Real-Time Performance Optimization for a Camber Morphing Wing Based on Domain Incremental Model under Concept Drifting
Abstract
:1. Introduction
2. System Modeling
2.1. Morphing Wing Overview
2.2. Wing Shape Parameterization
2.3. Physical Modeling
2.3.1. Aerodynamic Model
2.3.2. Aeroelastic Model
3. Surrogate Model Construction Methodology
- The computational cost of simulating the wing model is substantial, and wind tunnel or flight tests incur even higher costs.
- Existing aeroelastic coupling methods for the wing are not capable of meeting the real-time optimization demands for aerodynamic performance, while surrogate models offer significantly faster computation.
- Different wing models, such as aerodynamic models, aeroelastic models, and real-wing prototypes, exhibit varying degrees of fidelity. Each model’s data may be subject to concept drift, making one-time data collection insufficient to fully capture the characteristics of the wing accurately.
- Wing optimization should begin with a pre-trained model and continuous improvement of accuracy during the experimental process is necessary.
- Data Source Selection: The surrogate model presented in this paper was initially constructed using aerodynamic simulation data and later updated with aeroelastic simulation data. However, the ideal application of this method is to train the surrogate model with aeroelastic simulation data and then update it with wind tunnel or flight test data.
- Input and Output of the Surrogate Model: In this section, the inputs of the surrogate model are the angle of attack and shape, while the outputs are lift and drag coefficients. However, the surrogate model’s outputs can be expanded to include the lift distribution along the span of the wing, stress–strain distribution of the wing, and other parameters. Such an extension would allow for optimization of the lift distribution along the span and a reduction in maximum stress in the wing’s main beam through subsequent performance optimization tasks.
3.1. Model Architectures
3.2. Offline Static Learning
3.3. Online Incremental Learning
4. Surrogate Model Construction
4.1. Preparation of Training Samples
4.2. Offline Static Learning
- Taking both the accuracy and time consumption into account, the Neural Network (NN) method outperformed the Kernel Model (K) method.
- When the training data size reached 2000, the model achieved good accuracy, and the loss on the validation set was comparable to that on the training set.
- The NN and K models trained with aerodynamic data did not perform well on the aeroelastic data. The difference between the aeroelastic data and the aerodynamic data was approximately 4.23%.
4.3. Online Incremental Learning
- Reference incremental learning strategy 1: First, create an empty neural network structure and incrementally train the neural network from scratch using the aeroelastic data .
- Reference incremental learning strategy 2: Perform incremental learning based on the pre-trained neural network .
5. Aerodynamic Performance Optimization
5.1. Optimization Architecture
5.2. Basic Optimization Methods
5.3. Optimization Methods Based on Surrogate Models
- Control group 1: optimization based on the offline static model .
- Control group 2: optimization based on the offline static model .
- The optimization results for Control group 1 may appear good in the optimizer, but they did not perform well in validation. This is due to the static aerodynamic model and the aeroelastic model having systematic biases, making the optimization results unreliable.
- The optimization results of Control group 2 were more reliable compared to Control group 1; however, due to the inability to correct model fitting errors during the iterations, it was challenging to search for more reliable data near the target point for model updates, resulting in only moderate accuracy.
- The optimization results of our approach showed more stability and repeatability than those based on the static model. Results yielded from multiple repeated experiments of the static model are circled by the dashed line and the dash-dot line in Figure 11.
- The optimization results of our approach based on gradually improved over time. Notably, in the last few iterations, both the model accuracy and optimization results were excellent.
