The Application of the Novel Kolmogorov–Arnold Networks for Predicting the Fundamental Period of RC Infilled Frame Structures

Abstract

The fundamental period is a crucial parameter in structural dynamics that informs the design, assessment, and monitoring of structures to ensure the safety and stability of buildings during earthquakes. Numerous machine-learning and deep-learning approaches have been proposed to predict the fundamental period of infill-reinforced concrete frame structures. However, challenges remain, including insufficient prediction accuracy and excessive computational resource demands. This study aims to provide a new paradigm for accurately and efficiently predicting fundamental periods, namely, Kolmogorov–Arnold networks (KANs) and their variants, especially radial basis function KANs (RBF-KANs). KANs are formulated based on the Kolmogorov–Arnold representation theorem, positioning them as a promising alternative to multilayer perceptron. In this research, we compare the performance of KANs against fully connected neural networks (FCNNs) in the context of fundamental period prediction. The mutual information method was employed for the analysis of dependencies between features in the FP4026 data set. Nine predictive models, including KANs, F-KANs, FCNN-2, FCNN-11, CatBoost, Support Vector Machine, and others, were constructed and compared, with hyperparameters determined by Optuna, which will highlight the optimal model amongst the F-KANs models. Numerical results manifest that the highest performance is yielded by the KANs with R² = 0.9948, which offers an explicit form of the formula. Lastly, we further dive into the explainability and interpretability of the KANs, revealing that the number of stories and the opening percentage features have a significant effect on the fundamental period prediction results.

Keywords

deep learning / explainability and interpretability / fundamental period / Kolmogorov–Arnold networks / machine learning

References

[1] P. Thisovithan, H. Aththanayake, D. P. P. Meddage, I. U. Ekanayake, and U. Rathnayake, “A Novel Explainable AI-Based Approach to Estimate the Natural Period of Vibration of Masonry Infill Reinforced Concrete Frame Structures Using Different Machine Learning Techniques,” Results in Engineering 19 (2023): 101388.

[2] H. Crowley and R. Pinho, “Period–Height Relationship for Existing European Reinforced Concrete Buildings,” Journal of Earthquake Engineering 8, no. spec01 (2004): 93–119.

[3] A. Masi and M. Vona, “Experimental and Numerical Evaluation of the Fundamental Period of Undamaged and Damaged RC Framed Buildings,” Bulletin of Earthquake Engineering 8 (2010): 643–656.

[4] CEN. Eurocode 8: Design of Structures for Earthquake Resistance—Part 1: General Rules, Seismic Actions and Rules for Buildings (European Committee for Standardization, 2004), https://eurocodes.jrc.ec.europa.eu/EN-Eurocodes/eurocode-8-design-structures-earthquake-resistance.

[5] M. M. Kose, “Parameters Affecting the Fundamental Period of RC Buildings With Infill Walls,” Engineering Structures 31, no. 1 (2009): 93–102.

[6] K. M. Amanat and E. Hoque, “A Rationale for Determining the Natural Period of RC Building Frames Having Infill,” Engineering Structures 28, no. 4 (2006): 495–502.

[7] A. Noorifard, M. R. Tabeshpour, and F. M. Saradj, New Approximate Method to Identify Soft Story Caused by Infill Walls (Elsevier, 2020), 922–939.

[8] M. H. Arslan and H. H. Korkmaz, “What Is to Be Learned From Damage and Failure of Reinforced Concrete Structures During Recent Earthquakes in Turkey?,” Engineering Failure Analysis 14, no. 1 (2007): 1–22.

[9] G. Sandeep, H. Jagadisha, and V. Sindhu, “Influence of Vertical Geometric Irregularities of Reinforced Concrete Buildings on the Time Period for Different Bay Widths and Building Heights,” Civil Engineering and Architecture 12, no. 2 (2024): 840–849.

[10] S. Zhu, J. Zheng, Z. Zhu, Q. Zhu, and L. Zhou, “Experiments on Three-Dimensional Flaw Dynamic Evolution of Transparent Rock-Like Material Under Osmotic Pressure,” Tunnelling and Underground Space Technology 128 (2022): 104624.

