TY - CONF A1 - Völker, Christoph A1 - Kruschwitz, Sabine A1 - Moreno Torres, Benjami A1 - Firdous, R. A1 - Zia, G. J..A. A1 - Stephan, D. T1 - Accelerating the search for alkali-activated cements with sequential learning N2 - With 8% of man-made CO2 emissions, cement production is an important driver of the climate crisis. By using alkali-activated binders, part of the energy-intensive clinker production process can be dispensed. However, as numerous raw materials are involved in the manufacturing process here, the complexity of the materials increases by orders of magnitude. Finding a properly balanced binder formulation is like looking for a needle in a haystack. We have shown for the first time that artificial intelligence (AI)-based optimization of alkali-activated binder formulations can significantly accelerate research. The "Sequential Learning App for Materials Discovery" (SLAMD) aims to accelerate practice transfer. With SLAMD, materials scientists have low-threshold access to AI through interactive and intuitive user interfaces. The value added by AI can be determined directly. For example, the CO2 emissions saved per ton of cement can be determined for each development cycle: the more efficient the AI optimization, the greater the savings. Our material database already includes more than 120,000 data points of alternative binders and is constantly being expanded with new parameters. We are currently driving the enrichment of the data with a life cycle analysis of the building materials. Based on a case study we show how intuitive access to AI can drive the adoption of techniques that make a real contribution to the development of resource-efficient and sustainable building materials of the future and make it easy to identify when classical experiments are more efficient. T2 - fib International Congress CY - Oslo, Norway DA - 12.06.2022 KW - Concrete KW - Materials Design KW - Sequential Learning KW - Machine Learning PY - 2022 SP - 1 EP - 9 AN - OPUS4-56634 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Schartel, Bernhard A1 - Humphrey, J.K. A1 - Gibson, A.G. A1 - Hörold, Andreas A1 - Trappe, Volker A1 - Gettwert, V. T1 - Assessing the structural integrity of carbon-fibre sandwich panels in fire: Bench-scale approach N2 - The fire resistance of lightweight sandwich panels (SW) with carbon fibre/epoxy skins and a poly(methacryl imide) (PMI) foam core is investigated in compression under direct application of a severe flame (heat flux=200 kW m−2). A bench-scale test procedure was used, with the sample held vertically. The epoxy decomposition temperature was quickly exceeded, with rapid flash-over and progressive core softening and decomposition. There is a change in failure mode depending on whether the load is greater or less than 50% of the unexposed failure load, or in other words if one or two skins carry the load. At high loads, failure involved both skins with a single clear linear separation across each face. There is an inflection in the failure time relationship in the ∼50% load region, corresponding to the time taken for heat to be transmitted to the rear face, along with a change in the rear skin failure mode from separation to the formation of a plastic hinge. The integrity of the carbon front face, even with the resin burnt out, and the low thermal diffusivity of the core, both play key roles in prolonging rear face integrity, something to be borne in mind for future panel design. Intumescent coatings prolong the period before failure occurs. The ratio of times to failure with and without protection is proposed as a measure of their effectiveness. Apart from insulation properties, their adhesion and stability under severe fire impact play a key role. KW - Carbon fibres KW - Sandwich KW - Structural composites KW - Fracture KW - High-temperature properties KW - Surface treatments PY - 2019 DO - https://doi.org/10.1016/j.compositesb.2018.11.077 SN - 1359-8368 VL - 164 SP - 82 EP - 89 PB - Elsevier AN - OPUS4-46908 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -