Tchatchoua Philip, Graton Guillaume, Ouladsine Mustapha, Christaud Jean-François
LIS, CNRS, Aix Marseille University, University of Toulon, 13007 Marseille, France.
STMicroelectronics, 13106 Rousset, France.
Sensors (Basel). 2023 Nov 10;23(22):9099. doi: 10.3390/s23229099.
Amid the ongoing emphasis on reducing manufacturing costs and enhancing productivity, one of the crucial objectives when manufacturing is to maintain process tools in optimal operating conditions. With advancements in sensing technologies, large amounts of data are collected during manufacturing processes, and the challenge today is to utilize these massive data efficiently. Some of these data are used for fault detection and classification (FDC) to evaluate the general condition of production machinery. The distinctive characteristics of semiconductor manufacturing, such as interdependent parameters, fluctuating behaviors over time, and frequently changing operating conditions, pose a major challenge in identifying defective wafers during the manufacturing process. To address this challenge, a multivariate fault detection method based on a 1D ResNet algorithm is introduced in this study. The aim is to identify anomalous wafers by analyzing the raw time-series data collected from multiple sensors throughout the semiconductor manufacturing process. To achieve this objective, a set of features is chosen from specified tools in the process chain to characterize the status of the wafers. Tests on the available data confirm that the gradient vanishing problem faced by very deep networks starts to occur with the plain 1D Convolutional Neural Network (CNN)-based method when the size of the network is deeper than 11 layers. To address this, a 1D Residual Network (ResNet)-based method is used. The experimental results show that the proposed method works more effectively and accurately compared to techniques using a plain 1D CNN and can thus be used for detecting abnormal wafers in the semiconductor manufacturing industry.
在持续强调降低制造成本和提高生产率的背景下，制造过程中的一个关键目标是将工艺工具保持在最佳运行状态。随着传感技术的进步，制造过程中会收集大量数据，而如今的挑战是有效利用这些海量数据。其中一些数据用于故障检测与分类（FDC），以评估生产机械的总体状况。半导体制造的独特特性，如相互依存的参数、随时间波动的行为以及频繁变化的运行条件，在制造过程中识别有缺陷的晶圆时构成了重大挑战。为应对这一挑战，本研究引入了一种基于一维残差网络（ResNet）算法的多变量故障检测方法。其目的是通过分析在整个半导体制造过程中从多个传感器收集的原始时间序列数据来识别异常晶圆。为实现这一目标，从工艺链中的特定工具中选择一组特征来表征晶圆的状态。对现有数据的测试证实，当基于普通一维卷积神经网络（CNN）的方法网络深度超过11层时，非常深的网络所面临的梯度消失问题就会开始出现。为解决这一问题，采用了基于一维残差网络（ResNet）的方法。实验结果表明，与使用普通一维CNN的技术相比，该方法工作得更有效、更准确，因此可用于检测半导体制造业中的异常晶圆。
