Sorting of Zorba
A material handling system sorts mixed materials utilizing a combination of x-ray fluorescence and/or a vision system that implements an artificial intelligence system in order to identify or classify each of the materials, which are then sorted into separate groups based on such an identification or classification. The system is capable of sorting between materials typically found within Zorba, Zebra, and Twitch.
1. A method for sorting of scrap pieces from a conveyed stream of Zorba materials, comprising:
performing one or more vision checks on each scrap piece within the conveyed stream of Zorba materials, wherein each of the one or more vision checks comprises classifying each scrap piece as a function of processing visual images captured from each scrap piece through an artificial intelligence (“AI”) system;
performing one or more sensor system classifications on each scrap piece within the conveyed stream of Zorba materials; and
sorting scrap pieces from the conveyed stream of Zorba materials into one or more classification groups as a function of a combination of the one or more vision checks and the one or more sensor system classifications.
2. The method as recited in claim 1 , wherein the conveyed stream of Zorba materials comprises one or more wrought aluminum alloys and one or more cast aluminum alloys, wherein the sorting further comprises:
sorting from the conveyed stream of Zorba materials one or more of the cast aluminum alloys into one or more first classification groups based on a first combination of the one or more vision checks and the one or more sensor system classifications; and
sorting from the conveyed stream of Zorba materials one or more of the wrought aluminum alloys into one or more second classification groups based on a second combination of the one or more vision checks and the one or more sensor system classifications,
wherein the sorting from the conveyed stream of Zorba materials of the one or more cast aluminum alloys is performed before the sorting from the conveyed stream of Zorba materials of the one or more wrought aluminum alloys.
3. The method as recited in claim 1 , wherein the sorting further comprises sorting copper scrap pieces from the conveyed stream of Zorba materials based on a combination of the one or more vision checks and the one or more sensor system classifications, wherein the combination comprises a first vision check to determine whether a scrap piece is composed of copper and a first one of the one or more sensor system classifications to determine whether a ratio of a measured amount of copper to a measured amount of zinc in the scrap piece is greater than a first predetermined value, wherein a scrap piece is sorted out of the conveyed stream of Zorba materials as classified as a copper scrap piece when the first vision check determines that the scrap piece is composed of copper and the first one of the one or more sensor system classifications determines that the ratio of a measured amount of copper to a measured amount of zinc in the scrap piece is greater than the first predetermined value.
4. The method as recited in claim 3 , further comprising sorting from the conveyed stream of Zorba materials printed circuit board scrap pieces based on a second vision check, wherein the sorting of the printed circuit board scrap pieces is performed before the sorting of the copper scrap pieces.
5. The method as recited in claim 1 , wherein the sorting further comprises sorting copper and brass scrap pieces from the conveyed stream of Zorba materials based on a combination of the one or more vision checks and the one or more sensor system classifications, wherein the combination comprises a vision check to determine whether a scrap piece is composed of copper or brass, a first one of the one or more sensor system classifications to determine whether a ratio of a measured amount of copper to a measured amount of zinc in the scrap piece is greater than a first predetermined value, and a second one of the one or more sensor system classifications to determine whether the ratio of a measured amount of copper to a measured amount of zinc in the scrap piece is greater than a second predetermined value,
wherein a scrap piece is sorted out of the conveyed stream of Zorba materials as classified as a copper scrap piece when the vision check determines that the scrap piece is composed of copper and the first one of the one or more sensor system classifications determines that the ratio of a measured amount of copper to a measured amount of zinc in the scrap piece is greater than the first predetermined value,
wherein a scrap piece is sorted out of the conveyed stream of Zorba materials as classified as a red brass scrap piece when the vision check determines that the scrap piece is composed of brass, the first one of the one or more sensor system classifications determines that the ratio of a measured amount of copper to a measured amount of zinc in the scrap piece is less than the first predetermined value, and the second one of the one or more sensor system classifications determines that the ratio of a measured amount of copper to a measured amount of zinc in the scrap piece is greater than the second predetermined value,
wherein a scrap piece is sorted out of the conveyed stream of Zorba materials as classified as a yellow brass scrap piece when the vision check determines that the scrap piece is composed of brass, the first one of the one or more sensor system classifications determines that the ratio of a measured amount of copper to a measured amount of zinc in the scrap piece is less than the first predetermined value, and the second one of the one or more sensor system classifications determines that the ratio of a measured amount of copper to a measured amount of zinc in the scrap piece is less than the second predetermined value.
