Prediction of pile settlement using artificial neural networks based on standard penetration test data

In recent years artificial neural networks (ANNs) have been applied to many geotechnical engineering problems with some degree of success. With respect to the design of pile foundations, accurate prediction of pile settlement is necessary to ensure appropriate structural and serviceability performance. In this paper, an ANN model is developed for predicting pile settlement based on standard penetration test (SPT) data. Approximately 1000 data sets, obtained from the published literature, are used to develop the ANN model. In addition, the paper discusses the choice of input and internal network parameters which were examined to obtain the optimum model. Finally, the paper compares the predictions obtained by the ANN with those given by a number of traditional methods. It is demonstrated that the ANN model outperforms the traditional methods and provides accurate pile settlement predictions.     

Load-settlement behavior modeling of single piles using artificial neural networks and CPT data

Pile foundations are usually used when the conditions of the upper soil layers are weak and unable to support the super-structural loads. Piles carry these super-structural loads deep into the ground. Therefore, the safety and stability of pile-supported structures depends largely on the behavior of the piles. In addition, accurate prediction of pile behavior is necessary to ensure appropriate structural and serviceability performance. In this paper, an ANN model is developed for predicting pile behavior based on the results of cone penetration test (CPT) data. Approximately 500 data sets, obtained from the published literature, are used to develop the ANN model. The paper compares the predictions obtained by the ANN with those given by a number of traditional methods and it is observed that the ANN model significantly outperforms the traditional methods. An important advantage of the ANN model is that the complete load-settlement relationship is captured. Finally, the paper proposes a series of charts for predicting pile behavior that will be useful for pile design.     

Vertically loaded piles in non-homogeneous media

Analytical methods for the axial responses of piles can be classified under three broad categories of (1) simple but approximate analytical solutions, (2) one-dimensional numerical algorithms, (3) full axisymmetric analyses using boundary or finite element approaches. The first two categories rely on the so-called load transfer approach, with interaction between pile and soil determined by independent springs distributed along the pile shaft and at the pile base. The non-linear spring stiffness is related to the elastic–plastic properties of the actual soil partly by empirically based correlations and partly by theoretical arguments based on simplified models of the pile–soil system. This paper presents new closed-form solutions for the axial response of piles in elastic–plastic, non-homogeneous, media. The solutions fall in the first of the three categories above, and have been verified through extensive parametric studies using more rigorous one-dimensional and continuum analyses. The effect of non-homogeneity and partial slip on the load and displacement profiles along the pile shaft is explored, and comparisons are presented with experimental data. © 1997 John Wiley & Sons, Ltd.     

Estimation of air-overpressure produced by blasting operation through a neuro-genetic technique

Blasting operations usually produce significant environmental problems which may cause severe damage to the nearby areas. Air-overpressure (AOp) is one of the most important environmental impacts of blasting operations which needs to be predicted and subsequently controlled to minimize the potential risk of damage. In order to solve AOp problem in Hulu Langat granite quarry site, Malaysia, three non-linear methods namely empirical, artificial neural network (ANN) and a hybrid model of genetic algorithm (GA)–ANN were developed in this study. To do this, 76 blasting operations were investigated and relevant blasting parameters were measured in the site. The most influential parameters on AOp namely maximum charge per delay and the distance from the blast-face were considered as model inputs or predictors. Using the five randomly selected datasets and considering the modeling procedure of each method, 15 models were constructed for all predictive techniques. Several performance indices including coefficient of determination (R ²), root mean square error and variance account for were utilized to check the performance capacity of the predictive methods. Considering these performance indices and using simple ranking method, the best models for AOp prediction were selected. It was found that the GA–ANN technique can provide higher performance capacity in predicting AOp compared to other predictive methods. This is due to the fact that the GA–ANN model can optimize the weights and biases of the network connection for training by ANN. In this study, GA–ANN is introduced as superior model for solving AOp problem in Hulu Langat site.     

