Method for recycling lithium cobalt oxide positive electrode material in waste lithium battery by gradient pyrolysis method

Abstract

The invention discloses a method for recycling a lithium cobalt oxide positive electrode material in a waste lithium battery through a cascade pyrolysis method, and relates to the technical field of battery positive electrode recycling. The waste lithium battery is subjected to real-time adjustment according to a first-stage temperature adjustment formula within a first-stage pyrolysis temperature range to obtain a first-stage product; calculating a second-stage formula temperature of the first-stage product in a second-stage pyrolysis temperature range according to a second-stage temperature formula, constructing a second-stage temperature control model, and predicting a second-stage real-time prediction temperature; a second-stage product is obtained according to the second-stage formula temperature and the second-stage real-time predicted temperature, a third-stage formula temperature of the second-stage product is calculated according to a third-stage temperature formula in a third-stage pyrolysis temperature range, a third-stage temperature control model is constructed, a third-stage real-time predicted temperature is predicted, and a lithium cobalt oxide product is obtained according to the third-stage formula temperature and the third-stage real-time predicted temperature. The purity and the electrochemical performance of the lithium cobalt oxide positive electrode material are improved, and meanwhile, the energy consumption is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of battery positive electrode recovery, in particular to a method for recovering lithium cobalt oxide positive electrode materials in waste lithium batteries by a stepwise pyrolysis method. Background Art

[0002] With the rapid development of new energy vehicles and portable electronic devices, the use of lithium-ion batteries has increased dramatically. Among them, lithium cobalt oxide (LiCoO2), as a common positive electrode material, accounts for a considerable proportion of waste lithium batteries. Traditional recycling methods mainly include pyrometallurgy and hydrometallurgy:

[0003] Pyrometallurgy: Advantages: Simple process, can process large quantities of batteries. Disadvantages: High energy consumption, produces harmful gases, low metal recovery rate.

[0004] Hydrometallurgy: Advantages: high metal recovery rate and good product purity. Disadvantages: use of large amounts of chemical reagents, secondary pollution and high cost.

[0005] However, these traditional methods have problems such as high energy consumption, environmental pollution and high cost, which make it difficult to meet the needs of sustainable development. Therefore, the currently recommended method is the cascade pyrolysis method for recycling;

[0006] In the process of recycling lithium cobalt oxide positive electrode materials in waste lithium batteries by cascade pyrolysis, precise temperature control is crucial. The chemical reactions in each pyrolysis stage are extremely sensitive to temperature. A slight deviation may lead to incomplete removal of binders and organic matter, insufficient cobalt reduction, or uneven recrystallization, which in turn affects the purity and electrochemical properties of the final material. In existing pyrolysis processes, traditional temperature control methods are usually relied on, such as preset temperature curves and simple feedback control. However, these methods are often difficult to adapt to the changing raw material characteristics and complex reaction processes, resulting in the system's response to gas concentration, oxygen changes and product quality feedback not being timely enough. Due to the strong nonlinear characteristics of the reactions in each stage and the rapid changes in reaction rates, simple preset and real-time control often result in problems such as frequent temperature fluctuations, over-adjustment or lagging adjustment, which ultimately affect the quality stability of the product and process energy consumption.

[0007] A Chinese patent with authorization announcement number CN112607787B discloses a method for recycling lithium cobalt oxide high-iron material, comprising the following steps: (1) sintering the lithium cobalt oxide high-iron material at 900°C to 1100°C for 5h to 30h, crushing and classifying the sintered lithium cobalt oxide high-iron material to obtain a lithium cobalt oxide product; (2) uniformly mixing the lithium cobalt oxide product with a cobalt compound to obtain a uniformly mixed lithium cobalt oxide material; (3) sintering the uniformly mixed lithium cobalt oxide material at 800°C to 1100°C for 5h to 30h, crushing and classifying the sintered uniformly mixed lithium cobalt oxide material to obtain a coated lithium cobalt oxide product; however, this method fails to achieve precise temperature control.

[0008] To this end, the present invention proposes a method for recovering lithium cobalt oxide positive electrode materials in waste lithium batteries by a stepwise pyrolysis method. Summary of the invention

[0009] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a method for recycling lithium cobalt oxide positive electrode materials in waste lithium batteries by a cascade pyrolysis method, which improves the purity and electrochemical performance of potassium cobalt oxide positive electrode materials and reduces energy consumption.

