Prediction of shear wall residential beam height based on machine learning
Abstract
The beam height is an important design parameter that influences structural properties such as load-bearing capacity and stability of beams. In the early stages of structural design, the existing methods for determining beam height mainly include empirical formulae. However, empirical methods are highly subjective, lack accuracy, and are poorly adapted to complex conditions. This paper establishes a beam height prediction model for shear wall residential structures. Using structural design data from projects built by a real estate company across various regions in China, a large dataset of beam heights was collected. The Permutation Feature Importance (PFI) method and six unique machine learning (ML) models were used to rank the importance of input variables. The Gradient Boosting (GB) model, consistent with the feature ranking obtained from PFI, was selected. The model evaluation method was then used to select the number of input features for the GB model, and grid search and K-fold cross-validation were employed to optimize the GB prediction model. This model was compared with a prediction model obtained from a Back Propagation Neural Network (BPNN). Finally, the SHAP method was used to interpret the "black box" machine learning model. The results show that the GB model has higher accuracy compared to the BPNN model, and the input features of the proposed GB model contribute to the beam height in accordance with mechanical laws, demonstrating the model's rationality. The research findings can provide a reference for initial beam height design.
References
[2] Amezquita-Sancheza JP, Valtierra-Rodriguez M, Adeli H (2020) Machine learning in structural engineering. Sci Iran 27(6): 2645-2656.
[3] He DQ, Wang PJ, Yang J (2021) Application of deep neural networks in EMD false component identification. Eng Mech 38(Suppl): 195-201.
[4] Deng L et al (2021) Optimization on bearing capacity and ductility of cold formed thin-walled steel flexural member. Eng Mech 38(4): 93-101.
[5] Pan ZD et al (2019) Research on sliding mode decentralized control based on adaptive learning rate RBF neural network for large-scale engineering structures. Eng Mech 36(9): 120-127.
[6] Chen SG et al (2023) Machine learning models for cracking torque and pre-cracking stiffness of RC beams. Archiv Civ Mech Eng 23(6).
[7] Cao X et al (2023) Torsional capacity of ultra-high-performance concrete beams using rectangle stirrup. J Build Eng 69: 106231.
[8] Yu Y et al (2020) Machine learning-based evaluation of shear capacity of recycled aggregate concrete beams. Materials 13(20): 4552.
[9] Olalusi OB, Awoyera PO (2021) Shear capacity prediction of slender reinforced concrete structures with steel fibers using machine learning. Eng Struct 227: 111470.
[10] Wakjira TG et al (2022) Explainable machine learning model and reliability analysis for flexural capacity prediction of RC beams strengthened in flexure with FRCM. Eng Struct 255: 113903.
[11] Gao D et al (2023) Flexural capacity prediction of steel fiber reinforced concrete beam with recycled fine and coarse aggregate. Adv Struct Eng 26(6): 1042-1058.
[12] Demir A, Caglar N, Ozturk H (2019) Parameters affecting diagonal cracking behavior of reinforced concrete deep beams. Eng Struct 184: 217-231.
[13] Nicoletti RS et al (2023) Evaluation of the TRF of reinforced concrete beams through thermal and thermostructural analysis. J Struct Fire Eng 15(1).
[14] Mei Y et al (2022) Probabilistic prediction model of steel to concrete bond failure under high temperature by machine learning. Eng Fail Anal 142: 106786.
[15] Nariman N et al (2021) Optimum design of flexural strength and stiffness for reinforced concrete beams using machine learning. Appl Sci 11(18): 8762.
[16] Lai D, Demartino C, Xiao Y (2023) Interpretable machine-learning models for maximum displacements of RC beams under impact loading predictions. Eng Struct 281: 115723.
[17] Almustafa MK, Nehdi ML (2022) Novel hybrid machine learning approach for predicting structural response of RC beams under blast loading. Structures 39: 1092-1106.
[18] Hamidia M, Kaboodkhani M, Bayesteh H (2024) Vision-oriented machine learning-assisted seismic energy dissipation estimation for damaged RC beam-column connections. Eng Struct 301: 117345.
[19] Mangalathu S et al (2019) Rapid seismic damage evaluation of bridge portfolios using machine learning techniques. Eng Struct 201: 109785.
[20] Abushanab A, Wakjira TG, Alnahhal W (2023) Machine learning-based flexural capacity prediction of corroded RC beams with an efficient and user-friendly tool. Sustainability 15(6): 4824.
[21] Cai B, Xu L-F, Fu F (2019) Shear resistance prediction of post-fire reinforced concrete beams using artificial neural network. Int J Concr Struct Mater 13(1).
[22] Kumar Tipu R et al (2023) Shear capacity prediction for FRCM-strengthened RC beams using Hybrid ReLU-Activated BPNN model. Structures 58: 105432.
[23] Zhao J et al (2021) Improved Levenberg–Marquardt backpropagation neural network by particle swarm and whale optimization algorithms to predict the deflection of RC beams. Eng Comput 38(S5): 3847–3869.
[24] Rajaratnam B et al (2016) Lasso Regression: Estimation and Shrinkage via the Limit of Gibbs Sampling. J R Stat Soc 78(1): 153-157.
[25] Xie MH, Xie LL, Zhu P (2021) An Efficient Feature Weighting Method for Support Vector Regression. Math Probl Eng 2021: 6675218.
[26] Manzali Y et al (2024) A feature weighted K-nearest neighbor algorithm based on association rules. J Ambient Intell Humaniz Comput.
[27] Norouzi H et al (2021) Assessment of groundwater vulnerability using genetic algorithm and random forest methods (case study: Miandoab plain, NW of Iran). Environ Sci Pollut Res 28: 39598–39613.
[28] Gunasekara N et al (2024) Gradient boosted trees for evolving data streams. Mach Learn 113(5): 3325-3352.
[29] Liang GQ et al (2023) Fatigue life prediction of concrete under cyclic compression based on gradient boosting regression tree. Mater Struct 56: 172.
[30] Tong B, Guo JJ, Fang S (2021) Predicting Budgetary Estimate of Highway Construction Projects in China Based on GRA-LASSO. J Manage Eng 37(3).
[31] Breiman L (2001) Random forests. Mach Learn 45: 5–32.
[32] Ba LJ, Caruana R (2014) Do deep nets really need to be deep? in Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2. MIT Press, Cambridge, MA, USA, 2654–2662.
[33] Liu Y (2019) Predicting Construction Cost Using Fuzzy Logic and Neural Networks. Dissertation, Chongqing Jiaotong University.
[34] Lundberg S, Lee SI (2017) A Unified Approach to Interpreting Model Predictions. in Proceedings of the 31st International Conference on Neural Information Processing Systems. Curran Associates Inc, Red Hook, NY, USA, 4768–4777.
Authors
This work is licensed under a Creative Commons Attribution 4.0 International License.