Nonlinear control of turbofan engines in the flight envelope has attracted much attention in consideration of the inherent nonlinearity of the engine dynamics. Most nonlinear control design techniques rely on the correction theory of reference model parameter to extend the typical flight operations from ground operation. However, dynamic uncertainties in flight envelope lead to the deviation of operating state, and it is negative to control performance. This article is to develop online correction neural network–based speed control approaches for the turbofan engine with dynamic uncertainty in the flight envelope. Two improved online correction nonlinear ways combined with nonlinear autoregressive moving average (NARMA) are proposed, such as gradient search nonlinear autoregressive moving average with feedback linearization (NARMA-L2) control and iterative learning NARMA-L2 control. The contribution of this article is to provide better control quality of fast regulation and less steady errors of engine speed by the proposed methodology in comparison to the conventional NARMA-L2 control. Some important results are reached on both turbofan engine controller design and dynamic uncertainty tolerance at the typical flight operations, and the numerical examples demonstrate the superiority of the proposed control in the flight envelope.

考虑到发动机动力学固有的非线性，涡扇发动机在飞行包线内的非线性控制引起了很多关注。大多数非线性控制设计技术依靠参考模型参数的修正理论将典型的飞行操作从地面操作扩展。然而，飞行包线的动态不确定性导致运行状态的偏差，对控制性能不利。本文旨在为具有飞行包线动态不确定性的涡扇发动机开发基于在线校正神经网络的速度控制方法。提出了两种结合非线性自回归移动平均（NARMA）的改进在线校正非线性方法，例如梯度搜索非线性自回归移动平均与反馈线性化（NARMA-L2）控制和迭代学习NARMA-L2控制。本文的贡献是通过与传统的 NARMA-L2 控制相比，通过所提出的方法提供更好的快速调节控制质量和更少的发动机转速稳定误差。在典型的飞行操作中，涡扇发动机控制器设计和动态不确定性容限都取得了一些重要的结果，数值例子证明了所提出的控制在飞行包线中的优越性。