簡易檢索 / 詳目顯示

回結果列表
研究生： 曾絢娜
Stela Tjandrakusuma
論文名稱： 自然啟發式優化深度學習模型於預拌混凝土抗壓強度預測能力之研究
Nature-Inspired Optimization of Deep Learning Model for Compressive Strength Prediction of Ready-Mixed Concrete
指導教授： 周瑞生
Jui-Sheng Chou
口試委員: 陳柏華
Albert Chen
廖敏志
Min-Chih Liao
阮聖彰
Shanq-Jang Ruan
學位類別： 碩士
Master
系所名稱： 工程學院 - 營建工程系
Department of Civil and Construction Engineering
論文出版年： 2021
畢業學年度： 109
語文別： 英文
論文頁數： 465
中文關鍵詞： ready-mixed concrete 、compressive strength prediction 、engineering design planning 、metaheuristic optimization 、computer vision 、convolutional neural networks
外文關鍵詞： ready-mixed concrete, compressive strength prediction, engineering design planning, metaheuristic optimization, computer vision, convolutional neural networks
相關次數： 點閱：220  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • Most building structures that are built today are built from concrete, owing to its various favorable properties. Compressive strength is one of the mechanical properties of concrete that are directly related to the safety of the structures that built from it. Therefore, predicting compressive strength can facilitate early planning of material quality management. A type of deep learning (DL) model that suits computer vision tasks, the convolutional neural networks (CNNs), is used to predict the compressive strength. To demonstrate the effectiveness of computer vision in predicting compressive strength, its effectiveness using imaging numerical data was compared with that of deep neural networks (DNNs) techniques that use numerical data. Various DL prediction models were compared and the best ones were identified. The best DL models were then optimized by fine-tuning their hyperparameters using a bio-inspired metaheuristic algorithm to enhance the reliability. Numerical experiments indicate that the computer vision-based CNNs outperform the numerical data-based DNNs in all performance metrics except the training time. Thus, the bio-inspired optimization of convolutional neural networks is potentially a promising approach in predicting the compressive strength of concrete.

    Most building structures that are built today are built from concrete, owing to its various favorable properties. Compressive strength is one of the mechanical properties of concrete that are directly related to the safety of the structures that built from it. Therefore, predicting compressive strength can facilitate early planning of material quality management. A type of deep learning (DL) model that suits computer vision tasks, the convolutional neural networks (CNNs), is used to predict the compressive strength. To demonstrate the effectiveness of computer vision in predicting compressive strength, its effectiveness using imaging numerical data was compared with that of deep neural networks (DNNs) techniques that use numerical data. Various DL prediction models were compared and the best ones were identified. The best DL models were then optimized by fine-tuning their hyperparameters using a bio-inspired metaheuristic algorithm to enhance the reliability. Numerical experiments indicate that the computer vision-based CNNs outperform the numerical data-based DNNs in all performance metrics except the training time. Thus, the bio-inspired optimization of convolutional neural networks is potentially a promising approach in predicting the compressive strength of concrete.

    ABSTRACT i ACKNOWLEDGEMENT ii TABLE OF CONTENTS iii LIST OF FIGURES vi LIST OF TABLES vii ABBREVIATIONS AND SYMBOLS viii 1 Introduction 1 1.1 Research Background 1 1.2 Research Objective 2 1.3 Thesis Structure 3 2 Literature Review 4 2.1 Conventional Prediction of Compressive Strength 4 2.2 Application of Deep Learning to Determine Compressive Strength 5 2.3 Hyperparameters Optimization with Metaheuristic Algorithm 6 3 Methodology 8 3.1 Artificial Neural Networks and Deep Learning Techniques 8 3.1.1 Deep Neural Networks 9 3.1.2 Convolutional Neural Networks 10 3.2 Metaheuristic Optimization Algorithm: JellyfishSearch Optimizer 21 3.2.1 Movement Following Ocean Current 23 3.2.2 Motions Inside the Jellyfish Swarm 24 3.2.3 Time Control Mechanism 25 3.2.4 Algorithmic Flowchart and Pseudo-Code of Jellyfish Search Algorithm 25 3.3 Validation and Performance Evaluation 25 3.3.1 Validation Method 27 3.3.2 Performance Metrics 28 4 Experimental Results and Discussion 30 4.1 Experimental Settings 30 4.1.1 Software and Hardware 30 4.1.2 Collection and Pre-Processing of Data 30 4.1.3 Converting Numerical Data into Images 33 4.2 Model Implementation 35 4.2.1 Models Comparisons 36 4.2.2 Comparison of Optimized Deep Learning Models 38 4.2.3 Sensitivity Analyses of Input Variables and Image Pixel Orientation on Modeling Performance 41 5 Conclusions 44 REFERENCES 46 APPENDIX A. Numerical Data Samples 50 A.1 Training Dataset 1 – Industry Recommendation 50 A.2 Test Dataset 1 – Industry Recommendation 158 A.3 Training Dataset 2 – Suggested by Research Community 163 A.4 Test Dataset 2 – Suggested by Research Community 217 A.5 Training Dataset 3 – All Features Considered 219 A.6 Test Dataset 3 – All Features Considered 312 APPENDIX B. Image Data Samples 318 B.1 Annotation of Converted Image 318 B.2 Training Dataset 1 – Industry Recommendation 318 B.3 Test Dataset 1 – Industry Recommendation 346 B.4 Training Dataset 2 – Suggested by Research Community 348 B.5 Test Dataset 2 – Suggested by Research Community 366 B.6 Training Dataset 3 – All Features Considered 367 B.7 Test Dataset 3 – All Features Considered 399 APPENDIX C. Pyhton Code 402 C.1 Process of Numerical Data to Image 402 C.2 CNN 403 C.3 DNN 407 C.4 Deep Learning - Jellyfish Search Optimization 409 APPENDIX D. Tutorial 430

    [1] D.-C. Feng et al., "Machine learning-based compressive strength prediction for concrete: An adaptive boosting approach," Construction and Building Materials, vol. 230, p. 117000, 2020/01/10/ 2020, doi: https://doi.org/10.1016/j.conbuildmat.2019.117000.
