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 on-line prediction of calorific value of coal has a profound significance for the economic operation of power plants. Aiming at the problem of uncertainty of calorific value of coal, a soft measurement model for calorific value of coal is proposed based on the RBF neural network. And combined with the thought of k-cross validation, the genetic algorithm constructed a fitness function to optimize the RBF network parameters. It is shown by an example that the optimized model is concise and accurate, with good training accuracy and generalization ability. The model could provide a good guidance for the calculation of the calorific value of coal and optimization operation of coal fired power plants.
A new prediction model of main steam flow was come up with based on mean impact value (MIV) and support vector regression (SVR). At present, the main steam flow of large capacity unit is calculated by the Fulugel formula using the pressure after regulating stage and other parameters. Because of changing of flow path condition, varying load and other reasons, the working condition may not satisfied the Fulugel formula, and the result calculated by the Fulugel formula often has large error. Nowadays, researchers tend to take advantage of soft measurement. In this paper, mean impact value method in mathematics is introduced to the main steam flow prediction model of support vector regression, using mean impact value method to choose input variables that meet the requirements of model. The results show that, the mean impact value can effectively select the variables, and get 9 important variables from 16 initial variables, which greatly reduce the dimensions of model. In addition, the new model that combines the mean impact value with support vector machine can obtain much satisfied prediction precision than the model without getting rid of the not important variables. The maximal relative error is 3.1281 percent and the average absolute relative error is 0.9833 percent in the model without selecting variables. Compared with the former model, maximal relative error of the main steam flow predicted by the new model is 1.2248 percent, and the average absolute relative error is only 0.3687 percent. Obviously, the new model is capable of better generalization ability and high precision. Accurate measurement of main steam flow is significant to improve the online economic analysis reliability of units.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.