# US 2023/0409780 A1 · Method and System for Determining Ply-by-Ply Damage in a Composite Structure

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

- Number: US 2023/0409780 A1
- Document ID: US20230409780A1
- Status: Published application
- Kind: A1
- Application number: 17/845,283
- Filed: 2022-06-21
- Published: 2023-12-21
- Earliest claimed: 2022-06-21
- Assignees: The Boeing Company
- Applicants: The Boeing Company
- Inventors: Kenneth J. Hunziker; Jenna K. Pang
- Web page: https://patentgrep.com/patent/US20230409780A1

## CPC

- G06F 30/23: using finite element methods [FEM] or finite difference methods [FDM]
- G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30)
- G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- G06F 2113/26: Composites
- G06F 2119/02: Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A computer-implemented method that facilitates determining ply-by-ply damage in a composite structure comprises receiving, by a computing system, a geometric model that specifies geometric aspects of a composite structure. The geometric model facilitates the performance of finite element analysis (FEA). FEA logic of the computing system applies each of a plurality of material failure models (MFMs) to the geometric model to predict different types of damage to the composite structure due to an applied force or stress. Each MFM relates a force or stress applied to a material to a particular type of damage to the material. The machine learning logic predicts, based on each of the predicted different types of damage, an aggregate prediction of damage to the composite structure.

## Claims

### Claim 1

A computer-implemented method for determining ply-by-ply damage in a composite structure, method comprising:
receiving, by a computing system, a geometric model that specifies geometric aspects of a composite structure, wherein the geometric model facilitates performance of finite element analysis (FEA);
applying, by FEA logic of the computing system, each of a plurality of material failure models (MFMs) to the geometric model to predict different types of damage to the composite structure due to an applied force or stress, wherein each MFM relates a force or stress applied to a material to a particular type of damage to the material; and
predicting, by machine learning logic of the computing system and based on each of the predicted different types of damage, an aggregate prediction of damage to the composite structure.

### Claim 2 (depends on 1)

The computer-implemented method according to claim 1, wherein predicting an aggregate prediction of damage to the composite structure comprises:
outputting a composite image that depicts damage to each ply of the composite structure.

### Claim 3 (depends on 1)

The computer-implemented method according to claim 1, wherein applying each of the plurality of material failure models (MFMs) to the geometric model comprises
applying, by FEA logic of the computing system, an MFM to the geometric model that predicts stressed-based damage to the composite structure due to an applied force or stress.

### Claim 4 (depends on 1)

The computer-implemented method according to claim 1, wherein applying each of the plurality of material failure models (MFMs) to the geometric model comprises
applying, by FEA logic of the computing system, an MFM to the geometric model that predicts fracture-based damage to the composite structure due to an applied force or stress.

### Claim 5 (depends on 1)

The computer-implemented method according to claim 1, wherein receiving a geometric model that specifies geometric aspects of a composite structure comprises:
receiving a geometric model that specifies each ply of the composite structure with one element.

### Claim 6 (depends on 1)

The computer-implemented method according to claim 1, wherein predicting, by the machine learning logic, an aggregate prediction of damage to the composite structure comprises:
inputting a plurality of images into an input layer of the machine learning logic, wherein each image depicts damage that is predicted according to a particular MFM to occur to the composite structure.

### Claim 7 (depends on 6)

The computer-implemented method according to claim 6, wherein inputting into the input layer of the machine learning logic a plurality of images comprises:
inputting a plurality of images into an input layer of the machine learning logic, wherein each image depicts a binary mask indicative of where damage is predicted according to a particular MFM to occur to the composite structure.

### Claim 8 (depends on 6)

The computer-implemented method according to claim 6, wherein inputting into the input layer of the machine learning logic a plurality of images comprises:
inputting a plurality of images into an input layer of the machine learning logic, wherein each image depicts a gradient that represents different amounts of damage that are predicted according to a particular MFM to occur to the composite structure.

### Claim 9 (depends on 6)

The computer-implemented method according to claim 6, wherein inputting into the input layer of the machine learning logic a plurality of images comprises:
inputting into the input layer of the machine learning logic a plurality of images, wherein each image depicts a composite image of damage predicted according to a particular MFM to occur on each layer of the composite structure.

