Incremental Transformer for Surrogate-Based Inverse Design of Geopolymer Mixtures
2026-07-12 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors developed a new method to help design mixtures for geopolymer concrete, even when only small and complex data is available. Their approach uses a special transformer model to understand and organize the data’s structure, making sure designs meet physical rules and key goals like strength and low emissions. They show that just trying to optimize without considering these rules can lead to unrealistic results. Their method finds practical mixture designs by combining physics constraints with an understanding of the data’s underlying patterns, helping engineers focus on the most promising candidates. This tool is meant to aid, not replace, real-world testing.
inverse designsurrogate modeltransformertopologygeopolymer concretecompressive strengthcarbon emissionmanifold learningconstrained optimizationmixed-variable data
Authors
Giansalvo Cirrincione, Filippo Grassia
Abstract
Small-data inverse design is challenging in engineering informatics when observations are heterogeneous, mixed-type, and constrained by physical relations among design variables. This work proposes a topology-aware surrogate framework guided by an Incremental Transformer (INCRT) for physics-constrained inverse design, applied to geopolymer mixture design. The method integrates intrinsic-dimensionality analysis, mixed-variable design-space representation, tabular surrogate prediction, INCRT-based manifold rationalisation, and constrained inverse optimisation. Using a public benchmark of fly-ash and slag-based geopolymer concrete mixtures with compressive-strength and carbon-emission targets, the high-dimensional design space proves strongly redundant, organising around fewer effective mixture regimes. Compressive strength requires nonlinear tabular surrogates, while carbon emission is largely determined by composition and well recovered by regularised linear models. INCRT thus acts not as a replacement for tabular predictors but as a rationalisation layer providing prototype regimes and a manifold-support score for inverse design. Three strategies are compared: unconstrained surrogate optimisation, physics-constrained optimisation, and topology-aware physics-constrained optimisation. Unconstrained optimisation can match target strength but may yield physically invalid or off-manifold candidates; physics-only constraints do not always ensure data support. The topology-aware strategy yields candidates balancing target compliance, carbon reduction, physical admissibility, and proximity to the learned feasible manifold. The framework aims not to replace experimental validation but to support screening of credible candidate mixtures from small, mixed, physically constrained engineering datasets.