Automation and Artificial Intelligence Technology in Surface Mining: A Brief Introduction to Open-Pit Operations in the Pilbara [Survey

Truck haulage is responsible for a majority of cost in a surface mining operation. Diesel fuel, which is costly and has a significant environmental footprint, is used as a source of energy for haul trucks in surface mines. Reducing diesel fuel consumption would lead to a reduction in haulage cost and greenhouse gas emissions. The determination of fuel consumption is complex and requires multiple parameters including the mine, fleet, truck, fuel, climate and road conditions as input. Data analytics is used to simulate the complex relationships between the input parameters affecting the truck fuel consumption. This technique is also used to optimise the input parameters to minimise the fuel consumption without losing productivity or further capital expenditure for a specific surface mining operation. The aim of this research thesis is to develop an advanced data analytics model to improve the energy efficiency of haul trucks in surface mines. The most important controllable parameters affecting fuel consumption are first identified, namely payload, truck speed and total resistance. These parameters are selected based on the results of an online survey. A comprehensive analytical framework is developed to determine the opportunities for minimising the truck fuel consumption. The first stage of the analytical framework includes the development of an artificial neural network model to determine the relationship between truck fuel consumption and payload, truck speed and total resistance. This model is trained and tested using real data collected from some large surface mines in USA and Australia. A fitness function for the haul truck fuel consumption is successfully generated. This fitness function is then used in the second stage of the analytical framework to develop a computerised learning algorithm based on a novel multi-objective genetic algorithm. The aim of this algorithm is to estimate the optimum values of the three effective parameters to reduce the diesel fuel consumption. The following studies are also conducted to enhance the analysis of haul truck fuel consumption. First, a comprehensive investigation of loading variance influence on fuel consumption and gas emissions in mine haulage operation is carried out. Then, a discrete-event model to simulate the effect of payload variance on truck bunching, cycle time and hauled mine materials is developed. The influence of rolling resistance on haul truck fuel consumption in surface mines is investigated.

Haul trucks are used for material handling in most surface mines and consume about 32% of the total energy usage in mines that use them. This chapter deals with benchmarking approaches applicable to haul truck operation in mines. The specific fuel consumption (SFC) is used as the energy performance index for benchmarking energy consumption of haul trucks. Benchmarking using a statistical approach estimates the minimum SFC based on the comparison of past aggregate time series data and disaggregate data on fuel consumption and the production rate of haul trucks. A model-based approach calculates the minimum SFC using a mathematical model derived from vehicle dynamics, mass balance, and engine and mine characteristics. This chapter presents an analysis of two case studies of haul trucks operations at different surface mines (coal and limestone) to illustrate the benchmarking methods. The studies revealed that benchmarking of energy consumption in haul trucks using the model-based approach is appropriate for setting the fuel consumption target in an opencast mine and assess the fuel saving potential. The model-based approach results in minimum SFC of 89 g/t and fuel saving potential of 17% for multiple haul trucks operating in a limestone mine. The model-based approach shows a direction for setting rational targets for fuel consumption in haul trucks and result in more energy efficient mines.

The mining industry is undergoing a transformative shift driven by the rapid advancement and adoption of automation technologies. This paper provides a comprehensive overview of the current state of automation in mining, examining the technological advancements, their applications, and the prospects of automation in this critical industry. A key focus of this paper is the impact of automation on the safety and efficiency of mining operations. Highlighting the successful implementation of Automated Haul Truck Systems (AHSs) in surface mining. Additionally, this paper explores the development of automation in underground mining and its challenges, particularly limitations in communication and localization, which hinder the development and deployment of fully autonomous systems. It also provides an exploration of the challenges associated with widespread automation adoption in mining, including high initial investment costs, concerns about job displacement, and the need for specialized skills and training. Looking toward future advancements in enabling technologies will be critical for furthering automation in mining. Machine learning and AI will play an increasingly critical role in intelligent automation, enabling autonomous systems to adapt to dynamic environments, optimize processes, and make informed decisions. This paper provides a look into human–robot collaboration in the future of mining. As the industry transitions toward greater automation, it is essential to consider the evolving roles of human workers to foster a collaborative work environment. This involves prioritizing human safety, providing adequate training, and addressing concerns about job displacement to ensure a smooth transition toward a more automated future.

