Blast patterns
Techniques for improving a blast pattern at a mining site include conducting an initial blast and recording the initial blast as a high speed optical video. The high speed optical video, and the blast pattern used in the initial blast are sent as inputs to a machine learning model, which correlates one or more characteristics of the region being blasted with measurements associated with characteristics of the region being blasted obtained from the high speed optical video. The machine learning model can then determine an improved blast pattern based on the correlation made. This improved blast pattern can be displayed on a user computing device, or transmitted to a drilling system to automatically drill the improved blast pattern for subsequent blasts.
1. A method for blasting comprising:
identifying an initial blast pattern criteria
recording a high speed optical video of a blast conducted in accordance with the initial blast pattern criteria;
determining, by a machine learning model, one or more characteristics of an identified blasting region by correlating the high speed optical video with a plurality of measurements associated with the blasting region;
determining, by the machine learning model and based on the characteristics of the blasting region, an improved blast pattern criteria; and
generating for display on a user computing device, data indicating improved blast pattern criteria.
2. The method of claim 1 , further comprising:
identifying a three dimensional (3D) block model of the blasting region;
determining, by the machine learning model and based on the correlation, an updated 3D block model of the blasting region; and
generating for display on a user computing device, data indicating the updated 3D block model of the blasting region.
3. The method of claim 1 , further comprising:
using the improved blast pattern criteria as the initial blast pattern criteria in additional blasting events.
4. The method of claim 1 , wherein the one or more characteristics of the blasting region comprises at least one of geology type, defect locations, density, or rock hardness.
5. The method of claim 1 , wherein the measurements associated with the characteristics of the blasting region comprise at least one of fragment size, fragment velocity, fragment shape, fragment color, fragment travel distance, fracture length, fracture width, or fracture propagation rate.
6. The method of claim 1 , wherein the machine learning model comprises an artificial neural network.
7. The method of claim 1 , wherein the machine learning model is trained on a data corpus that comprises a plurality of high speed videos of blasting, wherein the blasting occurs in a region of known geology.
8. The method of claim 1 , wherein the high speed optical video is filmed with an aerial filming device.
9. The method of claim 8 , wherein the aerial filming device comprises:
an unmanned drone; and
a high speed optical recording device.
10. The method of claim 1 , wherein the initial and improved blast pattern criteria comprise at least one of:
a location for each of a plurality of charges;
a size of each charge;
a type of each charge;
a number of charges in the plurality of charges;
a depth of each charge; or
a detonation timing for each charge.
11. The method of claim 10 , wherein correlating the high speed optical video with one or more characteristics of the blasting region further comprises providing seismic data associated with the blast as input to the machine learning model.
12. A non-transitory computer readable storage medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
identifying an initial blast pattern criteria
recording a high speed optical video of a blast conducted in accordance with the initial blast pattern criteria;
determining, by a machine learning model, one or more characteristics of an identified blasting region by correlating the high speed optical video with a plurality of measurements associated with the blasting region;
determining, by the machine learning model and based on the characteristics of the blasting region, an improved blast pattern criteria; and
generating for display on a user computing device, data indicating improved blast pattern criteria.
13. The computer readable medium of claim 12 , further comprising:
identifying a three dimensional (3D) block model of the blasting region;
determining, by the machine learning model and based on the correlation, an updated 3D block model of the blasting region; and
generating for display on a user computing device, data indicating the updated 3D block model of the blasting region.
14. The computer readable medium of claim 12 , further comprising:
using the improved blast pattern criteria as the initial blast pattern criteria in additional blasting events.
15. The computer readable medium of claim 12 , wherein the one or more characteristics of the blasting region comprises at least one of geology type, defect locations, density, or rock hardness.
16. The computer readable medium of claim 12 , wherein the measurements associated with the characteristics of the blasting region comprise at least one of fragment size, fragment velocity, fragment shape, fragment color, or fragment travel distance.
17. The computer readable medium of claim 12 , wherein the high speed optical video is filmed at greater than 240 frames per second (FPS).
18. The computer readable medium of claim 12 , wherein the machine learning model is trained on a data corpus that comprises a plurality of high speed videos of blasting, wherein the blasting occurs in a region of known geology.
19. The computer readable medium of claim 12 , wherein the high speed optical video is filmed with an aerial filming device.
20. The computer readable medium of claim 12 , wherein the improved blast pattern criteria is an optimized blast pattern criteria.
21. The computer readable medium of claim 12 , wherein the initial and improved blast pattern criteria comprise at least one of:
a location for each of a plurality of charges;
a size of each charge;
a type of each charge;
a number of charges in the plurality of charges;
a depth of each charge; or
a detonation timing for each charge.
22. The computer readable medium of claim 12 , wherein correlating the high speed optical video with one or more characteristics of the blasting region further comprises providing seismic data associated with the blast as input to the machine learning model.
23. A blast mining system, comprising:
one or more processors;
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:
identifying an initial blast pattern criteria
recording a high speed optical video of a blast conducted in accordance with the initial blast pattern criteria;
determining, by a machine learning model, one or more characteristics of an identified blasting region by correlating the high speed optical video with a plurality of measurements associated with the blasting region;
determining, by the machine learning model and based on the characteristics of the blasting region, an improved blast pattern criteria; and
generating for display on a user computing device, data indicating improved blast pattern criteria.
24. The system of claim 23 , wherein the operations further comprise:
identifying a three dimensional (3D) block model of the blasting region;
determining, by the machine learning model and based on the correlation, an updated 3D block model of the blasting region; and
generating for display on a user computing device, data indicating the updated 3D block model of the blasting region.
25. The system of claim 23 , wherein the operations further comprise:
using the improved blast pattern criteria as the initial blast pattern criteria in additional blasting events.
26. The system of claim 23 , wherein the one or more characteristics of the blasting region comprises at least one of geology type, defect locations, density, or rock hardness.
27. The system of claim 23 , wherein the measurements associated with the characteristics of the blasting region comprise at least one of fragment size, fragment velocity, fragment shape, fragment color, or fragment travel distance.
28. The system of claim 23 , wherein the machine learning model comprises an artificial neural network.
29. The system of claim 23 , wherein the machine learning model is trained on a data corpus that comprises a plurality of high speed videos of blasting, wherein the blasting occurs in a region of known geology.
30. The system of claim 23 , wherein the high speed optical video is filmed with an aerial filming device.
31. The system of claim 23 , wherein the improved blast pattern criteria is an optimized blast pattern criteria.
32. The system of claim 23 , wherein the initial and improved blast pattern criteria comprise at least one of:
a location for each of a plurality of charges;
a size of each charge;
a type of each charge;
a number of charges in the plurality of charges;
a depth of each charge; or
a detonation timing for each charge.
33. The system of claim 23 , wherein correlating the high speed optical video with one or more characteristics of the blasting region further comprises providing seismic data associated with the blast as input to the machine learning model.
34. The system of claim 23 , wherein the high speed optical video comprises at least two videos recorded in at least two different locations.
35. The system of claim 23 , wherein the improved blast pattern is automatically transmitted to a drilling system for subsequent drilling and blasting events.