**Abstract**

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%.

**Keywords:** artificial intelligence, energy efficiency, fuel consumption, haul trucks, prediction, optimization, mining engineering

## **1. Introduction**

Climate change, energy security, water scarcity, land degradation, and dwindling biodiversity put pressure on communities, requiring more excellent environmental knowledge and resource-conscious economic practices. As a response to these genuine difficulties, both mining and industrial activities have adopted environmental plans.

The global accord, which 125 countries have signed, aims to reduce global glasshouse gas (GHG) emissions by 80% by 2050 to achieve a low-carbon society. Thus far, the agreement has significantly impacted energy-related laws, such as carbon taxes and energy pricing.

However, following the Paris agreement, the energy costs in the mining industry have risen substantially in respect of overall operating costs. Six years ago, energy accounted for 10% of mining companies' operational costs; now, it is pushing close to 20%. This increases the cost base of companies significantly.

Mining is critical to our national security, economy, and the lives of individual citizens. Millions of tons of resources should be mined each year for each individual to maintain his or her quality of living [1]. In addition, the mining sector is a critical component of the world economy, supplying crucial raw materials such as coal, metals, minerals, sand, and gravel to manufacturers, utilities, and other enterprises [2]. To put it another way, mining will continue to be an essential part of the global economy for many years.

Mining necessitates much energy. Mining, for example, is one of the few nonmanufacturing industrial sectors recognized as energy-intensive by the U.S. Department of Energy [3]. It is also widely acknowledged that the mining industry could enhance its energy efficiency dramatically. Using the United States as an example, the U.S. Department of Energy (DOE) estimates that the U.S. mining sector consumes around 1315 PJ per year and that this annual energy consumption might be reduced to 610 PJ or about 46% of current annual energy usage [3]. According to the most recent data, energy consumption in Australia's mining sector was at 730 petajoules (P.J.) in 2019–2020, up 9% from the previous year [4]. This is slightly greater than the average rate of increase in energy use during the last decade. Mining consumes 175 PJ of energy per year in South Africa and is the largest consumer of electricity at 110.9 PJ per year, according to 2003 figures. The association between rising interest in energy efficiency and energy prices demonstrates increasing energy intensity on mining operating expenses [5, 6]. Given recent governmental moves by various governments to make industry pay for the expenses associated with carbon emissions, such high energy-intensive processes are not sustainable or cost-effective (carbon taxes and similar regulatory costs). As a result, all stakeholders have a vested interest in improving mine energy efficiency.

Since the rise in fuel prices in the 1970s, the importance of reducing energy usage has gradually grown. In addition, because the mining industry's primary energy sources are petroleum products such as electricity, coal, and natural gas, increasing margins through efficiency savings can also save millions of tons of gas emissions.

Mining companies are looking into reducing energy consumption and emissions to cut costs and emissions, especially considering any possible carbon emissions strategy. First, however, businesses must have a comprehensive understanding of their current energy usage, which involves using technology that allows employees to make decisions.

Mining businesses actively review their investment, capital expenditure, and operational plans to ensure that their operations are sustainable and ecologically beneficial. Sustainable practices and capital equipment investments must result in measurable cost savings. Mining businesses are looking to increase their energy efficiency to cut costs and lessen their environmental effect.

Sustainable investments were not thought to produce significant returns on investment in earlier years, but they are becoming more appealing with the quickly changing legislative and economic climate. When all the advantages of new technology and business practices are considered, including direct savings from increased efficiency as well as associated incentives such as carbon tax credits, investments become much more appealing. Furthermore, when considered over a longer time horizon, these same investments in energy savings, for example, become incredibly beneficial.

Data analytics represents a very appropriate approach to pulling together disparate data sources since it is the science of examining raw data to conclude that information. In addition, cost savings, faster and better decision making, and finally, new goods and services are some of the key benefits of data analytics [7].

*Improve Energy Efficiency in Surface Mines Using Artificial Intelligence DOI: http://dx.doi.org/10.5772/intechopen.101493*

Data analytics represents a very appropriate approach to pulling together these disparate data sources since it is the science of examining raw data to conclude that information. Cost savings, faster and better decision making, and finally, new goods and services are some of the most significant advantages of data analytics [7]. Data analytics is widely used and can be used in areas many might not have thought about before. One area that sees much potential in data analytics is the mining industry. Data analytics should be considered a necessity, not a luxury, for an industry that does trillions of dollars in business every year.

