Systemic symptom detection in telemetry of ISS with explainability using FRAM and SpecTRM

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

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

Published Sep 4, 2023
Shota Iino Hideki Nomoto Takashi Fukui Sayaka Ishizawa Miki Sasaki Yohei Yagisawa Takayuki Hirose Yasutaka Michiura Hiroharu Shibayama

Abstract

Explainability is important for machine learning-based anomaly detection of safety critical systems. In this respect, we propose a new systemic symptom detection method by combining two methodologies: the Functional Resonance Analysis Method (FRAM) and the Specification Tools and Requirement Methodology-Requirement Language (SpecTRM-RL) with machine learning-based normal behavior prediction model. The method was verified with data of thermal control system of Japanese Experimental Module of the International Space Station, and the result found that the proposed method enables flight controllers and specialists to obtain additional information for identifying causes of anomaly with the method.  

Abstract 164 | PDF Downloads 167

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

Keywords

anomaly detection, aerospace, explainability, safety, formal method, machine learning

References
Hollnagel, E. (2012). FRAM: The Functional Resonance Analysis Method: Modelling Complex Socio-technical Systems. Ashgate Publishing Ltd

Gao, Y., Yang, T., Xu, M., & Xing, N. (2012, January). An unsupervised anomaly detection approach for spacecraft based on normal behavior clustering. In 2012 Fifth International Conference on Intelligent Computation Technology and Automation (pp. 478481). IEEE

Japan Aerospace Exploration Agency (JAXA). (2013). Japanese Manned Space Technology brought by Development and Operation of Internatiomal Space Station (ISS), Japanese Experimet Module KIBO. JAXA-SP-12-015, 1 227

Kostovska, A., Petković, M., Stepišnik, T., Lucas, L., Finn, T., Martínez-Heras, J., ... & Kocev, D. (2021, July). GalaxAI: Machine learning toolbox for interpretable analysis of spacecraft telemetry data. In 2021 IEEE 8th International Conference on Space Mission Challenges for Information Technology (SMC-IT) (pp. 44-52). IEEE

Leveson, N. G., Reese, J. D., & Heimdahl, M. P. (2003). SpecTRM: A CAD system for digital automation. In 17th DASC. AIAA/IEEE/SAE. Digital Avionics Systems Conference. Proceedings (Cat. No. 98CH36267) (Vol. 1, pp. B52-1). IEEE

Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in neural information processing systems, 30

Pugh, S. (1981, March). Concept selection: a method that works. In Proceedings of the International conference on Engineering Design (pp. 497-506)

Wang, C., Lu, N., Cheng, Y., & Jiang, B. (2019). A telemetry data based diagnostic health monitoring strategy for in-orbit spacecrafts with component degradation. Advances in Mechanical Engineering, 11(4), 1687814019839599

Zeng, Z., Jin, G., Xu, C., Chen, S., & Zhang, L. (2022). Spacecraft Telemetry Anomaly Detection Based on Parametric Causality and Double-Criteria Drift Streaming Peaks over Threshold. Applied Sciences, 12(4), 1803
Section
Special Session Papers