Study For Prediction Model Of Silicon Content In Molten Iron Based On Wavelet Analysis

Blast Furnace(BF) ironmaking, which is the main working procedure of the metallurgical, is the pillar of the national economy, and is very important for the development of iron & steel corporation and economizing energy consumption. BF ironmaking process is highly complicated, whose operating mechanism is characteristic of non-linearity, time lag, high dimension, big noise and distribution parameter etc. It is not come true to realize automation of BF ironmaking process in metallurgical technology from the eighties of the twentieth century. The model to predict the silicon content in molten iron is the kernel of automation in BF ironmaking and the key problem is to increase the hitting rate of predicting.In this paper, a new approach to predict the silicon content in molten iron based on wavelet analysis is proposed. On the basis of analyzing the data from the Intelligent Control Expert System on BF at Laiwu Iron & Steel Co, wavelet analysis model is established to predict the silicon content in molten iron.Wavelet analysis as an applied mathematical tool has formed the frame of reference since the eighties of the twentieth century. By wavelet transform, the original time series can be decomposed into several series according to scale in which the signal is steadier than the original time series, so wavelet analysis is good at analyzing and solving the problems. At the same time, wavelet analysis can abstract the details of the series at will in any scale. In this way, the results of the signal forecast could be more accurate than the forecast results without using wavelet analysis.Firstly BF ironmaking process, BF Expert System and the methods to predict the silicon content in molten iron are introduced in this paper. Secondly the basic theories of wavelet analysis and auto-regression forecasting model also are introduced. Finally a new model based on wavelet analysis is established to predict the silicon content in molten iron.In present dissertation, as the real time data measured in No. 1 BF in Laiwu Iron and Steel Group Co. to be sample space, the capacity is 1000 records and average...