Smart systems and methods for identification and processing of spent lithium cells
A method includes using machine learning to classify and sort energy storage devices based on at least one of the detected chemical or physical properties. In some embodiments, the method can include irradiating an energy storage device with an input radiation and detecting the output radiation reflected or backscattered by the energy storage device. The method may further include detecting a physical property of the energy storage device.
1 . A method, comprising:
detecting, via a physical sensing device, a physical property of a first plurality of energy storage devices;
dividing, based on the physical property via a first sorting instruction generated by a machine learning classification model, the first plurality of energy storage devices into a second plurality of energy storage devices and a third plurality of energy storage devices, the second plurality of energy storage devices including lithium-ion batteries (LIBs) and the third plurality of energy storage devices including other batteries;
detecting, via a chemical sensing device, an output radiation of the second plurality of energy storage devices including the lithium-ion batteries, the output radiation generated via an X-ray fluorescence (XRF) process;
dividing, based on the output radiation indicative of their cathode material chemistries via a second sorting instruction generated by the machine learning classification model, the second plurality of energy storage devices including the lithium-ion batteries into a fourth plurality of energy storage devices and a fifth plurality of energy storage devices.
2 . The method of claim 1 , wherein detecting the output radiation includes:
irradiating the second plurality of energy storage devices using an input radiation characterized by a first electromagnetic spectrum;
sensing the output radiation reflected or backscattered by the second plurality of energy storage devices;
determining a second electromagnetic spectrum of the output radiation that is characteristic of a chemical composition; and
comparing the second electromagnetic spectrum characteristic of a chemical composition with a reference electromagnetic spectrum to identify the chemical composition of the energy storage device.
3 . The method of claim 2 , wherein the second sorting instruction generated by the machine learning classification model is based on comparison of the second electromagnetic spectrum with the reference electromagnetic spectrum.
4 . The method of claim 2 , wherein the input radiation includes an X-ray radiation.
5 . The method of claim 1 , further comprising:
packaging at least one of the second plurality of energy storage devices, the fourth plurality of energy storage devices, or the fifth plurality of energy storage devices.
6 . The method of claim 1 , wherein the physical sensing device includes a camera.
7 . The method of claim 1 , wherein the physical sensing device includes a mass sensor.
8 . A method, comprising:
detecting, via a chemical sensing device, an output radiation of a first plurality of energy storage devices, the output radiation generated via an X-ray fluorescence (XRF) process;
dividing, based on the output radiation property via a first sorting instruction generated by a machine learning classification model, the first plurality of energy storage devices into a second plurality of energy storage devices and a third plurality of energy storage devices, the second plurality of energy storage devices including lithium-ion batteries (LIBs) and the third plurality of energy storage devices including other batteries;
detecting, via a physical sensing device, a physical property of the second plurality of energy storage devices including the lithium-ion batteries, indicative of their cathode material chemistries;
dividing, based on the physical property via a second sorting instruction generated by the machine learning classification model, the second plurality of energy storage devices including the lithium-ion batteries into a fourth plurality of energy storage devices and a fifth plurality of energy storage devices.
9 . The method of claim 8 , wherein detecting the output radiation includes:
irradiating the first plurality of energy storage devices using an input radiation characterized by a first electromagnetic spectrum;
sensing the output radiation reflected or backscattered by the first plurality of energy storage devices;
determining a second electromagnetic spectrum of the output radiation that is characteristic of a chemical composition; and
comparing the second electromagnetic spectrum characteristic of a chemical composition with a reference electromagnetic spectrum to identify the chemical composition of the energy storage device.
10 . The method of claim 9 , wherein the first sorting instruction generated by the machine learning classification model is based on comparison of the second electromagnetic spectrum with the reference electromagnetic spectrum.
11 . The method of claim 9 , wherein the input radiation includes an X-ray radiation.
12 . The method of claim 8 , further comprising:
packaging at least one of the second plurality of energy storage devices, the fourth plurality of energy storage devices, or the fifth plurality of energy storage devices.
13 . The method of claim 8 , wherein the physical sensing device includes at least one of a camera or a mass sensor.
14 . The method of claim 8 , further comprising:
housing the second plurality of energy storage devices in a holding unit.
