Title :
Research of neural network model prediction strategy based on PSO-BP algorithm
Author_Institution :
Sch. of Inf. & Technol., Northwest Univ., Xi´an, China
Abstract :
In the nonlinear model prediction, it is often difficult to obtain accurate nonlinear mathematical model, and therefore prediction accuracy is affected. Through combining particle swarm algorithm with BP algorithm, this paper puts forward a PSO-BP algorithm to improve BP algorithm, and also applies it to neural network model prediction to improve the accuracy of the nonlinear model prediction.
Keywords :
adaptive control; backpropagation; neural nets; nonlinear control systems; particle swarm optimisation; predictive control; BP algorithm; PSO-BP algorithm; neural network model prediction strategy; nonlinear mathematical model; nonlinear model prediction; particle swarm algorithm; Accuracy; Adaptation models; Mathematical model; Particle swarm optimization; Prediction algorithms; Predictive models; Training; BP neural networks; Nonlinear model prediction; Particle swarm algorithm;
Conference_Titel :
Electronic and Mechanical Engineering and Information Technology (EMEIT), 2011 International Conference on
Conference_Location :
Harbin, Heilongjiang
Print_ISBN :
978-1-61284-087-1
DOI :
10.1109/EMEIT.2011.6023949
