Sorting materials using a pattern recognition, such as upgrading nickel laterite ores through electromagnetic sensor-based methods

• US 9,316,537 B2
• Filed: 03/14/2013
• Issued: 04/19/2016
• Est. Priority Date: 06/29/2011
• Status: Active Grant

• Current Assignee: MineSense Technologies Ltd.
• Original Assignee: MineSense Technologies Ltd.
• Inventors: Bamber, Andrew Sherliker, Barcza, Nicholas, Csinger, Andrew
• Primary Examiner(s): LOGAN, KYLE O
• Application Number:
  US13/830,453
• Publication Number:
  US 20130201481A1
• Time in Patent Office: 1,132 Days
• Field of Search: 700/223
• US Class Current: 1/1
• CPC Class Codes: B07C 5/3416 according to radiation transmissivity, e.g. for light, x-rays, particle radiation detecting hidden objects G01V
• CPC Class Codes: B07C 5/342 according to optical properties, e.g. colour according to radiation transmittivity B07C5/3416
• CPC Class Codes: B07C 5/344 according to electric or electromagnetic properties sorting according to size measured electrically or electronically B07C5/08; material testing by magnetic means G01N24/00, G01N27/00, by electrical means G01N27/00; electrical measuring devices in general G01R; coin testing G07D5/00
• CPC Class Codes: G01J 3/00 Spectrometry; Spectrophotometry; Monochromators; Measuring colours
• CPC Class Codes: G01N 21/27 using photo-electric detection G01N21/31 takes precedence; circuits for computing concentration logarithmic circuits G06G7/24; photometric circuits in general G01J
• CPC Class Codes: G01N 2223/302 comparative arrangements
• CPC Class Codes: G01N 2223/635 fluids, granulates
• CPC Class Codes: G01N 2223/643 object on conveyor
• CPC Class Codes: G01N 23/12 the material being a flowing fluid or a flowing granular solid

Abstract

A system and method of sorting mineral streams, for example laterite mineral ores, into appropriately classified valuable and waste streams for maximum recovery of value from the mineral stream, e.g., a stream of minerals includes receiving response data indicating reflected, absorbed or backscattered energy from a mineral sample exposed to a sensor, where the mineral sample is irradiated with electromagnetic energy. The system determines spectral characteristics of the mineral sample by performing spectral analysis on the response data of the mineral sample and identifies a composition of the mineral sample by comparing the spectral characteristics of the mineral sample to previously developed spectral characteristics of samples of known composition. The system then generates a sort decision for the mineral sample based on the comparison, where the sort decision is used in diverting the mineral sample to a desired destination e.g. pyrometallurgical treatment stages, or to a waste stream.

Claims

1. A method of sorting a stream of minerals, comprising:

irradiating a mineral sample with electromagnetic energy to thereby generate reflected, absorbed, or backscattered energy from the mineral sample;

measuring the reflected, absorbed or backscattered energy generated by irradiating the mineral sample with a sensor configured to measure reflected, absorbed or backscattered energy;

determining spectral characteristics of the mineral sample by performing spectral analysis on the measured reflected, absorbed or backscattered energy generated by irradiating the mineral sample,

wherein the spectral characteristics include at least one of frequency content, wavelength content, or amplitude of the response data;

identifying a composition of the mineral sample by comparing the spectral characteristics of the mineral sample to previously developed spectral characteristics of samples of known composition,

wherein the spectral characteristics of samples of known composition are developed using at least one of;

conditional random field algorithms, Bayesian network, one or more Markov models, neural networks, or fuzzy logic techniques; and

generating a sort decision for the mineral sample based on the comparison,

wherein the sort decision is used in diverting the mineral sample to a desired destination.

2. The method of claim 1 further comprising collecting spectral response data from a series of mineral samples irradiated with electromagnetic energy and exposed to a sensor to develop the spectral characteristics of samples of known composition.

3. The method of claim 1 wherein comparing the spectral characteristics of the mineral sample to previously developed spectral characteristics of samples of known composition includes matching the spectral characteristics of the mineral sample to previously developed pattern sets.