[11] S. Zhu, Y. Zhang, J. Shao, Z. Zhu, X. Zhang, and J. Wu, “Experimental and Theoretical Study on Crack Growth Using Rock-Like Resin Samples Containing Inherent Fissures and Its Numerical Assessment,” Rock Mechanics and Rock Engineering 57 (2024): 4815–4834.

[12] M. I. Jordan and T. M. Mitchell, “Machine Learning: Trends, Perspectives, and Prospects,” Science 349, no. 6245 (2015): 255–260.

[13] K. Liakos, P. Busato, D. Moshou, S. Pearson, and D. Bochtis, “Machine Learning in Agriculture: A Review,” Sensors 18, no. 8 (2018): 2674.

[14] A. L. Tarca, V. J. Carey, X. Chen, R. Romero, and S. Drăghici, “Machine Learning and Its Applications to Biology,” PLoS Computational Biology 3, no. 6 (2007): e116.

[15] M. Abumohsen, A. Abumihsan, A. Y. Owda, and M. Owda, “Hybrid Machine Learning Model Combining of CNN-LSTM-RF for Time Series Forecasting of SPG,” e-Prime 9 (2024): 100636.

[16] J. Stallkamp, M. Schlipsing, J. Salmen, and C. Igel, “Man vs. Computer: Benchmarking Machine Learning Algorithms for Traffic Sign Recognition,” Neural Networks 32 (2012): 323–332.

[17] S. L. Brunton and J. N. Kutz, Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control (Cambridge University Press, 2022).

[18] Y. Reich, “Machine Learning Techniques for Civil Engineering Problems,” Computer-Aided Civil and Infrastructure Engineering 12, no. 4 (1997): 295–310.

[19] S. R. Vadyala, S. N. Betgeri, J. C. Matthews, and E. Matthews, “A Review of Physics-Based Machine Learning in Civil Engineering,” Results in Engineering 13 (2022): 100316.

[20] S. N. Somala, K. Karthikeyan, and S. Mangalathu, Time Period Estimation of Masonry Infilled RC Frames Using Machine Learning Techniques (Elsevier, 2021), 1560–1566.

[21] R. Chalabi, O. Yazdanpanah, and K. M. Dolatshahi, “Nonmodel Rapid Seismic Assessment of Eccentrically Braced Frames Incorporating Masonry Infills Using Machine Learning Techniques,” Journal of Building Engineering 79 (2023): 107784.

[22] S. Lin, M. Dong, Z. Liang, H. Guo, and H. Zheng, “Image-Based 3D Reconstruction and Permeability Modelling of Rock Using Enhanced Interpretable Deep Residual Learning,” Engineering Analysis With Boundary Elements 160 (2024): 187–200.

[23] S. Lin, Z. Liang, M. Dong, H. Guo, and H. Zheng, “Imbalanced Rock Burst Assessment Using Variational Autoencoder-Enhanced Gradient Boosting Algorithms and Explainability,” Underground Space 17 (2024): 226–245.

[24] S. Lin, M. Dong, X. Cao, Z. Liang, H. Guo, and H. Zheng, “The Pre-Trained Explainable Deep Learning Model With Stacked Denoising Autoencoders for Slope Stability Analysis,” Engineering Analysis With Boundary Elements 163 (2024): 406–425.

[25] P. G. Asteris, “The FP4026 Research Database on the Fundamental Period of RC Infilled Frame Structures,” Data in Brief 9 (2016): 704–709.

[26] K. Kuźniar and Z. Waszczyszyn, “Neural Networks and Principal Component Analysis for Identification of Building Natural Periods,” Journal of Computing in Civil Engineering 20, no. 6 (2006): 431–436.

[27] A. E. Charalampakis, G. C. Tsiatas, and S. B. Kotsiantis, “Machine Learning and Nonlinear Models for the Estimation of Fundamental Period of Vibration of Masonry Infilled RC Frame Structures,” Engineering Structures 216 (2020): 110765.

[28] P. G. Asteris and M. Nikoo, “Artificial Bee Colony-Based Neural Network for the Prediction of the Fundamental Period of Infilled Frame Structures,” Neural Computing and Applications 31, no. 9 (2019): 4837–4847.

[29] N. E.-I. Bioud, I. O. Laid, and M. A. Benbouras, “Estimating the Fundamental Period of Infilled RC Frame Structures via Deep Learning,” Urbanism Arhitectură Construcţii 14, no. 1 (2023): 1–22.

