{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T22:44:10Z","timestamp":1780353850535,"version":"3.54.1"},"reference-count":32,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2015,3,23]],"date-time":"2015-03-23T00:00:00Z","timestamp":1427068800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Tracking degradation of mechanical components is very critical for effective maintenance decision making. Remaining useful life (RUL) estimation is a widely used form of degradation prediction. RUL prediction methods when enough run-to-failure condition monitoring data can be used have been fully researched, but for some high reliability components, it is very difficult to collect run-to-failure condition monitoring data, i.e., from normal to failure. Only a certain number of condition indicators in certain period can be used to estimate RUL. In addition, some existing prediction methods have problems which block RUL estimation due to poor extrapolability. The predicted value converges to a certain constant or fluctuates in certain range. Moreover, the fluctuant condition features also have bad effects on prediction. In order to solve these dilemmas, this paper proposes a RUL prediction model based on neural network with dynamic windows. This model mainly consists of three steps: window size determination by increasing rate, change point detection and rolling prediction. The proposed method has two dominant strengths. One is that the proposed approach does not need to assume the degradation trajectory is subject to a certain distribution. The other is it can adapt to variation of degradation indicators which greatly benefits RUL prediction. Finally, the performance of the proposed RUL prediction model is validated by real field data and simulation data.<\/jats:p>","DOI":"10.3390\/s150306996","type":"journal-article","created":{"date-parts":[[2015,3,23]],"date-time":"2015-03-23T12:17:00Z","timestamp":1427113020000},"page":"6996-7015","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Degradation Prediction Model Based on a Neural Network with Dynamic Windows"],"prefix":"10.3390","volume":"15","author":[{"given":"Xinghui","family":"Zhang","sequence":"first","affiliation":[{"name":"Mechanical Engineering College, Shijiazhuang 050003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Xiao","sequence":"additional","affiliation":[{"name":"The State Key Lab of Mechanical Transmission, Chongqing University, Chongqing 400030, China"},{"name":"Department of Industrial and Systems Engineering, Rutgers University, Piscataway, NJ 08854, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianshe","family":"Kang","sequence":"additional","affiliation":[{"name":"Mechanical Engineering College, Shijiazhuang 050003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2015,3,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1502","DOI":"10.1016\/j.renene.2010.10.028","article-title":"Condition based maintenance optimization for wind power generation systems under continuous monitoring","volume":"36","author":"Tian","year":"2011","journal-title":"Renew. Energy"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1542","DOI":"10.1016\/j.ymssp.2009.11.005","article-title":"A neural network approach for remaining useful life prediction utilizing both failure and suspension histories","volume":"24","author":"Tian","year":"2010","journal-title":"Mech. Syst. Signal Pr."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1007\/s10845-009-0356-9","article-title":"An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring","volume":"23","author":"Tian","year":"2012","journal-title":"J. Intell. Manuf."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1016\/j.ymssp.2013.08.025","article-title":"An intelligent approach to machine component health prognostics by utilizing only truncated histories","volume":"42","author":"Lu","year":"2014","journal-title":"Mech. Syst. Signal Pr."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1016\/j.ymssp.2010.08.012","article-title":"Latent degradation indicators estimation and prediction: A Monte Carlo approach","volume":"25","author":"Zhou","year":"2011","journal-title":"Mech. Syst. Signal Pr."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1109\/TR.2014.2315956","article-title":"Degradation modeling and maintenance decision based on Bayesian Belief Network","volume":"63","author":"Zhang","year":"2014","journal-title":"IEEE Trans. Reliab."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2248","DOI":"10.1016\/j.ymssp.2006.10.001","article-title":"A segmental hidden semi-Markov model (HSMM)-based diagnostics and prognostics framework and methodology","volume":"21","author":"Dong","year":"2007","journal-title":"Mech. Syst. Signal Pr."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"858","DOI":"10.1016\/j.ejor.2006.01.041","article-title":"Hidden semi-Markov model-based methodology for multi-sensor equipment health diagnosis and prognosis","volume":"178","author":"Dong","year":"2007","journal-title":"Eur. J. Oper. Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"9046","DOI":"10.1016\/j.eswa.2008.12.017","article-title":"PM2.5 concentration prediction using hidden semi-Markov model-based times series data","volume":"36","author":"Dong","year":"2009","journal-title":"Expert Syst. Appl."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/j.ymssp.2012.05.004","article-title":"A novel method for online health prognosis of equipment based on hidden semi-Markov model using sequential Monte Carlo methods","volume":"32","author":"Liu","year":"2012","journal-title":"Mech. Syst. Signal Pr."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.ress.2013.11.006","article-title":"An integrated framework for online diagnostic and prognostic health monitoring using a multistate deterioration process","volume":"124","author":"Moghaddass","year":"2014","journal-title":"Reliab. Eng. Syst. Safe."