image
image
user-login
Patent search/

SYSTEM AND METHOD FOR GENERATION OF INPUT DATA FOR FINITE ELEMENT ANALYSIS OF STRUCTURES

search

Patent Search in India

  • tick

    Extensive patent search conducted by a registered patent agent

  • tick

    Patent search done by experts in under 48hrs

₹999

₹399

Talk to expert

SYSTEM AND METHOD FOR GENERATION OF INPUT DATA FOR FINITE ELEMENT ANALYSIS OF STRUCTURES

ORDINARY APPLICATION

Published

date

Filed on 14 November 2024

Abstract

ABSTRACT “SYSTEM AND METHOD FOR GENERATION OF INPUT DATA FOR FINITE ELEMENT ANALYSIS OF STRUCTURES” The present invention provides system and method for generation of input data for finite element analysis of structures using Generative AI and LLMs. The method includes dynamically developing policies and configurations for vibration testing, which are used to generate test data, validate the data, and perform analysis. Using retrieval-augmented generation (RAG) and LLMs, the system generates and validates synthetic data for structural vibration tests, ensuring the data meets predefined test conditions. If necessary, feedback is provided to refine data generation until valid test cases are achieved. The invention also includes a system for managing test cases, configuring analysis parameters, and automating the process of vibration testing, ensuring accurate and reliable results for structural analysis. Figure 1

Patent Information

Application ID202431088196
Invention FieldCOMPUTER SCIENCE
Date of Application14/11/2024
Publication Number47/2024

Inventors

NameAddressCountryNationality
Dr. Chinmay Kumar KunduKalinga Institute of Industrial Technology (Deemed to be University), Patia Bhubaneswar Odisha India 751024IndiaIndia

Applicants

NameAddressCountryNationality
Kalinga Institute of Industrial Technology (Deemed to be University)Patia Bhubaneswar Odisha India 751024IndiaIndia

