Prognostic and health management for engineering systems: a review of the data-driven approach and algorithms
- Author(s): Thamo Sutharssan 1 ; Stoyan Stoyanov 2 ; Chris Bailey 2 ; Chunyan Yin 2
-
-
View affiliations
-
Affiliations:
1:
Sustainable Energy Technologies Group , University of Hertfordshire , Hatfield , Hertfordshire , UK ;
2: Computational Mechanics and Reliability Group , Old Royal Naval College , University of Greenwich , Park Row , London , UK
-
Affiliations:
1:
Sustainable Energy Technologies Group , University of Hertfordshire , Hatfield , Hertfordshire , UK ;
- Source:
Volume 2015, Issue 7,
July
2015,
p.
215 – 222
DOI: 10.1049/joe.2014.0303 , Online ISSN 2051-3305
- « Previous Article
- Table of contents
- Next Article »
Prognostics and health management (PHM) has become an important component of many engineering systems and products, where algorithms are used to detect anomalies, diagnose faults and predict remaining useful lifetime (RUL). PHM can provide many advantages to users and maintainers. Although primary goals are to ensure the safety, provide state of the health and estimate RUL of the components and systems, there are also financial benefits such as operational and maintenance cost reductions and extended lifetime. This study aims at reviewing the current status of algorithms and methods used to underpin different existing PHM approaches. The focus is on providing a structured and comprehensive classification of the existing state-of-the-art PHM approaches, data-driven approaches and algorithms.
Inspec keywords: cost reduction; fault diagnosis; safety; maintenance engineering; remaining life assessment
Other keywords: remaining useful lifetime; fault diagnosis; prognostics and health management; maintenance cost reduction; PHM; RUL; operational cost reduction; engineering systems; anomaly detection; data-driven approach
Subjects: Financial management; Maintenance and reliability; Health and safety aspects
References
-
-
1)
-
18. Markou, M., Singh, S.: ‘Novelty detection: a review – part 1: statistical approaches’, Signal Process., 2003, 83, (12), pp. 2481–2497 (doi: 10.1016/j.sigpro.2003.07.018).
-
-
2)
-
7. Celaya, J.R., Saxena, A., Wysocki, P., Saha, S., Goebel, K.: ‘Towards prognostics of power MOSFETs: accelerated aging and precursors of failure’. Proc. of the Annual Conf. of the Prognostics and Health Management Society (PHM 2011), Montreal, 25–29 September 2011, pp. 1–10.
-
-
3)
-
28. Boriah, S., Chandola, V., Kumar, V.: ‘Similarity measures for categorical data: a comparative evaluation’. Proc. of the Eighth SIAM Int. Conf. on Data Mining, GA, 2–26 April 2008, pp. 243–254.
-
-
4)
-
4. Sotiris, V.A., Tse, P.W., Pecht, M.G.: ‘Anomaly detection through a Bayesian support vector machine’, IEEE Trans. Reliab., 2010, 59, (2), pp. 277–286 (doi: 10.1109/TR.2010.2048740).
-
-
5)
-
36. Tipping, M.E.: ‘Sparse Bayesian learning and the relevance vector machine’, J. Mach. Learn. Res., 2001, 1, pp. 211–244.
-
-
6)
-
20. Vapnik, V.N.: ‘Statistical learning theory’ (Wiley-Interscience, 1998).
-
-
7)
-
46. Orchard, M.E., Vachtsevanos, G.J.: ‘A particle filtering-based framework for real-time fault diagnosis and failure prognosis in a turbine engine’. Proc. of the 15th Mediterranean Conf. on Control & Automation, Athens, 27–29 July 2007, pp. 1–6.
-
-
8)
-
8. Goebel, K., Saha, B., Saxena, A.: ‘A comparison of three data-driven techniques for prognostics’. Proc. of the 62nd Meeting of the Society for Machinery Failure Prevention Technology (MFPT), Virginia Beach, 6–8 May 2008, pp. 119–131.
-
-
9)
-
3. Pecht, M.G., Jaai, R.: ‘A prognostics and health management roadmap for information and electronics-rich systems’, Microelectron. Reliab., 2010, 50, (3), pp. 317–323 (doi: 10.1016/j.microrel.2010.01.006).
-
-
10)
-
48. Orchard, M.E., Vachtsevanos, G.J.: ‘A particle filtering approach for online fault diagnosis and failure prognosis’, Trans. Inst. Meas. Control, 2009, 31, (3–4), pp. 221–246 (doi: 10.1177/0142331208092026).
-
-
11)
-
9. Ling, B., Khonsari, M., Hathaway, R.: ‘Data-driven roller bearing diagnosis using degree of randomness and Laplace test’. Proc. of the Annual Conf. of the Prognostics and Health Management Society (PHM 2009), San Diego, 27 September–01 October 2009, pp. 1–8.
