基于大数据挖掘的烧结参数优化调控模型

Sintering process, as an important part of blast furnace ironmaking, provides 70%~80% of iron-containing raw materials for blast furnace ironmaking, and the energy consumption accounts for about 18% of the total energy consumption of the iron and steel industry, the sintering process exists the problem of high energy consumption and production fluctuation, in order to achieve the goal of energy saving and cost saving, this paper constructs a sintering parameter optimization and regulation model based on big data mining, which consists of three sub-models, namely, parameter The model includes three sub-models, namely, parameter optimization model, operation parameter traceability model and operation parameter prediction model. Firstly, through the optimization model of sintering process, we identify the core parameters affecting the core economic indexes and determine the optimal set of operating parameters accordingly; then, using the optimal set of operating parameters determined by the optimization model, we explore the root causes of fluctuations in depth, identify the key influencing elements through the retrospective error and make dynamic adjustments accordingly; we establish an ARIMA time-series model, which breaks through the inherent limitations of the static calibration of historical data, and finally, we construct a time-series model based on historical data, and then we establish a time-series model based on the prediction model. The ARIMA time series model is established, which breaks through the inherent limitations of static calibration of historical data, and finally, a prediction model based on radial basis function neural network is constructed to provide a reference for sintering optimization. In the empirical demonstration of the production data of a steel plant, the model stabilizes the utilization factor at 1.47, increases the daily production by 47.52 t, and increases the annual output value by 13.87 million yuan. Meanwhile, the fuel unit consumption was reduced by 1.54 kg/t, saving 6.2 million yuan in annual fuel cost, and the drum index was improved to a stable interval of 77.4±0.1. The sintering parameter optimization and regulation model based on big data mining provides an innovative solution for iron and steel enterprises to realize green and efficient production.