Application of fuzzy neural network controller in hydropower generator unit

Author:

Xiao Zhihuai,Guo Jiang,Zeng Hongtao,Zhou Pan,Wang Shuqing

Abstract

PurposeThe purpose of this paper is to develop a new hybridized controller based on fuzzy reasoning and neural network (NN) for hydropower generator unit (HGU).Design/methodology/approachThe approach contains fuzzy neural networks controller (FNNC), RBF network identification (RBFNI) and HGU system. FNNC may give control value to control HGU via fuzzy NN reasoning and computing according to HGU rotate speed error and error varying rate. RBFNI is used to identify the character of HGU system and predict its output. FNNC may adjust parameters and member function according to the identifying and predictive outcome of RBFNI.FindingsSees that the hybridized control system is feasible and stable, and the controlling performance of the hybridized system is superior to conventional fuzzy controller.Research limitations/implicationsThe theoretical proof of stability of the proposed scheme still remains to be studied. Accessibility and availability of membership functions and control rules is also a limitation applied.Practical implicationsThe main advantage of the proposed method is that FNNC has reasoning, learning, and optimizing capability which can control effectively HGU. This will be useful for control engineers to control complex industrial plants.Originality/valueThe paper proposes new combined approach to optimal control of HGU using FNNC, and it is aimed at operational researches and engineers, especially those who dealt with HUG controller.

Publisher

Emerald

Subject

Computer Science (miscellaneous),Social Sciences (miscellaneous),Theoretical Computer Science,Control and Systems Engineering,Engineering (miscellaneous)

Cited by 5 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3