Groutability Prediction Research Articles

Groutability prediction model of coral sand reinforced by excess-sulfate phosphogypsum slag grouting material under permeation grouting

Excess-sulfate phosphogypsum slag grouting material (EPSGM) has strong advantages for stabilizing the coral sand foundation, which requires establishing a groutability prediction model involving multi-factors to ensure better stabilization. Specifically, the grain size (d85) and water-to-cement ratio (w/c) of the grout, particle size (D15), relative density (Dr), and fine content (FC) of coral sand, and grouting pressure (P) are considered. The results show that the optimal particle size d85 of EPSGM is 15.567 μm. As the w/c increases from 1.0 to 3.0, the compressive strength of mortar (EPSGM + coral sand) decreases from 11.74 MPa to 0.32 MPa, and the California Bearing Ratio (CBR) value meets the typical requirements (≥ 15%). The groutability criterion (N) is positively correlated with the D15, w/c, and P, while it is negatively correlated with the Dr and FC, namely, the model writes: N=1−0.071Dr1−1.54FC0.024D15d85+0.42w/c+0.897P−0.86. Particularly, the predictive accuracy can attain a level of 87.50% for systems characterized by varying grain sizes (D15 ≥ 0.431 mm) and densities (Dr ≤ 0.67) of EPSGM stabilizing coral sand foundations. Furthermore, it also applies to other systems in literature that exhibit accuracy ranging from 33.33% to 62.50%. Therefore, the derived predictive model performs greater engineering relevance in informing the selection of grout factors.

Use of sand pore-size distribution to predict cement suspension groutability

The investigation reported herein aims toward the development of novel, easy-to-use models based on the pore-size distributions of sands for the groutability prediction of cement suspensions in permeation grouting projects for soil improvement. The models were determined using 367 groutability measurements obtained in this research effort by conducting injection tests into 54 sands with different gradations. The documentation of model performance was based on a large database comprising the results of 604 injection tests conducted by other researchers with ordinary and microfine cement suspensions. Suspension groutability is improved by increasing sand characteristic pore size and suspension water/cement ratio and decreasing cement characteristic grain size and suspension apparent viscosity. The proposed models developed using the Binary Logistic Regression method, exhibit coefficients of multiple determination approximately equal or greater than 0.80 and estimate successfully the outcome of the injection tests collected from other studies at rates ranging from 70% to 76%.

Prediction of cement suspension groutability based on sand hydraulic conductivity

The experimental investigation reported herein aims toward the development of groutability prediction models based on the hydraulic conductivity of sand and other parameters affecting the groutability of cement suspensions. For the purposes of the present study, suspensions of three different cement types, each at four different gradations, having water to cement (W/C) ratios of 1, 2 and 3, by weight, were injected into dry and dense sand columns with a height of 36.5 cm. The tested cements cover the range from ordinary to microfine materials having nominal maximum grain sizes of 100, 40, 20 and 10 μm. Six uniform, clean sands with different grain sizes were used alone or mixed in various proportions to obtain 48 additional sands, with different gradations, for grouting. Suspension groutability is improved by increasing cement fineness and suspension W/C ratio or by decreasing apparent viscosity and is controlled by the hydraulic conductivity and the gradation of the sand. The groutability and filtration limits defined in the present study, are based on sand hydraulic conductivity and suspension apparent viscosity and depend on cement fineness and sand gradation. The best model developed by performing Binary Logistic Regression analyses of the injection test results is regarded as an efficient tool for the prediction of groutability of cement suspensions in sands with different gradations, as it exhibits a coefficient of multiple determination equal to 0.914 and estimates successfully the outcome of the injection tests available from this study and collected from other studies at a rate equal to 89% and 70.5%, respectively.

Evaluation of the Validity of Groutability Prediction Formulas by Means of Superfine Cement Grouts

Extensive laboratory grouting tests were conducted using ultrafine cement suspensions to evaluate the validity and reliability of groutability prediction formulas proposed by several researchers for the cement based grouts of soils. Initially, such basic rheological properties as setting time, viscosity and stability of ultrafine cement suspensions with or without dispersive agent were studied. Next, the penetration performance of suspensions into various graded medium to fine sand specimens prepared at different relative densities was investigated. Finally, the grouting test results were compared with those obtained from groutability prediction formulas and it was found out that the proposed prediction formulas could not be used as a sole and exclusive criterion to predict the groutability of soils.

