IES have been working with a distillery in Northern Italy, using their ICL digital twin technology to help the factory better understand and optimise their energy consumption, while identifying ways to reclaim and reuse waste heat produced on site. The technology provides an integrated approach to optimising building performance and manufacturing processes, allowing the factory to gain a complete understanding of the overall energy balance in their facility and virtually test future scenarios and improvements.
The work has been carried out as part of an EU Horizon 2020 project which aims to support industries and energy utilities in selecting, simulating and comparing alternative waste heat and cold exploitation technologies, to cost-effectively balance local heating and cooling demand. The project also looks at how renewable energy sources can be integrated to help meet energy demand locally.
This particular facility wanted to analyse their distillery process and understand what level of waste heat was being produced and what opportunities exist to reuse it on site. The project also considered how renewables, in this case solar PV installations, might help to further minimise the factory’s reliance on the grid.
All of the modelling work performed by IES was achieved using relatively simple data sets taken from the distillery’s utility bills and submeter data. Using the iSCAN data analytics platform, it was possible to collate all of this existing data within the centralised platform, providing a single pane operational view across the distillery’s various systems and production processes. This capability is particularly beneficial to manufacturing facilities, where there are multiple production lines, data sources and systems to manage, but often no unified access to production data.
Once the data had been imported into iSCAN, the IES team were able to disaggregate the monthly utility data into more granular time-series profiles. Using a process known as rough-cut profiling, it was possible to correlate the time-series data to specific processes and equipment within the distillery to build a more accurate view of the factory’s operations. This helped to provide operational insights at the level of detail required to effectively identify where the biggest sources of energy use and waste heat production lie, so the distillery could begin to target these. The AI and machine learning capabilities of the iSCAN platform also made it possible to fill any missing data gaps to provide a more complete picture of what is happening across the factory.
Next, IES were able to model the facility’s processes and components using an enhanced manufacturing process modelling functionality within the VE. From here, it was possible to assign the iSCAN data to the 3D model to create a digital twin of the facility, incorporating all of the factory components and building systems, which can now be used to simulate and analyse the factory’s current performance and forecast the impact of future interventions and scenarios.
The baseline digital twin analysis showed that the distillery was producing high levels of waste heat – the majority of which came from electrical loads – and was also drawing high consumptions of gas and electricity from the grid. The results can be viewed via dashboards, which can be accessed securely online from anywhere, with different versions available for different users. This included more in-depth technical views for the facilities staff responsible for operating the factory, as well as more basic views to help provide senior staff with a top-level understanding of the site’s energy performance and waste heat output at a glance. Of particular value to the distillery was the ability to view all of the energy flows across the factory – from the energy sources themselves, through the various equipment and processes, and ultimately the energy and waste heat outputs - as a Sankey diagram. IES have also created a “Recover” functionality within the software, so users can quickly and easily extract results to show the waste heat availability on the site.
With the baseline digital twin in place, the IES team were able to simulate and analyse different options to help optimise the efficient running of factory processes and take steps towards making the facility more energy self-sufficient. Using the iVN network modelling tool, the team focused their analysis upon two key interventions for the distillery; namely the potential for a waste heat recovery exchanger, to reclaim and reuse the available waste heat identified from the baseline analysis, as well as solar PV installations, to help meet more of the facility’s energy demands locally.
Analysis of the proposed interventions indicated that the waste heat exchanger would allow the distillery to meet 5% of its overall heating needs using waste heat recovered on site, while the proposed solar PV installations would further help to meet 4.1% of the site’s total electricity consumption. Overall, these interventions would lead to a 6.9% total saving in CO2 and a 6.3% reduction in total final energy consumption across the site. A financial analysis, also facilitated within the digital twin and communicated via dashboards, was also able to show the economic payback of different interventions, with the waste heat exchanger found to have a payback of ~11 years.
The project is ongoing with the digital twin providing the basis for further simulation and analysis of improvements the distillery can make to improve efficiency, as well as reduce its carbon impact and running costs. The technology is also being applied across a further 10 test sites across Europe as part of this project, to demonstrate the replicability of the solution across different industries and manufacturing facilities.