Shallow nanoindentation, needed for thin layers, individual phases and small volumes, gives hardness inflated by the indentation size effect (ISE). The Nix-Gao correction reduces this inflation but requires deep indentations of the same material, often impossible in such samples. We present a data-efficient workflow, trained on a few reference materials, that predicts a high-load reference hardness from a single shallow indentation. Seven models were trained on 703 indentations (5-350 mN) on three steels (2.0-6.5 GPa): Ridge regression, Random Forest, XGBoost, two feed-forward networks, and two physics-constrained neural networks (PCNNs) that apply a bounded learned correction q as H_app/sqrt(1+q). Over five seeds, models were tested on an external steel not used for training and indented at different loads, in leave-one-steel-out folds, and on fused silica, an out-of-domain material where all models failed. Random Forest and XGBoost, the best on the development set, transferred worst over all loads (MAPE 10.2 and 8.5%), whereas Ridge regression, the PCNNs and one feed-forward network reached 3.7-4.8%; with three training steels, development-set accuracy thus did not indicate accuracy on an unseen steel. From only the external steel's 3-15 mN indentations, the smooth (non-tree) models estimated the reference within 0.03-0.19 GPa on average. The PCNNs matched the linear baseline within the training hardness range and were the most accurate for a held-out steel softer than the training steels, but failed for a harder one. The workflow uses no steel-specific inputs and can be retrained for other material classes.

翻译：暂无翻译