Hybrid Grey Wolf Optimization Algorithm–Based Support Vector Machine for Groutability Prediction of Fractured Rock Mass

AbstractGroutability determination is a very important task in grouting quality control. There is little research on the groutability of cement-based grout in a fractured rock mass, and the predict...

Predicting groutability of granular soils using adaptive neuro-fuzzy inference system

In this paper, the applicability of adaptive neuro-fuzzy inference system (ANFIS) for the prediction of groutability of granular soils with cement-based grouts is investigated. A database of 117 grouting case records with relevant geotechnical information was used to develop the ANFIS model. The proposed model uses the water–cement ratio of the grout, the relative density and fines content of the soil, the grouting pressure, and the ratio between the particle size of the soil corresponding to 15% finer and that of grout corresponding to 85% finer as input parameters. The accuracy of the proposed ANFIS model in terms of the corresponding coefficient of correlation (R) and root mean square error (RMSE) values is found to be quite satisfactory. Furthermore, a comparative analysis with existing groutability prediction methods indicates that the ANFIS model demonstrates superior performance.

Metaheuristic optimization within machine learning-based classification system for early warnings related to geotechnical problems

Abstract This study proposes a novel classification system integrating swarm and metaheuristic intelligence, i.e., a smart firefly algorithm (SFA), with a least squares support vector machine (LSSVM). Benchmark functions were used to validate the optimization performance of the SFA. The experimental results showed that the SFA obtained 100% success rate in searching the optimum for most benchmark functions. The SFA was then integrated with the LSSVM to create a metaheuristic optimized classification model. A graphical user interface was developed for the proposed classification system to assist engineers and researchers in executing advanced machine learning tasks. The system was applied to several geotechnical engineering problems that involved measuring the groutability of sandy silt soil, monitoring seismic hazards in coal mines, predicting postearthquake soil liquefaction, and determining the propensity of slope collapse. The prediction problems in these studies were complex because they were dependent on various physical factors, and such factors exhibited highly nonlinear relations. The analytical results revealed that the metaheuristic optimization within machine learning-based classification system exhibited a groutability prediction accuracy of 95.42%, seismic prediction accuracy of 93.96%, soil liquefaction prediction accuracy of 95.18%, and soil collapse prediction accuracy of 95.45%. Hence, the proposed system is a promising tool to provide decision-makers with timely warnings of geotechnical hazards.

Groutability estimation of grouting processes with cement grouts using Differential Flower Pollination Optimized Support Vector Machine

This research presents a soft computing methodology for groutability estimation of grouting processes that employ cement grouts. The method integrates a hybrid metaheuristic and the Support Vector Machine (SVM) with evolutionary input factor and hyper-parameter selection. The new prediction model is constructed and verified using two datasets of grouting experiments. The contribution of this study to the body of knowledge is multifold. First, the efficacies of the Flower Pollenation Algorithm (FPA) and the Differential Evolution (DE) are combined to establish an integrated metaheuristic approach, named as Differential Flower Pollenation (DFP). The integration of the FPA and the DE aims at harnessing the strength and complementing the disadvantage of each individual optimization algorithm. Second, the DFP is employed to optimize the input factor selection and hyper-parameter tuning processes of the SVM-based groutability prediction model. Third, this study conducts a comparative work to investigate the effects of different evaluation functions on the model performance. Finally, the research findings show that the new integrated framework can help identify a set of relevant groutability influencing factors and deliver superior prediction performance compared with other state-of-the-art approaches.

GROUTABILITY PREDICTION OF MICROFINE CEMENT BASED SOIL IMPROVEMENT USING EVOLUTIONARY LS-SVM INFERENCE MODEL

Permeation grouting is a widely used technique for soil improvement in construction engineering. Thus, predicting the results of the grouting activity is a particularly interesting topic that has drawn the attention of researchers both from the academic field and industry. Recent literature has indicated that artificial intelligence (AI) approaches for groutability prediction are capable of delivering better performance than traditional formula-based ones. In this study, a novel AI method, evolutionary Least Squares Support Vector Machine Inference Model for groutability prediction (ELSIM-GP), is proposed to forecast the result of grouting activity that utilizes microfine cement grout. In the model, Least Squares Support Vector Machine (LS-SVM) is a supervised machine learning technique that is employed to learn the decision boundary for classifying high dimensional data. Differential Evolution (DE) is integrated into ELSIM-GP for automatically optimizing its tuning parameters. 240 historical cases of grouting process for sandy silt soil have been collected to train, validate, and test the inference model. Experimental results demonstrated that ELSIM-GP can overcome other benchmark approaches in terms of forecasting accuracy. Therefore, the proposed approach is a promising alternative for predicting groutability.

