Alchemite™ DOE is a data-driven experimental design tool that helps your organisation become more productive with no extra effort. It applies machine learning to enable an adaptive approach to Design of Experiments, reducing experimental time by 50-80%. By learning from your data and providing a simple task-oriented user interface, Alchemite™ reduces the DOE workflow to a few button-clicks. No lengthy training courses, no need for advanced statistics, and no coding required.
Application areas include formulation design, chemicals, materials research, life sciences, and additive manufacturing.
White paper – Adaptive experimental design
Identifying the optimal composition or chemistry and the ideal processing parameters to achieve commercial performance goals as quickly as possible is the key objective in the design of formulations, chemicals, materials, and biopharmaceuticals. Machine learning enables an adaptive experimental design approach, focusing on experiments that will lead to successful products and reducing experimental workloads by 50-80% compared to traditional Design of Experiments.
Case study – ink formulations
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.
Case study – clean air and life science applications
Sustainable materials producer Johnson Matthey used Alchemite™ in projects to develop new catalyst formulations for clean air and life science applications. The results were improved yields and the identification of faster experimental routes, including a 5x speedup in one project area.
Case study – additive manufacturing process parameters
In collaboration with the University of Sheffield Advanced Manufacturing Research Centre (AMRC), Boeing, Constellium, and GE Additive, Alchemite™ was used to design new AM parameter sets for laser powder bed fusion (LPBF), developing process parameters for a new powder. The project team was able to move from the new powder to final parameters in just two builds, while applying no expert statistical knowledge.
Recorded webinar
In this recorded session, hear how Alchemite™ DOE has been applied to accelerate experimental design and cut experimental workloads. A short demonstration of the software in action shows how quick and easy it is to learn and apply.
Blog series
Find out more about Design of Experiments and how machine learning can enable accelerate and improve your DOE in our short blog series. We explain why DOE is useful, limitations on conventional DOE, and the strengths of an adaptive DOE approach.
Alchemite™ vs conventional DOE
- Enables an iterative, targeted approach, resulting in 50-80% fewer experiments
- Learns from your data, requiring no statistical knowledge to set up experimental designs
- Works well for complex, high-dimensional problems with non-linear relationships
- Generates a machine learning model that enables additional insights into your data and can be applied as a predictive tool
