Coking Coal Intelligent Optimization Model And Its Application

The coal blending and coking process, in which much uncertainty exists, is too complicated to describe. The mixed coal quality, which is determined by the quality and proportioning ratio of single coal, has direct influence on the coke quality index. The nonlinear relation among the variables is so complex that the traditional methods can hardly control effectively.In coking process, blending ratio of coal is the main factor to influence on coke quality prediction. Starting from the coking process, an coal blending and coking intelligent optimization model which can accurately determine the coal blending rate is present in this paper, which effectively have been improved the quality of coke and the coal blending efficiency, thus have been lowered the cost of production. The main study achievements include:(1) Starting at the technique of coal blending process, this paper analyzed in detail all kinds of factors that influence the quality of the mixed coal, which include the component of ash, sulfur, volatility, and water and felting index of every single coals. This paper present building a quality forecasting model of mixed coal on the basis of principle analysis, which take the above five factors as assistant variables and obtain the quality forecasting value by linear regress. At the same time, this paper analyzed in detail the factors that influence the quality of the coke, described the relationship between the index of mixed coal and coke using BP neural network and build the quality forecasting model of coke (take the component of water, ash, volatility and sulfur, felting index and thinness of mixed coal and the input of neural network to forecast) .(2) Aiming at the characteristic of traditional coal blending based on manual experience which has large computing demand and low accuracy, and based on given mixed coal and coke quality index, quality index of every single coal and coal blending and coking condition, this paper built rate calculating and optimizing model using simulated annealing algorithm according to certain restriction condition of cost and storage. The optimized coal blending rate and coal blending solution can be obtained by this model .(3) In this paper, the intelligent optimization control of coal blending process is implemented with VC++ as its development tool on the platform of IFIX. The result of real-time control proves that the algorithm is high-performance. The control system has improved the efficiency of blending coal and reduced the production costs. Meanwhile, the forecast accuracy of the coke quality achieved by more than 90%, the quality of coke is improved effectively.