SummaryAn adaptive optimal controller is proposed in this paper to maximize the captured power of a variable speed wind power system. The proposed controller is a combination of optimal and adaptive control components. The Adaptive Dynamic Programming technique is used to design the optimal control component to overcome the nonlinear problem of system dynamics and ensure stability. While the neural network is used to approximate unknown disturbances and system uncertainties. After that, the adaptive control component fully compensates for the effects of these unknown elements. Neither optimal nor adaptive control components necessitate prior knowledge of system dynamics. Furthermore, the approximation network updates only the weight matrix norm rather than the weight matrix of the neural network in each interval time, which significantly reduces computation. The stability analysis of the closed‐loop system is obtained using Lyapunov stability theory. The correctness and robustness of the control scheme are validated in two different scenarios using MATLAB/Simulink. The presented robust adaptive optimal controller is also compared to other existing controllers to demonstrate its benefits.

中文翻译：

---

变速风力涡轮机系统的最佳捕获功率控制：自适应动态规划方法

摘要本文提出了一种自适应最优控制器，以最大化变速风力发电系统的捕获功率。所提出的控制器是最优和自适应控制组件的组合。采用自适应动态规划技术设计最优控制元件，克服系统动力学的非线性问题，保证稳定性。而神经网络则用于逼近未知的扰动和系统的不确定性。之后，自适应控制组件完全补偿这些未知因素的影响。最优控制组件和自适应控制组件都不需要系统动力学的先验知识。此外，近似网络在每个间隔时间内只更新权重矩阵范数，而不更新神经网络的权重矩阵，这大大减少了计算量。利用Lyapunov稳定性理论对闭环系统进行稳定性分析。使用 MATLAB/Simulink 在两种不同的场景下验证了控制方案的正确性和鲁棒性。所提出的鲁棒自适应最优控制器还与其他现有控制器进行了比较，以证明其优点。