基于深度神经网络的客机总体设计参数敏感性分析

飞机总体主要设计参数敏感性分析揭示了总体主要设计参数对飞机特性指标的影响，有助于总体设计方案的决策。针对宽体客机总体主要设计参数敏感性问题，根据其总体主要设计参数和特性指标的特点，以及多学科间的耦合关系，建立了深度神经网络模型。该深度神经网络模型以客机总体主要设计参数为输入，对特性指标进行预测。在深度神经网络模型中，设置了多个输入层、多个输出层以及多个分块的隐藏层，从而模拟客机总体主要设计参数对特性指标的影响以及不同特性指标之间的相互作用。测试结果表明，与传统代理模型相比，深度神经网络模型对客机特性指标的预测精度更高，多参数适应性更好。利用该深度神经网络模型对客机总体主要设计参数进行敏感性分析。分析结果表明，机翼1/4弦线后掠角在30°~31.5°时，有利于减少最大起飞重量和起飞平衡场长；发动机海平面最大静推力和机翼面积对客机直接使用成本、最大起飞重量等特性指标的影响最为显著。

Sensitivity analysis of key design parameters of commercial aircraft using deep neural network

The sensitivity analysis of key design parameters of aircraft reveals the relationship between the key design parameters and aircraft characteristics, facilitating the decision making in aircraft preliminary design. Aiming at the key design parameter sensitivity of wide-body commercial aircraft, we establish a deep neural network model based on the features of key design parameters and aircraft characteristics and the coupling relationship among multiple disciplines, taking the key design parameters as input to predict the aircraft characteristics. In this model, multiple input layers, multiple output layers, and multiple blocks of hidden layers are set to simulate the effects of key design parameters on aircraft characteristics and the interactions among different aircraft characteristics. Comparisons with traditional surrogate models reveal that the deep neural network model has higher prediction accuracy and better adaptability to the aircraft characteristics. The proposed model is then used to analyze the sensitivity of the commercial aircraft primary parameters. The analysis results show that a lower maximum takeoff weight and a shorter takeoff balanced field length can be achieved when the wing sweep at 1/4 chord is between 30° to 31.5°. The maximum static thrust of engines at sea level and the wing area have the most significant influence on the direct operation cost, maximum takeoff weight, and other characteristics.