4. The method of claim 1 wherein identifying a composition of the mineral sample includes assigning a compositional value to the mineral sample based on the comparison.

5. The method of claim 4 wherein the mineral sample is diverted to an accept pile when the compositional value is within a predetermined variation of the previously developed spectral characteristics.

6. At least one tangible computer-readable medium carrying instructions, which when executed by at least one processor, determines a composition of a mineral sample, comprising:

measuring reflected, absorbed or backscattered energy generated by exposing an unblended mineral sample to electromagnetic radiation;

comparing the measured reflected, absorbed or backscattered energy to previously recorded response data from samples of known composition to identify a composition of the unblended mineral sample; and

assigning a compositional value to the unblended mineral sample based on the comparison.

7. The at least one tangible computer-readable medium of claim 6, wherein the unblended mineral sample is a laterite, and wherein the sort signal is used to divert the mineral sample to one of:

a hydrometallurgical process, a pyrometallurgical process, or a waste pile.

8. The at least one tangible computer-readable medium of claim 6, wherein the instructions, which when executed by the at least one processor, further comprise:

transporting the unblended mineral sample into a source field.

9. The at least one tangible computer-readable medium of claim 6, wherein the instructions, which when executed by the at least one processor, further comprise:

generating a signal based on the compositional value.

10. The at least one tangible computer-readable medium of claim 9, wherein the signal is a sort signal used to divert the unblended mineral sample to a desired location.

11. A system for sorting minerals, comprising:

a device to introduce unblended mineral samples to a sensor;

a device to generate electromagnetic energy to apply to the unblended mineral samples and thereby generate reflected, absorbed or backscattered energy from the unblended mineral sample;

a scanner configured to measure the reflected, absorbed or backscattered energy generated by applying electromagnetic energy to the unblended mineral samples;

a means for comparing the reflected, absorbed or backscattered energy to previously determined response data of samples of known composition to determine a composition of the unblended mineral samples.

12. The system of claim 11 further comprising:

an analog to digital converter to digitize the measured reflected, absorbed or backscattered energy;

a control system to process signal outputs; and

a diverter coupled to the control system for the diversion of the mineral samples.

13. The system of claim 11 further comprising a graphical user interface to control operation and record data.

14. The system of claim 11 wherein the response data of samples of known composition includes spectral characteristics.

15. The system of claim 14 wherein the spectral characteristics of samples of known composition are developed using at least one of:

conditional random field algorithms, Bayesian network, one or more Markov models, neural networks, or fuzzy logic techniques.

16. A method of maximizing the recovered value of mineral ores, comprising:

extracting unblended mineral ore from a mine bench or pit using a mechanical excavator or similar earthmoving device;

delivering the unblended mineral ore to a haul truck or conveyor belt using the excavator;

transporting the unblended mineral ore to a first mineral sorting system, the first mineral sorting system configured to;

apply electromagnetic radiation to the unblended mineral ore,

detect a response of the mineral ore to the electromagnetic radiation, and

compare the response data to previously determined response data of samples of known composition to determine the composition of the unblended mineral ore;

classifying the unblended mineral ore, based on the comparison, into a first mineral product and a second mineral product;

transporting the first mineral product to a second mineral sorting system, the second mineral sorting system configured to;

apply electromagnetic radiation to the first mineral product;

detect a response of the first mineral product to the electromagnetic radiation, and

compare the response data to previously determined response data of samples of known composition to determine the composition of the first mineral product;

classifying the first mineral product, based on the comparison, into a final first mineral product and waste product;

transporting the second mineral product to a third mineral sorting system, the third mineral sorting system configured to;

apply electromagnetic radiation to the second mineral product;

detect a response of the second mineral product to the electromagnetic radiation, and

compare the response data to previously determined response data of samples of known composition to determine the composition of the second mineral product;

classifying the second mineral product, based on the comparison, into a final second mineral product and waste product.

17. The method of claim 16, wherein:

the final first mineral product is conditioned for pyrometallurgical treatment,

the final second mineral product is conditioned for hydrometallurgical treatment, and

the waste product is conditioned for disposal as a waste product.