Point Load Strength Research Articles

Examining Hybrid and Single SVM Models with Different Kernels to Predict Rock Brittleness

The aim of this study was twofold: (1) to assess the performance accuracy of support vector machine (SVM) models with different kernels to predict rock brittleness and (2) compare the inputs’ importance in different SVM models. To this end, the authors developed eight SVM models with different kernel types, i.e., the radial basis function (RBF), the linear (LIN), the sigmoid (SIG), and the polynomial (POL). Four of these models were developed using only the SVM method, while the four other models were hybridized with a feature selection (FS) technique. The performance of each model was assessed using five performance indices and a simple ranking system. The results of this study show that the SVM models developed using the RBF kernel achieved the highest ranking values among single and hybrid models. Concerning the importance of variables for predicting the brittleness index (BI), the Schmidt hammer rebound number (Rn) was identified as the most important variable by the three single-based models, developed by POL, SIG, and LIN kernels. However, the single SVM model developed by RBF identified density as the most important input variable. Concerning the hybrid SVM models, three models that were developed using the RBF, POL, and SIG kernels identified the point load strength index as the most important input, while the model developed using the LIN identified the Rn as the most important input. All four single-based SVM models identified the p-wave velocity (Vp) as the least important input. Concerning the least important factors for predicting the BI of the rock in hybrid-based models, Vp was identified as the least important factor by FS-SVM-POL, FS-SVM-SIG, and FS-SVM-LIN, while the FS-SVM-RBF identified Rn as the least important input.

Digitalization of mechanical and physical properties of Singapore Bukit Timah granite rocks based on borehole data from four sites

The Bukit Timah Granite (BTG) formation is widely distributed in the central and northern parts of Singapore Island. The BTG rocks in the formation vary from granite to granodiorite. Several hybrid rocks and dykes are also present in the BTG. The granite is in various states of fracturing and weathering, ranging from residual soils to intact, unweathered fresh rock. This paper presents some mechanical and physical properties of Singapore BTG rocks, based on data from the Factual Geotechnical Reports of more than 200 boreholes from Downtown Line stage II (DTL2) sites of Cashew, Hillview, Bukit Panjang and Beauty World. The variations of the parameters, including the unconfined compressive strength (UCS), the point-load strength index (Is50), the Cerchar abrasivity index (CAI), and the slake-durability index are derived from laboratory tests on samples from borelogs of different depths. The empirical correlations between the UCS and Is50 and between the CAI and the strength parameters (UCS and Is50) are derived and validated against the commonly adopted equations. Statistical information, including the average values, the standard deviations, and the coefficients of variation, are provided for these parameters. These statistics provide a useful reference for numerical simulations and future projects involving BTG rocks.

Evaluation of Strength and Deformability of Soft Sedimentary Rocks in Dry and Saturated Conditions Through Needle Penetration and Point Load Tests: A Comparative Study

The preparation of standardized soft rock specimens to perform unconfined compressive strength (UCS) tests is typically difficult, expensive and time-consuming. Needle penetration test (NPT) was originally developed in Japan as an alternative for the indirect estimation of UCS of soft rocks. The needle penetrometer is a simple, portable and non-destructive testing device that measures applied load and penetration depth for the rock to calculate the needle penetration index (NPI). A complimentary, portable and widely used destructive test is the point load test (PLT), which measures regular and irregular specimens by the application of a concentrated load using two coaxial conical platens that yield the point load strength index (IS(50)). We investigated and compared the NPT and PLT in terms of measuring changes induced by water saturation and obtaining UCS and the static Young’s modulus (Est) for dry and saturated soft sedimentary rocks. The results point to significant correlation functions from which to infer UCS and Est in terms of NPI and IS(50) in dry and saturated soft rocks. Furthermore, both NPT and PLT are suitable tests for evaluating changes in strength and deformability induced by water saturation. We also found a good correlation between the NPI and Is(50).

