Anomaly Detection and Fault Disambiguation in Large Flight Data: A Multi-modal Deep Auto-encoder Approach

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

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

Kishore K. Reddy Soumalya Sarkar Vivek Venugopalan Michael Giering

Abstract

Flight data recorders provide large volumes of heterogeneous data from arrays of sensors on-board to perform fault diagnosis. Challenges such as large data volumes, lack of labeled data, and increasing numbers of sensors (multiple modalities) exacerbate the challenges of being able to hand-craft the features needed for state-of-the-art PHM algorithms to effectively perform system diagnosis. In this paper, the authors propose leveraging existing unsupervised learning methods based on Deep Auto-encoders (DAE) on raw time series data from multiple sensors to build a robust model for anomaly detection. The anomaly detection algorithm analyzes the reconstruction error of a DAE trained on nominal data scenarios. The reconstruction error of individual sensors is examined to perform fault disambiguation. Training and validation are conducted in a laboratory setting for various operating conditions. The proposed framework does not need any hand-crafted features and uses raw time series data. Our approach is tested on data from the NASA open database and demonstrates high fault detection rates ( 97:8%) with zero false alarms. Our paper also demonstrates robust fault disambiguation on two different fault scenarios. Moreover, the paper provides a strong rationale for utilizing deep architecture (multi-hidden-layer neural network) via thorough comparison with a single hidden-layer DAE.

How to Cite

Reddy, K. K., Sarkar, S., Venugopalan, V., & Giering, M. (2016). Anomaly Detection and Fault Disambiguation in Large Flight Data: A Multi-modal Deep Auto-encoder Approach. Annual Conference of the PHM Society, 8(1). https://doi.org/10.36001/phmconf.2016.v8i1.2549
Abstract 145 | PDF Downloads 94

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

Keywords

deep learning, fault diagnostics, flight data, condition monitoring, electro-mechanical actuator

