Convolutional Neural Networks for Multi-Stage Semiconductor Processes

In semiconductor manufacturing processes, there are certain quality measurements cannot be easily obtained at a low cost. In such cases, virtual metrology (VM) is typically used to predict the relevant quality variables without increasing the number of physical measurements. Faced with large volumes of raw data, the traditional data-driven VM methods adopt data pre-processing for feature extraction before modeling with a predefined model. However, if the constructed model and the extracted features are not suitable, the identified VM model is generally not reliable. Moreover, almost no VM model has been proposed for multi-stage raw data. To improve the prediction performance of VM models, it is imperative that only suitable features are chosen and used in the modeling, especially for multi-stage raw process data. In this paper, we developed a convolutional neural network (CNN) based on the VM model for multi-stage raw semiconductor data. Owing to the intrinsic nature of CNN, the cascade-connected convolving filters and the regression part are trained together to provide appropriate features for the final prediction. The construction of CNN makes it possible to reasonably extract information at each stage separately when processing multi-stage data. The proposed method is validated using real semiconductor process data and found to be superior to conventional methods with significantly improved accuracy.