Stabilization of Organic Soils with Fly Ash

The effectiveness of fly ash use in the stabilization of organic soils and the factors that are likely to affect the degree of stabilization were studied. Unconfined compression and resilient modulus tests were conducted on organic soil–fly ash mixtures and untreated soil specimens. The unconfined compressive strength of organic soils can be increased using fly ash, but the amount of increase depends on the type of soil and characteristics of the fly ash. Resilient moduli of the slightly organic and organic soils can also be significantly improved. The increases in strength and stiffness are attributed primarily to cementing caused by pozzolanic reactions, although the reduction in water content resulting from the addition of dry fly ash solid also contributes to strength gain. The pozzolonic effect appears to diminish as the water content decreases. The significant characteristics of fly ash that affect the increase in unconfined compressive strength and resilient modulus include CaO content and CaO/SiO2 ratio [or CaO/(SiO2+Al2O3) ratio]. Soil organic content is a detrimental characteristic for stabilization. Increase in organic content of soil indicates that strength of the soil–fly ash mixture decreases exponentially. For most of the soil–fly ash mixtures tested, unconfined compressive strength and resilient modulus increased when fly ash percentage was increased.     

Neural Networks for Profiling Stress History of Clays from PCPT Data

This paper evaluates the feasibility of using artificial neural network (ANN) models for estimating the overconsolidation ratio (OCR) of clays from piezocone penetration tests (PCPT). Three feed-forward, back-propagation ANN models are developed, and trained using actual PCPT records from test sites around the world. The soil deposits range from soft, normally consolidated intact clays to very stiff, heavily overconsolidated fissured clays. ANN model 1 is a general model applicable for both intact and fissured clays. ANN model 2 is suited for intact clays, and ANN model 3 is applicable to fissured clays only. The models are validated using new PCPT data (not used for training), and by comparing model predictions with reference OCR values obtained from oedometer tests. For intact clays, ANN model 2 gives better OCR estimates compared to ANN model 1. For fissured clays, ANN model 3 gives better estimates compared to ANN model 1. Some of the existing interpretation methods are reviewed. Compared to the existing methods, ANN models 2 and 3 give very good estimates of OCR.     

Suction-Controlled Laboratory Test on Resilient Modulus of Unsaturated Compacted Subgrade Soils

Conventionally, the resilient modulus test is conducted in the laboratory under different moisture content in which matric suction is unknown during the test. To investigate the influence of the matric suction on the resilient modulus, this study integrated the suction-controlled testing system and developed a modified testing procedure for the resilient modulus test of unsaturated subgrade soils. Based on the axis-translation technique, two cohesive soils were tested to investigate the effect of matric suction on resilient modulus. In the modified testing procedure, in order to fulfill the equilibrium in matric suction, the number of load cycles at each loading sequence of the resilient modulus test (AASHTO T 292-91) needs to be increased significantly. Experimental data indicate that matric suctions measured in the specimen after consolidation and resilient modulus tests are consistent with the matric suctions deduced from the soil-water characteristic curve corresponding to the same moisture content. In general, the resilient modulus obtained by the suction-controlled resilient modulus test appears to be reasonable. The trends of resilient modulus obtained by the suction-controlled resilient modulus test are consistent with those obtained by the conventional resilient modulus test. However, the suction-controlled resilient modulus test provides better insights that can help in interpreting the test results.     

Experimental and Modeling Studies of Permanent Strains of Subgrade Soils

Mechanistic-empirical pavement design guide for flexible pavements as per the AASHTO design guide requires characterization of subgrade soils using the resilient modulus (MR) property. This property, however, does not fully account for the plastic or permanent strain or rutting of subgrade soils, which often distress the overlying pavements. Soils such as silts exhibit moderate to high resilient moduli properties but they still undergo large permanent deformations under repeated loading. This explains the fallacy in the current pavement material characterization practice. A comprehensive research study was performed to measure permanent deformation properties of subgrade soils by subjecting various soils under repeated cycles of deviatoric loads. This paper describes test procedure followed and results obtained on three soils including clay, silt, and sandy soils. The influence of compaction moisture content, confining pressure, and deviatoric stresses applied on the measured permanent deformations of all three soils are addressed. A four-parameter permanent strain model formulation as a function of stress states in soils and the number of loading cycles was used to model and analyze the present test results. The model constants of all three soils were first determined and these results were used to explain the effects of various soil properties on permanent deformations of soils. Validation studies were performed to address the adequacy of the formulated model to predict rutting or permanent strains in soils.     

