Prediction Of Uniaxial Compressive Strength Research Articles

Prediction of Uniaxial Compressive Strength and Modulus of Elasticity in Calcareous Mudstones Using Neural Networks, Fuzzy Systems, and Regression Analysis

The uniaxial compressive strength (UCS) and modulus of elasticity (E) are two important rock geomechanical parameters that are widely used in rock engineering projects such as tunnels, dams, and rock slope stability. Since the acquisition of high-quality core samples is not always possible, researchers often indirectly estimate these parameters. In the present study, prediction of UCS and E was investigated in calcareous mudstones of Aghajari Formation using multiple linear regression (MLR), multiple nonlinear regression (MNLR), artificial neural networks (ANN), and adaptive neuro-fuzzy ınference system (ANFIS). For this purpose, 80 samples from calcareous mudstones were subjected to the point loading, block punch, and cylinder punch tests. The performance of developed models was assessed based on determination coefficients (R2), mean absolute percentage error (MAPE), and variance accounted for (VAF) indices. The comparison of the obtained results revealed that, among the studied methods, ANFIS is the most suitable one for predicting UCS and E. Moreover, the results showed that ANN and MLNR respectively predict UCS and E better than MLR and a meaningful relationship between the observed and estimated UCS values in all regressions.

Prediction of uniaxial compressive strength and elastic modulus of migmatites using various modeling techniques

This study aims to develop several prediction models of uniaxial compressive strength (UCS) and elastic modulus (E) of different migmatite rocks from four areas of the Sanandaj-Sirjan zone in Iran. In addition to UCS and E, porosity, cylindrical punch Index (CPI), block punch index (BPI), Brazilian tensile strength (BTS), point load index (IS(50)), and P wave velocity (VP) were measured for migmatites. Various methods, like multiple regression (MR) analysis, artificial neural network (ANN), and adaptive neural fuzzy inference system (ANFIS), were used to predict UCS and E during the modeling process. In this study, a total of 120 inputs and outputs were used. According to the analyses performed in this study and the input parameters, five different models have been used to estimate UCS and E: (1) CPI, BPI, BTS, and IS(50); (2) CPI, BPI, BTS, and VP; (3) CPI, BPI, IS(50), and VP; (4) CPI, BTS, IS(50), and VP; (5) BPI, BTS, IS(50), and VP. Performance evaluation shows that ANN is a better prediction method compared to the others, and models 2, 4, and 5 are the best models for prediction. The developed models in this paper can have high prediction efficiency if they are used for similar types of rocks.

Prediction of Uniaxial Compressive Strength and Modulus of Elasticity for Some Sedimentary Rocks in Kurdistan Region- Iraq using Schmidt Hammer.

Prediction of Uniaxial Compressive Strength and Modulus of Elasticity for Some Sedimentary Rocks in Kurdistan Region- Iraq using Schmidt Hammer.

Evaluation of Specimen Size-Effect in Sedimentary Rocks and Grain Size Effect in Concrete Specimens on Uniaxial Compressive Strength

Summary In rock engineering, the effect of scale on the strength and deformation properties of the rock mass is one of the most important issues. Prediction of uniaxial compressive strength in different diameters using the specimen size-effect models is valuable. To specify the application scope of the specimen size-effect models in the rock and concrete specimens, a few significant study have so far been carried out. This paper proposes a model of appropriate size-effect in sedimentary rocks and concrete specimens. Another object of this paper is discussion on the effect of specimen size and grain size on uniaxial compressive strength of rock and concrete specimens using statistical and experimental methods. The results of this study can be used for engineering designs in or on rocks and are more useful for determining of the elastic constants and compressive strength of rock. Introduction Dependence of compressive strength on the specimen size has a fundamental role in the designing of rock structures. In the rock mechanics, many experimental and analytical methods have been used to determine the specimen size-effect on the mechanical behavior of intact rock. In the area of rock mechanics and solid mechanics, the most notable proposed analytical models to predict the specimen size-effect on the uniaxial compressive strength are including the Weibull statistical theory (1951), the Hoek and Brown empirical theory (1980), the specimen size-effect model using fracture energy theory (Bazant, 1983 and 1984), the multi-fractal scaling model (Carpinteri et al., 1995), the fractal fracture size-effect model (Bazant, 1997) and the unified size-effect model for intact rock (Masoumi et al., 2015). To specify the application scope of these models in the rock and concrete specimens, few significant study have so far been carried out. Methodology and Approaches Statistical analysis of this study, were conducted in each size-effect model by means of a non-linear least-squares fitting algorithm and Levenberg-Marquardt method using SPSS software. In the experimental study, three concrete blocks of approximately 500mm×500mm×500mm in size with three different grain sizes (0-12, 0-20 and 0-25) were manufactured. After the curing time, using a laboratory drilling machine, cylindrical specimens were obtained from blocks with diameters of 56, 68, 72 and 94 mm and with a length-to-diameter ratio of 2.0 (L/D=2.0) according to the recommendation of International Society of Rock Mechanics (ISRM, 2007). ACI-211 standard and ASTM C33 standard were utilized for mixture design of samples and required grain sizes respectively. Results and Conclusions In the sedimentary rocks and concrete specimens, respectively, there was a good agreement between outputs of laboratory tests with the specimen size-effect model using fracture energy and the multifractal scaling model. In experimental study, results of uniaxial compressive strength tests for grain sizes 0-20 and 0-25 mm indicated that increase of the specimens' diameter resulted in first increase and then decrease of uniaxial compressive strength. The results of this study confirmed grain size effect on the predictions of specimen size-effect models (i.e. increase of the grain size, leads to reduction of the value of correlation coefficient for different models. These results can be used for engineering designs in rocks and concrete mixtures.