    [2] T. Ayub, S. U. Khan, and F. A. Memon, "Mechanical Characteristics of Hardened Concrete with Different Mineral Admixtures: A Review," The Scientific World Journal, vol. 2014, p. 875082, 2014/01/29 2014, doi: 10.1155/2014/875082.
    [3] A.-D. Pham, N.-D. Hoang, and Q.-T. Nguyen, "Predicting Compressive Strength of High-Performance Concrete Using Metaheuristic-Optimized Least Squares Support Vector Regression," Journal of Computing in Civil Engineering, vol. 30, no. 3, p. 06015002, 2016, doi: doi:10.1061/(ASCE)CP.1943-5487.0000506.
    [4] M. Lessard, O. Chaalla, and P.-C. Aitcin, "Testing high-strength concrete compressive strength," ACI Materials Journal, Article vol. 90, no. 4, pp. 303-308, 1993. [Online]. Available: https://www.scopus.com/inward/record.uri?eid=2-s2.0-0027623878&partnerID=40&md5=5766e9fdb48eb1c69bd26553c5d4070e.
    [5] A. E. Ben-Zeitun, "Use of pulse velocity to predict compressive strength of concrete," International Journal of Cement Composites and Lightweight Concrete, vol. 8, no. 1, pp. 51-59, 1986/02/01/ 1986, doi: https://doi.org/10.1016/0262-5075(86)90024-2.
    [6] K. L. Chung, L. Wang, M. Ghannam, M. Guan, and J. Luo, "Prediction of concrete compressive strength based on early-age effective conductivity measurement," Journal of Building Engineering, vol. 35, p. 101998, 2021/03/01/ 2021, doi: https://doi.org/10.1016/j.jobe.2020.101998.
    [7] M. F. M. Zain and S. M. Abd, "Multiple regression model for compressive strength prediction of high performance concrete," Journal of Applied Sciences, Article vol. 9, no. 1, pp. 155-160, 2009, doi: 10.3923/jas.2009.155.160.
    [8] B. H. Bharatkumar, R. Narayanan, B. K. Raghuprasad, and D. S. Ramachandramurthy, "Mix proportioning of high performance concrete," Cement and Concrete Composites, vol. 23, no. 1, pp. 71-80, 2001/02/01/ 2001, doi: https://doi.org/10.1016/S0958-9465(00)00071-8.
    [9] J. V. R. Luke M. Snell and D. W. Norval, "Predicting Early Concrete Strength," Concrete International, vol. 11, no. 12, 12/1/1989.
    [10] S. H. Fakhrmoosavy, S. Setayeshi, and A. Sharifi, "A modified brain emotional learning model for earthquake magnitude and fear prediction," Engineering with Computers, vol. 34, no. 2, pp. 261-276, 2018/04/01 2018, doi: 10.1007/s00366-017-0538-6.
    [11] Y. Essam, P. Kumar, A. N. Ahmed, M. A. Murti, and A. El-Shafie, "Exploring the reliability of different artificial intelligence techniques in predicting earthquake for Malaysia," Soil Dynamics and Earthquake Engineering, vol. 147, p. 106826, 2021/08/01/ 2021, doi: https://doi.org/10.1016/j.soildyn.2021.106826.
    [12] S. M. J. Jalali et al., "Towards novel deep neuroevolution models: chaotic levy grasshopper optimization for short-term wind speed forecasting," Engineering with Computers, 2021/03/08 2021, doi: 10.1007/s00366-021-01356-0.
