 2017, 11(4):382-394.

[4] WANG Ziqi, LIU Changliang, Liu Shuai.Condition monitoring of wind turbine gearbox based on ensemble nonlinear state estimation technique and soft fuzzy clustering [J]. Chinese Journal of Scientific Instrument,2019,40(07):138-146.

[5] SUN Qunli, ZHOU Ying, LIU Changliang.Research on fault diagnosis of wind turbine based on LARS feature selection[J]. Renewable Energy Resources,2020,38(10):1349-1354.

[6] LIU Shuai, LIU Changliang, ZHEN Chenggang.Fault warning method for wind turbine based on classified data reconstuction [J]. Chinese Journal of Scientific Instrument,2019,40(08):1-11.

[7] LI Jianguo, HE Yunpeng, LI Bowen. Short-term traffic forecast of stereo garage based on improved KNN algorithm[J]. Measurement & Control Technology, 2020,39(06):115-120.

[8] XU Junling, ZHOU Yuming, CHEN Lin,et al.An unsupervised feature selection approach based on mutual information [J]. Journal of Computer Research and Development,2012(02):158-168.

[9] Peng H , Long F , Ding C . Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2005, 27(8):1226-1238.

[10] PAN Feng, WANG Jiandong, NIU Ben.Unsupervised feature selection approach based on spectral analysis [J]. Journal of Computer Applications, 2011,31(08):2108-2110+2114.

[11] Xiangyuan Gu, Jichang Guo, Chongyi Li, et al. A feature selection algorithm based on redundancy analysis and interaction weight. 2020, :1-15.

[12] A M P , A S T , B K D . Unsupervised feature selection and cluster center initialization based arbitrary shaped clusters for intrusion detection[J]. Computers & Security, 2020, 99.

[13] SHEN Haoxin, LV Chengde, ZHANG Rui. Application research on SPC in quality stability control of safety command receiver-decoder [J]. Quality and Reliability, 2020(02):51-55.