CDSEM image virtual measurement method based on machine learning

Abstract

The invention discloses a CDSEM image virtual measurement method based on machine learning, and the method comprises the steps of generating a training set and a verification set, enabling a photoetching space image to be aligned with a CDSEM image, employing a neural network model, enabling the photoetching space image to serve as the input, enabling the CDSEM image corresponding to the photoetching space image to serve as the target output, and traversing N1 groups of photoetching space image-CDSEM image data pairs in the training set to complete training of the neural network model; and traversing N2 groups of photoetching space image-CDSEM image data pairs in the verification set to complete verification of the neural network model. According to the invention, the mapping between the photomask pattern after OPC and the CDSEM image after the photoetching process is established, so that the CDSEM image is generated by adopting machine learning, and the verification model independentof the OPC model is obtained and is used for confirming the quality of the pattern after photoetching.

Description

Technical field [0001] The present invention belongs to the manufacture of semiconductor integrated circuits, and involves a CDSEM image virtual measurement method based on machine learning. Background technique [0002] In the photolithography process manufactured by the semiconductor integrated circuit, for a given pattern, in the case where the photolithography focus and dose determination, the photoresist image map (Aerial Image) is also determined. In the case of photoresist determination, the three-dimensional structure after photoresist development is determined, and the CDSEM image captured by the scanning electromtronic microscope, SEM is also determined, and the CDSEM image is usually confirmed. The quality of the photolithography is finally passed. [0003] Typically, in the photolithography process, in order to improve the quality of the graphic of the photolithography process, it is necessary to perform an optical proximity correction (OPC) for manufacturing the grap...

AI Technical Summary

Problems solved by technology

Moreover, due to the limitation of resolution, the pattern after EUV lithography needs to use an electron beam scanner (E-beam) to scan whether there are defects in the pattern after the lithography process on the wafer, and due to the design constraints of the electron beam scanner , the electron beam scanner cannot detect defects through the die-to-die inter-chip inspection mode, but can only detect defects through the die-to-database chip-to-database inspection mode

That is to say, the current EUV defect detection is realized by comparing the CDSEM image and the OPC target geometry. Such an implementation is not the best method

Images