# US 2024/0192659 A1 · Systems and methods for predicting material properties of a part to be additive-manufactured

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0192659 A1
- Document ID: US20240192659A1
- Status: Published application
- Kind: A1
- Application number: 18/063,773
- Filed: 2022-12-09
- Published: 2024-06-13
- Earliest claimed: 2022-12-09
- Assignees: The Boeing Company
- Applicants: The Boeing Company
- Inventors: Andrew H. Baker; Luke A. Berglind; Lawrence E. Pado; Justin L'Hote; Elaine MacDonald; Baily J. Thomas
- Web page: https://patentgrep.com/patent/US20240192659A1

## CPC

- G05B 19/4099: Surface or curve machining, making three-dimensional [3D] objects, e.g. desktop manufacturing
- G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- G05B 2219/49023: 3-D printing, layer of powder, add drops of binder in layer, new powder
- G06F 2111/10: Numerical modelling
- G06F 2113/10: Additive manufacturing, e.g. three-dimensional [3D] printing
- G06F 2119/08: Thermal analysis or thermal optimisation
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method is provided for predicting material properties of a part to be additive-manufactured. The method comprises additive-manufacturing a plurality of standard parts, and obtaining thermal profiles at select predetermined locations of physical samples of the plurality of standard parts during additive-manufacturing of the plurality of standard parts. The method also comprises storing the thermal profiles and corresponding material properties of the physical samples of the plurality of standard parts in a database. The method further comprises running a machine-learning algorithm to predict material properties of the part to be additive-manufactured based upon the thermal profiles and corresponding material properties of the physical samples of the plurality of standard parts stored in the database.

## Claims

### Claim 1

A method for predicting material properties of a part to be additive-manufactured, the method comprising:
additive-manufacturing a plurality of standard parts;
obtaining thermal profiles at select predetermined locations of physical samples of the plurality of standard parts during additive-manufacturing of the plurality of standard parts;
storing the thermal profiles and corresponding material properties of the physical samples of the plurality of standard parts in a database; and
running a machine-learning algorithm to predict material properties of the part to be additive-manufactured based upon the thermal profiles and corresponding material properties of the physical samples of the plurality of standard parts stored in the database.

### Claim 2 (depends on 1)

The method of claim 1 further comprising:
determining material properties associated with the thermal profiles of the physical samples of the plurality of standard parts in the database.

### Claim 3 (depends on 2)

The method of claim 2 wherein determining material properties associated with the thermal profiles of the physical samples of the plurality of standard parts in the database includes:
determining a combination of mechanical properties and microstructural properties of the physical samples.

### Claim 4 (depends on 3)

The method of claim 3 further comprising:
organizing the combination of mechanical properties and microstructural properties of the physical samples in the database to provide a unique thermal signature and history associated with each physical sample.

### Claim 5 (depends on 1)

The method of claim 1 wherein the machine-learning algorithm comprises a supervised learning algorithm.

### Claim 6 (depends on 5)

The method of claim 5 wherein the supervised learning algorithm comprises a select one of a generalized linear regression model, a neural network model, a Gaussian process model, and a support vector machine model.

### Claim 7 (depends on 1)

The method of claim 1 wherein the machine-learning algorithm has been trained using as inputs a plurality of features contained in a temperature versus time curve associated with a specific location of each physical sample of the plurality of standard parts.

### Claim 8 (depends on 7)

The method of claim 7 wherein the plurality of features contained in a temperature versus time curve associated with a specific location of each physical sample of the plurality of standard parts includes a combination of one or more times spent in a plurality of temperature zones and one or more cooling rates between temperature zones.

### Claim 9 (depends on 1)

The method of claim 1 wherein obtaining thermal profiles at select predetermined locations of physical samples of the plurality of standard parts during additive-manufacturing of the plurality of standard parts includes:
obtaining two-dimensional thermal profiles at the select predetermined locations of physical samples of the plurality of standard parts during additive-manufacturing of the plurality of standard parts; and
transforming the two-dimensional thermal profiles to three-dimensional thermal profiles that correspond to the select predetermined locations of physical samples of the plurality of standard parts during additive-manufacturing of the plurality of standard parts.

