神经元自适应控制器在矢量控制中的应用

感应电机矢量控制技术是通过坐标变换，实现对定于电流的励磁分量与转矩分量的解辐控制。传统PID控制器在电机参数改变时鲁棒性较差。神经网络具有自学习、自适应能力，用于控制时可以不依赖控制对象的数学模型。为实现对交流电机快速和精确控制，基于单神经元设计出用于感应电机矢量控制的自适应磁链和转速控制器，利用神经元的自学习功能在线调节连接权重，实现自适应控制。并将此设计应用于交流电机矢量控制系统中，数字仿真实验表明，此方法设计的控制器可克服传统PID控制器在电机参数改变时控制性能差等不足，鲁樟性强。该设计结构简单，实现应用时易于数字化实现。

The Application of Neuron Adaptive Controller for Vector Control

The technique of induction motor vector control is a way to realize the decoupling control of stator current excitation and torque variable using coordinates transform. The conventional PID controller is of poor robustness when the motor parameters varying. The neural network with the capability of self-study and self-adaptive,can control a system without modeling the plant. For the sake of fast and accurate control of induction motor, design the adaptive flux controller and speed controller based neuron for the induction motor vector control using the capability of neuron self-study adjusting the weight online. The result of digital simulation shows that the designed scheme overcomes the control defect of conventional PID controller,with the motor parameters varying, prefect in dynamic performance, strong in robustness. The configuration of the method is simply and easy to digital achieving.