A self-organizing radial basis function(RBF) neural network(SODM-RBFNN) was presented for predicting the production yields and operating optimization. Gradient descent algorithm was used to optimize the widths of RBF neural network with the initial parameters obtained by k-means learning method. During the iteration procedure of the algorithm, the centers of the neural network were optimized by using the gradient method with these optimized width values. The computational efficiency was maintained by using the multi-threading technique. SODM-RBFNN consists of two RBF neural network models: one is a running model used to predict the product yields of fluid catalytic cracking unit(FCCU) and optimize its operating parameters; the other is a learning model applied to construct or correct a RBF neural network. The running model can be updated by the learning model according to an accuracy criterion. The simulation results of a five-lump kinetic model exhibit its accuracy and generalization capabilities, and practical application in FCCU illustrates its effectiveness.
A complex exothermic batch reactor model was developed by using structure approaching hybrid neural networks(SAHNN).The optimal reactor temperature profiles were obtained via the PSO-SQP algorithm solving maximum product concentration problem based on recurrent neural network(RNN).Considering model-plant mismatches and unmeasured disturbances,a novel extended integral square error index(EISE)was proposed,which introduced mismatches of model-plant into the optimal control profile.The approach used a feedback channel for the control and therefore dramatically enhanced the robustness and anti-disturbance performance.The stability analysis of the one-step-ahead control strategy through SAHNN-based model was described based on Lyapunov theory in detail.The result fully demonstrated the effectiveness of the proposed optimal control profile.
