Automated part inspection system

Patent metadata

Field	Value
Publication number	US-12462372-B2
Application number	US-202217580921-A
Country	US
Kind code	B2
Filing date	Jan 21, 2022
Priority date	May 21, 2021
Publication date	Nov 4, 2025
Grant date	Nov 4, 2025

Abstract

A part inspection system includes a vision device configured to image a part being inspected and generate a digital image of the part. The inspection system includes a part inspection module communicatively coupled to the vision device and receiving the digital image of the part. The part inspection module includes an image quality module. The image quality module analyzes the digital image to determine if the digital image achieves a quality threshold. The image quality module generates an image quality output based on the analysis of the digital image. The part inspection module includes an image classifier module. The image classifier module analyzes the digital image to classify the image as a defective part or a non-defective part.

First claim

What is claimed is:

1 . A part inspection system comprising:
a vision device configured to image a part being inspected and generate a digital image of the part; a part inspection module communicatively coupled to the vision device and receiving the digital image of the part, the part inspection module including an image quality module, the image quality module analyzing the digital image to determine if the digital image achieves an image quality threshold for the image, the image quality module generating an image quality output based on the analysis of the digital image, the part inspection module including an image classifier module, the image classifier module analyzing the digital image to classify the part shown in the image as a defective part or a non-defective part, wherein the image classifier module does not analyze the image if the digital image fails the image quality threshold.

2 . The part inspection system of claim 1 , wherein the image quality module includes one or more processors configured to analyze the digital image to determine if the digital image achieves the image quality threshold.

3 . The part inspection system of claim 1 , wherein the image classifier module includes one or more processors configured to analyze the digital image to classify the part shown in the image as a defective part or a non-defective part.

4 . The part inspection system of claim 1 , wherein the image quality module analyzes the digital image based on image lighting.

5 . The part inspection system of claim 4 , wherein the image lighting is based on at least one of light intensity, ambient lighting, and background lighting.

6 . The part inspection system of claim 1 , wherein the image quality module analyzes the digital image based on image clarity.

7 . The part inspection system of claim 6 , wherein the image clarity is based on at least one of image resolution, working distance of the vision device from the part, background behind the part, focus of a lens of the vision device, zoom level of the vision device.

8 . The part inspection system of claim 1 , wherein the image quality output is a pass output if the digital image passes the image quality threshold and the image quality output is a fail output if the digital image fails the image quality threshold, the image classifier module analyzing the image only if receiving the pass output from the image quality module.

9 . The part inspection system of claim 1 , wherein the part inspection module includes an artificial intelligence (AI) module to analyze the images, the AI module operable in a training mode, at least one of the image quality module or the image classifier module is updated in the training mode.

10 . The part inspection system of claim 1 , wherein the part inspection module includes a memory for storing a neural network architecture having a plurality of convolutional layers, a plurality of pooling layers disposed after different convolutional layers and spaced apart from each other, and an output layer, the image classifier module including a processor configured to analyze the digital image through the layers of the neural network architecture to output one of a defective output or a non-defective output based on the image analysis of the digital image through the neural network architecture.

11 . The part inspection system of claim 10 , wherein the neural network architecture performs a principle component analysis to perform feature extraction, the image classifier module analyzing the digital image based on the feature extraction.

12 . The part inspection system of claim 10 , wherein the neural network architecture includes a VGG neural network.

13 . The part inspection system of claim 1 , further comprising a controller, the controller being operably coupled to the vision device to control operation of the vision device, the controller being operably coupled to the part inspection module and receiving an output of the part inspection module, the controller being operatively coupled to a secondary component and sending a signal to the secondary component based on the received output.

14 . The part inspection system of claim 13 , wherein the secondary component is an actuator configured to move the part, the signal from the controller causing the actuator to move the part differently dependent on the received output.

15 . The part inspection system of claim 13 , wherein the secondary component is a lighting device, the signal from the controller causing the lighting device to change lighting of the part dependent on the received output.

16 . The part inspection system of claim 13 , wherein the secondary component is a user interface having an indicator, the signal from the controller causing the indicator to operate differently dependent on the received output.

17 . The part inspection system of claim 1 , wherein the vision device includes a camera configured to image a cross hole and surrounding areas of the part including any burr defects in the cross hole, the neural network architecture analyzing the image to determine if the burr defects are present or absent.

18 . A part inspection method comprising:
imaging a part using a vision device to generate a digital image; analyzing the digital image through an image quality module of a part inspection system by comparing the digital image to an image quality threshold to determine if the digital image passes or fails the image quality threshold for the image; analyzing the digital image through an image classifier module of the part inspection system, if the digital image passes the image quality threshold, to determine if the part shown in the image is defective or non-defective, wherein the image classifier module does not analyze the image if the digital image fails the image quality threshold; and outputting one of a defective output or a non-defective output based on the image analysis of the digital image.

19 . The part inspection method of claim 18 , wherein said analyzing the digital image through an image quality module includes analyzing the digital image based on image lighting and based on image clarity.

Assignees

• TE Connectivity Services Gmbh
• Tyco Electronics Mexico S De R L De C V
• Tyco Electronics Shanghai Co Ltd
• Te Connectivity Solutions Gmbh
• Amp Ameremax S A De C V

Inventors

• Osunkwo Sonny O
• Slistan Angel Alberto
• Clayton Jorge Enrique
• Zhou Lei
• Lu Roberto Francisco-Yi
• Zhou Jiankun
• Martinez Luis Ernesto Thomson
• Diaz Christopher Arce
• Machado Nicole Castillo
• Waissman Julio

Classifications

• H04N23/66

  Remote control of cameras or camera parts, e.g. by remote control devices · CPC title

• H04N23/56 Primary

  provided with illuminating means · CPC title

• G06V10/7747

  Organisation of the process, e.g. bagging or boosting · CPC title

• G06T2200/24

  involving graphical user interfaces [GUIs] · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title