Making Mining Better and Faster

IMARC opens in Melbourne at the end of October, and Artificial Intelligence and the Internet of Things will be key to the discussions at this important annual mining conference.

Like Comment

The International Mining and Resources Conference (IMARC) opens in Melbourne in under three weeks (October 29-31) and Artificial Intelligence (AI, see recent blog) and the Internet of Things (IoT) will be an important part of the discussions.

New sensor and data technologies are helping big and small miners alike make better and faster decisions, and the potential impact of these technologies is huge. Indeed, the Commonwealth Scientific and Industrial Research Organisation (CSIRO) has estimated that IoT's impact on the mining, oil and gas industries will be worth US$160-930 billion by 2025.

There are challenges, however, in rolling out AI and IoT. The trend of digital convergence that drives the application of these technological solutions is not just about the science. It involves a coming together of tribes from the very different worlds of information and operational technology.

Some of these issues were highlighted at last year's IMARC event by Gavin Wood (chief information officer at Newcrest) and by Ashley Bosworth, who is a director at Pulse Mining Systems (a software developer specialising in developing technology for the mining industry). Gavin will be taking part again this year in a panel on digital strategy and on how companies are changing the way that they operate to implement and embrace the new technology.

Ashley told IMARC delegates last year that recent technological developments enable data to be "rapidly integrated and analysed to present one single version of the truth as an easy-to-read visualisation that's continually updated". He added that "there are no delays waiting for human interactions, nor any opportunity for human error or misinterpretation".

According to Pulse, the promise of IoT is fulfilled by people at all levels possessing business information that is timely, accurate and meaningful. Managers need to drill down instantly to the transactional details for immediate corrective actions. The empowerment of human decision-making by IoT will produce "quantum improvements in productivity, profitability and organisational culture".

From the corporate perspective, Gavin advised conference attendees that "digital technologies present an excellent opportunity to increase productivity without necessarily needing to invest in capital-intensive mine or plant expansion". He added that Newcrest believes (and has demonstrated) that "IoT and digital technologies can significantly improve plant and mobile fleet availabilities, throughput, and recoveries, which in turn will lead to more gold production and more free cash flow, delivered at a fraction of the cost of mine or plant expansion". 

Newcrest has concluded, Gavin told delegates, that "having all the players on the same page, and working together well, in the industrial IoT space at a mining company is critical to success". Indeed, "integrating the IT and operational teams is a key step to being ready to deliver secure and scalable IoT solutions, with integration at the both organisational and the process levels".

Looking into the not too distant future, Gavin theorises that all of Newcrest's mining and processing activities will be automated, hosted in public cloud offerings and delivered to the company's remote sites using IoT technologies. The company already has in place world-leading Big Data and Data Science platforms to support this mine of the future, and is in the process of building out an IoT platform to fully support the ongoing delivery of data science/AI to its sites regardless of whether the communications to the site are working or not at a point in time.

IoT Theory

IoT incorporates, in its broadest sense, any object (not people) that is connected to the internet. However, the term is increasingly used to define only those objects — from simple sensors through smart phones to fully-automated equipment — that actually communicate with each other.

In this latter definition, IoT is about the networks, the connected devices themselves and the data that flows between them. By combining these connected devices it is possible to gather information, analyse the data and then undertake a particular task — and also to learn from the process. The traditional fields of embedded systems, wireless sensor networks, control systems and automation all contribute to enabling the IoT.

The networking of smart devices has been discussed since the 1970s, and the actual term, the 'Internet of Things', was coined by Kevin Ashton of Procter & Gamble in 1999.

Cisco Systems estimates that the IoT can be considered to have been 'born' in 2008, which is the date when there were more objects than people were connected to the internet. Since then there has been an explosive growth in internet-connected devices, and there are now perhaps twice as many objects than people connected to the internet. Indeed, the number of IoT devices increased 31% year-over-year to 8.4 billion in 2017, and is expected to reach 30 billion devices by 2020, with a global market value of over US$7.0 trillion.

IoT can be considered to be a subset of the Internet of Everything (IoE), which includes people, and the functions have five levels; smart connections, data conversion, simple modelling, simulation and configuration. The connected devices themselves can be considered to be made up of four levels; physical elements (mechanical and electrical parts), smart elements (eg sensors, processors and software), connectivity elements (eg ports and antenna) and, where applicable, AI capabilities.

The real value of these connected devices comes when they are able to learn from each other, and instruct automatic actions. Behaviour can then be changed over time, and decisions made in response to incoming data. This is where machine learning (a subset of AI) is important in identifying patterns and anomalies in data without being explicitly programmed where to look. AI devices can separate signal from noise, and so are able to learn from their interaction, making AI an essential component of IoT for industry.

Benefits to Mining

There are three main areas of benefit for mining companies that embrace IoT.

1. Raising Productivity

Data collected from exploration, production, transportation and processing can make operations more efficient, and increasingly to function automatically. Also, machines, unlike humans, can work around the clock.

2. Improving Health and Safety

IoT, and AI specifically, is increasingly able to remove miners from harm's way by automating the mining and transport processes. IoT is also able to help predict equipment failures, roof collapse, unstable shafts etc.

3. Reducing Costs

Having a fully-integrated network makes monitoring far easier, and enables the early detection of equipment wear and tear. In addition to reducing maintenance costs, IoT will also lower the expenditure on energy.

IoT devices in mines are currently focused on the use of sensors and mobile telemetry to gather data that allows companies continuously to monitor operations and improve overall efficiency. For example, many open-pit controllers and drilling/blasting teams are supported through IoT solutions. Visualisation tools can provide 3D displays of mines, and it is already crucial for mining vehicles to have built-in sensors that measure oil temperature, tyre and brake pressures, vibration, engine revolutions etc. 

IoT will be increasingly important in mining as a means of reducing costs, improving productivity, and in increasing the health and safety of miners. IoT in mining certainly works well for improving safety and optimising maintenance. IoT-based sensors can deliver real-time data that contribute to identifying the equipment that may cause danger, and predictive maintenance reduces the frequency of sudden cash outflows.

Chris Hinde

Chief Commentator, Mining Beacon

Previously editorial director of Mining Journal, and more recently head of S&P Global Market Intelligence's metals and mining team, Chris is now Mining Beacon's editor-in-chief and lead commentator. He posts two blogs every week, one on Monday reviewing market conditions over the prior week, and a second on Thursday looking at issues on the global mining scene. There is also a quarterly blog on business opportunities in the sector.