The development of coke quality prediction model is one of the hot topics in coking industry in recent years, the coke quality prediction broadly speaking, including the coke ash, sulfur grade chemical nature of indicators, cold strength and thermal properties indicators. Many models of coke quality prediction have been proposed, most of which are based on coal characteristics and limited to the same coal geographic origin, but as yet there is no universally applicable prediction formula.At present using the traditional method combining coking experiences can't satisfy the demand of blast furnace. In order to seek a fast and scientific approach to coke quality prediction, the paper based on recent years a variety of coke quality prediction methods and researches at home and abroad, establish a linear regression model to predict the quality of coke.The results show that: coal ash and coke ash is a linear relationship. Coal ash, volatile, bond index and the intensity of coke showed a linear relationship too. Coal ash and the volatile nature of thermal, bond index also showed a linear relationship. It points out that using linear regression model to predict the coke quality is feasible. Using a series of multiple regression analysis deal with the data, then we get an coke quality prediction of the mathematical model which appropriate to product.
|