Optimal-Setting for Ore and Water Feeding in Grinding Process Based on Improved Case-Based Reasoning

The grinding product particle size is the most crucial operational index of mineral processes. and consistency directly affects subsequent dressing sintering. In this paper, a novel expert system proposed for guiding operating variables to keep stable with wildly varying ore properties. First, case-based reasoning (CBR) introduced describe whole process historical data experience. Second, generative adversarial network (GAN) employed extend raw enhance flexibility CBR. Moreover, weights different features in CBR optimized by improved non-dominated sorting genetic algorithm II (NSGA-II). Finally, method validated set actual collected from Chinese plant. experimental result demonstrates effectiveness method.