Real-time Mining Research Articles

Spectrometric borehole logging in mineral exploration and mining

Borehole logging tools based on pulsed neutron technology are used to infer geophysical parameters such as bulk density. If fitted with a gamma-ray spectrometer, they may also measure elemental mass fractions of a variety of formation elements. Spectrometric borehole logging tools of this kind are established in the oil and gas industry. With the demand for mineral resources surging, cost- and time-efficient measurement techniques are increasingly needed in mineral exploration. Their ability to detect multiple elements that are building blocks of minerals makes spectrometric borehole logging tools popular in mineral exploration and mining grade control. In this article, the potential of the OreLog pulsed neutron gamma spectrometric downhole logging tool is demonstrated at Erzberg Mountain (Styria, Austria). Erzberg hosts the largest known siderite deposit in the world, and open-pit mining is used to extract iron ore. The aim was to obtain a more detailed and faster geochemical characterization of iron ore deposits prior to blasting. Elemental logs were acquired with highest accuracies for Fe, Ca, and Mn, followed by Si, Mg, K, and S. The tool mapped a 2D cross section of formation element concentration within a few hours, which agrees with orogenetic fault and geologic contact lines. Mineralogical information retrieved from elemental logs confirmed the interlaced mineralogy of the site. It is dominated by a carbonate body, hosting an intergrowth of Mg-rich siderite (sideroplesite) and a solid solution of dolomite/ankerite/kutnohorite. In addition to the tool's potential for enhanced real-time mining control, the benefit of continuous depth-resolved elemental logs is seen in the possibility to deduce a more refined and reliable geochemical and mineralogical model of the deposit. The information-rich data stream opens applications beyond grade control and exploration, such as data assimilation with gravity models or geologic model building.

Tweeting for Health Using Real-time Mining and Artificial Intelligence-Based Analytics: Design and Development of a Big Data Ecosystem for Detecting and Analyzing Misinformation on Twitter.

Digital misinformation, primarily on social media, has led to harmful and costly beliefs in the general population. Notably, these beliefs have resulted in public health crises to the detriment of governments worldwide and their citizens. However, public health officials need access to a comprehensive system capable of mining and analyzing large volumes of social media data in real time. This study aimed to design and develop a big data pipeline and ecosystem (UbiLab Misinformation Analysis System [U-MAS]) to identify and analyze false or misleading information disseminated via social media on a certain topic or set of related topics. U-MAS is a platform-independent ecosystem developed in Python that leverages the Twitter V2 application programming interface and the Elastic Stack. The U-MAS expert system has 5 major components: data extraction framework, latent Dirichlet allocation (LDA) topic model, sentiment analyzer, misinformation classification model, and Elastic Cloud deployment (indexing of data and visualizations). The data extraction framework queries the data through the Twitter V2 application programming interface, with queries identified by public health experts. The LDA topic model, sentiment analyzer, and misinformation classification model are independently trained using a small, expert-validated subset of the extracted data. These models are then incorporated into U-MAS to analyze and classify the remaining data. Finally, the analyzed data are loaded into an index in the Elastic Cloud deployment and can then be presented on dashboards with advanced visualizations and analytics pertinent to infodemiology and infoveillance analysis. U-MAS performed efficiently and accurately. Independent investigators have successfully used the system to extract significant insights into a fluoride-related health misinformation use case (2016 to 2021). The system is currently used for a vaccine hesitancy use case (2007 to 2022) and a heat wave-related illnesses use case (2011 to 2022). Each component in the system for the fluoride misinformation use case performed as expected. The data extraction framework handles large amounts of data within short periods. The LDA topic models achieved relatively high coherence values (0.54), and the predicted topics were accurate and befitting to the data. The sentiment analyzer performed at a correlation coefficient of 0.72 but could be improved in further iterations. The misinformation classifier attained a satisfactory correlation coefficient of 0.82 against expert-validated data. Moreover, the output dashboard and analytics hosted on the Elastic Cloud deployment are intuitive for researchers without a technical background and comprehensive in their visualization and analytics capabilities. In fact, the investigators of the fluoride misinformation use case have successfully used the system to extract interesting and important insights into public health, which have been published separately. The novel U-MAS pipeline has the potential to detect and analyze misleading information related to a particular topic or set of related topics.

