In a challenging market pushing towards a ‘servitisation’ model, digital transformation can provide mining industries with the tools to mitigate changes in global demand
Many air and gas handling applications today operate against the backdrop of challenging markets. Digitalisation has become a key driver in mining to optimise processes and maximise the value of existing applications. Attention has shifted towards emerging technologies to optimise investments on equipment, improve safety at mines and reduce environmental impact.
The digitalisation trend has seen a steady move towards a servitisation model, ie product strategies delivered through or by a service. This is now starting to be very disruptive not only in organisations that are already service-centric, but also in areas that are product intensive. As a consequence, miners are seeing a push towards product strategies delivered through manufacturing industries, which not so long ago used to operate using a ‘demand and supply’ business model, but are now affected by the societal evolution of Industry 4.0 and the advent of the industrial Internet of Things (IoT).
While the implications of digitalisation are disruptive in more than one way, technology adoption happens at a remarkable pace. In fact, it may be argued that this fast adoption rate is also responsible for yet another unanticipated cultural shift. Research shows that manufacturing companies piloting new technologies to support the emerging servitisation model do not spend a lot of effort in measuring financial outcomes. Rather, they embrace the need for such technologies as vital in the quest for improved performance, with pressure to avoid being left in the wake of the digitalisation wave.
The broad consensus is that the opportunities to reduce costs and digitally transform far outweigh the risks of rapid technology adoption supported by IoT products previously unseen in mining.
Digital technology trends: the digital twin
One of the key strategic technology trends in mining is the digital twin. Digital twin models handle large volumes of historical data, and are supported by the advent of cloud technology that can store an effectively infinite volume of data.
Digital twin models are continuously evolving digital profiles comprising historical data superimposed on the current behaviour of the equipment. The digital twin is based on cumulative, real-world measurements across a wide range of operational parameters. Such measurements help create a digital performance profile that will support actions in the real world, leading to design improvements and changes in the manufacturing and operation of the asset.
While in theory the concept is sound and can enable real value, in practice deploying such digital twin models at full scale is challenging for a number of reasons:
• The digital profile is relying on the existence of historical data, and large amounts of it, to create an accurate representation of the equipment. In air and gas handling applications, the right or sufficient data to build the digital profile may not always be available.
• Accessing and processing raw data in a way that is relevant for equipment performance is not always possible. Creating the digital profile involves data tagging of events in the operational history of the asset. Looking for both efficient operation and failure modes can be a daunting task, especially for machines deployed in the field for some time.
• Historical data can only be a resource for already installed equipment; newly commissioned equipment does not have a digital performance profile from the beginning.
The new generation of digital twins
In air and gas handling applications in the resources sector, end users are typically focused on:
• detecting equipment failure before it occurs and identifying the root cause
• understanding the impact of change in operating conditions on the equipment and process performance
• moving critical equipment maintenance strategies from reactive to fully predictive
• optimising energy consumption to reduce costs and carbon footprint
• maintaining continuity of equipment operating history between several iterations of the
mine plan and changes to personnel.
A digital twin model designed to solve physical issues faster by detecting them sooner, predict outcomes to a much higher degree of accuracy, and evaluate performance of the equipment in real-time, may help companies realise value and benefits iteratively and faster than ever before.
This value starts with having a complete digital footprint of the product from design and development through to the end of the product lifecycle. This, in turn, may enable an understanding of not only the product as designed, but also the system that built the product and how the product is used in the field.
With the creation of the digital twin, manufacturing companies may realise significant value in the areas of speed to market with a new product, improved operations, reduced defective equipment, and emerging new business models to drive revenue.
One feature of the new generation digital twin approach is the source of the historical data. While superimposing digital profiles on real-life application data is the true enabler of value, revisiting the source of the data for the digital half of the model may result in a game-changing approach.
Traditionally, we think of historical data as operational data recorded and used to average a past behaviour. But what if the historical data is replaced by a design data set that includes the design principles of the equipment, the intended performance at the best efficiency point, and the CAD model with simulation values of the desired process and relevant air and gas properties?
A digital profile populated by such data will depict a ‘theoretical’ performance map of the equipment as per its design intent. Superimposed on the real-life operational data from the sensors, this information will enable the mapping of the current operation in respect to the equipment’s best efficiency point, without processing any historical data. Isolating and analysing the difference between the two data sets will optimise equipment performance to match operational requirements.
