A Hybrid Metaheuristic-Optimized Machine Learning Framework for Predicting Pile Capacity Using High Strain Dynamic Testing Data
DOI:
https://doi.org/10.70028/cpir.v2i2.95Keywords:
Spun Pile Efficiency, Hybrid Metaheuristics, Algorithm , Neuro-fuzzy, System, High Strain DynamicAbstract
The precise estimation of spun pile efficiency parameters through High Strain Dynamic Testing (HSDT) is critical for structural safety and foundational integrity; however, it is frequently constrained by significant economic, temporal, and logistical limitations that restrict physical testing to a minor fraction of installed piles. To overcome these prohibitive barriers, this study proposes a high-fidelity hybrid predictive framework that synergizes advanced machine learning architectures with nature-inspired metaheuristic optimizers. Three distinct predictive models: Adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Regression (SVR), and Regression Tree (RT) were formulated. To resolve the inherent limitations of suboptimal convergence and hyperparameter trapping in standard configurations, the structural parameters of these models were optimized using the Sparrow Search Algorithm (SSA), Whale Optimization Algorithm (WOA), and Manta Ray Foraging Optimization (MRFO). Utilizing a high-quality, rigorously validated dataset of 150 Pile Driving Analyzer (PDA) records, the models were trained to forecast the maximum case method capacity (RMX) and maximum compressive force (FMX). To ensure model robustness and completely eliminate small-sample bias, a rigorous 10-fold bootstrapping cross-validation protocol was implemented, alongside a SHapley Additive exPlanations (SHAP) sensitivity analysis and Wilcoxon signed-rank testing for non-parametric statistical validation. The comparative benchmarking confirms the absolute superiority of the SSA-ANFIS framework, which achieved unprecedented predictive precision with a perfect correlation (R2=1.000) and minimal error profiles for both RMX (RMSE=0.123) and FMX (RMSE=0.506), statistically outperforming baseline models such as eXtreme Gradient Boosting (XGBoost) and the empirical Danish Driving Formula. For practical field deployment, the optimized architecture was embedded into a MATLAB-based Intelligent Geotechnical Decision Support System (IGDSS) and subjected to independent validation on a geologically distinct site, verifying its exceptional generalization capabilities. The integration of swarm intelligence with neuro-fuzzy logic presents a highly reliable, physically explainable, and cost-effective alternative to ubiquitous physical testing, advancing the paradigm of digital geotechnical engineering.
Downloads
References
L. Huang, J. Gao, and H. Li, "Research on the Flexural Capacity of Pre-Tensioned Prestressed Hollow Concrete-Filled Steel Tubular Piles with Consideration of Pile–Soil Interaction," Infrastructures, vol. 10, no. 12, 2025, no. 332, doi: 10.3390/infrastructures10120332.
Y. Peng, X. Zhang, X. Shi, and M. Duan, "Dynamic response analysis of pile-soil interaction during pile driving by torsional vibration," Applied Mathematical Modelling, vol. 151, 2026, no. 116464, doi: 10.1016/j.apm.2025.116464.
P. Fu, J. Wu, J. Jia, E. Yi, K. Wang, and Z. Zhang, "Dynamic response of saturated layered soil around defective piles and its application in engineering testing," Soil Dynamics and Earthquake Engineering, vol. 194, 2025, no. 109391, doi: 10.1016/j.soildyn.2025.109391.
R. Skov, "Pile foundation—Danish design methods and piling practice," in Design of Axially Loaded Piles-European Practice: CRC Press, 2020, pp. 101-113.
A. Aziz, L. Gulaly, and M. Khan, "An Interpretable Machine Learning Approach for Predicting the End-Bearing Capacity of Rock-Socketed Piles," Transportation Infrastructure Geotechnology, vol. 12, no. 299, pp. 1-43, 2025, doi: 10.1007/s40515-025-00751-0
R. C. Mamat, A. Ramli, M. B. H. Che Omar, A. M. Samad, and S. A. Sulaiman, "Application of machine learning for predicting ground surface settlement beneath road embankments," International Journal of Nonlinear Analysis and Applications, vol. 12, no. Special Issue, pp. 1025-1034, 2021, doi: 10.22075/ijnaa.2021.5548.
