中文摘要：

永磁同步电动机伺服控制中，速度环和电流环的PI参数取决于电机参数。分析电机模型后，建立电机输出量的误差函数，使之含有各种待估参数。引入单层神经网络，运用梯度方法动态更新权值，再通过权值估算电机参数。改变学习速率的大小，影响估算精度和收敛速度。实验和仿真效果均验证其有效性，PI参数自调节后，电机控制性能明显改善。

英文摘要：

PI parameters of velocity loop and current loop in PMSM servo control, depend on the motor＇s pa- rameters. After analyzing the motor model, the output quantities error functions which contain the parameters to be estimated, was established. The single-layer neural network using gradient method to dynamically up- date the weights was proposed to achieve estimation. Learning rate affects estimation accuracy and conver- gence rate. Both experimental and simulation results verify its effectiveness and after PI parameters self-tun- ing, the motor control performance is significantly improved.