# US 2025/0165657 A1 · Methods and systems for generating an instant design for manufacturability of a part at a computing device

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

- Number: US 2025/0165657 A1
- Document ID: US20250165657A1
- Status: Published application
- Kind: A1
- Application number: 19/036,529
- Filed: 2025-01-24
- Published: 2025-05-22
- Earliest claimed: 2020-03-24
- Assignees: Proto Labs, Inc.
- Applicants: Proto Labs, Inc.
- Inventors: Shuji Usui
- Web page: https://patentgrep.com/patent/US20250165657A1

## CPC

- G06F 30/10: Geometric CAD
- G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- G06F 2111/20: Configuration CAD, e.g. designing by assembling or positioning modules selected from libraries of predesigned modules
- G06F 2119/18: Manufacturability analysis or optimisation for manufacturability
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A system for generating an instant design for manufacturability of a part includes a computing device configured to receive a representative part model, wherein the representative part model comprises a plurality of sides, to generate, at a graphics processing unit, a depth buffer model of the representative part model, to determine, at an assignment module operating on the graphics processing unit, each orientation of the plurality of orientations of the representative part model as a function of each depth buffer of the plurality of depth buffers, and to generate, at a simulation module operating on the graphics processing unit, a prospective part, wherein generating a prospective part further comprises generating a simulated casing of the representative part model. The system is further designed and configured to display the prospective part to a user device.

## Claims

### Claim 1

A method for generating an instant design for manufacturability of a part, the method comprising:
receiving, using at least a processor, a representative part model, wherein the representative part model comprises geometric attributes;
identifying, using the at least a processor, at least an attribute of the representative part model that affects a manufacturing process;
generating, at a simulation module operating on a graphics processing unit, a prospective part, wherein generating the prospective part comprises applying at least a digital filter to the representative part model as a function of the at least an attribute of the representative part model; and
displaying, using a user device, the prospective part.

### Claim 2 (depends on 1)

The method of claim 1, wherein generating the prospective part further comprises generating a simulated casing of the representative part model.

### Claim 3 (depends on 2)

The method of claim 2, wherein generating the prospective part further comprises filling at least a void space of a simulated casing of the representative part model by running the at least a digital filter on each depth buffer of a plurality of depth buffers of each side of the representative part model.

### Claim 4 (depends on 1)

The method of claim 1, wherein further configured to determine one or more orientation, wherein determining each of the one or more orientation comprises generating a geodesic representative part model, and wherein the geodesic representative part model includes the representative part model encased in a geodesic polygon.

### Claim 5 (depends on 4)

The method of claim 4, wherein determining each orientation further comprises computing, using a bitonic sorting algorithm, a thickness direction datum.

### Claim 6 (depends on 4)

The method of claim 4, wherein determining each orientation further comprises detecting features and associated manufacturing processes.

### Claim 7 (depends on 1)

The method of claim 1, wherein the representative part model further comprises non-geometric attributes, and wherein the non-geometric attributes of the representative part model comprises semantic information.

### Claim 8 (depends on 7)

The method of claim 7, wherein the at least a processor is further configured to receive the non-geometric attributes, wherein the non-geometric attributes of the representative part model comprises a quote request.

### Claim 9 (depends on 1)

The method of claim 1, wherein the at least an attribute of the representative part model comprises an unreachable zone.

### Claim 10 (depends on 1)

The method of claim 1, wherein the simulation module comprises a machine learning model, the machine learning model configured to:
identify at least one suboptimal characteristic of the representative part model based on predefined standards; and
generate a suggestion to modify the at least one suboptimal characteristic to improve compatibility with the manufacturing process.

### Claim 11 (depends on 10)

The method of claim 10, wherein the machine learning model is iteratively trained on training data, wherein the training data comprises two or more categories of data elements.

### Claim 12

A system for generating an instant design for manufacturability of a part, the system comprising a computing device designed and configured to:
receive, using at least a processor, a representative part model, wherein the representative part model comprises geometric attributes;
identify, using the at least a processor, at least an attribute of the representative part model that affects a manufacturing process;
generate, at a simulation module operating on a graphics processing unit, a prospective part, wherein generating the prospective part comprises applying at least a digital filter to the representative part model as a function of the at least an attribute of the representative part model; and
display, using a user device, the prospective part.

### Claim 13 (depends on 12)

The system of claim 12, wherein generating the prospective part further comprises generating a simulated casing of the representative part model.

### Claim 14 (depends on 13)

The system of claim 13, wherein generating the prospective part further comprises filling at least a void space of a simulated casing of the representative part model by running the at least a digital filter on each depth buffer of a plurality of depth buffers of each side of the representative part model.

### Claim 15 (depends on 12)

The system of claim 12, wherein further configured to determine one or more orientation, wherein determining one or more orientation comprises generating a geodesic representative part model, wherein the geodesic representative part model includes the representative part model encased in a geodesic polygon.

### Claim 16 (depends on 15)

The system of claim 15, wherein determining each orientation further comprises computing, using a bitonic sorting algorithm, a thickness direction datum.

### Claim 17 (depends on 12)

The system of claim 12, wherein the representative part model further comprises non-geometric attributes, and wherein the non-geometric attributes of the representative part model comprises semantic information.

### Claim 18 (depends on 17)

The system of claim 17, wherein the at least a processor is further configured to receive the non-geometric attributes, wherein the non-geometric attributes of the representative part model comprises a quote request.

### Claim 19 (depends on 12)

The system of claim 12, wherein the at least an attribute of the representative part model comprises an unreachable zone.

### Claim 20 (depends on 12)

The system of claim 12, wherein the simulation module comprises a machine learning model, the machine learning model configured to:
identify at least one suboptimal characteristic of the representative part model based on predefined standards; and
generate a suggestion to modify the at least one suboptimal characteristic to improve compatibility with the manufacturing process.

### Claim 21 (depends on 20)

The system of claim 20, wherein the machine learning model is iteratively trained on training data, wherein the training data comprise two or more categories of data elements.
