The mining industry is a major industry worldwide, producing everything from coal to gold. According to PWC annual report, as of April 2017, the market value of the top 40 mining companies was $748 billion. The entire industry experienced a recession in 2015, but since then, the industry has recovered due to rising commodity prices.
Since mining companies produce substantially interchangeable commodities in large quantities, the industry is highly focused on improving efficiency at all levels. Small improvements in speed, yield, and efficiency can often distinguish a profitable business from an unprofitable business. This is what companies using artificial intelligence and machine learning do in this field.
This article will explore how the mining industry uses or attempts to use artificial intelligence to increase productivity and efficiency throughout the process. We will cover:
· AI Mineral Exploration
· Self-Driving Haulers
· Prognostics and Health Management (PHM) System
· AI for Sorting
The mining industry is a large and diverse industry. Depending on the materials being mined, the technologies and techniques used are also very different, so it is difficult to make a comprehensive statement covering the entire industry. That said, this article will study how artificial intelligence is used to find ground mining, and how artificial intelligence is used to improve mining operations.
The first step is to find a place to mine. This mineral exploration step is crucial to mining operations. A company can build the most active automation and impressive efficient operation. Unless there are good materials available underground, it will be worthless. The application of artificial intelligence and machine learning to mineral exploration and exploration tasks is a very new phenomenon, which is attracting the interest of the industry.
The company Goldspot Discoveries Inc. uses AI to try to improve mineral exploration. The company claims that the current practice of trying to find gold deposits is more of an art than a science, and they plan to change that with machine learning .
They claim in their test they were able to predict 86% of the existing gold deposits in the Abitibi gold belt region of Canada using data such as geological, topography, and mineralogy from just 4 percent of total surface area. The first major publicly announced test of their system will be happening in the near future at the Jerritt Canyon mine.
Last month the Jerritt Canyon project announced they used Goldspot Discoveries Inc’s AI to analysis all geological data they have about the currently un-mined parts of their claim and information about where they have previously found gold in the region to identify target zones that might contain gold. The gold producer plans to perform preliminary drill testing as soon as is logistically possible.
The most direct use of artificial intelligence in the mining industry is to improve efficiency. Mines are usually large industrial operations. Many of them are using the basic advancements in robots and smart sensors that we have seen in factories to improve their performance in mining.
The mining industry was an ideal place for early commercial use of autonomous vehicles. Mining equipment and trucks travel relatively slowly. They also operate in well-defined and highly controlled areas.
The mining company Beijing Tage Zhixing Technology Co., Ltd. is a high-tech enterprise focusing on the research of unmanned driving technology for mining vehicles. The company launched a vehicle-ground-cloud collaborative smart mine unmanned transportation system, which realized a full-stack unmanned transportation solution consisting of cloud intelligent dispatch management, 4G/5G car networking communication, intelligent roadside units and vehicle-mounted intelligent terminals plan.
The solution has strong universality, which can be adapted to two categories of mining trucks: large mining dump truck and wide body dump truck. It is compatible with multiple brands and models. At the same time, it supports the production adaptation of new driverless models and the unmanned upgrading of in use vehicles.
Inexpensive connected sensors allow the company to continuously monitor almost all aspects of the equipment. Using artificial intelligence programs to analyze all this data can also improve maintenance, reduce downtime, and help predict problems before they occur.
Companies such as Alpha Intelligence offer these services to mining companies. As a leading SAAS service provider of PHM in the global resource industry and energy field, Alpha has laid more than 40,000 sensors in different factories around the world, and the machine learning time is more than 400 million hours / year.
It has established long-term cooperative relations with well-known customers Vale of Brazil, Lafarge Holcim and Testech of the Philippines, and stopped losses of more than 100 million yuan for customers.
Since Alpha's PHM system was installed in the factory, it has successfully predicted the hidden dangers of equipment operation for many times, which not only ensures the production efficiency of the factory, but also provides technical guarantee for the safe operation of the factory. In the mining industry, any overload event will effectively prevent the operation of the mine, and any shutdown is a major economic loss.
Mines tend to remove large amounts of material out of the ground, even if the minerals they pursue only account for a small percentage of their removal. In the mining process, separating the material they want from the worthless soil, rock and clay can be a very expensive step.
In addition, the earlier the sorting process, the less fuel and money the company wastes to transport useless materials. Machine learning has not been used to improve this process in the mining sector until recently.
HOT Mining is a China-based provider of mining, mineral processing plant, coal washing plant and ore mineral process equipment, and a one-stop solution for mining, ore mineral processing, coal washing and minerals handlings.
HOT Mining has developed an intelligent sorting equipment for mining based on machine learning and X-ray diffraction topography (XRT). In September 2021, the first XRT Intelligent Sensor-based Ore Sorter was successfully launched. It is an interdisciplinary innovative technology, which enables green selection and helps realize energy conservation and emission reduction in mines.
Fig. Schematic diagram of XRT intelligent photoelectric separation
They claim that use of their sorting equipment resulted in 12 percent less mass needing to be moved, and the recognition accuracy of their algorithm is more than 99.9%. This means less fuel, less energy during processing, and fewer truckloads.