Piles shaft capacity from CPT and CPTu data by polynomial neural networks and genetic algorithms

Cone penetration test (CPT) is one of the most common in situ tests which is used for pile design because it can be realized as a model pile. The measured cone resistance (q_c) and sleeve friction (f_s) usually are employed for estimation of pile unit toe and shaft resistances, respectively. Thirty three pile case histories have been compiled including static loading tests performed in uplift, or in push with separation of shaft and toe resistances at sites which comprise CPT or CPTu sounding. Group method of data handling (GMDH) type neural networks optimized using genetic algorithms (GAs) are used to model the effects of effective cone point resistance (q_E) and cone sleeve friction (f_s) as input parameters on pile unit shaft resistance, applying some experimentally obtained training and test data. Sensitivity analysis of the obtained model has been carried out to study the influence of input parameters on model output. Some graphs have been derived from sensitivity analysis to estimate pile unit shaft resistance based on q_E and f_s. The performance of the proposed method has been compared with the other CPT and CPTu direct methods and referenced to measured piles shaft capacity. The results demonstrate that appreciable improvement in prediction of pile shaft capacity has been achieved.     

Use of evolutionary computing for modelling some complex problems in geotechnical engineering

In this paper, the feasibility of using evolutionary computing for solving some complex problems in geotechnical engineering is investigated. The paper presents a relatively new technique, i.e. evolutionary polynomial regression (EPR), for modelling three practical applications in geotechnical engineering including the settlement of shallow foundations on cohesionless soils, pullout capacity of small ground anchors and ultimate bearing capacity of pile foundations. The prediction results from the proposed EPR models are compared with those obtained from artificial neural network (ANN) models previously developed by the author, as well as some of the most commonly available methods. The results indicate that the proposed EPR models agree well with (or better than) the ANN models and significantly outperform the other existing methods. The advantage of EPR technique over ANNs is that EPR generates transparent and well-structured models in the form of simple and easy-to-use hand calculation formulae that can be readily used by practising engineers.     

光纤光栅传感技术在PHC管桩中不同埋设工艺试验研究

通过在同一现场针对光纤光栅传感技术在预应力高强混凝土管桩（PHC桩）测试中的应用,采用桩身表面开槽和桩身内植入的两种不同埋设工艺,进行了PHC管桩的贯入对比试验,比较了两种埋设工艺的桩身应力分布情况、桩端阻力的异同,试验研究发现:两种埋设工艺桩身轴力都随贯入深度增加而减小,桩身轴力传递速度相近,都具有相近的斜率,采用桩身内植入埋设工艺小于采用桩身表面开槽埋设工艺桩端阻力测试数据,但两者的相差幅度较小。PHC管桩桩身植入的埋设工艺光纤光栅传感器存活率较高,数据可靠,可以应用在PHC管桩的应力测试中。     

Formulation of the axisymmetric CPDI with application to pile driving in sand

In foundation engineering practice, pile driving is often used as an efficient method to install piles. While large distortions take place along the pile shaft during the installation, the zone around the pile toe experiences compression. In an attempt to fully understand the build up of resistance when driving piles, it is desirable to model the driving process and the corresponding soil behaviour. The non-linear dynamic analysis of this problem is challenging, given the large deformation that develops together with the associated changes in soil properties. Some numerical methods offer the possibility of handling large material movements by utilising Lagrangian and Eulerian frames of references. However, few of these methods are capable of tracing the material displacement, such as the Material Point Method (MPM). Early implementation of MPM assumes that the mass is concentrated at the material points, which causes noise in the solution. Later implementations assign a spatial domain to the material points to mitigate the grid crossing error. The Convected Particle Domain Interpolation (CPDI) is one such implementation.This paper extends the two-dimensional CPDI formulation for an axisymmetric problem where a pile is driven into sand that is modelled as a hypoplastic model. The extended formulation is tested, validated and compared to that for the case of the two-dimensional plane-strain within the framework of the method of manufactured solution. The hammer blows on the pile are represented by a periodic forcing function. In contrast to earlier studies on pile installation using advanced models, deep penetration is achieved in the present analysis. A non-regular distribution for the particle domains is suggested to avoid unnecessary computation. A frictional contact algorithm is introduced to describe the pile–soil interaction.     

