Systems and methods for formulating or evaluating a construction composition

Patent metadata

Field	Value
Publication number	US-12555047-B2
Application number	US-202017429437-A
Country	US
Kind code	B2
Filing date	Feb 11, 2020
Priority date	Feb 11, 2019
Publication date	Feb 17, 2026
Grant date	Feb 17, 2026

Abstract

Example embodiments provide systems and methods for formulating and evaluating a construction composition (such as a mixture for concrete, asphalt, mortar, etc.). According to exemplary embodiments, a predictive model, artificial intelligence, machine learning algorithm, etc., may be trained using historical performance data and current deployment information. Based on a job specification that identifies various requirements for the construction composition and a set of available inputs (e.g., raw materials, mixing techniques, etc.), the model, AI, or algorithm, may output one or more formulations that meet or best approximate the requirements. The formulations may be provided to a simulation to estimate or predict their performance. The performance characteristics of the output formulation(s) may be displayed. Optionally, the system may control mixing machinery to produce the formulation. Some embodiments may use these capabilities to evaluate an existing or proposed construction composition, rather than proposing a new construction composition.

First claim

What is claimed is:

1 . A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:
receive a job specification for a construction composition to be used in a structure, the job specification specifying one or more performance requirements for the construction composition; access a set of inputs affecting one or more properties of the construction composition; provide the job specification and set of inputs to an artificial intelligence trained to map input construction compositions to associated performance characteristics; programmatically determine, using the artificial intelligence, a plurality of construction compositions that meet or approximate the performance requirements of the job specification given the set of inputs, wherein:
each of the construction compositions comprises a plurality of raw materials mixed in a determined ratio,
the plurality of raw materials comprise at least one of an aggregate, a dispersant, a set modifier, an air controller, a strength modifier, a cementing material, a workability retention modifier, or a rheology modifier,
the plurality of construction compositions differ from each other in at least one of an amount or a type of the raw materials, and
the artificial intelligence applies a mapping between the performance requirements and one or more variables, the variables comprising one or more producer-affectable variables and one or more ambient condition variables;
output, from the artificial intelligence, the plurality of construction compositions approximating the performance requirements of the job specification; determine a predicted performance for each of the plurality of construction compositions output from the artificial intelligence, the determining comprising one or more of applying historical data or running a simulation on each of the plurality of compositions output by the artificial intelligence to predict an expected performance of each respective construction composition by building a logical model of the structure using the respective construction composition and applying simulation logic to evaluate a performance of the respective construction composition with respect to the performance requirements in the job specification, the predicted performance comprising estimated values for the parameters specified in the job specification; output the predicted performance of each respective construction composition; receive a selection of a selected construction composition from among the plurality of compositions simulated by the simulation logic; generate instructions in real time configured to cause a controller associated with a mixing device to automatically produce the selected construction composition, and transmitting the instructions to the controller; and produce, using the mixing device under control of the controller, the construction composition by mixing the plurality of raw materials according to the instructions.

2 . The medium of claim 1 , further storing instructions for producing the determined construction composition.

3 . The medium of claim 1 , wherein the construction composition is selected from the group of an asphalt mixture, a concrete mixture, or a mortar mixture.

4 . The medium of claim 1 , wherein the job specification comprises one or more of a fresh property of the construction composition, a hardened property of the construction composition, a strength of the construction composition, a surface appearance of the construction composition, a cost of the construction mixture, or a durability of the construction mixture.

5 . The medium of claim 1 , further comprising receiving a priority for one or more of the performance requirements, and accounting for the priority.

6 . The medium of claim 1 , wherein the set of inputs comprise one or more of available raw materials, climatological data for a construction site, construction processes to be employed with the construction composition, project specification information, available construction admixtures, and information pertaining to travel from a mixing site to a construction site.

7 . The medium of claim 1 , further storing instructions for selecting one or more performance characteristics on which the plurality of construction compositions differ, the one or more performance characteristics not being specified as part of the job specification, and outputting a comparison of the plurality of construction compositions based on the selected performance characteristics.

8 . The medium of claim 1 , further storing instructions for:
receiving a notification that the set of inputs is changed; and reoptimizing the determined construction composition based on the notification.

9 . The medium of claim 8 , wherein the changed input comprises a different set of available raw materials and components than were available when the construction composition was first determined.

10 . The medium of claim 1 , further storing instructions configured to cause the processor to:
receive a report of a performance of the new construction composition; and retrain the artificial intelligence based on the performance of the new construction composition.

11 . The medium of claim 1 , further storing instructions configured to produce the selected construction composition, the producing comprising instructing mixing device to add the plurality of raw materials for the construction composition together in the determined ratio, and causing the construction composition.

12 . The medium of claim 1 , further comprising prioritizing a first construction composition over a second construction composition on a display when the predicted performance of the first construction composition exceeds the predicted performance of the second construction composition.

13 . The medium of claim 1 , further comprising estimating a cost for each of the plurality of construction compositions output from the artificial intelligence.

14 . The medium of claim 13 , further comprising prioritizing a first construction composition over a second construction composition on a display when a weighted performance of the first construction composition exceeds a weighted performance of the second construction composition, the weighted performances being configured to penalize a performance degradation unless a minimum level of cost savings is achieved.

15 . A computer-implemented method comprising:
receiving a job specification for a construction composition to be used in a structure, the job specification specifying one or more characteristics for the construction composition; accessing a set of variables affecting one or more properties of the construction composition, each of the variables associated with one or more corresponding characteristics that are affected by a change in the respective variable; providing the job specification and set of variables to an artificial intelligence trained to map input construction compositions to associated performance characteristics; determining an initial construction composition using initial values for the set of variables, the initial construction composition associated with an initial set of characteristics; applying the artificial intelligence to adjust one or more of the variables in the initial construction composition, the adjusting causing the corresponding characteristics associated with the one or more variables to change; adjusting the initial set of characteristics based on the adjusted variables; determining, using the artificial intelligence, a plurality of

Assignees

• Construction Research & Technology Gmbh

Inventors

• Daczko Joseph
• Kayello Hamed
• Schlagbaum Tony
• Henson David C
• Seiler Paul Horst
• Bury Jeffrey

Classifications

• G06Q10/06313

  Resource planning in a project environment · CPC title

• G06N20/00

  Machine learning · CPC title

• G06N3/0499

  Feedforward networks · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06Q10/04 Primary

  Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202) · CPC title