Dynamic Bayesian Networks for Prognosis



Published Oct 14, 2013
Gregory Bartram Sankaran Mahadevan


In this paper, a methodology for probabilistic prognosis of a system using a dynamic Bayesian network (DBN) is proposed. Dynamic Bayesian networks are suitable for probabilistic prognosis because of their ability to integrate information in a variety of formats from various sources and give a probabilistic representation of a system. Further, DBNs provide a platform naturally suited for seamless integration of diagnosis, uncertainty quantification, and prediction. In the proposed methodology, a DBN is used for online diagnosis via particle filtering, providing a current estimate of the joint distribution over the system variables. From this state estimate, future states of the system are predicted using the DBN and sequential Monte Carlo sampling. Prediction in this manner provides the necessary information to estimate the distribution of remaining use life (RUL). The DBN-based recursive prediction procedure may be used to estimate the system state between available measurements, when filtering is not possible. The prognosis procedure, which is system specific, is validated using a suite of offline hierarchical metrics. The prognosis methodology is demonstrated on a hydraulic actuator subject to a progressive seal wear that results in internal leakage between the chambers of the actuator.

How to Cite

Bartram, G. ., & Mahadevan, S. . (2013). Dynamic Bayesian Networks for Prognosis. Annual Conference of the PHM Society, 5(1). https://doi.org/10.36001/phmconf.2013.v5i1.2246
Abstract 239 | PDF Downloads 156



diagnosis, particle filtering, prognosis, Dynamic Bayesian Network, hydraulic actuator

Andrieu, C., Davy, M., & Doucet, A. (2003). Efficient particle filtering for jump Markov systems. Application to time-varying autoregressions. IEEE Transactions on Signal Processing, 51(7), 1762–1770. doi:10.1109/TSP.2003.810284

Banjevic, D., & Jardine, A. K. S. (2006). Calculation of reliability function and remaining useful life for a Markov failure time process. IMA Journal of Management Mathematics, 17(2), 115–130.doi:10.1093/imaman/dpi029

Bartram, G., & Mahadevan, S. (2013). Integration of Heterogeneous Information in SHM Models. Structural Control and Health Monitoring, Accepted.

Box, G. E. P., Jenkins, G. M., & Reinsel, G. C. (2008). Time series analysis: forecasting and control. Hoboken, N.J.:John Wiley.

Boyen, X., & Koller, D. (1998). Tractable inference for complex stochastic processes. In Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence (pp. 33–42).
San Francisco, CA, USA: Morgan Kaufmann Publishers Inc. Retrieved from http://dl.acm.org/citation.cfm?id=2074094.2074099

Briscoe, B. (1981). Wear of polymers: an essay on fundamental aspects. Tribology International, 14(4), 231–243. doi:10.1016/0301-679X(81)90050-5

Briscoe, B. J., & Sinha, S. K. (2002). Wear of polymers.Proceedings of the Institution of Mechanical Engineers, Part J: Journal of Engineering Tribology, 216(6), 401– 413. doi:10.1243/135065002762355325

Chen, Z. (2003). Bayesian filtering: From Kalman filters to particle filters, and beyond. Statistics, 1–69.

Chinnam, R. B., & Baruah, P. (2003). Autonomous diagnostics and prognostics through competitive learning driven HMM-based clustering. In Proceedings of the International Joint Conference on Neural Networks, 2003 (Vol. 4, pp. 2466–2471 vol.4). Presented at the Proceedings of the International Joint Conference on Neural Networks, 2003. doi:10.1109/IJCNN.2003.1223951

Dong, M., & Yang, Z. (2008). Dynamic Bayesian network based prognosis in machining processes. Journal of Shanghai Jiaotong University (Science), 13(3), 318– 322. doi:10.1007/s12204-008-0318-y

Doucet, A., Godsill, S., & Andrieu, C. (2000). On Sequential Monte Carlo Sampling Methods for Bayesian Filtering. STATISTICS AND COMPUTING, 10(3), 197–208.

Farrar, C. R., & Worden, K. (2012). Structural Health Monitoring: A Machine Learning Perspective. John Wiley & Sons.

Friedman, N., Murphy, K., & Russell, S. (1998). Learning the Structure of Dynamic Probabilistic Networks. In UAI’98 Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence (pp. 139–147). Morgan Kaufmann Publishers Inc. Retrieved from http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1. 1.32.6615

Gebraeel, N. Z., & Lawley, M. A. (2008). A neural network degradation model for computing and updating residual life distributions. Automation Science and Engineering, IEEE Transactions on, 5(1), 154–163.

Goebel, K., Saha, B., Saxena, A., Mct, N., & Riacs, N. (2008). A comparison of three data-driven techniques for prognostics. In 62nd Meeting of the Society For Machinery Failure Prevention Technology (MFPT) (pp.119–131).