6. The method as recited in claim 1 , wherein the sorting further comprises sorting Ni-plated and stainless-steel scrap pieces from the conveyed stream of Zorba materials based on a combination of sensor system classifications, wherein the combination comprises (1) a first one of the one or more sensor system classifications to determine whether a measured amount of chromium in the scrap piece is greater than a first predetermined value and (2) a second one of the one or more sensor system classifications to determine whether a ratio of a measured amount of nickel to a measured amount of chromium in the scrap piece is greater than a second predetermined value,
wherein a scrap piece is sorted out of the conveyed stream of Zorba materials as classified as a Ni-plated scrap piece when the first one of the one or more sensor system classifications determines that the measured amount of chromium in the scrap piece is greater than the first predetermined value and the second one of the one or more sensor system classifications determines that the ratio of a measured amount of nickel to a measured amount of chromium in the scrap piece is greater than the second predetermined value, and
wherein a scrap piece is sorted out of the conveyed stream of Zorba materials as classified as a stainless-steel scrap piece when the first one of the one or more sensor system classifications determines that the measured amount of chromium in the scrap piece is greater than the first predetermined value and the second one of the one or more sensor system classifications determines that the ratio of a measured amount of nickel to a measured amount of chromium in the scrap piece is less than the second predetermined value.
7. The method as recited in claim 6 , wherein the combination further comprises a third one of the one or more sensor system classifications to determine whether a measured amount of manganese in the scrap piece is greater than a third predetermined value,
wherein a scrap piece is sorted out of the conveyed stream of Zorba materials as classified as a 201 and/or 202 stainless-steel scrap piece when the first one of the one or more sensor system classifications determines that the measured amount of chromium in the scrap piece is greater than the first predetermined value, the second one of the one or more sensor system classifications determines that the ratio of a measured amount of nickel to a measured amount of chromium in the scrap piece is less than the second predetermined value, and the third one of the one or more sensor system classifications determines that the measured amount of manganese in the scrap piece is greater than the third predetermined value, and
wherein a scrap piece is sorted out of the conveyed stream of Zorba materials as classified as a 301, 302, 304, and/or 316 stainless-steel scrap piece when the first one of the one or more sensor system classifications determines that the measured amount of chromium in the scrap piece is greater than the first predetermined value, the second one of the one or more sensor system classifications determines that the ratio of a measured amount of nickel to a measured amount of chromium in the scrap piece is less than the second predetermined value, and the third one of the one or more sensor system classifications determines that the measured amount of manganese in the scrap piece is less than the third predetermined value.
8. The method as recited in claim 6 , wherein the sorting of Ni-plated and stainless-steel scrap pieces from the conveyed stream of Zorba materials based on the combination of sensor system classifications is performed before sorting of wrought or cast aluminum scrap pieces from the conveyed stream of Zorba materials.
9. The method as recited in claim 1 , wherein the conveyed stream of Zorba materials comprises one or more wrought aluminum alloys and one or more cast aluminum alloys, wherein the sorting further comprises sorting 356 and/or 360 cast aluminum alloy scrap pieces from the conveyed stream of Zorba materials based on a combination of a sensor system classification to determine whether measured amounts of copper and zinc in a scrap piece is greater than a predetermined value and a vision check to determine whether the scrap piece is a cast aluminum alloy, wherein the sorting further comprises sorting the scrap piece from the conveyed stream of Zorba materials as classified as a 356 or 360 cast aluminum alloy when the sensor system classification determines that measured amounts of copper and zinc in a scrap piece are less than the predetermined value and the vision check determines that the scrap piece is a cast aluminum alloy.
10. The method as recited in claim 9 , wherein the sorting of 356 and/or 360 cast aluminum alloy scrap pieces from the conveyed stream of Zorba materials is performed before sorting of wrought aluminum alloy scrap pieces from the conveyed stream of Zorba materials.
11. The method as recited in claim 1 , wherein the conveyed stream of Zorba materials comprises one or more wrought aluminum alloys and one or more cast aluminum alloys, wherein the sorting further comprises sorting die cast zinc scrap pieces from the conveyed stream of Zorba materials based on a combination of a first one of the one or more sensor system classifications to determine whether measured amounts of copper and zinc in a scrap piece are greater than a first predetermined value, a vision check to determine whether the scrap piece is a cast aluminum alloy, and a second one of the one or more sensor system classifications to determine whether a ratio of a measured amount of copper to a measured amount of zinc in the scrap piece is greater than a second predetermined value, wherein the sorting further comprises sorting the scrap piece from the conveyed stream of Zorba materials as classified as a die cast zinc scrap piece when:
(1) the first one of the one or more sensor system classifications determines that the total measured amount of copper and zinc in the scrap piece is greater than the first predetermined value, and
(2) the first vision check determines that the scrap piece is composed of a cast aluminum alloy, and
(3) the second one of the one or more sensor system classifications determines that the ratio of a measured amount of copper to a measured amount of zinc in the scrap piece is less than the second predetermined value.
12. The method as recited in claim 11 , wherein the sorting further comprises sorting the scrap piece from the conveyed stream of Zorba materials as classified as a 38x or 319 cast aluminum alloy scrap piece when:
(1) the first one of the one or more sensor system classifications determines that the total measured amount of copper and zinc in the scrap piece is greater than the first predetermined value, and
(2) the first vision check determines that the scrap piece is composed of a cast aluminum alloy, and
(3) the second one of the one or more sensor system classifications determines that the ratio of a measured amount of copper to a measured amount of zinc in the scrap piece is greater than the second predetermined value.
13. The method as recited in claim 11 , wherein the sorting of die cast zinc scrap pieces from the conveyed stream of Zorba materials is performed before sorting of wrought aluminum alloy scrap pieces from the conveyed stream of Zorba materials.
