Method to produce evolving concrete mixture heuristic

Patent metadata

Field	Value
Publication number	US-12025609-B2
Application number	US-202318329298-A
Country	US
Kind code	B2
Filing date	Jun 5, 2023
Priority date	Sep 24, 2021
Publication date	Jul 2, 2024
Grant date	Jul 2, 2024

Abstract

Methods, systems, and apparatus for generating a recipe for a concrete mixture, comprising: obtaining an optical characterization of a set of particles; determining, based on the optical characterization, physical characteristics of the set of particles; generating a multispherical approximation of the set of particles; selecting, based on the physical characteristics of the set of particles and from a database of performance rules, performance rules applicable to the set of particles; predicting performance of a proposed recipe for a concrete mixture formed from the set of particles by: determining a wet flowability rating of the proposed recipe based on the selected performance rules; and determining a dry packing rating of the proposed recipe based on the multispherical approximation; iteratively altering the proposed recipe and predicting performance of the altered proposed recipe until the predicted performance satisfies performance criteria to obtain a final recipe; and outputting the final recipe.

First claim

What is claimed is:

1. A method of generating a recipe for a concrete mixture, comprising:
determining, based on sensor measurements of a set of particles, physical characteristics of the set of particles;
generating, based on the physical characteristics, a multispherical approximation of the set of particles;
predicting performance of a proposed recipe for a concrete mixture formed from the set of particles to obtain a predicted performance by determining a wet flowability rating of the proposed recipe based on performance rules relevant to the physical characteristics of the set of particles, and determining a dry packing rating of the proposed recipe based on the multispherical approximation; and
outputting a final recipe based on the proposed recipe.

2. The method of claim 1 , wherein determining the physical characteristics comprises:
generating, from the sensor measurements, three dimensional (3D) models of the particles; and
determining the physical characteristics from the 3D models.

3. The method of claim 2 , wherein the physical characteristics comprise one or more of: particle elongation, particle flatness, particle angularity, or particle sphericity.

4. The method of claim 1 , wherein generating the multispherical approximation comprises selecting, using the physical characteristics, a set of one or more multispherical approximations of the particles from a database comprising a plurality of multispherical approximations indexed based on different physical characteristics.

5. The method of claim 1 , wherein determining the physical characteristics comprises:
generating, from the sensor measurements, heightmap representations of the particles; and
determining the physical characteristics from the heightmap representations.

6. The method of claim 5 , wherein the physical characteristics comprise one or more of: particle size, particle shape, or particle sphericity.

7. The method of claim 5 , wherein determining the physical characteristics comprises applying the heightmap representations of the particles to a dimension reducer to obtain the physical characteristics of the particles.

8. The method of claim 1 , wherein generating the multispherical approximation comprises applying the physical characteristics of the set of particles to an autoencoder trained to output the multispherical approximations from input comprising the physical characteristics.

9. The method of claim 1 , comprising determining the final recipe at least by iteratively altering the proposed recipe and predicting performance of the altered proposed recipe until the predicted performance satisfies performance criteria to obtain the final recipe.

10. The method of claim 9 , wherein the performance criteria comprises a highest dry packing rating subject to an acceptable wet flowability rating.

11. The method of claim 1 , comprising:
mixing a concrete mixture using the final recipe;
evaluating performance of the concrete mixture using one or more performance tests; and
updating the performance rules based on the evaluated performance of the concrete mixture.

12. The method of claim 11 , wherein updating the performance rules comprises generating, based on the evaluated performance, a limit curve for sets of particles matching the physical characteristics of the set of particles.

13. The method of claim 11 , wherein updating the performance rules comprises adjusting, based on the evaluated performance, a limit curve of a database of performance rules for sets of particles matching the physical characteristics of the set of particles.

14. The method of claim 1 , wherein the performance rules include curves representing wet flowability limits.

15. The method of claim 1 , comprising determining the dry packing rating by applying the multispherical approximation of the set of particles to a physics simulator.

16. The method of claim 1 , wherein the sensor measurements comprise an optical characterization of the set of particles obtained by scanning the set of particles with an imaging device.

17. The method of claim 16 , wherein the multispherical approximation has reduced dimensionality compared to the optical characterization.

18. The method of claim 1 , wherein the physical characteristics have reduced dimensionality compared to the sensor measurements.

19. A system comprising one or more computers and one or more storage devices on which are stored instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
determining, based on sensor measurements of a set of particles, physical characteristics of the set of particles;
generating, based on the physical characteristics, a multispherical approximation of the set of particles;
predicting performance of a proposed recipe for a concrete mixture formed from the set of particles to obtain a predicted performance by determining a wet flowability rating of the proposed recipe based on performance rules relevant to the physical characteristics of the set of particles, and determining a dry packing rating of the proposed recipe based on the multispherical approximation; and
outputting a final recipe based on the proposed recipe.

20. One or more non-transitory computer readable storage devices storing instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
determining, based on sensor measurements of a set of particles, physical characteristics of the set of particles;
generating, based on the physical characteristics, a multispherical approximation of the set of particles;
predicting performance of a proposed recipe for a concrete mixture formed from the set of particles to obtain a predicted performance by determining a wet flowability rating of the proposed recipe based on performance rules relevant to the physical characteristics of the set of particles, and determining a dry packing rating of the proposed recipe based on the multispherical approximation; and
outputting a final recipe based on the proposed recipe.

Assignees

• X Dev Llc

Inventors

• Papania-Davis Antonio Raymond
• Yan Weishi

Classifications

• G06F2113/02

  Data centres · CPC title

• G06F2119/02

  Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA] · CPC title

• G06F2113/26

  Composites · CPC title

• G06F30/25

  using particle-based methods · CPC title

• G16C60/00 Primary

  Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation · CPC title