Application of Statistical and Machine Learning Techniques for Laboratory-Scale Pressure Filtration: Modeling and Analysis of Cake Moisture

This study deals with the modeling and analysis of the pressure filtration process using statistical and machine learning techniques. The effects of externally controllable process-influencing factors such as pressure, pH, temperature, solids concentration, filtration time, air-blow time, and cake thickness on filtration performance, measured in terms of cake moisture, were modeled. A 9-factor regression model based on an exhaustive search algorithm and a 7-6-1 artificial neural network (ANN) model based on a resilient backpropagation algorithm were developed and gave R² values of 0.84 and 0.94, respectively. Relative importance of input variables was analyzed using novel methods such as added-variable plots based on the regression model and Olden’s method based on the ANN model. Results from both methods established a negative correlation for pressure, solids concentration, filtration time, temperature, and air-blow time and a positive correlation for cake thickness and pH. Analysis from regression and ANN models indicated pH to be the most significant process-influencing factor. Even though both models served as good interpretable models, the ANN model outperformed the regression model in terms of predictive capability, with an R² value of 0.965 compared with the regression model’s 0.750 for the test dataset.     

Resilient Properties of Unbound Road Materials during Seasonal Frost Conditions

During recent decades, a considerable amount of research has been devoted to the resilient properties of unbound road materials. However, the severe effects of cold region climates on resilient behavior have been less exhaustibly investigated. In this study, the results from extensive resilient modulus laboratory tests during full freeze-thaw cycling are presented. Various coarse and fine-grained subgrade soils were tested at selected temperatures from room temperature down to ?10°C and back to room temperature. The soils are frozen and thawed inside a triaxial cell, thus eliminating external disturbances due to handling. The results indicate that all the soils exhibited a substantially reduced resilient modulus after the freeze-thaw cycle. A significant hysteresis for the clay soil in warming and cooling was also observed. This paper presents equations for different conditions. The equations may be used for selecting the appropriate resilient modulus value in current and future evaluation and design methods.     

Neural network modelling of flow stress and mechanical properties for hot strip rolling of TRIP steel using efficient learning algorithm

Abstract

Transformation induced plasticity (TRIP) steels exhibit excellent strength and ductility and can be engineered to provide excellent formability for manufacturing complex parts. In this study, a data driven multi-input multi-output multilayer perceptron based neural network model has been developed to predict the flow stress, yield strength, ultimate tensile strength and elongation as a function of composition and thermomechanical processing parameters for strip rolling of TRIP steels. The input parameters in this generalised regression artificial neural network (ANN) model are steel chemistry, cooling rate and finish roll temperature. The network training architecture has been optimised using the Broyden–Fletcher–Goldfarb–Shanno algorithm to minimise the network training error within few training cycles. The algorithm facilitates a faster convergence of network training and testing errors. There has been an excellent agreement between the ANN model predictions and the target (measured) values for flow stress and mechanical properties depicted by the respective regression fit between these values.     

Predicting Longitudinal Dispersion Coefficient in Natural Streams by Artificial Neural Network

An artificial neural network (ANN) model was developed to predict the longitudinal dispersion coefficient in natural streams and rivers. The hydraulic variables [flow discharge (Q), flow depth (H), flow velocity (U), shear velocity (u*), and relative shear velocity (U/u*)] and geometric characteristics [channel width (B), channel sinuosity (σ), and channel shape parameter (β)] constituted inputs to the ANN model, whereas the dispersion coefficient (Kx) was the target model output. The model was trained and tested using 71 data sets of hydraulic and geometric parameters and dispersion coefficients measured on 29 streams and rivers in the United States. The training of the ANN model was accomplished with an explained variance of 90% of the dispersion coefficient. The dispersion coefficient values predicted by the ANN model satisfactorily compared with the measured values corresponding to different hydraulic and geometric characteristics. The predicted values were also compared with those predicted using several equations that have been suggested in the literature and it was found that the ANN model was superior in predicting the dispersion coefficient. The results of sensitivity analysis indicated that the Q data alone would be sufficient for predicting more frequently occurring low values of the dispersion coefficient (Kx<100?m2/s). For narrower channels (B/H<50) using only U/u* data would be sufficient to predict the coefficient. If β and σ were used along with the flow variables, the prediction capability of the ANN model would be significantly improved.     

