Abstract
The evaluation of the load-settlement behavior of piles is crucial in meeting the strength and serviceability criteria for pile analysis and design. The most reliable approach for estimating this behavior is by conducting pile load tests. However, due to the considerable expense and time requirements of these tests, the load-transfer methods were used routinely in practice. The objective of this study is to explore the potential application of several machine learning (ML) algorithms to evaluate the load-settlement behavior of axially loaded single square precast prestressed concrete from cone penetration test (CPT) data. Several ML models such as artificial neural network (ANN), random forest (RF), and gradient boosted tree (GBT), were developed to estimate the load-settlement behavior from CPT data (corrected cone tip resistance, qt, and sleeve friction, fs). A database of load-settlement curves of 64 static pile load tests and corresponding CPT data were compiled and used for the development of these ML models. The developed ANN, RF, and GBT models are evaluated based on several statistical criteria. The load-settlement curves predicted using the developed ML models were compared with the measured curves from pile load tests and the load-settlement curves predicted using the conventional load-transfer methods. The results of this study demonstrated the great potential of using ML models to predict the load-settlement behavior of axially loaded piles from CPT data. The comparison clearly shows that ML models outperformed the load-transfer methods. The results showed that both the GBT and ANN algorithms demonstrated to be the best-performing ML models.
Similar content being viewed by others
Data Availability
Some or all data, or models, used during the study are available from the corresponding author by request.
Abbreviations
- ANN:
-
Artificial neural network
- B:
-
Pile width
- COV:
-
Coefficient of variation
- CPT:
-
Cone penetration test
- DT:
-
Decision tree
- FFNN:
-
Feed-forward neural network
- FHWA:
-
Federal Higway Administration
- fs :
-
Sleeve friction
- fs , Avg :
-
Average sleeve friction
- FTNN:
-
Focused time-delay neural network
- GBT:
-
Gradient boosted tree
- HON:
-
High-order neural network
- Le :
-
Embedded length of pile
- ML:
-
Machine learning
- MLP:
-
Multilayer perception
- PPC:
-
Precast prestressed concrete
- Pfit :
-
Best fit normalized load
- Pm :
-
Measured normalized load
- Pp :
-
Predicted normalized load
- PUNN:
-
Product-unit neural network
- qt :
-
Corrected cone tip resistance
- qt , Avg :
-
Average cone tip resistance
- qt-tip , 4B above :
-
Average cone tip resistance within 4 width above pile tip
- qt-tip , 8B :
-
Average cone tip resistance within 8 width above pile tip
- qt-tip , 4B below :
-
Average cone tip resistance within 4 width below pile tip
- RNN:
-
Recurrent neural network
- R2 :
-
Coefficient of determination
- RF:
-
Random forest
- RMSE:
-
Root mean squared error
- si :
-
Normalized settlement
- SGD:
-
Stochastic gradient descent
- SPT:
-
Standard penetration test
- zb :
-
Base settlement
- µ:
-
Arithmetic mean
- σ:
-
Standard deviation
References
Abu-Farsakh MY, Amirmojahedi M, Mojumder MAH, Shoaib MM (2023) Update the pile design by CPT software to incorporate newly developed pile-cpt methods and other design features (Report No. FHWA/LA.23/682). Louisiana Transportation Research Center, Federal Highway Administration
Acosta SM, Amoroso AL, Sant’Anna ÂMO, Junior OC (2022) Predictive modeling in a steelmaking process using optimized relevance vector regression and support vector regression. Ann Oper Res 316:905–926. https://doi.org/10.1007/s10479-021-04053-9
American Petroleum Institute (API) (2014) Recommended practice for planning, designing, and constructing fixed offshore platforms- working stress design. Report RP 2A-WSD
Astarita V, Haghshenas SS, Guido G, Vitale A (2023) Developing new hybrid grey wolf optimization-based artificial neural network for predicting road crash severity. Transp Eng. https://doi.org/10.1016/j.treng.2023.100164
ASTM International (2013) Standard test method for deep foundations under static axial compressive load
