GENETIC ALGORITHM OPTIMIZED ANFIS CONTROL FOR COTTON SEED LINTING PROCESS
Kurbonov N. . & Gazieva R. .
Annotatsiya
This paper presents a Genetic Algorithm optimized Adaptive Neuro-Fuzzy Inference System (GA–ANFIS) controller for the cotton seed linting process characterized by strong nonlinearity, parameter uncertainty, and variable raw material properties. Conventional PID controllers and standard ANFIS models often exhibit performance degradation under such conditions due to fixed parameters and local optimization limitations. To address these challenges, a Sugeno-type ANFIS controller is developed to regulate linting productivity based on seed fuzziness level and feed drum rotational speed, while a Genetic Algorithm is employed to globally optimize both antecedent membership functions and consequent parameters. A nonlinear dynamic model of the linting process is formulated, and simulation-based datasets are used for training and validation. The proposed GA–ANFIS controller is evaluated in a closed-loop configuration and systematically compared with classical PID and standard ANFIS controllers. Simulation results demonstrate that the GA–ANFIS controller reduces overshoot from 18.5% (PID) and 9.2% (ANFIS) to 3.8%, shortens settling time from 12.4 s (PID) to 4.6 s, and decreases the mean squared error to 0.006. These results confirm the superior tracking accuracy, faster transient response, and improved robustness of the proposed approach. The developed GA–ANFIS control strategy provides an effective solution for intelligent control of cotton seed linting processes and can be extended to other nonlinear agro-industrial systems.
Adabiyotlar
- Bulent Haznedar, Adem Kalinli. Training ANFIS Using Genetic Algorithm for Dynamic Systems Identification IJISAE, 2016, 4(Special Issue), 44–47
- Ahmed M. Othman, Adel M. Sharaf. A GA-ANFIS Self Regulating Scheme for Induction Motor Filter Compensation International Journal of Energy Engineering 2013, 3(2): 74-96
- Panchenko, T. V. Genetic Algorithms: A Study Guide. Astrakhan University Publishing House, 2007. 87 [3] p.
- Gaziyeva, R., Ozodov, E., Bozorov, E., & Nigmatov, A. (2020, December). Automatic decision-making system for the desalinization of water for irrigation. In IOP Conference Series: Earth and Environmental Science (Vol. 614, No. 1, p. 012113). IOP Publishing.
- O.F. Lutfy, S.B. Mohd Noor, M.H. Marhaban and K.A. Abbas. A Simplified PID-like ANFIS Controller Trained by Genetic Algorithm to Control Nonlinear SystemsAustralian Journal of Basic and Applied Sciences, 4(12): 6331-6345, 2010
- Gaziyeva R.T., Kurbonov N.M., Yunusova S.O. Information converter of seed pubescence based on software tools for the use of improved process control systems of linting // IOP Conf. Series: Earth and Environmental Science [1043] Russia, 2022. – Pp.1-5.
- Gazieva R., Kurbonov N. Building a model of a recurrent neural network for controlling the technological process of controlling the fuzziness of cotton seeds. Agro-ilm, 2023. - 6 (95). - P. 6-7.