[30] S. G. Joshi, S. N. Londhe, and N. Kwatra, “Determination of Natural Periods of Vibration Using Genetic Programming,” Earthquakes and Structures 6, no. 2 (2014): 201–216.

[31] Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning,” Nature 521, no. 7553 (2015): 436–444.

[32] B. Liu, N. Vu-Bac, and T. Rabczuk, “A Stochastic Multiscale Method for the Prediction of the Thermal Conductivity of Polymer Nanocomposites Through Hybrid Machine Learning Algorithms,” Composite Structures 273 (2021): 114269.

[33] Z. Liu, Y. Wang, S. Vaidya, et al., “KAN: Kolmogorov–Arnold Networks,” preprint, arXiv, 30 April 2024, https://doi.org/10.48550/arXiv.2404.19756.

[34] H. Taud and J.-F. Mas, “ Multilayer Perceptron (MLP),” in Geomatic Approaches for Modeling Land Change Scenarios (Springer International Publishing, 2017), 451–455.

[35] M. B. Fazi, “Beyond Human: Deep Learning, Explainability and Representation,” Theory, Culture & Society 38, no. 7–8 (2021): 55–77.

[36] W. Samek, T. Wiegand, and K.-R. Müller, “Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models,” preprint, arXiv, 28 August 2017, https://doi.org/10.48550/arXiv.1708.08296.

[37] A. Barredo Arrieta, N. Díaz-Rodríguez, J. Del Ser, et al., “Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges Toward Responsible AI,” Information Fusion 58 (2020): 82–115.

[38] A. Adadi and M. Berrada, “Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI),” IEEE Access 6 (2018): 52138–52160.

[39] R. Steuer, J. Kurths, C. O. Daub, J. Weise, and J. Selbig, “The Mutual Information: Detecting and Evaluating Dependencies Between Variables,” Bioinformatics 18, no. suppl_2 (2002): S231–S240.

[40] N. Veyrat-Charvillon and F.-X. Standaert, Mutual Information Analysis: How, When and Why? (Springer, 2009), 429–443.

[41] A. Yahiaoui, S. Dorbani, and L. Yahiaoui, Machine Learning Techniques to Predict the Fundamental Period of Infilled Reinforced Concrete Frame Buildings (Elsevier, 2023), 918–927.

[42] Y.-S. Chun, J.-S. Yang, K.-K. Chang, and L.-H. Lee, “ Approximate Estimations of Natural Periods for Apartment Buildings With Sehar-Wall Dominant System,” in 12th World Conference on Earthquake Engineering, Nueva Zelanda, Artículo, Vol. 18. (2000).

[43] A. N. Kolmogorov, On the Representation of Continuous Functions of Many Variables by Superposition of Continuous Functions of One Variable and Addition (Russian Academy of Sciences, 1957), 953–956.

[44] T. Poggio, A. Banburski, and Q. Liao, “Theoretical Issues in Deep Networks,” Proceedings of the National Academy of Sciences 117, no. 48 (2020): 30039–30045.

[45] M.-J. Lai and Z. Shen, “The Kolmogorov Superposition Theorem Can Break the Curse of Dimensionality When Approximating High Dimensional Functions,” preprint, arXiv, 18 December 2021, https://doi.org/10.48550/arXiv.2112.09963.

[46] M. Köppen, On the Training of a Kolmogorov Network (Springer, 2002), 474–479.

[47] D. A. Sprecher and S. Draghici, “Space-Filling Curves and Kolmogorov Superposition-Based Neural Networks,” Neural Networks 15, no. 1 (2002): 57–67.

[48] J. Braun and M. Griebel, “On a Constructive Proof of Kolmogorov's Superposition Theorem,” Constructive Approximation 30 (2009): 653–675.

[49] D. W. Abueidda, P. Pantidis, and M. E. Mobasher, “Deepokan: Deep Operator Network Based on Kolmogorov Arnold Networks for Mechanics Problems,” preprint, arXiv, 29 May 2024, https://doi.org/10.48550/arXiv.2405.19143.

