Which alloy composition,what process parameters? Inferring the recipe from optimized metallic microstructure and texture

2026-10-06

AI Summary

This study addresses the challenge in alloy inverse design of inferring composition and processing routes from microstructures, which conventionally relies on expert knowledge. We present the first systematic evaluation of three microstructure descriptor paradigms: traditional statistical features, visual embeddings, and graph neural networks. Leveraging magnesium alloy datasets, we construct bidirectional structure–recipe mapping models by integrating optical microscopy images, X-ray texture measurements, pretrained encoders, and ordinal classification heads. Our findings reveal that traditional statistical descriptors outperform deep learning-based embeddings, correctly identifying 65% of alloy types. Furthermore, incorporating microstructural information halves the error in processing temperature prediction, thereby validating the feasibility of inverse inference for alloy design.

Abstract

The mechanical properties of a metallic alloy are set by its microstructure and texture: the size and shape of its grains and the orientation of their crystals. That structure is in turn set by a recipe, the alloy composition together with the processing parameters. Alloy development runs this chain forwards, tuning the structure until a target property is met. Running it backwards, from an optimized structure to the recipe that would produce it, still relies on expert knowledge. We ask whether this backwards step can be learned. On an in-house dataset of 107 magnesium alloy extrusion conditions across 14 alloys, each with optical micrographs and an X-ray texture measurement, we compare three descriptors of microstructure and texture: conventional grain and texture statistics, a vision embedding from a pretrained image encoder, and a graph neural network on the grain network. Each is paired with prediction heads for two tasks: the alloy composition given the process (Task A), and the process parameters given the composition (Task B). Under 5-fold cross-validation, the conventional descriptors identify the correct alloy for 65% of held-out conditions, against 17% for always guessing the most common alloy, while the learned embeddings stay below 30%. The process parameters are recoverable but noisier: compared with using the composition alone, the microstructure roughly halves the temperature error. Because only a few alloys were cast and only a few press settings were used, both answers are discrete, and heads that pick from these known options, while respecting their order, worked better than heads that predict a free value.

Problem

• inverse design
• alloy composition
• process parameters
• microstructure
• texture

Innovation

• Inverse design
• Graph neural network
• Microstructure descriptor
• Magnesium alloy
• Ordered classification