Goode, K. B., Moore, J., & Roylance, B. J. (2000). Plant machinery working life prediction method utilizing reliability and condition-monitoring data. Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering, 214(2), 109–122. doi:10.1243/0954408001530146

Heckerman, D., & Geiger, D. (1995). Learning Bayesian Networks: A unification for discrete and Gaussian domains. PROCEEDINGS OF ELEVENTH CONFERENCE ON UNCERTAINTY INARTI CIAL INTELLIGENCE. Retrieved from http://citeseer.ist.psu.edu/viewdoc/summary?doi=10.1.1 .156.7976

Jardine, A. K. S., Lin, D., & Banjevic, D. (2006). A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mechanical Systems and Signal Processing, 20(7), 1483–1510. doi:10.1016/j.ymssp.2005.09.012

Jinlin, Z., & Zhengdao, Z. (2012). Fault prognosis for data incomplete systems: A dynamic Bayesian network approach. In Control and Decision Conference (CCDC), 2012 24th Chinese (pp. 2244–2249). Presented at the Control and Decision Conference (CCDC), 2012 24th Chinese. doi:10.1109/CCDC.2012.6244360

Jones, M. H. (Ed.). (1983). Industrial Tribology: The Practical Aspects of Friction, Lubrication and Wear. North Holland.

Kacprzynski, G. J., Sarlashkar, A., Roemer, M. J., Hess, A., & Hardman, B. (2004). Predicting remaining life by fusing the physics of failure modeling with diagnostics. JOM, 56(3), 29–35. doi:10.1007/s11837-004-0029-2

Karpenko, M., & Sepehri, N. (2003). Robust Position Control of an Electrohydraulic Actuator With a Faulty Actuator Piston Seal. Journal of Dynamic Systems, Measurement, and Control, 125(3), 413–423. doi:10.1115/1.1592194

Khan, T., Udpa, L., & Udpa, S. (2011). Particle filter based prognosis study for predicting remaining useful life of steam generator tubing. In Prognostics and Health Management (PHM), 2011 IEEE Conference on (pp. 1 –6). doi:10.1109/ICPHM.2011.6024323

Khedkar, J., Negulescu, I., & Meletis, E. I. (2002). Sliding wear behavior of PTFE composites. Wear, 252(5–6), 361–369. doi:10.1016/S0043-1648(01)00859-6

Koller, D., & Friedman, N. (2009). Probabilistic Graphical Models: Principles and Techniques. MIT Press.

Kozlowski, J. D. (2003). Electrochemical cell prognostics using online impedance measurements and model- based data fusion techniques. In 2003 IEEE Aerospace Conference, 2003. Proceedings (Vol. 7, pp. 3257– 3270). Presented at the 2003 IEEE Aerospace Conference, 2003. Proceedings. doi:10.1109/AERO.2003.1234169

Kulakowski, B. T., Gardner, J. F., & Shearer, J. L. (2007). Dynamic modeling and control of engineering systems. Cambridge University Press.

Kwan, C., Zhang, X., Xu, R., & Haynes, L. (2003). A novel approach to fault diagnostics and prognostics. In IEEE International Conference on Robotics and Automation, 2003. Proceedings. ICRA ’03 (Vol. 1, pp. 604–609 vol.1). Presented at the IEEE International Conference on Robotics and Automation, 2003. Proceedings. ICRA ’03.

Lancaster, J. K. (1969). Abrasive wear of polymers. Wear, 14(4), 223–239. doi:10.1016/0043-1648(69)90047-7

Lauritzen, S. L. (1992). Propagation of Probabilities, Means, and Variances in Mixed Graphical Association Models. Journal of the American Statistical Association, 87(420), 1098–1108. doi:10.2307/2290647

Lin, D., & Makis, V. (2004). Filters and parameter estimation for a partially observable system subject to random failure with continuous-range observations. Advances in Applied Probability, 36(4), 1212–1230. doi:10.1239/aap/1103662964

Liu, J., Saxena, A., Goebel, K., Saha, B., & Wang, W. (2010). An Adaptive Recurrent Neural Network for Remaining Useful Life Prediction of Lithium-ion Batteries. DTIC Document.

Lorton, A., Fouladirad, M., & Grall, A. (2013). A methodology for probabilistic model-based prognosis. European Journal of Operational Research, 225(3), 443–454. doi:10.1016/j.ejor.2012.10.025

MacCormick, B. W. (1995). Aerodynamics, Aeronautics, and Flight Mechanics. John Wiley & Sons, Incorporated.

Mahulkar, V., McGinnis, H., Derriso, M., & Adams, D. E. (2010). Fault Identification in an Electro-Hydraulic Actuator and Experimental Validation of Prognosis Based Life Extending Control. DTIC Document.

Naval Surface Warfare Center. (2011). Handbook of Reliability Prediction Procedures for Mechanical Equipment. West Bethesda, Maryland 20817-5700. Retrieved from http://www.navsea.navy.mil/nswc/carderock/pub/mechr el/products/handbook.aspx

Nikas, G. K. (2010). Eighty years of research on hydraulic reciprocating seals: Review of tribological studies and related topics since the 1930s. Proceedings of the Institution of Mechanical Engineers, Part J: Journal of Engineering Tribology, 224(1), 1–23. doi:10.1243/13506501JET607

Orchard, M. E., & Vachtsevanos, G. J. (2009). A particle- filtering approach for on-line fault diagnosis and failure prognosis. Transactions of the Institute of Measurement and Control. doi:10.1177/0142331208092026

Pitt, M. K., & Shephard, N. (1999). Filtering via Simulation: Auxiliary Particle Filters. Journal of the American Statistical Association, 94(446), 590–599. doi:10.1080/01621459.1999.10474153
Technical Research Papers

Most read articles by the same author(s)