Search Documents

By Bruno Vingiani, Alessandro Bertero

"The use of Artificial Ground Freezing (AGF) for temporary soil strengthening and seepage control is an effective alternative to grouting when dealing with soils whose degree of finesses would imply the use of highly expensive chemical grouts. However, compared to grouting, the application of this improvement technique usually needs a more accurate preliminary soil investigation campaign and a design assisted by specific calculation software. Besides a general description of the main features of this technique, the paper will describe a recent application of AGF carried out in Rome to underpass an existing metro station.INTRODUCTIONNatural ground freezing occurs seasonally or permanently (permafrost) in some areas of the globe close to the poles and can negatively affect the engineering performance of underground structures. On the other hand, Artificial Ground Freezing (AGF) is man-made controllable freezing process that can be used in foundation engineering to temporarily strengthen the ground and create a barrier to the passage of groundwater. During the process, the heat is extracted from the soil in a cylindrical shape around a number of freezing pipes installed into the ground. This action produces columns of frozen soil, which expand gradually till they merge and create continuous frozen wall. The thickness of this barrier can be regulated according to the specific project requirements. Nowadays, AGF technique is applied to a wide range of foundation engineering problems where soil stability and groundwater flows are an issue (Pimentel et al. 2011, Haß and Schäfers, 2013). Typical applications include the temporary stabilization and waterproof of the ground around the excavation profile of mined tunnels until the construction of the final lining (Figure 1).The case history described in this paper deals with a recent application of AGF carried out during the construction of metro Line “C” in Rome. Specifically, this technique has been applied to allow the construction of two single-track mined tunnels running underneath an existing metro station belonging to Line “A”. In that case, the AGF has been evaluated by the Designers as the only possible solution for improving the mechanical and hydraulic characteristics"

Jan 1, 1900

By Luca Pingue, Regine Jagow-Klaff, Franco Muratore, Carlandrea Albonico, Damiano Frontini, Rudolf Wernecké

This paper describes an artificial ground freezing (AGF) application carried out to ensure both watertightness and structural support for the safe excavation of four cross passages of the Forrestfield Airport Link (FAL) project in Perth. The line will deliver 8.5 km extension of the existing urban rail network connecting the growing eastern suburbs of Perth with the existing suburban rail network. The proposed soil improvement technique is adopted as a smart alternative to jet grouting from the surface since the use of heavy equipment with long vertical mast was not allowed due to the line underpassing an airport in operation. In this paper, details of the challenges and lessons learned during both design and construction phases are given. Furthermore, it is described the geometry and the installation of freeze pipes in presence of a massive steel frame, ventilation system and slurry pipes of the tunnel boring machine (TBM) in operation. It is also illustrated the web monitoring system to allow key personnel to follow in real time the development of soil temperatures, tunnel convergences and ground surface deformations as well as changes in the interaction between international parties involved due to the COVID-19 pandemic.

May 1, 2022

By P Mugebe, M Yahyaei, M S. Kizil, R Low

This paper seeks to establish an empirical relationship between the impact of mining technological innovation implementation and a company’s market value. The company’s market value is represented by its stock price. In a bid to ascertain the relationship, a stock price prediction model is sought to be established using the firm-specific factors impacted by the implementation of innovative technology. This work is performed under the watch of the prevailing macroeconomic factors. The background anchors in the understanding that the difference between the economic status of a mineral deposit and its uneconomic status lies in the level of mining technological innovation most prevalent at a given time (Hartwick, Olewiler and Preuss, 1986; Wellmer and Scholz, 2017; Wright and Czelusta, 2003). This is derived from productivity improvement, resulting in sustainable profitability due to technological innovation. Unfortunately, there is not an adequately established relationship that links this technological innovation impact to the share price performance of the mineral commodity company.

Sep 1, 2024

By Paweł Stefaniak, Natalia Duda-Mróz, Sergii Anufriiev, Wioletta Koperska

Due to the high environmental risks and negative impact of a failure, tailings storage facilities (TSFs) need constant monitoring. Advanced mathematical models have been developed in the past to predict the behavior of TSFs and raise alerts if needed. To be precise and reliable, such models need a spatial distribution of soil types within the dam as an input. Getting this data from laboratory measurements is time and costconsuming. In this article, we propose an ANN-powered algorithm, which allows us to accurately estimate the soil distribution based on a cone penetration test (CPT).

