Open-die metal forging is challenging to automate due to the complex dynamics involved during deformation. Modern approaches use finite-element methods (FEM) to manually pre-plan deformation sequences on a per-part basis, requiring significant development and computation time. Inspired by autoencoder-based point cloud regression and segmentation methods, we introduce ForgeNet, a point cloud autoencoder that predicts the material displacement field given a state-action pair consisting of a metal workpiece and a deformation boundary condition. Standard point cloud autoencoders are trained with a permutation-invariant chamfer loss, which does not preserve point-to-point correspondence and therefore reproduces physically inconsistent displacement fields. ForgeNet uses barycentric point sampling to preserve point correspondence between deformations, enabling training with a standard mean-squared error loss that yields physically consistent displacement fields. We train our model on a large synthetic dataset simulated using JAX-Forge [1], a GPU-accelerated FEM package for open-die forging. Empirically, ForgeNet learns the dynamics of plastic deformation, accurately reconstructing displacement fields over long sequences, whereas standard point-based autoencoders reproduce only statistically similar point clouds after a single action. This allows ForgeNet to serve as a state-transition model that accelerates planning for optimal forging sequences, which we demonstrate on geometries outside our training dataset.
Plate impact experiments represent a canonical approach to studying the shock and impact response of materials. However, because of their low-throughput nature, it has been difficult to obtain statistically rich datasets of dynamic material properties. This work presents a closed-loop automation framework for a high-throughput laser-driven micro-flyer impact (LMI) system that uses drive and diagnostic lasers to rapidly investigate material response, enhancing both throughput and experimental consistency. An experiment control interface was developed to provide automated flyer velocity regulation, laser power control, sample positioning, laser triggering, and diagnostic feedback, all integrated within a single user application for closed-loop execution. Accurate micro-flyer positioning is achieved using an EfficientNet-based detection model, resulting in detection success rates of 100.0 μ m along the x- and y-directions. The performance and robustness of the framework were validated through automated flyer velocity regulation and PDV signal optimization experiments across flyer materials with varying surface characteristics. The results demonstrate reliable feedback-based shoot/skip decision-making, on-the-fly PDV signal optimization, and approximately an 8× improvement in experimental throughput compared with manual operation, completing 25 impact tests in approximately 4 min. The proposed framework improves the reproducibility and traceability of LMI experiments while providing a scalable foundation for autonomous high-throughput dynamic impact testing.
Dual-phase (DP) steel is widely used in the context of automotive lightweighting due to its excellent strength-ductility balance. Analyzing and optimizing microstructures to delay ductile fracture has become a widely researched topic. This study proposed a hybrid convolutional neural network–graph convolutional network (CNN–GCN) model enhanced by gated fusion to analyze the influence of microstructure on the local damage behavior of DP590 steel. First, a physics-guided dynamic extraction method was employed to isolate damage-prone local regions from the global microstructure, and a graph structure was constructed to describe the spatial topological relationships. Subsequently, a CNN was utilized to extract local image features, which were then fused with global martensite fraction ( V_M ) multimodal features via a two-level adaptively weighted gated fusion mechanism. Finally, a GCN was employed to learn inter-node correlations and predict local damage strain. The results demonstrated that the proposed model significantly outperformed a series of baseline models on the test set for the node-level prediction task and could be extended to graph-level prediction tasks. Introducing a multi-task learning framework was proven to further enhance its generalization capability. Furthermore, interpretability analysis of key modules validated the model's ability to capture the underlying physical mechanisms.
High-energy diffraction microscopy (HEDM) is a valuable technique that allows for time-resolved 3D characterization of grain-scale deformation during mechanical testing. In past studies, the local spatially resolved information provided by HEDM has revealed unintentionally imposed bending moments that complicate data analysis and efforts to couple experiments with microstructure-sensitive models. In this work, a mechanical test and in-situ HEDM experiment with both bending and tension loads applied was conducted on a polycrystalline nickel-based superalloy, IN718. Crystal plasticity finite element (CPFE) simulations were performed using the experimental microstructure as input and loaded to reproduce the bending-tension loads, as well as a pure tension loading procedure. This study examines the evolution of grain-by-grain strain and intragranular orientation distributions in both the experiment and model throughout loading, thus revealing the persistent effect of bending in both macroscopic elasticity and plasticity. Additionally, CPFE predictions of grains that accumulate relatively high and low amounts of slip reveal that extreme plasticity value grains can be sensitive to bending. Finally, recommendations are given for the interpretation and modeling of bending moment containing HEDM experiments.
Material properties are strongly influenced by their microstructure. Thus, the microstructure must be accurately quantified to predict material behavior. Although these properties are governed by their three-dimensional (3D) microstructure, most common characterization techniques rely on two-dimensional (2D) imaging. Serial sectioning methods can accurately capture 3D microstructural features, but they are time-consuming, expensive, and destructive. This work addresses 3D microstructure characterization using a power-law mapping derived from 2D images. To this end, a dataset of synthetic microstructures with equiaxed grains and six different grain size distributions is used. The extracted grain size distributions highlight the differences between 2D and 3D statistics. The study also quantifies the effect of the number of grains within a 2D image on the resulting statistics. The power-law mapping is also compared against the Saltykov stereological method. The mapping outperforms the Saltykov method for number-weighted statistics, where the Saltykov method exhibits a systematic underestimation of the mean of approximately 27