[0010] To achieve the above purpose, a method for recovering lithium cobalt oxide positive electrode materials from waste lithium batteries by cascade pyrolysis is proposed, comprising the following steps:

[0011] Step 1: performing primary pyrolysis on the waste lithium battery within the primary pyrolysis temperature range, wherein the real-time temperature of the primary pyrolysis is adjusted in real time according to the primary temperature adjustment formula to obtain a primary product;

[0012] Step 2: performing secondary pyrolysis on the primary product within the secondary pyrolysis temperature range; calculating the secondary formula temperature according to the secondary temperature formula for the secondary pyrolysis process, and constructing a secondary temperature control model to predict the secondary real-time predicted temperature; performing real-time adjustment according to the secondary temperature adjustment formula based on the secondary formula temperature and the secondary real-time predicted temperature to obtain the secondary product;

[0013] Step 3: performing a three-stage pyrolysis on the secondary product within a three-stage pyrolysis temperature range, calculating the three-stage formula temperature of the three-stage pyrolysis process according to the three-stage temperature formula, and constructing a three-stage temperature control model to predict the three-stage real-time predicted temperature, and performing real-time adjustment according to the three-stage temperature adjustment formula based on the three-stage formula temperature and the three-stage real-time predicted temperature to obtain a lithium cobalt oxide product;

[0014] The specific temperature range of the primary pyrolysis temperature range is [200°C, 300°C], the equipment used for the primary pyrolysis is a rotary kiln equipped with a temperature gradient control system, and the atmosphere of the primary pyrolysis adopts an inert gas;

[0015] The method of performing real-time adjustment according to the primary temperature adjustment formula is as follows:

[0016] Construct a first-stage temperature adjustment formula based on the preset first-stage initial temperature, real-time gas concentration and process product quality;

[0017] The temperature range of the secondary pyrolysis is [500°C, 700°C], the pyrolysis equipment used in the secondary pyrolysis is a vertical reactor equipped with a precise temperature control system, and the pyrolysis atmosphere used is a reducing gas;

[0018] The method for calculating the secondary temperature of the secondary pyrolysis process according to the secondary temperature formula is:

[0019] Construct a secondary temperature formula based on the preset secondary initial temperature, primary product quality index and secondary gas concentration ratio;

[0020] The method of constructing the secondary temperature control model and predicting the secondary real-time predicted temperature is as follows:

[0021] The secondary temperature control model selects the LSTM model;

[0022] The prediction of the secondary real-time predicted temperature comprises the following steps:

[0023] Step 11: Collect secondary training data; the secondary training data includes secondary input sample data and secondary label sample data;

[0024] The secondary input sample data includes the gas concentration time series composed of the concentrations of CO and CO2 collected in time sequence at fixed time intervals in the historical optimal recovery experience of the secondary pyrolysis process, the volatile concentration time series composed of the concentrations of volatile organic compounds in time sequence, and the temperature time series of the actual temperature in the secondary pyrolysis equipment changing with time. The gas concentration time series, volatile concentration time series and temperature time series in each time length are taken as a group of input samples;

[0025] The secondary label sample data includes a temperature label corresponding to each group of input samples in the historical optimal recovery experience of the secondary pyrolysis process, and the temperature label is a temperature value of a unit time after the corresponding input sample;

[0026] Step 12: Model the secondary temperature control model;

[0027] Step 13: Use the secondary input sample as the input of the secondary temperature control model, use the temperature label as the actual temperature of the secondary temperature control model, use the Adam optimizer to perform back propagation training on the secondary temperature control model, and adjust the model weights;

[0028] Step 14: According to the data form of the secondary input sample, actual input data in the secondary pyrolysis process is collected, and the actual input data is input into the secondary temperature control model to obtain the secondary real-time predicted temperature output by the secondary temperature control model;

[0029] The temperature range of the three-stage pyrolysis temperature range is [800°C, 1000°C], the equipment used for the three-stage pyrolysis is a tubular furnace equipped with a rapid temperature rise and fall system, and the atmosphere used is oxygen;

[0030] The method for calculating the three-stage temperature according to the three-stage temperature formula for the three-stage pyrolysis process is:

[0031] Construct a three-stage temperature formula according to the preset three-stage initial temperature, the first-stage product quality index, the second-stage product quality index and the three-stage gas concentration ratio;

[0032] The method of constructing the three-level temperature control model and predicting the three-level real-time predicted temperature is as follows:

[0033] The three-level real-time prediction temperature selection LSTM model;

[0034] The prediction of the three-level real-time prediction temperature includes the following steps:

[0035] Step 21: Collect three-level training data; the three-level training data includes three-level input sample data and three-level label sample data;

[0036] The three-level input sample data includes the corresponding oxygen concentration time series composed of the oxygen concentration collected in time sequence at fixed time lengths in the historical optimal recovery experience of the three-level pyrolysis process, and the temperature time series of the actual temperature in the three-level pyrolysis equipment changing with time. The oxygen concentration time series and temperature time series in each time length are taken as a set of three-level input samples;

[0037] The three-level label sample data includes a three-level temperature label corresponding to each group of three-level input samples in the historical optimal recovery experience of the three-level pyrolysis process, and the three-level temperature label is a temperature value of one unit time after the corresponding three-level input sample;

[0038] Step 22: Model the three-stage temperature control model;

[0039] Step 23: Use the three-level input sample as the input of the three-level temperature control model, use the three-level temperature label as the real temperature of the three-level temperature control model, use the Adam optimizer to perform back propagation training on the three-level temperature control model, and adjust the model weight;

[0040] Step 24: Collect the three-level actual input data in the three-level pyrolysis process in the data form of the three-level input sample, input the three-level actual input data into the three-level temperature control model, and obtain the three-level real-time predicted temperature output by the three-level temperature control model.

[0041] An electronic device is proposed, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0042] The processor executes the above-mentioned method of recycling lithium cobalt oxide positive electrode materials in waste lithium batteries by the step-by-step pyrolysis method by calling the computer program stored in the memory.

[0043] A computer-readable storage medium is provided, on which a rewritable computer program is stored;

[0044] When the computer program is run on a computer device, the computer device is enabled to execute the above-mentioned method for recovering lithium cobalt oxide positive electrode materials in waste lithium batteries by the cascade pyrolysis method.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] The present invention realizes multi-level intelligent temperature control by combining formula-based real-time feedback control with a neural network model. Formula control is used to respond to current gas concentration and product quality changes in real time to ensure precise regulation in the short term; the neural network model predicts the optimal temperature at the next moment by learning from historical data to avoid excessive or delayed regulation of the system. Control systems at different stages can work together based on real-time data and long-term trends to overcome the problems of delayed response and frequent fluctuations in traditional temperature control systems. Through this solution, temperature regulation during the pyrolysis process is more precise, can adapt to different batches of raw materials and complex reaction conditions, improve the purity and electrochemical properties of potassium cobalt oxide cathode materials, and reduce energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a flow chart of the method for recovering lithium cobalt oxide positive electrode materials from waste lithium batteries by cascade pyrolysis method in Example 1 of the present invention;

[0048] Figure 2 This is a flow chart of the prediction process of the secondary real-time prediction temperature in Example 1 of the present invention;

[0049] Figure 3 This is a flow chart of the prediction process of the three-level real-time prediction temperature in Example 1 of the present invention. DETAILED DESCRIPTION

[0050] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] Example 1

[0052] like Figure 1As shown, the method for recovering lithium cobalt oxide positive electrode materials from waste lithium batteries by step pyrolysis method comprises the following steps:

[0053] Step 1: performing primary pyrolysis on the waste lithium battery within the primary pyrolysis temperature range, wherein the real-time temperature of the primary pyrolysis is adjusted in real time according to the primary temperature adjustment formula to obtain a primary product;

[0054] Step 2: performing secondary pyrolysis on the primary product within the secondary pyrolysis temperature range; calculating the secondary formula temperature according to the secondary temperature formula for the secondary pyrolysis process, and constructing a secondary temperature control model to predict the secondary real-time predicted temperature; performing real-time adjustment according to the secondary temperature adjustment formula based on the secondary formula temperature and the secondary real-time predicted temperature to obtain the secondary product;

[0055] Step 3: performing a three-stage pyrolysis on the secondary product within a three-stage pyrolysis temperature range, calculating the three-stage formula temperature of the three-stage pyrolysis process according to the three-stage temperature formula, and constructing a three-stage temperature control model to predict the three-stage real-time predicted temperature, and performing real-time adjustment according to the three-stage temperature adjustment formula based on the three-stage formula temperature and the three-stage real-time predicted temperature to obtain a lithium cobalt oxide product;

[0056] The specific temperature range of the primary pyrolysis temperature range is [200°C, 300°C], the purpose of the primary pyrolysis is to remove the organic binder (such as PVDF) in the electrode material, the equipment generally used is a rotary kiln equipped with a temperature gradient control system, and the atmosphere of the primary pyrolysis is protected by an inert gas (such as nitrogen) to prevent oxidation of the material;