Probabilistic characterisation of uniaxial compressive strength of rock using test results from multiple types of punch tests

ABSTRACT The determination of uniaxial compressive strength (UCS) is central to most mining and geotechnical engineering analyses and designs in rock engineering. Direct measurement of UCS through uniaxial compression tests are costly and time-consuming. This is a challenge in mining engineering practice. However, there is a possibility to have results of other tests (e.g. punch tests) which are simple to conduct, particularly at the early stage of many mining engineering projects. The information contained in the results of multiple punch tests can be combined under a Bayesian approach to characterise UCS. This study proposes a Bayesian approach for probabilistic characterisation of UCS based on information from multiple sources, including the results of multiple punch tests available at a specific rock site. The proposed Bayesian approach is formulated to sequentially incorporate data from the parameters of three punch tests, namely Schmidt rebound hardness (SRH), block punch index (BPI) and point load strength () to update statistics and probability distribution of UCS. The approach is illustrated using real SRH, BPI and data at a sandstone site. The proposed Bayesian approach is shown to perform satisfactorily for the probabilistic characterisation of UCS as results of additional type of punch tests are incorporated.

Classification of Engineering Properties of Tropical Boulder in Completely Weathered Granite in Johor, Malaysia

Engineering properties of tropical weathered granite mass have been widely investigated and classified for engineering purposes. However, the engineering properties of tropical boulder in weathered granite profile is poorly understood and not well classified. This study aims to examine and classify the physico-mechanical properties of granite boulder in completely weathered zone. A total of 34 in-situ boulders were examined from two granite quarries located in Southern Johor, Malaysia. Microstructure-mineralogical alterations were analyzed based on petrographic analysis and scanning electron microscopy (SEM). The mechanical properties were including dry density, porosity, point load strength, uniaxial compressive strength and permeability. Three properties were identified as significant indicators to differentiate between tropical boulder and completely weathered granite when it is evaluated from the soil investigation drilling work namely; texture characteristics, discolourations and degree of weathering. Analysis revealed that the alteration of microstructures and minerals such as feldspar, biotite, and plagioclase from corestone (Grade I/II) to saprolite (Grade IV/V) zone were significantly reduced the dry density, point load strength, uniaxial compressive strength and permeability with 32%, 99.5%, 98.6% and 84.8%, respectively. It has also significantly increased the porosity up to 11.6 times or 1065% from corestone to saprolite. The significant different of physico-mechanical properties of material surrounding boulder due to weathering can be classified and useful in evaluation of geotechnical design and geological engineering applications.

Experimental investigation of rockfill particle breakage under large-scale triaxial tests using five different breakage factors

The process of particle breakage affects the mechanical characteristics of rockfill materials, which are used extensively in geotechnical projects. Therefore, in this research, a series of large-scale triaxial tests on angular rockfills were conducted to investigate the particle breakage behavior using five different methods (“Marsal”, “Lee & Farhoomand”, “Hardin”, “Lade & Yamamuro” and “Indraratna”). The relation between the particle breakage and each parameter, including “confining pressure”, “maximum deviatoric stress”, “maximum principal stress ratio”, “maximum dilatancy angle”, “peak friction angle” and “D10, D15 and D50” was investigated. Moreover, in order to present a more comprehensive and simplified description of the breakage factor variations, the parameters “Los Angeles abrasion”, “point load strength index” and “changes in Cu and Cc coefficients” were modified to one parameter named “J”. The results indicated that among five breakage factors, Marsal's index best described the breakage behavior of rockfill materials.

Data Mining Techniques for the Prediction of Bohme Surface Abrasion Rates from Rock Properties

Abstract Abrasion refers to the wearing down of rock surfaces due to abrasive grains. Abrasion resistance refers to the ability of rocks to withstand wear. Abrasion resistance is used to determine the resistance of building materials produced for flooring, cladding, and pavements and to demonstrate suitability for higher movement areas. While it is, therefore, very necessary to determine the abrasion rate of building materials prior to construction, it is, however, highly demanding and time consuming to determine abrasion rates. Thus, the aim of this study is to use some rock properties to determine abrasion rates. The study samples, consisting of 32 different types of rocks (sedimentary, metamorphic, and igneous) collected from different regions in Turkey, were subjected to some physical and mechanical tests, namely the following: unit volume weight (UVW), apparent porosity (AP), modulus of elasticity (E), uniaxial compressive strength (UCS), tensile strength (TS), Shore hardness (SH), and point load strength (PL) and Bohme abrasion tests. To ascertain the abrasion rate from some physical and mechanical properties of rocks, the results of these tests were analyzed using data mining (DM) techniques. The results showed that there are high correlation coefficients between abrasion rate and the aforementioned rock properties with the support vector machines (SVM) and random forests (RF) models obtained as R = 0.882 and 0.881, respectively. This work has shown that the rock Bohme abrasion rate can be predicted from some of its physical and mechanical properties with significant level of confidence.