14. The method as recited in claim 11 , wherein the sorting of die cast zinc scrap pieces from the conveyed stream of Zorba materials is performed before sorting of 7xxx series aluminum alloy scrap pieces from the conveyed stream of Zorba materials.
15. The method as recited in claim 1 , wherein the conveyed stream of Zorba materials comprises one or more wrought aluminum alloys and one or more cast aluminum alloys, wherein the sorting further comprises sorting 38x or 319 cast aluminum alloy scrap pieces from the conveyed stream of Zorba materials based on a combination of a first one of the one or more sensor system classifications to determine whether measured amounts of copper and zinc in a scrap piece are greater than a first predetermined value, a vision check to determine whether the scrap piece is a cast aluminum alloy, and a second one of the one or more sensor system classifications to determine whether a ratio of a measured amount of copper to a measured amount of zinc in the scrap piece is greater than a second predetermined value, wherein the sorting further comprises sorting the scrap piece from the conveyed stream of Zorba materials as classified as a 38x or 319 cast aluminum alloy scrap piece when:
(1) the first one of the one or more sensor system classifications determines that the total measured amount of copper and zinc in the scrap piece is greater than the first predetermined value, and
(2) the first vision check determines that the scrap piece is composed of a cast aluminum alloy, and
(3) the second one of the one or more sensor system classifications determines that the ratio of a measured amount of copper to a measured amount of zinc in the scrap piece is greater than the second predetermined value.
16. The method as recited in claim 2 , wherein the sorting from the conveyed stream of Zorba materials one or more of the wrought aluminum alloys into one or more first classification groups further comprises sorting a scrap piece from the conveyed stream of Zorba materials as classified as a 2xxx series wrought aluminum alloy when a vision check determines that the scrap piece is composed of a wrought aluminum alloy and a sensor system classification determines that a measured amount of copper in the scrap piece is greater than a predetermined value.
17. The method as recited in claim 2 , wherein the sorting from the conveyed stream of Zorba materials one or more of the wrought aluminum alloys into one or more first classification groups further comprises sorting a scrap piece from the conveyed stream of Zorba materials as classified as a 7xxx series wrought aluminum alloy when a vision check determines that the scrap piece is composed of a wrought aluminum alloy and a sensor system classification determines that a measured amount of zinc in the scrap piece is greater than a predetermined value.
18. The method as recited in claim 2 , wherein the sorting from the conveyed stream of Zorba materials one or more of the wrought aluminum alloys into one or more first classification groups further comprises sorting a scrap piece from the conveyed stream of Zorba materials as classified as a 3xxx series wrought aluminum alloy when:
(1) a vision check determines that the scrap piece is composed of a wrought aluminum alloy, and
(2) a first one of the one or more sensor system classifications determines that:
(i) a measured amount of manganese in the scrap piece is less than a first predetermined value, and
(ii) a measured amount of iron in the scrap piece is less than a second predetermined value.
19. The method as recited in claim 1 , wherein each of the one or more vision checks is performed by a single vision system implementing one or more AI models within the AI system, and wherein each of the one or more sensor system classifications is performed by a single x-ray fluorescence (“XRF”) system implementing one or more algorithms for analyzing XRF spectral data collected from the scrap pieces.
20. A method for sorting of scrap pieces from a conveyed stream of Zorba materials, comprising:
performing vision checks on each scrap piece within the conveyed stream of Zorba materials, wherein each of the vision checks comprises classifying each scrap piece as a function of processing visual images captured from each scrap piece through an artificial intelligence (“AI”) system, wherein the vision checks are performed by a single vision system implementing a different AI model within the AI system for each of the vision checks;
performing x-ray fluorescence (“XRF”) sensor system classifications on each scrap piece within the conveyed stream of Zorba materials, wherein each of the XRF sensor system classifications is performed by a different algorithm analyzing XRF spectral data collected from each scrap piece by a single XRF system; and
sorting scrap pieces from the conveyed stream of Zorba materials in a following order:
a) a plurality of different non-ferrous metal scrap pieces into separately sorted classification groups based on a first combination of one or more vision checks and one or more sensor system classifications;
b) a plurality of different cast aluminum alloy scrap pieces into separately sorted classification groups based on a second combination of one or more vision checks and one or more sensor system classifications; and
c) a plurality of different wrought aluminum alloys scrap pieces into separately sorted classification groups based on a third combination of one or more vision checks and one or more sensor system classifications.
21. The method as recited in claim 20 , wherein the plurality of different non-ferrous metal scrap pieces is selected from a group consisting of copper, red brass, yellow brass, Ni-plating, stainless-steel, die cast zinc, and lead, wherein the plurality of different non-ferrous metal scrap pieces is selected from a group consisting of 356, 360, 319, and 38x cast aluminum alloys, and wherein the plurality of different wrought aluminum alloys scrap pieces is selected from a group consisting of 2xxx, 3xxx, 5xxx, 6xxx, and 7xxx series wrought aluminum alloys.