6. Multi-Objective Optimization
6.1. Real-Time Drag Reduction with Varying Target Lift
6.2. Drag and Stress Reduction Simultaneously
6.3. Drag, Stress, and Actuation Energy Reduction Simultaneously
7. Conclusions and Discussion
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Li, D.; Zhao, S.; Da Ronch, A.; Xiang, J.; Drofelnik, J.; Li, Y.; Zhang, L.; Wu, Y.; Kintscher, M.; Monner, H.P.; et al. A review of modelling and analysis of morphing wings. Prog. Aerosp. Sci. 2018, 100, 46–62. [Google Scholar] [CrossRef]
- Chu, L.; Li, Q.; Gu, F.; DU, X.; He, Y.; Deng, Y. Design, modeling, and control of morphing aircraft: A review. Chin. J. Aeronaut. 2022, 35, 220–246. [Google Scholar] [CrossRef]
- Ajaj, R.M.; Parancheerivilakkathil, M.S.; Amoozgar, M.; Friswell, M.I.; Cantwell, W.J. Recent developments in the aeroelasticity of morphing aircraft. Prog. Aerosp. Sci. 2021, 120, 100682. [Google Scholar] [CrossRef]
- Monner, H.P. Realization of an optimized wing camber by using formvariable flap structures. Aerosp. Sci. Technol. 2001, 5, 445–455. [Google Scholar] [CrossRef]
- Woods, B.K.S.; Friswell, M.I. Preliminary Investigation of a Fishbone Active Camber Concept. In Proceedings of the ASME 2012 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, Stone Mountain, GA, USA, 19–21 September 2012; pp. 555–563. [Google Scholar] [CrossRef]
- Wang, D.P.; Bartley-Cho, J.D.; Martin, C.A.; Hallam, B.J. Development of high-rate large-deflection hingeless trailing-edge control surface for the Smart Wing wind tunnel model. In Proceedings of the SPIE’s 8th Annual International Symposium on Smart Structures and Materials, Newport Beach, CA, USA, 4–8 March 2001; pp. 407–418. [Google Scholar] [CrossRef]
- Campanile, L.F.; Sachau, D. The Belt-Rib Concept: A Structronic Approach to Variable Camber. J. Intell. Mater. Syst. Struct. 2000, 11, 215–224. [Google Scholar] [CrossRef]
- Heeb, R.M.; Dicker, M.; Woods, B.K.S. Design Space Exploration and Modelling of GATOR 3D Printed Morphing Skins. In Proceedings of the ASME 2022 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, Dearborn, MI, USA, 12–14 September 2022; pp. 1–10. [Google Scholar] [CrossRef]
- Blok, L.G.; Longana, M.L.; Yu, H.; Woods, B.K.S. An Investigation into 3D Printing of Fibre Reinforced Thermoplastic Composites. Addit. Manuf. 2018, 22, 176–186. [Google Scholar] [CrossRef]
- Mahid, N.M.; Woods, B.K.S. Initial Exploration of a Compliance-Based Morphing Fairing Concept for Hinged Aerodynamic Surfaces. Aerosp. Sci. Technol. 2023, 136, 108244. [Google Scholar] [CrossRef]
- Ahmad, D.; Ajaj, R.M.; Amoozgar, M. Elastomer-Based Skins for Morphing Aircraft Applications: Effect of Biaxial Strain Rates and Prestretch. Polym. Test. 2022, 113, 107655. [Google Scholar] [CrossRef]
- Heeb, R.M.; Dicker, M.; Woods, B.K.S. Manufacturing and Characterisation of 3D Printed Thermoplastic Morphing Skins. Smart Mater. Struct. 2022, 31, 085007. [Google Scholar] [CrossRef]
- Ruland, O.; Mkhoyan, T.; De Breuker, R.; Wang, X. Black-box Online Aerodynamic Performance Optimization for a Seamless Wing with Distributed Morphing. In Proceedings of the AIAA SCITECH 2022 Forum, San Diego, CA, USA, 3–7 January 2022; pp. 1–18. [Google Scholar] [CrossRef]
- Zhang, Z. Optimization Shape Design and Realization of Variable Camber Wing Based on Compliant Mechanisms. Ph.D. Thesis, Politecnico di Milano, Milan, Italy, 2022. [Google Scholar]
- Lyu, Z.; Martins, J.R.R.A. Aerodynamic Shape Optimization of an Adaptive Morphing Trailing-Edge Wing. J. Aircr. 2015, 52, 1951–1970. [Google Scholar] [CrossRef]
- Popov, A.V.; Grigorie, L.T.; Botez, R.; Mamou, M.; Mebarki, Y. Real Time Morphing Wing Optimization Validation Using Wind-Tunnel Tests. J. Aircr. 2010, 47, 1346–1355. [Google Scholar] [CrossRef]
- Ferrier, Y.; Nguyen, N.T.; Ting, E. Real-Time Adaptive Least-Squares Drag Minimization for Performance Adaptive Aeroelastic Wing. In Proceedings of the 34th AIAA Applied Aerodynamics Conference, Washington, DC, USA, 13–17 June 2016; pp. 1–33. [Google Scholar] [CrossRef]
- Yang, Y. Gust Alleviation and Flight Test Validation of High-Aspect-Ratio Flexible Aircraft. Ph.D. Thesis, Beihang University, Beijing, China, 2020. [Google Scholar]
- De Gaspari, A.; Ricci, S. Knowledge-Based Shape Optimization of Morphing Wing for More Efficient Aircraft. Int. J. Aerosp. Eng. 2015, 2015, 325724. [Google Scholar] [CrossRef]
- Kulfan, B.M. Universal Parametric Geometry Representation Method. J. Aircr. 2008, 45, 142–158. [Google Scholar] [CrossRef]
- Boeing A502I User’s Guide-PAN AIR Technology Program for Solving Potential Flow about Arbitrary Configurations. 1992. Available online: https://www.pdas.com/panairrefs.html (accessed on 5 March 2020).
