Lithium ion battery regenerated raw material solid waste attribute identification method and system

Abstract

The invention relates to recycling of lithium ion batteries, in particular to a method and a system for identifying properties of solid wastes of regenerated raw materials of lithium ion batteries. When the lithium ion battery regenerated raw material is subjected to solid waste identification, firstly, an X-ray fluorescence spectrum element spectrum and an X-ray diffraction spectrum of the material are obtained, characteristic parameters related to material components are extracted, a machine learning method is adopted, the advantages of the X-ray fluorescence spectrum and the diffraction spectrum are fused, the main components of the material are more accurately determined, and the identification accuracy is improved. The problem of single instrument analysis in the prior art is solved. Then, a machine learning method is adopted to carry out material source attribute judgment, suitable product quality standards are selected according to main components of the materials, whether the materials belong to solid waste or not is further judged according to whether the materials meet the requirements of the product quality standards or not, and a result can be obtained more quickly and more accurately.

Description

Technical Field

[0001] The present invention relates to the recycling of lithium-ion batteries, and particularly to a method and system for identifying the solid waste attributes of the recycled raw materials of lithium-ion batteries. Background Art

[0002] With the rapid development of the new energy vehicle industry and the electronic and electrical appliance industry, the lithium-ion battery industry has accelerated its development, driving the demand for upstream electrode materials. As the scale of power battery use continues to expand and the development cycle of power batteries continues to lengthen, the scrapping volume of power batteries has continued to grow rapidly. With the increase in battery installation capacity, the scrapping volume will continue to grow. The abundance of valuable metal resources such as nickel, cobalt, and lithium in power batteries is much higher than that of the original ore. Taking the common 622-type ternary cathode material in the market as an example, about 70 kg of metallic lithium, 350 kg of metallic nickel, and 120 kg of metallic cobalt are contained in 1 t of battery black powder. Therefore, by recycling waste power batteries, it is possible to alleviate the contradiction between China's economic development and resource constraints, and is also conducive to solving the contradiction between China's economic development and environmental protection.

[0003] The General Rules for the Identification of Solid Wastes (GB 34330-2017) is an important basis for the identification of the attributes of imported solid wastes, providing general guidelines for the identification of solid waste attributes. However, the recycled raw materials of waste lithium-ion batteries have special characteristics such as wide sources, diverse recycling processes, and complex compositions, and have the dual attributes of raw materials and products. The identification scale is relatively vague, and there are still differences in understanding and disputes regarding whether such recycled raw materials are resources or solid wastes. In the existing solid waste identification, it is overly dependent on the level of the identification personnel, requiring the identification personnel to be familiar with the relevant policies, detection methods, and technical background of lithium-ion batteries for solid waste identification, resulting in low efficiency of solid waste identification and prone to different conclusions. When identifying solid wastes, common detection methods include X-ray fluorescence spectrometry, X-ray diffraction analysis, etc. However, for example, in quantitative analysis by X-ray fluorescence spectrometry, the influence of matrix effects is relatively large. The X-ray diffraction analysis method can only perform qualitative analysis and cannot perform quantitative and comprehensive analysis on polycrystals. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides a method and system for identifying the solid waste attributes of the recycled raw materials of lithium-ion batteries to solve the problems existing in the prior art.

[0005] The present invention provides a method for identifying the solid waste attributes of the recycled raw materials of lithium-ion batteries, characterized by including: S1: Collect material data, analyze the composition of the material, and determine the main components of the material; The collection of the material data includes obtaining the X-ray fluorescence spectrum elements spectrum and the X-ray diffraction pattern of the material; Extract spectral characteristic parameters based on the X-ray fluorescence spectrometry elemental spectrum of the material; extract diffraction characteristic parameters based on the X-ray diffraction pattern; Input the spectral characteristic parameters and the diffraction characteristic parameters into a pre-trained random forest recognition model to analyze the composition of the material and determine the main components of the material; S2: Determination of the material source attribute; S3: Obtain the product quality standards applicable to the recycled raw materials; S4: Determine whether it is solid waste.

[0006] Preferably, in the S1, the collecting material data, analyzing the composition of the material, and determining the main components of the material include: Use an X-ray fluorescence spectrometer to obtain the X-ray fluorescence spectrometry elemental spectrum; use an X-ray diffractometer to obtain the X-ray diffraction pattern.

[0007] Preferably, the extracting spectral characteristic parameters and the extracting diffraction characteristic parameters include: extracting the key element concentration ratio and the total heavy metal content; extracting the peak intensity ratio and the lattice parameter.

