請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/57883
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 陳俊杉(Chuin-Shan Chen) | |
dc.contributor.author | Sung-Lin Tsai | en |
dc.contributor.author | 蔡松霖 | zh_TW |
dc.date.accessioned | 2021-06-16T07:09:25Z | - |
dc.date.available | 2021-01-01 | |
dc.date.copyright | 2020-08-24 | |
dc.date.issued | 2020 | |
dc.date.submitted | 2020-08-17 | |
dc.identifier.citation | Abueidda, D. W., Almasri, M., Ammourah, R., Ravaioli, U., Jasiuk, I. M., Sobh, N. A. (2019). Prediction and optimization of mechanical properties of composites using convolutional neural networks. Composite Structures, 227. Barthelat, F., Mirkhalaf, M. (2013). The quest for stiff, strong and tough hybrid materials: An exhaustive exploration. Journal of the Royal Society Interface, 10(89). Bekah, S., Rabiei, R., Barthelat, F. (2012). The Micromechanics of Biological and Biomimetic Staggered Composites. Journal of Bionic Engineering, 9(4), 446–456. Benyus, J. M. (2002). Biomimicry: innovation inspired by nature. New York: Perennial. Carpinteri, A., Accornero, F. (2018). Multiple snap-back instabilities in progressive microcracking coalescence. Engineering Fracture Mechanics, 187, 272–281. Chen, P. Y., Lin, A. Y., Lin, Y. S., Seki, Y., Stokes, A. G., Peyras, J., Olevsky, E. A., Meyers, M. A., McKittrick, J. (2008). Structure and mechanical properties of selected biological materials. Journal of the Mechanical Behavior of Biomedical Materials, 1(3), 208–226. Chollet, F. (2017). Deep Learning with Python. USA: Manning Publications Co., 1st ed. Council, N. R. (2009). A New Biology for the 21st Century. National Academies Press. Domingos, P. (2012). A few useful things to know about machine learning. Communications of the ACM, 55(10), 78–87. Espinosa, H. D., Rim, J. E., Barthelat, F., Buehler, M. J. (2009). Merger of structure and material in nacre and bone - Perspectives on de novo biomimetic materials. Progress in Materials Science, 54(8), 1059–1100. Gao, H., Ji, B., Jäger, I. L., Arzt, E., Fratzl, P. (2003). Materials become insensitive to flaws at nanoscale: Lessons from nature. Proceedings of the National Academy of Sciences of the United States of America, 100(10), 5597–5600. Goldberg, D. E. (1989). Genetic Algorithms in Search, Optimization and Machine Learn- ing. USA: Addison-Wesley Longman Publishing Co., Inc., 1st ed. Gu, G. X., Chen, C. T., Buehler, M. J. (2018). De novo composite design based on machine learning algorithm. Extreme Mechanics Letters, 18, 19–28. Huang, T. H., Chen, C. S., Chang, S. W. (2018). Microcrack patterns control the mechanical strength in the biocomposites. Materials and Design, 140, 505–515. Jäger, I., Fratzl, P. (2000). Mineralized collagen fibrils: A mechanical model with a staggered arrangement of mineral particles. Biophysical Journal, 79(4), 1737–1746. LeCun, Y., Kavukcuoglu, K., Farabet, C. (2010). Convolutional networks and applications in vision. In ISCAS 2010 - 2010 IEEE International Symposium on Circuits and Systems: Nano-Bio Circuit Fabrics and Systems, (pp. 253–256). Lee, H. (2018). Simulation and Analysis of Mechanical Properties for Bioinspired Structural Material - Cellular Structure and Nacre-inspired Composite. Master’s thesis, National Taiwan University, Taipei, Taiwan. Li, J., Meng, S., Tian, X., Song, F., Jiang, C. (2012a). A non-local fracture model for composite laminates and numerical simulations by using the FFT