Perspectives on using deep learning for system health management



Samir Khan Takehisa Yairi


Having a robust health management and diagnostic strategy is an important part of a system’s operational life cycle as it can be used to detect anomalies, analyze faults/failures and predict the remaining useful life of components. By utilizing condition data and on-site feedback, data models can be trained using machine learning and statistical concepts. Once trained, the logic for data processing can be embedded on onboard controllers whilst enabling real-time health assessment and analysis. More recently, deep learning has gained increasing attention due to its potential advantages with data classification and feature extraction problems. It is an evolving research area and hence its use for aerospace maintenance applications must be researched if it can be used to increase overall system resilience or potential cost benefits for maintenance, repair, and overhaul activities. This paper focuses on investigating the application of deep learning for system health management, therefore incorporating reliable redundancy at the adequate point in the system. Deep learning is discussed, some recent developments are reviewed to clarify potential applications, after which some research issues relating to their realization are highlighted.

Abstract 8 | PDF Downloads 19




Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M. and Ghemawat, S., 2016. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint
Barranco, R. C., Rodriguez, L. M., Urbina, R., & Hossain, M. S. (2016). Is a Picture Worth Ten Thousand Words in a Review Dataset?. arXiv preprint arXiv:1606.07496.
Bengio, Y., Simard, P., & Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE transactions on neural networks, 5(2), 157-166.
Beyca, O. F., Rao, P. K., Kong, Z., Bukkapatnam, S. T., & Komanduri, R. (2016). Heterogeneous Sensor Data Fusion Approach for Real-time Monitoring in Ultraprecision Machining (UPM) Process Using Non-Parametric Bayesian
Clustering and Evidence Theory. IEEE Transactions on Automation Science and Engineering, 13(2), 1033-1044.
Bishop, C., 1994. Novelty detection and neural network validation. In: Vision, Image and Signal Processing, IEE Proceedings, Vol. 141, No. 4. IET, pp. 217
Campbell, C. and Bennett, K., 2001. A Linear Programming Approach to Novelty Detection, Cambridge, UK: Cambridge Press.
Desforges, M., Jacob, P., and Cooper, J., 1998. Applications of Probability Density Estimation to the Detection of Abnormal Conditions in Engineering. pp. 687–703.
Diaz, I. and Hollmen, J., 2002. Residual Generation and Visualization for Understanding Novel Process Conditions. IEEE, pp. 2070–2075
Eti, M. C., Ogaji, S. O. T., & Probert, S. D. (2006). Reducing the cost of preventive maintenance (PM) through adopting a proactive reliability-focused culture. Applied energy, 83(11), 1235-1248.
Busseti, E., Osband, I., Wong, S. (2012). Deep Learning for Time Series Modeling CS 229 Final Project Report.
Fujimaki, R., Yairi, T., & Machida, K. (2005). An anomaly detection method for spacecraft using relevance vector learning. In Pacific-Asia Conference on Knowledge Discovery and Data Mining (pp. 785-790). Springer Berlin Heidelberg.
Guttormsson, S., Marks, R., El-Sharkawi, M. and Kerszenbaum, I., 1999. Elliptical novelty grouping for online short-turn detection of excited running rotors. IEEE Transactions of Energy Conversions, 14(1), 14.
Harries, T., 1993. Neural Network in Machine Health Monitoring. Professional Engin.
Hinton, G., Deng, L., Yu, D., Dahl, G. E., Mohamed, A. R., Jaitly, N., & Kingsbury, B. (2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine, 29(6), 82-97.
Huynh, K. T., Barros, A., & Bérenguer, C. (2015). Multi-level decision-making for the predictive maintenance of-out-of-: F deteriorating systems. IEEE Transactions on Reliability, 64(1), 94-117.
Jakubek, S. and Strasser, T., 2002. Fault-Diagnosis Using Neural Networks with Ellipsoidal Basis Functions. pp. 3846–3851.
Jia, F., Lei, Y., Lin, J., Zhou, X., & Lu, N. (2016). Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mechanical Systems and Signal Processing, 72, 303-315.
Khan, S., Phillips, P., Jennions, I., & Hockley, C. (2014). No Fault Found events in maintenance engineering Part 1: Current trends, implications and organizational practices. Reliability Engineering & System Safety, 123, 183-195.
Keogh, E., Lin, J., Lee, S.-H. and Herle, H., 2006. Finding the most unusual time series subsequence: Algorithms and applications. Knowledge Information Systems, 11(1), 1–27
