Anomaly Detection Using Deep CNN-ELM in Semiconductor Manufacturing

In modern society, technology is constantly evolving. This technological advancement creates new demands from consumers. To meet the needs of consumers, companies must improve the quality of their products. Semiconductor manufacturing requires many processes and fine techniques. Because of these characteristics, small defects or anomaly values have a great influence on the semiconductor yield. However, defects can be prevented if an anomaly can be determined from data collected during the semiconductor manufacturing process. In this paper, we propose an anomaly detection model that combines the deep convolutional neural network and extreme learning machine network. The proposed model provides better performance in detecting anomalies in semiconductor manufacturing data by taking advantage of the two models. The results of the proposed model are compared and analyzed with a widely used anomaly detection model.