Supercharge Your Innovation With Domain-Expert AI Agents!

Unlicensed proxy model generation

A technology that represents models and models, and is used in simulators, data processing applications, electrical digital data processing, etc.

Pending Publication Date: 2022-04-22
THE BOEING CO
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

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
  • Unlicensed proxy model generation
  • Unlicensed proxy model generation
  • Unlicensed proxy model generation

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0091] Example 1. A method performed by a proxy model node using the Functional Model Interface FMI standard to convert a proprietary model into a tool-agnostic proxy model, the method comprising the steps of: receiving the proprietary model as a functional model unit FMU; Perform automated dataset generation on the FMU to create input / output datasets based on experimental design and input requirements; determine steady-state operating points; generate tool-agnostic surrogate models based on input / output datasets and steady-state operating points; and The tool-agnostic surrogate model is exported as an output FMU model that is exempt from the licensing requirement for licensing of proprietary models.

example 2

[0092] Example 2. The method of example 1, further comprising the steps of: in response to any of the input requirements not being part of the FMU's metadata, in response to a user providing receiving a portion of input requirements, the input requirements including at least one of an input domain, a model accuracy, and a runtime performance requirement; and in response to the model accuracy or the runtime performance requirement not being part of the metadata and is not received, using a predetermined model accuracy when the model accuracy is not received, and using a predetermined runtime performance requirement when the runtime performance requirement is not received.

example 3

[0093] Example 3. The method of any one of examples 1-2, further comprising the step of validating the tool-agnostic proxy model.

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 license-free proxy model generation. Methods, nodes, and computer-readable media are provided for converting a proprietary model into a tool-agnostic proxy model using a Functional Model Interface (FMI) standard. A proprietary model is received as a functional model unit (FMU). Based on the experimental design and input requirements, automated dataset generation is performed on the FMU to create an input / output dataset. A steady state operating point is determined. A tool-agnostic proxy model is generated based on the input / output dataset and the steady-state operating point. The tool-agnostic proxy model is output as an output FMU model that exempts the permission requirements of the permission of the proprietary model. The tool-agnostic agent model may be a steady-state agent model, a dynamic agent model, or a combination thereof.

Description

technical field [0001] The present disclosure relates generally to autonomous model generation, and more particularly to methods and related apparatus that support autonomous model generation. In many product designs, including requirements validation and verification, engineering models are often used to represent product behavior and system behavior. These models are used in more aspects of product design. Models are also increasing in size and complexity to more accurately capture system behavior. Background technique [0002] Most engineering designs are developed using proprietary modeling tools licensed to model developers. Models are usually developed with their application in mind, and any use of the model has a direct impact on the quality of the model. For example, exhaustive system analysis requires the development of high-fidelity multiphysics models in order to extend system requirements and product requirements. [0003] Behavioral models are computationall...

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): G06F21/10G06F21/12
CPCG06F21/105G06F21/12G05B17/02G05B2219/25298G06Q40/12G06F30/20
Inventor P·范吉尔斯C·奥努尔
Owner THE BOEING CO
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com