Estimation of static parameters based on dynamical and physical properties in limestone rocks

Due to the importance of uniaxial compressive strength (UCS), static Young's modulus (ES) and shear wave velocity, it is always worth to predict these parameters from empirical relations that suggested for other formations with same lithology. This paper studies the physical, mechanical and dynamical properties of limestone rocks using the results of laboratory tests which carried out on 60 the Jahrum and the Asmari formations core specimens. The core specimens were obtained from the Bazoft dam site, hydroelectric supply and double-curvature arch dam in Iran. The Dynamic Young's modulus (Ed) and dynamic Poisson ratio were calculated using the existing relations. Some empirical relations were presented to estimate uniaxial compressive strength, as well as static Young's modulus and shear wave velocity (Vs). Results showed the static parameters such as uniaxial compressive strength and static Young's modulus represented low correlation with water absorption. It is also found that the uniaxial compressive strength and static Young's modulus had high correlation with compressional wave velocity and dynamic Young's modulus, respectively. Dynamic Young's modulus was 5 times larger than static Young's modulus. Further, the dynamic Poisson ratio was 1.3 times larger than static Poisson ratio. The relationship between shear wave velocity (Vs) and compressional wave velocity (Vp) was power and positive with high correlation coefficient. Prediction of uniaxial compressive strength based on Vp was better than that based on Vs. Generally, both UCS and static Young's modulus (ES) had good correlation with Ed.

Prediction of Uniaxial Compressive Strength of Some Sedimentary Rocks by Fuzzy and Regression Models

The purpose of this research is to construct predictive models to estimate the uniaxial compressive strength (UCS) of grainstone, wackestone-mudstone, boundstone, gypsum, and silty marl in the Qom area (central Iran). For this purpose, a series of rock mechanics tests were applied and indices such as block punch index, point load strength index (Is(50)), Schmidt rebound hardness and ultrasonic P-wave velocity (Vp) were determined for these rocks. Then, linear multiple regression and the Sugeno-type fuzzy algorithm were compared to check their accuracy. To improve the accuracy of the Sugeno fuzzy inference system, the weighted if-then rules are extracted. In addition to correlation coefficient, the variance account for (VAF) and the root mean square error (RMSE) were also calculated to check the predictive performances of these models. Obviously, performances of all four indices are reasonably good in predicting UCS (R2 > 0.76) from simple regression analyses. However, ultrasonic P-wave velocity does not give appropriate value (R2 = 0.67). The VAF and RMSE were calculated as 90% and 10.80 for the uniaxial compressive strengths obtained from the multiple regression model and 90% and 12.82 for uniaxial compressive strengths obtained from the fuzzy inference system, respectively. Thereby, both multiple regression analyses and fuzzy inference system exhibit better predictive performances for UCS than simple regression analyses. The predictive performances of multiple regression analyses and the fuzzy inference system show both models are comparable. Seemingly, fuzzy inference system is an efficient approach to predict UCS of rock materials from indices due to its efficiency in handling uncertainties of test results with transparency.

