Blast-induced ground vibration (PPV) evaluation for a safe blasting is a long-established criterion used mainly by the empirical equations. However, the empirical equations are again considering a limited information. Therefore, using Machine Learning (ML) tools [Support Vector Machine (SVM) and Random Forest (RF)] can help in this context, and the same is applied in this work. A total of 73 blasts are monitored and recorded in this work. For the ML tools, the dataset is divided into the 80-20 ratio for the training and testing purposes in order to evaluate the performance capacity of the models. The prediction accuracies by the SVM and RF models in predicting the PPV values are satisfactory (up to 9% accuracy). The results obtained show that the coefficient of determination (R2) for RF and SVM is 0.81 and 0.75, respectively. Compared to the existing linear regressions, this work recommends using a machine learning regression model for the PPV prediction.

Designing suitable extraction methods for mining randomly occurring pocket formation of gemstones has never been easy at the Musakashi emerald mine due to the limited geological information. In order to improve the productivity as well as the recovery, in this work, we undertake a detailed geological survey (airborne, surface mapping, geochemical sampling, and trenching activities), and review, analyze, and establish the appropriate extraction methods, and conduct the economic viability of the mining emeralds in the Musakashi area. A total of 51 holes are drilled in order to define the mineralization and estimate the mineral resource for the rubble ore and the in-situ ore zones using the Surpac Geovia software. The diamond drilling unravels the existence of an alteration zone enveloping the shales in an area of 150m by 100m. The emerald is localized within these reaction zones, and is estimated to extend to a depth of about 20–30m below the surface. The total mineral resource stands at 345, 290 grams for the rubble ore and 123,870 grams for the discordant veins. From the geological information obtained, a trial pit design is established with a target of increasing recovery of emeralds from the current 10 kg to 100 kg per year.

The blasting operation is an important rock fragmentation technique employed in several foundation engineering disciplines such as mining, civil, tunneling, and road planning. Back-break (BB) is one of the adverse effects caused by the blasting operations that produces several effects including vulnerability of mining machinery, bench slope design, and risks to the next blast-patterns due to the eruption of gases from several discontinuities in jointed rock masses. Several techniques have been executed by the researchers in order to predict BB in the blasting operations. However, this is the first work to implement a-state-of-the-art Catboost-based t-distributed stochastic neighbor embedding (t-SNE) approach to predict BB. A total of 62 datasets having 12 influential BB-generating features are collected from genuine blasting patterns. A novel dimensionality depletion technique t-SNE that operates the Kullback-Leibler divergence interpretation is employed to tailor the pioneer exaggeration of the blasting dataset. Then the t-SNE dataset obtained is split into a 70:30 ratio of the training and testing datasets. Finally, the Catboost method is implemented on a low-dimensionality blasting database. The performance evaluation criterion confirms that the BB predictive model is more stable with a goodness of fit = 99.04 in the training dataset, 97.26 in the testing datasets, and could anticipate a more accurate prediction. Moreover, the model presented in this work performs superior to the existing publicly available execution of BB. In summary, this model can be practiced in order to predict BB in several rock engineering practices and mining industry scenarios.

This work incorporates the DEMATEL-MABAC method for quantifying the potential of roof fall in coal mines by means of the coal mine roof rating (CMRR) parameters. For this purpose, considering the roof weighting interval as a quantitative criterion for the stability of the roof, the immediate roof falling potential was quantified and ranked in 15 stopes of Eastern Alborz Coal Mines Company. In this regard, on the basis of the experts’ judgments, the fuzzy DEMATEL method was used for designation weights of the parameters, and the MABAC method was incorporated to quantify and rank the stopes (alternatives). “UCS of roof” and “joint spacing” in the immediate roof were found to be the most important parameters that controlled roof falling in stopes; and “joint persistence” was also found to be a quite significant parameter. Finding confirms that overall strength of rood rock mass plays a main role in the falling potential. Comparison of the coefficients of determination (R2) between the weighting interval and proposed model with that and original CMRR indicated more than 15% increase, which represented that the new proposed model was more accurate to quantify roof quality. The findings of this work show that using this combined method and specializing the CMRR method for a given mine geo-condition to assess the quality of the roof and its potential of collapse possesses a higher performance when compared with the original CMRR method.

