The conceptual design phase of aircraft requires extensive analysis and comparison of the aerodynamic performance for numerous configuration candidates. High-fidelity methods like Computational Fluid Dynamics (CFD) are computationally prohibitive. Rapid analysis tools like the Vortex Lattice Method (VLM) often fail to meet accuracy requirements. Single-Fidelity Data-Driven surrogate models, which directly map geometric design variables to aerodynamic characteristics, suffer from prediction accuracy that is heavily dependent on the size and selection of training samples. To address the trade-off between computational accuracy, efficiency, and sample size, this study proposes a rapid aerodynamic prediction method that fuses multi-fidelity data from VLM and CFD simulations. Based on a Radial Basis Function Neural Network (RBFNN), the framework employs VLM to obtain low-fidelity aerodynamic parameters efficiently. These parameters, together with the original design variables, Mach number, and wetted surface area, form the enhanced input vector to improve the model's understanding of aerodynamic. The network is trained to predict the discrepancy between the multi-fidelity data. This approach significantly reduces the required number of high-fidelity training samples and improves computational efficiency. The method is validated using a Lambda-Wing UAV dataset. The results show that with 25 training samples, the UAV’s high-fidelity aerodynamic parameters can be accurately predicted. The prediction accuracy for all parameters outperforms that of single-source data-driven surrogate models, and is comparable to the co-Kriging method—with certain parameters even demonstrating superior prediction performance. Further validation against three typical engineering scenarios confirms the method's general applicability. The relative prediction error for aerodynamic coefficients remains within 3%, while the computational time is reduced by two orders of magnitude. The fusion method is applied to the optimization of the Lambda-wing UAV scheme. The cruise lift-to-drag ratio of the optimal scheme is increased by 11.6%, and the predicted relative error was less than 1.2%. This effectively enhanced the design efficiency and holds certain prospects for engineering application.
[1] MOHAMMAD H. SADRAEY. Aircraft Design A Systems Engineering Approach[M]. A John Wiley & Sons, Ltd., Publication, 2013: 4-8.
[2] CHEN X J, QIU Z P, WANG X J, et al. Uncertain reduced-order modeling for unsteady aerodynamics with interval parameters and its application on ro-bust flutter boundary prediction[J]. Aerospace Sci-ence and Technology, 2017, 71: 214–230.
[3] JOSHI H, THOMAS P. Review of vortex lattice method for supersonic aircraft design[J]. The Aero-nautical Journal, 2023, 127(1317): 1869–1903.
[4] LARRY L. ERICKSON. Panel Methods-An Intro-duction[R]. NASA TP-2995, Moffett Field, Califor-nia: Ames Reasearch Center, 1990.
[5] 李霓, 布树辉, 尚柏林, 等. 飞行器智能设计愿景与关键问题[J]. 航空学报, 2021, 42(4): 207–224.
LI N, Bu S H, SHANG B L, et al．Aircraft intelli-gent design：visions and key technologies[J]．Acta Aeronautica et Astronautica Sinica, 2021, 42(4)： 524752 (in Chinese).
[6] ZHANG W W, XIA M K, KOU J Q. A Scientometric Investigation of Artificial Intelligence for Fluid Me-chanics: Emerging Topics and Active Groups[J]. Progress in Aerospace Sciences, 2025, 157: 101130.
[7] SLOTNICK J P, KHODADOUST A, ALONSO J, et al. CFD Vision 2030 Study: A Path to Revolutionary Computational Aerosciences[R]. NF1676L-18332, 2014.
[8] WANG S, LIU Y, ZHOU Q, et al. A multi-fidelity surrogate model based on moving least squares: fus-ing different fidelity data for engineering design[J]. Structural and Multidisciplinary Optimization, 2021, 64(6): 3637–3652.
[9] FORRESTER A I J, SóBESTER A, KEANE A J. Multi-fidelity optimization via surrogate model-ling[J]. Proceedings of the Royal Society A: Mathe-matical, Physical and Engineering Sciences, 2007, 463(2088): 3251–3269.
[10] KEANE A J. Wing Optimization Using Design of Experiment, Response Surface, and Data Fusion Methods[J]. Journal of Aircraft, 2003, 40(4): 741–750.
[11] NAGAWKAR J, LEIFSSON L. Multifidelity aerody-namic flow field prediction using random forest-based machine learning[J]. Aerospace Science and Technology, 2022, 123: 107449.
[12] ZHAO S L, ZHANG W W. Euler equation embedded machine learning method for wall pressure and skin friction distribution[J]. Engineering Applications of Computational Fluid Mechanics, Taylor & Francis, 2025, 19(1): 2556450.
[13] ZHANG X S, XIE F F, JI T W, et al. Multi-fidelity deep neural network surrogate model for aerodynam-ic shape optimization[J]. Computer Methods in Ap-plied Mechanics and Engineering, 2021, 373: 113485.
[14] WANG Y T, LI K P, LI Q Y, et al. Multi-fidelity in-formation fusion with hierarchical surrogate guided by feature mapping[J]. Knowledge-Based Systems, 2023, 275: 110693.
[15] 张俊杰, 黄俊, 刘志勤, 等. 基于迁移学习的变可信度气动力建模方法[J]. 实验流体力学, 2025, 39(4): 93–103.
