Mining equipment inspection system, mining equipment inspection method, and mining equipment inspection device

Patent metadata

Field	Value
Publication number	US-12283040-B2
Application number	US-202017761364-A
Country	US
Kind code	B2
Filing date	Jun 30, 2020
Priority date	Sep 20, 2019
Publication date	Apr 22, 2025
Grant date	Apr 22, 2025

Abstract

A computer-implemented point-cloud data acquisitioning method for acquiring point-cloud data of the inside of a mining equipment. The method includes the step of acquiring from a sensor, a first dataset and a second dataset, wherein each dataset includes datapoints at coordinates. The method extracts features from the first and second dataset and aligns the first and second dataset using the extracted features. The first and second dataset are aligned into a point-cloud data. The geometry of the mining equipment is estimated based on the point-cloud data and the point-cloud data is used to identify a region of the estimated geometry indicating insufficient data.

First claim

The invention claimed is:

1. A computer-implemented point-cloud data acquisitioning method for acquiring point-cloud data of the inside of a mining equipment, the method comprising:
acquiring from a sensor, a first dataset and a second dataset, wherein each dataset comprises datapoints at coordinates;
extracting features from the first and second dataset;
aligning the first and second dataset using the extracted features;
combining the aligned first and second dataset into a point-cloud data;
estimating a geometry of the mining equipment based on the point-cloud data;
identifying by use of the point-cloud data a region of the estimated geometry indicating insufficient data.

2. The computer-implemented point-cloud data acquisitioning method according to claim 1 , wherein
if an area of the identified region is above a predetermined area,
a next coordinate is extracted from within the identified area, wherein the next coordinate is a coordinate closest to a scanning direction of the sensor, and
the sensor is caused to move in a direction towards the next coordinate until the next coordinate falls inside a scanning range of the sensor, or
a user is notified of the next coordinate and instructed to move the sensor in a direction towards the next coordinate until the next coordinate falls inside the scanning range of the sensor.

3. The computer-implemented point-cloud data acquisitioning method according to claim 2 , wherein
if the next coordinate falls inside the scanning range of the sensor, the method further comprises:
acquiring from the sensor, a third dataset comprising datapoints at coordinates;
extracting features from the point-cloud data and the third dataset;
aligning the third dataset to the point-cloud data;
combining the aligned third dataset into the point-cloud data;
re-estimating the geometry of the mining equipment as the estimated geometry based on the point-cloud;
re-identifying by use of the point-cloud data a region of the estimated geometry indicating insufficient data as the region indicating insufficient data.

4. The computer-implemented point-cloud data acquisitioning method according to claim 1 , wherein
if an area of the identified region is below a predetermined area, a fault analysis based on the point-cloud data is performed.

5. The computer-implemented point-cloud data acquisitioning method according to claim 1 , wherein
the sensor is a movable sensor, preferably handheld, flying or suspended.

6. The computer-implemented point-cloud data acquisitioning method according to claim 1 , wherein
the sensor is a depth sensor, sensing the distance from the sensor to a surface as depth.

7. The computer-implemented point-cloud data acquisitioning method according to claim 1 , wherein
the sensor senses information about a distance from the sensor to a surface inside the mining equipment as depth information.

8. The computer-implemented point-cloud data acquisitioning method according to claim 1 , wherein
the second dataset is acquired after the first dataset and after the sensor has been moved.

9. The computer-implemented point-cloud data acquisitioning method according to claim 1 , wherein
the sensor obtains information about orientation and/or odometry of the sensor.

10. The computer-implemented point-cloud data acquisitioning method according to claim 1 , wherein
the information about orientation includes roll, pitch and/or yaw information of the sensor; and
the information about odometry includes x, y and z information of the sensor.

11. The computer-implemented point-cloud data acquisitioning method according to claim 1 , wherein
the datapoints are coordinates indicating a location of a surface sensed by the sensor.

12. The computer-implemented point-cloud data acquisitioning method according to claim 1 , wherein
the features are extracted by use of one of feature detection, edge detection, line tracing or spline fitting over a surface represented by the datapoints.

13. The computer-implemented point-cloud data acquisitioning method according to claim 1 , wherein
the extracting extracts principle components of the features for the aligning.

14. The computer-implemented point-cloud data acquisitioning method according to claim 1 , wherein
the aligning comprises linearly transforming, preferably rotating, scaling and/or translating the first, second and/or third dataset to maximize alignment and/or match.

15. The computer-implemented point-cloud data acquisitioning method according to claim 14 , wherein
the alignment between the first, second and/or third dataset and/or point-cloud data is indicated by a dot product of the features, preferably the principle components.

16. The computer-implemented point-cloud data acquisitioning method according to claim 14 , wherein
the alignment of the first, second and/or third dataset and/or point-cloud data is indicated by convolution and/or correlation of the features, preferably the principle component.

17. The computer-implemented point-cloud data acquisitioning method according to claim 1 , wherein
the point-cloud data is meshed before estimating the geometry of the mining equipment.

18. A computer-implemented inspection method for inspecting the inside surface of an operating mining equipment that is performing its mining operation on mining material, the method comprising:
moving a sensor through the inside of the mining equipment;
acquiring by use of the sensor, first point-cloud data and second point-cloud data, wherein the point-cloud data represent a surface inside the mining equipment;
determining based on each the first and second point-cloud data, surfaces inside the mining equipment;
estimating based on the determined surfaces, an inside geometry of the mining equipment.

19. The computer-implemented inspection method according to claim 18 , wherein
the mining equipment is rotating during the acquiring.

20. The computer-implemented inspection method according to claim 18 , wherein
the sensor rotates in a direction opposite to a rotation direction of the mining equipment.

21. The computer-implemented inspection method according to claim 18 , wherein
the sensor rotates at an angular velocity faster than an angular velocity of the mining equipment.

22. The computer-implemented inspection method according to claim 18 , wherein
the mining equipment rotates at an angular velocity equal to or lower than an angular velocity during normal operation.

23. The computer-implemented inspection method according to claim 18 , wherein
the first point-cloud data and the second point-cloud data are acquired according to the method of claim 1 .

24. The computer-implemented inspection method according to claim 18 , wherein
the sensor is moved essentially parallel to a rotating axis of the mining equipment.

25. The computer-implemented inspection method according to claim 18 , wherein
the mining equipment rotates around its rotating axis when operated.

26. The computer-implemented inspection method according to claim 18 , wherein
the second point-cloud data is acquired after the first point-cloud data and after the sensor and/or the mining equipment have/has moved.

27. The computer-implemented inspection method according to claim 18 , wherein
the acquired first and second point-cloud data are corrected in rotation based on the rotation an

Assignees

• Metso Outotec Finland Oy

Inventors

• Johansson Fredrik
• Ståhlbröst Håkan
• Furtenbach Lars
• Fahlgren Johanna
• Kågström Lotta
• Eriksson Magnus J
• Silva Jhino
• Wesly Ruiz Victor

Classifications

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title

• B02C17/18

  Details · CPC title

• G06T7/33

  using feature-based methods · CPC title

• G06T17/00

  Three-dimensional [3D] modelling for computer graphics · CPC title

• G01B21/30

  for measuring roughness or irregularity of surfaces · CPC title