IEEE Trans Neural Netw Learn Syst. 2018 Jun;29(6):2179-2191. doi: 10.1109/TNNLS.2018.2810138.
This paper investigates the problem of optimal fault-tolerant control (FTC) for a class of unknown nonlinear discrete-time systems with actuator fault in the framework of adaptive critic design (ACD). A pivotal highlight is the adaptive auxiliary signal of the actuator fault, which is designed to offset the effect of the fault. The considered systems are in strict-feedback forms and involve unknown nonlinear functions, which will result in the causal problem. To solve this problem, the original nonlinear systems are transformed into a novel system by employing the diffeomorphism theory. Besides, the action neural networks (ANNs) are utilized to approximate a predefined unknown function in the backstepping design procedure. Combined the strategic utility function and the ACD technique, a reinforcement learning algorithm is proposed to set up an optimal FTC, in which the critic neural networks (CNNs) provide an approximate structure of the cost function. In this case, it not only guarantees the stability of the systems, but also achieves the optimal control performance as well. In the end, two simulation examples are used to show the effectiveness of the proposed optimal FTC strategy.
本文研究了一类具有执行器故障的未知非线性离散时间系统的最优容错控制（FTC）问题，该系统基于自适应评论家设计（ACD）框架。一个关键的亮点是执行器故障的自适应辅助信号，它旨在抵消故障的影响。所考虑的系统采用严格反馈形式，涉及未知的非线性函数，这将导致因果问题。为了解决这个问题，通过微分同胚理论将原始非线性系统转换为一个新系统。此外，在回溯设计过程中，动作神经网络（ANNs）用于逼近预定的未知函数。结合策略效用函数和 ACD 技术，提出了一种强化学习算法来建立最优 FTC，其中评论家神经网络（CNNs）提供了成本函数的近似结构。在这种情况下，它不仅保证了系统的稳定性，而且还实现了最优的控制性能。最后，通过两个仿真示例验证了所提出的最优 FTC 策略的有效性。
