DEVELOPMENT OF INTELLIGENT CONTROL MODELS FOR THE PHOSPHORITE BENEFICIATION PROCESS
Keywords:
Phosphorite beneficiation, intelligent control, neural networks, flotation process, process automation, adaptive control.Abstract
This study focuses on the development and application of intelligent control models for the automated management of the phosphorite beneficiation process. Phosphorite flotation is a complex, multivariable, and nonlinear process influenced by particle size, reagent consumption, pulp density, mixing speed, and other technological factors. Traditional control methods often fail to achieve optimal efficiency under such conditions. To address these challenges, a multilayer artificial neural network (ANN)–based intelligent control model was designed and integrated into the process control system. The neural network predicts phosphorus concentration in real time and provides adaptive control signals to optimize key operational parameters. Simulation results demonstrate that the proposed model enhances phosphorus recovery efficiency by 8–12% and reduces reagent consumption by up to 10%, confirming its practical applicability in industrial phosphorite beneficiation operations.
References
1. Haykin, S. Neural Networks and Learning Machines. Pearson Education, 2018.
2. Bishop, C.M. Pattern Recognition and Machine Learning. Springer, 2016.
3. Zadeh, L.A. Fuzzy Sets. Information and Control, 1965.
4. Kuznetsov, V.A. Automation of Mineral Processing Technologies. Nedra, 2019.
5. Ivanov, I.I. Intelligent Control Systems of Technological Processes. Energoatomizdat, 2020.
6. Liu, Q. Neural Network Control of Flotation Processes. Minerals Engineering, 2020.
7. Zhou, W., Yang, J. Intelligent Control in Mineral Processing. Springer, 2021.
8. Ahmed, R. Automation in Mineral Processing Plants. Elsevier, 2019.
9. Smith, R. Process Control and Optimization. Wiley, 2018.
10. Jang, J.S.R. Neuro-Fuzzy and Soft Computing. Prentice Hall, 2017.
