Intelligent monitoring system for mineral loading process
AssigneeJebi S.A.C.
InventorsMauricio Mesones Aurich, Christian Portugal Zambrano, Eder Joel Vivanco Olivera, Yherico Alberto Carpio Reynoso, Marlon Arnaldo Valerio Ogosi
Life of this patent
Estimating the term…
Abstract
The “GET smart” system uses AI modeling and neural network technology to efficiently identify wear part loss events and provide other useful metrics during excavator operation to improve efficiency and reduce downtime. The system monitors the integrity of ground engaging tools (GETs) by way of multidimensional sensors, determining regions of interest, and creating and processing enriched tensors via embedded systems with a combination of CPUs and TPUs.
Claims5
An AI-based monitoring system for use with detecting the condition of a shovel during mineral loading in a mining operation, the system comprising:
- one or more sensors;
- an enriched tensor data structure, further comprising storage for color image data, point cloud data, depth data, and inertial data;
- a weighing mechanism;
- one or more outputs;
- an artificial intelligence module, further comprising a plurality of neural networks adapted to detect a plurality of objects of interest, wherein:
- one or more neural networks are configured to process only color images;
- one or more neural networks are configured to process only point clouds;
- one or more neural networks are configured to process only depth maps;
- one or more neural networks are configured to process only inertial data;
- one or more foundational models adapted to detect objects of interest and are configured to holistically process color images, point clouds, depth maps, and inertial data;
- and
- the one or more neural networks and foundational models each return a result in the form of a predicted object label and a confidence level.
A method of detecting the condition of a shovel during mineral loading in a mining operation, the method comprising:
- defining one or more regions of interest where an object of interest is likely to be found;
- building an enriched tensor data structure based on time-divided frames;
- processing the enriched tensor with an artificial intelligence module;
- processing one or more results of the artificial intelligence module with a weighing mechanism;
- generating an alert based on the results of the weighing mechanism;
- wherein the artificial intelligence module comprises:
- a plurality of neural networks, wherein a first set of neural networks process color image data, a second set of neural networks process point cloud data, a third set of neural networks process depth data, and a fourth set of neural networks process inertial data;
- and
- one or more vision transformers that process data from the enriched tensor in its entirety.
Dependencies are inferred from the claim text.