A machine learning-based approach for product maintenance prediction with reliability information conversion

Abstract

Predictive maintenance (PdM) cannot only avoid economic losses caused by improper maintenance but also maximize the operation reliability of product. It has become the core of operation management. As an important issue in PdM, the time between failures (TBF) prediction can realize early detection and maintenance of products. The reliability information is the main basis for TBF prediction. Therefore, the main purpose of this paper is to establish an intelligent TBF prediction model for complex mechanical products. The reliability information conversion method is used to solve the problems of reliability information collection difficulty, high collection cost and small data samples in the process of TBF prediction based on reliability information for complex mechanical products. The product reliability information is fully mined and enriched to obtain more reliable and accurate TBF prediction results. Firstly, the Fisher algorithm is employed to convert the reliability information to expand the sample, and the compatibility test is also discussed. Secondly, BP neural network is used to realize the final prediction of TBF, and PSO algorithm is used to optimize the initial weight and threshold of BP neural network to avoid falling into local extreme value and improve the convergence speed. Thirdly, the mean-absolute-percentage-error and the Coefficient of determination are selected to evaluate the performance of the proposed model and method. Finally, a case study of TBF prediction for a remanufactured CNC milling machine tool (XK6032-01) is studied in this paper, and the results show that the feasibility and superiority of the proposed TBF prediction method.

Keywords

Predictive maintenance / Time between failures / Reliability Information conversion / Machine learning

References

[1] J. Yan, Y. Meng, L. Lu et al., Industrial Big Data in an Industry 4.0 Environment: Challenges, Schemes and Applications for Predictive Maintenance (IEEE Access, 2017), pp. 1–1

[2] GuillénA.J., CrespoA., MacchiM., et al.. On the role of prognostics and health management in advanced maintenance systems. Prod. Plan. Control, 2018, 27(12):991-1004

[3] SuleS.. Predictive maintenance, its implementation and latest trends. J. Eng. Manuf., 2017, 231(9):1670-1679

[4] LiuQ., MingD., LvW., et al.. Manufacturing system maintenance based on dynamic programming model with prognostics information. J. Intell. Manuf., 2017, 30(3):1155-1173

[5] ChenC., LiuY., WangS.X., et al.. Predictive maintenance using Cox proportional hazard deep learning. Adv. Eng. Inform., 2022, 44

[6] CuiP.H., WangJ.Q., ZhangW.P., et al.. Predictive maintenance decision-making for serial production lines based on deep reinforcement learning. Comput.-Integr. Manuf. Syst., 2021, 27(12):3416-3428

[7] PadgettJ., Sanchez-SilvaM., et al.. Maintenance and operation of infrastructure systems: review. J. Struct. Eng., 2016, 142(9

[8] WangK., YiW.. How AI Affects the Future Predictive Maintenance: A Primer of Deep Learning, 2018

[9] CarvalhoT.P., FabrízzioA.A., de SoaresM.N., VitaR., et al.. A systematic literature review of machine learning methods applied to predictive maintenance. Comput. Ind. Eng., 2019, 137

[10] TiagoZ., Da CostaC.A., Da Rosa RighiR., et al.. Predictive maintenance in the industry 4.0: a systematic literature review. Comput. Ind. Eng., 2020, 150

[11] KongC.. Review on advanced health monitoring methods for aero gas turbines using model based methods and artificial intelligent methods. Int. J. Aeronaut. Space Sci., 2014, 15 2):123-137

[12] K.P. Boshnakov, V.I. Petkov, L.A. Doukovska et al., Predictive maintenance model based approach for objects exposed to extremely high temperatures, in Signal Processing Symposium (2013)

[13] J. Ortiz, R.A. Carrasco, Model-based fault detection and diagnosis in ALMA subsystems: observatory operations: strategies, in Processes & Systems VI (2016)

[14] LungB., MonninM., VoisinA., et al.. Degradation state model-based prognosis for proactively maintaining product performance. CIRP Ann., 2008, 57(1):49-52

[15] LeiY., LiN., GontarzS., et al.. A model-based method for remaining useful life prediction of machinery. IEEE Trans. Reliab., 2016, 65(3):1314-1326