method. Composites Part B: Engineering, 43(3), 961–971. Li, J., Tian, X. X., Abdelmoula, R. (2012b). A damage model for crack prediction in brittle and quasi-brittle materials solved by the FFT method. International Journal of Fracture, 173(2), 135–146. Libonati, F., Buehler, M. J. (2017). Advanced Structural Materials by Bioinspiration. Advanced Engineering Materials, 19(5), 1600787. Lopez Pinaya, W. H., Vieira, S., Garcia-Dias, R., Mechelli, A. (2020). Convolutional neural networks. In Machine Learning, (pp. 173–191). Elsevier. Meyers, M. A., Chen, P. Y. (2014). Biological materials science: Biological materials, bioinspired materials, and biomaterials. Cambridge University Press. Moulinec, H., Suquet, P. (1998). A numerical method for computing the overall response of nonlinear composites with complex microstructure. Computer Methods in Applied Mechanics and Engineering, 157(1-2), 69–94. Nair, V., Hinton, G. E. (2010). Rectified linear units improve Restricted Boltzmann machines. In ICML 2010 - Proceedings, 27th International Conference on Machine Learning, (pp. 807–814). Naleway, S. E., Porter, M. M., McKittrick, J., Meyers, M. A. (2015). Structural Design Elements in Biological Materials: Application to Bioinspiration. Advanced Materials, 27(37), 5455–5476. Noh, J., Gu, G. H., Kim, S., Jung, Y. (2020). Machine-enabled inverse design of inorganic solid materials: promises and challenges. Chemical Science, 11(19), 4871– 4881. Ritchie, R. O. (2011). The conflicts between strength and toughness. Nature Materials, 10(11), 817–822. The MathWorks, I. (n.d.). Convolutional Neural Network. https://www.mathworks. com/solutions/deep-learning/convolutional-neural-network.html. Ac- cessed: 2020-08-16. Venter, C., Cohen, D. (2004). The Century of Biology. New Perspectives Quarterly, 21(4), 73–77. Wegst, U. G., Bai, H., Saiz, E., Tomsia, A. P., Ritchie, R. O. (2015). Bioinspired structural materials. Nature Materials, 14(1), 23–36. Wegst, U. G. K., Ashby, M. F. (2004). The mechanical efficiency of natural materials. Philosophical Magazine, 84(21), 2167–2186. Yu, C. H., Qin, Z., Buehler, M. J. (2019). Artificial intelligence design algorithm for nanocomposites optimized for shear crack resistance. Nano Futures, 3(3), 035001. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/57883 | - |
dc.description.abstract | 本研究針對珍珠母啟發微結構複合材料建立了一套以機器學習驅動的材料性質最佳化設計系統,希望能在強度及韌性之間的衝突以及廣大設計空間中找到符合目標材料性質的微結構設計。材料的設計與發展從古至今一直以來都與我們日常生活息息相關。近年來,隨著電腦模擬、3D列印以及機器學習等先進技術不斷蓬勃發展,設計材料所能拓展的層面也越來越廣。因此,如何在廣泛的可能性中找尋新穎、符合需求的材料設計,是本研究主要的研究動機。
本研究首先分別訓練了卷積神經網絡(CNN)預測模型,預測珍珠母啟發設計空間中微結構的最大強度以及韌性(吸收能量),藉此建立微結構以及材料性質之間的關聯性。強度預測模型準確度高達99%,而韌性預測模型亦有80%。因此,將預測模型作為快速篩選的工具,結合基因演算法(GA),探索以珍珠母啟發,可能組合高達10^10的設計空間。為了找尋既堅固又堅韌的微結構,本篇研究中針對不同的材料性質進行單目標及多目標的最佳化。在額外條件硬材體積分率0.95的限制下,透過結合機器學習與多目標最佳化演算法,設計出的微結構強度從129.7增加到150.0 MPa,韌性從0.095增加到0.123 mJ/mm^3。最後,本研究亦訓練了變分自動編碼器(VAE)模型,以建立珍珠質啟發設計空間和潛在空間之間的轉換關係,進而擴展設計更多可能性。 | zh_TW |
dc.description.abstract | In this research, a machine learning-enabled optimized design system for nacre-inspired microstructural composites is developed to tackle the conflict between strength and toughness and the challenge of design space exploration. The development of materials is always an essential issue that deeply affects our daily life. Recently, owing to the continuous advances in computational simulation, 3-D printing experiments, and machine learning techniques, the process of material design has been elevated to a new level.
