Abstract
Remaining useful life prediction of a system is one of the most important and critical items to achieve the optimal condition-based maintenance for availability and reliability increase, and maintenance reduction. We develop an artificial neural network (ANN) based approach to increase accuracy for the prediction of a system/component remaining useful life. The ANN model takes the working time/age and some parameters produced by a condition monitoring process at the present and previous inspection points as the inputs, and the percentage of the life is produced as the output. Also, different distribution functions, such as Weibull, Birnbaum–Saunders, Gamma, Wakeby, Logistic and Log–normal function are utilized to adjust each condition monitoring data for a failure history, and the adjusted values are applied to determine the training set so as to decrease the noise factors influences unrelated to the degradation of the equipment. The ANN method is validated using the collected vibration monitoring data from a particular machine (pump bearings in the field). Finally, the performance of the distribution functions on the results of the ANN output is compared and the more effective functions are defined.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ali JB, Chebel-Morello B, Saidi L, Malinowski S, Fnaiech F (2015) Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network. Mech Syst Signal Process 56–57:150–172
Banjevic D, Jardine AKS (2006) Calculation of reliability function and remaining useful life for a Markov failure time process. IMA J Manag Math 17:115–130
Elwany AH, Gebraeel NZ (2008) Sensor-driven prognostic models for equipment replacement and spare parts inventory. IIE Trans 40:629–639
Farsi MA (2016) Principles of reliability engineering. Symaye Danesh, Tehran
Ghods A, Lee H-H (2016) Probabilistic frequency-domain discrete wavelet transforms for better detection of bearing faults in induction motors. Neurocomputing 188:206–216
Guo L, Li N, Jia F, Lei Y, Lin J (2017) A recurrent neural network based health indicator for remaining useful life prediction of bearings. Neurocomputing 240:98–109
Harris TA (2001) Rolling bearing analysis. Wiley, Hoboken
Hitchcock L (2006) ISO standards for condition monitoring. In: Mathew J, Kennedy J, Ma L, Tan A, Anderson D (eds) Engineering asset management. Springer, London, pp 606–613
Jardine AK, Lin D, Banjevic D (2006) A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech Syst Signal Process 20:1483–1510
Jia F, Lei Y, Lin J, Zhou X, Na L (2016) Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mech Syst Signal Process 72:303–315
Lee J, Ni J, Djurdjanovic D, Qiu H, Liao H (2006) Intelligent prognostics tools and e-maintenance. Comput Ind 57:476–489
Lei Y, Lin J, Zuo MJ, He Z (2014) Condition monitoring and fault diagnosis of planetary gearboxes: a review. Measurement 48:292–305
Lei Y, Li N, Lin J (2016) A new method based on stochastic process models for machine remaining useful life prediction. IEEE Trans Instrum Meas 65:2671–2684
Li CJ, Lee H (2005) Gear fatigue crack prognosis using embedded model, gear dynamic model and fracture mechanics. Mech Syst Signal Process 19:836–846
Lin D, Banjevic D, Jardine AKS (2006) Using principal components in a proportional hazards model with applications in condition-based maintenance. J Oper Res Soc 57:910–919
Marble S, Morton BP (2006) Predicting the remaining life of propulsion system bearings. In: 2006 IEEE on aerospace conference, p 8. IEEE
Randall RB (2004) State of the art in monitoring rotating machinery—part 1. Sound Vib 38:14–21
Roulias D (2014) Methodologies for remaining useful life estimation with multiple sensors in rotating machinery. Πανεπιστήμιο Πατρών. Σχολή Πολυτεχνική. Τμήμα Μηχανολόγων και Αεροναυπηγών Μηχανικών
Sikorska JZ, Hodkiewicz M, Ma L (2011) Prognostic modeling options for remaining useful life estimation by industry. Mech Syst Signal Process 25:1803–1836
Tian Z (2012) An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring. J Intell Manuf 23:227–237
Vachtsevanos G, Lewis FL, Roemer M, Hess A, Wu B (2006) Intelligent fault diagnosis and prognosis for engineering systems. Wiley, Hoboken
Wang Y, Xu G, Zhang Q, Liu D, Jiang K (2015) Rotating speed isolation and its application to rolling element bearing fault diagnosis under large speed variation conditions. J Sound Vib 348:381–396
Wu S, Gebraeel N, Lawley MA, Yih Y (2007) A neural network integrated decision support system for condition-based optimal predictive maintenance policy. IEEE Trans Syst Man Cybern Part A Syst Hum 37:226–236
Zhu S-P, Huang H-Z, Peng W, Wang H-K, Mahadevan S (2016) Probabilistic physics of failure-based framework for fatigue life prediction of aircraft gas turbine discs under uncertainty. Reliab Eng Syst Saf 146:1–12
Zhu S-P, Liu Q, Peng W, Zhang X-C (2018) Computational-experimental approaches for fatigue reliability assessment of turbine bladed disks. Int J Mech Sci 142–143:502–517
Acknowledgements
The authors would like to thank the associate editor and anonymous reviewers for their constructive comments which have led to an improvement to an earlier version of the paper.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Farsi, M.A., Masood Hosseini, S. Statistical distributions comparison for remaining useful life prediction of components via ANN. Int J Syst Assur Eng Manag 10, 429–436 (2019). https://doi.org/10.1007/s13198-019-00813-w
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13198-019-00813-w