The paper provides a review of application research of multi-agent theories in industrial process control. Firstly, we introduce characteristics of industrial process control. Then, a comprehensive description of some research achievements for multi-agent theory problems, such as the architecture, algorithm, coordination, cooperation, negotiation, and communication, applied in industrial process control, is introduced to identify main research lines. Further multi-agent theories and applications in industrial process control are discussed in detail, and their significance is revealed, which applies directions for the further research and improvement.
In the manufacturing process of hot strip continuous rolling, it is one of key factors to ensure stability rolling and better quality of strip, to keep the relatively invariable strip tension between two stands. Draft compensation was adopted, which takes the initiative to compensate roller speed, in order to decrease the coupling effect of automatic gauge control subsystem, automatic speed regulator subsystem and automatic tension control subsystem in the control system of the hot strip rolling mill. As a result, the strip tension fluctuating was deceased effectively, which kept steady looper angle and improved strip thickness precision.
The problem of roll eccentricity has become one of important factors to affect the quality of strips as downstream industries require improvement of the strip quality. Reducing thickness control precision as little as possible is incompatible with restraining roll eccentricity perturbations on the requirement of the deadband size for the deadband drift method (DDM) with fixed deadband width. Therefore, the GM-AGC system in hot finishing mill of an aluminum plant uses the dynamic deadband eccentricity filter (DDEF) whose deadband width varies with the amplitude of the roll eccentricity signal. The operating principle of DDEF was introduced according to the characteristic of roll eccentricity signal. Based on the theory of DDEF, simulation was carried out. Comparing with DDM, the simulation result shows that DDEF can keep a balance between less lowering thickness control precision and restraining roll eccentricity perturbations on the requirement of the deadband size. Moreover, the deadband width of DDEF is capable to fit the variations in the frequency and amplitude of the synthetic roll eccentricity signal to restrain the misoperation of GM-AGC system.
In view of the process of automatic flatness control and automatic gauge control that is a nonlinear system with multi-dimensions, multi-variables, strong coupling and time variation, a novel control method called self-tuning PID with diagonal recurrent neural network (DRNN-PID) based on Q learning is proposed. It is able to coordinate the coupling of flatness control and gauge control agents to get the satisfactory control requirements without decoupling directly and amend output control laws by DRNN-PID adaptively. Decomposition-coordination is utilized to establish a novel multi-agent system for coordination control including flatness agent, gauge agent and Q learning agent. Simulation result demonstrates the validity of our proposed method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2025 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.