A PSO-ANN Integrated Model of Optimizing Cut-Off Grade and Grade of Crude Ore

This work proposes a particle swarm optimization (PSO) and artificial neural networks (ANN) integrated model to simulate the highly complexity and non-linear mine system, to optimize the cut-off grade and grade of crude ore. The inner layer of nesting is neural networks, which is used to compute loss rate, metal utilization rate and total cost; the outer layer is PSO algorithm, with cut-off grade and grade of crude ore as a particle, which is used to get the revenue. These two layers carry out the optimization of cut-off grade and grade of crude ore jointly. Take Daye Iron Mine as a case, the result shows that: During the period of January to November in the year 2007, the optimal cut-off grade is 17.83%, and optimal grade of crude ore is 46.4%. Comparing with the present scheme (cut-off grade is 18%, grade of crude ore is 41-42%), the optimized scheme can increase the amount of concentrate by 139200 tons, and improve the net present value by 6.698 million Yuan.