It is essentially a digital replica of your plant; a computer-generated dynamic simulation that allows you to see what is happening in greater detail. It is also something that can be used to test out theories, or to develop a deeper understanding of performance relationships. To create the digital twin that’s at the centre of our software, we use over 20,000 measure points – as well as machine learning and artificial intelligence – to provide extremely detailed and accurate insights. You can then monitor and review all of this information via a single, easy to use interface.
Resources companies around the world are in the process of minimising their greenhouse gas emissions over the next 10 – 30 years, with the goal of reaching net-zero emissions by 2050. However, achieving these targets is impossible without a robust digital solution which enables you to accurately measure, report and manage your emissions. MI Core®, the foundation of the Metallurgical Intelligence® suite of software, makes it easy to track, report and manage your plant’s emissions in granular detail. It gives you all-important visibility regarding your largest emitting activities. MI Scenario®, an extension to MI Core®, enables you to test alternative scenarios to current practices and processes, as well as set accurate reduction targets. You can also use it to create greenhouse gas emissions budgets and forecasts.
Resources companies have the ability to capture huge amounts of data – so much so, it can often be overwhelming. However, this data is actually one of the plant’s most valuable assets. Used in the right way, it can help you make better decisions, faster, to boost productivity, reduce operational expenditure and greenhouse gas emissions, and avoid costly downtime. MI Core®, the foundation of the Metallurgical Intelligence® suite, provides you with a digital twin of your plant. This digital twin completes a full plant-wide mass balance, and provides a second comparative set of data to cross-check results, including areas in the plant that cannot or are not measured. It also captures and analyses data from right across your plant, in granular detail, and provides you with the highly valuable, consolidated insights you need.
Currently, the mining sector supports over 1 million jobs in Australia.xii Almost half of employees are aged 45 years or older,xiii and the sector runs the risk of missing out on skilled, capable workers if it fails to find a way to make mining more attractive to future generations. Updating the ‘brand’ of mining will go a long way towards luring more people into the profession. To do this, mining companies need to show how far they have come – whether it’s showcasing ESG credentials, or walking the talk with advanced tech that resonates with today’s tech-savvy generation of workers.
No. While metallurgical accounting solutions have existed for some time, our Metallurgical Intelligence® suite of software sits in a category all of its own. It combines existing concepts from other sectors and industries, such as the digital twin, big data computing, process simulation, data visualisation and flexible data integration, and creates a new and entirely unique product that solves real problems for minerals processing plants.
There is no other solution on the market that even comes close in terms of scope, functionality or level of sophistication.
One of the key strengths of Metallurgical Intelligence® is its interoperability, and the fact it can work seamlessly alongside or with other, existing systems. This means that data can be extracted from current systems to provide very comprehensive and accurate insight right across the processing plant.
As Metallurgical Intelligence® can integrate with any existing systems or databases, a broad range of information can be accessed via the one portal. This means it is possible to consider and compare data from a number of different sources – including instrument or laboratory data, or even information from mining, maintenance, environmental or other departments. It can also incorporate budget, cost and forecast data, as well as other financial information, and can report directly to enterprise reporting systems such as SAP.
For organisations with multiple plant operations, it’s also possible to integrate information from multiple deployments of MI CORE in order to compare performance or benchmark different sites.
Absolutely! With international travel currently unfeasible due to Covid-19, we have also fully digitalised our design, deployment, customer service training and support processes, meaning every solution can be implemented remotely from start to finish.
We are currently facilitating 100% of our implementations remotely and have a sophisticated online learning management system.
Yes, we offer extensive training and support for every solution we implement. While our software is very seamless and easy to use, it’s essential that plant operators have the skills and understanding they need to get the most from the solution and ensure maximum return on investment for the plant.
We have developed an online learning management system which requires the end-users of our software to perform certain tests and pass certain criteria before they can progress further. This training system also gives us insights and information on areas that people may be finding challenging, so we can provide targeted support and advice in these areas.
