基于通用化等效模型的飞机系统辨识算法  

Aircraft system identification algorithm based on generalized equivalent model

作　　者：周大鹏 李贺琦 王业光 王立新[1] ZHOU Dapeng;LI Heqi;WANG Yeguang;WANG Lixin(School of Aeronautic Science and Engineering,Beihang University,Beijing 100191,China;AVIC Shenyang Aircraft Design and Research Institute,Shenyang 110035,China)

机构地区：[1]北京航空航天大学航空科学与工程学院,北京100191 [2]中国航空工业沈阳飞机设计研究所,沈阳110035

出　　处：《北京航空航天大学学报》2024年第5期1454-1462,共9页Journal of Beijing University of Aeronautics and Astronautics

摘　　要：针对舰载机等复杂动力学系统的高阶时滞模型拟配难题,提出了一种基于通用化等效模型的系统频域辨识算法。建立系统辨识通用化等效模型,引入自适应学习率梯度下降法对模型进行基于样本的迭代学习训练,使模型的频域参数自动收敛,辨识得到复杂系统的高阶时滞模型。以舰载机横航向荷兰滚等效拟配模型进行验证,与传统算法对比,并分析了系统的频域与时域响应,结果表明:所提算法具有较好的辨识效果,解决了高阶时滞模型的直接拟配难题,并通用于广泛的高阶时滞模型拟配。This study provides a frequency domain identification approach aimed at the high-order time-delay model matching problem for complex systems like carrier aircraft.A high-order time-delay model of the complex system is ultimately identified after the generalized frequency-domain identification model is established and the model is iteratively trained by system frequency domain response data using the gradient descent method of adaptive learning rate.This allows the model’s frequency domain parameters to automatically converge.Verification is carried out with the Dutch roll equivalent model of carrier aircraft.Through the identification and comparison of high-level and low-level models,the algorithm in this paper is compared with the traditional algorithm,and the frequency domain and time domain analysis show that the algorithm in this paper has a good identification effect.It solves the problem of direct fitting of high-order time-delay models,and is suitable for universal high-order time-delay models.

关 键 词：梯度下降法 频域建模 高阶时滞模型 自适应学习率 等效拟配 

分 类 号：V212.12[航空宇航科学与技术—航空宇航推进理论与工程]