无速度传感器的感应电机神经网络鲁棒自适应控制

针对感应电机定子电阻和负载转矩参数的不确定性，提出了无速度传感器的感应电机神经网络鲁棒自适应控制方案。用反步法设计了一种可以将各状态变量跟踪误差和神经网络各权值限制在规定范围内的神经网络鲁棒自适应控制器，提出了相应的算法，用Lyapunov定理对其稳定性进行了证明。提出了一种可以估算转子磁链和转速的观测器及相应的算法。仿真研究表明，所提出的感应电机无速度传感器控制方案对电机定子电阻、负载转矩的鲁棒性强，动态性能好，速度估算较精确。

Speed Sensorless Neural Network Robust Adaptive Control for Induction Motors

This paper proposes a speed sensorless neural network robust adaptive control scheme, which is robust to stator resistance and load torque of induction motor. Neural network robust adaptive controllers and their algorithms that can guarantee the tracking errors and the weights of the neural networks converge to defined sets are designed using backstepping. Lyapunov theory is applied to prove the stability of the control system. An observer and its algorithm are proposed to estimate rotor flux and speed. Simulation results show that the proposed scheme is robust to the considered uncertainties and has high dynamic performance. The speed estimation is accurate.