Jun 25, 2023

By I. Andras

The paper deals with the application of artificial intelligence methods in assessing the effectiveness of longwall shield support. A fuzzy sets based method is used to derive response surfaces/curves representing the dependence between basic parameters of the shield, as the initial setting pressure and the stiffness on the response metric, i.e. the convergence and load increase during a working cycle.

Jan 1, 2008

By Stavros A. Argyropoulos

The strides that have been made in recent years in applying Artificial Intelligence to pyrometallurgy, are reviewed. The computer reproduction of the way in which a human being reasons and calls on past experience and stored knowledge when faced with problem will be extremely helpful in pyrometallurgy. It is expected that Artificial Intelligence will be applied in all areas of human endeavor. Areas of pyrometallurgy that are most promising for expansion into A1 in the near future are presented.

Jan 1, 1990

By B. Denby

Following an introduction to the symposium and its topics, including techniques such as expert systems, neural networks, genetic algorithms and case-based reasoning, the contents list of the 8 selected papers is presented

Apr 1, 1994

By P. K. Chatterjee

Before coal can be extracted from surface or underground mines, approval must be obtained from state and federal authorities. Permitting is the application process through which such approval is sought. The application includes en environmental impact statement Which focuses on Such topics as subsidence, toxicity of acid mine drainage, pollution levels of rivers and streams, post mining reclamation, and the effect on the hydrological balance of the area. The permitting procedure is extremely time and labor intensive, and requires extensive interdisciplinary knowledge. This paper examines a LISP based permitting procedure which will help to reduce the time taken to prepare and review a permit application.

Jan 1, 1986

By Zhang Y. D, Zhang R. X

A new decision-making approach of artificial neural network system with hierarchic structure is presented. The fundamentals of network topology, node functions and network training are introduced. A neural network system with hierarchic struct

Jan 1, 1998

By G. T. Lineberry, B. R. Yama

Artificial intelligence research has produced several tools for commercial application. Some of the techniques that are widely used today include neural networks, fuzzy logic and expert systems. Artificial neural networks (ANNs) are excellent predictive, pattern recognition and data analysis tools. In the mining industry, ANN techniques are being used commercially for real-time process-control applications. Modeling of spatial data, ore-reserve estimation, tunnel design, long wall-stability prediction and geologic roof classification are additional applications in which neural networks have been applied successfully. In this study, a standard back propagation algorithm was used to train a series of neural networks for a real-world predictive task. After training and optimizing the neural network architecture, the performance of the network is measured on an independent validation set. Results indicate a mean error of less than 1 % between the actual and predicted values. A neural network model was developed for learning the spatial continuity of a mineral field and, consequently, for predicting sulfur values for given coordinates. The neural network not only performed satisfactorily, but in some cases performed even better than the kriging model.

Jan 1, 2000

By Babu R. Yama

Artificial Intelligence research has produced several tools for commercial application. Neural Networks, Fuzzy Logic and Expert Systems are some of the techniques that are widely used today. Artificial Neural Networks (ANNs) are excellent predictive, pattern recognition, and data analysis tools. In the mining industry, ANN techniques are being used commercially for real-time process control applications. Modeling of spatial data, ore reserve estimation, tunnel design, longwall stability prediction, and geologic roof classification are additional application areas in which neural networks have been applied successfully. A standard back-propagation algorithm was used to train a series of neural networks for a real-world predictive task. After training and optimizing the neural network architecture, performance of the network is measured on an independent validation set. Results indicate a correlation coefficient of up to 84 % between the actual and predicted values. A neural network model is developed for learning the spatial continuity of a mineral field and, consequently, for predicting sulfur values given coordinate values. The neural network performed not only satisfactorily, but in some cases performed better than the kriging model.