Analysis of axial pile-soil interaction in clay

A method for predicting the maximum mobilized side resistance and unit shaft resistance-displacement curves (load transfer functions) on piles in clay is described. The method was derived using a numerical solution to model pile installation effects and a finite element scheme to model pile loading. Results of three well-documented pile load tests on steel piles were used to develop intermediate steps and final solutions, and the method was verified by comparing predicted results to two other load tests. An expression is proposed to represent load transfer functins for use by practitioners for the design of bridge and other foundations in clay.     

Prediction of ultimate axial load-carrying capacity of piles using a support vector machine based on CPT data

The support vector machine (SVM) is a relatively new artificial intelligence technique which is increasingly being applied to geotechnical problems and is yielding encouraging results. In this paper SVM models are developed for predicting the ultimate axial load-carrying capacity of piles based on cone penetration test (CPT) data. A data set of 108 samples is used to develop the SVM models. These data were obtained from the literature containing pile load tests and each sample contains information regarding pile geometry, full-scale static pile load tests and CPT results. Moreover, a sensitivity analysis is carried out to examine the relative significance of each input variable with respect to ultimate strength prediction. Finally, a statistical analysis is conducted to make comparisons between predictions obtained from the SVM models and three traditional CPT-based methods for determining pile capacity. The comparison confirms that the SVM models developed in this paper outperform the traditional methods.     

夯实水泥土桩桩身压缩量对承载特性的影响

针对夯实水泥土桩的施工方法,在桩身埋设特制的应变传感器,测定桩身应变。基于试验测试数据,探讨桩身压缩量的计算方法,分析桩身压缩变形的分布规律及其对桩侧摩阻力的影响,并探讨不同桩长、不同水泥掺入比情况下,夯实水泥土桩桩身压缩量及其对承载特性的影响。研究表明,（1）对夯实水泥土桩,桩身压缩主要集中在桩身上部8 d（d为桩径）范围内,且变形速率变化较大,桩身压缩在桩顶位移中占比达80%以上;（2）桩身轴向荷载传递、桩侧摩阻力分布主要发生在此范围内;（3）桩身侧摩阻力分布非常不均匀,上部发挥较为充分,而下部发挥较少;（4）在工程常用水泥掺入比下,桩长大于12 d后,桩长径比和水泥掺入比的变化对桩承载特性影响不显著。     

Prediction of the Rock Mass Diggability Index by Using Fuzzy Clustering-Based,ANN and Multiple Regression Methods

Rock mass classification systems are one of the most common ways of determining rock mass excavatability and related equipment assessment. However, the strength and weak points of such rating-based classifications have always been questionable. Such classification systems assign quantifiable values to predefined classified geotechnical parameters of rock mass. This causes particular ambiguities, leading to the misuse of such classifications in practical applications. Recently, intelligence system approaches such as artificial neural networks (ANNs) and neuro-fuzzy methods, along with multiple regression models, have been used successfully to overcome such uncertainties. The purpose of the present study is the construction of several models by using an adaptive neuro-fuzzy inference system (ANFIS) method with two data clustering approaches, including fuzzy c-means (FCM) clustering and subtractive clustering, an ANN and non-linear multiple regression to estimate the basic rock mass diggability index. A set of data from several case studies was used to obtain the real rock mass diggability index and compared to the predicted values by the constructed models. In conclusion, it was observed that ANFIS based on the FCM model shows higher accuracy and correlation with actual data compared to that of the ANN and multiple regression. As a result, one can use the assimilation of ANNs with fuzzy clustering-based models to construct such rigorous predictor tools.     