Estimating Deterioration Rate of Some Carbonate Rocks Used as Building Materials under Repeated Frost Damage Process, China

The degradation of natural rocks due to severe environmental conditions can influence their durability over an extended period of time. This research aims to investigate the long‐term durability or disintegration rate of rocks used as construction materials under severe climatic conditions using frost damage action, and the deterioration rate was assessed using mathematical decay function approach. The mathematical model assumes an initial order operation and gives purposeful properties for the deterioration rate of rocks due to frost action. For this reason, six different limestone types used as building materials were quarried from limestone mine in China and subjected to a series of laboratory tests to determine the mineralogical, petrographical, physical, and mechanical characteristics. Then, 50 cycles of frost damage process was performed, and after each 10 cycles, the unconfined compressive strength, point load strength, and Schmidt rebound were determined. The disintegration rate or integrity loss characteristics of each rock type were assessed using the mathematical decay function approach parameters. This approach proved that the disintegration rate varies for the rocks of the same type especially which were extracted from the same areas, the rock durability under frost damage conditions can be estimated with good accuracy, the parameters of this model saved a lot of time and provided important practical features to assess a rapid durability, and hence, there is no need to carry out the frost damage test which is slow and consumes time.

Point load strength of clastic sedimentary rocks from the Semanggol Formation, Beris Dam, Kedah Darul Aman

Point load strength of clastic sedimentary rocks from the Semanggol Formation, Beris Dam, Kedah Darul Aman

Acoustic and strength characterization of Upper Cretaceous dolostones from the Bahariya Oasis, Western Desert, Egypt: The impact of porosity and diagenesis

The Western Desert of Egypt has huge reserves of good-quality natural stones such as limestones, travertines and dolostones. In this paper we assess the dolostones of El Heiz and Ain Giffara formations exposed at the Bahariya Oasis by investigating their lithological, textural, acoustic, and strength properties, and accordingly their economic significance and potential contribution to the national economy of Egypt. Representative dolostone rocks were collected at carefully-selected field sites. The microfacies analysis revealed that three main facies are recognized in the collected rocks: vuggy dolostone, marly dolostone, and sandy dolostone. The measured density and porosity of the studied rocks have been largely affected by the sediment composition, depositional setting, and the diagenetic alterations which, in turn, influenced the acoustic properties and strength of the rocks. Results of the uniaxial unconfined compressive strength (UCS), tensile strength (σt), point load strength (IS50), and the Schmidt Hammer rebound (SHR) number of the studied samples indicate generally high-strength rocks. Various interrelationships between the acoustic and strength properties were obtained using the regression analysis and have been interpreted in light of the rock microfacies and the observed diagenetic processes. Significant relationships have been obtained particularly between the UCS versus the acoustic velocities and the SHR. The resulting empirical relationships with the moderate/high coefficients of correlation can be used to compute important rock parameters from those that are measured on a routine basis; hence enabling a much quicker and efficient evaluation of the rocks. Results of the present study are also useful for studying the strength and acoustic properties of similar surface and subsurface dolostone sequences in the Western Desert of Egypt, as well as other areas of similar geological setting and depositional facies.

BÜYÜK ÖLÇEKLİ KÖMÜR ARININDA GERÇEKLEŞTİRİLEN SCHMİDT SERTLİK İNDEKSİ VE NOKTA YÜKLEME DAYANIMI DENEY SONUÇLARININ DEĞERLENDİRİLMESİ