Variable selection and prediction of uniaxial compressive strength and modulus of elasticity by random forest

Mechanical properties of rocks can significantly affect energy resource recovery and development. Uniaxial compressive strength (UCS) and Young’s modulus (E) are key parameters in rock mechanics for designing geotechnical structures. In this study, it is shown that a new practical machine learning tool known as random forest (RF) model can be used for variable importance measurements (VIMs) among various physical and mechanical properties of rocks. Moreover, RF is a predictive model which can estimate E and UCS based on selected variables by VIMs. Therefore, in this study first VIMs of RF were applied to assess various rock properties (porosity (n), point load index (Is(50)), P-wave velocity (Vp), and Schmidt hammer rebound number (Rn)) and to choose the best predictors to model E and UCS. Results of VIM, assisted by Pearson correlation, demonstrated that Vp is the most effective variable for the prediction of both E and UCS. The most effective variables (Vp-Rn for E, and Vp-Is for UCS) were selected as inputs of RF model for the E and UCS predictions. Outputs in the testing stage of the models verified that RF can yield a satisfactory prediction of both E and UCS, with correlations of determination (R2) of 0.91 and 0.93, respectively. For comparison purposes, multivariable regression and generalized regression neural networks were used for E and UCS prediction. According to these results, developing a nonlinear inter-dependence approximation among parameters for variable selection and also a non-parametric predictive model by soft computing methods such as RF can potentially be further employed as a reliable and accurate technique for evaluation and estimation of complex relationships in rock mechanics.

Uniaxial compressive strength prediction through a new technique based on gene expression programming

Proper estimation of rock strength is a critical task for evaluation and design of some geotechnical applications such as tunneling and excavation. Uniaxial compressive strength (UCS) test can be measured directly in the laboratory; nevertheless, the direct UCS determination is time-consuming and expensive. In this study, feasibility of gene expression programming (GEP) model in indirect determination of UCS values of sandstone rock samples is examined. In this regard, several laboratory tests including Brazilian test, density test, slake durability test and UCS test were conducted on 47 samples of sandstone which were collected from the Dengkil, Malaysia. Considering multiple inputs, several GEP models were constructed to estimate UCS of the rock and finally, the best GEP model was selected. In order to indicate capability of the proposed GEP model, linear multiple regression (LMR) was also performed. It was found that the GEP model is superior to LMR one in terms of applied performance indices. Based on coefficient of determination (R2) of testing datasets, by proposing GEP model, it can be improved from 0.930 (which was obtained by LMR model) to 0.965. As a result, it is concluded that the proposed models in this study, could be utilized to estimate UCS of similar rock type in practice.

An ANN Approach for the Prediction of Uniaxial Compressive Strength, of Some Sedimentary and Igneous Rocks in Eastern KwaZulu-Natal

The Uniaxial Compressive Strength (UCS) of intact rocks is an essential index of strength in rock engineering. Laboratory based direct compressive strength estimation may be problematic, as obtaining fresh samples is not always feasible. Thus, the aim of indirect methods index test such as point load index test, and empirical correlations with UCS of indexes like the Brazilian indirect tensile strength test, serve as an alternative for many geotechnical engineering projects. The aim of this paper is to propose a relationship between UCS and indirect tests or indexes for some sedimentary and igneous rocks in KwaZulu-Natal using the technology of artificial intelligence. These tests include the point load index (Is (50)) test and Brazilian Tensile Strength (σt), test. Block samples were collected in KwaZulu Natal, among these include sedimentary rocks (sandstones, siltstone, tillite) and igneous rocks (granitoids and dolerite). A back propagation artificial neural network was developed and trained in order to predict UCS. The input parameters were unit weight γ, (Is (50)), (σt), and lithology. The lithology was introduced in the neural network as a qualitative input parameter, in order to indirectly incorporate in the model the mineralogical content. Training results returned, R value of 0.99% for the training set, and R = 0.92% for the test set, which is conveying to the conclusion that the approach is valid and could be used, as an alternative indirect approach to UCS estimation.