Groundwater-level prediction using multiple linear regression and artificial neural network techniques: a comparative assessment

The potential of multiple linear regression (MLR) and artificial neural network (ANN) techniques in predicting transient water levels over a groundwater basin were compared. MLR and ANN modeling was carried out at 17 sites in Japan, considering all significant inputs: rainfall, ambient temperature, river stage, 11 seasonal dummy variables, and influential lags of rainfall, ambient temperature, river stage and groundwater level. Seventeen site-specific ANN models were developed, using multi-layer feed-forward neural networks trained with Levenberg-Marquardt backpropagation algorithms. The performance of the models was evaluated using statistical and graphical indicators. Comparison of the goodness-of-fit statistics of the MLR models with those of the ANN models indicated that there is better agreement between the ANN-predicted groundwater levels and the observed groundwater levels at all the sites, compared to the MLR. This finding was supported by the graphical indicators and the residual analysis. Thus, it is concluded that the ANN technique is superior to the MLR technique in predicting spatio-temporal distribution of groundwater levels in a basin. However, considering the practical advantages of the MLR technique, it is recommended as an alternative and cost-effective groundwater modeling tool.     

Uncertainty analysis in bed load transport prediction of gravel bed rivers by ANN and ANFIS

River flow is a complex dynamic system of hydraulic and sediment transport. Bed load transport have a dynamic nature in gravel bed rivers and because of the complexity of the phenomenon include uncertainties in predictions. In the present paper, two methods based on the Artificial neural networks (ANN) and adaptive neuro-fuzzy inference system (ANFIS) are developed by using 360 data points. Totally, 21 different combination of input parameters are used for predicting bed load transport in gravel bed rivers. In order to acquire reliable data subsets of training and testing, subset selection of maximum dissimilarity (SSMD) method, rather than classical trial and error method, is used in finding randomly manipulation of these subsets. Furthermore, uncertainty analysis of ANN and ANFIS models are determined using Monte Carlo simulation. Two uncertainty indices of d factor and 95% prediction uncertainty and uncertainty bounds in comparison with observed values show that these models have relatively large uncertainties in bed load predictions and using of them in practical problems requires considerable effort on training and developing processes. Results indicated that ANFIS and ANN are suitable models for predicting bed load transport; but there are many uncertainties in determination of bed load transport by ANFIS and ANN, especially for high sediment loads. Based on the predictions and confidence intervals, the superiority of ANFIS to those of ANN is proved.     

The Shaft Capacity of Displacement Piles in Clay: A State of the Art Review

The rapid expansion of the offshore wind sector, coupled with increasing demand for high rise structures, has placed renewed demand on the driven piling market. In light of this industry growth, this paper reviews the evolution of design approaches for calculating the shaft capacity of displacement piles installed in cohesive soils. The transition from traditional total stress design towards effective stress methods is described. Complex stress–strain changes occur during pile installation, equalisation and load testing and as a consequence, the selection of parameters for use in conventional earth-pressure type effective stress approaches is not straight-forward. These problems have led to the development of empirical correlations between shaft resistance and in situ tests, such as the cone penetration tests. However, many of these approaches are limited because they were developed for specific geological conditions. Significant insight into pile behaviour has been obtained from recent model pile tests, which included reliable measurements of radial effective stresses. These tests have allowed factors such as friction fatigue and interface friction to be included explicitly in design methods. Whilst analytical methods have been developed to investigate pile response, these techniques cannot yet fully describe the complete stress–strain history experienced by driven piles. The use of analytical methods in examining features of pile behaviour, such as the development of pore pressure during installation and the effects of pile end geometry on pile capacity, is discussed.     

Prediction of Uplift Pile Displacement Based on Cone Penetration Tests (CPT)

Accurate prediction of uplift pile displacement is necessary to ensure appropriate structural and serviceability performance of civil projects. On the other hand, in recent years, machine-learning models have been applied to many geotechnical-engineering problems, with some degrees of success. The scope of this research includes three main stages: (1) the compilation of load–displacement data sets, obtained from the published literature, (2) analysis of machine learning models that predict the uplift pile displacement based on the cone penetration test data, and the relative importance of input parameters that have been evaluated using senility analysis by the artificial neural network, In addition, this paper also examines the different selection of input parameters and internal network parameters to obtain the optimum model, (3) A parametric study has also been performed for the input parameters to study the consistency of the suggested model. The statistical parameters and parametric study obtained in this research show the superiority of the current model. It is demonstrated that machine learning models such as ANN and GP models outperform the traditional methods, and provide accurate uplift pile displacement predictions.     

