摘要
由于非线性系统在实际中大量存在,因此对其进行辨识研究显得十分重要。论文针对目前非线性系统难以辨识的问题,先利用BP神经网络对非线性对象进行逼近辨识,再采用粒子群算法优化BP网络的方法。仿真结果表明该方法能够实现更大精度的辨识效果。
The neural network has achieved great success in many areas, but it also has its own deficiencies and shortcomings such as slow convergence and prone to local minimum, the initial weights, the threshold is difficult to determine. To improve the control performance, improve forecast accuracy, PSO algorithm is used for neural network weights optimization, particle swarm neural network system iden tification of nonlinear systems can get short time, high precision, and achieved good results.
出处
《计算机与数字工程》
2013年第8期1220-1221,1261,共3页
Computer & Digital Engineering
基金
陕西省教育厅科研项目(编号:12JK0751)资助