In this paper, we aim to achieve two specific objectives. The first one is to examine the applicability of wavelet neural network (WNN) technique in ore grade estimation, which is based on integration between wavelet theory and Artificial Neural Network (ANN). Different wavelets are applied as activation functions to estimate Cu grade of borehole data in the hypogene zone of porphyry ore deposit, Shahr-e-Babak district, SE Iran. WNN parameters such as dilation and translation are fixed and only the weights of the network are optimized during its learning process. The efficacy of this type of network in function learning and estimation is compared with Ordinary Kriging (OK). Secondly, we aim to delineate the potassic and phyllic alteration regions in the hypogene zone of Cu porphyry deposit based on the estimation obtained of WNN and OK methods, and utilize Concentration–Volume (C–V) fractal model. In this regard, at first C–V log–log plots are generated based on the results of OK and WNN. The plots then are used to determine the Cu threshold values of the alteration zones. To investigate the correlation between geological model and C-V fractal results, the log ratio matrix is applied. The results showed that, Cu values less than 1.1% from WNN have more overlapped voxels with phyllic alteration zone by overall accuracy (OA) of 0.74. Spatial correlation between the potassic alteration zones resulted from 3D geological modeling and high concentration zones in C-V fractal model showed that the alteration zone has Cu values between 1.1% and 2.2% with OA of 0.72 and finally have an appropriate overlap with Cu values greater than 2.2% with OA of 0.7. Generally, the results showed that the WNN (Morlet activation function) with OA greater than OK can be can be a suitable and robust tool for quantitative modeling of alteration zones, instead of qualitative methods.

Sustainability assessment has received numerous attentions in the mining industry. Mining sustainability includes the environmental, economic, and social dimensions, and a sustainable development is achieved when all these dimensions improve in a balanced manner. Therefore, to measure the sustainability score of a mine, we require an approach that evaluates all these three dimensions of mining sustainability. Some frameworks have been developed to compute the sustainability score of mining activities; however, some of them are very complicated and the others do not cover all the environmental, economic, and social aspects of sustainability. In order to fill this gap, this work was designed to introduce a practical approach to determine the score of mining sustainability. In order to develop this approach, initially, 14 negative and positive influential macro factors in the sustainability of open-pit mines were identified. Then the important levels of the factors were estimated based on the comments and scores of some experts. Two checklists were constructed for the negative and positive factors. The sustainability score was computed using these checklists and the importance levels of the factors. The score range was between -100 and +100. In order to implement the proposed approach, the Angouran lead and zinc mine was selected. The sustainability score of the Angouran mine was +47.91, which indicated that the this mine had a sustainable condition. This score could increase through modification of some factors.

Displacements around a tunnel, occurring as a result of excavation, consist of the elastic and plastic parts. In this paper, we discuss the elastic part of displacements as a result of excavation, called net displacement. In general, the previous analytical solutions presented for determining the displacements around a circular tunnel in an elastic medium do not give the net displacements directly. The well-known Kirsch solution is the most widely used method for determining the induced stresses and net displacements around a circular opening in a biaxially-loaded plate of homogeneous, isotropic, continuous, linearly elastic material. However, the complete solution for obtaining the net displacements has not been presented or highlighted in the available literature. Using the linear elasticity, this paper reviews and presents three different analytical methods for determining the net displacements directly as well as induced stresses around a circular tunnel. The three solution methods are the Lame' method, airy stress function method, and complex variable method. The tunnel is assumed to be situated in an elastic, continuum, and isotropic medium in the plane strain condition. The solutions are presented for both the hydrostatic and non-hydrostatic in situ stresses in the 2D biaxial loading condition along with an internal pressure. Loading and unloading in tunneling occurring as a result of excavation and stress differences between the induced and initial ones are considered to evaluate the net displacements directly. Finally, some examples are given to demonstrate the complete solution and show the difference between the net elastic displacements as a result of excavation and total elastic displacements that are not real.

