{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T14:35:29Z","timestamp":1778250929429,"version":"3.51.4"},"reference-count":32,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:00:00Z","timestamp":1767312000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:00:00Z","timestamp":1767312000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Quality &amp;amp; Reliability Eng"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    Ensuring regular equipment maintenance is critical for any business that relies on machinery. Predictive maintenance (PdM) is a strategy for scheduling maintenance tasks, with a primary focus on predicting the remaining useful life (RUL) of equipment in advance. This approach helps optimize maintenance schedules, reduce downtime, and detect unexpected faults. Predictions are based on analyzing data collected from the equipment, with machine learning (ML) facilitating these forecasts by training models on historical input data and corresponding outputs. The trained model can then estimate the RUL of the equipment before it reaches the end of its operational capacity. Various ML techniques have been employed for the accurate estimation of the RUL. In this paper, we aim to identify the most effective ML regression methods for PdM and RUL prediction for an auxiliary power unit (APU), focusing on performance indicators such as the root mean squared error (RMSE), the mean absolute error (MAE), and the correlation coefficient (\n                    <jats:italic>R<\/jats:italic>\n                    ). The process begins with a dataset, followed by feature selection methods such as random forests and normalization during the preprocessing stage. Then, the ML models are trained and evaluated. To assess the effectiveness of the proposed approach, data from the NASA Ames Research Center, along with on\u2010wing sensor data from the Shenyang Maintenance Base of China Southern Airlines (SYMOB), are used. Six ML algorithms and a hybrid model are employed: Support Vector Machines (SVM), long short\u2010term memory (LSTM), gated recurrent unit (GRU), decision tree (DT), K\u2010nearest neighbors (KNNs), gradient boosting trees (GBTs), and a hybrid model (GBT\u00a0+\u00a0LSTM). The results for the regression techniques, based on the RMSE and R, are as follows: SVM (37.62, 0.84), LSTM (20.22, 0.91), GRU (31.29, 0.87), DT (17.89, 0.94), KNN (10.98, 0.98), GBT (22.62, 0.97), and (GBT\u00a0+\u00a0LSTM) (24.32, 0.96). The KNN method is the most effective approach for this study, as it demonstrates the lowest RMSE and the highest correlation coefficient (\n                    <jats:italic>R<\/jats:italic>\n                    ) compared to other methods. Therefore, we highly recommend utilizing the KNN technique for PdM analysis of APUs.\n                  <\/jats:p>","DOI":"10.1002\/qre.70140","type":"journal-article","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T16:35:09Z","timestamp":1767371709000},"page":"1369-1379","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Remaining Useful Life Prediction for Aircraft Maintenance Using Machine Learning"],"prefix":"10.1002","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6242-2994","authenticated-orcid":false,"given":"Sana","family":"Abbes","sequence":"first","affiliation":[{"name":"National School of Engineering University of Sfax  Sfax Tunisia"},{"name":"LA2MP Laboratory University of Sfax  Sfax Tunisia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hichem","family":"Hassine","sequence":"additional","affiliation":[{"name":"LA2MP Laboratory University of Sfax  Sfax Tunisia"},{"name":"Higher Institute of Transport and Logistics University of Sousse  Sousse Tunisia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Said","family":"Amari","sequence":"additional","affiliation":[{"name":"LURPA, ENS Paris Saclay LIPN University of Sorbonne Paris Nord  Villetaneuse