Even today, many minerals processing plants are operating either with manual spreadsheets, or with statistical data reconciliation (SDR) technology to reconcile their measurement data. Typically, this measurement data comes from lab assays and plant instruments, and the objective of the data reconciliation is to find a set of estimates for the measured values which are as close as possible to the actual measurements taken (known as the ‘least squares’ method), so as to verify mass balance conservation laws.
By contrast, digital twin systems are much more accurate and offer a much deeper level of analysis. A digital twin also offers anytime, anywhere access to data – inventory can be measured at any time and isn’t limited to scheduled lab assays. A digital twin model also takes multiple data inputs into account. As well as the most important information generated by the plant, it also considers other inputs such as multiple sample assay results and plant instrument data. All of this information is used to create a second set of data, where flows, inventory changes and even chemical reactions are accounted for.
A dynamic digital twin model is also able to capture volumes and residence times, which is particularly important in hydrometallurgical plants. Plus, the digital twin model can also be industry specific and supports automated data transfer.
No! While many plants are still using Excel spreadsheets, this mode of data analysis is extremely ineffective for several reasons. It requires a great deal of manual intervention, which means there is room for error. The absence of a digital twin model also means that the insights it can possibly provide are quite limited.
Most importantly, using Excel spreadsheets is not AMIRA P754 compliant. These guidelines specify that in order to be compliant, “the system must be consistent and transparent and the source of all input data to the system must be clear and understood by all users of the system. The design and specification of the system must incorporate the outcomes of a risk assessment of all aspects of the metal accounting process.”
A key problem with Excel is that the data can very easily be manipulated or misreported – either intentionally or accidently. The Katanga Mining case from Canada is a perfect example.
Another key issue is that Excel cannot provide traceability back to the source dataset. Simply labelling a column, and assuming the data is transferred accurately, is not a transparent process. Even spot checks cannot be considered a reasonable check due to the volume of data held in most minerals processing plants, and the ability for operators omit or correct values. With an Excel spreadsheet, there is no way to know that the data you are looking at reflects source data. While there are some tools that can provide a level of integration (e.g., the PI Excel Toolkit) this data can still be changed without record.
With Metallurgical Intelligence®, by comparison, all data is extracted from source data systems automatically. There is no user interaction required. The extraction process is detailed in the interface specification that is attached to the dataset. This makes it clear where the data comes from and how. The quality of the data that is loaded is also automatically analysed and reported upon, and allows for complex yet transparent data handling. Any interaction with the data is documented in an activity feed which lists the user.
AMIRA P754 Guidelines also specify that to be compliant, “the system must generate sufficient data to allow for data verification, the handling of metal/commodity transfers, the reconciliation of metal/commodity balances, the measurement of accuracies and error detection, which should not show any consistent bias.”
Although Excel can be configured to include calculations, it is not capable of storing enough source data to complete detailed verification. It is also incapable of generating sufficient cross check data without any user intervention and in fact relies on user discretion, which is a significant issue. Metallurgical Intelligence®, by contrast, is dedicated to data quality. It automatically assesses the data individually, by physical location, and by phenomena. This generates several plots that show if there is bias or instability. It can also show if there is a bias over time or for a specific period.
Metallurgical Intelligence® is highly cost effective given its functionality. Every deployment has seen a rapid return on investment and we pride ourselves on achieving success with all of our implementations. We also offer considerable flexibility with regards to how the solution is paid for and consumed – either as an up-front capital expense, or as part of an ongoing operational expense.
Given the scope of the savings and opportunities that we uncover, we often see payback several times over before the implementation has even been completed. The realised cost savings and efficiency improvements facilitated by Metallurgical Intelligence® are often dependent on the state of the operation before installing the new system, and how stakeholders action the information the system provides.
As Metallurgical Intelligence® is completely customisable, there is no limit to its geographic reach. Currently, it is deployed on several large mine sites around the world, including in Asia, Africa, South America and North America. It is also currently available, and being utilised, with English, French, Spanish and Russian interfaces, with other languages under development (German). Several of our clients have rolled out the solution across multiple plants within their wider operation.