Trusted Network Difference Data Mining Algorithm Based on Artificial Bee Colony Optimization

Abstract Trusted network is characterized by a large amount of data, abnormal dispersion, and high complexity. Traditional methods are easily affected by trusted network environment, resulting in unreliable mining results. Therefore, a new real-time mining method of trusted network difference data is proposed. Real-time collection of trusted network difference data through history system is performed on the basis of determining the principle of trusted network difference data mining and collecting and extracting the characteristics of difference data. The process of trusted network differential data mining is designed through the artificial bee colony algorithm. According to the process, differential data mining is carried out from three aspects: constructing a trusted network differential data transmission path, updating pheromone, and establishing a differential data transmission path set. The experimental results show that the proposed method can effectively realize the real-time mining of difference data, and the mining accuracy is more accurate.

Multiple regression method for working face mining pressure prediction based on hydraulic support monitoring dataset

Introduction: In the coal mining process, the intense mining pressure is an important factor hindering the safe and efficient production of the working face. In severe cases, it causes deformations in roadways such as roof breakages and rockbursts, and leads to instability. This can result in the roof falling over a large area and the coal wall, thereby inducing dynamic disasters. These aspects have restricted the economic benefits of coal.Methods: In this study, we set four model limitations based on the limited scope of action of the mining pressure itself and the quantitative relationships between mining pressures in different regions. A multiple linear regression model with these limitations is proposed for predicting the mining pressure for preventing roof breakages and rockbursts. Based on a hydraulic support monitoring dataset from a fully mechanized caving face of coal mining, the mining pressure prediction model is trained by using the first 70% of the dataset. And the linear regression coefficient of the model and the predicted value of the mining pressure are obtained. Then, the last 30% of the dataset was used for the validation of the model.Results: The research results show that the constrained multiple linear regression model can achieve remarkable prediction results. According to predictions of tens of thousands of on-site mining pressure datasets, the predicted data and actual pressure data have the same change trend and maintain a low relative error.Discussion: Therefore, after real-time mining pressure monitoring, the system obtains the roof pressure of the fully mechanized mining face. According to the dataset, the proposed prediction model algorithm quickly predicts the roof pressure value of the next mining section and effectively forewarns roof breakages and other accidents.

Editorial for Special Issue “3D/4D Geological Modeling for Mineral Exploration”

With the development of high-precision geological observation technology, in situ mineral microanalysis technology, isotope geochemical analysis technology, deep geophysical exploration technology, deep drilling, real-time mining, remote sensing high-resolution hyperspectral image technology, and supercomputer and industrial intelligence, geoscience has entered an era of big data and artificial intelligence in the 21st century [...]

Методика построения динамической модели управления качеством угля на сложно-структурных месторождениях

Методика построения динамической модели управления качеством угля на сложно-структурных месторождениях

Experimental Study on Damage Characteristics of Coal Samples under True Triaxial Loading and Dynamic Unloading

Abstract Coal bursts are one of the formidable hazards in underground coal mines, yet it is still not fully explored due to the complex stress environment that exists during mining. To better understand the bursting mechanism of coal under real-time mining conditions, it is necessary to develop an experimental method capable of reproducing in situ stress and loading-unloading paths of coal in in situ conditions. In this study, a self-developed true triaxial testing system was used to investigate the damage and failure characteristics of coal samples under true triaxial loading and dynamic unloading conditions. Acoustic Emission (AE) monitoring was used to capture the fracturing of the loaded coal. Passive Velocity Tomography (PVT) and Cumulative AE Energy Density (CAEED) were used to analyse damage evolution characteristics of the coal samples under true triaxial loading conditions. A high-speed camera was used to record the failure of the coal samples when the minimum principal stress σ3 was suddenly unloaded. It was found that continuous coal damage occurred primarily during the true triaxial loading period. The peak number of AE events in the coal samples increased and then dropped as σ1 levels increased. High and low wave velocity zones in the coal samples represent regenerations of the high-density zone and fracture emergence, respectively. Significant energy release zones transferred and expanded as the triaxial loading level increased. Under significant triaxial loads, the coal samples failed and were severely damaged, and the dynamic unloading of σ3 caused ejections of coal fragments at low velocities. The outcome of this study provides in-depth understanding of the failure mechanism of coal under in situ conditions.

