Remaining Useful Life Prediction of Kernel Density Estimation Based on Adaptive Window Width

Hui Shi; Hui Kang; Zhizhuang Zhang; Xiuquan Sun; Fengshou Gu

doi:10.1007/978-3-030-75793-9_65

Remaining Useful Life Prediction of Kernel Density Estimation Based on Adaptive Window Width

Hui Shi, Hui Kang, Zhizhuang Zhang, Xiuquan Sun, Fengshou Gu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

The kernel density estimation method is completely based on the data instead of the assumption distribution models considering the data-driven remaining useful life prediction. Among them, window width is an important parameter, and the selection of window width directly affects the accuracy of the final prediction results. To solve these problems, a kernel density remaining useful life prediction method based on the real-time updating of the adaptive window width is proposed. Firstly, when the new degraded data is obtained, the k-nearest neighbor method is used to update the data density in real-time, and the window width of the adaptive kernel density estimation is used. Further, the kernel density estimation model is constructed based on the degraded data of the system, and the probability density function of the remaining useful life is obtained, and the remaining useful life of the system is predicted. Finally, the proposed method is applied to the degradation modeling and remaining useful life prediction of gears. Results obtained demonstrate the accuracy and effectiveness of the method.

Original language	English
Title of host publication	Proceedings of IncoME-V & CEPE Net-2020
Subtitle of host publication	Condition Monitoring, Plant Maintenance and Reliability
Editors	D. Zhen, D. Wang, T. Wang, H. Wang, B. Huang, J. K. Sinha, A. D. Ball
Publisher	Springer, Cham
Pages	665-682
Number of pages	18
Volume	105
ISBN (Electronic)	9783030757939
ISBN (Print)	9783030757922
DOIs	https://doi.org/10.1007/978-3-030-75793-9_65
Publication status	Published - 16 May 2021
Event	5th International Conference on Maintenance Engineering: IncoME-V and the 2020 Annual Conference of the Centre for Efficiency and Performance Engineering Network: IncoME-V & CEPE Net-2020 - Zhuhai, China Duration: 23 Oct 2020 → 25 Oct 2020 Conference number: 5

Publication series

Name	Mechanisms and Machine Science
Publisher	Springer
Volume	105
ISSN (Print)	2211-0984
ISSN (Electronic)	2211-0992

Conference

Conference	5th International Conference on Maintenance Engineering: IncoME-V and the 2020 Annual Conference of the Centre for Efficiency and Performance Engineering Network
Country/Territory	China
City	Zhuhai
Period	23/10/20 → 25/10/20

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-030-75793-9_65Licence: Unspecified

Cite this

Shi, H., Kang, H., Zhang, Z., Sun, X., & Gu, F. (2021). Remaining Useful Life Prediction of Kernel Density Estimation Based on Adaptive Window Width. In D. Zhen, D. Wang, T. Wang, H. Wang, B. Huang, J. K. Sinha, & A. D. Ball (Eds.), Proceedings of IncoME-V & CEPE Net-2020: Condition Monitoring, Plant Maintenance and Reliability (Vol. 105, pp. 665-682). (Mechanisms and Machine Science; Vol. 105). Springer, Cham. https://doi.org/10.1007/978-3-030-75793-9_65

Shi, Hui ; Kang, Hui ; Zhang, Zhizhuang et al. / Remaining Useful Life Prediction of Kernel Density Estimation Based on Adaptive Window Width. Proceedings of IncoME-V & CEPE Net-2020: Condition Monitoring, Plant Maintenance and Reliability. editor / D. Zhen ; D. Wang ; T. Wang ; H. Wang ; B. Huang ; J. K. Sinha ; A. D. Ball. Vol. 105 Springer, Cham, 2021. pp. 665-682 (Mechanisms and Machine Science).

@inproceedings{fc2c50bbc4ea478f9b3e63adc8a1ef8b,

title = "Remaining Useful Life Prediction of Kernel Density Estimation Based on Adaptive Window Width",

abstract = "The kernel density estimation method is completely based on the data instead of the assumption distribution models considering the data-driven remaining useful life prediction. Among them, window width is an important parameter, and the selection of window width directly affects the accuracy of the final prediction results. To solve these problems, a kernel density remaining useful life prediction method based on the real-time updating of the adaptive window width is proposed. Firstly, when the new degraded data is obtained, the k-nearest neighbor method is used to update the data density in real-time, and the window width of the adaptive kernel density estimation is used. Further, the kernel density estimation model is constructed based on the degraded data of the system, and the probability density function of the remaining useful life is obtained, and the remaining useful life of the system is predicted. Finally, the proposed method is applied to the degradation modeling and remaining useful life prediction of gears. Results obtained demonstrate the accuracy and effectiveness of the method.",

keywords = "Adaptive window width, K-nearest neighbor, Kernel density estimation, Remaining useful life",

author = "Hui Shi and Hui Kang and Zhizhuang Zhang and Xiuquan Sun and Fengshou Gu",

note = "Funding Information: The first author was supported by the scholarship from China Scholarship Council (CSC No. 201808140236). Funding Information: Acknowledgements. The authors would like to thank the Youth Program of the National Natural Science Foundation of China (No. 61703297, 71701140); The Natural Science Foundation of Shanxi Province, China (No. 201801D121166, 201901D111264); the Ph.D. Research Startup Foundation of Taiyuan University of Science & Technology (No. 20202028). The authors also gratefully acknowledge the helpful comments and suggestions from the anonymous reviewers, which significantly helped to improve this paper. Publisher Copyright: {\textcopyright} 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.; 5th International Conference on Maintenance Engineering: IncoME-V and the 2020 Annual Conference of the Centre for Efficiency and Performance Engineering Network : IncoME-V & CEPE Net-2020 ; Conference date: 23-10-2020 Through 25-10-2020",

