A novel hierarchical tree-DCNN structure for unbalanced data diagnosis in microelectronic manufacturing process

The quality of flexible integrated circuit substrates (FICS) is critical to the reliability of various electronic products, making intelligent defect measurement essential for efficient manufacturing and cost-saving. However, existing solutions for substrate defect diagnosis heavily rely on human visual interpretation, which leads to poor efficiency and a high error rate. A novel vision-based detection system consisting of a multi-scale imaging module and a hierarchical structure based on the deep convolution neural network (DCNN) is proposed in this paper. Rapid and accurate fault diagnosis can be enabled for high-density FICS, and various defects could be located and classified in a coarse-to-fine resolution. Specifically, a new mechanism of hierarchical decision based on DCNNs is built for FICS fault diagnosis, wherein the challenge of unbalanced data is addressed in the network learning process to reach a good trade-off between detection accuracy and speed. The substantial experiments and effectiveness comparison by using the typical methods on three categories of FICS and their corresponding eight-type faults reveal that the proposed system could facilitate the solution of substrate fault measurement and achieve high accuracy and efficiency, which could provide essential information of FICS to divide its industrial acceptance quality level.