A Hypothesis testing approach to Zero-Fault-Shot learning for Damage Component Classification

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

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

Published Oct 26, 2023
Eric Bechhoefer Omri Matania Jacob Bortman

Abstract

Often, in condition monitoring, datasets are asymmetric. That is, for most machines being monitored, there is no labeled fault data, only nominal data (hence, the dataset is asymmetric). Deep Learning and other neural network-based mechanization have difficulty solving this type of problem, as they typically require a full set of labeled data, both nominal and faulted. Zero-Fault Shot learning is a class of machine learning problems with no labeled fault training data. In this class of problems, only nominal data is used for knowledge transfer. In this paper, a mixed hypothesis testing and Bayes classifier it used to provide both inferences to the type of fault and also provide information as to when maintenance should be provided. This is done without any fault data and demonstrates knowledge transfer from a set of nominal components, greatly reducing the cost of implementation and fielding of a system.

How to Cite

Bechhoefer, E., Matania, O., & Bortman, J. (2023). A Hypothesis testing approach to Zero-Fault-Shot learning for Damage Component Classification. Annual Conference of the PHM Society, 15(1). https://doi.org/10.36001/phmconf.2023.v15i1.3489
Abstract 355 | PDF Downloads 170

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

Keywords

Zero Shot Learning, Deep Learning, Predictive Maintenance

References
SAE HR-1 Standards, “A Guide to Extending Time Between Overhaul for Rotorcraft Power Train Transmissions Using Monitoring Data,” AIR6334, 2020.

AC29-2C, Chg4, “Airworthiness Approval of Rotorcraft Health Usage Monitoring Systems (HUMS),” 2003.

Airlines for America, “ATA MSG-3 Volume 2: Operator / Manufacture Scheduled Maintenance Development, Rotorcraft” 2018

Medvedovsky D, Ohana R, Klein R, Tur M, Bortman J. Spall length estimation based on strain model and experimental FBG data. Mech Syst Signal Process 2022;171:108923. https://doi.org/10.1016/J.YMSSP.2022.108923.

Zhang, S, Wei, H, Ding, J, “An Effective zero-short learning approach for intelligent fault detection using 1D CNN”, Applied Intelligence, 2022.

Zhang T et al (2022) Intelligent fault diagnosis of machines with small & imbalanced data: a state-of-the-art review and possible extensions. ISA Trans 119:152–171. https://doi.org/10.1016/j. isatra.2021.02.042

Abboud, D., Antoni, J., Sieg-Zieba, S., Eltaback, M., “Envelope analysis of rotating machine vibrations in variable speed conditions: A comprehensive treatment,” Mechanical Systems and Signal Processing, Vol 84, Part A, 2017, Page 200-226

Proakis, John, G., Digital Communications, McGraw-Hill, Boston MA, 1995, page 45-46

Bechhoefer, E., He, D., Dempsey, P., "Gear Health Threshold Setting Based On a Probability of False Alarm," Conference of the Prognostics and Health Management Society, 2011.

Fukunaga, K., Introduction to. Statistical. Pattern Recognition, Academic Press Professional, Inc. San Diego, CA, USA, 1990

Bechhoefer, E, Van Hecke, B/, & He, D. . (2013). Processing for Improved Spectral Analysis. Annual Conference of the PHM Society, 5(1). https://doi.org/10.36001/phmconf.2013.v5i1.2220
Section
Industry Experience Papers

Most read articles by the same author(s)

1 2 3 > >>