# US 10,504,218 B2 · Method and system for automated inspection utilizing a multi-modal database

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

- Number: US 10,504,218 B2
- Document ID: US10504218B2
- Status: Granted
- Kind: B2
- Application number: 14/692,302
- Filed: 2015-04-21
- Published: 2016-10-27
- Granted: 2019-12-10
- Earliest claimed: 2015-04-21
- Assignees: United Technologies Corporation
- Applicants: United Technologies Corporation
- Inventors: Alan Matthew Finn; Hongcheng Wang; Ziyou Xiong
- Web page: https://patentgrep.com/patent/US10504218B2

## CPC

- G06T 7/001: {using an image reference approach}
- G06F 16/40: of multimedia data, e.g. slideshows comprising image and additional audio data (retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70)
- G06F 18/24155: {Bayesian classification}
- G06F 30/17: Mechanical parametric or variational design
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 7/0004: {Industrial image inspection}
- G06T 2207/20221: Image fusion; Image merging
- G06T 2207/30164: Workpiece; Machine component
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method and system for performing automated defect detection is disclosed. The system may include at least one database, an image capture device and a processor. The method may comprise providing at least one database for storing information used in processing data to detect a defect in at least one member of a plurality of members in a device. The information may include a plurality of different modes of data. The method may further comprise providing a processing unit for processing the information; receiving, by the database, updates to the information; identifying a potential defect in a first mode of data; applying, by the processing unit, analysis of a second mode of data, the analysis of the second mode of data triggered by the identifying, the second mode of data different than the first mode of data; and reporting defects based on the results of the applying.

## Claims

### Claim 1

A method for detecting a defect in a part of a gas turbine engine comprising:
receiving image data of the part from an image capture device;
using the image data and another type of data about the part other than the image data to create composite data through multi-modal data fusion, wherein the another type of data is a 3-D CAD model of a shape of the part, and the multi-modal data fusion comprises overlaying the 3-D CAD model of the shape of the part on the image data of the part to create the composite data;
identifying a potential defect in the part by analyzing the composite data by computing a posterior probability of a potential defect based on new data and prior data of the composite data and generating a ranked list of failure parts/regions based on the posterior probability to identify a potential defect having a higher probability;
upon identifying a potential defect in the part, analyzing a type of data about the part other than the image data and the composite data to identify a defect; and
reporting the defect.

### Claim 2 (depends on 1)

The method of claim 1, in which the analyzing of the composite data to identify a potential defect includes utilizing linear or non-linear registration.

### Claim 3 (depends on 2)

The method of claim 2, wherein the type of data other than the image data and the composite data that is analyzed upon detection of a potential defect is a manufacturing record of the part.

### Claim 4 (depends on 3)

The method of claim 3, wherein the part is a blade.