System and method for determining locations for recoverable mineral in a stockpile
The method may comprise receiving historical data (e.g., mineralogy data, irrigation data, raffinate data, heat data, lift height data, geographic data on ore placement and/or blower data); training a predictive model using the historical data to create a trained predictive model; adding future assumption data to the trained predictive model; running the forecast engine for a plurality of parameters to obtain forecast data for a mining production target; comparing the forecast data for the mining production target to the actual data for the mining production target; determining deviations between the forecast data and the actual data, based on the comparing; and changing each of the plurality of parameters from the forecast data to the actual data to determine a contribution to the deviations for each of the plurality of parameters.
1 . A method comprising:
receiving, by one or more processors, ore placement data for a stockpile, wherein the ore placement data comprises dispatch data, haul truck sensor data, polygon data, assay data and mineralogy data;
determining, by the one or more processors, ore placement locations for the stockpile, based on the ore placement data;
determining, by the one or more processors, mineral extracted from the stockpile, based on historical leaching process data for the stockpile;
determining, by the one or more processors, recovery locations for recoverable mineral in the stockpile, based on historical leaching process data for the stockpile; and
performing percolating of leaching on the recovery locations, in response to receiving an activation signal activating a leaching device to optimize metal production.
2 . The method of claim 1 , wherein the mineralogy data is from the block model and included in the mine material tracking data.
3 . The method of claim 1 , wherein the determining the ore placement locations of recoverable minerals for the stockpile includes determining the total mineralogy for the stockpile.
4 . The method of claim 3 , wherein the determining the total mineralogy for the stockpile comprises:
aggregating mineralogy details to a section level by combining mine material tracking (MMT) truckload data at a dump level, MMT imputation data at the dump level and MMT final section mapping data at the dump level and the section level;
obtaining maximum days under leach (DUL) for each section at the section level by using irrigation data over all stockpiles at the section level; and
determining an intermediate ore map for a stockpile by combining the aggregating mineralogy details, the maximum DUL for each section and a primary new section polygon.
5 . The method of claim 1 , wherein the determining the amount of mineral extracted from the stockpile comprises determining a primary ore map for the stockpile.
6 . The method of claim 5 , wherein the determining the primary ore map for the stockpile comprises adding flow data, irrigation data and a remaining mineral prediction from a machine learning model to obtain information by section and by date for the stockpile.
7 . The method of claim 5 , wherein the determining the primary ore map for the stockpile comprises:
merging date and the stockpile at a date level and a section level by combining the PLS, raffinate flow and chemistry concentration at the date level and the stockpile level with the irrigation on the stockpile at the date level and the section level;
merging the section at the date level and the section level by combining the merge on data and the stockpile with the intermediate ore map for the stockpile;
predicting an estimated mineral recovery using a column test model with machine learning model predictions, based on the merge on section; and
creating the primary ore map for the stockpile at the section level based on the estimated mineral recovery.
8 . The method of claim 1 , further comprising reallocating the ore in neighboring sections to side slopes of the stockpile.
9 . The method of claim 8 , wherein the reallocating the ore in the neighboring sections to the side slopes of the stockpile comprises:
merging on the date and the stockpile at the date level and section level by combining the raffinate flow and acid content at the date level and the stockpile level with the irrigation on the stockpile with acid content at the date level and the section level;
combining the primary ore map for the stockpile at the section level with the primary new section polygon;
combining the reallocating of the ore with the merge on data and stockpile to create the merge on section at the date level and the section level;
predicting the mineral recovery using a column test model with machine learning model predictions, based on the creating the merge on section; and
creating the primary ore map slope for the stockpile at the section level based on the mineral recovery.
10 . The method of claim 1 , further comprising providing a visualization of the recovery locations for the recoverable amounts of mineral in the stockpile.
11 . The method of claim 1 , further comprising determining at least one of x,y,z coordinates or time-series layering information for the recovery locations for the recoverable amounts of mineral in the stockpile.
12 . The method of claim 1 , further comprising providing a visualization of section mineralogy populated on a map of each of the stockpiles.
13 . The method of claim 1 , further comprising filtering of the sections by at least one of lift, stockpile or mineralogy composition.
14 . The method of claim 1 , further comprising displaying aggregated values for at least a subset of the sections.
15 . The method of claim 1 , further comprising defining boundaries of the stockpiles and the sections based on polygons recorded in a geographic information system (GIS).
16 . The method of claim 15 , further comprising mapping dump locations of haul trucks into the polygons based on combined signals from at least one of MMT location information, GPS coordinates or a map of section identifiers and sub-piles to the stockpiles.
17 . The method of claim 16 , further comprising aggregating and averaging the MMT location information to estimate section-level characterizations of mineralogy and 80 th quantile particle size (P80).
18 . The method of claim 1 , further comprising estimating the recoverable amounts of mineral in the stockpile based on a column test model.
19 . The method of claim 1 , further comprising calculating the recoverable amounts of mineral at the section-level by deducting estimated recovered mineral from initial placements.
20 . The method of claim 1 , further comprising determining which sections are economically viable for recovery via irrigation based on a number of contiguous high-remaining sections and the proximity of the high-remaining sections to a top lift.
21 . The method of claim 1 , wherein the ore placement data further comprises data from a column test predictive model.
22 . The method of claim 1 , further comprising transmitting, by the one or more processors, the recovery locations to a forecast model input table.
23 . An article of manufacture including one or more non-transitory, tangible computer readable storage mediums medium-having instructions stored thereon that, in response to execution by one or more processors, cause the one or more processors to perform operations comprising:
receiving, by the one or more processors, ore placement data for a stockpile, wherein the ore placement data comprises dispatch data, haul truck sensor data, polygon data, assay data and mineralogy data;
determining, by the one or more processors, ore placement locations for the stockpile, based on the ore placement data;
determining, by the one or more processors, mineral extracted from the stockpile, based on historical leaching process data for the stockpile;
determining, by the one or more processors, recovery locations for recoverable mineral in the stockpile, based on historical leaching process data for the stockpile; and
performing percolating of leaching on the recovery locations, in response to receiving an activation signal activating a leaching device to optimize metal production.
24 . A system comprising:
one or more processors; and
one or more tangible, non-transitory memories configured to communicate with the one or more processors,
the one or more tangible, non-transitory memories having instructions stored thereon that, in response to execution by the one or more processors, cause the one or more processors processor to perform operations comprising:
receiving, by the one or more processors, ore placement data for a stockpile, wherein the ore placement data comprises dispatch data, haul truck sensor data, polygon data, assay data and mineralogy data;
determining, by the one or more processors, ore placement locations for the stockpile, based on the ore placement data;
determining, by the one or more processors, mineral extracted from the stockpile, based on historical leaching process data for the stockpile;
determining, by the one or more processors, recovery locations for recoverable mineral in the stockpile, based on historical leaching process data for the stockpile; and
performing percolating of leaching on the recovery locations, in response to receiving an activation signal activating a leaching device to optimize metal production.