KEY BENEFITS
Systematic experimental programs or trials can take many forms. Scientific experiments to support design of better formulations, materials, or chemicals. Market research in which you acquire and interrogate market data as you refine a product proposition. Business or finance projects to test and improve the effectiveness of an investment model. Whatever your focus, experiment or data acquisition is costly and time consuming – you want to focus these efforts as effectively as possible, and extract more insight from the data you have.
Machine learning methods can achieve these goals. But they are limited where your data is sparse (i.e., has gaps) or noisy – as it is in most ongoing experimental programs. Alchemite™ deep learning software has the answer. It works on sparse, noisy datasets. It generates models that help you to understand this data. It recommends what experiments to do next in order to improve your model most, for least effort. And it applies the models to predict outcomes and optimise system inputs. Originally developed for complex scientific applications in formulation and materials design, Alchemite™ can be applied to any numerical dataset.
Resources and case studies
The science behind adaptive experimental design
Identifying the optimal composition and processing parameters to achieve commercial performance goals as quickly as possible is the key objective of formulation design projects. Machine learning identifies improved formulations up to 10 times quicker than traditional approaches, by focusing experimental effort directly on formulations that will lead to successful products in as few experimental cycles as possible.
Formulation design at Domino Printing Sciences
Domino Printing Sciences applied Alchemite to help guide testing and find optimal formulations for their inks. This case study shows how to reduce time-to-market, identify new candidate formulations, and enable reformulation in response to market, environmental, or regulatory drivers.
“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
Design of Experiments for innovative manufacturing
In this short video extract from an Intellegens webinar, Ian Brooks of the Advanced Manufacturing Research Centre discusses some successful Design of Experiments results from a project, supported by Boeing, to optimise innovative additive manufacturing processes.
Alchemite™ for Design of Experiments
- Enable DoE, even when data is sparse and noisy
- Gap-fill and validate experimental data and enrich it with data from other sources (e.g., simulation)
- Quantify uncertainty to support a rational business case for your experimental program
- Decide which experiments to do next in order to improve your model
- Identify the likeliest candidate solutions and focus on those, thus reducing the number of experimental cycles