S. E. Miri, S. A. M. Shaarbaf, and H. Mohammadnezhad, "An Interpretable Machine Learning Approach for Predicting Bearing Capacity of Driven Piles Using SHAP," Numerical Methods in Civil Engineering, vol. 10, no. 3, pp. 12-24, 2026, doi: 10.61882/NMCE.2510.1102.
R. C. Mamat, A. Kasa, and S. F. M. Razali, "Performance prediction of road embankment on soft soil stabilized with prefabricated vertical drains using numerical method," International Journal of Advanced Trends in Computer Science and Engineering, vol. 8, no. 4, pp. 1601-1608, 2019, doi: 10.30534/ijatcse/2019/85842019.
M. Abdellatief, A. ElNemr, and A. Altahrany, "Pareto-optimized stacked ensemble machine learning framework for predicting bearing capacity of driven piles from static load test data," Scientific Reports, vol. 16, no. 11360, pp. 1-25, 2026, doi: 10.1038/s41598-026-43660-z.
M. Saxena and P. Samui, "Probabilistic Reliability Assessment of Pile Bearing Capacity Using a Hybrid XGBoost Surrogate Model With CPT Data," Transportation Infrastructure Geotechnology, vol. 13, no. 5, p. 164, 2026, doi: 10.1007/s40515-026-00935-2.
Z. Dang, "Advancing Pile-Bearing Capacity Prediction With Meta-Heuristic Enhanced Specific ANFIS Strategys," Journal of Applied Science and Engineering, vol. 28, no. 12, pp. 2549-2559, 2025, doi: 10.6180/jase.202512_28(12).0004.
R. C. Mamat and A. Ramli, "Evolutionary Polynomial Regression for Predicting the Unconfined Compressive Strength of Lime-Stabilized," Suranaree Journal of Science & Technology, vol. 30, no. 2, Art. no. 010212, pp. 1–7, 2023, doi: 10.55766/sujst-2023-02-e01865
A. Nyabadza et al., "Artificial intelligence for electrode quality control in battery manufacturing: Evaluating machine learning, deep learning, and transfer learning models for Tin, Zinc, and Titanium electrodes," Journal of Engineering Research, vol. 14, no. 2, pp. 2366–2383, Jun. 2026, doi: 10.1016/j.jer.2026.02.010.
R. C. Mamat, A. Ramli, and A. B. Bawamohiddin, "A Comparative Analysis of Gaussian Process Regression and Support Vector Machines in Predicting Carbon Emissions from Building Construction Activities," Journal of Advanced Research in Applied Mechanics, vol. 131, no. 1, pp. 185-196, 2025, doi: 10.37934/aram.131.1.185196.
J. Xue and B. Shen, "A novel swarm intelligence optimization approach: sparrow search algorithm," Systems Science and Control Engineering, vol. 8, no. 1, pp. 22-34, 2020, doi: 10.1080/21642583.2019.1708830.
S. Mirjalili and A. Lewis, "The Whale Optimization Algorithm," Advances in Engineering Software, vol. 95, pp. 51-67, 2016, doi: 10.1016/j.advengsoft.2016.01.008.
W. Zhao, Z. Zhang, and L. Wang, "Manta ray foraging optimization: An effective bio-inspired optimizer for engineering applications," Engineering Applications of Artificial Intelligence, vol. 87, 2020, no. 103300, doi: 10.1016/j.engappai.2019.103300.
M. S. Shankar, S. Sivarajan, A. Carie, S. Anamalamudi, and C. Sobin, "Machine Learning and Deep Learning with Swarm Algorithms," in Swarm Intelligence: CRC Press, 2025, pp. 74-95.
E. Quirós, Á. M. Felicísimo, and A. Cuartero, "Testing multivariate adaptive regression splines (MARS) as a method of land cover classification of TERRA-ASTER satellite images," Sensors, vol. 9, no. 11, pp. 9011-9028, 2009, doi: 10.3390/s91109011.
I. H. Umar et al., "Performance characterisation of machine learning models for geotechnical axial pile load capacity estimation: An enhanced GPR-based approach," Geomechanics and Geoengineering, vol. 20, no. 4, pp. 846-887, 2025, doi: 10.1080/17486025.2025.2468645.