Case Study: Finite Element Method and Artificial Neural Network Models for Flow through Jeziorsko Earthfill Dam in Poland

A finite element method (FEM) and an artificial neural network (ANN) model were developed to simulate flow through Jeziorsko earthfill dam in Poland. The developed FEM is capable of simulating two-dimensional unsteady and nonuniform flow through a nonhomogenous and anisotropic saturated and unsaturated porous body of an earthfill dam. For Jeziorsko dam, the FEM model had 5,497 triangular elements and 3,010 nodes, with the FEM network being made denser in the dam body and in the neighborhood of the drainage ditches. The ANN model developed for Jeziorsko dam was a feedforward three layer network employing the sigmoid function as an activator and the back-propagation algorithm for the network learning. The water levels on the upstream and downstream sides of the dam were input variables and the water levels in the piezometers were the target outputs in the ANN model. The two models were calibrated and verified using the piezometer data collected on a section of the Jeziorsko dam. The water levels computed by the models satisfactorily compared with those measured by the piezometers. The model results also revealed that the ANN model performed as good as and in some cases better than the FEM model. This case study offers insight into the adequacy of ANN as well as its competitiveness against FEM for predicting seepage through an earthfill dam body.     

Support Vector Machines Approach to HMA Stiffness Prediction

The application of artificial intelligence (AI) techniques to engineering has increased tremendously over the last decade. Support vector machine (SVM) is one efficient AI technique based on statistical learning theory. This paper explores the SVM approach to model the mechanical behavior of hot-mix asphalt (HMA) owing to high degree of complexity and uncertainty inherent in HMA modeling. The dynamic modulus (|E?|), among HMA mechanical property parameters, not only is important for HMA pavement design but also in determining HMA pavement performance associated with pavement response. Previously employed approaches for development of the predictive |E?| models concentrated on multivariate regression analysis of database. In this paper, SVM-based |E?| prediction models were developed using the latest comprehensive |E?| database containing 7,400 data points from 346 HMA mixtures. The developed SVM models were compared with the existing multivariate regression-based |E?| model as well as the artificial neural networks (ANN) based |E?| models developed recently by the writers. The prediction performance of SVM model is better than multivariate regression-based model and comparable to the ANN. Fewer constraints in SVM compared to ANN can make it a promising alternative considering the availability of limited and nonrepresentative data frequently encountered in construction materials characterization.     

ANN and Fuzzy Logic Models for Simulating Event-Based Rainfall-Runoff

This study presents the development of artificial neural network (ANN) and fuzzy logic (FL) models for predicting event-based rainfall runoff and tests these models against the kinematic wave approximation (KWA). A three-layer feed-forward ANN was developed using the sigmoid function and the backpropagation algorithm. The FL model was developed employing the triangular fuzzy membership functions for the input and output variables. The fuzzy rules were inferred from the measured data. The measured event based rainfall-runoff peak discharge data from laboratory flume and experimental plots were satisfactorily predicted by the ANN, FL, and KWA models. Similarly, all the three models satisfactorily simulated event-based rainfall-runoff hydrographs from experimental plots with comparable error measures. ANN and FL models also satisfactorily simulated a measured hydrograph from a small watershed 8.44?km2 in area. The results provide insights into the adequacy of ANN and FL methods as well as their competitiveness against the KWA for simulating event-based rainfall-runoff processes.     

Response Analysis of Field-Scale Fully Grouted Standard Cable Bolts Using a Coupled ANN–FDM Approach

This paper presents a coupled approach using an artificial neural network (ANN) and the finite difference method (FDM) that has been developed to predict the distribution of axial load along fully grouted standard cable bolts in the field using laboratory pullout test data. A back-propagation training algorithm was used in ANN to determine axial loads in the cables tested in the laboratory. The ANN component of the computational model was trained using two different types of data sets. At first, the ANN was trained to predict the axial loads in a series of short cables grouted with Portland cement at a specific water-to-cement ratio and subjected to different radial confining stiffness values. Next, the ANN model was trained for an expanded case to include the influence of lateral confining stress on the distribution of axial load in the cable reinforcement. Finally, the ANN model was implemented into a widely used, FDM-based geotechnical software (FLAC). The accuracy of the ANN–FDM model is demonstrated in this paper against measured data from laboratory and field tests. The analysis approach introduced in this study is a valuable computational tool that can be used to determine the axial load distribution in long standard cable bolts, which are commonly installed to stabilize rock masses in various geotechnical, transportation, and mining applications.     

