A Design Science Approach Comparing Ensemble Learning and Artificial Neural Networks for Uncertainty-Aware Helicopter Turbine Engines Health Monitoring

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Nov 6, 2024
Victor Henrique Alves Ribeiro Gilberto Reynoso-Meza

Abstract

This work presents the development of an uncertainty-aware health monitoring system for helicopter turbine engines, focusing on improving operational availability and reducing maintenance costs. We address the critical issue of uncertainty quantification in data-driven fault detection and prognostics, essential for increasing system reliability. The project follows an iterative development cycle, incorporating multiple techniques for data processing, such as polynomial feature generation and data cleansing, and model development, including ensemble learning and artificial neural networks. Evaluation is performed using K-fold and group-fold cross-validation. The final solution consists of a cascaded ensemble learning model combining bagged linear regression built on polynomial features and random forest. This model demonstrates robust performance, achieving a test score of 0.955719 and a validation score of 0.886953, showcasing the effectiveness of uncertainty-aware machine learning methods in health monitoring systems.

How to Cite

Alves Ribeiro, V. H., & Reynoso-Meza, G. (2024). A Design Science Approach Comparing Ensemble Learning and Artificial Neural Networks for Uncertainty-Aware Helicopter Turbine Engines Health Monitoring. Annual Conference of the PHM Society, 16(1). https://doi.org/10.36001/phmconf.2024.v16i1.4187
Abstract 65 | PDF Downloads 71

##plugins.themes.bootstrap3.article.details##

Keywords

Design Science Research Method, Ensemble Learning, Artificial Neural Networks, Fault Detection, Helicopter Turbine Engine

References
Banks, J., Batzel, T., Keolian, R., Poese, M., Lovell, T., Lebold, M., . . . Cunningham, K. (2011). Power system prognostics for the us army oh-58d helicopter. In 2011 aerospace conference (pp. 1–15).

Berri, P. C. C., Dalla Vedova, M. D. L., & Mainini, L. (2019). Real-time fault detection and prognostics for aircraft actuation systems. In Aiaa scitech 2019 forum (p. 2210).

Breiman, L. (1996). Bagging predictors. Machine learning, 24, 123–140.

Breiman, L. (2001). Random forests. Machine learning, 45, 5–32.

Brenning, A. (2012). Spatial cross-validation and bootstrap for the assessment of prediction rules in remote sensing: The r package sperrorest. In 2012 ieee international geoscience and remote sensing symposium (pp. 5372–5375).

Das, L., Gjorgiev, B., & Sansavini, G. (2024). Uncertaintyaware deep learning for monitoring and fault diagnosis from synthetic data. Reliability Engineering & System Safety, 251, 110386.

Del Mar-Raave, J. R., Bahs¸i, H., Mrˇsi´c, L., & Hausknecht, K. (2021). A machine learning-based forensic tool for image classification-a design science approach. Forensic Science International: Digital Investigation, 38, 301265.

Duque, J., Godinho, A., Moreira, J., & Vasconcelos, J. (2024). Data science with data mining and machine learning a design science research approach. Procedia Computer Science, 237, 245–252.

Fernandez-Delgado, M., Cernadas, E., Barro, S., & Amorim, D. (2014). Do we need hundreds of classifiers to solve real world classification problems? The journal of machine learning research, 15(1), 3133–3181.

Ghanem, R., Higdon, D., Owhadi, H., et al. (2017). Handbook of uncertainty quantification (Vol. 6). Springer New York.

Hastie, T., Tibshirani, R., Friedman, J. H., & Friedman, J. H. (2009). The elements of statistical learning: data mining, inference, and prediction (Vol. 2). Springer.

Hu, Y., Miao, X., Si, Y., Pan, E., & Zio, E. (2022). Prognostics and health management: A review from the perspectives of design, development and decision. Reliability Engineering & System Safety, 217, 108063.

Kafunah, J., Ali, M. I., & Breslin, J. G. (2023). Uncertainty-aware ensemble combination method for quality monitoring fault diagnosis in safety-related products. IEEE Transactions on Industrial Informatics, 20(2), 1975–1986.

Murphy, K. P. (2022). Probabilistic machine learning: an introduction. MIT press.

Nair, V., & Hinton, G. E. (2010). Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th international conference on machine learning (icml-10) (pp. 807–814).

Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., . . . others (2019). Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., . . . Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.

Peffers, K., Tuunanen, T., Rothenberger, M. A., & Chatterjee, S. (2007). A design science research methodology for information systems research. Journal of management information systems, 24(3), 45–77.

PHM Society. (2024). PHM 2024 Conference Data Challenge. https://data.phmsociety.org/phm2024-conference-data-challenge/. (Accessed: 2024-09-04)

Pumplun, L., Peters, F., Gawlitza, J. F., & Buxmann, P. (2023). Bringing machine learning systems into clinical practice: a design science approach to explainable machine learning-based clinical decision support systems. Journal of the Association for Information Systems, 24(4), 953–979.

Ribeiro, V. H. A., & Reynoso-Meza, G. (2018). Online anomaly detection for drinking water quality using a multi-objective machine learning approach. In Proceedings of the genetic and evolutionary computation conference companion (pp. 1–2).

Roberts, D. R., Bahn, V., Ciuti, S., Boyce, M. S., Elith, J., Guillera-Arroita, G., . . . others (2017). Crossvalidation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure. Ecography, 40(8), 913–929.

Schwabacher, M., & Goebel, K. (2007). A survey of artificial intelligence for prognostics. In Aaai fall symposium: artificial intelligence for prognostics (pp. 108–115).

Sculley, D. (2010). Web-scale k-means clustering. In Proceedings of the 19th international conference on world wide web (pp. 1177–1178).

Wold, S., Esbensen, K., & Geladi, P. (1987). Principal component analysis. Chemometrics and intelligent laboratory systems, 2(1-3), 37–52.

Yao, Y., Han, T., Yu, J., & Xie, M. (2024). Uncertainty-aware deep learning for reliable health monitoring in safetycritical energy systems. Energy, 291, 130419.

Zio, E. (2022). Prognostics and health management (phm): Where are we and where do we (need to) go in theory and practice. Reliability Engineering & System Safety, 218, 108119.
Section
Data Challenge Papers