Computer-aided tactical mine planning

The mining industry plays ‘first violin’ in the Russian economy. The software-managed mining and geology information systems enjoy wide-scale introduction and application these days. The technological innovations enable increased profitability and productivity in the mining industry, as well as the situation analysis and risk prediction over the whole service life of mines. This article discusses the experience of the mining and geology information system transformation at Lebedinsky GOK. The yearly and monthly mine planning procedures are described. The major value of GEOVIA products is the variability of mine planning scenarios toward the prompt managerial decisionmaking on open pit mining expansion. Furthermore, GEOVIA software products allow cutting-down the medium- and long-term mine planning time. Planning implementation requires both reliable and up-to-date data. The obligatory criterion of the decision-making promptness is the real-time information at all hours. To this effect, the either-direction integration of Modular Mining Systems, Automated Data Acquisition and Transfer System (ADAT) Kobus and GEOVIA Surpac has been accomplished, which enables using the actual data flow (locations of excavators, dump trucks and drill rigs, drilled and project boreholes) in the real-time mine planning and design process. Aimed to maintain competitive ability for a long time, a mining company should pursue continuous finding and introduction of technological innovations. Earlier the ‘manual and blind’ mine planning process took colossal labor costs and could run into a dead-end. For the avoidance of all these troubles, Metalloinvest has entered into an advanced software introduction contract with Dassault Systemes.

Calculation model for ventilation friction resistance coefficient by surrounding rock roughness distribution characteristics of mine tunnel

Real-time mine ventilation network solution is the core way to realize the actual intelligent ventilation, and ventilation friction resistance coefficient is a significant parameter of network solution. With the help of fractal theory to characterize the three-dimensional roughness characteristics of tunnel surrounding rock. A method to describe the roughness by fractal dimension and fractal intercept. We put the fractal dimension and fractal intercept into Matlab to randomly generate three-dimensional laser scanning data of tunnels. The fusion of the two fractal parameters made the three-dimensional roughness surface information more comprehensive. It has been applied to field practice accurately. Compared to the simulation results show that the relative error of the new prediction results is 3%. Comprehensive evaluation analysis shows that the new friction wind resistance formula can fully reflect the influence of three-dimensional rough surfaces on airflow friction resistance. With the help of three-dimensional laser scanning technology, we can calculate the airflow friction resistance of the tunnel quickly and accurately, which provides a reference for the development of key technology and the theory of intelligent ventilation parameter measurement.

Real Time Mine Fire Classification to Support Firefighter Decision Making

Real Time Mine Fire Classification to Support Firefighter Decision Making

Growth and biosorption of Purple guinea and Ruzi grasses in arsenic contaminated soils.

Increasing mining and industrial discharge of untreated wastewater, as well as excessive use of fertilizers for agricultural purposes, and heavy metal contamination in soil have become one of the serious environmental problems worldwide. In the present study, pot experiments were conducted to evaluate the influence of arsenic contamination and other factors on the growth and development of local forage grasses like Purple guinea and Ruzi grasses under controlled conditions. Influence of arsenic concentration, soil properties, and fertilizers on biosorption and withstanding potential of grasses was studied using model soil and real-time arsenic-contaminated mine soil. High arsenic contents in soil significantly affected the growth as well as biomass production of grasses and declined the overall biomass production concerning exposure durations. Purple guinea and Ruzi grasses showed growth tolerance in arsenic-contaminated soils with concentrations of 100 and 150 mg/kg respectively. Grass species, soil compositions, and properties, fertilizers, growth duration, etc. potentially influenced arsenic accumulation in grasses. Both local forage grasses showed <1 bio-accumulation factor (BAF) and bio-concentration factor (BCF) after 45 days that indicates the minimum harvesting time of 45 days, and biosorption rate was found significant to the exposure duration. Maximum translocation factor (TF) values observed in Purple guinea and Ruzi grasses were 0.65 and 0.95, respectively which are < 1, therefore, these local forage grasses could be labeled as arsenic-metallophytes and ability to tolerate high levels of heavy metals without much biosorption. The results confirmed that local forage grasses have much growth tolerance potential against arsenic in real-time mine soil with desired fertilizers and these species could be used for sustainable management of ecological health of the Thung Kum gold mine area in Thailand.

