Determining ore characteristics

Patent metadata

Field	Value
Publication number	US-11867608-B2
Application number	US-202217832910-A
Country	US
Kind code	B2
Filing date	Jun 6, 2022
Priority date	Jun 5, 2019
Publication date	Jan 9, 2024
Grant date	Jan 9, 2024

Abstract

Techniques for processing ore include the steps of causing an imaging capture system to record a plurality of images of a stream of ore fragments en route from a first location in an ore processing facility to a second location in the ore processing facility; correlating the plurality of images of the stream of ore fragments with at least one or more characteristics of the ore fragments using a machine learning model that includes a plurality of ore parameter measurements associated with the one or more characteristics of the ore fragments; determining, based on the correlation, at least one of the one or more characteristics of the ore fragments; and generating, for display on a user computing device, data indicating the one or more characteristics of the ore fragments or data indicating an action or decision based on the one or more characteristics of the ore fragments.

First claim

What is claimed is:

1. An ore processing system, comprising:
one or more processors; and
one or more tangible, non-transitory media operably connectable to the one or more processors and storing instructions that, when executed, cause the one or more processors to perform operations comprising:
causing an imaging capture system to record a plurality of images of a stream of ore fragments en route from a first location in an ore processing facility to a second location in the ore processing facility, wherein the ore fragments are treated with a fluid imaging enhancement prior to the recording of the plurality of images;
correlating the plurality of images of the stream of ore fragments with one or more characteristics of the ore fragments using a machine learning model that comprises a plurality of ore parameter measurements associated with the one or more characteristics of the ore fragments;
determining, based on the correlation, at least one of the one or more characteristics of the ore fragments;
determining, based on at least one of the plurality of images, an anomaly within the stream of ore fragments;
based on the determination of the anomaly, causing a change to an operation of the ore processing facility; and
generating, for display on a user computing device, data indicating the one or more characteristics of the ore fragments or data indicating an action or decision based on the one or more characteristics of the ore fragments.

2. The system of claim 1 , wherein the plurality of images comprise:
images comprising layers of red, green, blue, and grey;
hyperspectral images;
acoustic images;
gravimetric images; or
depth imagery images.

3. The system of claim 1 , wherein the plurality of ore parameter measurements comprise measurements based on at least one of x-ray diffraction (XRD), x-ray fluorescence (XRF), or energy dispersive x-ray (EDS).

4. The system of claim 1 , wherein the one or more characteristics comprises at least one of mineral composition, density, porosity, fracture type, fragment size, fragment moisture content, or hardness.

5. The system of claim 1 , wherein causing a change to the operation of the ore processing facility comprises at least one of:
causing a change of route of the stream of ore fragments from the first location in the ore processing facility to a third location in the ore processing facility different than the second location;
causing a stop to a movement of the stream of ore fragments en route from the first location in the ore processing facility to the second location in the ore processing facility; or
causing an adjustment of an ore source of the stream of ore fragments moving through the ore processing facility.

6. The system of claim 1 , further comprising an electromagnetic (EM) imaging system, the operations further comprising:
causing the EM imaging system to record a plurality of EM images of the stream of ore fragments moving from the first location in the ore processing facility to the second location in the ore processing facility; and
determining, based on the plurality of EM images, one or more mineral characteristics of the ore fragments.

7. The system of claim 6 , wherein the one or more mineral characteristics comprises at least one of ore fragment density, ore fragment size, or ore fragment surface composition.

8. The system of claim 1 , wherein causing the imaging capture system to record the plurality of images of the stream of ore fragments en route from the first location in the ore processing facility to the second location in the ore processing facility comprises:
causing the imaging capture system to record the plurality of images of the stream of ore fragments as the ore fragments are moving on a conveyor or belt continuous feed system from the first location in the ore processing facility to the second location in the ore processing facility.

9. The system of claim 1 , wherein the machine learning model is trained on a data corpus that comprises a plurality of ore fragment samples measured by at least one of x-ray diffraction (XRD), x-ray fluorescence (XRF), or energy dispersive x-ray (EDS) to correlate a plurality of ore parameter measurements of the ore fragment samples with at least one ore fragment characteristic of the ore fragment samples.

10. A computer-implemented ore processing method executed by one or more processors, the method comprising:
causing an imaging capture system to record a plurality of images of a stream of ore fragments en route from a first location in an ore processing facility to a second location in the ore processing facility, wherein the ore fragments are treated with a fluid imaging enhancement prior to the recording of the plurality of images;
correlating the plurality of images of the stream of ore fragments with one or more characteristics of the ore fragments using a machine learning model that comprises a plurality of ore parameter measurements associated with the one or more characteristics of the ore fragments;
determining, based on the correlation, at least one of the one or more characteristics of the ore fragments;
determining, based on at least one of the plurality of images, an anomaly within the stream of ore fragments;
based on the determination of the anomaly, causing a change to an operation of the ore processing facility; and
generating, for display on a user computing device, data indicating the one or more characteristics of the ore fragments or data indicating an action or decision based on the one or more characteristics of the ore fragments.

11. The method of claim 10 , wherein the plurality of images comprise:
images comprising layers of red, green, blue, and grey;
hyperspectral images;
acoustic images;
gravimetric images; or
depth imagery images.

12. The method of claim 10 , wherein the plurality of ore parameter measurements comprise measurements based on at least one of x-ray diffraction (XRD), x-ray fluorescence (XRF), or energy dispersive x-ray (EDS).

13. The method of claim 10 , wherein the one or more characteristics comprises at least one of mineral composition, density, porosity, fracture type, fragment size, fragment moisture content, or hardness.

14. The method of claim 10 , wherein causing a change to the operation of the ore processing facility comprises at least one of:
causing a change of route of the stream of ore fragments from the first location in the ore processing facility to a third location in the ore processing facility different than the second location;
causing a stop to a movement of the stream of ore fragments en route from the first location in the ore processing facility to the second location in the ore processing facility; or
causing an adjustment of an ore source of the stream of ore fragments moving through the ore processing facility.

15. The method of claim 10 , further comprising an electromagnetic (EM) imaging system, the operations further comprising:
causing the EM imaging system to record a plurality of EM images of the stream of ore fragments moving from the first location in the ore processing facility to the second location in the ore processing facility; and
determining, based on the plurality of EM images, one or more mineral characteristics of the ore fragments.

16. The method of claim 15 , wherein the one or more mineral characteristics comprises at least one of ore fragment density, ore fragment size, or ore fragment surface composition.

17. The method of claim 10 , wherein causing the imaging capture system to record the plurality of images of the stream o

Assignees

• X Dev Llc

Inventors

• Hunt Thomas Peter
• Treat Neil David
• Davis Karen R
• Goncharuk Artem
• Sahney Vikram Neal

Classifications

• G06N3/094

  Adversarial learning · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/0455

  Auto-encoder networks; Encoder-decoder networks · CPC title

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title