基于BP神经网络的直接转矩控制

提出一种基于神经网络智能控制的直接转矩控制系统,神经网络控制是智能控制一个重要的分支,它能够处理非线性、不确定性等问题,具有强大的学习能力。利用神经网络控制代替传统直接转矩控制中的矢量优化选择表,神经网络控制能够迅速、准确地选择逆变器的开关状态。仿真结果表明,基于神经网络控制的直接转矩控制系统能够改善系统非动态、稳态性能。

Direct Torque Control Based on BP Neural Network

DTC based on BP Neural Network was studied in this paper.Neural Network control is an important branch in intelligent control.It can resolve problem about nonlinear and uncertain.The Network has ability of learning.The voltage vector optimizing table of traditional DTC was replaced by the BP neural network.The network could select switch state quickly and precisely.The results of simulation show that system based on BP neural network has obvious advantage of good dynamical performance and smaller torque ripple.