近年來興起的機器學習演算法涉及大量的超參數調整，為了高效地使用這些演算法，工程師需要選擇合適的超參數值，而貝葉斯最佳化是一種常用於調整機器學習演算法的超參數或是一般參數最佳化的方法。本研究採用貝葉斯最佳化演算法作為結構最佳化的演算法，以有效率地方式搜索龐大的設計空間，找出複材壓力容器在不同製程和不同安全係數下的最輕設計。
本研究整合了商用有限元素軟體ABAQUS與貝葉斯最佳化演算法架構針對兩個航太工程問題進行最佳化。首先，針對具有不同邊界條件和幾何形狀的四邊形疊層板的層疊順序做最佳化，以實現最大基本頻率從而避免低頻共振，並作為貝葉斯最佳化演算法在實際應用上的驗證。其次，整合參數化模擬纏繞模式與複材壓力容器分析腳本於最佳化架構中，利用連續纖維纏繞與自動化纖維鋪放兩種複材壓力容器的製程技術，對複材壓力容器的重量進行減重，以提高火箭運載酬載的效率和降低運輸成本。
透過分析的結果可以顯露出最佳化對於連續纖維纏繞的重要性，並進一步解釋為何國外的航太科技強國不使用連續纖維纏繞作為大型運輸火箭的複材壓力容器的原因。

In recent years, the rise of machine learning algorithms involves a substantial amount of hyperparameter tuning. To effectively use these algorithms, engineers need to select appropriate hyperparameter values. Bayesian optimization is a commonly used method for tuning hyperparameters or general parameters of machine learning algorithms. This study adopts the Bayesian optimization algorithm as a structural optimization tool to efficiently search the vast design space and identify the lightest design for composite pressure vessels under different manufacturing processes and safety factors.
This research utilizes an integrated framework of commercial finite element software ABAQUS and Bayesian optimization algorithm to optimize two aerospace engineering problems. Firstly, the stacking sequence of quadrilateral laminate plates with different boundary conditions and geometries is optimized to achieve the maximum fundamental frequency, thereby avoiding low-frequency resonance, and serves as a validation for the practical application of the Bayesian optimization algorithm. Secondly, by integrating parameterized simulation winding patterns and composite pressure vessel analysis scripts into the optimization framework, the research employs filament winding and automated fiber placement technologies to reduce the weight of composite pressure vessels, thus improving the payload efficiency of rockets and reducing transportation costs.
The analysis results reveal the importance of optimization for continuous fiber winding and further explain why leading aerospace technology nations do not use continuous fiber winding for large transport rocket composite pressure vessels.

1. Narita, Y., Layerwise optimization for the maximum fundamental frequency of laminated composite plates. Journal of Sound and Vibration, 2003. 263(5): p. 1005-1016.
2. Apalak, M.K., D. Karaboga, and B. Akay, The Artificial Bee Colony algorithm in layer optimization for the maximum fundamental frequency of symmetrical laminated composite plates. Engineering Optimization, 2013. 46(3): p. 420-437.
3. Wang, W., et al., Stacking sequence optimization of arbitrary quadrilateral laminated plates for maximum fundamental frequency by hybrid whale optimization algorithm. Composite Structures, 2023. 310.
4. Abreu, S., Automated Architecture Design for Deep Neural Networks. CoRR, 2019. abs/1908.10714.
5. Bergstra, J., et al., Algorithms for hyper-parameter optimization, in Proceedings of the 24th International Conference on Neural Information Processing Systems. 2011, Curran Associates Inc.: Granada, Spain. p. 2546–2554.
6. Bergstra, J. and Y. Bengio, Random search for hyper-parameter optimization. J. Mach. Learn. Res., 2012. 13(null): p. 281–305.
7. Matosevic, A. and J. Nordqvist, On Bayesian optimization and its application to hyperparameter tuning. 2018.
8. Yamaguchi, K., et al., Ply-drop design of non-conventional laminated composites using Bayesian optimization. Composites Part A: Applied Science and Manufacturing, 2020. 139.