[0008] Preferably, the pre-trained random forest recognition model includes: selecting 3N historical identification materials including the main component confirmation information; obtaining the X-ray fluorescence spectrometry elemental spectra of 3N historical identification materials, extracting the key element concentration ratio and the total heavy metal content, obtaining the X-ray diffraction patterns of 3N historical identification materials, and extracting the peak intensity ratio and the lattice parameter; taking 2N historical identification materials and the corresponding main component confirmation information, using the key element concentration ratio, the total heavy metal content, the peak intensity ratio, the lattice parameter, and the main component confirmation information as the training data of the random forest recognition model to establish a random forest recognition training model; taking the remaining N historical identification materials and the corresponding main component confirmation information, using the key element concentration ratio, the total heavy metal content, the peak intensity ratio, and the lattice parameter as the test data to verify the random forest recognition training model and obtain the pre-trained random forest recognition model.

[0009] Preferably, in the S2, the material source attribute determination includes: using inductively coupled plasma atomic emission spectrometry and ion selective electrode method to determine the impurity element content; determining the material source according to the appearance of the material, the main components of the material, and the impurity element content of the material.

[0010] Preferably, in the S3, obtaining the product quality standards applicable to the recycled raw materials includes: obtaining the product quality standards applicable to the recycled raw materials according to the material source and the main components.

[0011] Preferably, in S4, determining whether it is solid waste includes: determining whether the material is solid waste according to the product quality standard of the recycled raw material.

[0012] According to another aspect of the present invention, there is provided a system for identifying the solid waste attribute of lithium-ion battery recycled raw materials. The system adopts the method for identifying the solid waste attribute of lithium-ion battery recycled raw materials according to any one of claims 1-7. The system includes: A main component confirmation module for the material, which is used to collect material data, analyze the components of the material, and determine the main components of the material to be tested; A material source attribute determination module, which is used to determine the source of the material according to the appearance of the material, the main components of the material, and the content of impurity elements in the material; A judgment standard acquisition module, which is used to obtain the product quality standard applicable to the recycled raw material according to the source and main components of the material; A solid waste determination module, which is used to determine whether the material is solid waste according to the product quality standard of the recycled raw material.

[0013] Preferably, the main component confirmation module for the material includes: a material data collection module, which is used to collect material data, and the material data includes the X-ray fluorescence spectrum element spectrum of the material and the X-ray diffraction pattern of the material.

[0014] Preferably, the component analysis module for the material includes: a material data processing module, which is used to perform data processing operations on the material data; wherein the data processing of the material data includes extracting the key element concentration ratio and the total amount of heavy metals based on the X-ray fluorescence spectrum element spectrum of the material; and extracting the peak intensity ratio and lattice parameters based on the X-ray diffraction pattern. A random forest recognition model establishment module, which is used to establish a random forest recognition model.

[0015] The embodiments of the present invention have the following technical effects: When the present invention conducts solid waste identification on lithium-ion battery recycled raw materials, it first obtains the X-ray fluorescence spectrum element spectrum and X-ray diffraction pattern of the material, extracts the characteristic parameters related to the material components, and uses the machine learning method to integrate the advantages of X-ray fluorescence spectrum and diffraction pattern to more accurately determine the main components of the material, solving the problem of single instrument analysis in the prior art. Then, the machine learning method is used to determine the material source attribute. The applicable product quality standard is selected according to the main components of the material, and further, it is determined whether the material belongs to solid waste according to whether the material meets the requirements of the product quality standard, and the result can be obtained more quickly and accurately. Description of the Drawings

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 It is a flowchart of a method for identifying the solid waste attributes of the regeneration raw materials of a lithium-ion battery provided by an embodiment of the present invention.

[0018] Figure 2 It is a schematic diagram of the appearance of one of the samples provided by an embodiment of the present invention.

[0019] Figure 3 It is a schematic diagram of the modules of the system provided by an embodiment of the present invention. Specific Embodiments

[0020] To make the purpose, technical solutions and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope protected by the present invention.

[0021] Appendix Figure 1 It shows a flowchart of a method for identifying the solid waste attributes of the regeneration raw materials of a lithium-ion battery, including: S1: Collect material data, analyze the composition of the material, and determine the main components of the material; Among them, when collecting material data, the X-ray fluorescence spectrum elements spectrum and X-ray diffraction pattern of the material are obtained. Analyzing and identifying the chemical composition of the sample is the most basic requirement for the identification work. In the identification, an X-ray fluorescence spectrometer (XRF) is usually used to analyze the elemental composition of inorganic samples, and other elements (usually located after nitrogen in the periodic table) with a content of more than 0.01% except for the light elements with smaller atomic numbers in the periodic table can be reflected. An X-ray diffractometer (XRD) is used to analyze and identify the phase structure of the sample. These two methods are very practical and effective for analyzing and identifying the overall chemical characteristics of the sample, and can effectively determine the main components of the identification sample. If necessary, other testing methods such as energy spectrum analysis and thermogravimetric analysis can also be used.

[0022] In this embodiment, for the material to be tested, an X-ray fluorescence spectroscopy elemental spectrum and an X-ray diffraction pattern are obtained. According to the X-ray fluorescence spectroscopy elemental spectrum, the critical element concentration ratio and the total heavy metal content are extracted. For example, if the material is nickel cobalt manganese hydroxide, the Ni / (Co+Mn) concentration ratio and the total heavy metal weight (ΣCo+Ni+Mn…) can be extracted according to the X-ray fluorescence spectroscopy elemental spectrum. According to the X-ray diffraction pattern, the peak intensity ratio and the lattice parameter are extracted. For example, if the material is nickel cobalt powder, the peak intensity ratio of the (003) peak / (104) peak and the c / a value can be extracted according to the X-ray diffraction pattern.

[0023] Among them, for the pre-trained random forest recognition model, during training, 3N historical identification materials are selected, including the main component confirmation information. The X-ray fluorescence spectroscopy elemental spectra of the 3N historical identification materials are obtained, and the critical element concentration ratio and the total heavy metal content are extracted. The X-ray diffraction patterns of the 3N historical identification materials are obtained, and the peak intensity ratio and the lattice parameter are extracted. Take 2N historical identification materials and the corresponding main component confirmation information, and use the critical element concentration ratio, the total heavy metal content, the peak intensity ratio, the lattice parameter, and the main component confirmation information as the training data of the random forest recognition model to establish a random forest recognition training model. Take the remaining N historical identification materials and the corresponding main component confirmation information, and use the critical element concentration ratio, the total heavy metal content, the peak intensity ratio, and the lattice parameter as the test data to verify the random forest recognition training model and obtain the pre-trained random forest recognition model.

[0024] Input the critical element concentration ratio, the total heavy metal content, the peak intensity ratio, and the lattice parameter of the material to be tested into the pre-trained random forest recognition model to confirm the main components of the material. For example, it is confirmed to be lithium nickel cobalt manganese oxide, nickel cobalt hydroxide, lithium carbonate, nickel hydroxide, cobalt carbonate, cobalt hydroxide, etc.

[0025] S2: Determination of the material source attribute; Determine the material source according to the main component of the material and the appearance of the material.

[0026] For example, after step S1, it is determined that the main component of the material named lithium nickel cobalt manganese oxide is lithium nickel cobalt manganese oxide, as shown in the appendix. Figure 2 Observe the appendix. Figure 2 The appearance of the material is grayish-black powder, the appearance is normal, and no obvious inclusions are seen. The main components of the sample are nickel, cobalt, and manganese elements. The appearance, chemical composition, and phase composition of the sample conform to the characteristics of lithium nickel cobalt manganese oxide, and the impurity elements and harmful elements of the sample are normal. That is, the material belongs to the intermediate product of the lithium-ion battery and does not belong to the recycled raw material of the lithium-ion battery.

[0027] For another example, after step S1, it is determined that the main components of the material named nickel cobalt powder are LiCoO2, LiNi0.333 Co 0.333 Mn 0.333 O2 and graphite. The contents of iron, copper, aluminum, lead, cadmium, arsenic, chromium, and fluorine in the sample were determined by inductively coupled plasma atomic emission spectrometry and ion selective electrode method. The sample is a grayish-black powder with uniform color, no peculiar smell, no lumping, and no obvious inclusions. The sample mainly contains the cathode material LiCoO2 of lithium-ion batteries, LiNi 0.333 Co 0.333 Mn 0.333 O2 and the graphite component of the anode material, as well as metallic aluminum as the cathode current collector and metallic copper as the anode current collector. The compositional characteristics of the sample conform to the characteristics of the crushed and recycled materials of waste lithium-ion batteries, and it is inferred that the sample belongs to the recycled materials obtained by crushing, screening, and impurity removal of various waste lithium-ion batteries. That is, the material belongs to the recycled raw materials of lithium-ion batteries.

