established a linear programming model with the goal of maximizing the sales value of phosphate rock and solved it with Matlab software. The solving speed and work efficiency of ore blending were significantly improved. adopted a 0–1 integer programming model and embedded it in DIMINE software to study the optimization problem of open-pit mine ore blending with the goal of a balanced quantity of ore.
Single-objective planning mostly adopts 0–1 integer programming, goal programming, and general linear programming methods for modeling. The modeling mainly takes ore grade, transportation work, production capacity, etc., as the optimization objectives. The preparation of an ore-blending plan mainly focuses on modeling and solutions. When compared with the traditional multiobjective optimization algorithm, the efficiency and accuracy of the solution have been greatly improved, and the calculation results can be obtained in real-time. The experimental results show that the ore-blending optimization model constructed is more in line with the actual production requirements of a mine.
Finally, taking a large open-pit metal mine as an example, the trained multiagent depth reinforcement learning algorithm model was verified via experiments, with the optimal training model displayed on the graphical interface. Thirdly, a multiagent deep reinforcement learning algorithm was introduced, which was trained continuously and modeled the environment to obtain the optimal strategy. Secondly, the open-pit ore-matching problem was transformed into a partially observable Markov decision process, and the ore supply strategy was continuously optimized according to the feedback of the environmental indicators to obtain the optimal decision-making sequence. Firstly, according to the actual production situation of the mine, the optimal control model for ore blending was established with the goal of minimizing deviations in ore grade and lithology. In order to solve the problems of a slow solving speed and easily falling into the local optimization of an ore-blending process model (of polymetallic multiobjective open-pit mines), an efficient ore-blending scheduling optimization method based on multiagent deep reinforcement learning is proposed.
0 kommentar(er)