Specification

Description:TECHNICAL FIELD
[0001] The present invention relates to the field of artificial intelligence and automated systems, and more particularly, the present invention relates to the system and method for generation of input data for finite element analysis of structures using Generative AI and LLMs.
BACKGROUND ART
[0002] The following discussion of the background of the invention is intended to facilitate an understanding of the present invention. However, it should be appreciated that the discussion is not an acknowledgment or admission that any of the material referred to was published, known, or part of the common general knowledge in any jurisdiction as of the application's priority date. The details provided herein the background if belongs to any publication is taken only as a reference for describing the problems, in general terminologies or principles or both of science and technology in the associated prior art.
[0003] Finite elements are extensively used in all branches of engineering, aerospace space applications, even bio-medical simulation and analysis. Correct simulation and analysis resulting for best products is needed to develop for the society. Given a structure, in order to carry out its structural analysis such as static or vibration analysis, input data is necessary to be given to the system that carries out computational finite element analysis. Input data is essential to carry out various types of analysis and tests of structures. The types of analysis are deflection, stress calculation, buckling, free vibration, transient analysis etc. For any type of finite element analysis, finite element mesh or discretization of the structures to be done.
[0004] In this invention, we focus on how to automatically run the FEM-based structural analysis process. It is expensive, inefficient and sometimes almost impossible to have the finite element data that is necessary to carry out the correct set of analysis using finite element methods. Apart from user defined geometrical and material data, manual finite element meshing is very time laborious, expensive, time consuming, sometimes bad and erroneous elements are used and are generated by software or user written codes. Sometimes the elements have discontinuity and gaps between elements. What is also needed is: correct selection of finite elements, Proper discretization of whole structures without any error with accurate elements, proper assignment of material data to the finite elements, application of boundary conditions and application of loads, in all steps.
[0005] If the finite element mesh and other processing data can be generated by AI, then it would save a lot of resources, time and project costs. Finally, design and analysis then manufacturing of any structural components can be done effectively. First proper finite element to be selected for a specific structure and nodal connectivity of each element must be generated along with following data.
[0006] Some of the input data to a finite element are as follows:
- Geometric data
- length width thickness
- Material data
- Type materials
- Young's modulus, shear modulus, Bulk modulus, Poisson's ratio
- Mass density of materials- \rho = m/v
- Composite materials
- Number of Layers
- Input for each layer: fiber angle, fiber and matrix type
- Young's modulus, Shear modulus, Bulk modulus, Poisson's ratio
- Boundary Conditions or Restraints or Supports
- Roller Support
- Hinge support
- Fixed support
[0007] In light of the foregoing, there is a need for System and method for generation of input data for finite element analysis of structures using Generative AI and LLMs that overcomes problems prevalent in the prior art associated with the traditionally available method or system, of the above-mentioned inventions that can be used with the presented disclosed technique with or without modification.
[0008] All publications herein are incorporated by reference to the same extent as if each individual publication or patent application were specifically and individually indicated to be incorporated by reference. Where a definition or use of a term in an incorporated reference is inconsistent or contrary to the definition of that term provided herein, the definition of that term provided herein applies, and the definition of that term in the reference does not apply.
OBJECTS OF THE INVENTION
[0009] The principal object of the present invention is to overcome the disadvantages of the prior art by providing system and method for generation of input data for finite element analysis of structures using Generative AI and LLMs.
[0010] Another object of the present invention is to provide system and method for generation of input data for finite element analysis of structures using Generative AI and LLMs that provides a system and method for generating input data for finite element analysis (FEA) of structures, leveraging generative AI and large language models (LLMs) to automate and enhance the data generation process.
[0011] Another object of the present invention is to provide system and method for generation of input data for finite element analysis of structures using Generative AI and LLMs that enables the dynamic development and modification of policies and configurations for vibration testing, ensuring flexible and adaptive input data generation for different structural analysis scenarios.
[0012] Another object of the present invention is to provide system and method for generation of input data for finite element analysis of structures using Generative AI and LLMs that improves the accuracy and reliability of vibration test data by using AI-based validation mechanisms that ensure compliance with predefined test conditions and boundary values.
[0013] Another object of the present invention is to provide system and method for generation of input data for finite element analysis of structures using Generative AI and LLMs that facilitates the automation of the vibration testing process by integrating generative AI for the generation of synthetic test data, including vibration test parameters and associated steps, and validating the data automatically.
[0014] Another object of the present invention is to provide system and method for generation of input data for finite element analysis of structures using Generative AI and LLMs that enhances the efficiency of the finite element analysis by providing a mechanism that automatically adjusts the testing approach based on past results, ensuring unique data generation and optimal test case execution.
[0015] Another object of the present invention is to provide system and method for generation of input data for finite element analysis of structures using Generative AI and LLMs that provides a system for seamless integration with existing structural analysis systems, enabling the transfer, storage, and management of generated data for use in subsequent test cases and analyses.
[0016] Another object of the present invention is to provide system and method for generation of input data for finite element analysis of structures using Generative AI and LLMs that enables the use of retrieval-augmented generation (RAG) techniques in creating context-based prompts for AI models, improving the quality and relevance of generated test data for vibration testing.
[0017] The foregoing and other objects of the present invention will become readily apparent upon further review of the following detailed description of the embodiments as illustrated in the accompanying drawings.
SUMMARY OF THE INVENTION
[0018] The present invention relates to system and method for generation of input data for finite element analysis of structures using Generative AI and LLMs. We also present a method for generating the policy and configurations as in the above flowchart first and second blocks of statements.
