Modelling pile capacity using Gaussian process regression

Abstract This paper investigates the potential of a Gaussian process (GP) regression approach to predict the load-bearing capacity of piles. Support vector machines (SVM) and empirical relations were used to compare the performance of the GP regression approach. The first dataset used in this study was derived from actual pile-driving records in cohesion-less soil. Out of a total of 94 pieces of data, 59 were used to train and the remaining 35 data were used to test the created models. A radial basis function and Pearson VII function kernels were used with both GP and SVM. The results from this dataset indicate improved performance by GP regression in comparison to SVM and empirical relations. To validate the performance of the GP regression approach, another dataset consisting of 38 pieces of data was considered. The results from this dataset also suggest improved performance by the Pearson VII function kernel-based GP regression modelling approach in comparison to SVM.

[1]  Mahesh Pal,et al.  Estimation of Discharge and End Depth in Trapezoidal Channel by Support Vector Machines , 2007 .

[2]  M. McKee,et al.  SOIL MOISTURE PREDICTION USING SUPPORT VECTOR MACHINES 1 , 2006 .

[3]  L. Buydens,et al.  Facilitating the application of Support Vector Regression by using a universal Pearson VII function based kernel , 2006 .

[4]  D. Hammerstrom,et al.  Working with neural networks , 1993, IEEE Spectrum.

[5]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  Multiclass SVM Design and Parameter Selection with Genetic Algorithms , 2006, 2006 Ninth Brazilian Symposium on Neural Networks (SBRN'06).

[6]  Malte Kuß,et al.  Gaussian process models for robust regression, classification, and reinforcement learning , 2006 .

[7]  John B. Dunckee.  The Iron Wharf At Fort Monroe, Va. , 1892 .

[8]  K Flaate.  AN INVESTIGATION OF THE VALIDITY OF THREE PILE-DRIVING FORMULAE IN COHESIONLESS MATERIAL , 1964 .

[9]  Johan A. K. Suykens,et al.  Advances in learning theory : methods, models and applications , 2003 .

[10]  Christopher M. Bishop,et al.  Bayesian Regression and Classification , 2003 .

[11]  Prabir Kumar Basudhar,et al.  Undrained lateral load capacity of piles in clay using artificial neural network , 2006 .

[12]  Mahesh Pal,et al.  KERNEL METHODS IN REMOTE SENSING: A REVIEW , 2009 .

[13]  Bojan Likar,et al.  Predictive control of a gas-liquid separation plant based on a Gaussian process model , 2007, Comput. Chem. Eng..

[14]  Y. K. Chow,et al.  Prediction of pile capacity from stress‐wave measurements: A neural network approach , 1995 .

[15]  Carl E. Rasmussen,et al.  Analysis of Some Methods for Reduced Rank Gaussian Process Regression , 2003, European Summer School on Multi-AgentControl.

[16]  Jie Yang,et al.  Optimizing the hyper-parameters for SVM by combining evolution strategies with a grid search , 2006 .

[17]  Dimitri P. Solomatine,et al.  Model Induction with Support Vector Machines: Introduction and Applications , 2001 .

[18]  S. Sathiya Keerthi,et al.  Efficient tuning of SVM hyperparameters using radius/margin bound and iterative algorithms , 2002, IEEE Trans. Neural Networks.

[19]  Mahesh Pal,et al.  Application of support vector machines in scour prediction on grade-control structures , 2009, Eng. Appl. Artif. Intell..

[20]  Christian Igel,et al.  Evolutionary tuning of multiple SVM parameters , 2005, ESANN.

[21]  A. Zell,et al.  Efficient parameter selection for support vector machines in classification and regression via model-based global optimization , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[22]  G G Mayerhof,et al.  Bearing Capacity and Settlement of Pile Foundations , 1976 .

[23]  E. Martin,et al.  Gaussian process regression for multivariate spectroscopic calibration , 2007 .

[24]  Tao Yu,et al.  Reliable multi-objective optimization of high-speed WEDM process based on Gaussian process regression , 2008 .

[25]  Harry M. Coyle,et al.  NEW DESIGN CORRELATIONS FOR PILES IN SAND , 1981 .

[26]  Mahesh Pal,et al.  Modeling Pile Capacity Using Support Vector Machines and Generalized Regression Neural Network , 2008 .

[27]  T. M. H. Lok,et al.  AXIAL CAPACITY PREDICTION FOR DRIVEN PILES USING ANN: MODEL COMPARISON , 2004 .

[28]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[29]  Weng Tat Chan,et al.  NEURAL NETWORK: AN ALTERNATIVE TO PILE DRIVING FORMULAS , 1995 .

[30]  C. G. Chua,et al.  Bayesian Neural Network Analysis of Undrained Side Resistance of Drilled Shafts , 2005 .

[31]  Anthony T. C. Goh,et al.  Pile Driving Records Reanalyzed Using Neural Networks , 1996 .

[32]  Neil D. Lawrence,et al.  Fast Forward Selection to Speed Up Sparse Gaussian Process Regression , 2003, AISTATS.

[33]  Roderick Murray-Smith,et al.  Switching and Learning in Feedback Systems , 2008 .

[34]  Mahesh Pal,et al.  Support vector machines‐based modelling of seismic liquefaction potential , 2006 .

[35]  Mahesh Pal,et al.  Prediction of the end-depth ratio and discharge in semi-circular and circular shaped channels using support vector machines , 2006 .

[36]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[37]  Anthony T. C. Goh,et al.  PREDICTION OF PILE CAPACITY USING NEURAL NETWORKS , 1997 .

[38]  Jiao Licheng,et al.  Automatic parameters selection for SVM based on GA , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[39]  Yan Guo,et al.  Evolutionary support vector machine and its application in remote sensing imagery classification , 2007, Geoinformatics.