Case Study with Domino
Empirical analysis is typically the most resource-intensive part of the R&D process – so much so that, in recent years, virtual experiments have become a topic of major interest. Virtual experiments allow researchers to use existing empirical data to predict and validate experimental outcomes, and are particularly useful when lab access is limited, as we have witnessed during the current global pandemic. The following case study highlights how Domino Printing Sciences (Domino) used Alchemite™ to leverage their historical data to obtain several novel ink formulations, some of which were later validated via physical experimentation. By utilising virtual experiments in this way, Domino was able to:
-
Maximise the insights gained from carefully chosen additional experiments
-
Reduce the number of physical experiments required
-
Decrease the timescale of ink formulation experimentation from months to minutes
“We were impressed with the ability of Alchemite™ to identify novel formulations quickly and accurately. This enabled us to make the most of limited lab resources and continue innovating during the COVID-19 lockdown.”
– Dr Andrew Clifton, Director of Marking Materials and Test Engineering Team at Domino
Challenge
The traditional ink development process requires the formulation and testing of a large number of designs in order to produce an optimum formulation with the best performance.
Domino is renowned for designing and manufacturing reliable and well-understood inks and, as such, has well-characterised historical data. In pursuit of innovation and sustainability, Domino is looking to utilise this data to replace ingredients that are no longer suitable or available. Intellegens’ aim was to leverage all the available data to build machine learning models to propose new ink formulations that would match, or exceed, the design targets associated with the existing products.
Limited lab access during the COVID-19 pandemic hampered most of the R&D activities that relied on empirical analysis, worldwide. It has therefore become essential to extract maximum value from newly acquired as well as historical data.
