用深度学习同时预测表面纹理参数和不确定度，支持仪器选型决策。
Multi-Task Deep Learning for Surface Metrology
- 多任务框架联合回归纹理参数与不确定度，引入分位数与异方差头建模不确定性。
- 单目标模型在Ra、Rz、RONt预测上R²超0.98，不确定度预测也达0.99以上，除RONt_uncert外均表现优异。
- 结果经校准后可用于实际测量流程中的仪器选择与验收，适合工业计量场景使用。
本文提出一种可复现的深度学习框架，用于表面计量学中同时预测表面纹理参数及其报告的标准不确定度。基于涵盖触觉与光学系统的多仪器数据集，该方法解决了测量系统类型分类问题，并协同回归Ra、Rz、RONt及其对应的不确定度目标（Ra_uncert、Rz_uncert、RONt_uncert）。通过分位数与异方差头部建模不确定度，并采用事后共形校准生成校准区间。在独立测试集上，单目标回归器取得高保真度：Ra（R²=0.9824）、Rz（R²=0.9847）、RONt（R²=0.9918）表现优异；两个不确定度目标也良好拟合（Ra_uncert R²=0.9899，Rz_uncert R²=0.9955），但RONt_uncert仍较困难（R²=0.4934）。分类器准确率达92.85%，温度缩放后概率校准基本不变（ECE从0.00504降至0.00503）。朴素多输出主干出现负迁移，单目标模型表现更优。结果提供可校准的预测，适用于计量工作流中的仪器选择与接受决策。
原文摘要 · Abstract (English)
A reproducible deep learning framework is presented for surface metrology to predict surface texture parameters together with their reported standard uncertainties. Using a multi-instrument dataset spanning tactile and optical systems, measurement system type classification is addressed alongside coordinated regression of Ra, Rz, RONt and their uncertainty targets (Ra_uncert, Rz_uncert, RONt_uncert). Uncertainty is modelled via quantile and heteroscedastic heads with post-hoc conformal calibration to yield calibrated intervals. On a held-out set, high fidelity was achieved by single-target regressors (R2: Ra 0.9824, Rz 0.9847, RONt 0.9918), with two uncertainty targets also well modelled (Ra_uncert 0.9899, Rz_uncert 0.9955); RONt_uncert remained difficult (R2 0.4934). The classifier reached 92.85% accuracy and probability calibration was essentially unchanged after temperature scaling (ECE 0.00504 -> 0.00503 on the test split). Negative transfer was observed for naive multi-output trunks, with single-target models performing better. These results provide calibrated predictions suitable to inform instrument selection and acceptance decisions in metrological workflows.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。