AI 中文总结
本文提出首个覆盖三种几何构型的端到端可微分HEDM正向模型，基于PyTorch实现，经三项演示验证有效，以开源midas-diffract包发布，可实现高精度参数重构与优化。
AI 中文摘要
高能衍射显微术（High-Energy Diffraction Microscopy, HEDM）可从旋转晶体X射线衍射图样中重构晶体学取向、应变和晶粒位置。现有远场（far-field, FF）、近场（near-field, NF）和点聚焦（point-focused, pf）HEDM的正向模型均不可微分，无法实现基于梯度的联合参数优化、物理信息正则化及贝叶斯不确定性量化。本文提出首个覆盖上述三种几何构型的端到端可微分HEDM正向模型，基于PyTorch实现，与成熟的MIDAS参考模拟器像素级一致：162/162个FF-HEDM、2304/2304个含非零探测器倾斜扫描的NF-HEDM、1088/1096个pf-HEDM斑点均匹配。三项演示验证了该框架的有效性：NF-HEDM中取向-应变-位置联合重构精度约6 nm；对真实含214个晶粒的α-Ti FF-HEDM数据集进行往返优化，从1.5度初始扰动实现100%晶粒恢复，残差与生产拟合的偏差达0.3%；对合成四面板FF-HEDM装置的所有探测器几何参数与晶粒状态进行联合优化，恢复面板绕束轴的旋转精度约10 μrad，全局旋转轴楔角精度约26 μrad。该框架以开源midas-diffract包形式发布（pip install midas-diffract）。
英文摘要
High-Energy Diffraction Microscopy (HEDM) recovers crystallographic orientation, strain, and grain position from rotating-crystal X-ray diffraction patterns. Existing forward models in far-field (FF), near-field (NF), and point-focused (pf) HEDM are not differentiable, which forecloses gradient-based joint parameter refinement, physics-informed regularisation, and Bayesian uncertainty quantification. We present the first end-to-end differentiable HEDM forward model covering all three geometries, implemented in PyTorch with pixel-exact agreement against the established MIDAS reference simulators (162/162 FF, 2304/2304 NF including a non-zero detector-tilt sweep, and 1088/1096 pf-HEDM spots matched). Three demonstrations validate the framework: joint orientation-strain-position recovery in NF-HEDM at ~6 nm precision; round-trip refinement on a real 214-grain alpha-Ti FF-HEDM dataset reaching 100% grain recovery from a 1.5 degree initial perturbation with residuals matching the production fit to 0.3%; and joint refinement of all per-detector geometry parameters and per-grain state on a synthetic four-panel FF-HEDM setup, recovering panel rotations about the beam axis to ~10 mu-rad and a global rotation-axis wedge to ~26 mu-rad. The framework is released as the open-source midas-diffract package (pip install midas-diffract).
