Form-finding of lifting self-forming GFRP elastic gridshells based on machine learning interpretability methods

다국어 초록 (Multilingual Abstract)

Glass fiber reinforced polymer (GFRP) elastic gridshells consist of long continuous GFRP tubes that form elastic deformations. In this paper, a method for the form-finding of gridshell structures is presented based on the interpretable machine learning (ML) approaches. A comparative study is conducted on several ML algorithms, including support vector regression (SVR), K-nearest neighbors (KNN), decision tree (DT), random forest (RF), AdaBoost, XGBoost, category boosting (CatBoost), and light gradient boosting machine (LightGBM). A numerical example is presented using a standard double-hump gridshell considering two characteristics of deformation as objective functions. The combination of the grid search approach and k-fold cross-validation (CV) is implemented for fine-tuning the parameters of ML models. The results of the comparative study indicate that the LightGBM model presents the highest prediction accuracy. Finally, interpretable ML approaches, including Shapely additive explanations (SHAP), partial dependence plot (PDP), and accumulated local effects (ALE), are applied to explain the predictions of the ML model since it is essential to understand the effect of various values of input parameters on objective functions. As a result of interpretability approaches, an optimum gridshell structure is obtained and new opportunities are verified for form-finding investigation of GFRP elastic gridshells during lifting construction.

참고문헌 (Reference)

1 Chen, T., "Xgboost : extreme gradient boosting"

2 Chen, T., "XGBoost : A scalable tree boosting system" 785-794, 2016

3 Apley, D. W., "Visualizing the effects of predictor variables in black box supervised learning models" 82 (82): 1059-1086, 2020

4 Lafuente Hernández, E., "Topology optimisation of regular and irregular elastic gridshells by means of a non-linear variational method" 2012 : 147-160, 2013

5 Hernández-Montes, E., "Topological mapping for tension structures" 132 (132): 970-977, 2006

6 Carbonell-Márquez, J. F., "Topological design of compression structures" 86 (86): 1495-1508, 2016

7 Fernandes, J. G., "Tectonic design of elastic timber gridshells" 2016

8 Mesnil, R., "Stability of pseudo-funicular elastic grid shells" 30 (30): 27-36, 2015

9 Tayeb, F., "Stability and robustness of a 300 m2 composite gridshell structure" 49 : 926-938, 2013

10 Kookalani, S., "Shape optimization of GFRP elastic gridshells by the weighted Lagrange ε-twin support vector machine and multi-objective particle swarm optimization algorithm considering structural weight" 33 : 2066-2084, 2021

11 Pedregosa, F., "Scikit-learn: Machine learning in {P}ython" 12 : 2825-2830, 2011

12 Baek, C., "Rigidity of hemispherical elastic gridshells under point load indentation" 124 : 411-426, 2019

13 Breiman, L., "Random forests" 45 (45): 5-32, 2001

14 Belle, V., "Principles and practice of explainable machine learning" 2021

15 Slater, E., "Predicting the shear strength of steel fiber reinforced concrete beams" 26 (26): 423-436, 2012

16 Fernández-Ruiz, M. A., "Patterns of force:length ratios for the design of compression structures with inner ribs" 148 : 878-889, 2017

17 Saka, M. P., "Optimum topological design of geometrically nonlinear single layer latticed domes using coupled genetic algorithm" 85 (85): 1635-1646, 2007

18 Hernández, E. L., "On the design and construction of elastic gridshells with irregular meshes" 28 (28): 161-174, 2013

19 Cover, T. M., "Nearest neighbor pattern classification" 13 (13): 21-27, 1967

20 Maryam Safa ; Nguyen Thoi Trung ; Ayub Shahgoli Fazli ; Yousef Zandi ; Mahdi Shariati ; Karzan Wakil ; Majid Khorami, "Moment rotation prediction of precast beam to column connections using extreme learning machine" 국제구조공학회 70 (70): 639-647, 2019

21 Bouhaya, L., "Mapping two-way continuous elastic grid on an imposed surface: Application to grid shells" 2009

22 Kopper, P., "Limitations of interpretable machine learning methods"

23 Ke, G., "LightGBM: A highly efficient gradient boosting decision tree" 30 : 2017

24 Mao, J. X., "Investigation of dynamic properties of long-span cable-stayed bridges based on one-year monitoring data under normal operating condition" 25 (25): e2146-, 2018

25 Molnar, C., "Interpretable Machine Learning. A Guide for Making Black Box Models Explainable"

26 Friedman, J.H., "Greedy function approximation : A gradient boosting machine" 1189-1232, 2001

27 Du Peloux, L., "From shape to shell : A design tool to materialize freeform shapes using gridshell structures" 2011

28 Kim-Lan Vaulot, L., "Form-finding of elastic gridshells" Massachusetts Institute of Technology 2016

29 Omidi, M., "Flow simulation and model analysis of efficiency and pressure ratio behaviours in GT4086 turbocharger compressor" 26 (26): 293-300, 2020

30 Wang, H., "Evolutionary power spectral density of recorded typhoons at Sutong Bridge using harmonic wavelets" 177 : 197-212, 2018

31 Dietterich, T. G., "Ensemble methods in machine learning"

32 Zhang, C., "Ensemble machine learning: Methods and applications, Ensemble Machine Learning: Methods and Applications" Springer Science & Business Media 2012

33 Murdoch, W. J., "Definitions, methods, and applications in interpretable machine learning" 116 (116): 22071-22080, 2019

34 Mangalathu, S., "Data-driven machine-learning-based seismic failure mode identification of reinforced concrete shear walls" 208 : 110331-, 2020

35 Duong Huong Nguyen ; T. Bui-Tien ; Guido De Roeck ; Magd Abdel Wahab, "Damage detection in structures using modal curvatures gapped smoothing method and deep learning" 국제구조공학회 77 (77): 47-56, 2021

36 Hung V. Dang ; Mohsin Raza ; H. Tran-Ngoc ; T. Bui-Tien ; Huan X. Nguyen, "Connection stiffness reduction analysis in steel bridge via deep CNN and modal experimental data" 국제구조공학회 77 (77): 495-508, 2021

37 Chopra, P., "Comparison of machine learning techniques for the prediction of compressive strength of concrete" 2018

38 Huang, H., "Classification of in-plane failure modes for reinforced concrete frames with infills using machine learning" 25 : 100767-, 2019

39 Mangalathu, S., "Classification of failure mode and prediction of shear strength for reinforced concrete beam-column joints using machine learning techniques" 160 : 85-94, 2018

40 Dorogush Veronika, A., "CatBoost: gradient boosting with categorical features support"

41 Lamberti, L., "An efficient simulated annealing algorithm for design optimization of truss structures" 86 (86): 1936-1953, 2008

42 Xiang, S., "An analytic solution for form finding of GFRP elastic gridshells during lifting construction" 244 : 112290-, 2020

43 Xiang, S., "An analytic approach to predict the shape and internal forces of barrel vault elastic gridshells during lifting construction" 29 : 628-637, 2021

44 Lundberg, S. M., "A unified approach to interpreting model predictions" 30 : 2017

45 Das, S., "A Data-driven physics-informed method for prognosis of infrastructure systems: Theory and application to crack prediction" 6 (6): 04020013-, 2020