簡易檢索 / 詳目顯示

回結果列表
研究生： 何少悅
Willy - Husada
論文名稱： Comparative Study on Data Mining Methods in Structural Reliability Prediction
Comparative Study on Data Mining Methods in Structural Reliability Prediction
指導教授： 楊亦東
I-Tung Yang
口試委員: 周瑞生
Jui-Sheng Chou
楊智斌
Jyh-Bin Yang
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： 2015
畢業學年度： 103
語文別： 英文
論文頁數： 167
外文關鍵詞： data mining, failure probability, reliability analysis, reliability-based design optimization, surrogate model
相關次數： 點閱：212  下載：6 
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

    • The goal of reliability-based design optimization (RBDO) is to find the optimal structure design with minimum cost subjected to reliability constraint such as maximum failure probability limit. RBDO has two processes which are design optimization and reliability analysis. Since failure probability is usually small, it takes a large amount of computation time for accurate estimation in reliability analysis. Surrogate models are usually created to replace the time-consuming reliability analysis. In this empirical study, we use several data mining methods with focus on three methods, classification and regression tree (CART), artificial neural network (ANN) and support vector machine (SVM) to create the surrogate models on a empirical benchmark case. Data mining is used because it can find the hidden rules from a training data set and create a surrogate model based on its pattern recognition. In this study, we aim to find the best data mining method in predicting the failure probability in terms of prediction accuracy and computational efficiency which divided into two parts: classification and regression. The main findings of this study is that for one best setting, the ANN method performed better than CART and SVM in both classification and regression in term of prediction accuracy. But, the CART method is more stable in terms of accuracy range. Moreover, the computation time of the CART method is much shorter and therefore superior to both ANN and SVM. In general, the CART method is more favourable than the ANN and SVM methods since it is very efficient in terms of computation time and attain high prediction accuracy.

    ABSTRACT i ACKNOWLEDGEMENTS iii TABLE OF CONTENTS v LIST OF FIGURES ix LIST OF TABLES xiii CHAPTER 1 INTRODUCTION 1 1.1. Research Background 1 1.2. Research Objectives 2 1.3. Research Flowchart 5 1.4. Thesis Organization 7 CHAPTER 2 LITERATURE REVIEW 9 2.1. Reliability Analysis and Assessment 9 2.1.1. First Order Second Moment Method (FOSM) 9 2.1.2. First Order Reliability Method (FORM) 12 2.1.3. Monte Carlo Simulation (MCS) 14 2.2. Reliability-Based Design Optimization (RBDO) 16 2.2.1. Double-Loop Method 16 2.2.2. Single-Loop Method 17 2.2.3. Decoupled Method 18 2.3. Data Mining Approaches 18 2.3.1. Classification and Regression Tree (CART) 19 2.3.2. Artificial Neural Network (ANN) 22 2.3.3. Support Vector Machine (SVM) 25 2.4. Previous Studies on Data Mining in Reliability-Based Design Optimization 28 CHAPTER 3 RESEARCH GENERAL PROCEDURE 31 3.1. Monte Carlo Simulation (MCS) Application in RBDO 31 3.2. Cross-Fold Validation 33 3.3. Research Framework of Data Mining for RBDO Case Study 34 3.4. Preliminary Experiment 39 3.5. Classification and Regression Tree (CART) Application in RBDO 42 3.6. Artificial Neural Network (ANN) Application in RBDO 42 3.7. Support Vector Machine (SVM) Application in RBDO 43 CHAPTER 4 CASE STUDY ANALYSIS RESULTS 47 4.1. Case Study Description 47 4.2. The Performance Criteria of Prediction Model 50 4.3. Monte Carlo Simulation (MCS) 53 4.4. Preliminary Experiment Results 57 4.5. Classification and Regression Tree (CART) Method Results 61 4.5.1. CART Classification Models 64 4.5.2. CART Regression Models 65 4.6. Artificial Neural Network (ANN) Method Results 67 4.6.1. ANN Classification Models 71 4.6.2. ANN Regression Models 73 4.7. Support Vector Machine (SVM) Method Results 74 4.7.1. SVM Classification Models 76 4.7.2. SVM Regression Models 78 4.8. Input Type Comparison 79 4.8.1. CART Classification Models in Input Comparison 80 4.8.2. ANN Classification Models in Input Comparison 81 4.8.3. SVM Classification Models in Input Comparison 82 4.8.4. CART Regression Models in Input Comparison 83 4.8.5. ANN Regression Models in Input Comparison 84 4.8.6. SVM Regression Models in Input Comparison 85 4.8.7. Overall Comparison of Input Types 86 4.9. Output Type Comparison 87 4.9.1. CART Classification Models in Output Comparison 88 4.9.2. ANN Classification Models in Output Comparison 89 4.9.3. SVM Classification Models in Output Comparison 90 4.9.4. Overall Comparison of Output Types in Classification 91 4.9.5. CART Regression Models in Output Comparison 92 4.9.6. ANN Regression Models in Output Comparison 93 4.9.7. SVM Regression Models in Output Comparison 94 4.9.8. Overall Comparison of Output Types in Regression 95 4.10. Method Comparison in Classification 96 4.11. Method Comparison in Regression 98 CHAPTER 5 CONCLUSIONS AND FUTURE DIRECTIONS 103 5.1. Conclusions 103 5.2. Future Study Directions 105 REFERENCES 107 APPENDIX A THE ANALYSIS RESULTS OF THE SURROGATE MODELS 111