A novel groutability estimation model for ground improvement projects in sandy silt soil based on Bayesian framework

In construction engineering, permeation grouting with microfine cement is a widely utilized approach for soil improvement. Hence, estimating groutability is a very important task that should be carried out in the planning phase of any grouting project. This research aims at establishing a novel method for groutability prediction with the utilization of microfine cement in sandy silt soil. The newly proposed approach integrates the Bayesian framework and the K-nearest neighbor (K-NN) density estimation technique. The Bayesian framework is used to achieve probabilistic groutability estimations. Meanwhile, the K-NN method is employed to approximate the conditional probability density functions. Moreover, to establish the new approach, 240 in-situ grouting cases have been recorded during the progress of Mass Rapid Transit and highway projects in Taiwan. Experimental results point out that the proposed method can deliver superior prediction accuracy. Hence, the new groutability estimation approach is a promising alternative to help construction engineers in grouting process assessment.

Groutability of Granular Soils Using Bentonite Grout Based on Filtration Model

This paper describes an experimental and a numerical study on the groutability of granular soils using sodium pyrophosphate (SPP)—modified bentonite grout to investigate its possible application in permeation grouting. While the groutability criteria based on the relative grain size of the soil and the grout have been widely used for particulate grouts, such criteria do not account for the change in groutability of soils due to chemical modifications of the grouts. Moreover, the bentonite grout has different physicochemical properties such as particle size and pH from those in the cement-based grout, resulting in different filtration character, and thus different groutability of soils. Therefore, it is difficult to apply the existing criteria developed for the cement-based grout to the bentonite grout. In this study, the apparent viscosities of various bentonite grouts (5, 7.5, 10, and 12 %, wt/wt %) with 0–4 % SPP were measured using an advanced rheometer. The grouts were injected through sand columns having different effective particle sizes (0.2, 0.28, and 0.31 mm) under two constant pressures (35 and 140 kPa). A 1D filtration model was utilized to simulate the grout flow through the sand columns. A lumped parameter that accounts for physicochemical properties of bentonite grouts was evaluated by calibrating the model with the experimental data. The results showed that the apparent viscosity of 7.5, 10, and 12 % bentonite suspensions decreased approximately 50 % with the SPP concentrations of 1, 3, and 4 %, respectively. Moreover, the lumped parameter increased with the decrease in the effective grain size of the sand and decreased with the decrease in the apparent viscosity of the grout. This implies that filtration during the grout flow was reduced with the SPP modification. The parameter also decreased with the increase in injection pressure and relative density. A new groutability criterion for bentonite grout was proposed based on the relationship between the injected pore volume and the lumped parameter. The criterion was compared to the existing criteria, leading to more accurate prediction of groutability in the tested sands. The proposed groutability criterion will be beneficial to design grouting works by more accurately predicting the groutability of granular soils for SPP modified bentonite grouts than the existing criteria.

Groutability Estimation of Grouting Processes with Microfine Cements Using an Evolutionary Instance-Based Learning Approach

AbstractIn the construction industry, estimating groutability is a crucial task in the planning phase of a grouting project. Hence, establishing an effective groutability prediction model that is s...

Groutability of granular soils using sodium pyrophosphate modified bentonite suspensions

Groutability of granular soils using sodium pyrophosphate (SPP) modified bentonite suspensions was studied to investigate its applicability in permeation grouting. While the relative grain size of the soil and the grout has been widely used to evaluate the groutability of granular soils with particulate grouts, such criteria do not account for the effect of chemical modifications of grouts such as the changes in their rheological properties. The modification of grouts may improve the depth of its penetration, and thus changing the groutability of the granular soils. For such cases, the rheological properties of grouts become crucial to evaluate groutability of soils. In this study, the rheological properties of bentonite suspensions were measured at various bentonite fractions (5%, 7.5%, 10%, and 12% by total mass of suspension) modified with 0%, 1%, 2%, 3%, and 4% SPP (by mass of dry bentonite), respectively. The small amounts of SPP effectively improved the mobility of the concentrated bentonite suspensions allowing the evaluation of change in groutability at different rheological properties but same concentrations. The modified bentonite suspensions were injected into the saturated sand columns prepared at various experimental conditions (effective particle size, relative density, and fines content) under two different constant pressures (35 and 140kPa). The results showed that the injected pore volumes increased with an increase of the apparent viscosity at equilibrium (high shear rates). A new groutability criterion for granular soils is proposed based on the rheological properties of the suspensions, relative density of the sand, relative grain size of the sand and bentonite, and injection pressure. The proposed groutability criterion provides a more accurate prediction of groutability in granular soils when using modified bentonite suspensions.