-
-
12)
-
43. Lall, P., Lowe, R., Goebel, K.: ‘Prognostics using Kalman-filter models and metrics for risk assessment in BGAs under shock and vibration loads’. Proc. of the 60th Electronic Components and Technology Conf. (ECTC), Las Vegas, 1–4 June 2010, pp. 889–901.
-
-
13)
-
5. Alam, M.A., Azarian, M.H., Osterman, M., Pecht, M.: ‘Prognostics of failures in embedded planar capacitors using model-based and data-driven approaches’, J. Intell. Mater. Syst. Struct., 2011, 22, (12), pp. 1293–1304 (doi: 10.1177/1045389X11416024).
-
-
14)
-
34. Jordan, M.I., Bishop, C.M.: ‘Neural networks’, in Tucker, A. (Ed.): ‘CRC handbook of computer science’ (CRC Press, Boca Raton, FL, 1996), pp. 536–556.
-
-
15)
-
15. Saha, B., Goebel, K.: ‘Model adaptation for prognostics in a particle filtering framework’, Int. J. Prognostics Health Manage., 2011, 6, (6), pp. 1–10.
-
-
16)
-
37. Rasmussen, C.E., Williams, C.K.I.: ‘Gaussian processes for machine learning’ (The MIT Press, MA, 2006).
-
-
17)
-
49. Butler, S., Ringwood, J.: ‘Particle filters for remaining useful life estimation of abatement equipment used in semiconductor manufacturing’. Proc. of the 2010 Conf. on Control and Fault Tolerant Systems, Nice, 6–8 October 2010, pp. 436–441.
-
-
18)
-
13. Saxena, A., Goebel, K., Simon, D., Eklund, N.: ‘Damage propagation modelling for aircraft engine run-to-failure simulation’. Proc. of the Annual Conf. of the Prognostics and Health Management Society (PHM 2008), Denver, 6–9 October 2008, pp. 1–9.
-
-
19)
-
29. Tang, Y.: ‘Size and power estimation for the Wilcoxon–Mann–Whitney test for ordered categorical data’, Stat. Med., 2011, 30, (29), pp. 3461–3470 (doi: 10.1002/sim.4407).
-
-
20)
-
31. Blum, A., Mitchell, T.: ‘Combining labeled and unlabeled data with co-training’. Proc. of the 11th Annual Conf. on Computational Learning Theory (COLT 98), Madisson, 24–26 July 1998, pp. 92–100.
-
-
21)
-
40. Cheng, J., Greiner, R.: ‘Learning Bayesian belief network classifiers: algorithms and system’. Proc. of the 14th Biennial Conf. of the Canadian Society on Computational Studies of Intelligence: Advances in Artificial Intelligence, Ottawa, 7–9 June 2001, pp. 141–151.
-
-
22)
-
38. Williams, C.K.I.: ‘Prediction with Gaussian processes: from linear regression to linear prediction and beyond’. Learning and Inference in Graphical Models, Kluwer, Netherlands, 1998, pp. 599–621.
-
-
23)
-
1. Vichare, N.M., Rodgers, P., Pecht, M.G.: ‘Methods for binning density estimation of load parameters for prognostics and health management’, Int. J. Performability Eng., 2006, 2, (2), pp. 149–161.
-
-
24)
-
33. Schwabacher, M., Goebel, K.: ‘A survey of artificial intelligence for prognostics’. Proc. of the AAAI Fall Symp., 9–11 November 2007, pp. 1–8.
-
-
25)
-
44. Orchard, M., Wu, B., Vachtsevanos, G.: ‘A particle filter framework for failure prognosis’. Proc. of the World Tribology Congress III (WTC2005), Washington DC, 12–16 September 2005, pp. 1–2.
-
-
26)
-
20. Arulampalam, M.S., Maskell, S., Clapp, T.: ‘A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking’, IEEE Trans. Signal Process., 2002, 50, (2), pp. 174–188 (doi: 10.1109/78.978374).
-
-
27)
-
17. Kalman, R.E.: ‘A new approach to linear filtering and prediction problems’, J. Basic Eng., 1960, 82, (1), pp. 35–45 (doi: 10.1115/1.3662552).
-
-
28)
-
39. Bishop, C.M.: ‘Pattern recognition and machine learning’ (Springer, New York, 2007).
-
-
29)
-
47. Orchard, M., Kacprzynski, G., Goebel, K., Saha, B., Vachtsevanos, G.: ‘Advances in uncertainty representation and management for particle filtering applied to prognostics’. Proc. of the Int. Conf. on Prognostics and Health Management (PHM 2008), Denver, 6–9 October 2008, pp. 1–6.
-
-
30)
-
45. Orchard, M.E.: ‘A particle filtering-based framework for on-line fault diagnosis and failure prognosis’. PhD dissertation, Georgia Institute of Technology, Atlanta, 2007.
-
-
31)
-
23. Box, G.E.P., Andersen, S.L.: ‘Permutation theory in the derivation of robust criteria and the study of departures from assumption’, J. R. Stat. Soc., 1955, 17, pp. 1–34.
