A Hybrid Approach for Fusing Physics and Data for Failure Prediction



Published Nov 13, 2020
Prashanth Pillai Anshul Kaushik Shivanand Bhavikatti Arjun Roy Virendra Kumar


This work describes the architecture for developing physics of failure models, derived as a function of machine sensor data, and integrating with data pertaining to other relevant factors like geography, manufacturing, environment, customer and inspection information, that are not easily modeled using physics principles. The mechanics of the system is characterized using surrogate models for stress and metal temperature based on results from multiple non-linear finite element simulations. A cumulative damage index measure has been formulated that quantifies the health of the component. To address deficiencies in the simulation results, a model tuning framework is designed to improve the accuracy of the model. Despite the model tuning, un-modelled sources of variation can lead to insufficient model accuracy. It is required to incorporate these un-modelled effects so as to improve the model performance. A novel machine learning based model fusion approach has been presented that can combine physics model predictions with other data sources that are difficult to incorporate in a physics framework. This approach has been applied to a gas turbine hot section turbine blade failure prediction example.

Abstract 451 | PDF Downloads 485



machine learning, prognostics, data fusion, Hybrid model

Baraldi, P., Mangili, F., & Zio, E. (2012). A kalman filter-based ensemble approach with application to turbine creep prognostics. IEEE Transactions on Reliability, 61(4), 966-977.
Bostwichk, D., & Burke, H. (2001). Prediction of individual patient outcome in cancer. Cancer Supplement, 91, 1643-1646.
Cheng, S., & Pecht, M. (2009). A fusion prognostics method for remaining useful life prediction of electronic products. IEEE International Conference on Automation Science and Engineering, (pp. 102-107).
Crowder, M., Kimber, A., Sweeting, T., & Smith, R. (1994). Statistical Analysis of Reliability Data. London: Chapman & Hall/CRC.
Elsayed, E. (1996). Reliability engineering. NJ: Prentice-Hall, Englewood Cliffs.
Groer, P. (2000). Analysis of time-to-failure with a Weibull model. Proceedings of the Maintenance and Reliability Conference, (pp. 59.01–59.04). Knoxville.
Hansen, R. J., Hall, D. L., & Kurtz, S. K. (1995). A new approach to the challenge of machinery prognostics. Journal of engineering for gas turbines and power, 117(2), 320-325.
Hastie, T., Friedman, J. H., & Tibishirani, R. (2001). The Elements of Statistical learning (Vol. 1). Berlin: Springer.
Heng, A., Zhang, S., Tan, A. C., & Mathew, J. (2009). Rotating machinery prognostics: State of the art, challenges and opportunities. Mechanical Systems and Signal Processing, 23(3), 724–739.
Javed, K. (2014). A robust & reliable Data-driven prognostics approach based on extreme learning machine and fuzzy clustering. Doctoral dissertation, Universite de Franche-Comte.
Joshi, R., & Reeves, C. (2006). Beyond the Cox model: artificial neural networks for survival analysis part II. Proceedings of the Eighteenth International Conference on Systems Engineering, 179-184.
Kapur, K., & Lamberson, L. (1977). Reliability in Engineering Design. New York: Wiley.
Keller, A., Perera, U., & Kamath, A. (1982). Reliability analysis of CNC machine tools. Reliability Engineering, 449-473.
Koul, A. K., Bhanot, S., Tiku, A., & Junkin, B. (2007). Importance of Physics-Based Prognosis for Improving Turbine Reliability: RRA 501KB Gas Turbine Blade Case Study. ASME 2007 Power Conference . San Antonio.
Koul, A. K., Zhou, X., Fuleki, D., Gauthier, D., & W., W. (2005). Importance of Physics-Based Prognosis for Improving Turbine Reliability Part 1 – A Turbine Blade Case Study. 16th Symposium on Industrial Application of Gas Turbines (IAGT) . Banff, Alberta, Canada .
Lawless, J. (2002). Statistical Models and Methods for Lifetime Data. New York: Wiley-Interscience.
Li, C., & Lee, H. (2005). Gear fatigue crack prognosis using embedded model, gear dynamic model and fracture mechanics. Mechanical Systems and Signal Processing, 19, 836-846.
Li, Y., Billington, S., Zhang, C., Kurfess, T., Danyluk, S., & Liang, S. (1999). Adaptive prognostics for rolling element bearing condition. Mechanical Systems and Signal Processing, 13, 103-113.
Medjaher, K., Tobon-Mejia, D. A., & Zerhouni, N. (2012). Remaining useful life estimation of critical components with application to bearings. IEEE Transactions on Reliability, 61(2), 292-302.
Oppenheimer, C., & Loparo, K. (2002). Physically based diagnosis and prognosis of cracked rotor shafts. Proceedings of SPIE Component and Systems Diagnostics (pp. 122-132). Bellingham: Prognostics, and Health Management II.
Paris, P. C., & Erdogan, F. (1963). A critical analysis of crack propagation laws. Journal of Basic Engineering, 85, 528-534.
Ramasso, E., Placet, V., Gouriveau, R., Boubakar, L., & Zerhouni, N. (2012). Health assessment of composite structures in unconstrained environments using partially supervised pattern recognition tools. Prognostics and Health Management Society , (pp. 1-11).
Saxena, A., Celaya, J. R., Roychoudhury, I., Saha, S., Saha, B., & Goebel, K. (2012). Designing data-driven battery prognostic approaches for variable loading profiles: Some lessons learned. European Conference of Prognostics and Health Management Society .
Schömig, A., & Rose, O. (2003). On the suitability of the Weibull distribution for the approximation of machine failures. Proceedings of the Industrial Engineering Research Conference. Portland.
Setiono, R., Leow, W., & Thong, J. (2000). Opening the neural network blackbox: An algorithm for extracting rules from function approximating artificial neural networks. Proceedings of International Conference on Information Systems, (pp. 176–186). Brisbane.
Si, X.-S., Wang, W., Hu, C.-H., & Zhou, D.-H. (2011). Remaining useful life estimation – A review on the statistical data driven approaches. European Journal of Operational Research, 213, 1-14.
Sikorska, J., M.Hodkiewicz, & Ma, L. (2011). Prognostic modelling options for remaining useful life estimation by industry. Mechanical Systems and Signal Processing, 25, 1803-1836.
Spera, D. A. (1969). Calculation of thermal-fatigue life based on accumulated creep damage. NASA. NASA Technical Note.
Suresh, S. (1998). Fatigue of Materials. Cambridge University Press.
Sutharssan, T., Stoyanov, S., Bailey, C., & Rosunally, Y. (2012). Prognostics and health monitoring of high power led. Micromachines, 3(1), 78-100.
Tickle, A., Andrews, R., Golea, M., & Diederich, J. (1998). The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks. IEE Transactions on Neural Networks, 9, 1057–1068.
Tse, P., & Atherton, D. (1999). Prediction of machine deterioration using vibration based fault trends and recurrent neural networks. Transactions of the ASME: Journal of Vibration and Acoustics, 121, 355-362.
Zaretsky, E. V. (1998). A. Palmgren revisited - A basis for bearing life prediction. Lubrication Engineering, 54, 18-24.
Technical Papers