Tarwaji Warsokusumo, T. Prahasto, W. Caesarendra, A. Widodo
{"title":"基于数据驱动的相关向量机回归算法优化电厂运行参数以提高效率","authors":"Tarwaji Warsokusumo, T. Prahasto, W. Caesarendra, A. Widodo","doi":"10.1109/INCAE.2018.8579156","DOIUrl":null,"url":null,"abstract":"In this paper, we will discuss about power generation efficiency improvement program (EIP) for saving fuel cost of electrical energy production. EIP will be focused on the embedding and enhancing operation culture by setting the operation parameters quality control chart as guidance for the power plant frontline operation. The data sources are limited to the controllable operation parameters acquired by Distributed Control System (DCS). New methodology that is algorithm as one of artificial intelligence tools will be proposed to be applied on the EIP. The new methodology consists of 5 steps: 1) collect operation parameter data acquisition, 2) select main operating indicator, 3) develop relevance vector machine (RVM) regression algorithm used for regression process, 4) define operation parameter quality control chart, 5) frontline operation optimization process. The operation parameter quality control chart is derived from statistical data acquired with the RVM regression algorithm. The mean regression curve achieved is proposed as a reference for maximum tolerable limit of operation parameter range and from the practical reference the efficient operation limit curve was set at 5% below it. The results show that RVM technique capable to produce an operation parameter regression curves from the sparse prior operation parameter data. This quality control chart can be applied as a helpful guidance for frontline operation in purpose for leading the change the operator behavior to become a new efficient mindset culture. Originality of the proposed methodology in this paper is the operation parameter quality control chart which derived by application of RVM regression algorithm.","PeriodicalId":387859,"journal":{"name":"2018 International Conference on Applied Engineering (ICAE)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Optimization of Power Plant Operation Parameters for Efficiency Improvement through Data-Driven Relevance Vector Machine Regression Algorithm\",\"authors\":\"Tarwaji Warsokusumo, T. Prahasto, W. Caesarendra, A. Widodo\",\"doi\":\"10.1109/INCAE.2018.8579156\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we will discuss about power generation efficiency improvement program (EIP) for saving fuel cost of electrical energy production. EIP will be focused on the embedding and enhancing operation culture by setting the operation parameters quality control chart as guidance for the power plant frontline operation. The data sources are limited to the controllable operation parameters acquired by Distributed Control System (DCS). New methodology that is algorithm as one of artificial intelligence tools will be proposed to be applied on the EIP. The new methodology consists of 5 steps: 1) collect operation parameter data acquisition, 2) select main operating indicator, 3) develop relevance vector machine (RVM) regression algorithm used for regression process, 4) define operation parameter quality control chart, 5) frontline operation optimization process. The operation parameter quality control chart is derived from statistical data acquired with the RVM regression algorithm. The mean regression curve achieved is proposed as a reference for maximum tolerable limit of operation parameter range and from the practical reference the efficient operation limit curve was set at 5% below it. The results show that RVM technique capable to produce an operation parameter regression curves from the sparse prior operation parameter data. This quality control chart can be applied as a helpful guidance for frontline operation in purpose for leading the change the operator behavior to become a new efficient mindset culture. Originality of the proposed methodology in this paper is the operation parameter quality control chart which derived by application of RVM regression algorithm.\",\"PeriodicalId\":387859,\"journal\":{\"name\":\"2018 International Conference on Applied Engineering (ICAE)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 International Conference on Applied Engineering (ICAE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/INCAE.2018.8579156\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 International Conference on Applied Engineering (ICAE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/INCAE.2018.8579156","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Optimization of Power Plant Operation Parameters for Efficiency Improvement through Data-Driven Relevance Vector Machine Regression Algorithm
In this paper, we will discuss about power generation efficiency improvement program (EIP) for saving fuel cost of electrical energy production. EIP will be focused on the embedding and enhancing operation culture by setting the operation parameters quality control chart as guidance for the power plant frontline operation. The data sources are limited to the controllable operation parameters acquired by Distributed Control System (DCS). New methodology that is algorithm as one of artificial intelligence tools will be proposed to be applied on the EIP. The new methodology consists of 5 steps: 1) collect operation parameter data acquisition, 2) select main operating indicator, 3) develop relevance vector machine (RVM) regression algorithm used for regression process, 4) define operation parameter quality control chart, 5) frontline operation optimization process. The operation parameter quality control chart is derived from statistical data acquired with the RVM regression algorithm. The mean regression curve achieved is proposed as a reference for maximum tolerable limit of operation parameter range and from the practical reference the efficient operation limit curve was set at 5% below it. The results show that RVM technique capable to produce an operation parameter regression curves from the sparse prior operation parameter data. This quality control chart can be applied as a helpful guidance for frontline operation in purpose for leading the change the operator behavior to become a new efficient mindset culture. Originality of the proposed methodology in this paper is the operation parameter quality control chart which derived by application of RVM regression algorithm.