Coal Calorific Value Prediction Based on Projection Pursuit Principle

The calorific value of coal is an important factor for the economic operation of coal-fired power plant. However, calorific value is tremendous difference between the different coal, and even if coal is from the same mine. Restricted by the coal market, most of coal fired power plants can not burn the designed-coal by now in China. The properties of coal as received are changing so frequently that pulverized coal firing is always with the unexpected condition. Therefore, the researches on the prediction of calorific value of coal have a profound significance for the economic operation of power plants. Aiming at the problem of uncertainty of coal calorific value, establish a soft measurement model for calorific value of coal based on projection pursuit principle combined with genetic algorithm to optimize parameters, and support vector machine algorithm. It is shown by an example that the model has a stronger objectivity, effective and feasible for avoiding the disadvantage of the artificially decided weights of feature indexes. The model could provide a good guidance for the calculation of the coal calorific value and optimization operation of coal-fired power plants.