[0019] Develop Policies and configurations: For structural analysis add to the policy: boundary conditions such as on how it is supported. Analysis type and parameters are specified as rules in a policy per analysis type. There is one or more policy that specifies what large language model to use (such as GPT4.0, Gemini, other AI models), to use them parallel. Analysis cases are specified in a configuration file. How to store or transfer the output in files, or in APIs, or in memory or sending it to directly to another system are specified in the configuration file.
[0020] The policies and configuration can be modified dynamically and the dynamic changes are taken into effect by AI models and the system after the current running is completed. Generate values for each parameter for each type of vibration testing using generative AI and large language models.
[0021] Method 1:
1. If a parameter type is a matrix of n dimensions, and m columns and r rows, then a prompt is issued to an LLM to generate that matrix for 'k' different values.
2. Validate that the generated values for a parameter satisfies a test condition.
Validate the matrices by carrying out matrix validation techniques.
a. Using LLMs as self-introspection engines: ask the LLM to validate the values using the policies as input in the prompt
b. Using LLMs as validation for data generated by others: ask the LLM to validate the values using the policies as input in the prompt
3. If the generated values match the test conditions, or boundary value conditions for testing, then transfer them as mentioned in configuration files.
4. If the test conditions are not required or met, the LLMs are informed not to generate data for such test conditions
[0022] Method 2: This method describes the next set of blocks.
1. Input the type of the structural component to be tested
2. What is the type of vibration test to be carried out
3. What tests have been carried out already
4. Optional: what data or test cases did you use
5. What is the level l(s) of testing being requested
6. What is the format of the output data to be generated for test case
7. Create a prompt for an LLM using this input for carrying out vibration analysis using RAGs and chain-of-thought process.
8. Send it to the LLM selected.
9. Get the output
10. Save the synthetic data for test case
11. Ask the LLM for the testing steps for the test case
12. Check and validate the data
13. Check correctness of the data with respect to its properties required for vibration testing for 1,2,5.
14. If 13 returns true, Carry out the test.
15. If the test is successful then save results, validate the results and return 'good test case'.
16. Else return 'bad test case' feedback to LLM.
17. Else if 13 returns false then return feedback to LLM - 'invalid test data not ready to test' and 'get correct data and test case' and return to step 8.
18. if repeat flag is set to true, move to the next test type and test level
19. Repeat the tests till all test types and levels and runs of tests return 'good test case'
20. If all test cases and levels are covered, stop.
[0023] The system comprises of the following components: System for information gathering about structure and vibration testing
1. Structural information collection
2. Types of vibration tests to be carried out
3. Breaking points evaluation for vibration tests
4. Types of data that are invalid
5. Types of data that are valid
6. Other descriptions of data and structure and test cases for vibration analysis
7. Test infrastructure for vibration testing and analysis
[0024] Data generation system: one component for each of the following steps.
1. Prompt generation system
2. Prompt context generation using RAGs
3. Vibration test data generation prompt generation with context
4. Vibration test data generation LLMs
5. Vibration test data validation
6. Vibration test generation
[0025] Novelties of our invention
- Finite Element Analysis of structures requires input data and steps for each test case to carry out the analysis. We present a method to generate such test data using generative AI and LLMs.
- Test case steps: we use generative AI and LLMs on the steps of how to use the data for testing for vibration
- Prompt generation: our method used retrieval augmented generation RAGs for context-based prompt generation
- Data validation: our method allows automated or manual validation of data and steps generated
- Test to test dependency: based on past tests and its data and results, the generative AI method is proposed to generate unique data and steps for the next tests
[0026] While the invention has been described and shown with reference to the preferred embodiment, it will be apparent that variations might be possible that would fall within the scope of the present invention.
BRIEF DESCRIPTION OF DRAWINGS
[0027] So that the manner in which the above-recited features of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may have been referred by embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only typical embodiments of this invention and are therefore not to be considered limiting of its scope, for the invention may admit to other equally effective embodiments.
[0028] These and other features, benefits, and advantages of the present invention will become apparent by reference to the following text figure, with like reference numbers referring to like structures across the views, wherein:
[0029] Figure 1 shows a System diagram is above for the design and components, in accordance with an exemplary embodiment of the present invention; and
[0030] Figure 2 shows Flow chart, in accordance with an exemplary embodiment of the present invention.
DETAILED DESCRIPTION OF THE INVENTION
[0031] While the present invention is described herein by way of example using embodiments and illustrative drawings, those skilled in the art will recognize that the invention is not limited to the embodiments of drawing or drawings described and are not intended to represent the scale of the various components. Further, some components that may form a part of the invention may not be illustrated in certain figures, for ease of illustration, and such omissions do not limit the embodiments outlined in any way. It should be understood that the drawings and the detailed description thereto are not intended to limit the invention to the particular form disclosed, but on the contrary, the invention is to cover all modifications, equivalents, and alternatives falling within the scope of the present invention as defined by the appended claim.
[0032] As used throughout this description, the word "may" is used in a permissive sense (i.e. meaning having the potential to), rather than the mandatory sense, (i.e. meaning must). Further, the words "a" or "an" mean "at least one" and the word "plurality" means "one or more" unless otherwise mentioned. Furthermore, the terminology and phraseology used herein are solely used for descriptive purposes and should not be construed as limiting in scope. Language such as "including," "comprising," "having," "containing," or "involving," and variations thereof, is intended to be broad and encompass the subject matter listed thereafter, equivalents, and additional subject matter not recited, and is not intended to exclude other additives, components, integers, or steps. Likewise, the term "comprising" is considered synonymous with the terms "including" or "containing" for applicable legal purposes. Any discussion of documents, acts, materials, devices, articles, and the like are included in the specification solely for the purpose of providing a context for the present invention. It is not suggested or represented that any or all these matters form part of the prior art base or were common general knowledge in the field relevant to the present invention.
[0033] In this disclosure, whenever a composition or an element or a group of elements is preceded with the transitional phrase "comprising", it is understood that we also contemplate the same composition, element, or group of elements with transitional phrases "consisting of", "consisting", "selected from the group of consisting of, "including", or "is" preceding the recitation of the composition, element or group of elements and vice versa.