This chapter aims to provide an overview of energy efficiency in the mining industry with a particular focus on the role of fuel consumption in hauling operations in mining. Moreover, as the most costly aspect of surface mining with a significant environmental impact, diesel consumption will be investigated in this chapter. This research seeks to develop an advanced data analytics model to estimate the energy efficiency of haul trucks used in surface mines, with the ultimate goal of lowering operating costs. Predicting truck fuel consumption can be accomplished by first identifying the significant factors affecting fuel consumption: total resistance, truck payload, and truck speed. Second, developing a comprehensive analysis framework. This framework involves generating a fitness function from a model of the relationship between fuel consumption and its affecting factors. Third, the model is trained and tested using actual data from large surface mines in Australia, obtained through field research. Finally, an artificial neural network is selected to predict haul truck fuel consumption. The visualized results also clarify the general minimum areas in the plotted fuel consumption graphs. These areas potentially open a new window for researchers to develop optimization models to minimize haul truck fuel consumption in surface mines.

In terms of method of extracting mineral from deposit, mining can be classified into: surface, underground, and borehole mining. Surface mining is a form of mining, in which the soil and the rock covering the mineral deposits are removed. Types of surface mining include mainly strip and open-cast methods, as well as quarrying. Tasks associated with surface mining of minerals include: resource estimation and deposit documentation, mine planning and deposit access, mine plant development, extraction of minerals from deposits, mineral and waste processing, reclamation and reclamation of former mining grounds. At each stage of mining, geodata describing changes occurring in space during the entire life cycle of surface mining project should be taken into consideration, i.e. collected, analysed, processed, examined, distributed. These data result from direct (e.g. geodetic) and indirect (i.e. remote or relative) measurements and observations including airborne and satellite methods, geotechnical, geological and hydrogeological data, and data from other types of sensors, e.g. located on mining equipment and infrastructure, mine plans and maps. Management of such vast sources and sets of geodata, as well as information resulting from processing, integrated analysis and examining such data can be facilitated with geomatic solutions. Geomatics is a discipline of gathering, processing, interpreting, storing and delivering spatially referenced information. Thus, geomatics integrates methods and technologies used for collecting, management, processing, visualizing and distributing spatial data. In other words, its meaning covers practically every method and tool from spatial data acquisition to distribution. In this work examples of application of geomatic solutions in surface mining on representative case studies in various stages of mine operation have been presented. These applications include: prospecting and documenting mineral deposits, assessment of land accessibility for a potentiallarge-scale surface mining project, modelling mineral deposit (granite) management, concept of a system for management of conveyor belt network technical condition, project of a geoinformation system of former mining terrains and objects, and monitoring and control of impact of surface mining on mine surroundings with satellite radar interferometry.

Purpose This paper aims to construct a systematic theoretical analysis framework from the perspective of knowledge management capabilities, and to explore the empowering effect and the underlying theoretical mechanisms of artificial intelligence (AI) technology application on enterprise technological innovation, thereby providing theoretical references and empirical evidence for policymaking and management practices. Design/methodology/approach This paper selects the operation data and technical invention patent data of Chinese listed companies from 2012 to 2023 to deeply explore the empowering effect of AI on enterprise technological innovation. This paper uses a fixed-effects model to perform regression analysis on the samples, and conducts systematic robustness tests, heterogeneity analysis and extensibility analysis. Findings This study finds that the application of AI technology can systematically enhance enterprises’ knowledge management capabilities (including knowledge acquisition, integration, application and transformation), thereby empowering technological innovation. This conclusion remains robust after a series of robustness checks. Moreover, compared with logical AI technologies, learning AI technologies exhibit a more pronounced empowering effect on enterprise’s technological innovation. The heterogeneity analysis reveals that the empowering effect of AI technology on technological innovation is stronger in enterprises with low financing constraints, high human capital and technology-intensive characteristics. The extended analysis further shows that AI technology application significantly promotes both incremental and radical technological innovations, though its impact on the latter demonstrates a notable lagged effect. Originality/value Based on the theory of knowledge management, this paper constructs a systematic theoretical analysis framework and explores the internal theoretical mechanism of AI empowering enterprise technological innovation from the perspective of knowledge management capabilities. Meanwhile, this paper innovatively uses machine learning methods to conduct text analysis on the annual reports of listed companies, and simultaneously uses the index of AI technology investment to directly quantify and measure the level of AI application of enterprises, and conduct classified research on it (logical AI and learning AI). In addition, this paper deeply explores the differentiated impact of AI on incremental technological innovation and breakthrough technological innovation.