Mechanistic Corrections for Determining the Resilient Modulus of Base Course Materials Based on Elastic Wave Measurements

The mechanical performance of pavement systems depends on the stiffness of subsurface soil and aggregate materials. The moduli of base course, subbase, and subgrade soils included in pavement systems need to be characterized for their use in the new empirical-mechanistic design procedure (NCHRP 1-37A). Typically, the resilient modulus test is used in the design of base and subbase layers under repetitive loads. Unfortunately, resilient modulus tests are expensive and cannot be applied to materials that contain particles larger than 25 mm (for 125-mm diameter specimens) without scalping the large grains. This paper examines a new methodology for estimating resilient modulus based on the propagation of elastic waves. The method is based on using a mechanistic approach that relates the P-wave velocity-based modulus to the resilient modulus through corrections for stress, void ratio, strain, and Poisson’s ratio effects. Results of this study indicate that resilient moduli are approximately 30% of Young’s moduli based on seismic measurements. The technique is then applied to specimens with large-grain particles. Results show that the methodology can be applied to large-grained materials and their resilient modulus can be estimated with reasonable accuracy based on seismic techniques. An approach is proposed to apply the technique to field determinations of modulus.     

Use of Artificial Neural Networks in the Prediction of Liquefaction Resistance of Sands

A backpropagation artificial neural network (ANN) model has been developed to predict the liquefaction cyclic resistance ratio (CRR) of sands using data from several laboratory studies involving undrained cyclic triaxial and cyclic simple shear testing. The model was verified using data that was not used for training as well as a set of independent data available from laboratory cyclic shear tests on another soil. The observed agreement between the predictions and the measured CRR values indicate that the model is capable of effectively capturing the liquefaction resistance of a number of sands under varying initial conditions. The predicted CRR values are mostly sensitive to the variations in relative density thus confirming the ability of the model to mimic the dominant dependence of liquefaction susceptibility on soil density already known from field and experimental observations. Although it is common to use mechanics-based approaches to understand fundamental soil response, the results clearly demonstrate that non-mechanistic ANN modeling also has a strong potential in the prediction of complex phenomena such as liquefaction resistance.     

Limit-State Curve of Base-Course Material and Its Relevance for Resilient Modulus Testing

The limit state characteristics of base-course granular materials were obtained using a typical triaxial testing equipment devoted to the measurement of resilient modulus. Accurate monitoring of axial strain during isotropic and anisotropic compression was used to determine the stress conditions where significant irrecoverable strains occur for samples prepared by static compression, Proctor rammer, and vibratory compaction. The limit state curve is highly anisotropic, centered about the q/p = 1 line. It is sensitive to sample preparation technique and fines content. The Strategic Highway Research Program (SHRP) procedure corresponds to stress paths during conditioning and repeated loading that remain within the limit state curve of the control base course material containing 3.5% fines. The resilient modulus values reflect henceforth the behaviour of the same material with its original particle contact distribution. The Laboratoires des Ponts et Chaussées (LCPC) procedure is characterized by stress paths that cross the original limit state curve of the Proctor compacted samples. Particle contact distribution changes thus continuously as the limit state curve expands in response to the various stress paths used in this procedure. The resilient modulus values correspond to samples with different fabrics. A simple procedure based on isotropic loading has been proposed for the determination of a simplified limit state curve of base course materials with the intent of specifying the testing conditions for obtaining adequate resilient modulus values.     

Prediction of shape defects over length of cold rolled sheet using artificial neural networks

Abstract

A model based on an artificial neural network (ANN) has been developed for prediction of flatness of cold rolled (CR) sheet in a tandem cold rolling mill for white goods applications. Various process parameters including roll bending, roll shifting, tensions between stands etc., which affect flatness of CR sheet are considered in the model. Substantial amounts of data are obtained from level II automation of PL-TCM of TATA Steel to develop the prediction model. The developed ANN model, based on back propagation algorithm, is able to predict the flatness defects like edge buckles, centre buckles for a given set of rolling parameters. The model involves a large number of process parameters and application of ANN to such kind of problems is successfully demonstrated in the present study. The model is in good agreement with the observed flatness values at different locations across the width. High coefficient of determination close to 0·919 is achieved for the prediction of flatness at edges.     

