Wafer map defect recognition based on deep transfer learning-based densely connected convolutional network and deep forest

Abstract

Due to the complexity and dynamics of the semiconductor manufacturing processes, wafer maps will present various defect patterns caused by various process faults. Identification of those defect patterns on wafer maps can help operators in finding out root-causes of abnormal processes, and then ensures that the manufacturing process is restored to the normal state as soon as possible. This paper proposes a wafer map defect recognition (WMDR) model based on integration of deep transfer learning and deep forest. Firstly, we transfer the network weight parameters of ImageNet to the convolutional neural network (CNN) (i.e., densely connected convolutional network (DenseNet)) and redesign the classification layer. This reduces the training time and then improves feature learning performance of DenseNet. Moreover, the transfer learning-based feature learning is able to solve class imbalance of wafer defect patterns. Finally, deep forest is utilized to identify the wafer defect pattern based on the abstract features from the wafer maps extracted by DenseNet. The experimental results on an industrial case show that the method can effectively improve WMDR performance and outperforms those well-known CNNs and other typical classifiers.