Material handling using machine learning system
Systems and methods for classifying materials utilizing one or more sensor systems, which may implement a machine learning system in order to identify or classify each of the materials, which may then be sorted into separate groups based on such an identification or classification. The machine learning system may utilize a neural network, and be previously trained to recognize and classify certain types of materials.
1 . An apparatus for handling a first mixture of materials comprising different first and second classes of materials, the apparatus comprising:
a sensor configured to capture data including a plurality of pixel values and representing one or more characteristics of each of the first mixture of materials; and
a data processing system comprising a machine learning system configured to receive the captured data as input to classify certain ones of the first mixture as belonging in the first class of materials based on each pixel value from the plurality of pixel values, wherein the classifying of certain ones of the first mixture is based on a previously generated first knowledge base of characteristics captured from one or more samples of the first class of materials.
2 . The apparatus as recited in claim 1 , wherein the sensor is a camera, and wherein the one or more captured characteristics were captured by the camera configured to capture images of the one or more samples of the first class of materials as they were conveyed past the camera.
3 . The apparatus as recited in claim 2 , wherein the camera is configured to capture visual images of the first mixture of materials to produce image data, and wherein the characteristics are visually observed characteristics.
4 . The apparatus as recited in claim 1 , further comprising:
a conveyor system configured to convey the first mixture past the sensor; and
a sorter configured to sort the classified certain ones of the first mixture from the first mixture as a function of the classifying of certain ones of the first mixture.
5 . The apparatus as recited in claim 4 , wherein the sorting by the sorter of the classified certain ones of the first mixture from the first mixture produces a second mixture of materials that comprises the first mixture minus the classified certain ones of the first mixture, wherein the second mixture of materials contains an aggregate amount of the first class of materials of less than a predetermined weight percentage.
6 . The apparatus as recited in claim 1 , wherein the classifying of certain ones of the first mixture is based on a comparison of the previously generated first knowledge base to a second previously generated knowledge base of characteristics captured from one or more samples of the second class of materials.
7 . The apparatus as recited in claim 1 , wherein the machine learning system comprises an artificial intelligence neural network, and wherein the classifying is performed by the artificial intelligence neural network.
8 . The apparatus as recited in claim 1 , wherein the data processing system comprising the machine learning system is configured to classify the certain ones of the first mixture as belonging in the first class of materials based on processing of the plurality of pixel values as an array.
9 . The apparatus as recited in claim 1 , wherein the data processing system comprising the machine learning system is configured to classify the certain ones of the first mixture as belonging in the first class of materials based on concurrent processing of the plurality of pixel values.
10 . A method for handling a first heterogeneous mixture of separable materials comprising at least one of a first type of materials and at least one of a second type of materials, the method comprising:
capturing, with a sensor, data associated with a plurality of pixels representing a characteristic of each of the first heterogeneous mixture of materials; and
providing the captured data as input to a machine learning system to assign a first classification to certain ones of the first heterogeneous mixture of materials as belonging to the first type of materials based on each pixel from the plurality of pixels, wherein the first classification is based on a first knowledge base produced from a previously generated classification of one or more examples of the first type of materials.
11 . The method as recited in claim 10 , further comprising conveying the first heterogeneous mixture of materials past the sensor configured to capture the characteristic.
12 . The method as recited in claim 10 , wherein the first knowledge base contains a library of observed characteristics captured by a camera configured to capture images of the one or more examples of the first type of materials as they were conveyed past the camera.
13 . The method as recited in claim 10 , wherein the sensor is a camera configured to capture visual images of the first heterogeneous mixture of materials to produce image data, and wherein the captured characteristic is a visually observed characteristic.
14 . The method as recited in claim 10 , further comprising sorting the certain ones of the first heterogeneous mixture of materials from the first heterogeneous mixture as a function of the first classification.
15 . The method as recited in claim 14 , wherein the sorting produces a second mixture of materials that comprises the first heterogeneous mixture of materials minus the sorted certain ones of the first heterogeneous mixture of materials, wherein the second mixture of materials contains an aggregate amount of the first type of materials of less than a predetermined weight or volume percentage.
16 . The method as recited in claim 14 , wherein the sorting produces a second mixture of materials that comprises the first heterogeneous mixture of materials minus the sorted certain ones of the first heterogeneous mixture of materials, the method further comprising utilizing Laser Induced Breakdown Spectroscopy to perform another sorting of materials of a certain classification from the second mixture of materials.
17 . The method as recited in claim 10 , wherein the first type of materials comprises organic waste materials.
18 . The method as recited in claim 10 , wherein the first type of materials comprises fiberglass or carbon fiber composites.
19 . The method as recited in claim 10 , wherein the first type of materials comprises electronic equipment or e-waste.
20 . The method as recited in claim 10 , wherein the first type of materials comprises agriculture materials.
21 . The method as recited in claim 10 , wherein the first type of materials comprises one or more specified metal alloys.
22 . The method as recited in claim 10 , wherein the first type of materials comprises a mass of the materials having a content of less than a predetermined weight or volume percentage of a certain element.
23 . The method as recited in claim 10 , wherein the data includes an array of pixel values associated with the plurality of pixels, the machine learning system configured to receive the array of pixel values as input to assign the first classification to the certain ones of the first heterogeneous mixture of materials as belonging to the first type of materials.