Breiman L, Friedman R, Olshen SC (1984) Classification and regression trees. Wadsworth, Belmont
Breiman L (2001) Random forests. Mach Learn 45:5–32. https://doi.org/10.1023/A:1010933404324
Campanella RG, Gillespie DG, Robertson PK (1981) Pore pressures during cone penetration testing. Department of Civil Engineering, University of British Columbia, Vancouver
Caudill M (1988) Neural networks primer, part III. AI Expert Mag 3(6):53–59
Chollet F (2015) Keras: deep learning library for theano and tensorflow. https://keras.io/
Coyle HM, Reese LC (1966) Load transfer for axially loaded piles in clay. Proc Am Soc Civ Eng 92(2):200. https://doi.org/10.1061/JSFEAQ.0000850
Coyle HM, Sulaiman IH (1967) Skin friction for steel piles in sand. J Soil Mech Found Div Am Soc Civ Eng 93:261
Dijkstra J, Broere W, Heeres OM (2011) Numerical simulation of pile installation. Comput Geotech 38(5):612–622. https://doi.org/10.1016/j.compgeo.2011.04.004
Ebid AM (2021) 35 years of (AI) in geotechnical engineering: state of the art. Geotech Geol Eng 39:637–690. https://doi.org/10.1007/s10706-020-01536-7
Ensoft (1998) APILE Plus Version 3.0-A program for the analysis of the axial capacity of driven piles. Ensoft, Inc., Austin
Fischer KA, Sheng D, Abbo AJ (2007) Modeling of pile installation using contact mechanics and quadratic elements. Comput Geotech 34(6):449–461. https://doi.org/10.1016/j.compgeo.2007.01.003
Friedman JH (2002) Stochastic gradient boosting. Comput Stat Data Anal 38(4):367–378. https://doi.org/10.1016/S0167-9473(01)00065-2
Gao W, Han J (2020) Prediction of destroyed floor depth based on principal component analysis (PCA)-genetic algorithm (GA)-support vector regression (SVR). Geotech Geol Eng 38:3481–3491. https://doi.org/10.1007/s10706-020-01227-3
Haghshenas SS, Guido G, Vitale A, Astarita V (2023) Assessment of the level of road crash severity: comparison of intelligence studies. Expert Syst Appl 234:200. https://doi.org/10.1016/j.eswa.2023.121118
Henke S (2010) Influence of pile installation on adjacent structures. Int J Numer Anal Methods Geomech 34(11):1191–1210. https://doi.org/10.1002/nag.859
Ismail A, Jeng D-S (2011) Modelling load–settlement behaviour of piles using high-order neural network (HON-PILE model). Eng Appl Artif Intell 24(5):813–821. https://doi.org/10.1016/j.engappai.2011.02.008
Ismail A, Jeng D-S, Zhang LL (2013) An optimized product-unit neural network with a novel PSO–BP hybrid training algorithm: applications to load–deformation analysis of axially loaded piles. Eng Appl Artif Intell 26(10):2305–2314. https://doi.org/10.1016/j.engappai.2013.04.007
James GD, Witten T, Hastie TR (2021) An introduction to statistical learning. Springer, New York
Khan MUA, Shukla SK, Raja MNA (2022) Load-settlement response of a footing over buried conduit in a sloping terrain: a numerical experiment-based artificial intelligent approach. Soft Comput 26:6839–6856. https://doi.org/10.1007/s00500-021-06628-x
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. CoRR https://doi.org/10.48550/arXiv.1412.6980
Kraft LM, Focht JA, Amerasinghe SF (1981) Friction capacity of piles driven into clay. J Geotech Eng Div 107:1521–1541
Lunne T, Eidsmon T, Gillespie D, Howland JD (1986) Laboratory and field evaluation of cone penetrometers. Paper presented at the Use of In Situ Tests in Geotechnical Engineering
Mojumder MAH (2020) Evaluation of undrained shear strength of soil, ultimate pile capacity and pile set-up parameter from cone penetration test (CPT) using artificial neural network (ANN). Master’s Thesis, Louisiana State University
Mosher RL (1984) Load transfer criteria for numerical analysis of axially loaded piles in sand. U. S. Army Waterways Experiment Station. Automatic Data Processing Center, Vicksburg, Mississippi
McVay MC, Townsend FC, Bloomquist DG, O’Brien MO, Caliendo JA (1989) Numerical analysis of vertically loaded pile groups. In: Proceedings, foundation engineering congress: current principles and practices, Evanston, IL, pp 675–690
Mikaeil R, Haghshenas SS, Ozcelik Y, Gharehgheshlagh HH (2018) Performance evaluation of adaptive neuro-fuzzy inference system and group method of data handling-type neural network for estimating wear rate of diamond wire saw. Geotech Geol Eng 36:3779–3791. https://doi.org/10.1007/s10706-018-0571-2
