模糊神经网络在直接转矩控制系统中的应用

本文针对基于直接转矩控制的异步电动机运行时存在较大的电流及转矩脉动问题，
提出了利用神经网络建立直接转矩控制系统的定子磁链观测器，并引入模糊控制算法，用较 少的模糊规则实现磁链误差、转矩误差和磁链角对逆变器开关状态的控制，并通过仿真实验 验证了该设计的有效性，实验结果表明该调速系统具有良好的动态性能和稳态性能。
关键词: 直接转矩控制；模糊控制；神经网络；异步电动机
Abstract: Aiming at the problem of great current and torque ripple of the asynchronous motor
based on direct torque control when it is running, this paper uses neural network to form stator flux linkage observer in the direct torque control system. After introducing fuzzy control algorithm, flux-linkage error, torque error and flux linkage angel are adopted to control the state selector of inverter by fewer fuzzy rules. The simulation results demonstrate that the realization of the system is effective, the speed regulating system has good dynamic performance and steady performance.
Keywords: direct torque control, fuzzy control, neural network, asynchronous motor