In order to improve the prediction precision of calorific value of coals

a forecasting method based on parameters adaptive particle swarm optimization(PSO)and least squares support vector machine(LSSVM)algorithm was presented.Through optimizing the parameters of LSSVM algorithm by parameters adaptive PSO algorithm

aprediction model for coals' calorific value was established.Moreover

the predicted calorific values were compared with the test data.The simulation results show that

the method based on the parameter adaptive PSO-LSSVM prediction model can accurately predict the change of calorific value

which has faster calculation speed

higher precision and is suitable for engineering application

compared with the parameter self-adaptive PSO-BP model

the PSO-LSSVM model and the genetic algorithm(GA)-LSSVM model.