[0028] In S3, obtain the product quality standards applicable to the recycled raw materials, including: obtain the product quality standards applicable to the recycled raw materials according to the source and main components of the material. Due to different sources, the intermediate products and recycled raw materials of power batteries are applicable to different articles of the General Rules for Identification of Solid Wastes (GB 34330-2017) (hereinafter referred to as the General Rules). The intermediate products of power batteries belong to the "target products" of industrial production, and their solid waste identification should be determined according to Article 4 of the General Rules. The power battery recycled raw materials derived from solid wastes such as scrapped power batteries, components, and raw materials belong to the "products produced from solid wastes", and their solid waste identification should be determined according to Article 5.2 of the General Rules. The recycled raw materials should comply with the product quality standards prevailing in the country, region, or industry. The product quality standards for recycled raw materials include GB / T 45203—2024, YS / T 1460—2021, YS / T 1552—2022, YS / T 1228—2018, etc.

[0029] In S4, judge whether it is a solid waste, including: judge whether the material is a solid waste according to the product quality standards of the recycled raw materials.

[0030] Exemplarily, for the source, main components, and content of harmful elements of the sample, the sample is applicable to GB / T 45203—2024. After analysis, the content of the main elements of the sample meets the requirements of GB / T 45203—2024, but the content of harmful elements exceeds the limit specified in this standard, and the sample does not meet the requirements of GB / T 45203—2024. According to the General Rules for Identification of Solid Wastes (GB 34330-2017), it is determined that the sample belongs to solid waste.

[0031] Example 2, as shown in the appendix Figure 3As shown in the figure, the present invention also provides a solid waste attribute identification system for lithium-ion battery recycling raw materials. The system adopts the solid waste attribute identification method of Embodiment 1. The system includes: A main component confirmation module for the material, which is used to collect material data and determine the main components of the material to be tested; A material data collection module for collecting material data, where the material data includes the X-ray fluorescence spectrum elements spectrum of the material and the X-ray diffraction pattern of the material.

[0032] A material data processing module for performing data processing operations on the material data; Among them, the processing of the material data includes extracting the key element concentration ratio and the total amount of heavy metals based on the X-ray fluorescence spectrum elements spectrum of the material; and extracting the peak intensity ratio and lattice parameters based on the X-ray diffraction pattern.

[0033] A random forest recognition model establishment module for establishing a random forest recognition model.

[0034] A material source attribute determination module for using inductively coupled plasma atomic emission spectrometry and ion selective electrode method to determine the content of impurity elements; and determining the material source according to the content of the impurity elements, the main components of the material and the appearance of the material; A judgment standard acquisition module for acquiring the product quality standard applicable to the recycling raw materials according to the source and main components of the material; A solid waste determination module for determining whether the material is solid waste according to the product quality standard of the recycling raw materials.

[0035] Embodiment 3, the present invention also provides an electronic device, including one or more processors and a memory.

[0036] The processor may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0037] The memory may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage media, and the processor may run the program instructions to implement a method for identifying the solid waste attributes of the recycled raw materials of a lithium-ion battery according to any embodiment of the present application described above and / or other desired functions. Various contents such as initial external parameters and thresholds may also be stored in the computer-readable storage media.

[0038] In one example, the electronic device may further include: an input device and an output device, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown). The input device may include, for example, a keyboard, a mouse, etc. The output device may output various information to the outside, including warning prompt information, braking force, etc. The output device may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0039] Of course, for simplicity, components such as buses, input / output interfaces, etc. are omitted. In addition, according to specific application scenarios, the electronic device may further include any other appropriate components.

[0040] In addition to the above methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, and when the computer program instructions are run by a processor, the processor is enabled to implement the functions of a method for identifying the solid waste attributes of the recycled raw materials of a lithium-ion battery provided by any embodiment of the present application.

[0041] The computer program product may be written in any combination of one or more programming languages to write program code for performing the operations of the embodiments of the present application. The programming languages include object-oriented programming languages, such as Java, C++, etc., and also include conventional procedural programming languages, such as the "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, executed as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0042] In addition, an embodiment of the present application may also be a computer-readable storage medium storing computer program instructions, which, when run by a processor, cause the processor to implement a method for identifying the solid waste attributes of the regenerated raw materials of a lithium-ion battery provided in any embodiment of the present application.

[0043] The computer-readable storage medium may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, include but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0044] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying the solid waste attributes of the regenerated raw materials of lithium-ion batteries, characterized in that, Including: S1: Collect material data, analyze the components of the material, and determine the main components of the material; The collecting of material data includes obtaining the X-ray fluorescence spectral element spectrum and the X-ray diffraction pattern of the material; Based on the X-ray fluorescence spectral element spectrum of the material, extract spectral characteristic parameters; Based on the X-ray diffraction pattern, extract diffraction characteristic parameters; Input the spectral characteristic parameters and the diffraction characteristic parameters into a pre-trained random forest recognition model to analyze the components of the material and determine the main components of the material; S2: Determine the source attribute of the material; S3: Obtain the product quality standards applicable to the recycled raw materials; S4: Determine whether the material is solid waste.

