摘要
基于改进BP神经网络,建立了一种自适应在线控制模型,并且该控制方法应用到离散非线性动力系统和倒立摆系统控制问题。为了避免BP神经网络在训练过程中的目标函数局部极小值问题,提出了一种基于BFGS优化算法的神经网络训练方法。与其它控制方法相对比,所提出的基于神经网络的倒立摆控制方法具有较高的控制精度。通过离散时间系统的控制模拟和倒立摆模型系统的控制两个算例,验证了所提出的控制方法的具有有效性和很好的控制效率。
An on-line training model for self-turning control is constructed based on the feedback error learning model, and its effectiveness is investigated through controlling an inverted pendulum. In order to deal with the local minimum problem in training neural network with back-propagation algorithm and to enhance controlling precision, neural network＇s weights are adjusted by optimization algorithm. When compared to other nonlinear modeling techniques for control purposes, it has several specific advantages that make it ideally suited to particular applications. Tow numerical examples are used to demonstrate the performance and properties of the proposed scheme. The simulation results show that the proposed controller with improved neural network is flexible and efficient in the control of discrete nonlinear dynamic system and inverted pendulum system.
出处
《科学技术与工程》
2008年第17期4891-4894,4900,共5页
Science Technology and Engineering
关键词
非线性动态系统
BFGS优化算法
离散时间系统
倒立摆模型系统
全局最优解
nonlinear dynamical system BFGS optimization algorithm discrete-time system inverted pendulum model system globally optimal solution