[0057] The method of performing real-time adjustment according to the primary temperature adjustment formula is as follows:

[0058] Construct a first-stage temperature adjustment formula based on the preset first-stage initial temperature, real-time gas concentration and process product quality;

[0059] The main goal of primary pyrolysis is to remove binders and organic matter in lithium batteries, so the quality assessment mainly focuses on the removal efficiency of residues. Therefore, the quality of the process product is the real-time removal efficiency of residues during the primary pyrolysis process;

[0060] It is understandable that in the process of removing organic matter and binders, gases such as carbon dioxide and carbon monoxide will be generated, and some residues will also be generated. Therefore, by evaluating the real-time generation rate of the gas and the change rate of the residues, the removal efficiency of the residues can be evaluated;

[0061] Preferably, the calculation formula for the real-time removal efficiency is:

[0062]

[0063] Wherein, X is the real-time removal efficiency, Vco2 is the generation rate of carbon dioxide, Vco is the generation rate of carbon monoxide, Mc is the residual organic matter mass, Mz is the total organic matter mass; α1 and α2 are both preset proportional coefficients;

[0064] Specifically, gas sensors for carbon dioxide and carbon monoxide are used to monitor the gas generation rate in real time;

[0065] A thermogravimetric analyzer (TGA) or an online spectrometer is used to detect the real-time changes in the residual organic matter mass of waste lithium batteries during the primary pyrolysis process;

[0066] Further preferably, the primary temperature adjustment formula may be:

[0067]

[0068] Wherein, T_1 is the real-time temperature during the primary pyrolysis process, T0 is the preset primary initial temperature, generally, T0 is the lower limit of the primary pyrolysis temperature range, i.e., 200°C, Cco2 is the real-time concentration of carbon dioxide, Cco is the real-time concentration of carbon monoxide, k1 and k2 are respectively the preset proportional coefficients; wherein the ratio of carbon dioxide concentration to carbon monoxide concentration can be used to judge the reaction degree of the primary pyrolysis, when the ratio tends to be stable, it indicates that the binder is removed more thoroughly and the temperature can also be kept stable;

[0069] It is understandable that the primary temperature adjustment formula is based on the change of real-time gas concentration (such as CO, CO2), which can reflect the decomposition state of organic matter. When the removal rate of the binder changes, the system can quickly adjust the temperature to keep it in the range that is most conducive to the removal of organic matter, while monitoring the deviation of the residual material quality to control the temperature, which can avoid excessive temperature causing material degradation or excessive decomposition, and ensure the purity and structural integrity of the product;

[0070] Further, the secondary pyrolysis temperature range is [500° C., 700° C.], the purpose of the secondary pyrolysis is to reduce the trivalent cobalt in the lithium cobalt oxide to improve the subsequent extraction efficiency, the pyrolysis equipment used is a vertical reactor equipped with a precise temperature control system, and the pyrolysis atmosphere used is a reducing gas (such as a H2 / N2 mixed gas);

[0071] The method for calculating the secondary temperature of the secondary pyrolysis process according to the secondary temperature formula is as follows:

[0072] Construct a secondary temperature formula based on the preset secondary initial temperature, primary product quality index and secondary gas concentration ratio;

[0073] Preferably, the primary product quality index is the purity of the primary product obtained after the primary pyrolysis process is completed;

[0074] It is understood that the purpose of the primary pyrolysis process is to remove binders and organic matter, so the purity of the primary product can be expressed as the remaining amount of binders and organic matter;

[0075] As another preferred embodiment, the quality index of the primary product may also be the integrity of the crystal structure of the primary product, that is, evaluating the degree of damage to the crystal structure of lithium cobalt oxide caused by long-term pyrolysis; specifically, the integrity of the crystal structure may be analyzed by X-ray diffraction (XRD);

[0076] The specific secondary temperature formula may be:

[0077]

[0078] Among them, T_2 is the secondary formula temperature in the secondary pyrolysis process, T1 is the preset secondary initial temperature, which is generally taken as the lower limit of the secondary pyrolysis temperature range, i.e. 500°C; Q1 is the value of the primary product quality index, Qy1 is the primary target quality index value of the primary product; CH2 is the real-time concentration of hydrogen; α3 and α4 are both preset proportional coefficients;

[0079] Specifically, the first-level target quality index value can be obtained by conducting several experiments in advance; specifically for the first-level pyrolysis, the goal of the first-level pyrolysis is to remove the binder, and through experiments, it can be determined that the removal rate of the binder and organic matter is the highest or the integrity of the crystal structure is the highest at a certain temperature and time, so that the quality index of the corresponding first-level product is used as the first-level target quality index value;

[0080] In other preferred embodiments, the primary target quality index value can also be predicted by using a big data model through data analysis of multiple production processes to obtain the best target quality index value for each stage. For example, a large amount of production data can be analyzed using a machine learning method to find the optimal target quality value under different process conditions.

