A novel HI construction method based on healthy-state data training for rotating machinery components

Abstract

In predictive maintenance for rotating machinery components, constructing health indicators is crucial for improving operational efficiency and extending the equipment lifespan. However, traditional processes of building health indicators face two significant challenges: the high cost of collecting full lifecycle data and the requirement for the operating conditions of the equipment to remain consistent with those under which the indicators were developed. These limitations make health indicators expensive and time-consuming to construct and use. This article proposed a health indicator developed based on the Joint Principal Component Cumulative Empirical Distribution Model (JPCCED-HI) to overcome these challenges. This innovative method utilizes only healthy state data, combining principal component analysis with the empirical cumulative distribution function to construct a health indicator that ranges from 0 to 1, thereby eliminating the reliance on complete lifecycle data and relaxing the requirements for specific operating conditions. The effectiveness and practical benefits of JPCCED-HI are illustrated through two detailed case studies. In the first case study, we explore the impact of different parameter settings on model performance and evaluate its anti-interference capabilities in high-noise environments based on a gearbox dataset. This study demonstrates the model’s robustness in maintaining accurate health assessments despite external noise. The second case study employs a publicly available bearing dataset to compare the JPCCED-HI method against other models trained on health-stage data. This analysis reveals the superior performance of JPCCED-HI in trendability and scale similarity, affirming its effectiveness in various operational conditions. These case studies not only prove the adaptability and robustness of JPCCED-HI but also highlight its potential as a scalable solution for real-time health monitoring and predictive maintenance in industrial applications.

Keywords

Prognostics health indicator degradation assessment PCA empirical cumulative distribution function

Get full access to this article

View all access options for this article.

References

Kundu

Darpe

Kulkarni

MS.

A review on diagnostic and prognostic approaches for gears. Struct Health Monit 2021; 20(5): 2853–2893.

Polverino

Abbate

Manco

, et al. Machine learning for prognostics and health management of industrial mechanical systems and equipment: a systematic literature review. Int J Eng Bus Manage 2023; 15: 18479790231186848.

Wang

Tsui

Miao

Prognostics and health management: a review of vibration based bearing and gear health indicators. IEEE Access 2018; 6: 665–676.

Widodo

Yang

BS.

Application of relevance vector machine and survival probability to machine degradation assessment. Expert Syst Appl 2011; 38(3): 2592–2599. DOI:10.1016/j.eswa.2010.08.049.

Mosallam

Medjaher

Zerhouni

Time series trending for condition assessment and prognostics. J Manuf Technol Manage 2014; 25(4): 550–567.

Hong

Zhou

Zio

, et al. An adaptive method for health trend prediction of rotating bearings. Digital Signal Process 2014; 35: 117–123.

Zhao

Tang

Tan

Bearing remaining useful life estimation based on time–frequency representation and supervised dimensionality reduction. Measurement 2016; 86: 41–55.

Chen

Zhang

, et al. Health indicator construction of machinery based on end-to-end trainable convolution recurrent neural networks. J Manuf Syst 2020; 54: 1–11.

Guo

Lei

, et al. Machinery health indicator construction based on convolutional neural networks considering trend burr. Neurocomputing 2018; 292: 142–150.

10.

Guo

Jia

, et al. A recurrent neural network based health indicator for remaining useful life prediction of bearings. Neurocomputing 2017; 240: 98–109.

11.

Zhang

Bearing performance degradation assessment using long short-term memory recurrent network. Comput Ind 2019; 106: 14–29.

12.

Shu

, et al. Health indicator construction for roller bearing based on an unsupervised deep belief network with a novel sigmoid zero local minimum point model. Struct Health Monit 2021; 20(4): 2110–2123.

13.

Lin

Tan

A bearing fault and severity diagnostic technique using adaptive deep belief networks and Dempster–Shafer theory. Struct Health Monit 2020; 19(1): 240–261.

14.

Chen

Guo

Lin

, et al. A data-driven health monitoring method using multiobjective optimization and stacked autoencoder based health indicator. IEEE Trans Ind Inf 2021; 17(9): 6379–6389.

15.

Guo

Duan

, et al. An unsupervised feature learning based health indicator construction method for performance assessment of machines. Mech Syst Signal Process 2022; 167: 108573.

16.

Zhou

Huang

Wen

, et al. Construction of health indicators for condition monitoring of rotating machinery: a review of the research. Expert Syst Appl 2022; 203: 117297.

17.

Wang

Peng

, et al. A two-stage data-driven-based prognostic approach for bearing degradation problem. IEEE Trans Ind Inf 2016; 12(3): 924–932.

18.

Schwartz

Montero Jiménez

Vingerhoeds

, et al. An unsupervised approach for health index building and for similarity-based remaining useful life estimation. Comput Ind 2022; 141: 103716.

19.

Yan

Chen

, et al. Remaining Useful Life prediction of rolling bearings based on risk assessment and degradation state coefficient. ISA Trans 2022; 129: 413–428.

20.

Qiu

Lee

Lin

, et al. Robust performance degradation assessment methods for enhanced rolling element bearing prognostics. Adv Eng Inf 2003; 17(3–4): 127–140.

21.

Huang

, et al. Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods. Mech Syst Signal Process 2007; 21(1): 193–207.

22.

Pei

Gao

A novel machinery RUL prediction method based on exponential model and cross-domain health indicator considering first-to-end prediction time. Mech Syst Signal Process 2024; 209: 111122.

23.

Yan

Liu

Jia

Health condition identification for rolling bearing using a multi-domain indicator-based optimized stacked denoising autoencoder. Struct Health Monit 2020; 19(5): 1602–1626.

24.

Kundu

Darpe

Kulkarni

MS.

An ensemble decision tree methodology for remaining useful life prediction of spur gears under natural pitting progression. Struct Health Monit 2020; 19(3): 854–872.

25.

Tao

Fan

An intelligent approach to machine component health prognostics by utilizing only truncated histories. Mech Syst Signal Process 2014; 42(1–2): 300–313.

26.

Wang

Tsui

KL.

Theoretical investigation of the upper and lower bounds of a generalized dimensionless bearing health indicator. Mech Syst Signal Process 2018; 98: 890–901.

27.

Zhou

Zhao

, et al. Zero-shot learning for compound fault diagnosis of bearings. Expert Syst Appl 2022; 190: 116197.

28.

Stack

Habetler

Harley

Fault Classification and fault signature production for rolling element bearings in electric machines. IEEE Trans Ind Appl 2004; 40(3): 735–739.

29.

Zhao

Zheng

, et al. Fault diagnosis method based on principal component analysis and broad learning system. IEEE Access 2019; 7: 99263–99272.

30.

Dong

Qin

SJ.

A novel dynamic PCA algorithm for dynamic data modeling and process monitoring. J Process Control 2018; 67: 1–11.

31.

Jiang

Yan

Huang

Performance-driven distributed PCA process monitoring based on fault-relevant variable selection and Bayesian inference. IEEE Trans Ind Electron 2016; 63(1): 377–386.

32.

Nectoux

Gouriveau

Medjaher

, et al. PRONOSTIA: an experimental platform for bearings accelerated degradation tests. In IEEE international conference on prognostics and health management, PHM’12, volume sur CD ROM, Denver, CO, USA, pp. 1–8. IEEE Catalog Number: CPF12PHM-CDR.