Innovative Methods for Predicting Material Stress-Strain Curves Based on Transfer Learning and Artificial Intelligence
2025-01-8317
To be published on 04/01/2025
- Event
- Content
- The mechanical properties of materials play a crucial role in predicting performance across various applications. However, traditional methods for measuring these properties often involve complex, resource-intensive, and time-consuming tests, which may be impractical in certain situations. The Small Punch Test (SPT) is a small-sample detection technique for evaluating material mechanical properties, characterized by its "non-destructive" nature: applying localized loads to small specimen samples and measuring the resulting deformation. While SPT can obtain load-displacement curves for specimens, it cannot directly reflect material mechanical properties and relies on empirical formulas for estimation. To address this challenge, we designed a specialized SPT experiment and fixture, and established a Finite Element Method (FEM) model. We developed a multi-fidelity model capable of predicting the mechanical properties of steel and aluminum alloys, representing a novel machine learning approach for mechanical property prediction. This model utilizes multi-fidelity datasets obtained from SPT and FEM simulation experiments. This integration enables us to support and optimize the predictive accuracy of our research, ensuring comprehensive and reliable characterization of material mechanical properties. Our model accounts for variations in material thickness, effectively predicting mechanical properties for materials of different thicknesses to accommodate real-world scenarios where material samples exhibit varying thicknesses due to different applications or manufacturing processes. By combining SPT and multi-fidelity modeling techniques to predict the performance of steel and aluminum alloys of various thicknesses, our research provides a practical and effective solution for extracting mechanical properties while ensuring versatility and applicability in real-world scenarios.
- Citation
- Zou, J., Li, S., Huayang, X., and Chen, Y., "Innovative Methods for Predicting Material Stress-Strain Curves Based on Transfer Learning and Artificial Intelligence," SAE Technical Paper 2025-01-8317, 2025, .