Fault detection method and device, terminal equipment and storage medium

Abstract

The invention discloses a fault detection method and device, terminal equipment and a storage medium. The method is used for detecting a fault in a semiconductor wafer manufacturing process, and comprises the steps: obtaining monitoring signal data in a semiconductor wafer manufacturing process; performing feature extraction on the monitoring signal data to obtain a target general signal in the semiconductor wafer manufacturing process; and detecting whether a fault exists in the semiconductor wafer manufacturing process according to the target general signal. According to the method, full-automatic feature extraction of signal data collected in the semiconductor wafer manufacturing process can be achieved, dependence on expert experience in fault detection is reduced, key features of monitoring signal data in the semiconductor manufacturing process can be reserved through the extracted target summarized signal, and feature information is prevented from being lost, so that the fault detection precision in the semiconductor manufacturing process is improved.

Description

technical field [0001] The invention relates to the technical field of semiconductor manufacturing, in particular to a fault detection method, device, terminal equipment and storage medium. Background technique [0002] With the continuous development of sensors and information technology, the modern semiconductor industry mostly uses advanced process control to monitor the production process and production equipment to determine whether there is a fault in the semiconductor production process, and then initially judge whether the manufactured semiconductor is qualified. However, due to the complexity and dynamics of the semiconductor manufacturing process, the existing fault detection methods rely too much on expert experience when modeling, and require manual processing and feature extraction of the collected data, which is not only time-consuming but also extremely costly. Furthermore, conventional feature extraction methods based on expert experience will inevitably caus...

AI Technical Summary

Problems solved by technology

[0003] The main purpose of the present invention is to provide a fault detection method, device, terminal equipment and storage medium, aiming to solve the technical problem of manual feature extraction in the fault detection method in the semiconductor manufacturing process, resulting in loss of features and affecting the accuracy of fault detection

Images