Kobayashi, T., & Simon, D. L. (2005). Hybrid neural-network genetic-algorithm technique for aircraft engine performance diagnostics. Journal of Propulsion and Power, 21(4), 751-758.
Lee, D., Siu, V., Cruz, R., & Yetman, C. (2016, January). Convolutional Neural Net and Bearing Fault Analysis. In Proceedings of the International Conference on Data Mining (DMIN) (p. 194). The Steering Committee of The World
Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp).
Li, Y., Pont, M. and Jones, N., 2002. Improving the performance of radial basis function classifers in condition monitoring and fault diagnosis applications where unknown faults may occur. Pattern Recognition Letters, 23(5), 569–577
Litjens, G., Kooi, T., Bejnordi, B.E., Setio, A.A.A., Ciompi, F., Ghafoorian, M., van der Laak, J.A., van Ginneken, B. and Sánchez, C.I., 2017. A survey on deep learning in medical image analysis. arXiv preprint arXiv:1702.05747.
Lv, F., Wen, C., Bao, Z., & Liu, M. (2016, July). Fault diagnosis based on deep learning. In American Control Conference (ACC), 2016 (pp. 6851-6856). IEEE.
Meziane, F. (Ed.). (2009). Artificial Intelligence Applications for Improved Software Engineering Development: New Prospects: New Prospects. IGI Global.
McDuff, R. J., Simpson, P. K., & Gunning, D. (1989, September). An investigation of neural networks for F-16 fault diagnosis. I. System description. In AUTOTESTCON'89. IEEE Automatic
Testing Conference. The Systems Readiness Technology Conference. Automatic Testing in the Next Decade and the 21st Century. Conference Record. (pp. 351-357). IEEE.
Nelles, O. (2013). Nonlinear system identification: from classical approaches to neural networks and fuzzy models. Springer Science & Business Media.
Patton, R. J., Frank, P. M., & Clark, R. N. (Eds.). (2013). Issues of fault diagnosis for dynamic systems. Springer Science & Business Media.
Purarjomandlangrudi, A., Ghapanchi, A. H., & Esmalifalak, M. (2014). A data mining approach for fault diagnosis: An application of anomaly detection algorithm. Measurement, 55, 343-352.
Russell, B. D., & Benner, C. L. (2010). Intelligent systems for improved reliability and failure diagnosis in distribution systems. IEEE Transactions on Smart Grid, 1(1), 48-56.
Şeker, S., Ayaz, E., & Türkcan, E. (2003). Elman's recurrent neural network applications to condition monitoring in nuclear power plant and rotating machinery. Engineering Applications of Artificial Intelligence, 16(7), 647-656.
Shin, J. H., & Jun, H. B. (2015). On condition based maintenance policy. Journal of Computational Design and Engineering, 2(2), 119-127.
Shui, H., Jin, X., & Ni, J. (2015). An Anomaly Detection and Diagnosis Method Based on Real-Time Health Monitoring for Progressive Stamping Processes. In ASME 2015 International Manufacturing Science and Engineering Conference (pp. V002T05A021-V002T05A021). American Society of Mechanical Engineers.
Sutharssan, T., Stoyanov, S., Bailey, C. and Yin, C. (2015). Prognostic and health management for engineering systems: a review of the data-driven approach and algorithms. The journal of engineering. doi: 10.1049/joe.2014.0303
Volponi, A. J., DePold, H., Ganguli, R., & Daguang, C. (2003). The use of Kalman filter and neural network methodologies in gas turbine performance diagnostics: a comparative study. Journal of engineering for gas turbines and power, 125(4), 917-924.
Wang, G., Li, Q., Sun, J., & Meng, X. (2015). Telemetry data processing flow model: a case study. Aircraft Engineering and Aerospace Technology: An International Journal, 87(1), 52-58.
Yairi, T., Hori, K., & Hirama, K. (2005). Qualitative map learning based on covisibility of objects. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 35(4), 779-800.
Yairi, T., Kawahara, Y., Fujimaki, R., Sato, Y., & Machida, K. (2006, July). Telemetry-mining: a machine learning approach to anomaly detection and fault diagnosis for space systems. In 2nd IEEE International Conference on Space Mission Challenges for Information Technology (SMC-IT'06) (pp. 8-pp). IEEE.
Yairi, T., Kato, Y., & Hori, K. (2001, June). Fault detection by mining association rules from house-keeping data. In proceedings of the 6th International Symposium on Artificial Intelligence, Robotics and Automation in Space (pp. 18-21).
Zhang, Y., & Jiang, J. (2008). Bibliographical review on reconfigurable fault-tolerant control systems. Annual reviews in control, 32(2), 229-252.
Regular Session Papers