Prediction of grinding granularity based on the combination of grey model and neural network

The beneficiation process is an important production process of smelting economic indicators, and a process of dressing production grinding and classification plays a vital role in the beneficiation process, the grinding particle size is an important index of grinding production in the production process, not only affects the concentrate grade and recovery rate and subsequent operation. The key factors in the grinding process. The grinding production process is a very complex control system. There are many interference factors, large inertia and serious nonlinearity. The prediction cost is high and the prediction error is very large. Based on the analysis of the structure and characteristics of GM (1, N) grey prediction model, the grey prediction model is applied to predict the grinding granularity and the prediction error is compensated by neural network. The experimental results show that the predicted values obtained by using the constructed grey model and the neural network for error compensation are closer to the actual value. Meanwhile, the learning time is short, the amount of data needed is small, and the running speed is fast, which can meet the requirements of subsequent processes.