Explainable machine learning
3 articles · search the full text for this term
-
Artificial Intelligence-Assisted Multi-Objective Optimization of Agricultural Biomass-Reinforced Polymer Composites
Abstract: Agricultural biomass can reduce the environmental burden of polymer composites, yet its heterogeneous structure creates competing effects on strength, moisture resistance, density, and process ability. This study developed an artificial intelligence-assisted framework for balanced composite formulation. Experimental data of agricultural biomass reinforced polymer composites were gathered, harmonized and validated using leakage controlled validation. The mechanical and physical properties were predicted by artificial neural networks and conventional regression models. Explainable analysis …
Published in Journal of Polymer & Composites · Vol. 14, Issue 4, 2026 Read article
-
Image-Based Quantitative Mapping of Structure Property Relationships in Polymer Composite Materials
Abstract: The performance of polymer composite materials is intrinsically governed by their microstructural architecture, which is shaped by manufacturing conditions and constituent interactions. Despite extensive experimental characterization efforts, establishing transparent and quantitative structure–property relationships from microstructural images remains a challenge. In this study, an explainable image-driven framework is developed to systematically correlate microstructural features with composite property indicators. Microstructure images are processed to identify voids, fibers, and filler phases, from which …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 188–196 Read article
-
Explainable Machine Learning for Process Parameter Optimization in Gradient 3D-Printed Polymer Composites
Abstract: The explainable machine learning-based structure may be employed to achieve a favorable process parameter of the graduate 3D-printed polymer composite structures to improve the mechanical and thermal properties without compromising the transparency of the decisions made during the fabrication process. Gradient composite specimens were made by systematically varied process parameters like nozzle temperature, raster orientation, deposition speed, gradient transition rate and fused filament fabrication. A predictive model of tensile strength …
Published in Journal of Polymer & Composites · Vol. 14, Issue 2, 2026 · pp. 847–866 Read article