FAILURE PREDICTION USING FACTOR ANALYSIS METHODS
Abstract
This article discusses the application of a risk assessment method based on the combination of the FMEA (failure mode and effect analysis) methodology and the MCDM (Multiple Criteria Decision Making) methods. This approach allows taking into account both expert knowledge and historical data on the operation of the equipment. MCDM methods process the assessment more flexibly in comparison with the standard method of calculating the priority number of risks (PRN), which helps to better assess the risks by three criteria: the probability of occurrence, the complexity of detection and the severity of the consequences. One of the criteria can be obtained not only through an expert assessment, but also on the basis of data recording the operation of the equipment. This approach was tested using the example of synthetic open-source data on the operating modes of production equipment. The task was to predict both the failure itself and its type, as well as to identify the factors that have the greatest impact on the failure. For this purpose, data preprocessing was carried out, during which it was necessary to eliminate the imbalance of classes. There are several approaches to solving this problem, aimed at reducing the dominant class or generating instances of poorly represented classes. In this example, random reduction of the number of records without errors was used. Then, AdaBoost, Random Forest and LinearSVC were compared as classification algorithms. Since multi-class classification was required, it was decided to use the one-vs-the-rest strategy. As a result, it was possible to achieve 86% forecasting accuracy by F-measure using the AdaBoost and Random Forest algorithms. LinearSVC turned out to be ineffective. Thus, the resulting forecasting model recognizes different types of errors, but there is room for improvement, which requires a larger sample, including more examples with different types of failure. Based on this, this approach as an alternative to expert assessment is promising, improving objectivity, and also making it possible to foresee risks and prevent a real failure or risk-related incident.
References
1. McDermott R.E., Mikulak, Raymond J., Beauregard Michael R. The Basics of FMEA. Productivity Press, 1996, 80 p. ISBN 9780527763206.
2. GOST R 51814.2–2001. Sistemy kachestva v avtomobilestroenii. Metod analiza vidov I posledstviy potentsial’nykh defektov [GOST R 51814.2–2001. Quality systems in the automotive industry. Method for analyzing the types and consequences of potential defects].
3. Podoplelova E.S., Knyazev I.I. Modifikatsiya metoda FMEA pri pomoshchi algoritmov mashinnogo obucheniya [Modification of the FMEA method using machine learning algorithms], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SfedU. Engineering Sciences], 2024, No. 6 (2023), pp. 88-95.
4. Sprajcer M., Matthew J.W. Thomas, Charli Sargent, Meagan E. Crowther, Diane B. Boivin, Imelda S. Wong, Alison Smiley, Drew Dawson. How effective are Fatigue Risk Management Systems (FRMS)? A review, Accident Analysis & Prevention, 2022, No. 165, pp. 106398.
5. Jin C., Ran Y., Zhang G. An improving failure mode and effect analysis method for pallet exchange rack risk analysis, Soft Comput, 2021, 25, pp. 15221-15241. Available at: https://doi.org/10.1007/ s00500-021-06359-z.
6. Filz M., Langner J.E., Herrmann C., Thiede S. Data-driven failure mode and effect analysis (FMEA) to enhance maintenance planning, Comput. Ind., 2021, 129, 103451.
7. Aboozar Jamalnia, Yu Gong, Kannan Govindan, Michael Bourlakis, Sachin Kumar Mangla. A decision support system for selection and risk management of sustainability governance approaches in multi-tier supply chain, International Journal of Production Economics, 2023, No. 264, pp. 108960.
8. Wan Suzila Wan Husin, Yazriwati Yahya, Nurulhuda Firdaus Mohd Azmi, Nilam Nur Amir Sjarif, Su-riayati Chuprat, Azri Azmi. Risk Management Framework for Distributed Software Team: A Case Study of Telecommunication Company, Procedia Computer Science, 2019, 161, pp. 178-186.
9. Nabil K., Dkhissi. P.B. A decision support system for evaluating the logistical risks in Supply chains based on RPN factors and multi criteria decision making approach, 2022 IEEE 6th International Confer-ence on Logistics Operations Management (GOL). Strasbourg, France, 2022, pp. 1-6.
10. Dent T.H.S. et al. Risk prediction models: a framework for assessment, Public health genomics, 2012, Vol. 15 (2), pp. 98-105. DOI: 10.1159/000334436.
11. Cai Y., Cai YQ., Tang, LY. et al. Artificial intelligence in the risk prediction models of cardiovascular disease and development of an independent validation screening tool: a systematic review, BMC Med., 2024, 22, 56. Available at: https://doi.org/10.1186/s12916-024-03273-7.
12. Matzka S. AI4I 2020 Predictive Maintenance Dataset, submitted to UCI Machine Learning Repository, 2020.
13. Kim Dzh.-O., M'yuller Ch.U. Faktornyy analiz: statisticheskie metody i prakticheskie voprosy [Factor analysis: statistical methods and practical issues], Sb. rabot «Faktornyy, diskriminantnyy i klasternyy an-aliz» [Collection of works "Factor, discriminant and cluster analysis"]: transl. from engl., ed. by
I.S. Enyukova. Moscow: Finansy i statistika, 1989, 215 p.
14. Byuyul' A., Tsefel' P. SPSS: Iskusstvo obrabotki informatsii. Analiz statisticheskikh dannykh i voss-tanovlenie skrytykh zakonomernostey [SPSS: The art of information processing. Analysis of statistical data and reconstruction of hidden patterns]. Saint Petersburg: OOO «DiaSoftYUP», 2002, 603 p.
15. Pearson K. On lines and planes of closest fit to systems of points in space, Philosophical Magazine, 1901, Vol. 2, pp. 559-572.
16. Scikit-learn. Feature importances with a forest of trees. Available at: https://scikit-learn.org/stable/ au-to_examples/ensemble/plot_forest_importances.html.
17. Freund Y., Schapire R. A Decision-Theoretic Generalization of on-Line Learning and an Application to Boosting, 1995.
18. Zhu J., Zou H., Rosset S., Hastie T. Multi-class adaboost, Statistics and its Interface, 2009, Vol. 2,
pp. 349-360.
19. Prinzie A, Poel D. Random Multiclass Classification: Generalizing Random Forests to Random MNL and Random NB, Database and Expert Systems Applications. Lecture Notes in Computer Science, 2007, Vol. 4653, pp. 349. DOI: 10.1007/978-3-540-74469-6_35. ISBN 978-3-540-74467-2.
20. Denisko D, Hoffman M.M. Classification and interaction in random forests, Proceedings of the National Academy of Sciences of the United States of America, 2018, 115 (8), pp. 1690-1692. Bibcode: 2018PNAS..115.1690D. DOI: 10.1073/pnas.1800256115. PMC 5828645. PMID 29440440.
21. Bishop Christopher M. Pattern Recognition and Machine Learning. Springer, 2006.
22. Scikit-learn. User Guide. OneVsRestClassifier. Available at: https://scikit-learn.org/stable/modules/ mul-ticlass.html#ovr-classification
