Research on Prediction of Coal Combustion Calorific Value Based on Intelligent Optimisation of ELM by PSO Algorithm

In thermal power plants, different coals must be blended and combusted when they are fed into the furnace. As one of the key indices of blending, accurately and rapidly predicting the heat of coal is very important for coal blending in power plants. In order to improve the accuracy of the thermal value of coal prediction, a model is proposed for the calorific value of coal combustion based on the particle swarm optimization (PSO) algorithm and the extreme learning machine (ELM) for the coal quality data of a power plant. In comparison to the BP neural network and the ELM prediction model, the PSO-ELM prediction model proposed in this paper exhibits the lowest error, superior overall prediction efficacy, and a goodness of fit of 99.4%.