Skip to main content
Top
Published in: The International Journal of Advanced Manufacturing Technology 5-6/2024

27-12-2023 | ORIGINAL ARTICLE

Time to failure prediction of rotating machinery using dynamic feature extraction and gaussian process regression

Authors: Wo Jae Lee, John W. Sutherland

Published in: The International Journal of Advanced Manufacturing Technology | Issue 5-6/2024

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Recent advances in sensor technology and computing capabilities have enabled the creation of data-driven models that can support real-time decision making. Such a decision aid can allow for predictive maintenance (PdM) to be undertaken on a much greater scale in manufacturing plants. PdM includes data-driven prognostics and health management (PHM). A key element in developing prognostic models involves the acquisition of high-quality data, traditionally achieved through feature extraction methods to distill meaningful insights from extensive and noisy datasets. However, such methods may not handle noisy data well or address measurement errors adequately, potentially resulting in extracted features that inadequately represent the degradation process as a machine approaches failure or fault. Also, effects of sensor types on the feature extraction and prediction model have not been much explored yet. To overcome this limitation, we proposed a solution which involves dynamic feature extraction where a statistical penalty is introduced to mitigate the influence of noisy statistical features within a monotonic trend. Subsequently, the features extracted using this method are utilized to construct a health indicator (HI). Leveraging historical HI values, a probabilistic regression model may be used to forecast the time to failure (TTF) of rotating machinery with uncertainty propagation. To validate the proposed method, acceleration data were collected from rotating machinery for several run-to-failure cases. The proposed method is demonstrated to provide excellent forecasts of TTF for both accelerometer types.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Footnotes
1
When a machine failure occurs, many in the literature describe this as the "end of useful life." But, of course, in many cases the machine can be repaired to put it back into service life. For such a case, the authors prefer the phrase "time to failure (TTF)" over the frequently used "remaining useful life (RUL)." For elements that cannot be repaired, such as a bearing, RUL is certainly appropriate.
 
2
In all, roughly 7000 h of data were collected on each of the three pumps using the two types of accelerometers. Every hour a sample was collected from each accelerometer (sampling rates of 12,000 Hz for piezo and 545 Hz for MEMS). These data were all stored and could be reviewed as necessary. In practice, the pumps were operated using a run-to-failure approach. When a failure occurred, the data leading up to the failure was analyzed. The data records in Fig. 5 do not show the entire "run-to-failure," but rather the portion of the signal in the days leading up to the failure, i.e., "function to failure."
 