For operations with pre-existing historical data, these patterns can be pre-populated and the recorded operational data may be used as a subset to assess the asset performance to date, which when mapped to the design data, can be indicative of the asset’s remaining life.
Driving business value with digital twins
Digital twins may help equipment manufacturers with asset fleet management, but improvement in operational efficiency and insights into operation will require time and a lot of data gathering and processing, and therefore multiple years to realise financial benefit. In light of this, setting on a path of digital transformation that is focused on solely building digital twin models should be done with the longer-term business benefits in mind, driven by customer and organisational KPIs.
Once these objectives are clearly defined, a wider enterprise readiness assessment may be required in order to identify other IoT initiatives that are focused on leveraging the full value of the digital twins. In this way, digital twins can offer strong potential to achieve the desired value improves and support improved decision making. The risk, especially in organisations that do not have a strong suite of IoT equipment, is in the absence of clear objectives. In this case, it may be difficult to transform an organisation’s digital journey into a data collection and storage driven process.
Artificial intelligence and augmented reality
In air and gas handling applications in the resources sector, digital twins of rotating equipment can deliver more value if focused on critical performance goals, such as efficient/optimised operation and elapsed/remaining operational life. These goals can be achieved by coupling the digital twin with the two emerging ‘A’ IoT technologies – artificial intelligence (AI) and augmented reality (AR).
AI stands out as a transformational technology and questions about what it is, and what it can do, are still being explored. The definition of AI is ever evolving and extensive research in the field has mapped these capabilities to specific industries and problem types.
As more asset performance data is analysed and interpreted through digital twins, AI-enabled maintenance strategies will continue to increase, changing the operation of equipment to data-enabled decisions and actions that result in optimised performance and the avoidance of unplanned downtime.
AI-enabled strategies will allow equipment behaviour learning and automation of digital
analytics to deliver situational analysis that responds to changing operating conditions. This results in clear business value around asset performance optimisation, predictive maintenance opportunities and extending operational life of the equipment.
AR, though still in its infancy, is another quickly evolving technology that superimposes a computer generated three-dimensional model on the viewer’s real world, providing a hybrid view of the physical and digital.
With AR transforming volumes of data and analytics into images or animations that are overlaid on the real world, it can deliver great customer value. AR allows a digital object to be placed in the customer’s physical environment, providing a detailed experience of the internal features that would otherwise be difficult to see, enhancing the understanding of fundamental principles of operation and design. Secondly, AR enhances product perception, with 3D thinking and visualisation rather than 2D that helps facilitate the real-time display of the equipment with operational and digital twin data.
Furthermore, AR has the potential to fully immerse the digital twin into the physical world, focusing on real equipment and process performance indicators. The not-so-distant future of AR will no doubt see a full immersion of the customer experience from end to end, connecting sales to design and manufacturing through to installation and operation into a space where the data is displayed right in front of you, in real time.
We are witnessing a truly global uptake of digital trends where mines are faced with increasing pressure to transform their traditional operations and foster a digital culture. In a challenging market pushing towards servitisation, digital transformation can provide mining industries with the tools to mitigate the changes in global demand. This involves mining operations developing the capabilities they need to provide services and solutions that supplement their traditional product offerings.
The biggest limitation of digitalisation in this space is the data, either too little or too much of it, and only a clear data strategy can yield a successful digital transformation journey that adds business advantage.
One approach is by driving digital transformation through customer KPIs with a focus on the business value. This approach can enhance customer operations and can be achieved with the new generation of ‘smart’ digital twins with pre-populated design data to reflect the equipment’s best efficiency point, as well as deviation from intended operation conditions. This data strategy focuses on the right operational data, setting the scene for performance optimisation, and can be further enhanced by enabling the smart digital twins with advanced IoT technologies like AI and AR, thus delivering business value according to predefined KPIs.
With over a century of experience, Howden is a leading global supplier of air and gas handling equipment. Renowned for engineering excellence with highly experienced specialists across multiple industrial sectors; from mine ventilation and waste water treatment to heating and cooling, Howden is committed to putting customers at the heart of our operations. Visit www.howden.com.