One of the advanced data analytic techniques discussed in this chapter aims to enhance the crucial issue of mining energy efficiency. The focus will be on open-pit mine haulage activities. This study aims to create a sophisticated data analytics model for assessing the complex connections that affect haul truck energy efficiency in surface mining. The application of Artificial Neural Networks for predictive simulation and Genetic Algorithms (GAs) for optimization in the investigation of energy efficiency is the focus of this study.

## **2. Mining energy efficiency—Using artificial intelligence**

Global resource firms are currently struggling in challenging economic and regulatory environments. However, most companies in the mining business are now disclosing their performance in this area in response to growing social concern about the industry's numerous consequences and the birth of the idea of sustainable development. Many firm sustainability reports include total energy consumption and associated glasshouse gas (GHG) emissions in absolute and relative terms, indicating that energy consumption and its impact on climate change are priorities.

Mining companies are setting goals to improve these metrics, but there is also a global trend towards more complicated and lower-grade orebodies, which require more energy to process. As a result, mining businesses must be more innovative to improve their environmental sustainability and efficiency operations. In addition, companies must consider the specific energy usage of their processes to limit glasshouse gas emissions.

According to Australian government research, the most significant energy use industries in 2013–2014 were transportation, metal manufacturing, oil and gas, and mining. Transportation consumes a quarter of Australia's annual energy. The manufacturing of metal products such as aluminum, steel, nickel, lead, iron, zinc, copper, silver, and gold accounted for over 16% of total energy consumption. The mining industry consumes 10% of all energy used by participants. **Figure 1** shows the other industries that used the most energy in 2019–2020.

Grinding (40%) and materials handling by diesel equipment are the most energy-intensive equipment types in the mining industry (17%) [8].

According to the Australian Energy Statistics, Australian energy consumption has increased by an average of 0.6% a year for the past decade and reached 6171 PJ in 2019–2020.

Energy efficiency can significantly cut energy demand while also assisting in reducing GHG emissions at a low cost to industry and the larger economy. Therefore, it makes commercial and environmental sense to be aware of opportunities to maximize energy efficiency. The glasshouse gas emissions produced by mining companies were calculated using various fuels, including electricity, natural gas, and diesel. The mining companies' energy savings translated to a possible reduction in glasshouse gas emissions.

Data analytics is the science of examining raw data to discover useful information, reach conclusions about the meaning of the data, and support decision-making. The

**Figure 1.**

*Top energy users by industry sector 2019–2020 (Total 6069 PJ) [8].*

foremost opportunity that data analytics presents for mining is its potential to identify, understand, and then guide the correction of complex root causes of high costs, poor process performance, and adverse maintenance practices. Therefore, data analytics can reduce costs and accelerate better decision-making, which ultimately enables new products and services to be developed and delivered, creating added value for all [7].

**Figure 2** illustrates the two dimensions of maturity: a time dimension (over which capability and insights are developed) and a competitive advantage dimension (the value of insights generated). At the lowest levels, analytics are routinely used to produce reports and alerts. These use simple, retrospective processing and reporting tools, such as pie graphs, top-ten histograms, and trend plots. They typically answer the fundamental question: 'what happened and why?' Increasingly, sophisticated analytical tools, capable of working at or near real-time and providing rapid insights for process improvement, can show the user "what just happened" and assist them in understanding "why" as well as the following best action to take. Towards the top end of the comparative advantage scale are predictive models and ultimately optimization tools, with the capability to evaluate 'what will happen and the ability to identify the best available responses—'what is the best that could happen?'

The mining sector and governments have been pushed to perform research on energy consumption reduction due to the potential for energy (and financial) savings. As a result, a significant number of research studies and industrial projects have been conducted worldwide to achieve this in mining operations [8]. As a result, the mining industry might save roughly 37% of its current energy use by fully implementing state-of-the-art technology and installing new technology through research and development expenditure [9]. Furthermore, energy usage is

*Improve Energy Efficiency in Surface Mines Using Artificial Intelligence DOI: http://dx.doi.org/10.5772/intechopen.101493*

**Figure 2.** *Data analytics maturity levels [7].*

significantly reduced when mining technologies and energy management systems improve. To put it another way, there are substantial further chances to minimize energy use in the mining business.

The four main phases of the mining process that data analytics can use are (1) extraction of ore, (2) materials handling, (3) ore comminution and separation, and (4) mineral processing. The focus of many companies is efficiency improvements in the materials handling phase. For example, the hauling activity at an open-pit mine consumes a significant amount of energy and can be more energy-efficient [10]. The case study presented here- haulage equipment- is one of these potential areas for improving the mining energy efficiency as well as reducing greenhouse gas emissions.