    Adeli, H., & Hung, S. (1995). Machine Learning: Neural Networks. Genetic Algorithms And Fuzzy Systems, John Wiley & Sons, Inc.
    Agarwal, H., & Renaud, J. (2004). Reliability based design optimization using response surfaces in application to multidisciplinary systems. Engineering Optimization, 36(3), 291-311.
    Ang, A. H.-S., & Cornell, C. A. (1974). Reliability bases of structural safety and design. Journal of the Structural Division, 100(Proc. Paper 10777).
    Au, S.-K., & Beck, J. L. (2001). Estimation of small failure probabilities in high dimensions by subset simulation. Probabilistic Engineering Mechanics, 16(4), 263-277.
    Ayyub, B., & Haldar, A. (1985). Improved simulation techniques as structural reliability models. Paper presented at the ICOSSAR.
    Breiman, L., Friedman, J., Stone, C. J., & Olshen, R. A. (1984). Classification and regression trees: CRC press.
    Chang, H.-H. (2012). Parallel Programming Paradigms for Reliability-based Design Optimization with Discrete Design Variables. Master Thesis, National Taiwan University of Science and Technology (國立台灣科技大學).
    Ching, J., & Hsieh, Y.-H. (2009). Observations in reliability analysis of a 1-D consolidation problem. Journal of GeoEngineering, 4(1), 19-27.
    Chou, J.-S., & Pham, A.-D. (2013). Enhanced artificial intelligence for ensemble approach to predicting high performance concrete compressive strength. Construction and Building Materials, 49, 554-563.
    CNS 4435, G3102 (1995). Carbon steel pipes for general structures. Chinese National Bureau of Standards, Ministry of Economic
    Affairs, Taiwan, http://www.cnsonline.com.tw/en/.
    Cornell, C. A. (1969). A probability-based structural code*. Paper presented at the ACI Journal Proceedings.
    Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3), 273-297.
    Deb, K. (2001). Multi-objective optimization using evolutionary algorithms (Vol. 16): John Wiley & Sons.
    Geisser, S. (1993). Predictive inference (Vol. 55): CRC Press.
    Genton, M. G. (2001). Classes of kernels for machine learning: a statistics perspective. The Journal of Machine Learning Research, 2, 299-312.
    Gyekenyesi, J. Z., Strack, B., Zampino, E. J., & Pai, S. S. (2008). System reliability analysis with the response surface method. Paper presented at the Reliability and Maintainability Symposium, 2008. RAMS 2008. Annual.
    Haftka, R. T., & Gürdal, Z. (1992). Elements of structural optimization (Vol. 11): Springer Science & Business Media.
    Hagan, M. T., Demuth, H. B., & Beale, M. H. (2002). Neural network design: University of Colorado Bookstore.
    Hasofer, A. M., & Lind, N. C. (1974). Exact and invariant second-moment code format. Journal of the Engineering Mechanics division, 100(1), 111-121.
    Juang, C., Lin, P.-S., & Tso, T.-H. (1997). Interpretation of in-situ test data using artificial neural networks. Paper presented at the Intelligent Information Systems, 1997. IIS'97. Proceedings.
    Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. Paper presented at the Ijcai.
    Kumar, S., Pippy, R. J., Acar, E., Kim, N. H., & Haftka, R. T. (2009). Approximate probabilistic optimization using exact-capacity-approximate-response-distribution (ECARD). Structural and Multidisciplinary Optimization, 38(6), 613-626.
    Liao, K.-W., & Ha, C. (2008). Application of reliability-based optimization to earth-moving machine: hydraulic cylinder components design process. Structural and Multidisciplinary Optimization, 36(5), 523-536.
    Liao, K.-W., & Ivan, G. (2014). A single loop reliability-based design optimization using EPM and MPP-based PSO. Latin American Journal of Solids and Structures, 11(5), 826-847.
    Liao, S.-H., Chu, P.-H., & Hsiao, P.-Y. (2012). Data mining techniques and applications–A decade review from 2000 to 2011. Expert Systems with Applications, 39(12), 11303-11311.
    Liu, Y.-S. (2013). Tuning the Parameters of Least Squares Support Vector Machine using Particle Swarm Optimization. Master Thesis, National Taiwan University of Science and Technology (國立台灣科技大學).