Analytical solution for distributed torsional low strain integrity test for pipe pile

Low strain integrity tests (LSITs) are the most popular non-destructive methods for pile testing. However, traditional LSITs have encountered unprecedented challenges as the need for long pile and existing pile testing keeps multiplying. Compared to traditional longitudinal excitations, the torsional wave is less influenced by the velocity attenuation effect and can be subjected at the pile shaft for existing piles. Distributed torsional LSIT is proposed in this article with the presentation of the corresponding analytical solutions that exhibiting the velocity responses along the pile shaft. The solution is verified with previous simplified theoretical and rigorous finite element method (FEM) answers. At the end, the application of this method is exhibited through the identification of necking and concrete segregation defects on pipe piles, which shows the advantage of this method on long pile testing.     

Reliability analysis of drilled shaft behavior using finite difference method and <Emphasis Type="Italic">Monte Carlo</Emphasis> simulation

Load displacement analysis of drilled shafts can be accomplished by utilizing the “t-z” method, which models soil resistance along the length and tip of the drilled shaft as a series of springs. For non-linear soil springs, the governing differential equation that describes the soil-structure interaction may be discretized into a set of algebraic equations based upon finite difference methods. This system of algebraic equations may be solved to determine the load–displacement behavior of the drilled shaft when subjected to compression or pullout. By combining the finite difference method with Monte Carlo simulation techniques, a probabilistic load–displacement analysis can be conducted. The probabilistic analysis is advantageous compared to standard factor of safety design because uncertainties with the shaft–soil interface and tip properties can be independently quantified. This paper presents a reliability analysis of drilled shaft behavior by combining the finite difference technique for analyzing non-linear load–displacement behavior with Monte Carlo simulation method. As a result we develop probabilistic relationships for drilled shaft design for both total stress (undrained) and effective stress (drained) parameters. The results are presented in the form of factor of safety or resistance factors suitable for serviceability design of drilled shafts.     

基坑开挖时立柱桩的沉降计算

在基坑工程中,立柱桩和工程桩形成了长短桩复合桩基础。通过有限元法模拟桩侧摩阻力分布的变化,认为在这种复合桩基础中短桩（工程桩）的存在会影响到长桩（立柱桩）桩侧摩阻力的分布。根据剪切位移法得到考虑短桩影响的计算方法,并将被影响后的长桩桩侧摩阻力分布形式做了等量简化,使之适用于Geddes应力法。提出了利用Geddes应力法计算长短桩复合桩基础沉降的方法,并编制了相应的计算程序PLS,根据实际工程资料进行验算的结果与实测数据基本一致。     

Growth-rate-dependent prediction of pile set-up and its application in driven pile foundation construction

In this paper research was presented on the development of a growth-rate-dependent model for pile set-up prediction using the restrike and static/statnamic load testing data collected from different projects. The data included: a) restrike records from ninety-five production piles and restrike and load test results of nine instrumented piles driven in soft clays from the relocation project of Highway No. 1 in Louisiana (LA-1); and b) restrike and static load testing data of five fully instrumented square PPC piles driven at four different bridge sites in various soil layers from sands to clays in Florida. Research effort was focused on the prediction of the ultimate shaft resistances with pile set-up formulated using the pile resistance growth rate-dependent model. The timeframe of interest was studied for a practical set-up magnitude such as 90% of the ultimate shaft resistance (Q₉₀). As an application of the rate-dependent model, it was found that piles at the LA-1 relocation project, in general, reached about 95% of the ultimate shaft resistances at the time of 2 weeks after pile installation. The strategy of incorporation of pile set-up in adjusting pile driving criteria or/and design during pile construction, such as the experience-based plan of a two-week waiting period adopted by Louisiana DOTD, was investigated and justified.