T. Wang, H. Yang, and H. Sun, "Intelligent prediction of post-seismic debris flow source volumes: a physics-informed generative deep learning framework," Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards, pp. 1-29, 2026, doi: 10.1080/17499518.2026.2651228.
S. Pawan et al., "Integrated Hyperparameter Optimization with Dimensionality Reduction and Clustering for Radiomics: A Bootstrapped Approach," Multimodal Technologies and Interaction, vol. 9, no. 5, Art. no. 49, 2025, doi: 10.3390/mti9050049.
R. C. Mamat and A. Ramli, "A Simple Solution for Estimating the Smear Effect Permeability Ratio using Finite Element Method," Journal of Rehabilitation in Civil Engineering, vol. 12, no. 1, pp. 34-46, 2024, doi: 10.22075/jrce.2023.28956.1751.
O. Møller, J. K. Frederiksen, A. H. Augustesen, C. T. Leth, N. Okkels, and K. K. Sørensen, “Design of piles – Danish practice,” in Proceedings of the ISSMGE ETC3 International Symposium on Design of Piles in Europe: How Did Eurocode 7 Change Daily Practice?, Leuven, Belgium, Apr. 28–29, 2016.
R. C. Mamat, A. Ramli, and S. A. P. Rosyidi, "Shear strength prediction of treated soft clay with sugarcane bagasse ash using artificial intelligence methods," Jurnal Kejuruteraan, vol. 35, pp. 597-605, 2023, doi: 10.17576/jkukm-2023-35(3)-07.
J.-S. Jang, "ANFIS: Adaptive-network-based fuzzy inference system," IEEE Transactions on Systems, Man, and Cybernetics, vol. 23, no. 3, pp. 665–685, 1993, doi: 10.1109/21.256541.
R. C. Mamat, A. Ramli, and A. B. Bawamohiddin, "Optimizing Carbon Footprint Estimation in Residential Construction: A Comparative Analysis of Regression Trees and ANFIS for Enhanced Sustainability," Pertanika Journal of Science & Technology, vol. 33, no. 5, 2025, doi: 10.47836/pjst.33.5.04.
D. Lourençoni, A. M. Salviano, N. Olszevski, J. S. Pereira, and E. H. M. Cavalcante, "Adaptive neuro-fuzzy inference system for predicting sandy soils bulk density," Earth Science Informatics, vol. 19, no. 3, 2026, no. 28, doi: 10.1007/s12145-026-02077-y.
R. C. Mamat, A. Kasa, and S. F. M. Razali, "The Applications and Future Perspectives of Adaptive Neuro-Fuzzy Inference System in Road Embankment Stability," Journal of Engineering Science & Technology Review, vol. 12, no. 5, pp. 75-90, 2019, doi: 10.25103/jestr.125.09.
V. Vapnik and R. Izmailov, "Reinforced SVM method and memorization mechanisms," Pattern Recognition, vol. 119, p. 108018, 2021, doi: 10.1016/j.patcog.2021.108018.
P. Abishek, N. K. Libeesh, S. Arivazhagan, and C. Sreejith, "Spectral dispersion matching technique for multi-class spatial-spectral feature detection of REE-fertile lithology in the Samalpatti alkaline–carbonatite complex (SACC) using Hyperion data," Geosystems and Geoenvironment, vol. 5, no. 2, 2026, no. 100488, doi: 10.1016/j.geogeo.2025.100488.
I. K. Harith, "Predicting frost resistance of rubberized concrete for sustainable design: a comparative analysis of regression trees and stepwise regression models," Advances in Bridge Engineering, vol. 7, no. 1, 2026, no. 2, doi: 10.1186/s43251-025-00190-4.
C. Lu, J. Zhao, Y. Xia, Y. Sun, and J. Cai, "Predicting permeability of natural gas hydrate reservoir based on machine learning assisted by sparrow search algorithm," Geoenergy Science and Engineering, vol. 257, 2026, no. 214192, doi: 10.1016/j.geoen.2025.214192.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Rufaizal Che Mamat, Azuin Ramli, Muhammad Nasim Abdul Ghani (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
