以S形进气道为研究对象的主动流动控制研究中，流场状况分析对控制器的设计起到至关重要的作用，而在实时控制中，显然不可能通过流场的数值模拟获得流场分布情况。本文从神经网络模型辨识理论出发，结合进气道流场的数值模拟和实验采集数据，对神经网络进行训练和验证，建立了不同来流马赫数下进气道沿程壁面静压的预测模型，证明了从辨 识理论出发建立流场模型的可行性，为流场状况的实时获取提供了可靠易行的方法。

In the research of active flow control of S-shaped inlet, the analysis of flow field plays an important role in the design of the controller. In the real-time control, it is obviously impossible to get the flow through numerical simulation of the flow field Field distribution. Based on the neural network model identification theory and the numerical simulation and experimental data collection of the inlet flow field, the neural network is trained and validated, and the prediction model of the static pressure along the inlet wall of the inlet is established. , Which proves the feasibility of establishing the flow model from the identification theory and provides a reliable and easy method for the real-time acquisition of the flow field.

V219