Kömür ve kömür damarı içerisinde konumlanan ara kesmelerin (t=0,5m) yerinde malzeme özelliklerinin belirlenmesine yönelik bu çalışma, TKİ-GLİ-Ömerler yeraltı maden ocağında gerçekleştirilmiştir. Kömür arın yüksekliği 3,5 m ve uzunluğu ise 110 m olan A1 hazırlık panosunda, yaklaşık 385 m2’ lik yüzey alanı üzerinde her biri yaklaşık 15 m2 olan 4 deney alanı belirlenmiştir. Bu deney bölgeleri arının iki kenar uç tarafında ve arın ortasında konumlanmıştır. Deney bölgeleri kendi içlerinde toplam 238 birim hücreye bölünmüştür. Birim hücrelerin orta noktasında en az üç kez tekrarlanmak kaydı ile Schmidt sertlik belirleme deneyleri yapılmıştır. Nokta yükleme dayanımı indeks deneyi için A1 panosunun kömür arını yaklaşık 5’ er metre aralıklar ile toplam 21 birim bölgeye ayrılmıştır. Her birim bölge ise kendi içerisinde beş alt birim hücreye bölünerek her bir alt birim hücreden alınan düzensiz örnekler ile toplam 563 adet nokta yükleme dayanımı belirleme deneyleri yapılmıştır. Sonuç olarak yapılması pratik olan Schmidt sertlik ölçümleri ile nokta yükleme dayanım deney sonuçları arasındaki mekanik ilişkiler ve bu deney sonuçlarına dayalı kazı kolaylığına ait bir sınıflama bu çalışmada önerilmiştir.

Estimation of uniaxial compressive strength of pyroclastic rocks (Cappadocia, Turkey) by gene expression programming

Compressive strength of rocks is an important factor in structural design in rock engineering. Compressive strength can be determined in the laboratory by means of the uniaxial compressive strength (UCS) test, or it can be estimated indirectly by simple experiments such as point load strength (PLT) test and Schmidt hammer rebound test. Although the UCS test method is time-consuming and expensive, it is simple when compared to other methods. Therefore, many studies have been performed to estimate UCS values of rocks. Studies indicated that correlation coefficient of rock groups is low unless they are classified as metamorphic, sedimentary, or volcanic. Pyroclastic rocks are widely used as construction materials because of the fact that they crop out over extensive areas in the world. To estimate the UCS values of pyroclastic rocks in Central and Western Anatolia region, Turkey, multiple linear regression (MLR) analysis and gene expression programming (GEP) were employed and during the analysis, and PLT, ρd, ρs, and n were used as the independent variables. Based on the analysis results, it was detected that the GEP methods gave better results than MLR method. Additionally, the correlation coefficient (R2) values of training and sets of validation of the GEP-I model are 0.8859 and 0.9325, respectively, and this model, thereby, is detected the best of generation individuals for prediction of the UCS.

Tensile Strength Modeling of Limestone Rocks in Sulaymaniyah City, Iraq Using Simple Tests

Tensile strength of rocks is one of the mechanical properties of intact rock that is a significant parameter for designing geotechnical structures includes dam foundations and tunnels. The tensile strength can be determined indirectly using Brazilian indirect test procedure that is mentioned in the International Society for Rock Mechanics suggested methods. The availability of rock samples is needed to perform the Brazilian indirect test so as to determine their tensile strength which is expensive, time-consuming, and cost-effective especially for weak quality rock formations. Therefore, non-destructive methods for predicting the tensile strength of the rock are crucially needed during the poor quality of rock samples. Non-destructive tests can be correlated with indirect tests to predict Brazilian tensile strength (BTS) of rocks such as ultrasonic pulse velocity and Schmidt hammer. These methods are simple and can be easily conducted in the field. This study is focused on the tensile strength of limestone rocks for three main formations of Sulaymaniyah city. The samples were obtained using a standard core barrel. Statistical analysis including minimum, maximum, mean, standard deviation, variance, and coefficient of variance for the results was conducted. Single and multiple correlations between BTS and each of ultrasonic pulse velocity and Schmidt hammer rebound number of limestone rocks were created. Reasonable empirical equations were developed to predict the tensile strength of limestone rocks. In addition, the point load strength index was correlated with BTS. The comparison between proposed equations from this study and equation from the literature was also investigated.

