Application of PSO-BP Neural Network Model on Identification of Human Dynamic Balance

Abstract

Since the human dynamic balance system is nonlinear, common models can hardly characterize the adjustment process of human dynamic balance veritably. In this research, the particle swarm optimization (PSO) algorithm and back propagation (BP) neural network algorithm had been introduced to the identification of nonlinear system models for human dynamic balance. Firstly, in order to establish BP neural network based on prediction model about human dynamic balance system, torque and angle of human ankle for 50 healthy college students had been acquisited to act as input and output of nonlinear identification respectively in conditions of suffering random visual excitation; secondly, aiming at improving the convergence performance of conventional BP neural network, this article adopted PSO algorithm to optimize the initial weights and thresholds of BP neural network and then the prediction model based on PSO-BP algorithm had been built; finally, the predictive results before and after optimization had been compared. According to the results of simulation and quantitative comparison, the presented algorithm had accomplished modeling for the adjustment process of human dynamic balance, and it also showed that PSO optimization algorithm not only improved the performance of BP neural network, making it didn’t fall into local minimum easily, but also strengthened the generalization capability and enhanced prediction accuracy, making it more truly and accurately to characterize the adjustment process when human body maintains dynamic balance.