Jan 1, 1997

By D F. Akhmetov, M Yasuike, M Komazaki, Y Kawa

Remote monitoring of geological situation at distant regions with complicated relief, including reliable detection of the rock falls and estimation of the scale of accidents, is of great importance for practical needs. In the paper, vibration data, caused by fall of sample objects and registered by cable sensors, are processed and analysed in order to construct some measure for the indirect evaluation of weight of fallen objects. Nonlinear models, which based on artificial neural networks (ANN), are proposed for the signal presentation. To improve and simplify the learning and classification abilities of the whole system, the aggregative learning method (ALM) is implemented. ALM features relatively low memory and computational resources needed for the procedure realisation, especially for data classification (recall) stage, in compare to conventional methods. The validity and efficiency of the proposed approach are tested through its application for rock fall detection and weight evaluation system using cable sensors and mobile communication network. Classification abilities of the proposed approach are shown useful for estimation of the fallen object weight. Characterised with high computational efficiency and simple decisionmaking procedure, the derived method can be useful for simple and reliable real-time monitoring system design.

Jan 1, 2003

By Sepideh Javanshir

The process of liquid?liquid extraction of gold from chloride solution is complicated by the presence of many variables acting simultaneously in an unknown non-linear fashion for the determination of the final extraction efficiency. In practice, it is quite difficult to develop a model for predicting various properties of such process. Therefore, an alternative approach based on Artificial Neural Network (ANN) is considered to assist in the simulation process. Artificial neural networks (ANN) are powerful tools that can be used to model and investigate various highly complex and non-linear phenomena. This paper presents application of Multi-Layer Perceptions (MLP) to construct relationship that will be employed to develop a quantitative method for the estimation of the extraction efficiency as a function of hydrodynamical parameters such as stirrer speed, [AuCl4]- and DBC concentration, organic and aqueous flow rate. The model is shown to be in excellent agreement with the experimental data (R2 value for training and testing data was 0.9992 and 0.9915 respectively). Therefore, it can be used to optimize the parameters of liquid?liquid gold extraction with dibutyl carbitol (DBC).

Sep 1, 2012

By E P. Leite, L A. Magalhpes

The Amazon Craton is one of the largest cratonic areas and comprises one of the est-endowed metallogenic provinces in the world. It hosts a number of different ore deposit types for which a variety of mineral exploration data are presently available at various scales and formats. These data, however, are not properly organised nor integrated by means of advanced spatial analysis tools. In this view, here we present a suite of neural network methods that were applied to these data, providing unprecedented mineral potential scenarios for several precious and base metals in the region. An EXTENDED ABSTRACT is available for download. A full-length paper was not prepared for this presentation.

Jan 1, 2008

In longwall mining, premining prediction of methane emission rate depends on a number of geological factors, geographical factors, and operational factors. These same factors also can impact the selection of a specific degasification system. This study proposes a principle component analysis (PCA) and artificial neural network (ANN) approach to predict the ventilation methane emission rates of U.S. longwall mines and the optimum combination of degasification boreholes based on the given characteristics of the mine. Artificial neural networks, more than conventional computer models, are adaptable systems that can solve problems such as non-polynomial or very complex relationships that are difficult to describe mathematically. Data on ventilation emissions and degasification system design were obtained from 63 longwall mines in 10 states and were combined with corresponding geological, geographical, and operational parameters for the period 1985-2005. PCA was used to determine the variables that most influence ventilation emissions and degasification system design. Different combinations of variables in the data set and network structures were used for network training, cross-validation, and testing. The resultant ANN models predicted ventilation methane emissions with a 90-95% accuracy and were superior to multi-linear and second order non-linear models. The ANN-based expert classification system was able to classify the design of the degasification system (no degasification, gob vent borehole, horizontal and gob vent borehole, and horizontal, vertical and gob vent borehole) with more than 80% accuracy. The models can be used as prediction and decision tools for the ventilation emissions and degasification system selection for specific site and mine-design conditions.

Jan 1, 2009

By Daniel Hodouin

Artificial neural networks (ANN) are of growing interest in a wide variety of applications. Pattern recognition, speech processing, financial analysis, signal processing and process control are at present the most successful ones. This paper is an attempt to illustrate the potentiality of ANN applied to mineral processing. An introduction to the technology of ANN is first proposed to describe the various components and to explain the various phases encountered in setting up a network. Then examples are given to illustrate the use of ANN dynamic modelling of mineral processing units or plants and in process control.