9. Shahriari, B., et al., Taking the Human Out of the Loop: A Review of Bayesian Optimization. Proceedings of the IEEE, 2016. 104(1): p. 148-175.
10. Garnett, R., Bayesian optimization. 2023: Cambridge University Press.
11. Douglas, Z. and H. Wang. Bayesian optimization-derived batch size and learning rate scheduling in deep neural network training for head and neck tumor segmentation. in 2022 IEEE 10th International Conference on Healthcare Informatics (ICHI). 2022.
12. Vardhan, H., et al., Constrained Bayesian Optimization for Automatic Underwater Vehicle Hull Design. Proceedings of Cyber-Physical Systems and Internet of Things Week 2023, 2023.
13. Xu, H., et al., Tuning Bayesian optimization for materials synthesis: simulating two- and three-dimensional cases. Science and Technology of Advanced Materials: Methods, 2023. 3(1).
14. Chuang, P.-J., et al., Algorithmic Optimization of Transistors Applied to Silicon LDMOS. IEEE Access, 2023.
15. Kolli, S., B.R. Parvathala, and A.V.P. Krishna, A novel liver tumor classification using improved probabilistic neural networks with Bayesian optimization. e-Prime - Advances in Electrical Engineering, Electronics and Energy, 2024. 8: p. 100514.
16. Ide, Y., et al., Development and improvement of a method for determining the worst-case typhoon path for storm surge deviation through Bayesian optimization. Engineering Applications of Artificial Intelligence, 2024. 132: p. 107950.
17. Bessa, M.A. and S. Pellegrino, Design of ultra-thin shell structures in the stochastic post-buckling range using Bayesian machine learning and optimization. International Journal of Solids and Structures, 2018. 139-140: p. 174-188.
18. Finley, J.M., M.S.P. Shaffer, and S. Pimenta, Data-driven intelligent optimisation of discontinuous composites. Composite Structures, 2020. 243.
19. Hu, W., et al., Design optimization of composite wind turbine blades considering tortuous lightning strike and non-proportional multi-axial fatigue damage. Engineering Optimization, 2020. 52(11): p. 1868-1886.
20. Valladares, H. and A. Tovar, Multilevel Design of Sandwich Composite Armors for Blast Mitigation using Bayesian Optimization and Non-Uniform Rational B-Splines. SAE International Journal of Advances and Current Practices in Mobility, 2021. 3(4): p. 2146-2158.
21. Chuaqui, T.R.C., et al., A data-driven Bayesian optimisation framework for the design and stacking sequence selection of increased notched strength laminates. Composites Part B: Engineering, 2021. 226.
22. Ghiasi, H., D. Pasini, and L. Lessard, Optimum stacking sequence design of composite materials Part I: Constant stiffness design. Composite Structures, 2009. 90(1): p. 1-11.
23. Roque, C.M.C. and P.A.L.S. Martins, Maximization of fundamental frequency of layered composites using differential evolution optimization. Composite Structures, 2018. 183: p. 77-83.
24. Kalita, K., R.K. Ghadai, and S. Chakraborty, A comparative study on the metaheuristic-based optimization of skew composite laminates. Engineering with Computers, 2021. 38(4): p. 3549-3566.
25. Azeem, M., et al., Application of Filament Winding Technology in Composite Pressure Vessels and Challenges: A Review. Journal of Energy Storage, 2022. 49.
26. Vickers, J., Composite Cryotank Technologies and Demonstration.pdf. 2015: George C. Marshall Space Flight Center Research and Technology Report 2014.
27. McCarville, D.A., et al., 3.5 Design, Manufacture and Test of Cryotank Components, in Comprehensive Composite Materials II, P.W.R. Beaumont and C.H. Zweben, Editors. 2018, Elsevier: Oxford. p. 153-179.
28. Air, A., M. Shamsuddoha, and B. Gangadhara Prusty, A review of Type V composite pressure vessels and automated fibre placement based manufacturing. Composites Part B: Engineering, 2023. 253.
29. Ebermann, M., et al., Analytical and numerical approach to determine effective diffusion coefficients for composite pressure vessels. Composite Structures, 2022. 291: p. 115616.