References
Balaban, E., Saxena, A., Bansal, P., Goebel, K. F., & Curran, S. (2009, Dec). Modeling, detection, and disambiguation of sensor faults for aerospace applications. IEEE Sensors Journal, 9(12), 1907-1917. doi: 10.1109/JSEN.2009.2030284
Balaban, E., Saxena, A., Narasimhan, S., Roychoudhury, I., Koopmans, M., Ott, C., & Goebel, K. (2015). Prognostic health-management system development for electromechanical actuators. Journal of Aerospace Information Systems, 12, 329-344.
Basir, O., & Yuan, X. (2007). Engine fault diagnosis based on multi-sensor information fusion using dempstershafer evidence theory. Information Fusion, 8(4), 379 - 386.
Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H., et al. (2007). Greedy layer-wise training of deep networks. Advances in neural information processing systems, 19, 153.
Chen, W., & Saif, M. (2007). A sliding mode observer-based strategy for fault detection, isolation, and estimation in a class of Lipschitz nonlinear systems. International Journal of Systems Science, 38(12), 943–955.
Das, S., Sarkar, S., Ray, A., Srivastava, A., & Simon, D. L. (2013). Anomaly detection in flight recorder data: A dynamic data-driven approach. In American control conference (acc), 2013 (pp. 2668–2673).
Duda, R. O., Hart, P. E., & Stork, D. G. (2000). Pattern classification, second ed. (Vol. 654). New York: John Wiley and Sons.
Erhan, D., Courville, A., & Bengio, Y. (2010). Understanding representations learned in deep architectures. Department d’Informatique et Recherche Operationnelle, University of Montreal, QC, Canada, Tech. Rep, 1355.
Gardner, W., Napolitano, A., & Paura, L. (2006). Cyclostationarity: half a century of research. Signal processing, 86(4), 639–697.
Gertler, J. J. (1988). Survey of model-based failue detection and isolation in complex plants. IEEE Control Systems Magazine, 11.
Gertler, J. J. (1997). Fault detection and isolation using parity equations. Control Engineering Practice, 5(5), 653–661.
Gustafsson, F. (2002). Stochastic fault diagnosability in parity spaces. In 15th IFAC world congress, barcelona, spain.
Hagenblad, A., Gustafsson, F., & Klein, I. (2003). A comparison of two methods for stochastic fault detection and principal component analysis. In 13th ifac symposium on system identification (sysid), rotterdam, nl (pp. 27–29).
Hinton, G., & Salakhutdinov, R. (2006). Reducing the dimensionality of data with neural networks. Science, 313.5786, 504-507.
Kim, S., Kim, Y., & Park, C. (2004). Hybrid fault detection and isolation techniques for aircraft inertial measurement sensors. In Aiaa guidance, navigation and control conference and exhibit, providence, rh.
Kim, S. J., & Lee, C.W. (1999). Diagnosis of sensor faults in active magnetic bearing system equipped with built-in force transducer. IEEE Transactions on Mechatronics, 4(3), 180–186.
Kiyak, E., Cetin, O., & Kahvecioglu, A. (2008). Aircraft sensor fault detection based on unknown input observers. Aircraft Engineering and Aerospace Technology, 80(5), 545–548.
Litt, J., Kurtkaya, M., & Duyar, A. (1994). Sensor fault detection and diagnosis simulation of a helicopter. In Conference of military, government, and aerospace simulation, san diego, ca.
Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., & Ng, A. Y. (2011). Multimodal Deep Learning. In Proceedings of the 28th international conference on machine learning (icml-11) (pp. 689–696).
Rizzoni, G., & Min, P. S. (1991). Detection of sensor failures in automotive engines. IEEE Transactions on Vehicular Technology, 40(2), 487–500.
Sarkar, S., Lore, K. G., Sarkar, S., Ramanan, V., Chakravarthy, S. R., Phoha, S., & Ray, A. (2015). Early detection of combustion instability from hi-speed
flame images via deep learning and symbolic time series analysis. In Annual conference of the prognostics and health management society 2015.
Sarkar, S., Mukherjee, K., Sarkar, S., & Ray, A. (2013). Symbolic dynamic analysis of transient time series for fault detection in gas turbine engines. Journal of Dynamic Systems, Measurement, and Control, 135(1), 014506.
Sarkar, S., Sarkar, S., Mukherjee, K., Ray, A., & Srivastav, A. (2013). Multi-sensor information fusion for fault detection in aircraft gas turbine engines. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, 227(12), 1988–2001.
Sarkar, S., Sarkar, S., & Ray, A. (2014). Data-enabled health management of complex industrial systems. Fault Detection: Classification, Techniques and Role in Industrial Systems, NOVA Science Publishers.
Sarkar, S., Sarkar, S., Virani, N., Ray, A., & Yasar, M. (2014). Sensor fusion for fault detection and classification in distributed physical processes. Frontiers in Robotics and AI, 1, 16.
Seda, P., Kadir, E., & Dogru, B. E. (2007). Intelligent sensor fault detection and identification for temperature control. In Proceedings of the 11th wseas international conference on computers, agios nikolaos, greece.
Simani, S., Fantuzzi, C., & Beghelli, S. (2000). Diagnosis techniques for sensor faults of inustrial processes. IEEE Transactions on Control Systems Technology, 8(5), 848–855.
Tan, C. P., & Edwards, C. (2002). Sliding mode observers for detection and reconstruction of sensor faults. Automatica, 38, 1815–1821.
Tran, V., AlThobiani, F., & Ball, A. (2014). An approach to fault diagnosis of reciprocating compressor valves using teager-kaiser energy operator and deeep belief networks. Expert Systems with Applications.
Verma, K., Gupta, V., Sharma, M., & Sevakula, R. (2013). Intelligent condition based monitoring of rotating machines using sparse auto-encoders. IEEE.
Section
Technical Papers