Predicting Coal Ash Fusion Temperature Using Hybrid of Ant Colony Algorithm and BP Neural Network

A novel algorithm based on the hybrid of ant colony algorithm and BP algorithm (ACA-BP) is presented in this paper. It adopts ACA to search the optimal combination of weights in the solution space, and then uses BP to obtain the accurate optimal solutions. The proposed method can obtain better generalization ability. Compared with BP neural network, the ACA-BP neural network can achieve better performance in predicting the coal ash fusion temperature.