[16] R. Magargle, L. Johnson, P. Mandloi et al. A simulation-based digital twin for model-driven health monitoring and predictive maintenance of an automotive braking system. Proceedings of the 12th International Modelica Conference, Prague, Czech Republic, May 15–17, 2017

[17] Basic T, Distribution W.9. The Weibull Distribution (2009)

[18] HuJ.W., ChenP.. Predictive maintenance of systems subject to hard failure based on proportional hazards model. Reliab. Eng. Syst. Saf., 2020, 196

[19] X.J. Zhou, F.X. Li, L. Jay, A Reliability-Based Sequential Preventive Maintenance Model. J. Shanghai Jiaotong Univ. (2005)

[20] LiC., ZhangY., XuM.. Reliability-based maintenance optimization under imperfect predictive maintenance. Chin. J. Mech. Eng., 2012, 25(1):160-165

[21] J. Shimada, S. Sakajo, A statistical approach to reduce failure facilities based on predictive maintenance, in (International Joint Conference on Neural Networks) (2016)

[22] DailyJ., PetersonJ.. Predictive Maintenance: How Big Data Analysis Can Improve Maintenance. Supply Chain Integration Challenges in Commercial Aerospace, 2017 Berlin Springer 267-278

[23] W.J.C. Verhagen, R. Curran, L.W.M. De Boer, Component-Based Data-Driven Predictive Maintenance to Reduce Unscheduled Maintenance Events (2017)

[24] BaptistaM., SankararamanS., MedeirosI.P.D., et al.. Forecasting fault events for predictive maintenance using data-driven techniques and ARMA modeling. Comput. Ind. Eng., 2018, 115: 41-53

[25] ZenisekJ., HolzingerF., AffenzellerM.. Machine learning based concept drift detection for predictive maintenance. Comput. Ind. Eng., 2019, 137

[26] ZhangJ.J., WangP., YanR.Q., et al.. Long short-term memory for machine remaining life prediction. J. Manuf. Syst., 2018, 48: 78-86

[27] HorenbeekA.V., PintelonL.. A dynamic predictive maintenance policy for complex multi-component systems. Reliab. Eng. Syst. Saf., 2013, 120: 39-50

[28] BaptistaM., SankararamanS., de MedeirosI.P., et al.. Forecasting fault events for predictive maintenance using data-driven techniques and ARMA modeling. Comput. Ind. Eng., 2018, 15: 41-53

[29] RoccoS., ClaudioM.. Singular spectrum analysis and forecasting of failure time series. Reliab. Eng. Syst. Saf., 2013, 114: 126-136

[30] MouraM.C., ZioE., LinsI.D., et al.. Failure and reliability prediction by support vector machine. Reliab. Eng. Syst. Saf., 2011, 96(11):1527-1534

[31] LazakisI., RaptodimosY., VarelasT.. Predicting ship machinery system condition through analytical reliability tools and artificial neural networks. Ocean Eng., 2018, 152: 404-415

[32] JanaJ., RadkaS.. Finite-sample density and its small sample asymptotic approximation. Stat. Probab. Lett., 2011, 81: 1311-1318

[33] ReliabilityB.S.. Evaluation of the servo turret with accurate failure data and interval censored data based on EM algorithm. J. Mech. Sci. Technol., 2020, 34: 1503-1513

[34] LiT., ZhangW.H., ZhangS.J., et al.. Research-on gray-scale prediction model of product failure interval time based on genetic algorithm weight. Modem Manuf. Eng., 2021, 9: 101-106

[35] LiK., ShiX.M., LiJ., et al.. Bayesian estimation of ammunition demand based on multinomial distribution. Discrete Dyn. Nat. Soc., 2021, 2021

[36] LenhardJ.. A transformation of Bayesian statistics: computation, prediction, and rationality. Stud. Hist. Philos. Sci., 2022, 92: 144-151

[37] MandalA.K., RakshitS., StalinC.S., et al.. Estimation of the size and structure of the broad line region using Bayesian approach. Mon. Not. R. Astron. Soc., 2021, 502(1):2140-2157

