Ehsan Esmailian, Young-Rong Kim, Sverre Steen, Kourosh Koushan
{"title":"一种利用船舶在役数据进行功率预测的新方法——以某普通货船为例","authors":"Ehsan Esmailian, Young-Rong Kim, Sverre Steen, Kourosh Koushan","doi":"10.1080/09377255.2023.2275378","DOIUrl":null,"url":null,"abstract":"To increase energy efficiency and reduce greenhouse gas (GHG) emissions in the shipping industry, an accurate prediction of the ship performance at sea is crucial. This paper proposes a new power prediction method based on minimizing a normalized root mean square error (NRMSE) defined by comparing the results of the power prediction model with the ship in-service data for a given vessel. The result is a power prediction model tuned to fit the ship for which in-service data was applied. A general cargo ship is used as a test case. The performance of the proposed approach is evaluated in different scenarios with the artificial neural network (ANN) method and the traditional power prediction models. In all studied scenarios, the proposed method shows better performance in predicting ship power. Up to 86% percentage difference between the NRMSEs of the best and worst power prediction models is also reported.","PeriodicalId":51883,"journal":{"name":"Ship Technology Research","volume":null,"pages":null},"PeriodicalIF":1.4000,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A new power prediction method using ship in-service data: a case study on a general cargo ship\",\"authors\":\"Ehsan Esmailian, Young-Rong Kim, Sverre Steen, Kourosh Koushan\",\"doi\":\"10.1080/09377255.2023.2275378\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"To increase energy efficiency and reduce greenhouse gas (GHG) emissions in the shipping industry, an accurate prediction of the ship performance at sea is crucial. This paper proposes a new power prediction method based on minimizing a normalized root mean square error (NRMSE) defined by comparing the results of the power prediction model with the ship in-service data for a given vessel. The result is a power prediction model tuned to fit the ship for which in-service data was applied. A general cargo ship is used as a test case. The performance of the proposed approach is evaluated in different scenarios with the artificial neural network (ANN) method and the traditional power prediction models. In all studied scenarios, the proposed method shows better performance in predicting ship power. Up to 86% percentage difference between the NRMSEs of the best and worst power prediction models is also reported.\",\"PeriodicalId\":51883,\"journal\":{\"name\":\"Ship Technology Research\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2023-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Ship Technology Research\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1080/09377255.2023.2275378\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, MARINE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ship Technology Research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/09377255.2023.2275378","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, MARINE","Score":null,"Total":0}
A new power prediction method using ship in-service data: a case study on a general cargo ship
To increase energy efficiency and reduce greenhouse gas (GHG) emissions in the shipping industry, an accurate prediction of the ship performance at sea is crucial. This paper proposes a new power prediction method based on minimizing a normalized root mean square error (NRMSE) defined by comparing the results of the power prediction model with the ship in-service data for a given vessel. The result is a power prediction model tuned to fit the ship for which in-service data was applied. A general cargo ship is used as a test case. The performance of the proposed approach is evaluated in different scenarios with the artificial neural network (ANN) method and the traditional power prediction models. In all studied scenarios, the proposed method shows better performance in predicting ship power. Up to 86% percentage difference between the NRMSEs of the best and worst power prediction models is also reported.