Machining Process Time Series Data Analysis with a Decision Support Tool
- 350Downloads
Abstract
Dynamic industrial data growth necessitates the development of several new concepts of these data analysis that will allow to select not only the right data, but also to apply appropriate methods in order to extract knowledge from them. For this purpose, the possible use of decision trees as a decision support tool for a machining process data analysis was discussed in this article. With the use of the generated decision rules, we identify parameters that affect the state of a blade (blunt, sharp). In consequence that makes it possible to predict its future state at specific values of the identified parameters. Decision trees enable the analyses of the importance of each variable for the dependent variable. This makes it possible to analyse how each individual parameter and the relationships between them affect the condition of a cutter blade. The results of variables importance for a decision tree analysis can be used to determine the most important input variables, while rejecting those which do not affect the condition of a cutter blade. The study offers some promising results. It is confirmed by the achieved prediction model quality indicators.
Keywords
Decision trees Identification of cutter state Machining process analysisReferences
-
1.de Jonge, B.: Maintenance Optimization Based on Mathematical Modeling. University of Groningen, SOM Research School, Groningen, Holland (2017)Google Scholar
-
2.Yan, J., Meng, Y., Lei, L., Li, L.: Industrial big data in an industry 4.0 environment: challenges, schemes, and applications for predictive maintenance. IEEE Access5, 23484–23491 (2017)CrossRefGoogle Scholar
-
3.Valis, D., Mazurkiewicz, D., Forbelska, M.: Modelling of a transport belt degradation using state space model. In: Proceedings of the 2017 IEEE International Conference on Industrial Engineering & Engineering Management, pp. 949–953. IEEE, Singapore (2017)Google Scholar
-
4.Vališ, D., Mazurkiewicz, D.: Application of selected Levy processes for degradation modelling of long range mine belt using real-time data. Arch. Civil Mech. Eng.18(4), 1430–1440 (2018)CrossRefGoogle Scholar
-
5.Varela, M.L.R., Putnik, G.D., Manupati, V.K., Rajyalakshmi, G., Trojanowska, J., Machado, J.: Integrated process planning and scheduling in networked manufacturing systems for I4.0: a review and framework proposal. Wireless Netw.27(3), 1587–1599 (2019)CrossRefGoogle Scholar
-
6.Jasiulewicz-Kaczmarek, M., Żywica, P.: The concept of maintenance sustainability performance assessment by integrating balanced scorecard with non-additive fuzzy integral. Eksploatacja i Niezawodnosc – Maintenance Reliab.20(4), 650–661 (2018)CrossRefGoogle Scholar
-
7.Kozłowski, E., Mazurkiewicz, D., Żabiński, T., Prucnal, S., Sęp, J.: Assessment model of cutting tool condition for real-time supervision system. Eksploatacja i Niezawodnosc - Maintenance Reliab.21(4), 679–685 (2019)CrossRefGoogle Scholar
-
8.Borucka, A., Grzelak, M.: Application of logistic regression for production machinery efficiency evaluation. Appl. Sci.9, 4770 (2019)CrossRefGoogle Scholar
-
9.Antosz, K., Paśko, Ł, Gola, A.: The use of intelligent systems to support the decision-making process in Lean Maintenance management. IFAC PapersOnLine52(10), 148–153 (2019)CrossRefGoogle Scholar
-
10.Pavlenko, I., Trojanowska, J., Ivanov, V., Liaposhchenko, O.: Parameter identification of hydro-mechanical processes using artificial intelligence systems. Int. J. Mechatron. Appl. Mech.5, 19–26 (2019)Google Scholar
-
11.Gareth, J., Witten, D., Hastie, T., Tibshirani, R.: An introduction to statistical learning with applications with R. Springer, London (2013)zbMATHGoogle Scholar
-
12.Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and Regression Trees. Chapman & Hall, New York (1984)zbMATHGoogle Scholar
-
13.Larose, D.T.: Discovering Knowledge From Data. Introduction to Data Mining. Scientific Publisher PWN, Warsaw (2013)zbMATHGoogle Scholar
-
14.科斯塔密纹唱片,曾,交流,卡瓦略,A.C.P.L.F, Freitas, A.A.: A review of performance evaluation measures for hierarchical classifiers. In: Evaluation Methods for Machine Learning II: Papers from the AAAI-2007 Workshop, pp. 182–196. AAAI Press (2007)Google Scholar
-
15.Provost, F., Fawcett, T., Kohavi, R.: The case against accuracy estimation for comparing classifiers. In: Proceedings of the ICML-1998, pp. 445–453. Morgan Kaufmann, San Francisco (1998)Google Scholar
-
16.Powers, D.: Evaluation: from precision, recall and F-score to ROC, unforcedness, nakedness & correlation. J. Mach. Learn. Technol.2, 37–63 (2011)Google Scholar
-
17.Żabiński, T. Mączka, T., Kluska, J.: Industrial platform for rapid prototyping of intelligent diagnostic systems trends. In: Mitkowski, W., Kacprzyk, J., Oprzędkiewicz, K., Skruch P. (eds.) Advanced Intelligent Control, Optimization and Automation Polish Control Conference, Kraków, Poland, pp. 712–21. Springer, Heidelberg (2017)https://doi.org/10.1007/978-3-319-60699-6_69
-
18.Charemza, W.W., Syczewska, E.M.: Joint application of the Dickey-Fuller and KPSS tests. Econ. Lett.61(1), 17–21 (1998)CrossRefGoogle Scholar
-
19.Dickey, D.A., Fuller, W.A.: Distribution of the estimators for autoregressive time series with a unit root. J. Am. Stat. Assoc.74, 427–431 (1979)MathSciNetzbMATHGoogle Scholar
-
20.Box, G.E.P., Pierce, D.A.: Distribution of residual autocorrelations in autoregressive-integrated moving average time series models. J. Am. Stat. Assoc.65(332), 1509–1526 (1970)MathSciNetCrossRefGoogle Scholar
-
21.Ljung, G.M., Box, G.E.P.: On a measure of lack of fit time series models. Biometrika65(2), 297–303 (1978)CrossRefGoogle Scholar