Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{188215,
        author = {Saravanabalaji M and AmirthaVarshini BA and Karthika R and Baranidharan P},
        title = {Comparative Study of PID, MPC, Fuzzy and FOPID Control for Conical Tank System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {1079-1083},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188215},
        abstract = {Nonlinear process systems such as conical tanks exhibit varying cross-sectional area, making liquid-level control highly challenging with conventional control methods. This work presents an intelligent control framework for a nonlinear conical tank by integrating classical, model-based, and reinforcement learning control strategies. The system is experimentally tested using PID, Model Predictive Control (MPC), Fuzzy Logic, and Fractional-Order PID (FOPID) to establish baseline performance. A nonlinear mathematical model of the conical tank is developed, and open-loop tests are carried out to validate the process dynamics. To address the limitations of conventional methods in handling nonlinearity and varying inflow conditions, advanced reinforcement learning controllers—Soft Actor Critic (SAC), Twin Delayed Deep Deterministic Policy Gradient (TD3), and Deep Deterministic Policy Gradient (DDPG)—are implemented. These algorithms learn optimal control actions through continuous interaction with the environment, eliminating the need for manual tuning. Experimental analysis demonstrates that reinforcement learning controllers achieve faster settling time, lower error, improved disturbance rejection, and superior adaptability compared to traditional controllers. The results highlight the potential of RL-based controllers as robust, self-learning solutions for nonlinear industrial level-control applications.},
        keywords = {Conical Tank, Nonlinear System, PID Control; MPC, Fuzzy Logic, FOPID, Reinforcement Learning, SAC, TD3, DDPG, Process Control, Level Control.},
        month = {December},
        }