Generative Pre-Training of Time-Series Data for Unsupervised Fault Detection in Semiconductor Manufacturing

arXiv:2309.11427v2 Announce Type: replace
Abstract: This paper introduces TRACE-GPT, which stands for Time-seRies Anomaly-detection with Convolutional Embedding and Generative Pre-trained Transformers. TRACE-GPT is designed to pre-train univariate time-series sensor data and detect faults on unlabeled datasets in semiconductor manufacturing. In semiconductor industry, classifying abnormal time-series sensor data from normal data is important because it is directly related to wafer defect. However, small, unlabeled, and even mixed training data without enough anomalies make classification tasks difficult. In this research, we capture …

abstract anomaly arxiv cs.ai cs.lg data datasets detection embedding generative gpt industry manufacturing paper pre-training semiconductor semiconductor manufacturing sensor series train training transformers type unsupervised