With the progress of high-bypass turbofan and the innovation of silencing nacelle in engine noise reduction, airframe noise has now become another important sound source besides the engine noise. Thus, reducing airframe noise makes a great contribution to the overall noise reduction of a civil aircraft. However, reducing airframe noise often leads to aerodynamic performance loss in the meantime. In this case, an approach based on artificial neural network is introduced. An established database serves as a basis and the training sample of a back propagation （BP） artificial neural network, which uses confidence coefficient reasoning method for optimization later on. Then the most satisfactory configuration is selected for validating computations through the trained BP network. On the basis of the artificial neural network approach, an optimization pro- cess of slat cove filler （SCF） for high lift devices （HLD） on the Trap Wing is presented. Aerody- namic performance of both the baseline and optimized configurations is investigated through unsteady detached eddy simulations （DES）, and a hybrid method, which combines unsteady DES method with acoustic analogy theory, is employed to validate the noise reduction effect. The numerical results indicate not merely a significant airframe noise reduction effect but also excellent aerodynamic performance retention simultaneously.
针对民用客机机翼-机身-平尾构型开展了后缘连续变弯度机翼气动优化设计,并探索了在优化设计中添加俯仰力矩配平约束的必要性.采用自由型面变形(free form deformation,FFD)方法对全机构型进行参数化,可实现机翼型面、后缘弯度和平尾偏转角的改变.采用基于RANS(Reynolds-averaged Navier-Stokes)方程的离散伴随技术求解气动力系数对设计变量的梯度,并采用序列二次规划算法进行基于梯度的气动优化设计.针对CRM(common research model)构型开展了考虑多约束的气动减阻优化设计,验证了优化设计系统的有效性.在此基础上,针对不同巡航升力系数分别进行了考虑和不考虑全机力矩配平约束的变弯度机翼优化设计.优化结果表明,通过机翼后缘变弯度可以改善机翼展向升力系数分布、减小激波强度;为了获得综合最优的减阻设计结果,必须考虑力矩配平约束.
