发表机构
Sukkur IBA University（苏库尔IBA大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对热成像视频深度回归的空间过拟合问题，提出时空解耦架构，采用正则化XGBoost实现0.056mm MAE的高精度测量，可快速生成三维缺陷模型。
AI 中文摘要
碳纤维增强聚合物（CFRP）中 subsurface delamination 深度的准确贯穿厚度测量对结构评估至关重要，因为缺陷位置决定了受影响的承重层。光学脉冲热成像（OPT）提供二维热视频而非体积测量，因此必须从时间热扩散响应中推断深度。一个挑战是空间数据集偏差：当校准缺陷遵循规则网格时，回归模型可能会记住其几何形状而非学习热衰减与深度之间的物理关系。本研究引入一种时空解耦架构，将空间缺陷定位与时间深度测量分离。首先使用分割方法定位缺陷区域，之后对热响应进行空间平均并转换为16个物理信息的时间、能量、统计和几何特征。这些特征揭示了一维热传导关系，同时向深度模型隐藏像素坐标。使用样本级交叉验证评估四种回归模型：随机森林（RF）、梯度提升机（GBM）、高级多层感知器（Adv-MLP）和XGBoost。未正则化的树和过参数化的Adv-MLP在几何偏移下表现出校准崩溃，误差超过0.5毫米。相比之下，带有L1/L2惩罚和列采样的正则化XGBoost保持了跨样本校准，达到平均绝对误差（MAE）为0.056毫米，均方根误差（RMSE）为0.085毫米。预测的深度与掩码合并，生成Delaunay三角剖分的三维缺陷模型，每个样本耗时3至5秒。结果表明，数学正则化和时空解耦减少了热视频深度回归中的空间记忆。
英文摘要
Accurate through-thickness measurement of subsurface delamination depth in Carbon Fiber Reinforced Polymer (CFRP) is important for structural assessment because defect location determines affected load-bearing layers. Optical pulsed thermography (OPT) provides a two-dimensional thermal video rather than volumetric measurements, so depth must be inferred from temporal heat-diffusion responses. A challenge is spatial dataset bias: when calibration defects follow regular grids, regression models may memorize their geometry instead of learning physical relationship between thermal decay and depth. This work introduces a spatio-temporal decoupling architecture that separates spatial defect localization from temporal depth measurement. Defect regions are first localized using segmentation methods, after which thermal responses are spatially averaged and converted into sixteen physics-informed temporal, energy, statistical, and geometric features. These features expose the one-dimensional heat-conduction relationship while withholding pixel coordinates from the depth model. Four regression models are evaluated using specimen-level cross-validation: Random Forest (RF), Gradient Boosting Machine (GBM), Advanced Multi-Layer Perceptron (Adv-MLP), and XGBoost. Unregularized trees and over-parameterized Adv-MLP exhibit calibration collapse under geometric shifts, with errors exceeding 0.5 mm. In contrast, regularized XGBoost with L1/L2 penalties and column sampling maintains cross-specimen calibration, achieving a mean absolute error (MAE) of 0.056 mm and root mean square error (RMSE) of 0.085 mm. Predicted depths are merged with masks to generate Delaunay-triangulated three-dimensional defect models in three to five seconds per specimen. Results show that mathematical regularization and spatio-temporal decoupling reduce spatial memorization in thermal-video depth regression.