Mikaeil R, Mokhtarian M, Haghshenas SS, Careddu N, Alipour A (2022) Assessing the system vibration of circular sawing machine in carbonate rock sawing process using experimental study and machine learning. Geotech Geol Eng 40:103–119. https://doi.org/10.1007/s10706-021-01889-7
Moayedi H, Hayati S (2018) Applicability of a CPT-based neural network solution in predicting load-settlement responses of bored pile. Int J Geomech 18(8):200. https://doi.org/10.1061/(ASCE)GM.1943-5622.0001125
Nejad FP, Jaksa MB (2017) Load-settlement behavior modeling of single piles using artificial neural networks and CPT data. Comput Geotech 59:9–21. https://doi.org/10.1016/j.compgeo.2017.04.003
Nejad FP, Jaksa MB, Kakhi M, McCabe BA (2009) Prediction of pile settlement using artificial neural networks based on standard penetration test data. Comput Geotech 36(7):1125–1133. https://doi.org/10.1016/j.compgeo.2009.04.003
Noori AM, Mikaeil R, Mokhtarian M, Haghshenas SS, Foroughi M (2020) Feasibility of intelligent models for prediction of utilization factor of TBM. Geotech Geol Eng 38:3125–3143. https://doi.org/10.1007/s10706-020-01213-9
Pando MA, Ealy CD, Filz GM, Lesko JJ, Hoppe EJA (2006) Laboratory and field study of composite piles for bridge substructures (No. FHWA-HRT-04-043). Federal Highway Administration
Penumadu D, Zhao R (1999) Triaxial compression behavior of sand and gravel using artificial neural networks (ANN). Comput Geotech 24(3):207–230. https://doi.org/10.1016/S0266-352X(99)00002-6
Pedregosa F, Gaël V, Alexandre VG, Michel V, Thirion B, Grisel O, Blondel M (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2830
Randolph MF (1994) Design methods for pile groups and pile drafts. In: Proceedings, XIII ICSMFE, New Delhi, India, pp 61–82
Seed HB, Reese LC (1957) The action of soft clay along friction piles. Trans Am Soc Civ Eng 122:731–754
Shoaib MM (2023) Exploring machine learning in deep foundation and soil classification application. Master’s Thesis, Louisiana State University
Shoaib MM, Abu-Farsakh MY (2023) Exploring tree-based machine learning models to estimate the ultimate pile capacity from cone penetration test data. Transp Res Rec. https://doi.org/10.1177/03611981231170128
Shahin MA (2014) Load-settlement modeling of axially loaded drilled shafts using CPT-based recurrent neural networks. Int J Geomech. https://doi.org/10.1061/(ASCE)GM.1943-5622.0000370
Skempton AW (1951) The bearing capacity of clays. In: Proceedings, building research congress, division I, London, England
Vijayvergiya VN (1977) Load-movement characteristics of piles. In: 4th symposium of waterways, port, coastal and ocean division, vol 2. American Society of Civil Engineers, Long Beach, pp 561–584
Yang L, Shami A (2020) On hyperparameter optimization of machine learning algorithms: theory and practice. Neurocomputing 415(20):295–316. https://doi.org/10.1016/j.neucom.2020.07.061
Acknowledgements
The authors would like to express gratitude to the Louisiana Department of Transportation and Development (LA DOTD) engineers for their continuous support and help throughout the study.
Funding
This research project is funded by the Louisiana Transportation Research Center (LTRC Project No. 17-2GT) and the Louisiana Department of Transportation and Development (State Project No. DOTLT1000165).
Author information
Authors and Affiliations
Contributions
All authors contributed to the study's conception and design. Material preparation, data collection, and analysis were performed by the two authors. The first draft of the manuscript was written by MS and was reviewed and revised by MA-F. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
No potential conflict of interest is reported by the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Abu-Farsakh, M.Y., Shoaib, M.M. Machine Learning Models to Evaluate the Load-Settlement Behavior of Piles from Cone Penetration Test Data. Geotech Geol Eng (2024). https://doi.org/10.1007/s10706-023-02737-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10706-023-02737-6