Application of Artificial Neural Networks in Prediction of Uniaxial Compressive Strength of Rocks using Well Logs and Drilling Data

It is critical to obtain the rock strength along the wellbore to control drilling problems such as pipe sticking, tight hole, collapse and sand production. The purpose of this research is to predict the uniaxial compressive strength based on data of sonic travel time, formation porosity, density and penetration rate. For prediction of UCS, artificial neural networks were developed between UCS and input data resulting a practical correlation. In this research, a long well segment possessing complete and continuous data coverage has been analysed, and collected data of the wellbore are used to correlate data of the four mentioned input parameters of artificial neural networks with uniaxial compressive strength data as network targets. Selection of input parameters is based on a vast literature review in this area. Due to the fact that standard experimental test methods based on established standards require costly equipment and that the methods for sample preparation is difficult and time-consuming, indirect methods are more favourable. Using these methods, the UCS values are predicted in a simpler, faster and more economical way. In this study, it is concluded that artificial neural networks are a good predictor of rock strength, and can reduce drilling costs significantly. It is observed in this paper that UCS predicted values by neural networks are very close with lab and field data, which is concluded by analysis of network performance results including mean squared error and correlation coefficient. It is also concluded in this study that input parameters which are chosen in this study, have deep effects in UCS prediction studies, and should be considered in other scientific studies. Conclusions show that using artificial neural networks to predict UCS of formation rocks in petroleum fields around the world, would ease UCS estimation, optimize drilling plans and decrease costs.

Correlation Between P-wave Velocity and Strength Index for Shale to Predict Uniaxial Compressive Strength Value

Seismic refraction survey is a non destructive method used in site investigation to identify the seismic velocity subsurface strata. Although it is widely known, the reliability of the result is still doubtable for some reason as well as due to an engineer’s ignorant, which insist on using conventional method rather than new advanced method causing the lack of usage in geophysical method for testing. This study aims to produce a correlation between P-wave velocity value and point load strength index value for shale. Both field and laboratory tests were carried out. In order to obtain the P-wave value, seismic refraction method was conducted as a field test at Precint 4, Putrajaya, Malaysia to achieve the Pwave velocity value of the shale bed. Ten samples of shale were collected from the field and laboratory tests were conducted. The tests are divided into three sections, namely non-destructive laboratory test, physical properties test and mechanical properties test. Ultrasonic Velocity Test via PUNDIT test was conducted as non-destructive laboratory test to acknowledge the P-wave velocity value in laboratory. Both field and laboratory P-wave velocity value were then compared and the result delivers are reliable due to it is within the range. For physical properties test, the rock density and porosity were acknowledged. Meanwhile, Point Load Test was conducted as mechanical properties. Correlation for both Pwave velocity value and point load strength value were achieved via producing an empirical relationship as the end result. Prediction of uniaxial compressive strength (UCS) value was made via converting the point load strength value to UCS value using a correlation. By acknowledging this empirical relationship, it shows that geophysical methods are able to produce a reliable result. Hence more and widely used of geophysical method will be profound in the future.

Influences of petrographic and textural properties on the strength of very strong granitic rocks

In this study, the petrographic characteristics affecting the strength of granitic rocks were investigated and a new mineralogical-based model was suggested for the prediction of uniaxial compressive strength (UCS) in line with the obtained data. Increase in quartz and alkali feldspar contents with decrease in plagioclase content partially increase the strength of granitic rocks. However, the results of modal analyses show that the rate of physically competent minerals do not directly affect strength of the granitic rock because the mineral size has a greater effect on strength than that of mineral type. The higher strength values were determined for the rocks containing monotype mineral in terms of size and quantity. In the scope of the study, significant relationships with a 0.89 correlation coefficient between UCS values and the Quality Index values (QI) were determined using mineral percentages, content and size. Because the modal analysis technique is a time-consuming process, ultrasonic velocity ratio (UVR) was defined in order to evaluate rock strength in the study and significant relationships were found with the correlation coefficient of 0.77 between UVR and QI. To estimate UCS using only ultrasonic wave velocity, it was determined whether there is a statistical relationship between UVR and UCS. The test result shows significant relation was found characterized with correlation coefficient of 0.84 value. UCS values obtained from the proposed equation and experimental studies were compared to test the suggested model; the results of the study showed that UCS values can be predicted without needing modal analysis with the new method proposed.

Updated relations for the uniaxial compressive strength of marlstones based on P-wave velocity and point load index test

Abstract Although there are many proposed relations for different rock types to predict the uniaxial compressive strength (UCS) as a function of P-wave velocity (V P) and point load index (Is), only a few of them are focused on marlstones. However, these studies have limitations in applicability since they are mainly based on local studies. In this paper, an attempt is therefore made to present updated relations for two previous proposed correlations for marlstones in Iran. The modification process is executed through multivariate regression analysis techniques using a provided comprehensive database for marlstones in Iran, including UCS, V P and Is from publications and validated relevant sources comprising 119 datasets. The accuracy, appropriateness and applicability of the obtained modifications were tested by means of different statistical criteria and graph analyses. The conducted comparison between updated and previous proposed relations highlighted better applicability in the prediction of UCS using the updated correlations introduced in this study. However, the derived updated predictive models are dependent on rock types and test conditions, as they are in this study.

