Indexed by:期刊论文

First Author:Zhang, Xiaoping

Correspondence Author:Zhao, J (reprint author), Dalian Univ Technol, Res Ctr Informat & Control, Dalian, Peoples R China.

Co-author:Zhao, Jun,Wang, Wei,Cong, Liqun,Feng, Weimin

Date of Publication:2011-04-01

Journal:EXPERT SYSTEMS WITH APPLICATIONS

Included Journals:SCIE、EI

Document Type:J

Volume:38

Issue:4

Page Number:4588-4599

ISSN No.:0957-4174

Key Words:Optimal scheduling of byproduct gases; Gasholder level prediction; Machine learning; Intelligent optimization algorithm

Abstract:To maintain the balance of byproduct gas holder is an important task in optimal scheduling of byproduct energy in steel industry. However, this is often influenced by many factors and is difficult to obtain a precise mechanism model for analysis. In this paper, an optimal method for prediction and adjustment on byproduct gas holder is proposed. Considering the different operation styles of gasholders, both single and multiple gasholders level prediction models are established by machine learning methodology. And, a hybrid parameter optimization algorithm is developed to optimize the model for high prediction accuracy. Then, based on the predicted gasholder level, the optimal adjustment amount is calculated by a novel reasoning method to sustain the gasholder within safety zone. This method has been verified in the Energy Center of Baosteel, China. The results demonstrate that the proposed approach can precisely predict and adjust gasholders and provide a remarkable guidance for reasonable scheduling of byproduct gases. (C) 2010 Elsevier Ltd. All rights reserved.

Translation or Not:no