Machine learning method, system and equipment for metasurface lens design and medium

A lens design and machine learning technology, applied in the field of nanophotonics, can solve the problems of large computing resource consumption, large resource consumption, and long design cycle, etc., to reduce time and hardware resource costs, strong universal applicability, and short design cycle Effect

Pending Publication Date: 2022-06-17
TSINGHUA UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The design of metasurface lenses based on traditional methods also faces the problems of long design cycle and large resource consumption.
[0004] In summary, existing metasurface lens designs have problems such as high computational resource consumption, long simulation cycle, and low efficiency.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Machine learning method, system and equipment for metasurface lens design and medium
  • Machine learning method, system and equipment for metasurface lens design and medium
  • Machine learning method, system and equipment for metasurface lens design and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045]Embodiment 1: This embodiment completes the establishment of a large-scale performance database for the functional primitives constituting the metasurface lens through machine learning and the optimization of the functional primitives to complete the design of the metasurface lens, including:

[0046] S1. The establishment of the database based on the training of the neural network: by constructing and training the neural network, the basic properties of the functional primitives (including geometric features and materials) and the optical effects (including the output phase, group delay, etc.), and finally establish a performance database of large-scale functional primitives. The implementation process includes:

[0047] S11. Delineate the scope of the functional primitives according to the requirements and the basic attributes of the functional primitives.

[0048] Specifically, the basic properties of functional primitives include but are not limited to size, symmetry...

Embodiment 2

[0082] Embodiment 2: The above Embodiment 1 provides a machine learning method for designing a metasurface lens, and correspondingly, this embodiment provides a machine learning system for designing a metasurface lens. The system provided in this embodiment may implement the machine learning method for metasurface lens design in Embodiment 1, and the system may be implemented by software, hardware, or a combination of software and hardware. For the convenience of description, when describing this embodiment, the functions are divided into various units and described respectively. Of course, during implementation, the functions of each unit may be implemented in one or more software and / or hardware. For example, the system may include integrated or separate functional modules or functional units to perform corresponding steps in each method of the first embodiment. Since the system of this embodiment is basically similar to the method embodiment, the description process of thi...

Embodiment 3

[0086] Embodiment 3: This embodiment provides an electronic device corresponding to the machine learning method for metasurface lens design provided in Embodiment 1. The electronic device may be an electronic device used for a client, such as a mobile phone, a A tablet computer, a desktop computer, etc., to execute the method of the first embodiment.

[0087] like Image 6 As shown, the electronic device includes a processor, a memory, a communication interface and a bus, and the processor, the memory and the communication interface are connected through the bus to complete mutual communication. The bus may be an Industry Standard Architecture (ISA, Industry Standard Architecture) bus, a Peripheral Component Interconnect (PCI, Peripheral Component) bus or an Extended Industry Standard Architecture (EISA, Extended Industry Standard Component) bus and the like. A computer program that can be run on the processor is stored in the memory, and the processor executes the machine le...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a machine learning method, system and device for metasurface lens design and a medium, and the method comprises the steps: obtaining a relation between basic attributes of functional elements and optical effects which can be generated by the functional elements through constructing and training a neural network, and building a performance database of the functional elements; and optimizing the required target function element in the performance database by using a particle swarm optimization algorithm to complete the design of the metasurface lens. Compared with the existing metasurface lens design related to machine learning, the machine learning method provided by the invention is the only method for determining the excellent performance of the designed metasurface lens through experimental verification, and the performance of the metasurface lens designed by the method is higher than that of the metasurface lens designed by a traditional numerical method.

Description

technical field [0001] The invention relates to a machine learning method, system, equipment and medium for metasurface lens design, and relates to the field of nanophotonics. Background technique [0002] In the optical system, the lens is an extremely important component, which plays an important role in mobile phone cameras, microscopes, cameras, and laser processing. The lens shape and material dispersion seriously affect the image quality of the lens system, and optical error correction is required. In traditional optics, chromatic aberration correction is achieved by selecting different lens materials by combining multiple lenses, but the volume and weight of the system inevitably increase, which limits the requirements for miniaturization and integration of optical imaging systems. [0003] Metasurface is a new type of two-dimensional metamaterial composed of a single layer of functional primitives. The height of the functional primitives is generally smaller than th...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/27G06F119/02
CPCG06F30/27G06F2119/02
Inventor 孙竞博王斐镂周济
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap