Estimating penetration rates of Jumbo drills is crucial for optimizing underground mining drilling processes, aiming to reduce costs and time. This study investigates various regression and machine ...learning methods, including Multilayer Perceptron (MLP), Support Vector Regression (SVR), and Random Forests (RF), to predict the penetration rates (ROP) using multivariate inputs such as operation parameters and rock mass characteristics. The Rock Mass Drillability Index (RDi), incorporating both intact rock properties and structural parameters, was utilized to characterize the rock mass. The dataset was split into 80% for training and 20% for testing. Performance metrics including correlation coefficient (R
), variance accounted for (VAF), mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE) were calculated for each method to evaluate the accuracy of the predictions. SVR exhibited the best prediction performance for ROP, achieving the highest R2, lowest RMSE, MAE, and MAPE, as well as the largest VAF values of 0.94, 0.15, 0.11, 4.84, and 94.13 during training, and 0.91, 0.19, 0.13, 6.02, and 91.11 during testing, respectively. With this high accuracy, we conclude that the proposed machine learning algorithms are valuable and efficient predictors for estimating jumbo drill penetration rates in underground mining operations.
Penetrability is a dominant factor in selecting the suitable drilling method, adjustment of machine parameters and tool wear analysis. In this paper, it is aimed to classify the rock penetrability ...using Artificial Bee Colony (ABC) algorithm as one of the powerful meta-heuristic algorithms and Self-Organizing Map (SOM) as one of the precise scientific tools. For this purpose, eight different rocks from open pit mines and highway slopes were classified into four separate clusters according to physical and mechanical properties of rock including uniaxial compressive strength, mean Mohs hardness, Young modulus and Schimazek’s F-abrasivity. To evaluate and validate the obtained clusters, field studies were performed and the drilling rate of studied rocks was measured. The results of field study were compared with the results of ABC algorithm and SOM. The results showed that, the studied rocks were reliably classified with respect to their drilling rate. It is concluded that applied techniques can be used for solving the complex rock engineering problems specially in engineering classification of rocks.
Rock abrasivity index (RAI) and uniaxial compressive strength (UCS) are two key parameters for assessing abrasivity and durability of building stones, respectively. Direct determination of these ...parameters is a time-consuming, tedious and costly task. Hence, indirect and nondestructive tests such as P-wave velocity (Vp) and Schmidt hammer rebound (SHR) are good alternative for prediction of RAI and UCS. This study mainly focuses on developing fast and reliable correlations for predicting RAI and UCS of Iranian granite building stones using Vp and SHR. For this purpose, 15 types of commercial granite building stones were collected from different regions of Iran. After preparing the required samples, petrographic studies and physico-mechanical tests were performed. Then, using simple and multiple regression analysis, various empirical correlations for RAI and UCS prediction based on Vp and SHR were developed. The coefficient of determination (R
2
), the variance account for (VAF), the normalized root mean square error (NRMSE) and the performance index (PI) were calculated to check the prediction performance of the correlations. The results showed that the proposed correlations derived from nonlinear multiple regression have more prediction capability than the others. These correlations can be applied for fast prediction of RAI and UCS with acceptable error for practical applications in building stone industry.
This paper aims to investigate the impact of mixed ground conditions and the presence of groundwater, which are critical geotechnical variables during mechanized tunneling, on the tool life, ...reliability, and maintainability of the EPB-TBM cutterhead. To achieve this goal, field data from the Tabriz urban railway project were gathered and classified into two groups: failures occurring in the tunnel's upper section above the water level and failures in the lower section below the water level. A comprehensive analysis of this data was conducted. The examination of various cutting tool types' consumption in mixed ground conditions revealed that scrapers had the highest replacement rate, while other tool types experienced fewer replacements. In terms of maintainability, the analysis showed that under dry ground conditions, there is an 80% probability of completing cutterhead maintenance within less than four shifts. However, in saturated ground conditions, this figure rises to 18.5 shifts. The reliability analysis demonstrated that the mean time between failures in dry ground and below the water level stands at 49.8 and 107.4 h, respectively. The significant contrast between maintainability and reliability findings underscores the influence of ground conditions on machine downtime and operational efficiency. The outcomes of this study provide valuable operational benchmarks that can be applied in EPB mechanized tunneling, enabling better project scheduling and enhancing the reliability of construction contracts.
The Leeb hardness test is a non-destructive and portable technique that can be used both in the laboratory and in-field applications. The main purpose of this study is to predict the dynamic elastic ...constants of the igneous and sedimentary rocks using Leeb dynamic hardness testing. For this purpose, three vital topics have been investigated and analyzed. First, the relationships between ultrasonic wave velocities and dynamic elastic constants with the Leeb hardness were investigated. Thereafter, by determining the rock quality index (IQ) using microscopic studies and by analyzing the quality index-porosity plot, the variation of the Leeb hardness values was studied. Eventually, the longitudinal waveform in rock samples with different quality indexes and Leeb hardness were analyzed. To achieve these outputs, 33 samples of igneous and sedimentary rocks with a wide range of physical, mechanical, and textural features were collected and tested. The results of the analyses show that in both igneous and sedimentary rocks, the dynamic modulus of elasticity (E
d
) has a significant correlation with the Leeb hardness. Generally, based on the microscopic studies, it was observed that the existence of the porosity in sedimentary rocks and intercrystalline and intracrystalline fissures in igneous rocks sharply reduce the Leeb hardness and thus lead to changes in the form of the longitudinal waves.
Purpose - Longwall mining is a special mining method with high productivity and smooth operation and the drum shearer is known as the most important component in longwall mines due to its direct role ...in the coal cutting and production process. Therefore, its reliability is important in keeping the mine production at a desired level. Hence, reliability analysis is essential in identifying and removing existing problems of this machine in order to achieve a better production condition. This paper seeks to learn about the reliability of the shearer machine in order to locate critical subsystems. The improvement of the reliability of the critical subsystems, to enhance the optimum operation of the shearer machine, is the main objective of this research.Design methodology approach - A basic methodology was used in this paper for the reliability modeling of the shearer machine. First, failure and performance data from a two-year period at the Tabas Coal Mine-Iran was classified and sorted. The tests for validating the assumption of independent and identical distribution (iid) of TBF data are done and the best modeling method for each subsystem was selected among the renewal process, homogeneous Poisson process and non-homogeneous Poisson process. Finally, the reliability of subsystems and the machine were assessed.Findings - The study revealed that six important subsystems of the shearer machine are; water system, haulage, electrical system, hydraulic system, cutting arms, and cable system. Pareto analysis shows that the 30 percent of failures and stoppages of the shearer were related to the water system and this system is the most critical subsystem of the machine. The failure rate analysis shows that the failure rates of the hydraulic, haulage and electrical systems were decreasing, meanwhile, the failure rates of the water system, cutting arms and cable system were increasing. The reliability of drum shearer reaches the zero value after 100 hours.Originality value - This paper, for the first time, defines a practical set of subsystems for the coal shearer based on field data and machine design.
Display omitted
•Mapping the instrumentation for online monitoring, analysis, and characterization.•Data-centric and in-discipline expertise two congenial ingredients in modern ...mining.•Instrumentation to accelerate digital transformation in the minerals sector.•Emerging instrumentation, sensors, and infrastructure.•Digitalization in the minerals industry: Dry labs and a systematic transition.
Dry laboratories (dry labs) are laboratories dedicated to using and creating data (they are data-centric). Several aspects of the minerals industry (e.g., exploration, extraction and beneficiation) generate multi-scale and multivariate data that are ultimately used to make decisions. Dry labs and digitalization are closely and intricately linked in the minerals industry. This paper focuses on the instrumentation and infrastructure that are required for accelerating digital transformation initiatives in the minerals sector. Specifically, we are interested in the ability of current and emerging instrumentation, sensors and infrastructure to capture relevant information, generate and transport high-quality data. We provide an essential examination of existing literature and an understanding of the 21st century minerals industry. Critical analysis of the literature and review of the current configuration of the minerals industry revealed similar data management and infrastructure needs for all segments of the minerals industry. There are, however, differences in the tools and equipment used at different stages of the mineral value chain. As demand for data-driven approaches grows, and as data resulting from each segment of the minerals industry continues to increase in abundance, diversity and dimensionality, the tools that manage and utilize such data should evolve in a way that is more transdisciplinary (e.g., data management, artificial intelligence, machine learning and data science). Ideally, data should be managed in a dry lab environment, but minerals industry data is currently and historically disaggregated. Consequently, digitalization in the minerals industry must be coupled with dry laboratories through a systematic transition. Sustained generation of high-quality data is critical to sustain the highly desirable uses of data, such as artificial intelligence-based insight generation.
