A Father-Keeping Immune Genetic Algorithm Based Neural Network Model for Properties Prediction of Carbon Fiber

Abstract

Aiming to guide the manufacture process of carbon fiber and obtain high properties productions, we propose a hybrid algorithm named father-keeping immune genetic algorithm based on back propagation neural network (FKIGA-BP) as a properties prediction model. The present study also compares it with BP neural network forecasting method. It shows better search precision and convergence efficiency. The prediction results are consistent with the practical experiment data.