Neural network construction and its predication for coal-blending at coal combustion power station

With the coal consumption increasing gradually, coal blending is becoming a routine work in power stations. Due to the fluctuation of the coal quality, coal blending is in fact an optimization problem under uncertain conditions, so that it is difficult to solve with the traditional linear programming model. On the other hand, BP neural network, a nonlinear optimization tool, has been successfully applied to coal blending. In this paper, the prediction effects of different BP neural network model were analyzed and the main factors affecting the prediction effects were also studied. These factors included network structure, learning sample quantities, hidden nodes, learning accuracy and etc. Based on the above analyses and studies, BP neural networks were built to predict characteristics, such as low heat and others, of blended coals, and the prediction accuracy is extremely high. Three cases were predicted in this paper. In addition, the optimization of coal blending was conducted with exhaustive method, and it is very directive to the practical coal blending. The characteristics of neural network are with close relation with the data extension of the input and output samples, so it is universal and has strong expansion.