Strength evaluation of granite block samples with different predictive models

Over the last decade, application of soft computing techniques has rapidly grown up in different scientific fields, especially in rock mechanics. One of these cases relates to indirect assessment of uniaxial compressive strength (UCS) of rock samples with different artificial intelligent-based methods. In fact, the main advantage of such systems is to readily remove some difficulties arising in direct assessment of UCS, such as time-consuming and costly UCS test procedure. This study puts an effort to propose four accurate and practical predictive models of UCS using artificial neural network (ANN), hybrid ANN with imperialism competitive algorithm (ICA–ANN), hybrid ANN with artificial bee colony (ABC–ANN) and genetic programming (GP) approaches. To reach the aim of the current study, an experimental database containing a total of 71 data sets was set up by performing a number of laboratory tests on the rock samples collected from a tunnel site in Malaysia. To construct the desired predictive models of UCS based on training and test patterns, a combination of several rock characteristics with the most influence on UCS has been used as input parameters, i.e. porosity (n), Schmidt hammer rebound number (R), p-wave velocity (Vp) and point load strength index (Is(50)). To evaluate and compare the prediction precision of the developed models, a series of statistical indices, such as root mean squared error (RMSE), determination coefficient (R2) and variance account for (VAF) are utilized. Based on the simulation results and the measured indices, it was observed that the proposed GP model with the training and test RMSE values 0.0726 and 0.0691, respectively, gives better performance as compared to the other proposed models with values of (0.0740 and 0.0885), (0.0785 and 0.0742), and (0.0746 and 0.0771) for ANN, ICA–ANN and ABC–ANN, respectively. Moreover, a parametric analysis is accomplished on the proposed GP model to further verify its generalization capability. Hence, this GP-based model can be considered as a new applicable equation to accurately estimate the uniaxial compressive strength of granite block samples.

Evaluation of empirical estimation of uniaxial compressive strength of rock using measurements from index and physical tests

Abstract The uniaxial compressive strength (UCS) of rock is an important parameter required for design and analysis of rock structures, and rock mass classification. Uniaxial compression test is the direct method to obtain the UCS values. However, these tests are generally tedious, time-consuming, expensive, and sometimes impossible to perform due to difficult rock conditions. Therefore, several empirical equations have been developed to estimate the UCS from results of index and physical tests of rock. Nevertheless, numerous empirical models available in the literature often make it difficult for mining engineers to decide which empirical equation provides the most reliable estimate of UCS. This study evaluates estimation of UCS of rocks from several empirical equations. The study uses data of point load strength (Is(50)), Schmidt rebound hardness (SRH), block punch index (BPI), effective porosity (n) and density (ρ) as inputs to empirically estimate the UCS. The estimated UCS values from empirical equations are compared with experimentally obtained or measured UCS values, using statistical analyses. It shows that the reliability of UCS estimated from empirical equations depends on the quality of data used to develop the equations, type of input data used in the equations, and the quality of input data from index or physical tests. The results show that the point load strength (Is(50)) is the most reliable index for estimating UCS among the five types of tests evaluated. Because of type-specific nature of rock, restricting the use of empirical equations to the similar rock types for which they are developed is one of the measures to ensure satisfactory prediction performance of empirical equations.

Effect of water saturation on strength and deformability of building calcarenite stones: Correlations with their physical properties

Stone construction elements are frequently in moist environments or in direct contact with water. Design and test standards have traditionally ignored the water impact on rock materials. However, several studies have shown that moisture can cause drastic strength reductions and deformability increase in some sedimentary rocks. For that reason, the main objectives of this work are: a) to quantify and understand the influence of water saturation on strength and deformability of four porous calcarenite building stones widely used in SE Spain; b) to establish correlations between physical and mechanical properties of these rock materials in dry and saturated states and c) to compare the results with previous findings. The results showed a very significant reduction of mechanical properties such as unconfined compressive strength, Young’s modulus and point load strength index when these stones undergo saturated. In addition, significant correlations between physical properties (density, porosity, P wave velocity and dynamic elastic parameters) and the mentioned mechanical properties were established in dry and saturated conditions. Additionally, relationships among the mechanical properties of stones in both states are also proposed.

Properties of fly ash-based lightweight geopolymer concrete prepared using pumice and expanded perlite as aggregates

Abstract The present paper aims to utilize the fly ash wastes with lightweight aggregates for geopolymer concrete production process in which sodium hydroxide (NaOH) and sodium metasilicate (Na2SiO3) were used as alkali activators, respectively. The designed experiments were examined by the Yates Analyses and so the productions of geopolymer concrete were investigated depending on curing temperature, solid/liquid rate and concentration of alkali activators. The curing temperature and alkali activator concentration were revealed as effective parameters in geopolymerization. The effects of expanded perlite (EP) and acidic pumice (AP) aggregates were discovered for the production of lightweight geopolymer concretes. The microstructural properties of each produced geopolymer concrete were characterized using SEM, EDS and laser particle size analyses. The specifications of the concrete were evaluated based on their uniaxial compressive strength (UCS), point load strength (PLS), sonic speed (SS), Mohs hardness (MH), and water absorption (WAR) ratio results. In addition, the effects of pre-wetting of EP aggregates, which have hydrophilic nature, were examined. To the best of our knowledge, this is the first time that pre-wetted lightweight EP aggregates were used to produce lightweight GP concretes. As a result of pre-wetting, chemical usage decreased by 32.5%. The UCSs of the lightweight geopolymer concretes were in a range of 10–50 MPa and their unit weights changed between 1250 and 1700 kg/m3. Lighter concretes were obtained by the addition of EP aggregates rather than AP ones.

