(101c) A Lower-Risk Pathway to Digital-Centric Chemical Product R&D | AIChE

(101c) A Lower-Risk Pathway to Digital-Centric Chemical Product R&D


Heiber, M. - Presenter, University of Akron
Farrow, C., Enthought
Digital technologies like machine learning, AI, and robotic automation are starting to have a significant impact on R&D labs across all technology driven industries, including chemistry and materials science. Central R&D organizations of most large specialty chemical companies have started investing in these areas and exploring the long term business potential of these technologies. However, there is a significant challenge in how to evolve R&D labs in a way that delivers value early and continuously, while creating an environment for innovation that can deliver orders of magnitude improvements in performance, and ultimately, business value in the future.

Industry R&D labs must overcome unique challenges to fully leverage data-driven problem solving approaches. Unlike in operations where many process engineering teams are tackling big data analytics problems, most product development problems are small data problems. R&D data is different. Product development teams are often working with orders of magnitude more tunable variables and orders of magnitude less data that is sparse, non-uniformly distributed, and unstructured. Overcoming this does require the use of different machine learning and AI methods, but most importantly it requires a data-centric view and much tighter interaction between data science and chemistry expertise. This is best achieved, not by hiring centralized data science teams that liaise with researchers, but by digitally transforming R&D labs and teams from the ground up.

Tackling the small data problem and transforming an R&D lab in today’s digital world is a complex journey. To help structure this journey, we have framed the process in 5 distinct levels, with measurable advances through infrastructure, data capture and use, digital processes and steadily advancing levels of automation. However, this journey is not just about new technology adoption. Scientists must acquire new skills, adopt a strong data culture, and be empowered to bring digital innovation into the lab. Furthermore, the digital technologies that are adopted must be able to rapidly evolve in lock-step with the lab’s needs. An R&D system that is too rigid, inefficient, or adopted as a quick fix must be avoided, as it will be incapable of broader transformation and unable to adapt as business needs change.

When the lab arrives at a point where scientists can dial-in desired product properties, samples with those properties are produced automatically, and continuous digital innovation is built into the process, there has been a true transformation. It is then possible to develop highly customized products for each customer, bring specialty services into new markets, and stave off commoditization. The lab is now far more agile, resilient, and valuable with the ability to support the broader digital business transformation goals.

In this presentation, we’ll overview our R&D laboratory digital transformation framework, discuss why this approach is needed, and show specific examples of where this approach has yielded success.