[38] MlE., SjkabC., RlA., et al.. Long-term forecasting of El Nio events via dynamic factor simulations. J. Econom., 2020, 214(1):46-66

[39] ZengB., DuanH., BaiY., et al.. Forecasting the output of shale gas in China using an unbiased grey model and weakening buffer operator. Energy, 2018, 151: 238-249

[40] HuY.C.. Constructing grey prediction models using grey relational analysis and neural networks for magnesium material demand forecasting. Appl. Soft Comput., 2020, 93

[41] WangC., YenG.G., JiangM.. A grey prediction-based evolutionary algorithm for dynamic multiobjective optimization. Swarm Evol. Comput., 2020, 56(1

[42] YeL., XiaX.T., ZhenC., et al.. Evaluation of dynamic uncertainty of rolling bearing vibration performance. Math. Probl. Eng., 2019, 2: 1-17

[43] SuoH.L., GaoJ.M., GaoZ.Y., et al.. Bootstrap and maximum entropy based small-sample product lifetime probability distribution. IFAC-PapersOnLine, 2015, 48 3):219-224

[44] MarelliS., SudretB.. An active-learning algorithm that combines sparse polynomial chaos expansions and bootstrap for structural reliability analysis. Struct. Saf., 2018, 75: 67-74

[45] MikshowskyA.A., GianolaD., WeigelK.A.. Improving reliability of genomic predictions for Jersey sires using bootstrap aggregation sampling. J. Dairy Sci., 2016, 99(5):3632-3645

[46] LiH.Y.. The Decision Making on Scheduled Maintenance of Civil Aircraft Based on the Reliability, 2016 Nanjing Nanjing University of Aeronauticsand Astronautics

[47] ZhongH.M., LiangY.N., HeS.L., et al.. Construction of a knowledge base for log interpretation using KNN-Fisher. Geophys. Prospect. Pet., 2021, 60(3):395-402

[48] AhmedN.K., AtiyaA.F., GayarN.E., et al.. An empirical comparison of machine learning models for time series forecasting. Econom. Rev., 2010, 29(5–6):594-621

[49] YangJ.F., ZhaiY.J., WangD.F., et al.. Time series prediction based on support vector regression. Proc. CSEE, 2005, 25(017):110-114 (in Chinese)

[50] BontempiG., TaiebS.B., Le BorgneY.A.. Machine Learning Strategies for Time Series Forecasting//European Business Intelligence Summer School, 2012 Brussels Springer 62-77

[51] WanC., LiW.Z., DingW.X., et al.. A multivariate time series forecasting algorithm based on self-evolution and pre-training. Chinese J. Comput., 2022, 45(3):513-525

[52] DaiZ., LiZ., JiaoY., et al.. Reliability assessment based on BP neural network for relay protection system with a few failure data samples. Electr. Power Autom. Equip., 2014, 34(11):129-134

[53] WangJ.W., WangJ., LiuS., et al.. Construction period prediction of open-cut subway station based on PSO-BP. J. Civ. Eng. Manag., 2022, 39(2):7-18

[54] ShangY., KangL.Y., ZhangM.X., et al.. Prediction method of electricity stealing behavior based on multi-dimensional features and BP neural network. Energy Rep., 2022, 8(4):523-531

[55] CaoH.J., LiuL., WuB., et al.. Process optimization of high-speed dry milling UD-CF/PEEK laminates using GA-BP neural network. Composites, Part B, Eng., 2021, 221: 1359-8368

[56] BaiB., ZhangJ.Y., WuX., et al.. Reliability prediction-based improved dynamic weight particle swarm optimization and back propagation neural network in engineering systems. Expert Syst. Appl., 2021, 177

[57] WangB., JiangP., GuoB.. Reliability evaluation of aerospace valves based on multi-source information fusion. Acta Armament., 2022, 43(1):199-206

[58] LiuT., YinS.. An improved particle swarm optimization algorithm used for BP neural network and multimedia course-ware evaluation. Multimed. Tools Appl., 2017, 76(9):11961-11974

Funding

National Natural Science Foundation of China(No.51905392); China Scholarship Council(No. 202008420116)