Application of Particle Swarm Optimization Algorithm in Prediction of Coal Calorific Value

A prediction model of coal calorific value based on BP neural network was established according to measured contents of total moisture of as received basis, ash of as received bass, ash of dry basis and volatile matter of as received basis in coal. Particle swarm optimization algorithm was used to optimize weights and thresholds of the BP neural network, which achieved rapid prediction of coal calorific value. The simulation and experimental results showed that the prediction model optimized by particle swarm optimization algorithm can be used for coal quality analysis, which has high study precision and good stability and robustness.