As the near surface deposits are being mined out, underground mines will increasingly operate at greater depths. This will increase the challenges related to transporting materials from deeper levels to the surface. For many years, the ore and waste transportation from most deep underground mines has depended on some or all of the following: truck haulage, conveyor belts, shafts, rails, and ore pass systems. In sub-level caving, and where ore passes are used, trains operating on the main lower level transport the ore from ore passes to a crusher, for subsequent hoisting to the surface through the shaft system. In many mines, the use of the ore pass system has led to several problems related to the ore pass availability, causing production disturbances and incurred cost and time for ore pass rehabilitation. These production disturbances have an impact on the mining activities since they increase the operational costs, and lower the mine throughput. A continued dependency on rock mass transportation using ore passes will generate high capital costs for various supporting structures such as rail tracks, shaft extensions, and crushers for every new main level. This study was conducted at an existing underground mine and analyzed the transport of ore from loading areas at the lower levels up to the existing shaft points using trucks without employing ore passes. The results show that, when the costs of extending ore passes to lower levels become too great or ore passes cannot be used for production, haul trucks can be a feasible alternative method for transport of ore and waste up the ramp to the existing crusher located at the previous main level. The use of trucks will avoid installing infrastructure at the next main level and extending the ore passes to lower levels, hence reducing costs.

Determination of ultimate pit limit, and sequence of blocks extraction through the mine life is referred as mine design and planning. The aim of mine design and planning is to develop a yearly extraction plan which guides the mining operation to the highest Net Present Value (NPV). Future mines are going to be giant mines that exploit low grade material. Protecting the environment and its reclamation is one of the main issues in future mining activities. These issues highlight the importance of mine planning in the texture of future mines. Mine plans are classified as long term, medium term, and short term plans. These plans consider all the technical constraints of the specific mining operation. The preciseness of date and the required constraint differ in long term and short term plans, which cause the deviation of plans from the predetermined objectives. This paper provides a list of factors and their importance on mine plans. This way, those factors that affect the interactions of long term and short term mine plans are also determined.

Long term exposure to high amplitude whole-body vibration is known to be a cause of back pain. Operators of equipment such as surface mining haul trucks are exposed to whole-body vibration. Although a range of control measures have been recommended, there is little evidence that these control measures are consistently implemented by mine sites. The research presented in this thesis provides information and technology which will assist the surface mining industry to manage exposure of their operators to whole-body vibration. Two research questions are addressed: (i) What are the whole-body vibration exposures to operators of haul trucks at surface coal mines and how do these exposures vary with different road surface conditions, haul truck activity and truck types? and (ii) How accurate are the accelerometer measurements obtained via an iPod Touch for estimating whole-body vibration exposure? Whole-body vibration measurements were gathered from 34 haul trucks operating under normal conditions at a surface coal mine using commercially available, “gold standard” measurement devices. The health effects were determined in accordance with the methods and Health Guidance Caution Zone criteria provided by ISO 2631-1. Twenty-eight haul truck drivers were exposed to whole-body vibration levels within the Health Guidance Caution Zone and five drivers were exposed to levels above the Health Guidance Caution Zone. Whilst haul truck type did not significantly affect whole-body vibration exposure to operators, the road condition and haul truck activity were associated with whole-body vibration amplitudes. Whilst accurate vibration measurement devices are commercially available, the cost and complexity of the devices is a barrier to the systematic and regular collection of whole-body vibration data by mine sites. Consumer electronic devices have potential to be used to estimate whole-body vibration. Forty-two pairs of measurements were collected simultaneously from a gold standard accelerometer and a 5th generation iPod touch whilst driving light vehicles on different roadway surfaces. A further fifty-eight pairs of measurements were collected simultaneously from a gold standard accelerometer and a 5th generation iPod touch whilst a range of heavy surface mining equipment was operated at three coal mines. The results suggest that accelerometer data gathered from an iPod Touch are able to be used to measure whole-body vibration amplitude with 95% confidence of +/- 0.09 m/s2 r.m.s. or better, depending on the direction of interest. Errors were lower in the vertical direction (usually the dominant vibration direction) and the limits of agreement were calculated to be +/- 0.063 m/s2 r.m.s. Whole-body vibration exposure is a hazard to operators of haul trucks and should be systematically managed by mine sites. The cost and complexity of commercially available measurement devices is a barrier to regular collection of whole-body vibration exposure. Such ad hoc measurements are unlikely to provide a reliable indication of the vibration exposures of equipment operators and do not provide the information required to effectively manage whole-body vibration exposures. The development of an iOS application that allows an iPod touch to measure whole-body vibration exposure using the frequency weightings specified by ISO 2631-1 provides a simple and inexpensive whole-body vibration measurement device. This device can enable the collection of the information by mine sites required to manage exposure to this hazard.