[50] Z. Bozorgasl and H. Chen, “Wav-KAN: Wavelet Kolmogorov– Arnold Networks,” preprint, arXiv, 21 May 2024, https://doi.org/10.48550/arXiv.2405.12832.

[51] M. Unser, A. Aldroubi, and M. Eden, “B-Spline Signal Processing. II. Efficiency Design and Applications,” IEEE Transactions on Signal Processing 41, no. 2 (1993): 834–848.

[52] G. P. Tolstov, Fourier Series (Courier Corporation, 2012).

[53] V. Bayona, M. Moscoso, M. Carretero, and M. Kindelan, “RBF-FD Formulas and Convergence Properties,” Journal of Computational Physics 229, no. 22 (2010): 8281–8295.

[54] Z. Zong and K. Y. Lam, “Estimation of Complicated Distributions Using B-Spline Functions,” Structural Safety 20, no. 4 (1998): 341–355.

[55] G.-B. Huang, P. Saratchandran, and N. Sundararajan, “A Generalized Growing and Pruning RBF (GGAP-RBF) Neural Network for Function Approximation,” IEEE Transactions on Neural Networks 16, no. 1 (2005): 57–67.

[56] K. Hornik, M. Stinchcombe, and H. White, “Multilayer Feedforward Networks Are Universal Approximators,” Neural Networks 2, no. 5 (1989): 359–366.

[57] Q. Zhang, Y. Jin, G. Wang, Q. Sun, and H. Ghorbani, “Improving Stability and Safety in Concrete Structures Against High-Energy Projectiles: A Machine Learning Perspective,” Frontiers in Materials 11 (2024): 1416918.

[58] B. Liu, N. Vu-Bac, X. Zhuang, X. Fu, and T. Rabczuk, “Stochastic Full-Range Multiscale Modeling of Thermal Conductivity of Polymeric Carbon Nanotubes Composites: A Machine Learning Approach,” Composite Structures 289 (2022): 115393.

[59] T. Song, D. Guan, Z. Wang, and H. Ghorbani, “Maximizing Hydropower Station Safety Against Earthquake Through Extreme Learning Machine-Enabled Shear Waves Velocity Prediction,” Frontiers in Environmental Science 12 (2024): 1414461.

[60] O. Hazbeh, M. Rajabi, S. Tabasi, et al., “Determination and Investigation of Shear Wave Velocity Based on One Deep/Machine Learning Technique,” Alexandria Engineering Journal 92 (2024): 358–369.

[61] L. Prokhorenkova, G. Gusev, A. Vorobev, A. V. Dorogush, and A. Gulin, “CatBoost: Unbiased Boosting With Categorical Features,” Advances in Neural Information Processing Systems 31 (2018): 6639–6649.

[62] J. T. Hancock and T. M. Khoshgoftaar, “CatBoost for Big Data: An Interdisciplinary Review,” Journal of Big Data 7, no. 1 (2020): 94.

[63] T. Chen and C. Guestrin, “ Xgboost: A Scalable Tree Boosting System,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016), 785–794.

[64] X. Zhu, J. Chu, K. Wang, S. Wu, W. Yan, and K. Chiam, “Prediction of Rockhead Using a Hybrid N-XGBoost Machine Learning Framework,” Journal of Rock Mechanics and Geotechnical Engineering 13, no. 6 (2021): 1231–1245.

[65] Y. Qiu, J. Zhou, M. Khandelwal, H. Yang, P. Yang, and C. Li, “Performance Evaluation of Hybrid WOA-XGBoost, GWO-XGBoost and BO-XGBoost Models to Predict Blast-Induced Ground Vibration,” Engineering With Computers 38, no. Suppl. 5 (2022): 4145–4162.

[66] L. Breiman, “Random Forests,” Machine Learning 45 (2001): 5–32.

[67] B. Liu and W. Lu, “Surrogate Models in Machine Learning for Computational Stochastic Multi-Scale Modelling in Composite Materials Design,” International Journal of Hydromechatronics 5, no. 4 (2022): 336–365.

[68] P. Probst, M. N. Wright, and A. L. Boulesteix, “Hyperparameters and Tuning Strategies for Random Forest,” WIREs Data Mining and Knowledge Discovery 9, no. 3 (2019): e1301.

