Intelligent modelling of clay compressibility using hybrid meta-heuristic and machine learning algorithms

Compression index Ccis an essential parameter in geotechnical design for which the effectiveness of correlation is still a challenge.This paper suggests a novel modelling approach using machine learning(ML)technique.The performance of five commonly used machine learning(ML)algorithms,i.e.back-propagation neural network(BPNN),extreme learning machine(ELM),support vector machine(SVM),random forest(RF)and evolutionary polynomial regression(EPR)in predicting Cc is comprehensively investigated.A database with a total number of 311 datasets including three input variables,i.e.initial void ratio e0,liquid limit water content wL,plasticity index Ip,and one output variable Cc is first established.Genetic algorithm(GA)is used to optimize the hyper-parameters in five ML algorithms,and the average prediction error for the 10-fold cross-validation(CV)sets is set as thefitness function in the GA for enhancing the robustness of ML models.The results indicate that ML models outperform empirical prediction formulations with lower prediction error.RF yields the lowest error followed by BPNN,ELM,EPR and SVM.If the ranges of input variables in the database are large enough,BPNN and RF models are recommended to predict Cc.Furthermore,if the distribution of input variables is continuous,RF model is the best one.Otherwise,EPR model is recommended if the ranges of input variables are small.The predicted correlations between input and output variables using five ML models show great agreement with the physical explanation.

An improved artificial bee colony-random forest(IABC-RF)model for predicting the tunnel deformation due to an adjacent foundation pit excavation

An improved artificial bee colony-random forest(IABC-RF)model is proposed for predicting the tunnel deformation due to the excavation of an adjacent foundation pit.A new search strategy of the artificial bee colony(ABC)algorithm is herein developed and incorporated,with the results showing that a much higher computational efficiency can be achieved with the new model,while high computational accuracy can also be maintained.The improved ABC algorithm is thereafter utilised and combined with the random forest(RF)model,where four important hyper-parameters are optimized,for a tunnel deformation prediction.Results are thoroughly compared with those of other prediction methods based on machine learning(ML),as well as the monitored data on the site.Via the comparisons,the validity and effectiveness of the proposed model are fully demonstrated,and a more promising perspective can be seen of the method for its potential wide applications in geotechnical engineering.

Large deformation analysis in geohazards and geotechnics

For geohazards and geotechnics,numerous problems involve large deformation,such as the installation of foundations(Jin YF et al.,2018a),landslides(Jin YF et al.,2020b),debris flow(Dai et al.,2017),collapse of underground structures(Zhang et al.,2019),and the formation of sinkholes(Baran-diaran Villegas,2018).Benefitting from the sustained development of computing power,numerical simulations have become useful analytical methods in geomechanics and related fields.

Practice of artificial intelligence in geotechnical engineering

Geotechnical engineering deals with materials(e.g.soil and rock)that,by their very nature,exhibit varied and uncertain behavior due to the imprecise physical processes associated with their formation(Mitchell and Soga,2005).Modeling the behavior of such materials in geotechnical engineering applications is complex and sometimes beyond the ability of most traditional forms of physically-based engineering methods.In recent years,the application of artificial intelligence(AI)in a wide range of geotechnical engineering has grown rapidly(Nawari et al.,1999;Miranda,2007;Javadi and Rezania,2009;Shahin,2013,2016;Chen et al.,2018;Yin et al.,2018;Jin et al.,2019a,2019b,2019c;Zhang P et al.,2020a).

Influence of natural deposition plane orientation on oedometric consolidation behavior of three typical clays from southeast coast of China

The parameters obtained from oedometric consolidation tests are commonly used in the development of constitutive modeling and for engineering practice. This paper focuses on the influence of the natural deposition plane orientation on oedometric consolidation behavior of three natural clays from the southeast coast of China. Oedometer tests were conducted on intact specimens prepared by sampling at a series of angles relative to the natural deposition plane. For each specimen, yield stress,compressibility indexes, secondary compression, and permeability coefficients were determined. The influence of the sampling angle on these properties was investigated, revealing that yield stress, compression index, swelling index, creep index, ratio of secondary compression coefficient to compression index(Cae/Cc) and permeability coefficient were all dependent to some extent on the sampling angle. These findings indicate the role of the anisotropy due to the natural deposition on the oedometric consolidation behavior.

一个结构性软土参数的确定方法（英文）

目的:软土流变和结构破坏的相互耦合导致结构性软土的参数难以准确得到。本文拟建立一个有效的参数确定方法,期望仅基于常规的室内试验得到可靠的、合理的本构参数。创新点:1.通过采用优化方法来实现结构性软土参数的确定;2.仅基于常规的室内试验得到本构参数;3.采用最近提出的考虑各向异性、流变和结构破坏的超应力本构模型。方法:1.建立数值模拟和试验数据之间的误差计算公式;2.通过流变本构模拟室内常规试验,并计算模拟误差;3.采用下山单纯形法(simplex)优化方法,寻找模拟误差的最小值;此最小值对应的这组模拟参数即为土体的最优参数;4.利用最优参数模拟其他类型的试验,验证参数的合理性和可靠性。结论:本文提出的优化程序可以有效的找到结构性土体的流变和结构破坏参数,并且找到的参数非常的合理。