France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Riadh","family":"Chaari","sequence":"additional","affiliation":[{"name":"LA2MP Laboratory University of Sfax  Sfax Tunisia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Haddar","sequence":"additional","affiliation":[{"name":"National School of Engineering University of Sfax  Sfax Tunisia"},{"name":"LA2MP Laboratory University of Sfax  Sfax Tunisia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2014.02.006"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2009.07.001"},{"key":"e_1_2_8_4_1","doi-asserted-by":"crossref","unstructured":"D.BruneoandF.De Vita \u201cOn the Use of LSTM Networks for Predictive Maintenance in Smart Industries \u201d inProceedings of the IEEE International Conference on Smart Computing (SMARTCOMP)(2019) 241\u2013248 https:\/\/doi.org\/10.1109\/SMARTCOMP.2019.00059.","DOI":"10.1109\/SMARTCOMP.2019.00059"},{"key":"e_1_2_8_5_1","doi-asserted-by":"crossref","unstructured":"M.Yuan Y.Wu andL.Lin \u201cFault Diagnosis and Remaining Useful Life Estimation of Aero Engine Using LSTM Neural Network \u201d inProceedings of the IEEE\/CSAA International Conference on Aircraft Utility Systems (AUS)(2016) 135\u2013140.","DOI":"10.1109\/AUS.2016.7748035"},{"key":"e_1_2_8_6_1","doi-asserted-by":"crossref","unstructured":"S.Zheng K.Ristovski A.Farahat andC.Gupta \u201cLong Short\u2010Term Memory Network for Remaining Useful Life Estimation \u201d inProceedings of the IEEE International Conference on Prognostics and Health Management (ICPHM)(2017) 88\u201395.","DOI":"10.1109\/ICPHM.2017.7998311"},{"key":"e_1_2_8_7_1","doi-asserted-by":"crossref","unstructured":"D.Azevedo B.Ribeiro andA.Cardoso \u201cWeb\u2010Based Tool for Predicting the Remaining Useful Lifetime of Aircraft Components \u201d inProceedings of the 5th Experiment International Conference(IEEE 2019) 231\u2013232 https:\/\/doi.org\/10.1109\/EXPAT.2019.8876503.","DOI":"10.1109\/EXPAT.2019.8876503"},{"key":"e_1_2_8_8_1","doi-asserted-by":"crossref","unstructured":"T.Wang J.Yu D.Siegel andJ.Lee \u201cA Similarity\u2010Based Prognostics Approach for Remaining Useful Life Estimation of Engineered Systems \u201d inProceedings of the International Conference on Prognostics and Health Management(IEEE 2008) 1\u20136 https:\/\/doi.org\/10.1109\/PHM.2008.4711421.","DOI":"10.1109\/PHM.2008.4711421"},{"key":"e_1_2_8_9_1","unstructured":"P.Adhikari H. G.Rao andD. I. M.Buderath \u201cMachine Learning\u2010Based Data\u2010Driven Diagnostics & Prognostics Framework for Aircraft Predictive Maintenance \u201d inProceedings of the 10th International Symposium on NDT in Aerospace(ICTON 2018) 1\u201315."},{"key":"e_1_2_8_10_1","doi-asserted-by":"crossref","unstructured":"D.Kusumaningrum K.Nani andB.Santosa \u201cMachine Learning for Predictive Maintenance \u201d inProceedings of the International Conference on Industrial Engineering and Operations Management(IEOM Society Int 2021) 2348\u20132356.","DOI":"10.46254\/SA02.20210717"},{"key":"e_1_2_8_11_1","doi-asserted-by":"crossref","unstructured":"K.Panagiotis S.Besseau andM.Vazirgiannis \u201cPredictive Maintenance in Aviation: Failure Prediction From Post\u2010Flight Reports \u201d inProceedings of the IEEE 34th International Conference on Data Engineering (ICDE)(2018) 1414\u20131422.","DOI":"10.1109\/ICDE.2018.00160"},{"key":"e_1_2_8_12_1","doi-asserted-by":"crossref","unstructured":"S.Behera A.Choubey C. S.Kanani Y. S.Patel R.Misra andA.Sillitti \u201cEnsemble Trees Learning\u2010Based Improved Predictive Maintenance Using IIoT for Turbofan Engines \u201d inProceedings of the 34th ACM\/SIGAPP Symposium on Applied Computing(2019) 842\u2013850 https:\/\/doi.org\/10.1145\/3297280.3297363.","DOI":"10.1145\/3297280.3297363"},{"key":"e_1_2_8_13_1","doi-asserted-by":"crossref","unstructured":"A. P.Hermawan D.\u2010S.Kim andM.