Skip to main content
Erschienen in:
Buchtitelbild

2021 | OriginalPaper | Buchkapitel

Importance of Variables in Gearbox Diagnostics Using Random Forests and Ensemble Credits

verfasst von : Anna M. Bartkowiak, Radoslaw Zimroz

Erschienen in: Computer Information Systems and Industrial Management

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

We consider a multivariate data matrix of size \(n \times d = 2183 \times 15\), where \(n=2183\) is the number of time segments recorded from vibration signals of two gearboxes, and \(d=15\) is the number of variables (traits) characterizing these segments. To learn about the role played by each of the 15 variables in the gearbox diagnostics, we use the Random Forest (RF) methodology with its ‘Variables Importance Plot’ (VIP) algorithm, which yields a kind of ranking of the variables with regard of their importance in the performed diagnostics. This ranking is different in various runs of the RF. We propose to use at this stage an additional module performing a specific ensemble learning yielding credits scores for each variable. It shows clearly the top most important variables.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

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!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Bartelmus, W., Zimroz, R.: A new feature for monitoring the condition of gearboxes in non-stationary operating systems. Mech. Syst. Signal Process. 23(5), 1528–1534 (2009)CrossRef Bartelmus, W., Zimroz, R.: A new feature for monitoring the condition of gearboxes in non-stationary operating systems. Mech. Syst. Signal Process. 23(5), 1528–1534 (2009)CrossRef
2.
Zurück zum Zitat Bartkowiak, A., Zimroz, R.: Dimensionality reduction via variables selection - linear and nonlinear approaches with application to vibration-based condition monitoring of planetary gearbox. Appl. Accoustics 77, 169–177 (2014)CrossRef Bartkowiak, A., Zimroz, R.: Dimensionality reduction via variables selection - linear and nonlinear approaches with application to vibration-based condition monitoring of planetary gearbox. Appl. Accoustics 77, 169–177 (2014)CrossRef
3.
Zurück zum Zitat Breiman, L., Friedman, J., Stone, C.J., Olshen, R.A.: Classification and Regression Trees. Taylor & Francis (1984) Breiman, L., Friedman, J., Stone, C.J., Olshen, R.A.: Classification and Regression Trees. Taylor & Francis (1984)
4.
6.
Zurück zum Zitat Breiman, L., Cutler, A.: Random Forest Manual v. 4.0. Technical Report UC Berkeley (2003) Breiman, L., Cutler, A.: Random Forest Manual v. 4.0. Technical Report UC Berkeley (2003)
8.
Zurück zum Zitat Cerrada, M., et al.: Fault diagnosis in spur gears based on genetic algorithm and random forest. Mech. Syst. Signal Process. 70, 87–103 (2016) Cerrada, M., et al.: Fault diagnosis in spur gears based on genetic algorithm and random forest. Mech. Syst. Signal Process. 70, 87–103 (2016)
9.
Zurück zum Zitat Dey, A., Shaikh, S.H., Saeed, K., Chaki, N.: Modified majority voting algorithm towards creating reference image for binarization. In: Kumar Kundu, M., Mohapatra, D.P., Konar, A., Chakraborty, A. (eds.) Advanced Computing, Networking and Informatics- Volume 1. SIST, vol. 27, pp. 221–227. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-07353-8_26CrossRef Dey, A., Shaikh, S.H., Saeed, K., Chaki, N.: Modified majority voting algorithm towards creating reference image for binarization. In: Kumar Kundu, M., Mohapatra, D.P., Konar, A., Chakraborty, A. (eds.) Advanced Computing, Networking and Informatics- Volume 1. SIST, vol. 27, pp. 221–227. Springer, Cham (2014). https://​doi.​org/​10.​1007/​978-3-319-07353-8_​26CrossRef
10.