    [13] H. Jin and J. Zhao, "Real-time energy consumption detection simulation of network node in internet of things based on artificial intelligence," Sustainable Energy Technologies and Assessments, vol. 44, p. 101004, 2021/04/01/ 2021, doi: https://doi.org/10.1016/j.seta.2021.101004.
    [14] H. Adeli, "Four Decades of Computing in Civil Engineering," Singapore, 2020: Springer Singapore, in CIGOS 2019, Innovation for Sustainable Infrastructure, pp. 3-11.
    47
    [15] N.-D. Hoang and Q.-L. Nguyen, "A novel method for asphalt pavement crack classification based on image processing and machine learning," Engineering with Computers, vol. 35, no. 2, pp. 487-498, 2019/04/01 2019, doi: 10.1007/s00366-018-0611-9.
    [16] Y. Xu, Y. Zhou, P. Sekula, and L. Ding, "Machine learning in construction: From shallow to deep learning," Developments in the Built Environment, p. 100045, 2021/02/20/ 2021, doi: https://doi.org/10.1016/j.dibe.2021.100045.
    [17] A. Rezaie, R. Achanta, M. Godio, and K. Beyer, "Comparison of crack segmentation using digital image correlation measurements and deep learning," Construction and Building Materials, vol. 261, p. 120474, 2020/11/20/ 2020, doi: https://doi.org/10.1016/j.conbuildmat.2020.120474.
    [18] A. Garcia-Garcia, S. Orts-Escolano, S. Oprea, V. Villena-Martinez, P. Martinez-Gonzalez, and J. Garcia-Rodriguez, "A survey on deep learning techniques for image and video semantic segmentation," Applied Soft Computing, vol. 70, pp. 41-65, 2018/09/01/ 2018, doi: https://doi.org/10.1016/j.asoc.2018.05.018.
    [19] W. G. Hatcher and W. Yu, "A Survey of Deep Learning: Platforms, Applications and Emerging Research Trends," IEEE Access, vol. 6, pp. 24411-24432, 2018, doi: 10.1109/ACCESS.2018.2830661.
    [20] O. R. Abuodeh, J. A. Abdalla, and R. A. Hawileh, "Assessment of compressive strength of Ultra-high Performance Concrete using deep machine learning techniques," Applied Soft Computing, vol. 95, p. 106552, 2020/10/01/ 2020, doi: https://doi.org/10.1016/j.asoc.2020.106552.
    [21] F. Deng, Y. He, S. Zhou, Y. Yu, H. Cheng, and X. Wu, "Compressive strength prediction of recycled concrete based on deep learning," Construction and Building Materials, vol. 175, pp. 562-569, 2018/06/30/ 2018, doi: https://doi.org/10.1016/j.conbuildmat.2018.04.169.
    [22] H. R. Maier, S. Razavi, Z. Kapelan, L. S. Matott, J. Kasprzyk, and B. A. Tolson, "Introductory overview: Optimization using evolutionary algorithms and other metaheuristics," Environmental Modelling & Software, vol. 114, pp. 195-213, 2019/04/01/ 2019, doi: https://doi.org/10.1016/j.envsoft.2018.11.018.
    [23] Q. Liu, X. Li, H. Liu, and Z. Guo, "Multi-objective metaheuristics for discrete optimization problems: A review of the state-of-the-art," Applied Soft Computing, vol. 93, p. 106382, 2020/08/01/ 2020, doi: https://doi.org/10.1016/j.asoc.2020.106382.
    [24] P. E. Black. "Greedy Algorithm." https://xlinux.nist.gov/dads/HTML/greedyalgo.html (accessed July 30, 2021).
    [25] P. Baldi, "Gradient descent learning algorithm overview: a general dynamical systems perspective," IEEE Transactions on Neural Networks, vol. 6, no. 1, pp. 182-195, 1995, doi: 10.1109/72.363438.
    [26] J. Pearl, Heuristics: Intelligent search strategies for computer problem solving. United States: Addison-Wesley Pub. Co., Inc.,Reading, MA (in English), 1984.
    [27] J.-S. Chou and N.-M. Nguyen, "FBI inspired meta-optimization," Applied Soft Computing, vol. 93, p. 106339, 2020/08/01/ 2020, doi: https://doi.org/10.1016/j.asoc.2020.106339.
    [28] J.-S. Chou and D.-N. Truong, "A novel metaheuristic optimizer inspired by behavior of jellyfish in ocean," Applied Mathematics and Computation, vol. 389, p. 125535, 2021/01/15/ 2021, doi: https://doi.org/10.1016/j.amc.2020.125535.