Jan 1, 1991

By Ben L. Seegmiller

The artificial stabilization of a pit slope at the Twin Buttes Mine near Tucson, Arizona has been completed as part of a practical rock mechanics program. The research program began in June 1971 as a result of the three million ton South Slope slide(1) which caused significant economic and operational problems. Hydrological studies, field and laboratory testing and investigation of various stabilization systems(2)occupied the first year of research. In July 1972 a design for an artificial stabilization test using post-tensioned cable bolts was completed and the selection of an outside contractor was made the following month. The project began in mid-September and was completed during the first week of January 1973. The test site is located adjacent to the South Slope slide in a zone of high potential failure. When the site was initially selected it was thought that it would remain stable at least until the test could be completed. However, heavy rains which fell in late October induced displacement in the half of the test site adjacent to the South Slope slide. Prior to this stabilization test it was thought both impractical as well as improbable that a moving slide could be stabilized with an artificial support system(3). Because the project was nearing the half-way point it was decided that an attempt should be made to complete the test as originally planned. This meant, in effect, that an attempt would be made to stabilize the moving section as well as the stable section.

Jan 1, 1973

By Ben L. Seegmiller

Artificial support of rock slopes in mining applications may consist of rock anchors with and without auxiliary support systems, but- tresses or shotcrete. The use of artificial support systems is not applicable in all cases of slope instability. Some pit slope problems simply cannot be cured with a support system. In other cases, a sup- port system which would solve the problem would be uneconomical. Rock anchor design may be undertaken using an active or tensioned system or a passive or untensioned system. Failure problems to which artificial support systems are most commonly applied include planar, wedge, rotational and toppling failures. Design of auxiliary support systems and rock anchor peripheral items may be initially estimated using analytical concepts, but field trials are commonly used to determine final requirements. Field procedures usually require a close coordination between mining personnel and the support installation team. Great care must be exercised during installation to prevent numerous potential problems including poor anchorage, excess bearing and corrosion. Displacement monitoring of the completed system is a must if the effectiveness is to be closely judged by means other than total slope and/or support system failure. The cost of a support system is relatively high when compared to other remedial measures that may be taken to solve a slope instability problem. Therefore, the system costs play a vital role in determining whether or not artificial support should be considered beyond the initial assessment stage. Case histories are few, but do include examples of each type of support system.

Jan 1, 1983

The South Wall Base Case Design for Mt Whaleback indicated that along portion of the South Wall a cigar shaped synclinal keel, contain- ing 14 800 m', of Dales Gorge Member ore, would be unkeyed and bed- ding undercut. The dry "ore lobe" slope would be 60m high, unbenched and approximately 170 m long. Stability analyses using specific design parameters established that artificial reinforcement could stabilise the slope and be economically justifiable. To implement the slope design reinforcement for such a complex geo- logical structure it was necessary that all functions pertaining to slope excavation be integrated and co-ordinated within the Mine Geotechnical Section. The objective being to minimise slope damage and thereby optimise the effect of design reinforcement. The successful excavation of the ore lobe in 1988, three years after the introduction of artificial reinforcement, was achieved by strictly main- taining the following parameters. 1. Accurate Geological Model 2. Controlled Perimeter Blasting 3. Controlled Excavation Techniques 4. Quality control -Reinforcement Installation 5. Additional Reinforcement.

Jan 1, 1989

It is a well known fact that the best method of rock reinforcement is to avoid physical ground support. This goal can be achieved by means of: - Increasing the rock structural strength - Geological definition and forecasting. - Sequencing the excavation - Smooth blasting In many cases however, extra ground support is needed in order to maintain safe working conditions. In an open pit, the structural strength of rock cannot be increased by lowering the pit walls due to economical reasons. Economy demands steeper walls and less waste to be hauled to the dump. The geological conditions can also often be extremely poor and unpredictable. For excavation sequencing and smooth blasting there are good possi- bilities, such as cleaning of the pit walls after the main excavation, arul- ing of long small diameter straight inclined holes, use of smooth blasting techniques and lightened explosives.

Jan 1, 1989