A new classification system is presented to evaluate and ranking the sawability of carbonate rock. The sawability of carbonate rock is classified into five categories: excellent, good, fair, poor and ...very poor. The sawability is assumed to depend on the uniaxial compressive strength, Young’s modulus, Mohs hardness, and a new abrasivity index. The FAHP approach is used to determine the weights of the above-mentioned parameters by decision makers. Moreover, in this paper, a new classification system was developed to modify Schimazek’s F-abrasiveness factor. In this new abrasivity classification, each parameter has a different importance coefficient. The new abrasivity index of carbonate rocks can be obtained from this new abrasivity classification system. The calculated sawability index of developed classification is applied for Iranian carbonate rocks to evaluation the energy consumption in rock sawing process. A variety of two groups of carbonate rocks (seven types) were saw using a fully instrumented laboratory sawing rig at different feed rates, peripheral speeds, and depth of cut. Then, a new statistical model was obtained using multiple regression method based on operating parameters and rock sawability index.
► A new classification system to evaluate sawability of carbonate rock is developed. ► FAHP approach is used in determining of the weights of parameters. ► The application of new classification index was studied. ► A new statistical model was obtained for predicting the energy consumption.
This paper aims to discuss the recent development in rock hardness testing methods and their applications in rock engineering and geological studies. Hardness is one of the essential physical ...characteristics of minerals and rocks, with dominant effects on rock mechanics and excavatability. In this paper, all available rock hardness testing methods are classified into main categories: static and dynamic methods. After that, standards and testing procedures have been briefly discussed using various literature. The review clarifies the dominant factors that affect the rock hardness as well as physicomechanical characteristics, which affect the hardness. The correlations between different hardness testing methods are analyzed using regression analysis, and their interconnections between them are presented. Also, the applications of hardness scales in the assessment of rock excavatability and machinability have been investigated. In total, it could be concluded that dynamic hardness testing methods have been widely applied in rock engineering. However, the relative standards and field measurement procedures have not been developed well. Future research must incredibly be focused on this lack of past studies and should try to develop reliable models for the prediction of physicomechanical rock parameters.
Operating parameters affect the wear of abrasive tools during the polishing stage in building stone processing plants. This study investigates the effects of essential operating parameters including ...polishing head pressure, head rotation speed and water flow rate on the wear of the abrasive tools. For this purpose, a building stone abrasivity test was used to determine the weight loss of the abrasive tools during laboratory polishing of fifteen different types of Iranian granitic building stones. The standard operating parameters of the test were a polishing head pressure of 5 bar, a head rotation speed of 300 revolutions per minute (rpm), and a water flow rate of 4 L/min. The values of the operating parameters were changed to values within the range from ±25% and ±50% of the standard conditions in order to investigate the effect of variations in these parameters on the wear of the abrasive tools during the polishing stage. The results of different tests showed that the wear of the abrasive tools was directly proportional to the pressure up until a critical value of around 6.25 bar, after which it gradually decreased. This nonlinear wear behavior does not conform to Archard’s well-known classical wear law. The FESEM images of the worn surfaces showed that due to excessive load, debonded abrasive particles could not be pulled out from the pin surface and led to an interlocking phenomenon between the pin and stone surface. It was also found that the wear of the abrasive tools increased with increasing head rotation speed, while it decreased with the water flow rate. Moreover, the main wear mechanism of tests was abrasive wear and in some cases with a mixture mode of adhesion and delamination.