Multivariate probability distribution for some intact rock properties

A multivariate probability distribution model for nine parameters of intact rocks, including unit weight (γ), porosity (n), L-type Schmidt hammer hardness (RL), Shore scleroscope hardness (Sh), Brazilian tensile strength (σbt), point load strength index (Is50), uniaxial compressive strength (σc), Young’s modulus (E), and P-wave velocity (Vp), is constructed based on the ROCK/9/4069 database that was compiled by the authors. It is shown that the multivariate probability distribution captures the correlation behaviors in the database among the nine parameters. This multivariate distribution model serves as a prior distribution model in the Bayesian analysis and can be updated into the posterior distribution of the design intact rock parameter when multivariate site-specific information is available. In this paper, the parameters for the posterior distribution of the design intact rock parameter are summarized into user-friendly tables so that engineers do not need to conduct the actual Bayesian analysis. Caution should be taken in extrapolating the results of this paper to cases that are not covered by ROCK/9/4069, because the resulting posterior distribution can be misleading.

Strength Characteristics of Reef Limestone for Different Cementation Types

The strength of reef limestone is an important parameter for conducting the bearing capacity designing of coral reef foundation. Therefore, it is important to obtain the strength index of reef limestone to ensure the strength and stability of reef foundation. In this paper, reef limestone of three different cementation types [gravelly calcareous sandstone (A); calcareous conglomerate (B); coral limestone (C)] were tested by field point load test. Then, the uniaxial compression test was carried out indoors by using the rock samples of corresponding cementation type, and the relationship between the two strengths was discussed. The results show that: ① the point load strength and uniaxial compressive strength of gravelly calcareous sandstone (A) are similar to that of calcareous conglomerate (B), and are significantly lower than that of coral limestone (C); the point load strength is about 1/3 to 1/2 of that of coral limestone and the uniaxial compressive strength is less than 50% of that of coral limestone. ② The uniaxial compressive strength of reef limestone is generally greater than the point load strength, which is due to the brittle nature of the reef limestone, and the different mechanism of action of point load test and uniaxial compression test. ③ There is a positive correlation between the point load strength and uniaxial compressive strength of reef limestone. The difference between the two strengths varies with the cementation type. The quantitative research on relationship between the two strengths of reef limestone must take into account the cementation type.

A new methodology to estimate the powder factor of explosives considering the different lithologies of volcanic lands: A case study from the island of Tenerife, Spain

Many populations live on small islands where there are no naturally occurring rivers and lakes. Therefore, they need to look for underground water sources that involves the use of complex, expensive civil engineering operations which normally use explosives. An adequate prediction of the amount of explosive and performance of blasts is essential for a proper drilling plan. In the present work, a new methodology is proposed to estimate the consumption of explosives with respect to each type of rock drilled, based on a regression model that relates the geomechanical characteristics of the rocks with the progress made with each blast. The model is obtained using real data from the drilling of 85.70 m in a water tunnel with a cross section of 4 m2 on a volcanic island. The blast used gelatin-based explosives based on nitroglycol, placed according to the drilling and blasting pattern for tunnels (structure to capture groundwater). The extracted rocks were mechanically characterized (density, porosity and point load strength index) and correlated with the powder factor. A methodology based on a regression model was constructed with this information that allows predictions of the powder factor, number of blasts and the amount of explosive needed as a function of the geomechanical properties of the tested rocks. The blasting progress had a non-linear relationship with the geomechanical parameters of the different lithotypes. The data show that advance is strongly non-linearly correlated with the porosity and the point load strength index of the rock. The regression model will be useful in the design of tunnel construction projects, as it can provide a better estimation of duration and costs of civil works than those used at present.