### Claim 10 (depends on 9)

The method of claim 9 wherein transforming the two-dimensional thermal profiles to three-dimensional thermal profiles that correspond to the select predetermined locations of physical samples of the plurality of standard parts during additive-manufacturing of the plurality of standard parts includes:
identifying one or more pixels associated with each of a plurality of laser position coordinates during additive-manufacturing of the plurality of standard parts; and
assigning one or more voxels with each of a plurality of machine-axis coordinates; and
linking the identified one or more pixels and the assigned one or more voxels.

### Claim 11 (depends on 10)

The method of claim 10 wherein linking the identified one or more pixels and the assigned one or more voxels includes:
linking the identified one or more pixels and the assigned one or more voxels based upon alignment of time data associated with the plurality of laser position coordinates and time data associated with the machine-axis coordinates.

### Claim 12 (depends on 10)

The method of claim 10 wherein linking the identified one or more pixels and the assigned one or more voxels includes:
matching color of each voxel to color of its associated one or more pixels.

### Claim 13 (depends on 1)

The method of claim 1 wherein at least a portion of the method is performed by a computer having a memory executing one or more programs of instructions which are tangibly embodied in a program storage medium readable by the computer.

### Claim 14 (depends on 1)

The method of claim 1 wherein the predetermined locations are based on one or more geometrical characteristics found at such locations.

### Claim 15 (depends on 1)

An aerospace part manufactured according to the method of claim 1.

### Claim 16

A system for predicting material properties of a part to be additive-manufactured, the system comprising:
a first device for collecting thermal data associated with additive-manufactured standard parts; and
a second device for predicting material properties of the part to be additive-manufactured based upon collected thermal data associated with the additive-manufactured standard parts.

### Claim 17 (depends on 16)

The system of claim 16 wherein the first device includes a combination of an infrared camera, a single-wavelength pyrometer, a multiple-wavelength pyrometer, a baseplate having one or more thermocouple sensors, and a laser head.

### Claim 18 (depends on 16)

The system of claim 16 wherein the second device comprises a processor of a computer.

### Claim 19 (depends on 16)

The system of claim 16 wherein the second device for predicting material properties of the part to be additive-manufactured part predicts a combination of material properties and microstructural properties associated with the part to be additive-manufactured.

### Claim 20 (depends on 19)

The system of claim 19 wherein the combination of material properties and microstructural properties associated with the part to be additive-manufactured includes a combination of yield strength, tensile strength, and elongation strength.

### Claim 21 (depends on 16)

The system of claim 16 wherein the second device includes a machine-learning algorithm that has been trained using as inputs a plurality of features contained in a temperature versus time curve associated with a specific location of each additive-manufactured standard part.

### Claim 22 (depends on 21)

The system of claim 21 wherein the machine-learning algorithm comprises a supervised learning algorithm.

### Claim 23 (depends on 22)

The system of claim 22 wherein the machine-learning algorithm comprises a select one of a generalized linear regression model, a neural network model, a Gaussian process model, and a support vector machine model.

### Claim 24 (depends on 16)

The system of claim 16 wherein the collected thermal data associated with each additive-manufactured part comprises a unique thermal signature and history associated with that particular additive-manufactured part.

### Claim 25 (depends on 16)

The system of claim 16 wherein the first device comprises one or more infrared cameras for collecting thermal data associated with additive-manufactured standard parts.

### Claim 26 (depends on 25)

The system of claim 25 wherein the collected thermal data associated with each additive-manufactured standard part comprises three-dimensional thermal data that is transformed from two-dimensional thermal data.

### Claim 27 (depends on 16)

The system of claim 16 wherein the first device collects thermal profiles at select predetermined locations of physical samples of a plurality of standard parts during additive-manufacturing of the plurality of standard parts, and wherein the predetermined locations are based on one or more geometrical characteristics found at such locations.

### Claim 28 (depends on 16)

An aerospace part manufactured using the system of claim 16.

### Claim 29

A system for predicting material properties of a part to be additive-manufactured, the system comprising:
one or more infrared cameras for collecting thermal data associated with additive-manufactured standard parts, wherein the collected thermal data associated with each additive-manufactured part comprises a unique thermal signature and history associated with that particular additive-manufactured part; and
a computer processor for predicting a combination of material properties and microstructural properties associated with the part to be additive-manufactured based upon collected thermal data associated with the additive-manufactured standard parts.

### Claim 30 (depends on 29)

The system of claim 29 wherein the collected thermal data associated with each additive-manufactured standard part comprises two-dimensional thermal data and three-dimensional thermal data that is transformed from the two-dimensional thermal data.