Estimating the uniaxial compressive strength of pyroclastic rocks from the slake durability index

Because the preparation of standard samples may not always be possible for weak or soft rocks, the prediction of uniaxial compressive strength (UCS) from indirect methods is widely used for preliminary investigations. In this study, the possibility of predicting UCS from the slake durability index (SDI) was investigated for pyroclastic rocks. For this purpose, pyroclastic rocks were collected from 31 different locations in the Cappadocian Volcanic Province of Turkey. The UCS and SDI tests were carried out on the samples in the laboratory. The UCS values were correlated with the SDI values and a very strong exponential relation was found between the two parameters. Since some data were scattered over the UCS values of 20 MPa, the correlation plot was redrawn for above and below the UCS values of 20 MPa, respectively. Very strong linear correlations were developed for two cases. Our concluding remark is that the UCS of pyroclastic rocks can be estimated from the SDI.

Comparative evaluation of artificial intelligence models for prediction of uniaxial compressive strength of travertine rocks, Case study: Azarshahr area, NW Iran

Uniaxial compressive strength (UCS) is one of the most widely used and important rock mechanical parameters in rock engineering. The main objective of the present study was to evaluate the ability of artificial intelligence models including multi-layer perceptron (MLP), Sugeno fuzzy logic (SFL), Mamdani fuzzy logic (MFL), adaptive neuro-fuzzy inference system (ANFIS) and support vector machine (SVM) to predict the UCS of travertine rocks in the Azarshahr area (NW Iran). To attempt this objective, 85 core samples of travertine rock were collected from the study area and the laboratory tests were performed to determine the P-wave velocity [Vp (km/s)], porosity (n %), Schmidt rebound hardness (Rn) and UCS of the rocks at the Rock Mechanics Laboratory in the Tarbiat Modares University. The data set including Vp (km/s), n % and Rn as the inputs and UCS as the output were divided into training (80 % of dataset) and testing (20 % of dataset) subsets to construct the models. The coefficient of determination (R2), root mean square error (RMSE) and mean absolute error (MAE) were used to evaluate the models performance. The models accuracy followed the order SVM > ANFIS > SFL > MLP > MFL. The SVM model with RBF kernel function yielded the highest R2 (0.9516), and the lowest RMSE (2.14 MPa) and MAE (1.351 MPa) in the testing step. Accuracy results indicated that SVM model predictions were better than MLP, SFL, MFL and ANFIS models for prediction of UCS of travertine rocks.

Prediction of uniaxial compressive strength of rock samples using hybrid particle swarm optimization-based artificial neural networks

Many attempts have been made to predict unconfined compressive strength (UCS) of rocks using back-propagation (BP) artificial neural network (ANN). However, BP-ANN suffers from some disadvantages such as slow rate of learning and getting trapped in local minima. Utilization of particle swarm optimization (PSO) algorithm as a mechanism to improve the performance of ANNs is recently underlined in literature. The objective of this paper is to develop a PSO-based ANN predictive model of UCS. For this reason, a comprehensive experimental program was conducted on 66 granite and limestone sample sets taken from different states in Malaysia. The experimental program consists of direct and indirect estimation of UCS of rocks. The results of laboratory tests including point load index test (IS(50)), Schmidt hammer rebound number (SRn), p-wave velocity test (Vp) and dry density (DD) test were used as inputs of the network while UCS results were set to be the output. For comparison purpose, the prediction performance of the proposed hybrid model was checked against that of a conventional ANN. Comparison between the coefficients of determination, R2, obtained through conventional ANN and PSO-based ANN techniques reveal the superiority of the PSO-based ANN model in predicting UCS. In overall, the R2 for the proposed hybrid predictive model was 0.97 while in case of conventional ANN, the R2 was found to be 0.71. By performing sensitivity analysis, it was concluded that the effect of DD and SRn on predicted UCS values is slightly higher compared to other parameters.