基于LR-ANN-SVM的滑坡易发性评价

针对传统大数据机器学习等方法进行滑坡易发性评价时,存在过于追求模型评价精度,导致在中易发区与低易发区存在滑坡产生的风险,提出了风险预警来降低中与低易发区产生的滑坡灾害。选取神经网络模型（ANN）、逻辑回归模型（LR）、支持向量机模型（SVM）3种学习方法,对上犹县进行滑坡易发性评价,将上犹县分为高易发区、较高易发区、中易发区、较低易发区,低易发区。由受试者工作曲线（ROC）下的面积（AUC)显示:神经网络（ANN）的AUC=0.939, 逻辑回归模型（LR）的AUC=0.897, 支持向量机（SVM）的AUC=0.884,均具有较高的评价精度。根据以上的易发性评价结果,得到上犹县栅格的易发性指数（LSI）,然后基于MAX（LSI（LR）、LSI（ANN）、LSI（SVM））函数对上述模型的易发性指数取最大值,并对上犹县进行滑坡易发性评价。结果显示:LR-ANN-SVM的AUC=0.815,有较高的易发性评价精度。从高易发区与较高易发区所含滑坡占比来看,LR、ANN、SVM、LR-ANN-SVM的滑坡占比分别为80.6%、74.6%、91%、93.2%,表明根据ANN-LR-SVM易发性分区治理更安全。      

Application of Artificial Intelligence to Estimate Daily Pan Evaporation Using Available and Estimated Climatic Data in the Khozestan Province (South Western Iran)

Estimation of evaporation, a major component of the hydrologic cycle, is required for a variety of purposes in water resources development and management. This paper investigates the abilities of genetic programming (GP) to improve the accuracy of daily evaporation estimation. In the first part of the study, different GP models, comprising various combinations of daily climatic variables, namely, air temperature, sunshine hours, wind speed, and relative humidity, were developed to evaluate the degree of the effect of each variable on daily pan evaporation. A dynamic modeling of evaporation was also performed, with the current climatic variables and one of the previous variables, to evaluate the effect of their time series on evaporation. In the second part of the study, the estimated solar radiation data were used as input vectors instead of recorded sunshine values. Statistics such as correlation coefficient (R), root mean square error (RMSE), coefficient of residual mass (CRM) and scatter index (SI) were used to measure the performance of models. Tthe dynamic model approach was shown to give the best results with relatively fewer errors and higher correlations. To assess the ability of GP relative to the neuro-fuzzy (NF) and artificial neural networks (ANN), several NF and ANN models were developed by using the same data set. The obtained results showed the superiority of GP to the NF and ANN approaches. The Stephen-Stewart and Christiansen methods were also considered for comparison. The results indicated that the proposed GP model performed quite well in modeling evaporation processes from the available climatic data. The results also showed that the estimated solar radiation data can be applied successfully instead of the recorded sunshine data.     

Estimation of a Resilient Modulus Model for Cohesive Soils Using Joint Estimation and Mixed Effects

This paper presents the specification and estimation of a model based on the mechanistic empirical Pavement Design Guide (PDG) for estimating resilient modulus of fine-grained soils by using common soil parameters and by combining two different data sources: a database developed with Hawaiian fine-grained soils and data extracted from the Long Team Pavement Performance database for fine-grained subgrade soils. Two statistical techniques are combined to estimate the model parameters: joint estimation and mixed effects. Joint estimation considers multiple databases and allows identification of influential parameters that may be present only in some but not all databases whereas the mixed-effects statistical estimation approach is used to account for the within-group correlation between observations. The general structure of the PDG model is found acceptable if an allowance is made for the compaction level in addition to the saturation level in the PDG sigmoidal function. The resulting model contains parameters that are statistically significant and is more robust in that it can be used under a wider range of conditions than would have been possible if only one data source was available.     

Evaluation of artificial neural network modelling to predict torso muscle activity

Owing to the complexities involved in obtaining direct measures of in vivo muscle forces, validation of predictive models of muscle activity has been difficult. An artificial neural network (ANN) model had been previously developed for the estimation of lumbar muscle activity during moderate levels of static exertion. The predictive ability of this model is evaluated in this study using several techniques, including comparison of response surfaces and composite statistical tests of values derived from model output, with multiple EMG experimental datasets. ANN-predicted activation levels were accurately modelled to within 3% across a range of experiments and levels of combined flexion/extension and lateroflexion loadings. The results indicate both a high degree of consistency in the averaged muscle activity measured in several different experiments, and substantiate the ability of the ANN model to predict generalized recruitment patterns. It also is suggested that the use of multiple comparison methods provides a better indication of model behaviour and prediction accuracy than a single evaluation criterion.