Dapeng Niu

A New Method for Decision on the Structure of RBF Neural Network

RBF, as a feedforward neural network with single hidden layer, is applied widely in signal disposing, system modeling, control fields, etc. But the decision of its structure lacks effective methods. The discussion on ability of network generalization ability is one of important research aspects. The paper proposed a method based on PCA to decide the number of hidden neurons. Firstly it gives the larger number of network hidden neurons and compute the output of hidden layer, then makes PCA on it, calculates the cumulative explained variance rate and gets the number of principal components as the number of hidden neurons. The method has certain optimization ability to confirm the structure, which not only simplifies the generalization ability, but also has robustness to noises

Plant-wide optimization for gold hydrometallurgy based on the fuzzy qualitative model and interval number: Plant-Wide Optimization for Gold Hydrometallurgy

Since the difficulty of obtaining accurate online‐measurement of some key variables in hydrometallurgy plant‐wide production process causes that the quantitative models of some procedures are difficult to establish and the plant‐wide optimization based on quantitative model is difficult to realize, a plant‐wide optimization method based on interval numbers is proposed in this work. First, based on the information of expert knowledge and the experience of field workers, a fuzzy qualitative model is constructed, and outputs of the qualitative model are reasonably divided into multiple modes simultaneously. By analyzing the process properties, an optimal control problem for hydrometallurgy plant‐wide production process in the steady state is proposed to achieve process requirements which is to obtain the lowest cost of sodium cyanide and zinc as well as high gold quality. Then, by using interval numbers to represent the key variables that cannot be measured, an optimization method based on interval numbers is proposed for every output mode of the qualitative model. Finally, the hydrometallurgy process is carried in industrial simulation experiment. The results demonstrate that the proposed optimization scheme has much wider applicability than conventional optimization methods, especially for its improved performance of solving optimization problem with uncertainty.

Hybrid modeling method for predicting the cooling water outlet temperature in plate heat exchanger

The circulating cooling water system which ensures the production process running safely plays a very important role in the iron and steel enterprise and its energy-saving operation is based on the accurate prediction of the cooling water outlet temperature in the plate heat exchanger. A hybrid modeling method is proposed in this paper to predict the cooling water outlet temperature in the plate heat exchanger. By analyzing the operational mechanism of the heat transfer process in the plate heat exchanger, the mechanistic model is established according to the thermal transfer equation and the thermal balance equation and then the radial basis function neural network (RBFNN) is applied to develop the hybrid model with the mechanistic model, in which the RBFNN corrects the error made by the mechanistic model due to the theoretical assumption and the inaccurate value of parameter. Finally the simulation is made to verify the modeling method and the results show that the hybrid model has the better prediction performance than the mechanistic model, which lays the foundation for the operation optimization of the circulating cooling water system.

An improved multi-objective differential evolution algorithm

Based on multi-objective differential evolution algorithm, adaptive chaotic multi-objective differential evolution algorithm (AC-DEMO) is proposed, combining with adaptive and chaotic principles. In AC-DEMO, chaotic initialization and adaptive mutation operator are introduced to improve the efficiency of the algorithm. Numerical experiment results of commonly used test functions show that the algorithm has a good approximation and uniformity index and is suitable to solve complex multi-objective optimization problems.

A modified differential evolution algorithm for feed rate optimization of fed-batch fermentation

A novel modified differential evolution (MDE) algorithm that contains simplex acceleration operator and chaotic migration operator is proposed for feed rate optimization of fed-batch fermentation process. The simplex acceleration operator improves the speed of getting global optimum, and the chaotic migration operator keeps the individualspsila diversity in the population to overcome prematurity. Three selection rules are introduced into the algorithm for constrained optimization problem, which ensures that the solution could accord with the constraint condition. The modified algorithm is applied to optimize feed rate of a certain fed-batch fermentation process, which improves the final product yield. The results show that the algorithm is effective.