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.ymssp.2012.08.016","article-title":"A Wiener-process-based degradation model with a recursive filter algorithm for remaining useful life estimation","volume":"35","author":"Si","year":"2013","journal-title":"Mech. Syst. Signal Pr."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1109\/TR.2014.2299155","article-title":"An additive Wiener process-based prognostic model for hybrid deteriorating systems","volume":"63","author":"Wang","year":"2014","journal-title":"IEEE Trans. Reliab."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.ress.2013.11.011","article-title":"Residual life estimation based on a generalized Wiener degradation process","volume":"124","author":"Wang","year":"2014","journal-title":"Reliab. Eng. Syst. Safe."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.ress.2012.11.022","article-title":"Remaining useful life estimation based on stochastic deterioration models: A comparative study","volume":"112","author":"Son","year":"2013","journal-title":"Reliab. Eng. Syst. Safe."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Si, X.S. (2015). An adaptive prognostic approach via nonlinear degradation modelling: Application to battery data. IEEE Trans. Ind. Electron.","DOI":"10.1109\/TIE.2015.2393840"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1080\/00401706.2013.869261","article-title":"Semiparametric estimation of Gamma processes for deteriorating products","volume":"56","author":"Ye","year":"2014","journal-title":"Technometrics"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1080\/00401706.2013.830074","article-title":"The inverse Gaussian process as a degradation model","volume":"56","author":"Ye","year":"2014","journal-title":"Technometrics"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.ress.2014.06.005","article-title":"Inverse Gaussian process models for degradation analysis: A Bayesian perspective","volume":"130","author":"Peng","year":"2014","journal-title":"Reliab. Eng. Syst. Safe."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ye, Z.S., and Xie, M. (2014). Stochastic modelling and analysis of degradation for highly reliable products. Appl. Stoch. Model Bus. Ind.","DOI":"10.1002\/asmb.2063"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.1016\/j.ymssp.2007.11.012","article-title":"Machine condition prognosis based on regression trees and one-step-ahead prediction","volume":"22","author":"Tran","year":"2008","journal-title":"Mech. Syst. Signal Pr."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1109\/TR.2010.2083231","article-title":"Health condition prediction of gears using a recurrent neural network approach","volume":"59","author":"Tian","year":"2010","journal-title":"IEEE Trans. Reliab."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"9378","DOI":"10.1016\/j.eswa.2009.01.007","article-title":"Multi-step ahead direct prediction for the machine condition prognosis using regression trees and neuro-fuzzy systems","volume":"36","author":"Tran","year":"2009","journal-title":"Expert. Syst. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1016\/j.ymssp.2011.10.009","article-title":"Machine remaining useful life prediction: An integrated adaptive neuro-fuzzy and high-order particle filtering approach","volume":"28","author":"Chen","year":"2012","journal-title":"Mech. Syst. Signal Pr."},{"key":"ref_25","unstructured":"He, D., Bechhoefer, E., Ma, J., and Li, R. (2011, January 25\u201329). Particle filtering based gear prognostics using one-dimensional health index. Proceedings of the 2011 Annual Conference of the Prognostics and Health Management Society, Montreal, QC, Canada."},{"key":"ref_26","unstructured":"Ma, J., and He, D. (2011, January 10\u201313). An integrated approach for hybrid ceramic bearing life prognostics. Proceedings of the 2011 Conference of the Society for Machinery Failure Prevention Technology, Virginia Beach, VA, USA."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1007\/s11668-014-9902-7","article-title":"Development of an efficient prognostic estimator","volume":"15","author":"Yoon","year":"2015","journal-title":"J. Fail. Anal. Prev."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/j.ymssp.2012.03.011","article-title":"Combining relevance vector machines and exponential regression for bearing residual life estimation","volume":"31","author":"Maio","year":"2012","journal-title":"Mech. Syst. Signal Pr."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1151","DOI":"10.1002\/qre.1466","article-title":"Condition-based maintenance optimization using neural network-based health condition prediction","volume":"29","author":"Wu","year":"2013","journal-title":"Qual. Reliab. Eng. Int."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1080\/07408170590929018","article-title":"Residual-life distribution from component degradation signals: A Bayesian approach","volume":"37","author":"Gebraeel","year":"2005","journal-title":"IIE. Trans."},{"key":"ref_31","first-page":"295","article-title":"A new feature extraction method for gear fault diagnosis and prognosis","volume":"16","author":"Zhang","year":"2014","journal-title":"Eksploat. Niezawodn."},{"key":"ref_32","unstructured":"Bechhoefer, E., Bernhard, A., He, D., and Banerjee, P. (2006, January 9\u201311). Use of Semi Hidden Markov Models in the prognostics of shaft failure. Proceedings of the American Helicopter Society 62nd Annual Forum, Phoenix, AZ, USA."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/15\/3\/6996\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T20:43:48Z","timestamp":1760215428000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/15\/3\/6996"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,3,23]]},"references-count":32,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2015,3]]}},"alternative-id":["s150306996"],"URL":"https:\/\/doi.org\/10.3390\/s150306996","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,3,23]]}}}