[0081] It can be understood that the secondary temperature formula combines the mass feedback of the previous stage product and the gas concentration control, not only based on the current gas concentration (such as H2 and CO2), but also combined with the reduction degree information of the previous stage product, so that the temperature control is more accurately targeted at the actual progress of the reduction process to ensure that the reduction reaction proceeds as expected;

[0082] Furthermore, the method of constructing the secondary temperature control model and predicting the secondary real-time predicted temperature is as follows:

[0083] The secondary temperature control model selects the LSTM model;

[0084] like Figure 2 As shown, the prediction of the secondary real-time predicted temperature includes the following steps:

[0085] Step 11: Collect secondary training data;

[0086] Specifically, the secondary training data includes secondary input sample data and secondary label sample data;

[0087] The secondary input sample data includes the historical optimal recovery experience of the secondary pyrolysis process, at fixed time intervals, the corresponding gas concentration time series composed of the concentrations of CO and CO2 collected in time sequence, the volatile concentration time series composed of the concentrations of volatile organic compounds in time sequence, and the temperature time series of the actual temperature in the secondary pyrolysis equipment changing with time, and the gas concentration time series, volatile concentration time series and temperature time series in each time length are used as a group of input samples; the historical optimal recovery experience of the secondary pyrolysis process refers to the recovery experience data that screens out the quality indicators of the secondary products that reach the expected secondary target quality indicator values ​​in the past process of recycling waste lithium batteries using the cascade pyrolysis method;

[0088] The secondary target quality index value may be the reduction rate of the reduced cobalt element; because the secondary pyrolysis process requires setting a target value for the completion of the reduction reaction, such as when the cobalt reduction rate reaches more than 95%, the corresponding quality can be used as the secondary target quality index value;

[0089] The secondary label sample data includes a temperature label corresponding to each group of input samples in the historical optimal recovery experience of the secondary pyrolysis process, and the temperature label is a temperature value of a unit time after the corresponding input sample;

[0090] Step 12: Model the secondary temperature control model;

[0091] The input layer of the secondary temperature control model receives multidimensional time series input (gas concentration time series, temperature time series), the hidden layer is one or more layers of LSTM units, which are used to capture long-term dependencies in the time series, and the output layer is a single node, which is used to predict the temperature at the next moment; and the mean square error is used to calculate the error between the model predicted temperature and the actual temperature;

[0092] Step 13: Use the secondary input sample as the input of the secondary temperature control model, use the temperature label as the actual temperature of the secondary temperature control model, use the Adam optimizer to perform back propagation training on the secondary temperature control model, and adjust the model weights;

[0093] Step 14: According to the data form of the secondary input sample, actual input data in the secondary pyrolysis process is collected, and the actual input data is input into the secondary temperature control model to obtain the secondary real-time predicted temperature output by the secondary temperature control model;

[0094] Furthermore, the specific form of the secondary temperature adjustment formula may be:

[0095] Tr_2=β×T_2+(1-β)×Tp2;

[0096] Among them, Tr_2 is the real-time temperature of secondary pyrolysis, Tp2 is the real-time predicted temperature of the secondary temperature control model, and β is the preset control parameter;

[0097] It is understandable that the LSTM model can reduce the temperature fluctuation of the system by smoothing the prediction, while the formula adjustment can quickly correct the deviation. The combined use can minimize the adverse effects of temperature changes and ensure the stability of product quality;

[0098] Further, the temperature range of the three-stage pyrolysis temperature is [800°C, 1000°C], the purpose of the three-stage pyrolysis is to recrystallize lithium cobalt oxide to improve purity and electrochemical performance, the equipment used is a tubular furnace equipped with a rapid temperature rise and fall system, and the atmosphere used is oxygen to promote the lithiation reaction;

[0099] Wherein, the method of calculating the third-level temperature according to the third-level temperature formula for the third-level pyrolysis process is:

[0100] Construct a three-stage temperature formula according to the preset three-stage initial temperature, the first-stage product quality index, the second-stage product quality index and the three-stage gas concentration ratio;