15 . A system, comprising:
a radiation source configured to irradiate an energy storage device using an input radiation characterized by a first electromagnetic spectrum;
a detector configured to detect an output radiation reflected or backscattered by the energy storage device;
a physical sensing device configured to detect a physical property of an energy storage device;
a compute device configured to generate an instruction based on a machine learning classification model, to sort the energy storage device based on the output radiation and the physical property,
wherein the instruction to sort the energy storage device includes:
a first instruction to sort a plurality of energy storage devices into lithium ion batteries (LIBs) and other batteries; and
a second instruction to further sort the sorted LIBs based on their cathode material chemistries.
16 . The system of claim 15 , wherein the radiation source includes an X-ray radiation source.
17 . The system of claim 15 , wherein the radiation source and the detector form at least a portion of an X-ray fluorescence (XRF) spectrometer.
18 . The system of claim 15 , further comprising:
a sorting device configured to receive the instruction and sort the energy storage device based on the instruction.
19 . The system of claim 15 , the sorting device includes a guiding switch.
20 . The system of claim 19 , further comprising:
a packaging device, disposed after the sorting device, configured to package the energy storage device.
21 . The system of claim 15 , further comprising:
an inlet configured to receive the energy storage device, wherein the physical sensing device is operatively coupled to the inlet.
22 . A method, comprising:
detecting, via a physical sensing device, a physical property of a first plurality of energy storage devices;
dividing, based on the physical property via a first sorting instruction generated by a machine learning classification model, the first plurality of energy storage devices into a second plurality of energy storage devices and a third plurality of energy storage devices, the second plurality of energy storage devices including lithium-ion batteries (LIBs) and the third plurality of energy storage devices including other batteries;
detecting, via a chemical sensing device, an output radiation of the second plurality of energy storage devices including the lithium-ion batteries, the detecting the output radiation including:
irradiating the second plurality of energy storage devices using an input radiation characterized by a first electromagnetic spectrum;
sensing the output radiation reflected or backscattered by the second plurality of energy storage devices;
determining a second electromagnetic spectrum of the output radiation that is characteristic of a chemical composition; and
comparing the second electromagnetic spectrum characteristic of a chemical composition with a reference electromagnetic spectrum to identify the chemical composition of the energy storage device; and
dividing, based on the output radiation indicative of their cathode material chemistries via a second sorting instruction generated by the machine learning classification model, the second plurality of energy storage devices including the lithium-ion batteries into a fourth plurality of energy storage devices and a fifth plurality of energy storage devices.
23 . The method of claim 22 , wherein the first sorting instruction generated by the machine learning classification model is based on comparison of the second electromagnetic spectrum with the reference electromagnetic spectrum.
24 . The method of claim 22 , wherein the input radiation includes an X-ray radiation.
25 . The method of claim 22 , further comprising:
packaging at least one of the second plurality of energy storage devices, the fourth plurality of energy storage devices, or the fifth plurality of energy storage devices.
26 . The method of claim 22 , wherein the physical sensing device includes at least one of a camera or a mass sensor.
27 . A method, comprising:
detecting, via a chemical sensing device, an output radiation of a first plurality of energy storage devices, the detecting the output radiation including:
irradiating the first plurality of energy storage devices using an input radiation characterized by a first electromagnetic spectrum;
sensing the output radiation reflected or backscattered by the first plurality of energy storage devices;
determining a second electromagnetic spectrum of the output radiation that is characteristic of a chemical composition; and
comparing the second electromagnetic spectrum characteristic of a chemical composition with a reference electromagnetic spectrum to identify the chemical composition of the energy storage device;
dividing, based on the output radiation property via a first sorting instruction generated by a machine learning classification model, the first plurality of energy storage devices into a second plurality of energy storage devices and a third plurality of energy storage devices, the second plurality of energy storage devices including lithium-ion batteries (LIBs) and the third plurality of energy storage devices including other batteries;
detecting, via a physical sensing device, a physical property of the second plurality of energy storage devices including the lithium-ion batteries, indicative of their cathode material chemistries;
dividing, based on the physical property via a second sorting instruction generated by the machine learning classification model, the second plurality of energy storage devices including the lithium-ion batteries into a fourth plurality of energy storage devices and a fifth plurality of energy storage devices.
28 . The method of claim 27 , wherein the second sorting instruction generated by the machine learning classification model is based on comparison of the second electromagnetic spectrum with the reference electromagnetic spectrum.
29 . The method of claim 27 , wherein the input radiation includes an X-ray radiation.
30 . The method of claim 27 , wherein the physical sensing device includes at least one of a camera or a mass sensor.
31 . The method of claim 27 , further comprising:
packaging at least one of the second plurality of energy storage devices, the fourth plurality of energy storage devices, or the fifth plurality of energy storage devices.