Application of RBF Algorithm Based on Generalized Genetic Optimization in Prediction Model for Molten Iron Desulfuration

Desulfuration process is a very sophisticate reaction which is not only diverse but also non-line. A RBF algorithm based on generalized genetic optimization is proposed after studying the standard genetic and RBF algorithm. The authors also introduce its application in prediction Model for molten Iron Desulfuration. The algorithm perfectly resolve the problem of random selection of RBF cluster center number. Furthermore, it also reduces the time which GA uses. Comparison between the simulation results of RBF and RBF algorithm Based on GGA optimization further proves the efficiency and precision of its application in Prediction Model for Molten Iron Desulfuration. Finally the result of the test shows that after adopting the algorithm, the end-point hitting ratio can reach eighty-five percent. This indicate the algorithm has the engineering practicability.     

Orthogonal Back-Propagation Algorithm of Generalized Inverse of a Matrix

Calculating generalized inverse of a matrix is a basic algorithm for inverstigating linear equations and optimization problems. In this paper we investigate the algorithm of generalized inversion of a matrix by using Orthogonalized Back-Propagation Algorithm (OBPA). There is no problem for convergence in OBPA. It is shown how OBPA avoids some of the difficulties posed by the Back-Propagation(BP)algorithm.     

Dynamical Programming Algorithm for Multilayer feedforward Neural Networks

This paper trains the multilayer neural networks using dynamical programming.The weithts are adjusted layer by layer. The optimal weishts of each layer are calculated using OBPalgorithm proposed in the related reference. The globally optimal weights of each layer can be obtained by finite iterations.