Empirical relations of rock properties of outcrop and core samples from the Northwest German Basin for geothermal drilling

<p><strong>Abstract.</strong> Information about geomechanical and physical rock properties, particularly uniaxial compressive strength (UCS), are needed for geomechanical model development and updating with logging-while-drilling methods to minimise costs and risks of the drilling process. The following parameters with importance at different stages of geothermal exploitation and drilling are presented for typical sedimentary and volcanic rocks of the Northwest German Basin (NWGB): physical (<i>P</i> wave velocities, porosity, and bulk and grain density) and geomechanical parameters (UCS, static Young's modulus, destruction work and indirect tensile strength both perpendicular and parallel to bedding) for 35 rock samples from quarries and 14 core samples of sandstones and carbonate rocks. <br><br> With regression analyses (linear- and non-linear) empirical relations are developed to predict UCS values from all other parameters. Analyses focus on sedimentary rocks and were repeated separately for clastic rock samples or carbonate rock samples as well as for outcrop samples or core samples. Empirical relations have high statistical significance for Young's modulus, tensile strength and destruction work; for physical properties, there is a wider scatter of data and prediction of UCS is less precise. For most relations, properties of core samples plot within the scatter of outcrop samples and lie within the 90% prediction bands of developed regression functions. The results indicate the applicability of empirical relations that are based on outcrop data on questions related to drilling operations when the database contains a sufficient number of samples with varying rock properties. The presented equations may help to predict UCS values for sedimentary rocks at depth, and thus develop suitable geomechanical models for the adaptation of the drilling strategy on rock mechanical conditions in the NWGB.</p>

UCS Prediction: A New Set of Concepts for Reservoir Geomechanical Modeling

Simulation and estimation are based on geostatistics methods; they have been greatly accepted to simulate different features of hydrocarbon reservoirs, so that much software for reservoir simulation work are based on these methods. A good estimator provides not only average errors of estimations but also shows the geostatistical distribution of the estimated errors. Generally, geostatistical estimation is a process that obtains the value of a feature in points with known coordinates, using the value of this feature in other points with known coordinates. This geostatistical estimator is called kriging. Rock strength has an important role in oil production and drilling in hydrocarbon reservoir. Thus, uniaxial compressive strength (UCS) is an efficacious parameter in drilling operation in hydrocarbon reservoir. Here the UCS has been examined and processed by using geostatistical methods for one of the oil fields in southwestern Iran.

Support vector machines applied to uniaxial compressive strength prediction of jet grouting columns

Learning from data is a very attractive alternative to “manually” learning. Therefore, in the last decade the use of machine learning has spread rapidly throughout computer science and beyond. This approach, supported on advanced statistics analysis, is usually known as Data Mining (DM) and has been applied successfully in different knowledge domains. In the present study, we show that DM can make a great contribution in solving complex problems in civil engineering, namely in the field of geotechnical engineering. Particularly, the high learning capabilities of Support Vector Machines (SVMs) algorithm, characterized by it flexibility and non-linear capabilities, were applied in the prediction of the Uniaxial Compressive Strength (UCS) of Jet Grouting (JG) samples directly extracted from JG columns, usually known as soilcrete. JG technology is a soft-soil improvement method worldwide applied, extremely versatile and economically attractive when compared with other methods. However, even after many years of experience still lacks of accurate methods for JG columns design. Accordingly, in the present paper a novel approach (based on SVM algorithm) for UCS prediction of soilcrete mixtures is proposed supported on 472 results collected from different geotechnical works. Furthermore, a global sensitivity analysis is applied in order to explain and extract understandable knowledge from the proposed model. Such analysis allows one to identify the key variables in UCS prediction and to measure its effect. Finally, a tentative step toward a development of UCS prediction based on laboratory studies is presented and discussed.

Selection of regression models for predicting strength and deformability properties of rocks using GA

Recently, many regression models have been presented for prediction of mechanical parameters of rocks regarding to rock index properties. Although statistical analysis is a common method for developing regression models, but still selection of suitable transformation of the independent variables in a regression model is difficult. In this paper, a genetic algorithm (GA) has been employed as a heuristic search method for selection of best transformation of the independent variables (some index properties of rocks) in regression models for prediction of uniaxial compressive strength (UCS) and modulus of elasticity (E). Firstly, multiple linear regression (MLR) analysis was performed on a data set to establish predictive models. Then, two GA models were developed in which root mean squared error (RMSE) was defined as fitness function. Results have shown that GA models are more precise than MLR models and are able to explain the relation between the intrinsic strength/elasticity properties and index properties of rocks by simple formulation and accepted accuracy.