This paper investigates the position tracking control problem for an induction motor with completely unknown nonlinearities. A novel control scheme is presented by using the gradient descent algorithm, adaptive backstepping technique, neural networks (NNs), and extended differentiators. Differing from some existing results which only designed the adaption of weights of NNs, our proposed control strategy provides training for all the parameters of NNs, including the basis functions’ widths and centers. With the help of the gradient descent algorithm and Lyapunov stability criterion, the convergence of both the NN approximation error and the system tracking error can be guaranteed. Finally, a simulation example shows the advantages of our proposed method compared with direct adaptive NN control strategy.

中文翻译：

---

基于梯度下降算法的感应电机自适应神经网络控制设计

本文研究了非线性完全未知的感应电机的位置跟踪控制问题。通过使用梯度下降算法、自适应反步技术、神经网络 (NN) 和扩展微分器，提出了一种新的控制方案。与现有的一些仅设计神经网络权重自适应的结果不同，我们提出的控制策略为神经网络的所有参数提供训练，包括基函数的宽度和中心。借助梯度下降算法和Lyapunov稳定性判据，可以保证NN逼近误差和系统跟踪误差均收敛。最后，一个仿真实例显示了我们提出的方法与直接自适应 NN 控制策略相比的优势。