Bayesian network based machine learning for design of pile foundations

Abstract Realistic estimation of the uncertainty associated with the bearing capacity, which is often represented by the uncertainty of a model bias factor, is important to reliability-based design of pile foundations. Due to the existence of cross-site variability, the statistics of a model bias factor may vary from one site to another. Also, as the number of site-specific load test data is often very limited, it is difficult to obtain the site-specific statistics of the model bias factor. This paper aims to establish a Bayesian network based machine learning method to develop site-specific statistics of the model bias factor utilizing information from both the regional and site-specific load test data, through which the resistance factor for design of the pile foundation can be calibrated. The suggested method has been verified using a comprehensive load test database for design of driven piles in Shanghai, China. It is found that a few site-specific pile load test data can significantly reduce the uncertainty associated with the model bias factor and hence increase the cost-effectiveness of the pile design. The method suggested in this paper lays a sound foundation for site-specific reliability-based design of pile foundations, and provides useful insight into the planning of site-specific load tests for design of pile foundations.

[1]  Volker Schmid,et al.  Statistical and syntactic pattern recognition , 2014 .

[2]  R. K. Rowe.  Pile foundation analysis and design: Book review , 1981 .

[3]  Li Min Zhang.  RELIABILITY VERIFICATION USING PROOF PILE LOAD TESTS , 2004 .

[4]  Dian-Qing Li,et al.  Reliability of bored pile foundations considering bias in failure criteria , 2005 .

[5]  David Maxwell Chickering,et al.  Learning Bayesian Networks: The Combination of Knowledge and Statistical Data , 1994, Machine Learning.

[6]  Amir Hossein Alavi,et al.  Machine learning in geosciences and remote sensing , 2016 .

[7]  Stuart German,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1988 .

[8]  F. Necati Catbas,et al.  A machine learning-based algorithm for processing massive data collected from the mechanical components of movable bridges , 2016 .

[9]  Yi Li,et al.  Susceptibility assessment of earthquake-induced landslides using Bayesian network: A case study in Beichuan, China , 2012, Comput. Geosci..

[10]  Oswaldo Morales-Nápoles,et al.  Reliability analysis of reinforced concrete vehicle bridges columns using non-parametric Bayesian networks , 2019, Engineering Structures.

[11]  Kok-Kwang Phoon,et al.  Measuring Similarity between Site-Specific Data and Records from Other Sites , 2020 .

[12]  James N. M. Smith,et al.  Bayesian meta‐analysis of demographic parameters in three small, temperate passerines , 2000 .

[13]  Dina D'Ayala,et al.  Development of Bayesian Networks for the multi-hazard fragility assessment of bridge systems , 2016 .

[14]  Wilson H. Tang,et al.  Expected Design Factor of Safety from a Pile Load Test Program , 2010 .

[15]  Zhongjie Zhang,et al.  Calibration of Side, Tip, and Total Resistance Factors for Load and Resistance Factor Design of Drilled Shafts , 2012 .

[16]  Bruno Sudret,et al.  Bayesian Multilevel Model Calibration for Inverse Problems Under Uncertainty with Perfect Data , 2015, J. Aerosp. Inf. Syst..

[17]  Adel Javanmard,et al.  Learning Linear Bayesian Networks with Latent Variables , 2012, ICML.

[18]  K. Phoon,et al.  Characterization of model uncertainty in predicting axial resistance of piles driven into clay , 2019, Canadian Geotechnical Journal.

[19]  Kok-Kwang Phoon,et al.  Characterisation of geotechnical model uncertainty , 2019, Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards.

[20]  Rafael Rumí,et al.  Bayesian networks in environmental modelling , 2011, Environ. Model. Softw..

[21]  L. Hedges,et al.  Introduction to Meta‐Analysis , 2009, International Coaching Psychology Review.

[22]  Hareton K. N. Leung,et al.  Assessment of Catastrophic Risk Using Bayesian Network Constructed from Domain Knowledge and Spatial Data , 2010, Risk analysis : an official publication of the Society for Risk Analysis.

[23]  David J. Spiegelhalter,et al.  Bayesian graphical modelling: a case‐study in monitoring health outcomes , 2002 .

[24]  Dennis E Becker,et al.  EIGHTEENTH CANADIAN GEOTECHNICAL COLLOQUIUM: LIMIT STATES DESIGN FOR FOUNDATIONS. PART II. DEVELOPMENT FOR THE NATIONAL BUILDING CODE OF CANADA , 1996 .

[25]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[26]  Kok-Kwang Phoon,et al.  Constructing Site-Specific Multivariate Probability Distribution Model Using Bayesian Machine Learning , 2019, Journal of Engineering Mechanics.

[27]  Sankaran Mahadevan,et al.  Bayesian Network Learning for Data-Driven Design , 2018 .

[28]  Richard E. Neapolitan,et al.  Learning Bayesian networks , 2007, KDD '07.

[29]  Dan M. Frangopol,et al.  Probabilistic optimization framework for inspection/repair planning of fatigue-critical details using dynamic Bayesian networks , 2018 .

[30]  Muhammad Qaiser Saleem,et al.  Phagocytosis-based camera-in-situ method for pile load testing , 2014 .

[31]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[32]  Kash Barker,et al.  Modeling infrastructure resilience using Bayesian networks: A case study of inland waterway ports , 2016, Comput. Ind. Eng..

[33]  Michael Havbro Faber,et al.  Risk Assessment of Decommissioning Options Using Bayesian Networks , 2002 .

[34]  José Carlos Príncipe,et al.  Irregular Tree-Structured Bayesian Network for image segmentation , 2011, 2011 IEEE International Workshop on Machine Learning for Signal Processing.

[35]  Yiannis Xenidis,et al.  Risk source-based constructability appraisal using supervised machine learning , 2019, Automation in Construction.

[36]  Hongwei Huang,et al.  Calibrating cross-site variability for reliability-based design of pile foundations , 2014 .

[37]  Wilson H. Tang,et al.  Probability concepts in engineering planning and design , 1984 .

[38]  Kok-Kwang Phoon,et al.  Statistics of model factors in reliability-based design of axially loaded driven piles in sand , 2018, Canadian Geotechnical Journal.

[39]  Adnan Darwiche,et al.  Modeling and Reasoning with Bayesian Networks , 2009 .

[40]  Tao Chen,et al.  Latent Tree Models and Approximate Inference in Bayesian Networks , 2008, AAAI.

[41]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[42]  Ove Ditlevsen,et al.  Bayesian soil assessments combining prior with posterior censored samples , 2000 .

[43]  David B. Dunson,et al.  Bayesian Data Analysis , 2010 .

[44]  HosseiniSeyedmohsen,et al.  Modeling infrastructure resilience using Bayesian networks , 2016 .

[45]  C. H. Juang,et al.  Reliability-based code revision for design of pile foundations: Practice in Shanghai, China , 2015 .

[46]  Jie Zhang,et al.  Geotechnical reliability analysis with limited data: Consideration of model selection uncertainty , 2014 .

[47]  Azad Yazdani,et al.  Bayesian networks for disaggregation of structural reliability , 2020 .