The uniaxial compressive strength of weak rocks (UCSWR) is among the essential parameters involved for the design of underground excavations, surface and underground mines, foundations in/on rock masses, and oil wells as an input factor of some analytical and empirical methods such as RMR and RMI. The direct standard approaches are difficult, expensive, and time-consuming, especially with highly fractured, highly porous, weak, and homogeneous rocks. Numerous endeavors have been made to develop indirect approaches of predicting UCSWR. In this research work, a new intelligence method, namely relevance vector regression (RVR), improved by the cuckoo search (CS) and harmony search (HS) algorithms is introduced to forecast UCSWR. The HS and CS algorithms are combined with RVR to determine the optimal values for the RVR controlling factors. The optimized models (RVR-HS and RVR-CS) are employed to the available data given in the open-source literature. In these models, the bulk density, Brazilian tensile strength test, point load index test, and ultrasonic test are used as the inputs, while UCSWR is the output parameter. The performances of the suggested predictive models are tested according to two performance indices, i.e. mean square error and determination coefficient. The results obtained show that RVR optimized by the HS model can be successfully utilized for estimation of UCSWR with R2 = 0.9903 and MSE = 0.0031203.

Determination of the borehole and fracture initiation positions is the main aim of a borehole stability analysis. A wellbore trajectory optimization with the help of the mud pressure may be unreasonable since the mud pressure can only reflect the degree of difficulty for the initial damage to occur at the wellbore rather than the extent of the wellbore damage. In this work, we investigate the failure extension in different arbitrary inclination boreholes under different in-situ stress regimes. Assuming the plane strain condition, the Mohr-Coulomb, Mogi-Coulomb, and Modified Lade rock failure criteria are utilized. We present an analytical equation to determine the optimum drilling trajectory of an Iranian oilfield. In order to predict the degree of wellbore damage, the initial shear failure location, failure width, and failure depth of arbitrary wellbores are determined. Then a new model is derived to calculate the initial failure area of a directional wellbore because it is more efficient in a wellbore stability analysis. The results obtained show that in the target oilfield, the vertical and low-deviated direction is the optimum drilling path. According to the results of this work, optimization of the wellbore trajectory based on the estimated failure zone is a reasonable method if a considerable failure zone takes place around the borehole wall.

Prediction of the production rate of the cutting dimensional stone process is crucial, especially when chain saw machines are used. The cutting dimensional rock process is generally a complex issue with numerous effective factors including variable and unreliable conditions of the rocks and cutting machines. The Group Method of Data Handling (GMDH) type of neural network and Radial Basis Function (RBF) neural network, as two kinds of the soft computing method, are powerful tools for identifying and assessing the unpredicted and uncertain conditions. Hence, this work aims to develop prediction models for estimating the production rate of chain saw machines using the RBF neural network and GMDH type of neural network, and then to compare the results obtained from the developed models based on the performance indices including value account for, root mean square error, and coefficient of determination. For this purpose, the parameters of 98 laboratory tests on 7 carbonate rocks are accurately investigated, and the production rate of each test is measured. Some operational characteristics of the machines, i.e. arm angle, chain speed, and machine speed, and also the three important physical and mechanical characteristics including uniaxial compressive strength, Los Angeles abrasion test, and Schmidt hammer (Sch) are considered as the input data, and another operational characteristic of the machines, i.e. production rate, is considered as the output dataset. The results obtained prove that the developed GMDH model is able to provide highly promising results in order to predict the production rate of chain saw machines based on the performance indices.