Highest-Level Implementation of Push–Relabel Algorithm to Solve Ultimate Pit Limit Problem

Nowadays due to the existence of the economic and geological uncertainties and the increasing use of scenario-based project evaluation in the design of open-pit mines, it is necessary to find an exact algorithm that can determine the ultimate pit limit in a short period of time. Determining the ultimate pit limit is an important optimization problem that is solved to define what will be eventually extracted from the ground, and directly impacts the mining costs, revenue, choosing mining equipment, and approximation of surface infrastructures outside the pit. This problem is solved in order to maximize the non-discounted profit under the precedence relation (access) constraints. In this paper, the Highest-Level Push-Relabel (HI-PR) implementation of the push–relabel algorithm is discussed and applied in order to solve the ultimate pit limit optimization problem. HI-PR uses the highest-label selection rule, global update, and gap heuristics to reduce the computations. The proposed algorithm is implemented to solve the ultimate pit limit for the nine real-life benchmark case study publicly available on the Minelib website. The results obtained show that the HI-PR algorithm can reach the optimum solution in a less computational time than the currently implemented algorithms. For the largest dataset, which includes 112687 blocks and 3,035,483 constraints, the average solution time in 100 runs of the algorithm is 4 s, while IBM CPLEX, as an exact solver, could not find any feasible solution in 24 hours. This speeding-up capability can significantly improve the current challenges in the real-time mine planning and reconciliation, where fast and reliable solutions are required.

A neural network approach for classifying events and blasts in real-time mining seismicity

Disclaimer Text and Data Mining. Any automated analytical technique aimed at analysing text and data in digital form in order to generate information including - but not limited to - patterns, trends and correlations (so-called Text and Data Mining) may only be applied if it is done by a research organisation or cultural heritage institution solely for the purpose of (non-commercial) scientific research as mentioned in Clause 3 of Directive (EU) 2019/790 (the Digital Single Market Directive) and Clause 15n of the Dutch Copyright Act [Auteurswet]. Text and Data Mining for commercial purposes is not allowed; all rights in this respect are reserved pursuant to Clause 4 paragraph 3 of the Digital Single Market Directive and Clause 15o paragraph 1 of the Dutch Copyright Act.

Distance variable improvement of time-series big data stream evaluation

Real-time information mining of a big dataset consisting of time series data is a very challenging task. For this purpose, we propose using the mean distance and the standard deviation to enhance the accuracy of the existing fast incremental model tree with the drift detection (FIMT-DD) algorithm. The standard FIMT-DD algorithm uses the Hoeffding bound as its splitting criterion. We propose the further use of the mean distance and standard deviation, which are used to split a tree more accurately than the standard method. We verify our proposed method using the large Traffic Demand Dataset, which consists of 4,000,000 instances; Tennet’s big wind power plant dataset, which consists of 435,268 instances; and a road weather dataset, which consists of 30,000,000 instances. The results show that our proposed FIMT-DD algorithm improves the accuracy compared to the standard method and Chernoff bound approach. The measured errors demonstrate that our approach results in a lower Mean Absolute Percentage Error (MAPE) in every stage of learning by approximately 2.49% compared with the Chernoff Bound method and 19.65% compared with the standard method.

A deep learning model for mining and detecting causally related events in tweets

AbstractNowadays, public gatherings and social events are an integral part of a modern city life. To run such events seamlessly, it requires real time mining and monitoring of causally related events so that the management can make informed decisions and take appropriate actions. The automatic detection of event causality from short text such as tweets could be useful for event management in this context. However, detecting event causality from tweets is a challenging task. Tweets are short, unstructured, and often written in highly informal language which lacks enough contextual information to detect causality. The existing approaches apply different techniques including hand‐crafted linguistic rules and machine learning models. However, none of the approaches tackle the issue related to the lack of contextual information. In this paper, we detect event causality in tweets by applying a context word extension technique and a deep causal event detection model. The context word extension technique is driven by background knowledge extracted from one million news articles. Our model achieves 79.35% recall and 67.28% f1‐score, which are 17.39% and 2.33% improvements to the state‐of‐the‐art approach.

Clean Technology for the Treatment and Modelling of Acid Mine Drainage Effluent

Acid Mine Drainage (AMD) exists as a phenomenon that involves the release of acidic water and metal conjugates, in and around mines, degrading the surrounding water environment. A real-time mining effluent is treated using low-cost adsorption technology using Combined Vegetable Waste Carbon (CVWC) as sorbent. Batch sorption was reviewed to know the effect of process factors on the removal of Cadmium (Cd), Zinc (Zn), and Iron (Fe). A two-level CCD (Central Composite Design) with three factors was adopted in the optimization of process factors. Also, the same factors were considered to review the ANNs (Artificial Neural Networks), model. A comparative statistical analysis was performed for the experimental data based on RMSE and R2 values in both RSM (Response Surface Methodology) and ANNs models. This study revealed that the ANNs model was well fit compared to RSM and this would probably reduce the experimental trials thereby reducing cumbersome calculations.

