Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Modelling the mechanical behaviour of soils using machine learning algorithms with explicit formulations
This study systematically presents the application of machine learning (ML) algorithms for constructing a constitutive model for soils. A genetic algorithm is integrated with ML algorithms to determine the global optimum model, and the k-fold cross-validation method is used to enhance the models’ robustness. Three typical ML algorithms with formulations explicitly expressed [i.e., back-propagation neural network (BPNN), extreme learning machine (ELM) and evolutionary polynomial regression (EPR)], and two modelling strategies (i.e. total or incremental stress–strain strategies) are used. A synthetic database is first generated based on a simple constitutive model to objectively evaluate the performance of three ML algorithms and two modelling strategies. Next, the optimum ML algorithm and the well evaluated modelling strategy are applied to experimental tests for examining its robustness. All results indicate that a BPNN-based constitutive model using the incremental stress–strain strategy performs best in modelling the mechanical behaviour of soils in terms of interpolation and extrapolation abilities, followed by ELM and then EPR.
Modelling the mechanical behaviour of soils using machine learning algorithms with explicit formulations
This study systematically presents the application of machine learning (ML) algorithms for constructing a constitutive model for soils. A genetic algorithm is integrated with ML algorithms to determine the global optimum model, and the k-fold cross-validation method is used to enhance the models’ robustness. Three typical ML algorithms with formulations explicitly expressed [i.e., back-propagation neural network (BPNN), extreme learning machine (ELM) and evolutionary polynomial regression (EPR)], and two modelling strategies (i.e. total or incremental stress–strain strategies) are used. A synthetic database is first generated based on a simple constitutive model to objectively evaluate the performance of three ML algorithms and two modelling strategies. Next, the optimum ML algorithm and the well evaluated modelling strategy are applied to experimental tests for examining its robustness. All results indicate that a BPNN-based constitutive model using the incremental stress–strain strategy performs best in modelling the mechanical behaviour of soils in terms of interpolation and extrapolation abilities, followed by ELM and then EPR.
Modelling the mechanical behaviour of soils using machine learning algorithms with explicit formulations
Acta Geotech.
Zhang, Pin (Autor:in) / Yin, Zhen-Yu (Autor:in) / Jin, Yin-Fu (Autor:in) / Liu, Xian-Feng (Autor:in)
Acta Geotechnica ; 17 ; 1403-1422
01.04.2022
20 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Constitutive model , Extreme learning machine , Evolutionary computation , Neural network , Optimization , Soils Engineering , Geoengineering, Foundations, Hydraulics , Solid Mechanics , Geotechnical Engineering & Applied Earth Sciences , Soil Science & Conservation , Soft and Granular Matter, Complex Fluids and Microfluidics
Material Behaviour Modelling using Machine Learning Model
| British Library Online Contents | 2006
Some open questions in modelling the mechanical behaviour of soils
| British Library Conference Proceedings | 2001
Elastoplastic modelling of hydraulic and mechanical behaviour of expansive soils
| British Library Conference Proceedings | 2011