Surface roughness measurement system

Patent metadata

Field	Value
Publication number	US-12372349-B2
Application number	US-202118260715-A
Country	US
Kind code	B2
Filing date	Jan 13, 2021
Priority date	Jan 13, 2021
Publication date	Jul 29, 2025
Grant date	Jul 29, 2025

Abstract

It is known for a product to be mass produced by way of a manufacturing process. Typically, a quality control step is used in a manufacturing process to monitor the quality of manufactured products. However, quality control procedures in manufacturing are typically labour intensive. A technician or other person must inspect the product and carry out any necessary tests. The present disclosure provides a surface roughness measurement system and method for determining a surface roughness of a product with an imaging system, a coherent light source, a light sensor and several trained machine learning algorithms.

First claim

The invention claimed is:

1. A surface roughness measurement system comprising:
an imaging system configured to, in use, image a target surface;
a coherent light source configured to, in use, illuminate the target surface;
a light sensor configured to, in use, detect light from the coherent light source that is reflected by the target surface; and
a processor configured and operable to:
capture, with the imaging system, a first image depicting the target surface;
generate, with a trained depth-perception machine learning model, a depth map corresponding to the first image;
determine a maximum and a minimum depth of the first image based on the depth map;
determine the maximum and minimum depths lie within a predetermined acceptable threshold range of depths;
illuminate, with the coherent light source, the target surface;
receive, from the light sensor, a waveform related to light reflected by the target surface;
determine, with a trained material inspection machine learning model, a material of the target surface based on a wavelength or frequency of the waveform;
illuminate, with the coherent light source, an area of interest of the target surface to create a speckle light pattern on the area of interest;
capture, with the imaging system, a second image depicting the area of interest of the target surface;
determine, with a trained surface roughness machine learning model, a value relating to a surface roughness of the area of interest based on the speckle light pattern and the material of the target surface.

2. The surface roughness measurement system of claim 1 , wherein the imaging system comprises a plurality of imaging devices.

3. The surface roughness measurement system of claim 2 , wherein a first imaging device is configured to capture the first image and a second imaging device is configured to capture the second image.

4. The surface roughness measurement system of claim 1 , wherein the coherent light source comprises an infrared laser and the imaging system comprises an infrared camera.

5. The surface roughness measurement system of claim 1 , wherein the processor is further configured to discretise and filter the waveform before applying the trained material inspection machine learning model.

6. The surface roughness measurement system of claim 1 , wherein the processor is further configured to store, in a data store, the material of the target surface following determination of the material.

7. The surface roughness measurement system of claim 6 , wherein the processor is further configured to query the data store for the material type before applying the trained surface roughness machine learning model.

8. The surface roughness measurement system of claim 1 , wherein the predetermined acceptable threshold range of depths includes a measurement tolerance.

9. The surface roughness measurement system of claim 1 , wherein the light sensor is an optoelectronic sensor.

10. The surface roughness measurement system of claim 9 , wherein the optoelectronic sensor comprises a lens to collect and focus light, an optical element to diffract light into separate wavelengths, and an optoelectronic detector.

11. The surface roughness measurement system of claim 1 , wherein the processor is networked with at least one other processor of a surface roughness measurement system according to claim 1 .

12. The surface roughness measurement system of claim 1 , wherein the coherent light source includes a plurality of lasers.

13. The surface roughness measurement system of claim 12 , wherein a first laser is configured to illuminate the target surface and a second laser is configured to illuminate the area of interest of the target surface.

14. The surface roughness measurement system of claim 1 , wherein the trained depth-perception machine learning model is trained with a labelled dataset including images and corresponding depth maps measured with a depth sensor.

15. The surface roughness measurement system of claim 1 , wherein the trained material inspection machine learning model is trained with a labelled dataset including material surface types and corresponding waveforms of coherent light reflected by the material surface and collected by an optoelectronic sensor.

16. The surface roughness measurement system of claim 1 , wherein the trained surface roughness machine learning model is trained with a labelled dataset including speckle pattern images and measured surface roughness values.

17. The surface roughness measurement system of claim 16 , wherein the speckle pattern images are captured by a plurality of co-located cameras.

18. The surface roughness measurement system of claim 17 , wherein contrast calculation and Doppler histogram are performed and stored, the dataset is hashed, and the hashed contrast calculations and the hashed Doppler histogram are appended and stored.

19. A surface roughness measurement method comprising the steps:
capturing, with an imaging system, a first image depicting a target surface;
generating, with a trained depth-perception machine learning model, a depth map corresponding to the first image;
determining a maximum and a minimum depth of the first image based on the depth map;
determining the maximum and minimum depths lie within a predetermined acceptable threshold range of depths;
illuminating, with a coherent light source, the target surface;
receiving, from a light sensor, a waveform related to light reflected by the target surface;
determining, with a trained material inspection machine learning model, a material of the target surface based on a wavelength or frequency of the waveform;
illuminating, with the coherent light source, an area of interest of the target surface to create a speckle light pattern on the area of interest;
capturing, with the imaging system, a second image depicting the area of interest of the target surface;
determining, with a trained surface roughness machine learning model, a value relating to a surface roughness of the area of interest based on the speckle light pattern and the material of the target surface.

20. A manufacturing quality control method comprising the steps of the method of claim 19 , wherein the target surface is a surface of a manufactured component and the manufactured component is rejected if:
the maximum depth lies outside the predetermined acceptable threshold range of depths;
the minimum depth lies outside the predetermined acceptable threshold range of depths; or
the value relating to a surface roughness of the area of interest is outside of a predetermined range of acceptable values.

Assignees

• Eaton Intelligent Power Ltd

Inventors

• Abdulaziz Salma
• Nolan Keith
• Van De Belt Johannes
• Ryle James

Classifications

• G06T2207/30108

  Industrial image inspection · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/10048

  Infrared image · CPC title

• G06T7/40

  Analysis of texture (depth or shape recovery from texture G06T7/529) · CPC title

• G06T7/0004

  Industrial image inspection · CPC title