Abstract
Passenger comfort systems such as Heating, Ventilation, and Air-Conditioning units (HVACs) usually lack the data monitoring quality enjoyed by mission-critical systems in trains. But climate change, in addition to the high ventilation standards enforced by authorities due to the COVID pandemic, have increased the importance of HVACs worldwide. We propose a machine learning (ML) approach to the challenge of failure detection from incomplete data, consisting of two steps: 1. human-annotation bootstrapping, on a fraction of temperature data, to detect ongoing functional loss and build an artificial ground truth (AGT); 2. failure prediction from digital-data, using the AGT to train an ML model based on failure diagnose codes to foretell functional loss. We exercise our approach in trains of Dutch Railways, showing its implementation, ML-predictive capabilities (the ML model for the AGT can detect HVAC malfunctions online), limitations (we could not foretell failures from our digital data), and discussing its application to other assets.
This work was partially funded by EU grants 830929 (H2020-CyberSec4Europe), and 952647 (H2020-AssureMOSS), and NWO grant NWA.1160.18.238 (PrimaVera).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Besides being COVID-friendly, this is less cost- and time-consuming (although arguably less flexible) than mechanical experiments by technicians and engineers.
References
Aslansefat, K., Kabir, S., Gheraibia, Y., Papadopoulos, Y.: Dynamic fault tree analysis: state-of-the-art in modelling, analysis and tools, pp. 73–112. Taylor & Francis (2020). https://doi.org/10.1201/9780429268922-4
Catelani, M., Ciani, L., Guidi, G., Patrizi, G., Galar, D.: Estimate the useful life for a heating, ventilation, and air conditioning system on a high-speed train using failure models. ACTA IMEKO 10(3), 100–107 (2021)
Daniel, R., et al.: Filtration understanding: FY10 testing results and filtration model update. Technical report, Pacific Northwest National Laboratory (2011)
Hale, P., Arno, R.: Survey of reliability and availability information for power distribution, power generation, and HVAC components for commercial, industrial, and utility installations. In: IEEE Industrial and Commercial Power Systems Technical Conference (Cat. No.00CH37053), pp. 31–54 (2000). https://doi.org/10.1109/ICPS.2000.854354
Lin, N., Du, W., Wang, J., Yun, X., Chen, L.: The effect of COVID-19 restrictions on particulate matter on different modes of transport in China. Environ. Res. (2021). https://doi.org/10.1016/j.envres.2021.112205
Ojala, M., Garriga, G.C.: Permutation tests for studying classifier performance. J. Mach. Learn. Res. 11, 1833–1863 (2010)
Pedregosa, F., Varoquaux, G., Gramfort, A., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Ruijters, E., Guck, D., Drolenga, P., Peters, M., Stoelinga, M.: Maintenance analysis and optimization via statistical model checking. In: Agha, G., Van Houdt, B. (eds.) QEST 2016. LNCS, vol. 9826, pp. 331–347. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-43425-4_22
Settles, B.: Active Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning (2012). https://doi.org/10.2200/S00429ED1V01Y201207AIM018
Tehrani, M.M., Beauregard, Y., Rioux, M., Kenne, J.P., Ouellet, R.: A predictive preference model for maintenance of a heating ventilating and air conditioning system. IFAC 48(3), 130–135 (2015). https://doi.org/10.1016/j.ifacol.2015.06.070
Wong, D.: A knowledge-based decision support system in reliability-centered maintenance of HVAC systems. Ph.D. thesis, University of Newfoundland (2000)
Acknowledgement
The authors thank Nick Oosterhof, who contributed with invaluable discussion and feedback that helped to carry out and shape this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Budde, C.E., Jansen, D., Locht, I., Stoelinga, M. (2022). Learning to Learn HVAC Failures: Layering ML Experiments in the Absence of Ground Truth. In: Collart-Dutilleul, S., Haxthausen, A.E., Lecomte, T. (eds) Reliability, Safety, and Security of Railway Systems. Modelling, Analysis, Verification, and Certification. RSSRail 2022. Lecture Notes in Computer Science, vol 13294. Springer, Cham. https://doi.org/10.1007/978-3-031-05814-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-05814-1_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05813-4
Online ISBN: 978-3-031-05814-1
eBook Packages: Computer ScienceComputer Science (R0)