[0034] The present invention is described hereinafter by various embodiments with reference to the accompanying drawing, wherein reference numerals used in the accompanying drawing correspond to the like elements throughout the description. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiment set forth herein. Rather, the embodiment is provided so that this disclosure will be thorough and complete and will fully convey the scope of the invention to those skilled in the art. In the following detailed description, numeric values and ranges are provided for various aspects of the implementations described. These values and ranges are to be treated as examples only and are not intended to limit the scope of the claims. In addition, several materials are identified as suitable for various facets of the implementations. These materials are to be treated as exemplary and are not intended to limit the scope of the invention.
[0035] The present invention relates to system and method for generation of input data for finite element analysis of structures using Generative AI and LLMs.
[0036] We also present a method for generating the policy and configurations as in the above flowchart first and second blocks of statements.
[0037] Develop Policies and configurations: For structural analysis add to the policy: boundary conditions such as on how it is supported. Analysis type and parameters are specified as rules in a policy per analysis type. There is one or more policy that specifies what large language model to use (such as GPT4.0, Gemini, other AI models), to use them parallel. Analysis cases are specified in a configuration file. How to store or transfer the output in files, or in APIs, or in memory or sending it to directly to another system are specified in the configuration file.
[0038] The policies and configuration can be modified dynamically and the dynamic changes are taken into effect by AI models and the system after the current running is completed. Generate values for each parameter for each type of vibration testing using generative AI and large language models.
[0039] Method 1:
5. If a parameter type is a matrix of n dimensions, and m columns and r rows, then a prompt is issued to an LLM to generate that matrix for 'k' different values.
6. Validate that the generated values for a parameter satisfies a test condition.
Validate the matrices by carrying out matrix validation techniques.
a. Using LLMs as self-introspection engines: ask the LLM to validate the values using the policies as input in the prompt
b. Using LLMs as validation for data generated by others: ask the LLM to validate the values using the policies as input in the prompt
7. If the generated values match the test conditions, or boundary value conditions for testing, then transfer them as mentioned in configuration files.
8. If the test conditions are not required or met, the LLMs are informed not to generate data for such test conditions
[0040] Method 2: This method describes the next set of blocks.
21. Input the type of the structural component to be tested
22. What is the type of vibration test to be carried out
23. What tests have been carried out already
24. Optional: what data or test cases did you use
25. What is the level l(s) of testing being requested
26. What is the format of the output data to be generated for test case
27. Create a prompt for an LLM using this input for carrying out vibration analysis using RAGs and chain-of-thought process.
28. Send it to the LLM selected.
29. Get the output
30. Save the synthetic data for test case
31. Ask the LLM for the testing steps for the test case
32. Check and validate the data
33. Check correctness of the data with respect to its properties required for vibration testing for 1,2,5.
34. If 13 returns true, Carry out the test.
35. If the test is successful then save results, validate the results and return 'good test case'.
36. Else return 'bad test case' feedback to LLM.
37. Else if 13 returns false then return feedback to LLM - 'invalid test data not ready to test' and 'get correct data and test case' and return to step 8.
38. if repeat flag is set to true, move to the next test type and test level
39. Repeat the tests till all test types and levels and runs of tests return 'good test case'
40. If all test cases and levels are covered, stop.
[0041] The system comprises of the following components: System for information gathering about structure and vibration testing
8. Structural information collection
9. Types of vibration tests to be carried out
10. Breaking points evaluation for vibration tests
11. Types of data that are invalid
12. Types of data that are valid
13. Other descriptions of data and structure and test cases for vibration analysis
14. Test infrastructure for vibration testing and analysis
[0042] Data generation system: one component for each of the following steps.
7. Prompt generation system
8. Prompt context generation using RAGs
9. Vibration test data generation prompt generation with context
10. Vibration test data generation LLMs
11. Vibration test data validation
12. Vibration test generation
[0043] Novelties of our invention
- Finite Element Analysis of structures requires input data and steps for each test case to carry out the analysis. We present a method to generate such test data using generative AI and LLMs.
- Test case steps: we use generative AI and LLMs on the steps of how to use the data for testing for vibration
- Prompt generation: our method used retrieval augmented generation RAGs for context-based prompt generation
- Data validation: our method allows automated or manual validation of data and steps generated
- Test to test dependency: based on past tests and its data and results, the generative AI method is proposed to generate unique data and steps for the next tests
[0044] Various modifications to these embodiments are apparent to those skilled in the art from the description and the accompanying drawings. The principles associated with the various embodiments described herein may be applied to other embodiments. Therefore, the description is not intended to be limited to the 5 embodiments shown along with the accompanying drawings but is to be providing the broadest scope consistent with the principles and the novel and inventive features disclosed or suggested herein. Accordingly, the invention is anticipated to hold on to all other such alternatives, modifications, and variations that fall within the scope of the present invention and appended claims.
, Claims:CLAIMS
We Claim:
1) A method for generating input data for finite element analysis of structures using generative AI and large language models (LLMs), the method comprising:
- Developing one or more policies for structural analysis, including specifying boundary conditions, analysis types, and parameters for each analysis type;
- Configuring the analysis cases using a configuration file that defines parameters for AI model selection, output storage methods, and communication protocols;
- Dynamically modifying the policies and configuration during operation, with updates taking effect after the current running is completed;
- Generating values for each parameter of each type of vibration testing using generative AI and LLMs.
2. The method as claimed in claim 1, wherein the configuration file specifies how to store, transfer, or transmit the generated data using files, APIs, memory, or directly to another system.
3. A method for generating test data for vibration testing, the method comprising:
- Inputting the type of structural component to be tested and the vibration test to be carried out;
- Generating a prompt for an LLM based on the input data for vibration analysis;
- Sending the prompt to the selected LLM for analysis;
- Receiving the output from the LLM, which includes synthetic test data;
- Validating the generated test data against predefined test conditions or boundary conditions for vibration testing;
- Storing the test data and validating the test steps to ensure correctness before carrying out the vibration test.