An artificial neural network for groutability prediction of permeation grouting with microfine cement grouts

The use of microfine cements in permeation grouting has been growing as a strategy in geotechnical engineering because it usually provides improved groutability ( N). One of the major challenges of using microfine cement grouts is the ability to estimate the N within a reasonable level of error. The suitability of traditional groutability prediction formulas, which are mostly based on the grain-size of the soil and the grout, is questionable for semi-nanometer scale grout. This study first investigated the accuracy of the current formulas; we found that the accuracy ranges from 45% to 68%, a level that is not adequate for practical engineering. An alternative approach, based on a Radial Basis Function Neural Network (RBFNN), was developed. RBFNN provides a prediction with a 95.8% accuracy within a short time frame. Several parameters were considered in our proposed network; besides the grain-size of the soil ( D 10/ D 15), other important parameters included the void ratio ( e), the fines content (FC), the uniformity coefficient ( C u ), the coefficient of gradation ( C z ) and the water-to-cement ratio (w/c). A total of 240 in situ data samples were collected to support the training and testing of the network. After finding a good correlation between the field observation and the RBFNN output, it was concluded that RBFNN is a suitable and reliable tool to predict the outcome of permeation grouting when microfine cement grout is used.

Artificial neural networks approach for estimating the groutability of granular soils with cement-based grouts

A reliable estimation of the groutability of the target geomaterial is an essential part of any grouting project. An artificial neural network (ANN) model has been developed for the estimation of groutability of granular soils by cement-based grouts, using a database of 87 laboratory results. The proposed model used the water:cement ratio of the grout, relative density of the soil, grouting pressure, and diameter of the sieves through which 15% of the soil particles and 85% of the grout pass. A very good correlation was obtained between the ANN predictions and the laboratory experiments. Comparison of these results with those obtained using traditional methods for groutability prediction confirmed the viability of using ANN to estimate groutability.

Estimating the groutability of granular soils: a new approach

This paper evaluates different parameters that affect the grouting of soil, and presents a new approach to predict the groutability of granular soil. An accurate prediction of the groutability of granular soils has always been complicated due to the effects of different soil parameters. We know that these parameters are the grain-size of soil and cement-based grouts, the relative density and fine contents of soil, the water/cement ratio of grout mixture and grouting pressure, which directly affect the groutability of soil media. However, the relative density, fine contents of soil, the water/cement ratio, and grouting pressure are seldom considered as the prediction of groutability. In order to study the effects of the parameters on groutability, an alternative empirical formula to estimate the groutability of granular soils is presented in this paper and supported by experimental results obtained from the grouted sand samples prepared with various relative densities. The newly developed approach will help for the more accurate prediction of the groutability in granular soils and may also be used to provide first-hand information about the groutability of soils.

Prediction of groutability from grout properties and hydrogeological data

Sealing tunnels and caverns in fractured crystalline rocks has been considered notoriously unpredictable and possible to manage only through experience and intuitive knowledge. Words such as “witchcraft” and “black art” have been used ironically in Sweden to describe the state of the art. In this paper, initially grout penetration and grout take in parallell planar fractures are discussed. General expressions for these entities are also derived for fractures with varying width. In this paper, the grout take of a system of inhomogeneous channels in a fracture plane is studied further and the grout takes of such systems are modelled numerically. Grout takes are calculated for increased variability of the fracture aperture and the influence of this is assessed. In normal Swedish grouting procedures, the grouting boreholes are tested by water pressure tests (WPT). The hydrogeological information from these tests can be transferred to grouting apertures, and thus yield design information for grouting operations. Finally, the applicability of the findings is evaluated using field data from grouting of the access tunnel of the Äspö Hard Rock Laboratory, Sweden. The conclusion is that field methods for prediction and design of grouting operations can successfully be based on the theory.