Research and application of reinforcement learning driven density optimization control in dense-medium sorting
Song Wanjun
Bai Long
Abstract：In-depth research and analysis on density circuit process and related characteristics of dense-medium sorting were conduc-ted.An optimization control method based on online model free reinforcement learning was proposed,making the density control system of dense-medium separation suspension asymptotically stable and tracked the set value of suspension density online,and improved effi-ciency and accuracy of dense-medium sorting.Meanwhile,the optimization control method was simulated and validated using MATLAB simulation experiments.The results indicate that this method has precise control effect.
Keywords：dense-medium sorting processreinforcement learningstrategy iterationoptimization controloptimal performance indicators
Publication Date：2025-08-25
Online Publishing Date：2025-09-12(First online date of this platform, not the publication date of the document)
Pages：6( 29-34 )