发表机构
School of Mechanical Engineering, Hangzhou Dianzi University; Information Engineering School, Hangzhou Dianzi University（杭州电子科技大学机械工程学院; 杭州电子科技大学信息工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出PCINN混合代理模型，实现SALD覆盖率实时高精度预测，完成动力学可识别性分析，验证了 pipeline 自洽性与可识别性边界。
AI 中文摘要
空间原子层沉积（SALD）是工业原子层沉积（ALD）的主流大气压、高通量工艺路线，但其设计与控制受限于表面覆盖率预测的成本：高保真计算流体动力学（CFD）运算速度过慢，无法用于操作窗口扫描，而解析模型会忽略气幕等输运调制效应。本文提出一种基于物理化学信息的神经网络（PCINN），这是一种混合代理模型，兼具CFD级精度与实时运算速度：单次查询返回覆盖率仅需约7毫秒，比CFD求解快约5×10^4倍，仅用30个训练案例（覆盖率跨度达4个数量级）就达到测试R²_log=0.998（留一法R²_raw=0.974）。该架构并非黑箱：小型网络仅学习操作条件到近壁浓度的闭合关系，而已知的表面动力学是沿衬底轨迹集成的硬编码可训练化学层。这种单标量瓶颈使其在稀疏数据下仍保持精度，且具备可解释性与可反演性。本文补充了完整的可识别性分析（费舍尔信息、轮廓似然）：吸附能E_ads和解吸速率k_des可稳健识别；单温度下吸附速率k_ads无法单独识别（仅k_ads·c_wall可识别）；四个温度下，指前因子ν与E_ads沿斜率为0.065 eV/十年的弱可识别简并谷绑定，该斜率经解析推导为k_B T_eff ln(10)，并用作可靠性诊断：七化学失配矩阵显示其在任何单阿伦尼乌斯失配下不变，仅当出现第二个热激活过程时才会偏移，因此斜率偏离可标记未建模的位点异质性。本文数据来自模拟（已知真实值通过相同动力学形式反演），因此该研究验证了 pipeline 的自洽性与可识别性边界，而非真实参数。
英文摘要
Spatial atomic layer deposition (SALD) is a leading atmospheric-pressure, high-throughput route to industrial ALD, but design and control are limited by the cost of predicting surface coverage: high-fidelity CFD is far too slow for operating-window scans, while analytic models miss transport modulation such as the gas curtain. We present a physics-chemistry-informed neural network (PCINN), a hybrid surrogate with CFD-level accuracy at real-time speed: a query returns coverage in about 7 ms, roughly 5x10^4 times faster than a CFD solve, reaching a test R^2_log = 0.998 (leave-one-out R^2_raw = 0.974) from only 30 training cases spanning four orders of magnitude in coverage. The architecture is not a black box: a small network learns only the operating-condition to near-wall concentration closure, while the known surface kinetics is a hard-coded, trainable chemistry layer integrated along the substrate trajectory. This single-scalar bottleneck keeps it accurate under sparse data, interpretable and invertible. We add a full identifiability analysis (Fisher information, profile likelihood). The adsorption energy E_ads and desorption rate k_des are robustly identifiable; k_ads is not separately identifiable at a single temperature (only k_ads*c_wall is). Across four temperatures the prefactor nu and E_ads bind along a weakly identifiable degeneracy valley of slope 0.065 eV/decade, derived analytically as k_B T_eff ln(10) and turned into a reliability diagnostic: a seven-chemistry mismatch matrix shows it is invariant under any single-Arrhenius mismatch and shifts only when a second thermally activated process appears, so a slope departure flags unmodelled site heterogeneity. Data come from simulation with known ground truth inverted by the same kinetic form, so the study verifies pipeline self-consistency and the identifiability boundary, not real parameters.
Comments31 pages, 12 figures, 8 tables
