摘要
为了提高薄膜厚度测量对低信噪比光谱数据的稳定性,提出了一种基于自注意力神经网络(Self-Attention-based Neural Network,SANN)的测量方法。由于传统傅里叶变换方法在信噪比降低时噪声成分可能掩盖主要干涉频率,难以准确提取厚度信息,因此构建了一种以光谱数据为输入,薄膜厚度为输出的自注意力神经网络模型,利用自适应注意力机制对不同波长的光谱点赋予动态权重,以增强对低信噪比光谱数据的解析能力。采用光谱干涉膜厚测量系统采集实验数据,并通过波长偏移和光强归一化动态调整策略进行数据增强,用以扩充训练集并提高模型的泛化能力。该系统优化了基于自注意力机制的编码器层数及隐藏节点数,最终选定包含8层编码器、每层128个隐藏节点的模型。以晶圆为例进行验证,测试含有异常值的光谱数据集合,结果显示该模型在低信噪比测试集上的最大相对厚度测量误差为3.62%,证明该方法能有效抑制噪声影响,避免傅里叶变换方法中常见的异常值偏差,显著提升测量稳定性。所提方法可扩展至更广泛的薄膜测量应用中。
To enhance the robustness of film thickness measurements from low signal-to-noise ratio(SNR)spectral data,a measurement approach based on a self-attention neural network(SANN)is devel⁃oped.While the conventional Fourier transform method effectively measures thickness on high SNR data,its accuracy deteriorates as noise obscures the principal interference frequency under low SNR conditions,hindering precise thickness extraction.This study introduces a self-attention neural network model that takes spectral data as input and outputs film thickness,employing an adaptive attention mechanism to dynamically weight spectral points across different wavelengths,thereby improving analysis of low SNR spectral data.Experimental data were obtained using a spectral interference film thickness measurement system and subsequently augmented through wavelength drift and adaptive intensity normalization strategies to expand the dataset and enhance the model′s generalization.Model optimization identified an architecture comprising eight encoder layers and 128 hidden nodes per layer.Using wafer measurements as a case study,evaluation on spectral data containing outliers demonstrated a maximum relative thickness measurement error of 3.62%on the low SNR validation set.These results indicate that the proposed method effectively suppresses noise influence,mitigates outlier deviations common in Fourier transform approaches,and substantially improves measurement stability.the applicability of the proposed method is validated to a broader range of thin film measurement scenarios.
作者
王晨
王子政
刘曌燃
姚程源
胡春光
WANG Chen;WANG Zizheng;LIU Zhaoran;YAO Chengyuan;HU Chunguang(State Key Laboratory of Precision Measurement Technology and Instruments,Tianjin University,Tianjin 300072,China)
出处
《光学精密工程》
北大核心
2025年第9期1341-1352,共12页
Optics and Precision Engineering
基金
国家重点研发计划资助项目(No.2022YFF0708300)
国家自然科学基金面上项目(No.52475566)。
关键词
干涉测量
晶圆厚度
光谱干涉式
自注意力神经网络
抗噪声能力
测量稳定性
interferometric measurement
wafer thickness
spectral interference
self-attention neural network
anti-noise ability
measurement robustness