- Carmichael, R.; Erickson, L. PAN AIR—A higher order panel method for predicting subsonic or supersonic linear potential flows about arbitrary configurations. In Proceedings of the 14th Fluid and Plasma Dynamics Conference, Palo Alto, CA, USA, 23–25 June 1981; pp. 1–35. [Google Scholar] [CrossRef]
- Hallissy, B.; Cesnik, C. High-Fidelity Aeroelastic Analysis of Very Flexible Aircraft. In Proceedings of the 52nd AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference, Denver, CO, USA, 4–7 April 2011; pp. 1–22. [Google Scholar] [CrossRef]
- Liu, Y. Aeroelastic Stability and Response Analysis of Very Flexible Aircraft. Ph.D. Thesis, Beihang University, Beijing, China, 2016. [Google Scholar]
- Le, Q.; Sarlós, T.; Smola, A. Fastfood—Approximating Kernel Expansions in Loglinear Time. In Proceedings of the International Conference on Machine Learning, Atlanta, GA, USA, 16–21 June 2013; Volume 85, p. 8. [Google Scholar]
- Rahimi, A.; Recht, B. Random Features for Large-Scale Kernel Machines. Adv. Neural Inf. Process. Syst. 2008, 20, 1177–1184. [Google Scholar]
- Javed, K.; White, M. Meta-Learning Representations for Continual Learning. Adv. Neural Inf. Process. Syst. 2019, 32, 1818–1828. [Google Scholar]
- Wang, L.; Yang, K.; Li, C.; Hong, L.; Li, Z.; Zhu, J. ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 20–25 June 2021; pp. 5383–5392. [Google Scholar] [CrossRef]
- Kirkpatrick, J.; Pascanu, R.; Rabinowitz, N.; Veness, J.; Desjardins, G.; Rusu, A.A.; Milan, K.; Quan, J.; Ramalho, T.; Grabska-Barwinska, A.; et al. Overcoming Catastrophic Forgetting in Neural Networks. Proc. Natl. Acad. Sci. USA 2017, 114, 3521–3526. [Google Scholar] [CrossRef] [PubMed]
- Van de Ven, G.M.; Tolias, A.S. Three Scenarios for Continual Learning. arXiv 2019, arXiv:1904.07734. [Google Scholar] [CrossRef]
- Dharani, G.; Nair, N.G.; Satpathy, P.; Christopher, J. Covariate Shift: A Review and Analysis on Classifiers. In Proceedings of the 2019 Global Conference for Advancement in Technology (GCAT), Bangalore, India, 18–20 October 2019; pp. 1–6. [Google Scholar] [CrossRef]
- Isele, D.; Cosgun, A. Selective experience replay for lifelong learning. In Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA, 2–7 February 2018; Volume 32. [Google Scholar] [CrossRef]
- Regis, R.G.; Shoemaker, C.A. A Stochastic Radial Basis Function Method for the Global Optimization of Expensive Functions. INFORMS J. Comput. 2007, 19, 497–509. [Google Scholar] [CrossRef]
Data Size | NN | K | NN | K | NN | K |
---|---|---|---|---|---|---|
50 | 1.33% | 1.85% | 4.82% | 2.85% | 7.20% | 5.43% |
400 | 0.18% | 2.01% | 0.70% | 1.83% | 4.84% | 4.96% |
2000 | 0.13% | 2.22% | 0.13% | 1.95% | 4.35% | 4.46% |
4000 | 0.13% | 1.67% | 0.13% | 1.62% | 4.37% | 4.46% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Jia, S.; Zhang, Z.; Dang, Q.; Song, C.; Yang, C. Real-Time Performance Optimization for a Camber Morphing Wing Based on Domain Incremental Model under Concept Drifting. Aerospace 2023, 10, 853. https://doi.org/10.3390/aerospace10100853
Jia S, Zhang Z, Dang Q, Song C, Yang C. Real-Time Performance Optimization for a Camber Morphing Wing Based on Domain Incremental Model under Concept Drifting. Aerospace. 2023; 10(10):853. https://doi.org/10.3390/aerospace10100853
Chicago/Turabian StyleJia, Sijia, Zhenkai Zhang, Qi Dang, Chen Song, and Chao Yang. 2023. "Real-Time Performance Optimization for a Camber Morphing Wing Based on Domain Incremental Model under Concept Drifting" Aerospace 10, no. 10: 853. https://doi.org/10.3390/aerospace10100853