Literature
1.
go back to reference Hu Q, Si XS, Zhang QH, Qin AS (2020) A rotating machinery fault diagnosis method based on multi-scale dimensionless indicators and random forests. Mech Syst Signal Process 139:106609CrossRef Hu Q, Si XS, Zhang QH, Qin AS (2020) A rotating machinery fault diagnosis method based on multi-scale dimensionless indicators and random forests. Mech Syst Signal Process 139:106609CrossRef
3.
go back to reference Qin A, Zhang Q, Hu Q et al (2017) Remaining useful life prediction for rotating machinery based on optimal degradation indicator. Shock Vib 2017 Article ID 6754968, pp 12 Qin A, Zhang Q, Hu Q et al (2017) Remaining useful life prediction for rotating machinery based on optimal degradation indicator. Shock Vib 2017 Article ID 6754968, pp 12
4.
go back to reference Lee WJ, Wu H, Huang A, Sutherland JW (2020) Learning via acceleration spectrograms of a DC motor system with application to condition monitoring. Int J Adv Manuf Technol 106:803–816CrossRef Lee WJ, Wu H, Huang A, Sutherland JW (2020) Learning via acceleration spectrograms of a DC motor system with application to condition monitoring. Int J Adv Manuf Technol 106:803–816CrossRef
5.
go back to reference Bektas O, Jones JA, Sankararaman S et al (2019) A neural network filtering approach for similarity-based remaining useful life estimation. Int J Adv Manuf Technol 101:87–103CrossRef Bektas O, Jones JA, Sankararaman S et al (2019) A neural network filtering approach for similarity-based remaining useful life estimation. Int J Adv Manuf Technol 101:87–103CrossRef
10.
go back to reference Lee WJ, Mendis GP, Sutherland JW (2019) Development of an intelligent tool condition monitoring system to identify manufacturing tradeoffs and optimal machining conditions. Procedia Manuf 33:256–263CrossRef Lee WJ, Mendis GP, Sutherland JW (2019) Development of an intelligent tool condition monitoring system to identify manufacturing tradeoffs and optimal machining conditions. Procedia Manuf 33:256–263CrossRef
13.
go back to reference Kimotho JK, Sextro W (2014) An approach for feature extraction and selection from non-trending data for machinery prognosis. Proc Second Eur Conf Progn Heal Manag Soc 5:1–8 Kimotho JK, Sextro W (2014) An approach for feature extraction and selection from non-trending data for machinery prognosis. Proc Second Eur Conf Progn Heal Manag Soc 5:1–8
14.
go back to reference Ren L, Cui J, Sun Y, Cheng X (2017) Multi-bearing remaining useful life collaborative prediction: A deep learning approach. J Manuf Syst 43:248–256CrossRef Ren L, Cui J, Sun Y, Cheng X (2017) Multi-bearing remaining useful life collaborative prediction: A deep learning approach. J Manuf Syst 43:248–256CrossRef
15.
go back to reference Ben AJ, Chebel-Morello B, Saidi L et al (2015) Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network. Mech Syst Signal Process 56:150–172CrossRef Ben AJ, Chebel-Morello B, Saidi L et al (2015) Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network. Mech Syst Signal Process 56:150–172CrossRef
16.
go back to reference Park J, Hamadache M, Ha JM et al (2019) A positive energy residual (PER) based planetary gear fault detection method under variable speed conditions. Mech Syst Signal Process 117:347–360CrossRef Park J, Hamadache M, Ha JM et al (2019) A positive energy residual (PER) based planetary gear fault detection method under variable speed conditions. Mech Syst Signal Process 117:347–360CrossRef
17.
go back to reference Guo L, Li N, Jia F et al (2017) A recurrent neural network based health indicator for remaining useful life prediction of bearings. Neurocomputing 240:98–109CrossRef Guo L, Li N, Jia F et al (2017) A recurrent neural network based health indicator for remaining useful life prediction of bearings. Neurocomputing 240:98–109CrossRef
18.
go back to reference Li X, Duan F, Mba D, Bennett I (2017) Multidimensional prognostics for rotating machinery: A review. Adv Mech Eng 9:1–20 Li X, Duan F, Mba D, Bennett I (2017) Multidimensional prognostics for rotating machinery: A review. Adv Mech Eng 9:1–20
21.
go back to reference Hong S, Zhou Z (2012) Application of Gaussian Process Regression for bearing degradation assessment. In: 2012 6th International Conference on New Trends in Information Science, Service Science and Data Mining (ISSDM2012). IEEE, pp 644–648 Hong S, Zhou Z (2012) Application of Gaussian Process Regression for bearing degradation assessment. In: 2012 6th International Conference on New Trends in Information Science, Service Science and Data Mining (ISSDM2012). IEEE, pp 644–648
24.
go back to reference Silverman BW (1986) Density Estimation for Statistics and Data Analysis. Chapman and Hall/CRC, New York Silverman BW (1986) Density Estimation for Statistics and Data Analysis. Chapman and Hall/CRC, New York
25.
go back to reference Coble J, Wesley Hines J (2009) Identifying optimal prognostic parameters from data: a genetic algorithms approach. In: Annual conference of the prognostics and health management society, vol 14, no 1 Coble J, Wesley Hines J (2009) Identifying optimal prognostic parameters from data: a genetic algorithms approach. In: Annual conference of the prognostics and health management society, vol 14, no 1
26.
go back to reference Lee WJ, Mendis GP, Triebe M, Sutherland J (2020) Monitoring of a machining process using kernel principal component analysis and kernel density estimation. J Intell Manuf 31:1175–1189CrossRef Lee WJ, Mendis GP, Triebe M, Sutherland J (2020) Monitoring of a machining process using kernel principal component analysis and kernel density estimation. J Intell Manuf 31:1175–1189CrossRef
27.
go back to reference Chati YS, Balakrishnan H (2017) A Gaussian Process Regression approach to model aircraft engine fuel flow rate. In: 2017 ACM/IEEE 8th International Conference on Cyber-Physical Systems (ICCPS). IEEE, pp 131–140 Chati YS, Balakrishnan H (2017) A Gaussian Process Regression approach to model aircraft engine fuel flow rate. In: 2017 ACM/IEEE 8th International Conference on Cyber-Physical Systems (ICCPS). IEEE, pp 131–140
28.
go back to reference Bishop CM (2006) Pattern Recognition and Machine Learning. Springer, New York Bishop CM (2006) Pattern Recognition and Machine Learning. Springer, New York
Metadata
Title
Time to failure prediction of rotating machinery using dynamic feature extraction and gaussian process regression
Authors
Wo Jae Lee
John W. Sutherland
Publication date
27-12-2023
Publisher
Springer London
Published in
The International Journal of Advanced Manufacturing Technology / Issue 5-6/2024
Print ISSN: 0268-3768
Electronic ISSN: 1433-3015
DOI
https://doi.org/10.1007/s00170-023-12799-8

Other articles of this Issue 5-6/2024

The International Journal of Advanced Manufacturing Technology 5-6/2024 Go to the issue

Premium Partners