This study first creates linkages between microstructure representations and material properties by respectively training convolutional neural networks (CNN) predictive models for ultimate strength and toughness (absorbed energy) with a nacre-inspired dataset of combinations of soft and stiff materials up to 10^10 order derived from computational simulations. An impressive 99% accuracy for ultimate strength prediction and 80% accuracy for toughness prediction are achieved. Accordingly, served as high-throughput mapping tools, predictive models were implemented in conjunction with genetic algorithm (GA) to explore nacre-inspired design space for obtaining microstructural designs with target properties in the image size of 512 by 512. Single objective and multi-objective optimization tasks were conducted to find microstructures that are both strong and tough. For volume fraction ratio of hard material 0.95, strength increases from 129.7 to 150.0 MPa, and toughness increases from 0.095 to 0.123 mJ/mm^3, through machine-learning enabled multi-objective microstructural design. Last but not least, a variational autoencoder (VAE) model is trained for bridging between nacre-inspired design space and a latent space, which broadens the design. | en |
dc.description.provenance | Made available in DSpace on 2021-06-16T07:09:25Z (GMT). No. of bitstreams: 1 U0001-1607202012141300.pdf: 16766727 bytes, checksum: 0a08d79a8c35bd4f2d04732e6cb85345 (MD5) Previous issue date: 2020 | en |
dc.description.tableofcontents | 口試委員審定書 i 誌謝 iii 中文摘要 v Abstract vii Table of Contents ix List of Figures xiii List of Tables xvii Chapter 1 Introduction 1 1.1 Background and Motivation 1 1.2 Literature Reviews 6 1.3 Objectives of the Thesis 10 1.4 Organization of the Thesis 11 Chapter 2 Materials and Methods 13 2.1 Nacre-inspired Dataset 13 2.1.1 Nacre-inspired design space 13 2.1.2 Material properties - data labeling 14 2.2 Machine Learning Approaches 18 2.2.1 Basic concepts of machine learning 18 2.2.2 Deep learning 19 2.2.3 Convolutional neural networks (CNN) 21 2.2.4 Performance metrics 24 2.3 Optimization Algorithm - Genetic Algorithm (GA) 24 Chapter 3 Machine Learning Models 27 3.1 Dataset Preparation 27 3.2 CNN Model Setup 28 3.3 Results and Discussion 29 3.3.1 Evaluation of the predictive models 29 3.3.2 Predictive ability under different volume fraction ratio 30 3.3.3 High-throughput virtual screening 38 3.4 Short Summary 39 Chapter 4 Genetic Algorithm Optimization 41 4.1 GA for Nacre-inspired Design Space 41 4.2 Experiments Settings 44 4.3 Results and Discussion 45 4.3.1 GA optimization process 45 4.3.2 Control volume fraction ratio as constraint 47 4.4 Short Summary 49 Chapter 5 Generator of Nacre-inspired Microstructure using VAE 51 5.1 Variational Auto-encoder (VAE) 51 5.2 Results and Discussion 52 5.2.1 Latent size of VAE models 52 5.2.2 Reconstruct results 53 5.2.3 Micro-structures decoded from random latent variables 53 5.3 Short Summary 56 Chapter 6 Conclusions and Future Work 57 6.1 Conclusions 57 6.2 Future Work 58 References 61 | |
dc.language.iso | en | |
dc.title | 機器學習驅動強度與韌性最佳化仿生珍珠母微結構設計 | zh_TW |
dc.title | Machine Learning Enabled Strength and Toughness Optimization for Nacre-inspired Microstructural Design | en |
dc.type | Thesis | |
dc.date.schoolyear | 108-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 陳柏宇(Po-Yu Chen),張書瑋(Shu-Wei Chang),游濟華(Chi-Hua Yu) | |
dc.subject.keyword | 機器學習,多目標最佳化,微結構設計,拓樸最佳化,仿生珍珠母結構,基因演算法,卷積神經網路, | zh_TW |
dc.subject.keyword | Machine Learning,Multi-objective Optimization,Microstructural Design,Topology Optimization,Nacre-inspired Composite,Genetic Algorithm,Convolutional Neural Networks, | en |
dc.relation.page | 64 | |
dc.identifier.doi | 10.6342/NTU202001570 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2020-08-17 | |
dc.contributor.author-college | 工學院 | zh_TW |
dc.contributor.author-dept | 土木工程學研究所 | zh_TW |
顯示於系所單位: | 土木工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
U0001-1607202012141300.pdf 目前未授權公開取用 | 16.37 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。