Unsupervised wafer defect detection method, device and equipment and storage medium

• Main Authors: YANG WANLI, WANG WEI, DUAN JIANGWEI, BI HAI, KE LIANBAO
• Format: Patent
• Language: Chinese; English
• Published: 02.09.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIRCHEMICAL OR PHYSICAL PROPERTIES; MEASURING; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; TESTING

The invention belongs to the technical field of wafer detection, and discloses an unsupervised wafer defect detection method, device and equipment and a storage medium. The method comprises the following steps: acquiring an initial wafer detection data set; making a pseudo label for the label-free wafer detection data in the initial wafer detection data set by using a preset unsupervised auto-encoder, and generating a target wafer detection data set; training a preset classifier according to the target wafer detection data set to obtain a trained target classifier; and when the to-be-detected wafer data is received, detecting the to-be-detected wafer data by using the target classifier to obtain a wafer defect detection result. Through the above mode, the pseudo label is made for the label-free wafer detection data, and the target classifier is trained by using the label data and the pseudo label data, so that the target classifier learns different defect features and can identify unknown defect types, and th