8.0 Abteilungsleitung und andere
Filtern
Dokumenttyp
Sprache
- Englisch (2)
Referierte Publikation
- nein (2) (entfernen)
Schlagworte
- Sequential learning (2) (entfernen)
Organisationseinheit der BAM
WEBSLAMD
(2022)
The objective of SLAMD is to accelerate materials research in the wet lab through AI. Currently, the focus is on sustainable concrete and binder formulations, but it can be extended to other material classes in the future.
1. Summary
Leverage the Digital Lab and AI optimization to discover exciting new materials Represent resources and processes and their socio-economic impact.
Calculate complex compositions and enrich them with detailed material knowledge. Integrate laboratory data and apply it to novel formulations. Tailor materials to the purpose to achieve the best solution.
Workflow
Digital Lab
Specify resources: From base materials to manufacturing processes – "Base" enables a detailed and consistent description of existing resources
Combine resources: The combination of base materials and processes offers an almost infinite optimization potential. "Blend" makes it easier to design complex configurations.
Digital Formulations: With "Formulations" you can effortlessly convert your resources into the entire spectrum of possible concrete formulations. This automatically generates a detailed set of data for AI optimization.
AI-Optimization
Materials Discovery: Integrate data from the "Digital Lab" or upload your own material data. Enrich the data with lab results and adopt the knowledge to new recipes via artificial intelligence. Leverage socio-economic metrics to identify recipes tailored to your requirements.
Environmentally friendly alternatives to cement are created through the synthesis of numerous base materials. The variation of their proportions alone leads to millions of materials candidates. Identifying suitable materials is very laborious; traditional systematic research in the laboratory consumes a lot of time and effort.
Sequential learning (SL) potentially speeds up the materials research process despite limited but highly complex available information. SL does not make direct predictions of material properties but ranks possible experiments according to their utility. The most promising experiments are prioritized over dead-end experiments and experiments whose outcome is already known.
Our work has shown that SL seems to be promising for cement research. So far, research has mainly focused on materials whose synthesis is faster and whose material properties require less time for development or characterization (allowing many successive experiments). Contrarily, in the case of binders, SL is only useful if few experiments lead to the desired goal, as for example, the determination of the compressive strength alone typically requires 28 days.
In research practice, experimental designs and the availability of resources often determine which data can be used - for example, when some laboratory resources are not available or deemed irrelevant to a task. As a result, new research scenarios are constantly emerging, each of which requires to demonstrate SL’s performance.
We are presenting the SLAMD app to facilitate the exploration of SL methods in numerous research scenarios. The app provides flexible and low-threshold access to AI methods via intuitive and interactive user interfaces. We deliberately pursue a software-based research approach (as opposed to code-, or script-based). On the one hand, the results are more comprehensible since we refer to a common (code) basis (’reproducible science’). On the other hand, the methods are easily accessible to all which accelerates the knowledge transfer into laboratory practice.