    Liu, Y., Lu, N., & Yin, X. (2015). A Hybrid Method for Structural System Reliability‐Based Design Optimization and its Application to Trusses. Quality and Reliability Engineering International.
    McCulloch, W. S., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5(4), 115-133.
    McDonald, M., & Mahadevan, S. (2008). Design optimization with system-level reliability constraints. Journal of Mechanical Design, 130(2), 021403.
    Orozco, J., & García, C. A. R. (2003). Detecting pathologies from infant cry applying scaled conjugate gradient neural networks. Paper presented at the European Symposium on Artificial Neural Networks, Bruges (Belgium).
    Papadrakakis, M., & Lagaros, N. D. (2002). Reliability-based structural optimization using neural networks and Monte Carlo simulation. Computer methods in applied mechanics and engineering, 191(32), 3491-3507.
    Pelckmans, K., Suykens, J. A., Van Gestel, T., De Brabanter, J., Lukas, L., Hamers, B., . . . Vandewalle, J. (2003). LS-SVMlab toolbox user’s guide. Pattern recognition letters, 24, 659-675.
    Royset, J., Kiureghian, A. D., & Polak, E. (2001). Reliability-based optimal design of series structural systems. Journal of Engineering Mechanics, 127(6), 607-614.
    Rubinstein, R. Y., & Kroese, D. P. (2011). Simulation and the Monte Carlo method (Vol. 707): John Wiley & Sons.
    Salmon, C. G., Johnson, J. E., & Malhas, F. A. (2008). Steel structures: design and behavior, 5th edition: Prentice Hall, New Jersey.
    Samui, P., & Kothari, D. (2011). Utilization of a least square support vector machine (LSSVM) for slope stability analysis. Scientia Iranica, 18(1), 53-58.
    Selle, B., & Huwe, B. (2005). Optimising soil-hydrological predictions using effective CART models. Advances in Geosciences, 5, 37-41.
    Sinha, S. K., & Wang, M. C. (2008). Artificial neural network prediction models for soil compaction and permeability. Geotechnical and Geological Engineering, 26(1), 47-64.
    Steenackers, G., Versluys, R., Runacres, M., & Guillaume, P. (2011). Reliability‐based design optimization of computation‐intensive models making use of response surface models. Quality and Reliability Engineering International, 27(4), 555-568.
    Stehman, S. V. (1997). Selecting and interpreting measures of thematic classification accuracy. Remote sensing of Environment, 62(1), 77-89.
    Sun, L., De Visser, C., Chu, Q., & Mulder, J. (2014). A novel online adaptive kernel method with kernel centers determined by a support vector regression approach. Neurocomputing, 124, 111-119.
    Suykens, J. A., Van Gestel, T., De Moor, B., & Vandewalle, J. (2002). Basic Methods of Least Squares Support Vector Machines Least Squares Support Vector Machines: World Scientific.
    Vapnik, V. (1995). The nature of statistical learning theory: Springer Science & Business Media.
    Yan, K., & Shi, C. (2010). Prediction of elastic modulus of normal and high strength concrete by support vector machine. Construction and Building Materials, 24(8), 1479-1485.
    Yang, I.-T., & Hsieh, Y.-H. (2011). Reliability-based design optimization with discrete design variables and non-smooth performance functions: AB-PSO algorithm. Automation in construction, 20(5), 610-619.
    Yang, I.-T., & Hsieh, Y.-H. (2013). Reliability-based design optimization with cooperation between support vector machine and particle swarm optimization. Engineering with Computers, 29(2), 151-163.
    Yang, R., & Gu, L. (2004). Experience with approximate reliability-based optimization methods. Structural and Multidisciplinary Optimization, 26(1-2), 152-159.
    Yeh, I.-C. (1998). Modeling of strength of high-performance concrete using artificial neural networks. Cement and Concrete research, 28(12), 1797-1808.
    Yin, X., & Chen, W. (2006). Enhanced sequential optimization and reliability assessment method for probabilistic optimization with varying design variance. Structures and Infrastructure Engineering, 2(3-4), 261-275.
    Zhao, Y.-G., & Ono, T. (2001). Moment methods for structural reliability. Structural safety, 23(1), 47-75.

    QR CODE