Zurück zum Zitat Genuer, R., Poggi, J.M., Tuleau-Malot, Ch., Elsevier: Variable selection using random forests. Pattern Recogn. Lett. 31(14), 2225–2236 (2010)CrossRef Genuer, R., Poggi, J.M., Tuleau-Malot, Ch., Elsevier: Variable selection using random forests. Pattern Recogn. Lett. 31(14), 2225–2236 (2010)CrossRef
14.
Zurück zum Zitat Li, Y., Wu, F.X., Ngom, A.: A review on machine learning principles for multi-view biological data integration. Briefings Bioinf. 19(2), 325–340 (2018) Li, Y., Wu, F.X., Ngom, A.: A review on machine learning principles for multi-view biological data integration. Briefings Bioinf. 19(2), 325–340 (2018)
15.
Zurück zum Zitat Liaw, A., Wiener, M.: Classification and regression by random forest. R News 2(3), 18–22 (2002) Liaw, A., Wiener, M.: Classification and regression by random forest. R News 2(3), 18–22 (2002)
16.
Zurück zum Zitat Lipinski, P., Brzychczy, E., Zimroz, R.: Decision tree-based classification for planetary gearboxes’ condition monitoring with the use of vibration data in multidimensional symptom space. Sensors 20, 1–17 (2020). https://doi.org/10.3390/s20215979 Lipinski, P., Brzychczy, E., Zimroz, R.: Decision tree-based classification for planetary gearboxes’ condition monitoring with the use of vibration data in multidimensional symptom space. Sensors 20, 1–17 (2020). https://​doi.​org/​10.​3390/​s20215979
17.
Zurück zum Zitat Maqsood, I., Abraham, A.: Weather analysis using ensemble of connectionist learning paradigms. Appl. Soft Comput. 7, 995–1004 (2007)CrossRef Maqsood, I., Abraham, A.: Weather analysis using ensemble of connectionist learning paradigms. Appl. Soft Comput. 7, 995–1004 (2007)CrossRef
18.
Zurück zum Zitat Polikar, R.: Bootstrap inspired techniques in computational intelligence: ensemble of classifiers, incremental learning, data fusion and missing features. IEEE Signal Process. Mag. 24(4), 59–72 (2007)CrossRef Polikar, R.: Bootstrap inspired techniques in computational intelligence: ensemble of classifiers, incremental learning, data fusion and missing features. IEEE Signal Process. Mag. 24(4), 59–72 (2007)CrossRef
19.
Zurück zum Zitat Polikar, R.: Ensemble based systems in decision making. IEEE Circ. Syst. Mag. 9(3), 21–45 (2006)CrossRef Polikar, R.: Ensemble based systems in decision making. IEEE Circ. Syst. Mag. 9(3), 21–45 (2006)CrossRef
20.
21.
Zurück zum Zitat Ripley, B.D.: Pattern Recognition and Neural Networks. Cambridge University Press, Great Britain (1996)CrossRef Ripley, B.D.: Pattern Recognition and Neural Networks. Cambridge University Press, Great Britain (1996)CrossRef
22.
Zurück zum Zitat Ripley, B.D.: Package ‘nnet’. Package for feed-forward neural networks with a single hidden layer, and for multinomial log-linear models, pp. 1–11. cran.r-project.org. 3 May 2021 Ripley, B.D.: Package ‘nnet’. Package for feed-forward neural networks with a single hidden layer, and for multinomial log-linear models, pp. 1–11. cran.r-project.org. 3 May 2021
23.
Zurück zum Zitat Stapor, K., Ksieniewicz, P., Garcia, S., Wozniak, M.: How to design the fair experimental classifier evaluation. Appl. Soft Comput. J. 104, 107219 (2021) Stapor, K., Ksieniewicz, P., Garcia, S., Wozniak, M.: How to design the fair experimental classifier evaluation. Appl. Soft Comput. J. 104, 107219 (2021)
24.
Zurück zum Zitat Zimroz, R., Bartkowiak, A.: Two simple multivariate procedures for monitoring planetary gearboxes in non-stationary operating conditions. Mech. Syst. Signal Process. 38, 237–247 (2013)CrossRef Zimroz, R., Bartkowiak, A.: Two simple multivariate procedures for monitoring planetary gearboxes in non-stationary operating conditions. Mech. Syst. Signal Process. 38, 237–247 (2013)CrossRef
Metadaten
Titel
Importance of Variables in Gearbox Diagnostics Using Random Forests and Ensemble Credits
verfasst von
Anna M. Bartkowiak
Radoslaw Zimroz
Copyright-Jahr
2021
DOI
https://doi.org/10.1007/978-3-030-84340-3_1