A constructive-pruning hybrid method （CPHM） for radial basis function （RBF） networks is proposed to improve the prediction accuracy of ash fusion temperatures （AFT）. The CPHM incorporates the advantages of the c...A constructive-pruning hybrid method （CPHM） for radial basis function （RBF） networks is proposed to improve the prediction accuracy of ash fusion temperatures （AFT）. The CPHM incorporates the advantages of the construction algorithm and the pruning algorithm of neural networks, and the training process of the CPHM is divided into two stages： rough tuning and fine tuning. In rough tuning, new hidden units are added to the current network until some performance index is satisfied. In fine tuning, the network structure and the model parameters are further adjusted. And, based on components of coal ash, a model using the CPHM is established to predict the AFT. The results show that the CPHM prediction model is characterized by its high precision, compact network structure, as well as strong generalization ability and robustness.展开更多
基金The National Natural Science Foundation of China(No.60875035)the Natural Science Foundation of Jiangsu Province(No.BK2008294)the National High Technology Research and Development Program of China(863 Program)(No.2006AA05A107)
文摘A constructive-pruning hybrid method （CPHM） for radial basis function （RBF） networks is proposed to improve the prediction accuracy of ash fusion temperatures （AFT）. The CPHM incorporates the advantages of the construction algorithm and the pruning algorithm of neural networks, and the training process of the CPHM is divided into two stages： rough tuning and fine tuning. In rough tuning, new hidden units are added to the current network until some performance index is satisfied. In fine tuning, the network structure and the model parameters are further adjusted. And, based on components of coal ash, a model using the CPHM is established to predict the AFT. The results show that the CPHM prediction model is characterized by its high precision, compact network structure, as well as strong generalization ability and robustness.