This chapter demonstrates the practical application of artificial intelligence (AI) to improve energy efficiency in surface mines. The suggested AI approach has been applied in two different mine sites in Australia and Iran, and the achieved results have been promising. Mobile equipment in mine sites consumes a massive amount of energy, and the main part of this energy is provided by diesel. The critical diesel consumers in surface mines are haul trucks, the huge machines that move mine materials in the mine sites. There are many effective parameters on haul trucks’ fuel consumption. AI models can help mine managers to predict and minimize haul truck energy consumption and consequently reduce the greenhouse gas emission generated by these trucks. This chapter presents a practical and validated AI approach to optimize three key parameters, including truck speed and payload and the total haul road resistance to minimize haul truck fuel consumption in surface mines. The results of the developed AI model for two mine sites have been presented in this chapter. The model increased the energy efficiency of mostly used trucks in surface mining, Caterpillar 793D and Komatsu HD785. The results show the trucks’ fuel consumption reduction between 9 and 12%.

Haul truck transportation is one of the most important transportation methods in large surface mining operations. It is a key factor that affects the mining productivity and cost effective, however, its accidents rate and dangers are far higher than other types of developing transportation in the surface mining accidents. For the environmental characteristics of surface mining roads and the weather factors, this paper eliminates the open-pit haul truck security risks during haul trucks transportation by the installation of the haul trucks CCD camera equipment. This paper proposes haul trucks transportation environment detection video display enhancement technologies based on the physical models of atmospheric degradation, recovery algorithm to improve the haul trucks drivers' visual distance under the rain, snow, fog dust, etc. lower visibility severe weather conditions in surface mining operations. The results indicate that this technology can increase reliability and reduce uncertainty in surface mining operations.

Mining Robotics and Media Change

The impact of AI technology adoption on operational decision-making in competitive heterogeneous ports☆

Transport and tramming operations on South African mines are an area of considerable accident risk. In the context of surface mining, 74 percent of such accidents were associated with ore transfer by haul truck and service vehicle operations. However, the extent to which haul road design and operation activities impact on the overall safety of transport operations in mining was previously unclear, as was the status of road design activities for the various types of mining encountered This paper presents some findings from die Safety in Mines Research Advisory Committee research project OTH308 which examined the role of haul road design in transportation accidents. The objective of research was to determine whether a relationship existed between haul road design, construction and maintenance practices and accidents. In the case of surface mines, the objective was addressed through an assessment of transportation accidents and incidents, together with an evaluation of formal haul road design activities and associated safety critical defects and accident potentials for the various classes of surface mines studied It was concluded that whilst the overall contribution to transportation accidents derived from inadequate road design alone was small, low tonnage surface mining operations exhibited higher accident frequency rates than the industry average. Furthermore, there was clear evidence to suggest that there was no formal recognition of road design and management in transportation management, especially in the case of smaller surface mining and quarrying operations. To improve awareness of the role of good design in reducing transportation accidents, a mine haul road safety audit system was developed. A mine haul road safety audit system is described and recommended as a means to attaining a reduction in transportation accidents through the structured recognition and assessment of haulage hazards and the application of optimally safe designs for mine haul roads.

Spearheading the promotion of international technology transfer in the fields of mine planning, mining systems design, equipment selection and operation techniques, the International Symposium on Mine Planning and Equipment Selection is recognised by the mining society as a key annual event in highlighting developments within the field. Here in this volume, proceedings from the thirteenth annual symposium concentrate on the following major topics:* open pit and underground mine planning, modelling and design* geomechanics * mining and processing methods* design, monitoring and maintenance of mine equipment* simulation, optimalization and control of technological processes* management, mine economics and financial analysis* health, safety and environmental protection.Including 147 papers from leading experts and authorities, Mine Planning and Equipment Selection undoubtedly provides valuable information and insight for a range of engineers, scientists, researchers and consultants involved in the planning, design and operation of underground and surface mines.