Double-Layer Fuzzy Neural Network Based Optimal Control for Wastewater Treatment Process

IF 10.7 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

IEEE Transactions on Fuzzy Systems Pub Date : 2025-03-12 DOI:10.1109/TFUZZ.2025.3550810

Junfei Qiao;Dingyuan Chen;Cuili Yang;Dapeng Li

{"title":"Double-Layer Fuzzy Neural Network Based Optimal Control for Wastewater Treatment Process","authors":"Junfei Qiao;Dingyuan Chen;Cuili Yang;Dapeng Li","doi":"10.1109/TFUZZ.2025.3550810","DOIUrl":null,"url":null,"abstract":"To obtain the effective purification performance in wastewater treatment process (WWTP), the optimal control is an important method to guarantee the effluent quality reaching the standard and improve the treatment efficiency. The concentrations of dissolved oxygen (DO) and nitrate nitrogen (NO<inline-formula><tex-math>$_{\\text{3}}$</tex-math></inline-formula>-N) are primary metrics that impact effluent quality, which is needed to be stably tracking controlled for achieving optimal performance in WWTP. Therefore, the double-layer fuzzy neural network (FNN)-based optimal control method with multivariable is proposed. First, considering the dynamic characteristic of WWTP, the FNN-based actor network is exploited to approximate the unknown dynamic information. Subsequently, the FNN-based critic network is integrated to minimize the cost function of DO and NO<inline-formula><tex-math>$_{\\text{3}}$</tex-math></inline-formula>-N concentrations, which is composed of the control error and the control variable. Then, to guarantee the stability of the optimal controller, the Lyapunov function is constructed through backstepping method to analyze the control system performance. Finally, the optimality and effectiveness of the control system with multivariable are verified via the simulation experiments in benchmark simulation model 1.","PeriodicalId":13212,"journal":{"name":"IEEE Transactions on Fuzzy Systems","volume":"33 7","pages":"2062-2073"},"PeriodicalIF":10.7000,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Fuzzy Systems","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10923747/","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

To obtain the effective purification performance in wastewater treatment process (WWTP), the optimal control is an important method to guarantee the effluent quality reaching the standard and improve the treatment efficiency. The concentrations of dissolved oxygen (DO) and nitrate nitrogen (NO

$_{\text{3}}$

-N) are primary metrics that impact effluent quality, which is needed to be stably tracking controlled for achieving optimal performance in WWTP. Therefore, the double-layer fuzzy neural network (FNN)-based optimal control method with multivariable is proposed. First, considering the dynamic characteristic of WWTP, the FNN-based actor network is exploited to approximate the unknown dynamic information. Subsequently, the FNN-based critic network is integrated to minimize the cost function of DO and NO

$_{\text{3}}$

-N concentrations, which is composed of the control error and the control variable. Then, to guarantee the stability of the optimal controller, the Lyapunov function is constructed through backstepping method to analyze the control system performance. Finally, the optimality and effectiveness of the control system with multivariable are verified via the simulation experiments in benchmark simulation model 1.

查看原文本刊更多论文

基于双层模糊神经网络的污水处理过程最优控制

为了在污水处理过程中获得有效的净化性能，最优控制是保证出水水质达标、提高处理效率的重要手段。溶解氧（DO）和硝酸盐氮（NO$_{\text{3}}$-N）浓度是影响污水水质的主要指标，需要对其进行稳定的跟踪控制，以实现污水处理厂的最佳性能。为此，提出了基于双层模糊神经网络（FNN）的多变量最优控制方法。首先，考虑污水处理厂的动态特性，利用基于fnn的行动者网络来逼近未知的动态信息。随后，集成基于fnn的评价网络，最小化DO和NO$_{\text{3}}$-N浓度的代价函数，该函数由控制误差和控制变量组成。然后，为了保证最优控制器的稳定性，通过反推法构造Lyapunov函数来分析控制系统的性能。最后，通过基准仿真模型1中的仿真实验，验证了多变量控制系统的最优性和有效性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Transactions on Fuzzy Systems 工程技术-工程：电子与电气

CiteScore

20.50

自引率

13.40%

发文量

517

审稿时长

3.0 months

期刊介绍： The IEEE Transactions on Fuzzy Systems is a scholarly journal that focuses on the theory, design, and application of fuzzy systems. It aims to publish high-quality technical papers that contribute significant technical knowledge and exploratory developments in the field of fuzzy systems. The journal particularly emphasizes engineering systems and scientific applications. In addition to research articles, the Transactions also includes a letters section featuring current information, comments, and rebuttals related to published papers.