{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T05:48:11Z","timestamp":1761976091739},"reference-count":23,"publisher":"EDP Sciences","issue":"5","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"vor","delay-in-days":43,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["RAIRO-Oper. Res."],"accepted":{"date-parts":[[2024,8,15]]},"published-print":{"date-parts":[[2024,9]]},"abstract":"<jats:p>Accurate spare part demand forecasting for the key components of ships is one of the key factors to ensure normal ship operation. Large errors in demand forecasting not only bring challenges to the normal operation of ships but also cause an inventory backlog of key components and thus increase the operation and maintenance costs. A three-level spare parts combination prediction method based on historical data has been proposed, aiming to solve the problem of insufficient data in existing prediction methods. First, three types of individual direct forecasting models are used for predictions. Secondly, we used convolutional neural networks to perform convolutional operations on the prediction results, and then constructed a three-layer combined prediction model using backpropagation neural networks (BP). Experimental results have shown that the predictive performance of this model is significantly better than that of single-layer models. This study used spare parts data from shipping companies to predict the three-layer combination model, and the results fully demonstrated its significant advantages over single-layer models.<\/jats:p>","DOI":"10.1051\/ro\/2024159","type":"journal-article","created":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T18:56:23Z","timestamp":1723834583000},"page":"4181-4195","source":"Crossref","is-referenced-by-count":2,"title":["A convolutional neural network\u2013back propagation based three-layer combined forecasting method for spare part demand"],"prefix":"10.1051","volume":"58","author":[{"given":"Guoxing","family":"Huang","sequence":"first","affiliation":[]},{"given":"Yukang","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Weichang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xianhuai","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Zhipeng","family":"Yang","sequence":"additional","affiliation":[]}],"member":"250","published-online":{"date-parts":[[2024,10,14]]},"reference":[{"key":"R1","doi-asserted-by":"crossref","first-page":"100814","DOI":"10.1016\/j.iot.2023.100814","volume":"22","author":"Alhilali","year":"2023","journal-title":"Internet Things"},{"key":"R2","doi-asserted-by":"crossref","first-page":"6695","DOI":"10.1016\/j.eswa.2010.04.037","volume":"37","author":"Chen","year":"2010","journal-title":"Expert Syst. Appl. Int. J."},{"key":"R3","doi-asserted-by":"crossref","first-page":"289","DOI":"10.2307\/3007885","volume":"23","author":"Croston","year":"1972","journal-title":"Oper. Res. Q. (1970\u20131977)"},{"key":"R4","doi-asserted-by":"crossref","first-page":"109211","DOI":"10.1016\/j.cie.2023.109211","volume":"179","author":"Goli","year":"2023","journal-title":"Comput. Ind. Eng."},{"key":"R5","doi-asserted-by":"crossref","first-page":"106244","DOI":"10.1016\/j.cor.2023.106244","volume":"155","author":"Goli","year":"2023","journal-title":"Comput. Oper. Res."},{"key":"R6","doi-asserted-by":"crossref","first-page":"119077","DOI":"10.1016\/j.eswa.2022.119077","volume":"213","author":"Goli","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"R7","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1007\/s10479-022-04829-7","volume":"328","author":"Goli","year":"2023","journal-title":"Ann. Oper. Res."},{"key":"R8","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1016\/j.cie.2006.12.010","volume":"52","author":"Gonzalez-Romera","year":"2007","journal-title":"Comput. Ind. Eng."},{"key":"R9","first-page":"163","volume":"1","author":"Guo","year":"2012","journal-title":"Comput. Modern."},{"key":"R10","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.cie.2017.05.002","volume":"110","author":"Guo","year":"2017","journal-title":"Comput. Ind. Eng."},{"key":"R11","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1016\/j.ijpe.2013.01.009","volume":"143","author":"Kourentzes","year":"2013","journal-title":"Int. J. Prod. Econ."},{"key":"R12","doi-asserted-by":"crossref","first-page":"110489","DOI":"10.1016\/j.knosys.2023.110489","volume":"269","author":"Li","year":"2023","journal-title":"Knowl. Based Syst."},{"key":"R13","doi-asserted-by":"crossref","unstructured":"Montazerolghaem A., Khosravi M., Rezaee F. and Khayyambashi M.R., An optimal workflow scheduling method in cloud-fog computing using three-objective Harris-Hawks algorithm, in 2022 12th International Conference on Computer and Knowledge Engineering (ICCKE). IEEE (2022) 300\u2013306.","DOI":"10.1109\/ICCKE57176.2022.9960123"},{"key":"R14","doi-asserted-by":"crossref","first-page":"276","DOI":"10.14419\/gjma.v2i4.3253","volume":"2","author":"Nazim","year":"2014","journal-title":"Glob. J. Math. Anal."},{"key":"R15","doi-asserted-by":"crossref","first-page":"914","DOI":"10.1057\/jors.2014.62","volume":"66","author":"Petropoulos","year":"2015","journal-title":"J. Oper. Res. Soc."},{"key":"R16","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"R17","doi-asserted-by":"crossref","first-page":"2825","DOI":"10.1007\/s11063-022-10986-4","volume":"55","author":"Sareminia","year":"2023","journal-title":"Neural Process. Lett."},{"key":"R18","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1016\/S0925-5273(00)00143-2","volume":"71","author":"Syntetos","year":"2001","journal-title":"Int. J. Prod. Econ."},{"key":"R19","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/MIS.2004.49","volume":"19","author":"Thadakamaila","year":"2005","journal-title":"IEEE Intell. Syst."},{"key":"R20","doi-asserted-by":"crossref","first-page":"153694","DOI":"10.1109\/ACCESS.2019.2948859","volume":"7","author":"Wang","year":"2019","journal-title":"IEEE Access"},{"key":"R21","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1016\/j.asoc.2016.07.053","volume":"49","author":"Yang","year":"2016","journal-title":"Appl. Soft Comput."},{"key":"R22","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1109\/JSYST.2010.2100192","volume":"5","author":"Zhao","year":"2011","journal-title":"IEEE Syst. J."},{"key":"R23","first-page":"195","volume":"8","author":"Zhou","year":"2016","journal-title":"Int. J. Eng. Syst. Model. Simul."}],"container-title":["RAIRO - Operations Research"],"original-title":[],"link":[{"URL":"https:\/\/www.rairo-ro.org\/10.1051\/ro\/2024159\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T07:51:53Z","timestamp":1728892313000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.rairo-ro.org\/10.1051\/ro\/2024159"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":23,"journal-issue":{"issue":"5"},"alternative-id":["ro240198"],"URL":"https:\/\/doi.org\/10.1051\/ro\/2024159","relation":{},"ISSN":["0399-0559","2804-7303"],"issn-type":[{"type":"print","value":"0399-0559"},{"type":"electronic","value":"2804-7303"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}