\u2010J.Lee \u201cPredictive Maintenance of Aircraft Engine Using Deep Learning Technique \u201d inProceedings of the International Conference on Information and Communication Technology Convergence (ICTC)(2020) 1296\u20131298.","DOI":"10.1109\/ICTC49870.2020.9289466"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.36001\/phmconf.2010.v2i1.1896"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.02.045"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.05.063"},{"key":"e_1_2_8_17_1","doi-asserted-by":"crossref","unstructured":"Y.Zhang C.Su andJ.Wu \u201cRemaining Useful Life Prediction via K\u2010Means Clustering Analysis and Deep Convolutional Neural Network \u201d inProceedings of the Asia Conference on Machine Learning Algorithms and Neural Networks(2023) https:\/\/doi.org\/10.1145\/3596286.3596297.","DOI":"10.1145\/3596286.3596297"},{"key":"e_1_2_8_18_1","doi-asserted-by":"crossref","unstructured":"V.Mathew T.Toby V.Singh B. M.Rao andM. G.Kumar \u201cPrediction of Remaining Useful Lifetime (RUL) of Turbofan Engine Using Machine Learning \u201d inProceedings of the IEEE International Conference on Circuits and Systems(IEEE 2017) 306\u2013311 https:\/\/doi.org\/10.1109\/ICCS1.2017.8326010.","DOI":"10.1109\/ICCS1.2017.8326010"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.2979797"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1177\/0957650919883718"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227\u2010022\u201004730\u2010x"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2019.10.001"},{"key":"e_1_2_8_23_1","doi-asserted-by":"crossref","unstructured":"A.Saxena K.Goebel D.Simon andN.Eklund \u201cDamage Propagation Modeling for Aircraft Engine Run\u2010to\u2010Failure Simulation \u201d inProceedings of the International Conference on Prognostics and Health Management(2008) 1\u20139.","DOI":"10.1109\/PHM.2008.4711414"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2017.11.016"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2019.106024"},{"key":"e_1_2_8_26_1","doi-asserted-by":"crossref","unstructured":"T.Sexton M. P.Brundage M.Hoffman andK. C.Morris \u201cHybrid Datafication of Maintenance Logs From AI\u2010Assisted Human Tags \u201d inProceedings of the IEEE International Conference on Big Data(IEEE;2017) 1769\u20131777.","DOI":"10.1109\/BigData.2017.8258120"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet\u2010epa.2015.0469"},{"key":"e_1_2_8_28_1","doi-asserted-by":"crossref","unstructured":"L.Breiman \u201cRandom Forests \u201d Working Paper (CISL 2001) 1\u201319.","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCPMT.2016.2589206"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2738069"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2010.2078296"},{"key":"e_1_2_8_32_1","unstructured":"J.Chung C.Gulcehre K.Cho andY.Bengio \u201cEmpirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling \u201d inProceedings of the NIPS 2014 Deep Learning and Representation Learning Workshop(2014) https:\/\/doi.org\/10.48550\/arXiv.1412.3555."},{"key":"e_1_2_8_33_1","volume-title":"User's Guide for the Commercial Modular Aero\u2010Propulsion System Simulation (C\u2010MAPSS)","author":"Frederick D. K.","year":"2007"}],"container-title":["Quality and Reliability Engineering International"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/qre.70140","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/qre.70140","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/qre.70140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T18:39:21Z","timestamp":1774377561000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/qre.70140"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,2]]},"references-count":32,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1002\/qre.70140"],"URL":"https:\/\/doi.org\/10.1002\/qre.70140","archive":["Portico"],"relation":{},"ISSN":["0748-8017","1099-1638"],"issn-type":[{"value":"0748-8017","type":"print"},{"value":"1099-1638","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,2]]},"assertion":[{"value":"2025-06-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}