Prediction of axial capacity of piles driven in non-cohesive soils based on neural networks approach. Benali, A., Boukhatem, B., Hussien, M. N., Nechnech, A., & Karray, M. Journal of Civil Engineering and Management, 23(3):393 - 408, 2017. Bayesian regularization;Failure zone;Multi layer perceptron;Pile base resistance;Pile load test;Predictive performance;Principal components analysis;Ultimate capacity;![Prediction of axial capacity of piles driven in non-cohesive soils based on neural networks approach [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex This paper presents an application of two advanced approaches, Artificial Neural Networks (ANN) and Principal Component Analysis (PCA) in predicting the axial pile capacity. The combination of these two approaches allowed the development of an ANN model that provides more accurate axial capacity predictions. The model makes use of Back-Propagation Multi-Layer Perceptron (BPMLP) with Bayesian Regularization (BR), and it is established through the incorporation of approximately 415 data sets obtained from data published in the literature for a wide range of un-cemented soils and pile configurations. The compiled database includes, respectively 247 and 168 loading tests on large- and low-displacement driven piles. The contributions of the soil above and below pile toe to the pile base resistance are pre-evaluated using separate finite element (FE) analyses. The assessment of the predictive performance of the new method against a number of traditional SPT-based approaches indicates that the developed model has attractive capabilities and advantages that render it a promising tool. To facilitate its use, the developed model is translated into simple design equations based on statistical approaches.
© 2017 Vilnius Gediminas Technical University (VGTU) Press.
@article{20171003424224 ,
language = {English},
copyright = {Compilation and indexing terms, Copyright 2023 Elsevier Inc.},
copyright = {Compendex},
title = {Prediction of axial capacity of piles driven in non-cohesive soils based on neural networks approach},
journal = {Journal of Civil Engineering and Management},
author = {Benali, Amel and Boukhatem, Bakhta and Hussien, Mahmoud N. and Nechnech, Ammar and Karray, Mourad},
volume = {23},
number = {3},
year = {2017},
pages = {393 - 408},
issn = {13923730},
abstract = {This paper presents an application of two advanced approaches, Artificial Neural Networks (ANN) and Principal Component Analysis (PCA) in predicting the axial pile capacity. The combination of these two approaches allowed the development of an ANN model that provides more accurate axial capacity predictions. The model makes use of Back-Propagation Multi-Layer Perceptron (BPMLP) with Bayesian Regularization (BR), and it is established through the incorporation of approximately 415 data sets obtained from data published in the literature for a wide range of un-cemented soils and pile configurations. The compiled database includes, respectively 247 and 168 loading tests on large- and low-displacement driven piles. The contributions of the soil above and below pile toe to the pile base resistance are pre-evaluated using separate finite element (FE) analyses. The assessment of the predictive performance of the new method against a number of traditional SPT-based approaches indicates that the developed model has attractive capabilities and advantages that render it a promising tool. To facilitate its use, the developed model is translated into simple design equations based on statistical approaches.<br/> © 2017 Vilnius Gediminas Technical University (VGTU) Press.},
key = {Piles},
keywords = {Backpropagation;Neural networks;Forecasting;Soils;Finite element method;Principal component analysis;},
note = {Bayesian regularization;Failure zone;Multi layer perceptron;Pile base resistance;Pile load test;Predictive performance;Principal components analysis;Ultimate capacity;},
URL = {http://dx.doi.org/10.3846/13923730.2016.1144643},
}
Downloads: 0
{"_id":"iPodsEhjSjeiSLuDE","bibbaseid":"benali-boukhatem-hussien-nechnech-karray-predictionofaxialcapacityofpilesdriveninnoncohesivesoilsbasedonneuralnetworksapproach-2017","author_short":["Benali, A.","Boukhatem, B.","Hussien, M. N.","Nechnech, A.","Karray, M."],"bibdata":{"bibtype":"article","type":"article","language":"English","copyright":"Compendex","title":"Prediction of axial capacity of piles driven in non-cohesive soils based on neural networks approach","journal":"Journal of Civil Engineering and Management","author":[{"propositions":[],"lastnames":["Benali"],"firstnames":["Amel"],"suffixes":[]},{"propositions":[],"lastnames":["Boukhatem"],"firstnames":["Bakhta"],"suffixes":[]},{"propositions":[],"lastnames":["Hussien"],"firstnames":["Mahmoud","N."],"suffixes":[]},{"propositions":[],"lastnames":["Nechnech"],"firstnames":["Ammar"],"suffixes":[]},{"propositions":[],"lastnames":["Karray"],"firstnames":["Mourad"],"suffixes":[]}],"volume":"23","number":"3","year":"2017","pages":"393 - 408","issn":"13923730","abstract":"This paper presents an application of two advanced approaches, Artificial Neural Networks (ANN) and Principal Component Analysis (PCA) in predicting the axial pile capacity. The combination of these two approaches allowed the development of an ANN model that provides more accurate axial capacity predictions. The model makes use of Back-Propagation Multi-Layer Perceptron (BPMLP) with Bayesian Regularization (BR), and it is established through the incorporation of approximately 415 data sets obtained from data published in the literature for a wide range of un-cemented soils and pile configurations. The compiled database includes, respectively 247 and 168 loading tests on large- and low-displacement driven piles. The contributions of the soil above and below pile toe to the pile base resistance are pre-evaluated using separate finite element (FE) analyses. The assessment of the predictive performance of the new method against a number of traditional SPT-based approaches indicates that the developed model has attractive capabilities and advantages that render it a promising tool. To facilitate its use, the developed model is translated into simple design equations based on statistical approaches.<br/> © 2017 Vilnius Gediminas Technical University (VGTU) Press.","key":"20171003424224","keywords":"Backpropagation;Neural networks;Forecasting;Soils;Finite element method;Principal component analysis;","note":"Bayesian regularization;Failure zone;Multi layer perceptron;Pile base resistance;Pile load test;Predictive performance;Principal components analysis;Ultimate capacity;","url":"http://dx.doi.org/10.3846/13923730.2016.1144643","bibtex":"@article{20171003424224 ,\nlanguage = {English},\ncopyright = {Compilation and indexing terms, Copyright 2023 Elsevier Inc.},\ncopyright = {Compendex},\ntitle = {Prediction of axial capacity of piles driven in non-cohesive soils based on neural networks approach},\njournal = {Journal of Civil Engineering and Management},\nauthor = {Benali, Amel and Boukhatem, Bakhta and Hussien, Mahmoud N. and Nechnech, Ammar and Karray, Mourad},\nvolume = {23},\nnumber = {3},\nyear = {2017},\npages = {393 - 408},\nissn = {13923730},\nabstract = {This paper presents an application of two advanced approaches, Artificial Neural Networks (ANN) and Principal Component Analysis (PCA) in predicting the axial pile capacity. The combination of these two approaches allowed the development of an ANN model that provides more accurate axial capacity predictions. The model makes use of Back-Propagation Multi-Layer Perceptron (BPMLP) with Bayesian Regularization (BR), and it is established through the incorporation of approximately 415 data sets obtained from data published in the literature for a wide range of un-cemented soils and pile configurations. The compiled database includes, respectively 247 and 168 loading tests on large- and low-displacement driven piles. The contributions of the soil above and below pile toe to the pile base resistance are pre-evaluated using separate finite element (FE) analyses. The assessment of the predictive performance of the new method against a number of traditional SPT-based approaches indicates that the developed model has attractive capabilities and advantages that render it a promising tool. To facilitate its use, the developed model is translated into simple design equations based on statistical approaches.<br/> © 2017 Vilnius Gediminas Technical University (VGTU) Press.},\nkey = {Piles},\nkeywords = {Backpropagation;Neural networks;Forecasting;Soils;Finite element method;Principal component analysis;},\nnote = {Bayesian regularization;Failure zone;Multi layer perceptron;Pile base resistance;Pile load test;Predictive performance;Principal components analysis;Ultimate capacity;},\nURL = {http://dx.doi.org/10.3846/13923730.2016.1144643},\n} \n\n\n","author_short":["Benali, A.","Boukhatem, B.","Hussien, M. N.","Nechnech, A.","Karray, M."],"id":"20171003424224","bibbaseid":"benali-boukhatem-hussien-nechnech-karray-predictionofaxialcapacityofpilesdriveninnoncohesivesoilsbasedonneuralnetworksapproach-2017","role":"author","urls":{"Paper":"http://dx.doi.org/10.3846/13923730.2016.1144643"},"keyword":["Backpropagation;Neural networks;Forecasting;Soils;Finite element method;Principal component analysis;"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/network/files/m3A3cns49MKmeRzt5","dataSources":["t3LjCpZw6L2kk69Qf","6Aw5QAtT2yLJ3d2JP","qBPxBjrzghRQ4Wzbf","EnwwBMFxopKkypo2f","8uWbXNBCDiEboMj8h"],"keywords":["backpropagation;neural networks;forecasting;soils;finite element method;principal component analysis;"],"search_terms":["prediction","axial","capacity","piles","driven","non","cohesive","soils","based","neural","networks","approach","benali","boukhatem","hussien","nechnech","karray"],"title":"Prediction of axial capacity of piles driven in non-cohesive soils based on neural networks approach","year":2017}