Although adaptive control design with function approximators, for example, neural networks (NNs) and fuzzy logic systems, has been studied for various nonlinear systems, the classical adaptive laws derived based on the gradient descent algorithm with σ -modification or e -modification cannot guarantee the parameter estimation convergence. These nonconvergent learning methods may lead to sluggish response in the control system and make the parameter tuning complex. The aim of this paper is to propose a new learning strategy driven by the estimation error to design the alternative adaptive laws for adaptive control of nonlinear servo systems. The parameter estimation error is extracted and used as a new leakage term in the adaptive laws. By using this new learning method, the convergence of both the estimated parameters and the tracking error can be achieved simultaneously. The proposed learning algorithm is further tailored to retain finite-time convergence. To handle unknown nonlinearities in the servomechanisms, an augmented NN with a new friction model is used, where both the NN weights and some friction model coefficients are estimated online via the proposed algorithms. Comparisons with the σ -modification algorithm are addressed in terms of convergence property and robustness. Simulations and practical experiments are given to show the superior performance of the suggested adaptive algorithms.

中文翻译：

---

非线性伺服系统的有限时间收敛自适应神经网络控制。

尽管已经针对各种非线性系统研究了带有函数逼近器的自适应控制设计，例如神经网络（NNs）和模糊逻辑系统，但是基于具有σ-修改或e-修改的梯度下降算法的经典自适应定律无法保证参数估计收敛。这些非收敛学习方法可能导致控制系统响应缓慢，并使参数调整变得复杂。本文的目的是提出一种由估计误差驱动的新的学习策略，以设计用于非线性伺服系统的自适应控制的替代自适应律。提取参数估计误差并将其用作自适应定律中的新泄漏项。通过使用这种新的学习方法，估计参数和跟踪误差的收敛可以同时实现。所提出的学习算法经过进一步调整，可以保留有限时间的收敛性。为了处理伺服机构中未知的非线性，使用带有新摩擦模型的增强神经网络，其中通过所提出的算法在线估算神经网络权重和一些摩擦模型系数。就收敛性和鲁棒性而言，与σ修改算法进行了比较。仿真和实际实验表明了所提出的自适应算法的优越性能。通过所提出的算法在线估算神经网络权重和一些摩擦模型系数。就收敛性和鲁棒性而言，与σ修改算法进行了比较。仿真和实际实验表明了所提出的自适应算法的优越性能。通过所提出的算法在线估算神经网络权重和一些摩擦模型系数。就收敛性和鲁棒性而言，与σ修改算法进行了比较。仿真和实际实验表明了所提出的自适应算法的优越性能。