Documents

NameDate
202431088196-COMPLETE SPECIFICATION [14-11-2024(online)].pdf14/11/2024
202431088196-DECLARATION OF INVENTORSHIP (FORM 5) [14-11-2024(online)].pdf14/11/2024
202431088196-DRAWINGS [14-11-2024(online)].pdf14/11/2024
202431088196-EDUCATIONAL INSTITUTION(S) [14-11-2024(online)].pdf14/11/2024
202431088196-EVIDENCE FOR REGISTRATION UNDER SSI [14-11-2024(online)].pdf14/11/2024
202431088196-EVIDENCE FOR REGISTRATION UNDER SSI(FORM-28) [14-11-2024(online)].pdf14/11/2024
202431088196-FORM 1 [14-11-2024(online)].pdf14/11/2024
202431088196-FORM FOR SMALL ENTITY(FORM-28) [14-11-2024(online)].pdf14/11/2024
202431088196-FORM-9 [14-11-2024(online)].pdf14/11/2024
202431088196-POWER OF AUTHORITY [14-11-2024(online)].pdf14/11/2024
202431088196-REQUEST FOR EARLY PUBLICATION(FORM-9) [14-11-2024(online)].pdf14/11/2024

footer-service

By continuing past this page, you agree to our Terms of Service,Cookie PolicyPrivacy Policy  and  Refund Policy  © - Uber9 Business Process Services Private Limited. All rights reserved.

Uber9 Business Process Services Private Limited, CIN - U74900TN2014PTC098414, GSTIN - 33AABCU7650C1ZM, Registered Office Address - F-97, Newry Shreya Apartments Anna Nagar East, Chennai, Tamil Nadu 600102, India.

Please note that we are a facilitating platform enabling access to reliable professionals. We are not a law firm and do not provide legal services ourselves. The information on this website is for the purpose of knowledge only and should not be relied upon as legal advice or opinion.