-
-
32)
-
25. Roberts, S.J.: ‘Novelty detection using extreme value statistics’, IEE J. Vis. Image Signal Process., 1999, 146, (3), pp. 124–129 (doi: 10.1049/ip-vis:19990428).
-
-
33)
-
30. Samuel, A.L.: ‘Some studies in machine learning using the game of checkers. II – recent progress’, IBM J. Res. Dev., 1967, 11, (6), pp. 601–617 (doi: 10.1147/rd.116.0601).
-
-
34)
-
26. Awate, S.P.: ‘Adaptive, nonparametric Markov models and information-theoretic methods for image restoration and segmentation’. PhD dissertation, University of Utah, Salt Lake City, 2006.
-
-
35)
-
16. Celaya, J.R., Saxena, A., Saha, S., Goebel, K.F.: ‘Prognostics of power MOSFETs under thermal stress accelerated aging using data-driven and model-based methodologies’. Proc. of the Annual Conf. of the Prognostics and Health Management Society (PHM 2011), Montreal, 25–29 September 2011, pp. 1–10.
-
-
36)
-
11. Pecht, M.G.: ‘Prognostics and health management of electronics’ (John Wiley & Sons, New York, 2008).
-
-
37)
-
14. Saha, B., Goebel, K.: ‘Prognostics HIL testbed’. Proc. of the Aviation Safety IVHM Posters, Virginia, 17–19 November 2009, pp. 1–1.
-
-
38)
-
17. Celaya, J.R., Kulkarni, C., Biswas, G., Saha, S., Goebel, K.: ‘A model-based prognostics methodology for electrolytic capacitors based on electrical overstress accelerated aging’. Proc. of the Annual Conf. of the Prognostics and Health Management Society (PHM 2011), Montreal, 25–29 September 2011, pp. 1–9.
-
-
39)
-
19. Clifton, D.A., Clifton, L.A., Bannister, P.R., Tarassenko, L.: ‘Automated novelty detection in industrial systems’, Stud. Comput. Intell., 2008, 116, (1), pp. 269–296 (doi: 10.1007/978-3-540-78297-1_13).
-
-
40)
-
21. Bishop, C.M., Tipping, M.E.: ‘Vibrational relevance vector machines’. Proc. of the 16th Conf. on Uncertainty in Artificial Intelligence, Stanford, 30 June–3 July 2000, pp. 46–53.
-
-
41)
-
24. Lee, H.-J., Roberts, S.J.: ‘On-line novelty detection using the Kalman filter and extreme value theory’. Proc. of the 19th Int. Conf. on Pattern Recognition (ICPR 2008), FL, 8–11 December 2008, pp. 1–4.
-
-
42)
-
12. Sankavaram, C., Pattipati, B., Kodali, A., et al: ‘Model-based and data-driven prognosis of automotive and electronic systems’. Proc. of the IEEE Int. Conf. on Automation Science and Engineering (CASE 2009), Bangalore, 22–25 August 2009, pp. 96–101.
-
-
43)
-
27. Yeung, D.-Y., Chow, C.: ‘Parzen–window network intrusion detectors’. Proc. of the 16th Int. Conf. on Pattern Recognition, 2002, vol. 4, pp. 385–388.
-
-
44)
-
22. Chandola, V., Banerjee, A., Kumar, V.: ‘Anomaly detection: a survey’, ACM Comput. Surv., 2009, 41, (3), pp. 15:1–58 (doi: 10.1145/1541880.1541882).
-
-
45)
-
22. Burges, C.J.C.: ‘A tutorial on support vector machines for pattern recognition’, Data Min. Knowl. Discov., 1998, 2, (2), pp. 121–167 (doi: 10.1023/A:1009715923555).
-
-
46)
-
2. Tang, L., Kacprzynski, G.J., Goebel, K., Saxena, A., Saha, B., Vachtsevanos, G.: ‘Prognostics-enhanced automated contingency management for advanced autonomous systems’. Proc. of the Annual Conf. of the Prognostics and Health Management Society (PHM 2008), Denver, 6–9 October 2008, pp. 1–9.
-
-
47)
-
6. Byington, C.S., Watson, M., Edwards, D.: ‘Data-driven neural network methodology to remaining life predictions for aircraft actuator components’. Proc. of the IEEE Aerospace Conf., Big Sky, 6–13 March 2004, vol. 6, pp. 3581–3589.
-
-
48)
-
10. Pecht, M., Kumar, S.: ‘Data analysis approach for system reliability, diagnostics, and prognostics’. Proc. of the Pan Pacific Microelectronics Symp., Hawaii, 22–24 January 2008, pp. 1–9.
-
-
49)
-
32. Schwabacher, M.: ‘A survey of data-driven prognostics’. Proc. of the AIAA Infotech@Aerospace Conf., Virginia, 26–29 September 2005, pp. 1–5.
-
-
1)