单神经元PID控制器在直接矢量控制中的应用研究

Research on Application of Single Neuron PID Controller in Direct Vector Control

异步电机矢量控制改善了电机的转矩控制特性,但是由于系统运行过程中一些不可控或不确定的因素,传统PID控制难以满足精度高、反应快、鲁棒性好的要求。基于单神经元网络设计了用于矢量控制的增益自调整的自适应磁链和速度控制器,并运用改进的学习与控制算法,实现单神经元PID控制器的参数优化与在线自动调整。仿真与实验结果表明:单神经元PID控制器可以改善异步电动机矢量控制的性能,具有较强的自适应性与鲁棒性。

The vector control can highly improve the torque control performance of the AC motor drive, but due to some uncertain reasons during the control process, the traditional PID controller can not satisfy the requests of high-performance control, such as fast dynamic response and accurate speed or torque control and robustness. This paper designs the adaptive flux controller and speed controller based on single neural network. The improved study and control algorithms are adopted to achieve the parameter optimum and automatic adjustment on line. The emulation and experiment results show that the single neuron PID controller can improve the vector control property of induction motor the and has stronger self- adaptability and robustness.