30. Oromiehie, E., et al., Automated fibre placement based composite structures: Review on the defects, impacts and inspections techniques. Composite Structures, 2019. 224.
31. Alam, S., et al., Design and development of a filament wound composite overwrapped pressure vessel. Composites Part C: Open Access, 2020. 2.
32. Liu, P.F., L.J. Xing, and J.Y. Zheng, Failure analysis of carbon fiber/epoxy composite cylindrical laminates using explicit finite element method. Composites Part B: Engineering, 2014. 56: p. 54-61.
33. Onder, A., et al., Burst failure load of composite pressure vessels. Composite Structures, 2009. 89(1): p. 159-166.
34. Rafiee, R. and M.A. Torabi, Stochastic prediction of burst pressure in composite pressure vessels. Composite Structures, 2018. 185: p. 573-583.
35. Wu, Q.G., et al., Stress and Damage Analyses of Composite Overwrapped Pressure Vessel. Procedia Engineering, 2015. 130: p. 32-40.
36. Wu, J., et al., Hyperparameter Optimization for Machine Learning Models Based on Bayesian Optimizationb. Journal of Electronic Science and Technology, 2019. 17(1): p. 26-40.
37. Murphy, K.P., Machine Learning, second edition: A Probabilistic Perspective. 2020: MIT Press.
38. Bilionis, I. Introduction to Scientific Machine Learning (Lecture Book). 2022; Available from: https://predictivesciencelab.github.io/data-analytics-se/index.html.
39. Rasmussen, C.E. and C.K.I. Williams, Gaussian Processes for Machine Learning. 2005: The MIT Press.
40. Frazier, P., A Tutorial on Bayesian Optimization. ArXiv, 2018. abs/1807.02811.
41. Mockus, J., V. Tiesis, and A. Zilinskas, The application of Bayesian methods for seeking the extremum. 2014. p. 117-129.
42. Wang, X., et al., Recent Advances in Bayesian Optimization. ACM Comput. Surv., 2023. 55(13s): p. Article 287.
43. Jones, D.R., M. Schonlau, and W.J. Welch, Efficient Global Optimization of Expensive Black-Box Functions. Journal of Global Optimization, 1998. 13(4): p. 455-492.
44. Mockus, J. On Bayesian Methods for Seeking the Extremum. in Optimization Techniques. 1974.
45. Gardner, J.R., et al., Bayesian optimization with inequality constraints, in Proceedings of the 31st International Conference on International Conference on Machine Learning - Volume 32. 2014, JMLR.org: Beijing, China. p. II–937–II–945.
46. Corp, D.S. ABAQUS/Standard User's Manual 2020.
47. Arora, J.S., Introduction to Optimum Design. 2016: Elsevier Science.
48. Adorio, E.P. and R. January. MVF - Multivariate Test Functions Library in C for Unconstrained Global Optimization. 2005.
49. Xiang, S., et al., Thin plate spline radial basis functions for vibration analysis of clamped laminated composite plates. European Journal of Mechanics - A/Solids, 2010. 29(5): p. 844-850.
50. Zamani, M., A. Fallah, and M.M. Aghdam, Free vibration analysis of moderately thick trapezoidal symmetrically laminated plates with various combinations of boundary conditions. European Journal of Mechanics - A/Solids, 2012. 36: p. 204-212.
51. Zhang, H., et al., A simple first-order shear deformation theory for vibro-acoustic analysis of the laminated rectangular fluid-structure coupling system. Composite Structures, 2018. 201: p. 647-663.
52. Jones, H.W., The Recent Large Reduction in Space Launch Cost.pdf, in International Conference on Environmental Systems (ICES). 2018: Albuquerque, NM, United States.
53. Jun-Xu, C., Variable-fidelity Laminate Definition for Composite Overwrapped Pressure Vessels. 2024, National Cheng-Kung University.
54. Yu-Xuan, W., Advanced Analysis Techniques for Continuous Fiber Reinforced Pressure Vessel. 2024, National Cheng-Kung University.