Successful aircraft predictive maintenance relies on the accurate prediction of major aircraft component failures for operators to schedule and carry out maintenance operations before failure actually happens. In this paper, we share important lessons learned from our development of prognostics alerts using full flight sensor data, including various challenges of using big data, data quality issues, failure identification for data labeling, engineering-driven vs. data-driven methods, and aggregating alerts into actionable alerts. We also provide recommendations based on our experience with prognostic alerts developed and deployed for many airline operators.
sensor data, predictive maintenance, data quality, machine learning, actionable alert
Hodkiewicz, M., Ho, M. (2016). Cleaning historical maintenance work order data for reliability analysis. Journal of Quality in Maintenance Engineering. Volume 22, Issue 2, 2016.
Liaw, R., Liang, E., Nishihara, R., Moritz, P., Gonzalez, J., Stoica, I. (2018). Tune: A Research Platform for Distributed Model Selection and Training. July 13, 2018. https://arxiv.org/abs/1807.05118.
Lukens, S., Rousis, D., Thomas, D., Baer, T., Lujan, M., Smith, M. (2022). A Data Quality Scorecard for Assessing the Suitability of Asset Condition Data for Prognostics Modeling. Annual Conference of the PHM Society, 2022.
Mitici, M., de Pater, I., Barros, A., Zeng, Z. (2023). Dynamic predictive maintenance for multiple components using data-driven probabilistic RUL prognostics: The case of turbofan engines. Journal of Reliability Engineering and System Safety 234 (2023).
West, C. (2023). AI and the FCI: Can ChatGPT project an understanding of introductory physics? March 3, 2023. https://arxiv.org/pdf/2303.01067.pdf.
Yuan, J. (2022). Boeing Operationalized Aircraft Predictive Maintenance. AAAI Fall Symposia Series on Artificial Intelligence for Predictive Maintenance. Nov 19, 2022.
This work is licensed under a Creative Commons Attribution 3.0 Unported License.