2. A method for identifying the solid waste attribute of the regenerated raw materials of a lithium-ion battery according to claim 1, characterized in that: In S1, the collecting of material data and the analysis of the components of the material include: Use an X-ray fluorescence spectrometer to obtain the X-ray fluorescence spectral element spectrum; use an X-ray diffractometer to obtain the X-ray diffraction pattern.

3. A method for identifying the solid waste attribute of the regenerated raw material of a lithium-ion battery according to claim 2, characterized in that: The extraction of spectral characteristic parameters and the extraction of diffraction characteristic parameters include: Extract the critical element concentration ratio and the total amount of heavy metals; Extract the peak intensity ratio and the lattice parameter.

4. A method for identifying the solid waste attributes of the recycled raw materials of a lithium-ion battery according to claim 3, characterized in that: The pre-trained random forest recognition model includes: Select 3N historical identified materials, including main component confirmation information; Obtain the X-ray fluorescence spectral element spectra of the 3N historical identified materials, and extract the critical element concentration ratio and the total amount of heavy metals; obtain the X-ray diffraction patterns of the 3N historical identified materials, and extract the peak intensity ratio and the lattice parameter; Take 2N of the historical identified materials and the corresponding main component confirmation information, and use the critical element concentration ratio, the total amount of heavy metals, the peak intensity ratio, the lattice parameter, and the main component confirmation information as the training data of the random forest recognition model to establish a random forest recognition training model; Take the remaining N historical identified materials and the corresponding main component confirmation information, and use the critical element concentration ratio, the total amount of heavy metals, the peak intensity ratio, and the lattice parameter as the test data to verify the random forest recognition training model and obtain the trained random forest recognition model.

5. A method for identifying the solid waste attribute of the regenerated raw material of a lithium-ion battery according to claim 1, characterized in that: In S2, the determination of the source attribute of the material includes: Use inductively coupled plasma atomic emission spectrometry and ion selective electrode method to determine the impurity element content of the material; Determine the source of the material according to the appearance of the material, the main components of the material, and the impurity element content of the material.

6. A method for identifying the solid waste attribute of the regenerated raw material of a lithium-ion battery according to claim 1, characterized in that: In S3, obtaining the product quality standards applicable to the recycled raw materials includes: Obtain the product quality standards applicable to the recycled raw materials according to the source and main components of the material.

7. A method for identifying the solid waste attribute of the regenerated raw materials of a lithium-ion battery according to claim 1, characterized in that: In S4, determining whether the material is solid waste includes: Determine whether the material is solid waste according to the product quality standards of the recycled raw materials.

8. A solid waste attribute identification system for lithium-ion battery recycling raw materials, characterized in that, The system adopts the method for identifying the solid waste attribute of the lithium-ion battery recycled raw materials according to any one of claims 1-7. The system includes: A module for confirming the main components of the material, which is used to collect material data, analyze the components of the material, and determine the main components of the material; The material source attribute determination module includes determining the content of impurity elements by using inductively coupled plasma atomic emission spectrometry or ion selective electrode method; obtaining the appearance of the material; and determining the source of the material according to the appearance of the material, the main components of the material, and the content of impurity elements in the material. The judgment standard acquisition module is used to obtain the product quality standard applicable to the recycled raw material according to the source and main components of the material. The solid waste determination module is used to determine whether the material is solid waste according to the product quality standard used for the recycled raw material.

9. The solid waste attribute identification system for lithium-ion battery recycling raw materials according to claim 8, characterized in that: The material main component confirmation module includes: The material data acquisition module is used to acquire material data, and the material data includes the X-ray fluorescence spectral elements of the material and the X-ray diffraction pattern of the material.

10. The solid waste attribute identification system for lithium-ion battery recycling raw materials according to claim 9, characterized in that: The material main component confirmation module includes: The material data processing module is used to perform data processing operations on the material data. Among them, the processing of the material data includes extracting the key element concentration ratio and the total amount of heavy metals based on the X-ray fluorescence spectral elements of the material; and extracting the peak intensity ratio and lattice parameters based on the X-ray diffraction pattern. The random forest recognition model establishment module is used to establish a random forest recognition model.

Images