{"title":"Multivariable Control of Wastewater Treatment Process Based on Multi-Agent Deep Reinforcement Learning","authors":"Shengli Du, Rui Sun, Peixi Chen","doi":"10.1049/cth2.70021","DOIUrl":"https://doi.org/10.1049/cth2.70021","url":null,"abstract":"<p>This paper investigates the multivariable control of wastewater treatment processes (WWTP). This paper integrates deep reinforcement learning (DRL) with PID control and proposes a multivariable adaptive PID control strategy based on multi-agent DRL (MADRL) for WWTP. The approach begins with the construction of a MADRL-PID controller structure, consisting of an agent and a PID controller module. The agent adjusts the PID controller values while the PID module calculates the control signal. To enhance the agent's ability to cooperatively tune multiple PID controllers, the algorithm's components–reward function, action space, environment, and state space–are designed according to the BSM1 simulation platform principles and the MADRL framework requirements. Additionally, to handle WWTP's non-linearities, uncertainties, and parameter coupling, the multi-agent deep deterministic policy gradient algorithm is selected as the foundation for training the agents. Experimental results demonstrate that the proposed algorithm exhibits greater adaptability than traditional PID control and achieves superior control performance.</p>","PeriodicalId":50382,"journal":{"name":"IET Control Theory and Applications","volume":"19 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cth2.70021","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852838","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Data-Based \u0000 \u0000 \u0000 H\u0000 ∞\u0000 \u0000 ${H_infty }$\u0000 Optimal Tracking Control of Completely Unknown Linear Systems Under Input Constraints","authors":"Peyman Ahmadi, Aref Shahmansoorian, Mehdi Rahmani","doi":"10.1049/cth2.70022","DOIUrl":"https://doi.org/10.1049/cth2.70022","url":null,"abstract":"<p>This paper presents an <span></span><math>\u0000 <semantics>\u0000 <msub>\u0000 <mi>H</mi>\u0000 <mi>∞</mi>\u0000 </msub>\u0000 <annotation>${H_infty }$</annotation>\u0000 </semantics></math> optimal tracking control approach for linear systems with unknown models and input constraints. The proposed method is based on data-based adaptive dynamic programming (ADP) that is computationally tractable and does not require model approximation. This study consists of two new algorithms: a model-based constrained control algorithm and a data-based algorithm for systems with completely unknown models. A lower bound for the <span></span><math>\u0000 <semantics>\u0000 <msub>\u0000 <mi>H</mi>\u0000 <mi>∞</mi>\u0000 </msub>\u0000 <annotation>${H_infty }$</annotation>\u0000 </semantics></math> attenuation coefficient is determined to ensure optimality. Additionally, the approach allows for constraints on the amplitude and frequency of the control signal, which are incorporated using the idea of inverse optimal control (IOC). The effectiveness of the proposed method is demonstrated through a simulation example, showcasing its ability to achieve robust tracking performance and satisfy input constraints.</p>","PeriodicalId":50382,"journal":{"name":"IET Control Theory and Applications","volume":"19 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2025-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cth2.70022","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}