Lithium niobate metasurface defect intelligent identification method based on reactive ion beam etching

By establishing a multimodal image database of lithium niobate metasurfaces, designing domain-specific convolutional kernels and embedding physical constraints, and constructing a self-supervised learning model, the problem of insufficient feature capture in the defect identification of lithium niobate metasurfaces by existing models is solved, and efficient defect identification and process optimization are achieved.

CN121545153AActive Publication Date: 2026-02-17NAT UNIV OF DEFENSE TECH
4 Cites 3 Cited by

Patent Information

Application Number
CN202610063287.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-01-19
Publication Date
2026-02-17
Estimated Expiration
2046-01-19

AI Technical Summary

Technical Problem

Existing ImageNet-pretrained CNN models cannot effectively capture the phase information of metasurface periodic structures, subtle changes in etching depth, and material anisotropy characteristics in lithium niobate metasurface defect identification, resulting in poor identification performance.

Method used

By collecting multimodal image data, a ternary association database of images to parameters is established, domain-specific convolutional kernels are designed, physical constraints are embedded, a self-supervised learning model is constructed, and multi-scale feature fusion and domain adaptive transfer learning are realized. The sample labeling process is optimized to form a closed-loop control.

Benefits of technology

It improves the accuracy and generalization ability of lithium niobate metasurface defect identification, reduces data acquisition costs, enhances the model's generalization ability under unseen process conditions, and realizes intelligent manufacturing with real-time defect identification and process optimization.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of industrial detection, and discloses a lithium niobate metasurface defect intelligent identification method based on reactive ion beam etching, which systematically solves the problem of scarcity of experimental data through physical driving simulation and a physics-based rendering algorithm, and provides large-scale field specific training data for a deep learning model. The bidirectional coupling simulation model generates defect morphology prediction data conforming to an etching dynamics law based on real process parameters and material parameters, the prediction data is converted into a synthetic image with real microscopic image statistical characteristics by a physical rendering algorithm, and the quality and consistency of the synthetic data are ensured by an automatic labeling and statistical verification process. According to the method, the number of samples of the ternary association database is multiplied, and extreme process conditions and rare defect modes which are difficult to obtain through experimental collection are covered.
Need to check novelty before this filing date? Find Prior Art