year = "2021",

month = may,

day = "16",

doi = "10.1007/978-3-030-75793-9_65",

language = "English",

isbn = "9783030757922",

volume = "105",

series = "Mechanisms and Machine Science",

publisher = "Springer, Cham",

pages = "665--682",

editor = "D. Zhen and D. Wang and T. Wang and H. Wang and B. Huang and Sinha, {J. K.} and Ball, {A. D.}",

booktitle = "Proceedings of IncoME-V & CEPE Net-2020",

address = "Switzerland",

}

Shi, H, Kang, H, Zhang, Z, Sun, X & Gu, F 2021, Remaining Useful Life Prediction of Kernel Density Estimation Based on Adaptive Window Width. in D Zhen, D Wang, T Wang, H Wang, B Huang, JK Sinha & AD Ball (eds), Proceedings of IncoME-V & CEPE Net-2020: Condition Monitoring, Plant Maintenance and Reliability. vol. 105, Mechanisms and Machine Science, vol. 105, Springer, Cham, pp. 665-682, 5th International Conference on Maintenance Engineering: IncoME-V and the 2020 Annual Conference of the Centre for Efficiency and Performance Engineering Network, Zhuhai, China, 23/10/20. https://doi.org/10.1007/978-3-030-75793-9_65

Remaining Useful Life Prediction of Kernel Density Estimation Based on Adaptive Window Width. / Shi, Hui; Kang, Hui; Zhang, Zhizhuang et al.

Proceedings of IncoME-V & CEPE Net-2020: Condition Monitoring, Plant Maintenance and Reliability. ed. / D. Zhen; D. Wang; T. Wang; H. Wang; B. Huang; J. K. Sinha; A. D. Ball. Vol. 105 Springer, Cham, 2021. p. 665-682 (Mechanisms and Machine Science; Vol. 105).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Remaining Useful Life Prediction of Kernel Density Estimation Based on Adaptive Window Width

AU - Shi, Hui

AU - Kang, Hui

AU - Zhang, Zhizhuang

AU - Sun, Xiuquan

AU - Gu, Fengshou

N1 - Conference code: 5

PY - 2021/5/16

Y1 - 2021/5/16

N2 - The kernel density estimation method is completely based on the data instead of the assumption distribution models considering the data-driven remaining useful life prediction. Among them, window width is an important parameter, and the selection of window width directly affects the accuracy of the final prediction results. To solve these problems, a kernel density remaining useful life prediction method based on the real-time updating of the adaptive window width is proposed. Firstly, when the new degraded data is obtained, the k-nearest neighbor method is used to update the data density in real-time, and the window width of the adaptive kernel density estimation is used. Further, the kernel density estimation model is constructed based on the degraded data of the system, and the probability density function of the remaining useful life is obtained, and the remaining useful life of the system is predicted. Finally, the proposed method is applied to the degradation modeling and remaining useful life prediction of gears. Results obtained demonstrate the accuracy and effectiveness of the method.

AB - The kernel density estimation method is completely based on the data instead of the assumption distribution models considering the data-driven remaining useful life prediction. Among them, window width is an important parameter, and the selection of window width directly affects the accuracy of the final prediction results. To solve these problems, a kernel density remaining useful life prediction method based on the real-time updating of the adaptive window width is proposed. Firstly, when the new degraded data is obtained, the k-nearest neighbor method is used to update the data density in real-time, and the window width of the adaptive kernel density estimation is used. Further, the kernel density estimation model is constructed based on the degraded data of the system, and the probability density function of the remaining useful life is obtained, and the remaining useful life of the system is predicted. Finally, the proposed method is applied to the degradation modeling and remaining useful life prediction of gears. Results obtained demonstrate the accuracy and effectiveness of the method.

KW - Adaptive window width

KW - K-nearest neighbor

KW - Kernel density estimation

KW - Remaining useful life

UR - http://www.scopus.com/inward/record.url?scp=85106002704&partnerID=8YFLogxK

UR - https://www.springer.com/gp/book/9783030757922

U2 - 10.1007/978-3-030-75793-9_65

DO - 10.1007/978-3-030-75793-9_65

M3 - Conference contribution

AN - SCOPUS:85106002704

SN - 9783030757922

VL - 105

T3 - Mechanisms and Machine Science

SP - 665

EP - 682

BT - Proceedings of IncoME-V & CEPE Net-2020

A2 - Zhen, D.

A2 - Wang, D.

A2 - Wang, T.

A2 - Wang, H.

A2 - Huang, B.

A2 - Sinha, J. K.

A2 - Ball, A. D.

PB - Springer, Cham

T2 - 5th International Conference on Maintenance Engineering: IncoME-V and the 2020 Annual Conference of the Centre for Efficiency and Performance Engineering Network

Y2 - 23 October 2020 through 25 October 2020

ER -

Shi H, Kang H, Zhang Z, Sun X, Gu F. Remaining Useful Life Prediction of Kernel Density Estimation Based on Adaptive Window Width. In Zhen D, Wang D, Wang T, Wang H, Huang B, Sinha JK, Ball AD, editors, Proceedings of IncoME-V & CEPE Net-2020: Condition Monitoring, Plant Maintenance and Reliability. Vol. 105. Springer, Cham. 2021. p. 665-682. (Mechanisms and Machine Science). Epub 2021 May 16. doi: 10.1007/978-3-030-75793-9_65

Remaining Useful Life Prediction of Kernel Density Estimation Based on Adaptive Window Width

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this