MODIFICATION OF THE FMEA METHOD USING MACHINE LEARNING ALGORITHMS
Abstract
Risk assessment is an important task in any field, from manufacturing to medicine. Risks accompany
a project, product or process throughout its life, from the moment of planning until its
complete termination. Each of them has its own approaches. These include FMEA (Failure Mode
and Effects Analysis) - analysis of the types and consequences of failures. The proposed model is
based on the FMEA method, which is based on risk assessment according to three criteria: the
severity of the consequences when a threat is realized and the complexity of identifying a failure,
the probability of occurrence. The first two criteria are based on expert assessment obtained in
accordance with artificial intelligence methods. The authors proposed a modification of the third
criterion. In our work, we replaced the expert assessment of the “probability of occurrence” criterion
with a machine learning model capable of predicting this indicator based on statistical data.
We carried out the first stage of research into the task at hand on NASA’s open dataset about engine
operating cycles before failure. Initially, the task was set to predict the remaining number of
cycles before failure, then we moved to the classification task, determining whether the equipment
is at risk, depending on its potential remaining life. The best result was obtained by the support
vector machine (SVM), with a classification accuracy of 80%. The goal of the work is to create a
risk assessment model based on the FMEA methodology, which allows to improve the quality of
assessment, reduce subjectivity in decision making, making a forecast based on historical data,
and not just the subjective experience of an expert.
References
– Productivity Press, 1996. – 80 p. – ISBN 9780527763206.
2. Analiz vidov i posledstviy potentsial'nykh otkazov. FMEA. Ssylochnoe rukovodstvo [Analysis
of the types and consequences of potential failures. FMEA. Reference manual]: trans. from
English fourth ed. dated June 2008. Nizhny Novgorod: OOO SMTS «Prioritet», 2012, 282 p.
(bilingual). ISBN 978-5-98366-042-7.
3. Xiang-Kun Zhao, Xiao-Min Zhu, Kai-Yuan Bai, Run-Tong Zhang. A novel failure model and
effect analysis method using a flexible knowledge acquisition framework based on picture
fuzzy sets, Engineering Applications of Artificial Intelligence, 2023, Vol. 117, Part A, 105625.
4. Jiawan Liu, Duojin Wang, Qinglian Lin, Meikui Deng. Risk assessment based on FMEA combining
DEA and cloud model: A case application in robot-assisted rehabilitation, Expert Systems
with Applications, 2023, Vol. 214, 119119.
5. Nabil K. and 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 Conference on Logistics Operations Management (GOL). Strasbourg, France,
2022, pp. 1-6.
6. Kaggle: NASA Turbofan Jet Engine Data Set. Available at: https://www.kaggle.com/datasets/
behrad3d/nasa-cmaps.
7. Hastie, T., Tibshirani R., Friedman J. Chapter 15. Random Forests. The Elements of Statistical
Learning: Data Mining, Inference, and Prediction. 2nd ed. Springer-Verlag, 2009, 746 p.
8. Scikit-learn: Machine Learning in Python: Documentation RandomForestClassifier. Available at:
https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html.
9. Deng H., Runger G., Tuv E. Bias of importance measures for multi-valued attributes and solutions,
Proceedings of the 21st International Conference on Artificial Neural Networks
(ICANN), 2011, pp. 293-300.
10. Demidenko E.Z. Lineynaya i nelineynaya regressiya [Linear and nonlinear regression]. Moscow:
Finansy i statistika, 1981, 302 p.
11. Alexander Statnikov, Constantin F. Aliferis, Douglas P. Hardin. A Gentle Introduction to Support
Vector Machines in Biomedicine: Theory and methods. World Scientific, 2011.
12. Nello Cristianini, John Shawe-Taylor. An Introduction to Support Vector Machines and Other
Kernel-based Learning Methods. Cambridge University Press, 2000.
13. Vladimir V'yugin. Matematicheskie osnovy teorii mashinnogo obucheniya i prognozirovaniya
[Mathematical foundations of the theory of machine learning and forecasting]. MTSMNO,
2013, 390 p.
14. Madeh Piryonesi S., Tamer E. El-Diraby. Role of Data Analytics in Infrastructure Asset Management:
Overcoming Data Size and Quality Problems, Journal of Transportation Engineering.
Part B: Pavements, 2020-06, Vol. 146, Issue 2, pp. 04020022.
15. Domingos, Pedro & Michael Pazzani. On the optimality of the simple Bayesian classifier under
zero-one loss, Machine Learning, 1997, 29, pp. 103-137.
16. Scikit-learn: Machine Learning in Python: Dokumentatsiya: Naivnye metody Bayesa [Scikitlearn:
Machine Learning in Python: Documentation: Naive Bayes methods]. Available at:
https://scikit-learn.ru/1-9-naive-bayes/.
17. Time Series Predictions with RNNs. Available at: https://encord.com/blog/time-seriespredictions-
with-recurrent-neural-networks/.
18. Wong Ka, Wong Raymond. An Efficient Risk Data Learning with LSTM RNN, 2019.
19. Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning. 2nd ed. Springer,
2009, 533 p
20. Nicolai Meinshausen. Quantile Regression Forests, Journal of Machine Learning Research,
2006, pp. 983-999.
21. Wang Di, Wang Ping, Wang Cong, Wang Pingping. Calibrating probabilistic predictions of
quantile regression forests with conformal predictive systems, Pattern Recognition Letters,
2022, Vol. 156, pp. 81-87.