ZHANG J J, HUANG J, LIU Z Q, et al. Variable fidelity aerodynamic modeling method based on transfer learning[J]. Journal of Experiments in Fluid Mechanics, 2025, 39(4): 93-103. (in Chinese).
[16] 王雨桐, 罗骁, 刘红阳, 等. 基于多保真深度神经网络的超声速客机声爆预测[J]. 航空学报, 2025, 46(20): 73–93.
WANG Y T, LUO X, LIU H Y, et al. Sonic boom prediction of supersonic passenger aircraft based on multi-fidelity deep neural network[J]. Acta Aero-nautica et Astronautica Sinica，2025，46(20)：531936 (in Chinese).
[17] LE J L, YANG M T, GUO M M, et al. Progress and prospects of artificial intelligence development and applications in supersonic flow and combustion[J]. Progress in Aerospace Sciences, 2024, 151: 101046.
[18] KOU J Q, ZHANG W W. Multi-fidelity modeling framework for nonlinear unsteady aerodynamics of airfoils[J]. Applied Mathematical Modelling, 2019, 76: 832–855.
[19] KOU J Q, ZHANG W W. Multi-kernel neural net-works for nonlinear unsteady aerodynamic reduced-order modeling[J]. Aerospace Science and Technolo-gy, 2017, 67: 309–326.
[20] 王晓军. 基于大数据的风洞马赫数集成建模方法的研究[M]. 大连: 东北财经大学出版社, 2024: 40-63.
WANG X J. The Research of Ensemble Method Based on Big Data for the Mach Number Prediction in Wind Tunnel[M].Dalian: Dongbei University of Finance & Economics Press, Dalian, 2024: 40-63. (in Chinese)
[21] ZOU Z C, XIE C C, AN C, et al. Development of Accelerated CFD/CSD Coupling Nonlinear Static Aeroelastic Algorithm Using Vortex Lattice Meth-od[J]. AIAA Journal, 2025, 63(6): 2568–2573.
[22] 施英杰, 刘斌超, 鲁嵩嵩, 等. 融合“试验-仿真”标定数据的机翼应变载荷关系神经网络模型[J]. 航空学报, 2025, 46(19): 530921.
SHI Y J, LIU B C, LU S S, et al. Neural network model for wing strain-load relationship by fusing real data and virtual data [J]. Acta Aeronautica et Astro-nautica Sinica, 2025, 46(19): 530921. (in Chinese).
[23] WANG X, HUANG R Q, KOU J Q, et al. Goal-Oriented Feature Extraction: A Novel Approach to Enhance Data-Driven Surrogate Models[J]. AIAA Journal, 2025: 1–15.
[24] HAI C L, WANG J Z, GUO S M, et al. Online multi-fidelity data aggregation via hierarchical neural net-work[J]. Computer Methods in Applied Mechanics and Engineering, 2025, 437: 117795.
[25] SUN G Y, LI G Y, GONG Z H, et al. Radial basis functional model for multi-objective sheet metal forming optimization[J]. Engineering Optimization, 2011, 43(12): 1351–1366.
[26] ZHOU Q, JIANG P, SHAO X Y, et al. A variable fidelity information fusion method based on radial basis function[J]. Advanced Engineering Informatics, 2017, 32: 26–39.
[27] JIN R, CHEN W, SIMPSON T W. Comparative stud-ies of metamodelling techniques under multiple modelling criteria[J]. Structural and Multidiscipli-nary Optimization, 2001, 23(1): 1–13.
[28] FANG H B, HORSTEMEYER M F. Global response approximation with radial basis functions[J]. Engi-neering Optimization, Taylor & Francis, 2006, 38(4): 407–424.
[29] 武泽平, 王志祥, 张为华. 数据驱动的近似建模方法及应用[M]. 北京: 国防工业出版社, 2023: 31-35.
Wu Z P, WANG Z X, ZHANG W H, Data_Driven Metamodeling Methods and Applications[M]. Bei-jing: National Defense Industry Press, 2023: 31-35 (in Chinese).
[30] SONG L, YANG H, XIE J F, et al. Method for Im-proving the Natural Lateral-Directional Stability of Flying Wings[J]. Journal of Aerospace Engineering, 2016, 29(5): 06016003.
[31] 宋磊. 涡格法计算软件VLM513[EB/OL]. https://teacher.buaa.edu.cn/songlei/zh_CN/jxzy/20673/content/1167.htm#jxzy.
SONG L. Vortex-lattice method calculation software VLM513[EB/OL]. https://teacher.buaa.edu.cn/songlei/zh_CN/jxzy/20673/content/1167.htm#jxzy. (in Chinese)
[32] DANIEL P. RAYMER. Aircraft design: A conceptual approach[M]. Washington, D.C.: American Institute of Aeronautics and Astronautics, Inc, 1989: 280-282.
[33] 国家数值风洞. CHN-F1飞翼亚跨声速标模[EB/OL]. CHN-F1飞翼亚跨声速标模. https://nnw-vvdb.nssdc.ac.cn:8443/VVDB/doSSOLoginNew.rdm.
National Numerical Wind Tunnel, CHN-F1 Flying Wing subsonic scale module data[EB/OL]. CHN-F1 Fly. Wing Subsonic Scale Module Data. https://nnw-vvdb.nssdc.ac.cn:8443/VVDB/doSSOLoginNew.rdm (in Chinese)
CJA