Fabricated shape estimation for additive manufacturing processes

Patent metadata

Field	Value
Publication number	US-11571740-B2
Application number	US-202016821458-A
Country	US
Kind code	B2
Filing date	Mar 17, 2020
Priority date	Mar 17, 2020
Publication date	Feb 7, 2023
Grant date	Feb 7, 2023

Abstract

A computer representation of a printable product part and a plan for the printable product part to be deposited using an additive manufacturing process are received. The printable product part comprises an accumulation of material deposited by the additive manufacturing process. The plan comprises a tool-path representation of the printable product part and process parameters. A plurality of as-printed shapes of the printable product part are determined after it has been deposited according to the plan. Geometric differences between any of the plurality of as-printed shapes with the computer representation of the product part are determined.

First claim

What is claimed is:

1. A method comprising:
receiving a computer representation of a printable product part and a plan for the printable product part to be deposited using an additive manufacturing process, the printable product part comprising an accumulation of material deposited by the additive manufacturing process, the plan comprising a process parameter and a representation of a tool-path used in building the printable product part;
determining a plurality of as-printed shapes of the printable product part after it has been deposited according to the plan, wherein determining the plurality of as-printed shapes comprises performing a plurality of physics informed simulations where uncertainty is introduced in the tool-path, wherein for each of the plurality of as printed shapes, the physics informed simulation comprises:
for each deposition event of the plan, inputting an initial state of a distribution of liquid and solid phases into a feedforward neural network with physics informed loss and activation functions, the feedforward neural network outputting a spatial distribution of a substrate after the deposition event; and
performing convolution of a kernel with the tool-path to obtain a spatial distribution of a solid phase of the as-printed shapes;

determining geometric differences between any of the plurality of as-printed shapes with the computer representation of the product part; and
using the geometric differences in the additive manufacturing process to build the printable product part with acceptable part quality.

2. The method of claim 1 , wherein the additive manufacturing process comprises a plurality of liquid metal droplets that coalesce and solidify according to the plan.

3. The method of claim 1 , further comprising determining a manufacturing error from the plurality of as-printed shapes of the product part based on a statistical analysis.

4. The method of claim 1 , further comprising determining the plurality of as-printed shapes based on at least one physical state of one or both of at least one deposited material and a substrate.

5. The method of claim 4 , wherein the at least one physical state comprises one or more of a spatial distribution of solid and liquid phases of the material, a spatial distribution of temperature, a pressure, and a flow velocity.

6. The method of claim 1 , comprising generating training data for the feedforward neural network using one or more of synthetically generated data and experimental data.

7. The method of claim 1 , comprising computing the difference between the computer representation of the product part and any or all of the as-printed shapes of the product part.

8. The method of claim 7 , further comprising displaying the geometric differences on a user interface.

9. The method according to claim 1 , wherein the kernel is estimated by training a convolutional neural network with a single convolutional layer.

10. A system, comprising:
a processor; and
a memory storing computer program instructions which when executed by the processor cause the processor to perform operations comprising:
receiving a computer representation of a printable product part and a plan for the printable product part to be deposited using an additive manufacturing process, the printable product part comprising an accumulation of material deposited by the additive manufacturing process, the plan comprising a process parameter and a representation of a tool-path used in building the printable product part;
determining a plurality of as-printed shapes of the printable product part after it has been deposited according to the plan, wherein determining the plurality of as-printed shapes comprises performing a plurality of physics informed simulations where uncertainty is introduced in the tool-path, wherein for each of the plurality of as printed shapes, the physics informed simulation comprises:
for each deposition event of the plan, inputting an initial state of a distribution of liquid and solid phases into a feedforward neural network with physics informed loss and activation functions, the feedforward neural network outputting a spatial distribution of a substrate after the deposition event; and
performing convolution of a kernel with the tool-path to obtain a spatial distribution of a solid phase of the as-printed shapes; and

determining geometric differences between any of the plurality of as-printed shapes with the computer representation of the product part, the geometric differences being used in the additive manufacturing process to build the printable product part with acceptable part quality.

11. The system of claim 10 , wherein receiving the plan for the printable product part comprises receiving at least one of a multi-physics model and a machine learning model as a surrogate for the multi-physics model.

12. The system of claim 10 , further comprising a user interface configured to display to geometric differences.

13. The system of claim 10 , wherein the additive manufacturing process comprises a plurality of liquid metal droplets that coalesce and solidify according to the plan.

14. The system of claim 10 , wherein the processor is further configured to determine a manufacturing error from the plurality of as-printed shapes of the product part based on a statistical analysis.

15. The system of claim 10 , wherein the processor is further configured to determine the plurality of as-printed shapes based on at least one physical state of one or both of at least one deposited material and a substrate.

16. The system of claim 15 , wherein the at least one physical state comprises one or more of a spatial distribution of solid and liquid phases of the material, a spatial distribution of temperature, a pressure, and a flow velocity.

17. The system of claim 15 , wherein each of the plurality of as-printed shapes comprise a spatial distribution of a solid phase of the as-printed shapes.

18. A non-transitory computer readable medium storing computer program instructions, the computer program instructions when executed by a processor cause the processor to perform operations comprising:
receiving a computer representation of a printable product part and a plan for the printable product part to be deposited using an additive manufacturing process, the printable product part comprising an accumulation of material deposited by the additive manufacturing process, the plan comprising a process parameter and a representation of a tool-path used in building the printable product part;
determining a plurality of as-printed shapes of the printable product part after it has been deposited according to the plan, wherein determining the plurality of as-printed shapes comprises performing a plurality of physics informed simulations where uncertainty is introduced in the tool-path, wherein for each of the plurality of as printed shapes, the physics informed simulation comprises:
for each deposition event of the plan, inputting an initial state of a distribution of liquid and solid phases into a feedforward neural network with physics informed loss and activation functions, the feedforward neural network outputting a spatial distribution of a substrate after the deposition event; and
performing convolution of a kernel with the tool-path to obtain a spatial distribution of a solid phase of the as-printed shapes;

determining geometric differences between any of the plurality of as-printed shapes with the computer representation of the product part; and
using the geometric differences in the additive manufacturing process to

Assignees

• Palo Alto Res Ct Inc

Inventors

• Korneev Svyatoslav
• Thiagarajan Vaidyanathan
• Nelaturi Saigopal
• Wang Ziyan

Classifications

• B33Y50/00 Primary

  Data acquisition or data processing for additive manufacturing · CPC title

• G06F30/27

  using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model · CPC title

• G06F2119/18

  Manufacturability analysis or optimisation for manufacturability · CPC title

• B22D23/003 Primary

  Moulding by spraying metal on a surface · CPC title

• Y02P90/02

  Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS] · CPC title