Semiconductor packaging process early warning method and device based on time sequence generative adversarial network

Abstract

The invention provides a semiconductor packaging process early warning method and device based on a time sequence generative adversarial network, and relates to the technical field of data processing,and the method comprises the steps: obtaining monitoring data, carrying out the preprocessing of the monitoring data, and obtaining training data; obtaining a normal sample set from the training data, calculating a density function of the normal sample set, and estimating an abnormal threshold according to the density function; obtaining a trained generator network, and generating a predeterminednumber of abnormal samples by using the trained generator network; and mixing a predetermined number of abnormal samples and the training data and then inputting the mixed abnormal samples and the training data into a neural network for training, so that in the semiconductor packaging process, the key process parameters are input into the trained neural network to obtain an abnormal prediction value, and early warning processing is carried out according to the abnormal prediction value and an abnormal threshold value. Therefore, the abnormal samples are generated and mixed to the training data for training, the abnormal threshold value is determined to realize early warning of production abnormality in advance, and the product yield and the production line efficiency are improved.

Description

technical field [0001] The present application relates to the technical field of data processing, and in particular to a semiconductor packaging process early warning method and device based on sequential generative adversarial networks. Background technique [0002] Semiconductor packaging is a very important part of the semiconductor manufacturing chain, with various related equipment and complex processes. In the production process, occasional production abnormalities will cause product quality defects, reduce product yield, and cause economic losses. Reliable abnormal early warning, that is, to predict the occurrence of abnormalities in advance, it can provide sufficient response time for production line operators, provide meaningful information for decision-making of production line maintenance, reduce losses in the production process, and improve product yield, which is very important industrial application value. Due to the many steps in the production process, the ...

AI Technical Summary

Problems solved by technology

However, most of the existing data-driven anomaly prediction methods are limited to the prediction of the remaining service life of the equipment, lack of abnormal early warning research in the semiconductor manufacturing process, and even less research on the packaging process

Images