초록 ▼

A laser repair method includes a repair process of performing repair work by setting a laser radiation range for a defect part in a multi-layer film substrate and irradiating the defect part with a laser beam under set laser working conditions. In the repair process, spectrum data of the defect part

A laser repair method includes a repair process of performing repair work by setting a laser radiation range for a defect part in a multi-layer film substrate and irradiating the defect part with a laser beam under set laser working conditions. In the repair process, spectrum data of the defect part is acquired, and the laser working conditions of the laser beam, with which the defect part is to be irradiated, are set using a neural network after learning on the basis of the spectrum data, and the neural network has undergone machine learning using, as learning data, measurement data including multi-layer film structure data, spectrum data of each multi-layer film structure, and laser working experimental data of each multi-layer film structure.

대표청구항 ▼

1. A laser repair method comprising: a repair process of performing repair work by setting a laser radiation range for a defect part in a multi-layer film substrate and irradiating the defect part with a laser beam under set laser working conditions, whereinin the repair process, spectrum data of th

1. A laser repair method comprising: a repair process of performing repair work by setting a laser radiation range for a defect part in a multi-layer film substrate and irradiating the defect part with a laser beam under set laser working conditions, whereinin the repair process, spectrum data of the defect part is acquired, and the laser working conditions of the laser beam, with which the defect part is to be irradiated, are set using a neural network after learning on the basis of the spectrum data, andthe neural network has undergone machine learning using, as learning data, measurement data including multi-layer film structure data, spectrum data of each multi-layer film structure, and laser working experimental data of each multi-layer film structure. 2. The laser repair method according to claim 1, wherein the spectrum data of the defect part is acquired for each pixel of a defect part image, and the laser working conditions are set for each pixel at a laser scanning position in the defect part image. 3. The laser repair method according to claim 1, wherein the multi-layer film substrate has a two-dimensional periodic pattern,a position of the defect part is identified from a result of an inspection process performed prior to the repair process,a periodic pattern image including the defect part is compared with a periodic pattern image that does not include the defect part to identify a shape of the defect part, andthe laser radiation range is set to include the identified shape of the defect part. 4. The laser repair method according to claim 3, wherein the shape of the defect part is identified by a machine learning model after learning on the basis of the periodic pattern image including the defect part, and the machine learning model has learned, as learning data, a periodic pattern image of the multi-layer film substrate. 5. A laser repair device comprising: a repair work part that performs repair work by setting a laser radiation range for a defect part in a multi-layer film substrate and irradiating the defect part with a laser beam under set laser working conditions, whereinthe repair work part is adapted to acquire spectrum data of the defect part and set the laser working conditions of the laser beam, with which the defect part is to be irradiated, using a neural network after learning on the basis of the spectrum data, andthe neural network has undergone machine learning using, as learning data, measurement data including multi-layer film structure data, spectrum data of each multi-layer film structure, and laser working experimental data of each multi-layer film structure. 6. The laser repair device according to claim 5, wherein the repair work part includes: an image acquiring part that acquires a defect part image via a microscope,a laser radiation part that irradiates the defect part with a laser beam through the microscope,a spectral camera that irradiates the multi-layer film substrate with white incident light that is coaxial with the microscope, separates reflected light from the multi-layer film substrate, and acquires the spectrum data of each pixel, anda laser control part that controls the laser working conditions, andthe laser control part sets the laser working conditions for each pixel at a laser scanning position in the defect part image. 7. The laser repair method according to claim 2, wherein the multi-layer film substrate has a two-dimensional periodic pattern,a position of the defect part is identified from a result of an inspection process performed prior to the repair process,a periodic pattern image including the defect part is compared with a periodic pattern image that does not include the defect part to identify a shape of the defect part, andthe laser radiation range is set to include the identified shape of the defect part. 8. The laser repair method according to claim 7, wherein the shape of the defect part is identified by a machine learning model after learning on the basis of the periodic pattern image including the defect part, and the machine learning model has learned, as learning data, a periodic pattern image of the multi-layer film substrate.