[69] V. Cherkassky and Y. Ma, “Practical Selection of SVM Parameters and Noise Estimation for SVM Regression,” Neural Networks 17, no. 1 (2004): 113–126.

[70] T. Joachims, Estimating the Generalization Performance of a SVM Efficiently, Technical Report no. 20 (2001).

[71] Y. Xia, C. Zhang, C. Wang, et al., “Prediction of Bending Strength of Glass Fiber Reinforced Methacrylate-Based Pipeline UV-CIPP Rehabilitation Materials Based on Machine Learning,” Tunnelling and Underground Space Technology 140 (2023): 105319.

[72] F. Feng, H. Ghorbani, and A. E. Radwan, “Predicting Groundwater Level Using Traditional and Deep Machine Learning Algorithms,” Frontiers in Environmental Science 12 (2024): 1291327.

[73] T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, “ Optuna: A Next-Generation Hyperparameter Optimization Framework,” in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (2019), 2623–2631.

[74] P. Srinivas and R. Katarya, “hyOPTXg: OPTUNA Hyper-Parameter Optimization Framework for Predicting Cardiovascular Disease Using XGBoost,” Biomedical Signal Processing and Control 73 (2022): 103456.

[75] T. O. Hodson, “Root Mean Square Error (RMSE) or Mean Absolute Error (MAE): When to Use Them or Not,” Geoscientific Model Development 2022 (2022): 1–10.

[76] B. Liu, N. Vu-Bac, X. Zhuang, X. Fu, and T. Rabczuk, “Stochastic Integrated Machine Learning Based Multiscale Approach for the Prediction of the Thermal Conductivity in Carbon Nanotube Reinforced Polymeric Composites,” Composites Science and Technology 224 (2022): 109425.

[77] L. J. Saunders, R. A. Russell, and D. P. Crabb, “The Coefficient of Determination: What Determines a Useful R² Statistic?,” Investigative Ophthalmology & Visual Science 53, no. 11 (2012): 6830–6832.

[78] B. Liu, N. Vu-Bac, X. Zhuang, and T. Rabczuk, “Stochastic Multiscale Modeling of Heat Conductivity of Polymeric Clay Nanocomposites,” Mechanics of Materials 142 (2020): 103280.

[79] H. Li, S. Li, and H. Ghorbani, “Data-Driven Novel Deep Learning Applications for the Prediction of Rainfall Using Meteorological Data,” Frontiers in Environmental Science 12 (2024): 1445967.

[80] A. Heuillet, F. Couthouis, and N. Díaz-Rodríguez, “Explainability in Deep Reinforcement Learning,” Knowledge-Based Systems 214 (2021): 106685.

[81] Y. Zhang, P. Tino, A. Leonardis, and K. Tang, “A Survey on Neural Network Interpretability,” IEEE Transactions on Emerging Topics in Computational Intelligence 5, no. 5 (2021): 726–742.

[82] L. H. Gilpin, D. Bau, B. Z. Yuan, A. Bajwa, M. Specter, and L. Kagal, Explaining Explanations: An Overview of Interpretability of Machine Learning (IEEE, 2018), 80–89.

[83] G. Vilone and L. Longo, “Notions of Explainability and Evaluation Approaches for Explainable Artificial Intelligence,” Information Fusion 76 (2021): 89–106.

[84] S. Gawde, S. Patil, S. Kumar, P. Kamat, K. Kotecha, and S. Alfarhood, “Explainable Predictive Maintenance of Rotating Machines Using LIME, SHAP, PDP, ICE,” IEEE Access 12 (2024): 29345–29361.

[85] D. Collaris and J. J. van Wijk, “ Machine Learning Interpretability Through Contribution-Value Plots,” in Proceedings of the 13th International Symposium on Visual Information Communication and Interaction (2020), 1–5.

[86] B. Liu, W. Lu, T. Olofsson, X. Zhuang, and T. Rabczuk, “Stochastic Interpretable Machine Learning Based Multiscale Modeling in Thermal Conductivity of Polymeric Graphene-Enhanced Composites,” Composite Structures 327 (2024): 117601.

RIGHTS & PERMISSIONS

2025 The Author(s). International Journal of Mechanical System Dynamics published by John Wiley & Sons Australia, Ltd on behalf of Nanjing University of Science and Technology.