### Claim 10 (depends on 1)

The computer-implemented method according to claim 1, wherein receiving a geometric model that specifies geometric aspects of a composite structure comprises:
receiving a geometric model that specifies geometric aspects of a composite panel; and
wherein applying, by the FEA logic of the computing system, each of a plurality of material failure models (MFMs) to the geometric model to predict different types of damage to the composite structure due to an applied force or stress comprises:
applying, by the FEA logic of the computing system, each of a plurality of material failure models (MFMs) to the geometric model to predict different types of damage to the composite panel due to a ballistic impact.

### Claim 11

A computing system that for determining ply-by-ply damage in a composite structure, the computing system comprising:
one or more instruction storage devices for storing instruction code; and
one or more processors in communication with the one or more instruction storage devices, wherein execution of the instruction code by the one or more processors causes the computing system to perform operations comprising:
receiving, by a computing system, a geometric model that specifies geometric aspects of a composite structure, wherein the geometric model facilitates performance of finite element analysis (FEA);
applying, by FEA logic of the computing system, each of a plurality of material failure models (MFMs) to the geometric model to predict different types of damage to the composite structure due to an applied force or stress, wherein each MFM relates a force or stress applied to a material to a particular type of damage to the material; and
predicting, by machine learning logic of the computing system and based on each of the predicted different types of damage, an aggregate prediction of damage to the composite structure.

### Claim 12 (depends on 11)

The computing system according to claim 11, wherein predicting an aggregate prediction of damage to the composite structure comprises:
outputting a composite image that depicts damage to each ply of the composite structure.

### Claim 13 (depends on 11)

The computing system according to claim 11, wherein applying each of the plurality of material failure models (MFMs) to the geometric model comprises
applying, by FEA logic of the computing system, an MFM to the geometric model that predicts stressed-based damage to the composite structure due to an applied force or stress.

### Claim 14 (depends on 11)

The computing system according to claim 11, wherein applying each of the plurality of material failure models (MFMs) to the geometric model comprises
applying, by FEA logic of the computing system, an MFM to the geometric model that predicts fracture-based damage to the composite structure due to an applied force or stress.

### Claim 15 (depends on 11)

The computing system according to claim 11, wherein receiving a geometric model that specifies geometric aspects of a composite structure comprises:
receiving a geometric model that specifies each ply of the composite structure with one element.

### Claim 16 (depends on 11)

The computing system according to claim 11, wherein predicting, by the machine learning logic, an aggregate prediction of damage to the composite structure comprises:
inputting a plurality of images into an input layer of the machine learning logic, wherein each image depicts damage that is predicted according to a particular MFM to occur to the composite structure.

### Claim 17 (depends on 16)

The computing system according to claim 16, wherein inputting into the input layer of the machine learning logic a plurality of images comprises:
inputting a plurality of images into an input layer of the machine learning logic, wherein each image depicts a binary mask indicative of where damage is predicted according to a particular MFM to occur to the composite structure.

### Claim 18 (depends on 16)

The computing system according to claim 16, wherein inputting into the input layer of the machine learning logic a plurality of images comprises:
inputting a plurality of images into an input layer of the machine learning logic, wherein each image depicts a gradient that represents different amounts of damage that are predicted according to a particular MFM to occur to the composite structure.

### Claim 19 (depends on 16)

The computing system according to claim 16, wherein inputting into the input layer of the machine learning logic a plurality of images comprises:
inputting into the input layer of the machine learning logic a plurality of images, wherein each image depicts a composite image of damage predicted according to a particular MFM to occur on each layer of the composite structure.

### Claim 20

A non-transitory computer-readable medium that stores instruction code that facilitates determining ply-by-ply damage in a composite structure, wherein execution of the instruction code by one or more processors of a computing system causes the computing system to perform operations comprising:
receiving, by a computing system, a geometric model that specifies geometric aspects of a composite structure, wherein the geometric model facilitates performance of finite element analysis (FEA);
applying, by FEA logic of the computing system, each of a plurality of material failure models (MFMs) to the geometric model to predict different types of damage to the composite structure due to an applied force or stress, wherein each MFM relates a force or stress applied to a material to a particular type of damage to the material; and
predicting, by machine learning logic of the computing system and based on each of the predicted different types of damage, an aggregate prediction of damage to the composite structure.