    [29] J. Schmidhuber, "Deep learning in neural networks: An overview," Neural Networks, vol. 61, pp. 85-117, 2015/01/01/ 2015, doi: https://doi.org/10.1016/j.neunet.2014.09.003.
    48
    [30] D. C. Ciresan, U. Meier, J. Masci, L. M. Gambardella, and J. Schmidhuber, "Flexible, high performance convolutional neural networks for image classification," in Twenty-second international joint conference on artificial intelligence, 2011.
    [31] P. Ramachandran, B. Zoph, and Q. V. Le, "Searching for activation functions," arXiv preprint arXiv:1710.05941, 2017.
    [32] K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014.
    [33] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778.
    [34] K. He, X. Zhang, S. Ren, and J. Sun, "Identity mappings in deep residual networks," in European conference on computer vision, 2016: Springer, pp. 630-645.
    [35] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, "Rethinking the inception architecture for computer vision," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 2818-2826.
    [36] C. Szegedy, S. Ioffe, V. Vanhoucke, and A. Alemi, "Inception-v4, inception-resnet and the impact of residual connections on learning," in Proceedings of the AAAI Conference on Artificial Intelligence, 2017, vol. 31, no. 1.
    [37] F. Chollet, "Xception: Deep learning with depthwise separable convolutions," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 1251-1258.
    [38] A. G. Howard et al., "Mobilenets: Efficient convolutional neural networks for mobile vision applications," arXiv preprint arXiv:1704.04861, 2017.
    [39] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, "Mobilenetv2: Inverted residuals and linear bottlenecks," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 4510-4520.
    [40] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, "Densely connected convolutional networks," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 4700-4708.
    [41] B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le, "Learning transferable architectures for scalable image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 8697-8710.
    [42] M. Tan and Q. Le, "Efficientnet: Rethinking model scaling for convolutional neural networks," in International Conference on Machine Learning, 2019: PMLR, pp. 6105-6114.
    [43] J. H. Holland, "Genetic Algorithms," Scientific American, vol. 267, no. 1, pp. 66-73, 1992. [Online]. Available: http://www.jstor.org/stable/24939139.
    [44] J. Kennedy and R. Eberhart, "Particle swarm optimization," in Proceedings of ICNN'95 - International Conference on Neural Networks, 27 Nov.-1 Dec. 1995 1995, vol. 4, pp. 1942-1948 vol.4, doi: 10.1109/ICNN.1995.488968.
    [45] R. V. Rao, V. J. Savsani, and D. P. Vakharia, "Teaching–learning-based optimization: A novel method for constrained mechanical design optimization problems," Computer-Aided Design, vol. 43, no. 3, pp. 303-315, 2011/03/01/ 2011, doi: https://doi.org/10.1016/j.cad.2010.12.015.
    [46] K. Nordhausen, "The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition by Trevor Hastie, Robert Tibshirani, Jerome Friedman," International Statistical Review, vol. 77, no. 3, pp. 482-482, 2009, doi: https://doi.org/10.1111/j.1751-5823.2009.00095_18.x.
    [47] A. S. Distribution, "Conda," ed: Anaconda.
    49
    [48] M. Abadi et al., "Tensorflow: Large-scale machine learning on heterogeneous distributed systems," arXiv preprint arXiv:1603.04467, 2016.
    [49] F. Chollet, "keras," ed, 2015.
    [50] J. S. Chou and A. D. Pham, "Enhanced artificial intelligence for ensemble approach to predicting high performance concrete compressive strength," Construction and Building Materials, Article vol. 49, pp. 554-563, 2013, doi: 10.1016/j.conbuildmat.2013.08.078.
    [51] J. S. Chou, C. F. Tsai, A. D. Pham, and Y. H. Lu, "Machine learning in concrete strength simulations: Multi-nation data analytics," Construction and Building Materials, Article vol. 73, pp. 771-780, 2014, doi: 10.1016/j.conbuildmat.2014.09.054.
    [52] Q. Han, C. Gui, J. Xu, and G. Lacidogna, "A generalized method to predict the compressive strength of high-performance concrete by improved random forest algorithm," Construction and Building Materials, vol. 226, pp. 734-742, 11/01 2019, doi: 10.1016/j.conbuildmat.2019.07.315.
    [53] A. Khashman and P. Akpinar, "Non-Destructive Prediction of Concrete Compressive Strength Using Neural Networks," Procedia Computer Science, vol. 108, pp. 2358-2362, 2017/01/01/ 2017, doi: https://doi.org/10.1016/j.procs.2017.05.039.

    無法下載圖示 全文公開日期 2031/09/29 (校內網路)
    全文公開日期 本全文未授權公開 (校外網路)
    全文公開日期 本全文未授權公開 (國家圖書館：臺灣博碩士論文系統)
    QR CODE