DEODORANT: a novel approach for early detection and prevention of polycystic ovary syndrome using association rule in hypergraph with the dominating set property

Present online health discussion forums generate the bountiful amount of digitized data through health-blogs, posts, tweets, and chats in the social media. People post queries, health issues they undergo along with the symptoms, diagnosis, and clinical reports to get direction for preventive measures and medical relief. As a case study, this work focus on detection of Polycystic Ovary Syndrome, a prevalent condition that affects a woman’s hormone levels. This PCOS problem has been investigated as it forms high-risk factor for infertility, heart disease, diabetes, stroke and many such diseases. We propose a novel model named as DEODORANT (Detection and prEvention of polycystic Ovary synDrome using assOciation rule hypeRgrAph and domiNating set properTy) to derive prospective use of real-time mining data. The unstructured data collected from various media sources are preprocessed using NLTK and association rules are derived by applying apriori algorithm. These association rules are represented in hypergraph and then regenerated as line graph to make it suitable for cluster construction. Spectral clustering is performed on line graph to partition into clusters of hypergraphs. By applying dominating set property on the resultant hypergraph, required inferences can be elicited. From the experimental results, support value of the outcome derived from the dominating set of each cluster has exhibited the symptoms and the causes with percentage ranking. It is evident that they get aligned with precise result portraying real statistics. This type of analysis will empower doctors and health organizations to keep track of the diseases, their symptoms for early detection and safe recovery.

Real-Time Mine Road Boundary Detection and Tracking for Autonomous Truck.

Road boundary detection is an important part of the perception of the autonomous driving. It is difficult to detect road boundaries of unstructured roads because there are no curbs. There are no clear boundaries on mine roads to distinguish areas within the road boundary line and areas outside the road boundary line. This paper proposes a real-time road boundary detection and tracking method by a 3D-LIDAR sensor. The road boundary points are extracted from the detected elevated point clouds above the ground point cloud according to the spatial distance characteristics and the angular features. Road tracking is to predict and update the boundary point information in real-time, in order to prevent false and missed detection. The experimental verification of mine road data shows the accuracy and robustness of the proposed algorithm.

Research on post-match score mechanism of players based on artificial intelligence and clustering regression model

Currently, the athletes’ post-match scores are mostly manual methods, and artificial intelligence is still less used in athletes’ post-match scores. Based on this, this study is based on machine learning algorithms and combined with athletes’ scores for analysis. At the same time, this study uses the reptile technology to conduct real-time mining of athletes’ data and proposes a model-based regression algorithm in the construction of scoring algorithm. Moreover, based on the actual situation, a comprehensive model combining clustering and regression is proposed. In addition, in order to study the validity of the model, this paper designs a performance simulation test, compares the proposed algorithm model with the traditional algorithm model, and collects relevant experimental data and draws the corresponding statistical graph. The experimental results show that the combination of clustering and regression can improve the model’s effect and the results are like the expert scores, which verifies the practicality of the proposed algorithm and provides a theoretical reference for subsequent related research.

Coal mine area monitoring method by machine learning and multispectral remote sensing images

Coal is currently the main energy in the world. A large amount of gangue is produced during the coal mining process, and the gangue contains a large amount of metal and sulfide, which is one of the environmental pollution sources. Therefore, how to monitor changes in coal mines in real time is an important task. With regard to this problem, we propose a new method of monitoring coal mining area. First, we collect samples of coal, gangue, and other objects from the Shenhua Baori Xile coal mine, and then measure the ground measured spectral reflectance data of these samples. For satellite data, we remove the interference information of the reflectance spectra from these images and established a relationship with the ground measured data. We propose a tree root algorithm and then combine extreme learning machine to build a classification model. Finally, the model is applied to remote sensing images, and a good extraction effect is obtained. Compared with typical monitoring methods, our method has the superiorities of high precision, low-priced, and fast speed, and it can monitor the changes in the coal mine area in real time. This is the basis for improving the environmental pollution around the coal mining area.