[0101] The secondary product quality index is the cobalt reduction rate of the secondary product obtained after the secondary pyrolysis process is completed;

[0102] Specifically, the three-level temperature formula may be:

[0103]

[0104] Among them, T_3 is the third-stage formula temperature in the three-stage pyrolysis process, T2 is the preset third-stage initial temperature, and the general value is the lower limit of the three-stage pyrolysis temperature range, that is, 800°C; Q2 is the secondary product quality index, Qy2 is the secondary target quality index value, ΔCo2 is the real-time change rate of oxygen concentration, and Co2 is the real-time oxygen concentration; α5, α6 and α7 are all preset proportional coefficients;

[0105] It can be understood that the three-stage temperature formula ensures the optimal reorganization of the crystal structure through multi-level feedback control. Specifically, the temperature setting combines the product quality feedback of the first two stages, the current oxygen concentration change and the real-time monitoring of the crystal structure, which can better adjust the temperature to adapt to the crystal reorganization process and improve the purity of lithium cobalt oxide. The temperature can be adjusted by oxygen concentration feedback, which can optimize the use of oxygen at different stages of the oxidation reaction, prevent insufficient or excessive oxidation, and improve the electrochemical performance of the final product.

[0106] Furthermore, the three-level temperature control model is constructed to predict the three-level real-time predicted temperature in the following manner:

[0107] The three-level real-time prediction temperature selection LSTM model;

[0108] like Figure 3 As shown, the prediction of the three-level real-time prediction temperature includes the following steps:

[0109] Step 21: Collect three-level training data;

[0110] Specifically, the three-level training data includes three-level input sample data and three-level label sample data;

[0111] The three-level input sample data includes the corresponding oxygen concentration time series composed of the oxygen concentration collected in time sequence at fixed time lengths in the historical optimal recovery experience of the three-level pyrolysis process, and the temperature time series of the actual temperature in the three-level pyrolysis equipment changing with time, and the oxygen concentration time series and temperature time series in each time length are used as a group of three-level input samples; the historical optimal recovery experience of the three-level pyrolysis process refers to the recovery experience data that screens out the quality indicators of the final product that reaches the expected final target quality in the past process of recycling waste lithium batteries using the cascade pyrolysis method; the final target quality can be the target purity of crystallized lithium cobalt oxide set according to experience;

[0112] The three-level label sample data includes a three-level temperature label corresponding to each group of three-level input samples in the historical optimal recovery experience of the three-level pyrolysis process, and the three-level temperature label is a temperature value of one unit time after the corresponding three-level input sample;

[0113] Step 22: Model the three-stage temperature control model;

[0114] The input layer of the three-level temperature control model receives multi-dimensional time series input (oxygen concentration time series, temperature time series), the hidden layer is one or more layers of LSTM units, which are used to capture long-term dependencies in the time series, and the output layer is a single node, which is used to predict the temperature at the next moment; and the mean square error is used to calculate the error between the model predicted temperature and the actual temperature;

[0115] Step 23: Use the three-level input sample as the input of the three-level temperature control model, use the three-level temperature label as the real temperature of the three-level temperature control model, use the Adam optimizer to perform back propagation training on the three-level temperature control model, and adjust the model weight;

[0116] Step 24: collecting the third-level actual input data in the third-level pyrolysis process according to the data form of the third-level input sample, inputting the third-level actual input data into the third-level temperature control model, and obtaining the third-level real-time predicted temperature output by the third-level temperature control model;

[0117] Furthermore, the specific form of the three-stage temperature adjustment formula may be:

[0118] Tr_3=γ×T_3+(1-γ)×Tp3;

[0119] Among them, Tr_3 is the real-time temperature of secondary pyrolysis, Tp3 is the third-level real-time predicted temperature predicted by the three-level temperature control model, and γ is a pre-set control parameter.

[0120] Example 2

[0121] According to another aspect of the present application, an electronic device is provided. The electronic device may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are executed by one or more processors, the method for recovering lithium cobalt oxide positive electrode materials from waste lithium batteries by the stepwise pyrolysis method as described above may be executed.

[0122] The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, an input / output component, a hard disk, etc. A storage device in the electronic device, such as a ROM or a hard disk, may store the method for recycling lithium cobalt oxide positive electrode materials in waste lithium batteries by a cascade pyrolysis method provided in the present application.

[0123] Furthermore, the electronic device may also include a user interface. Of course, when implementing different devices, one or more components in the above electronic device may be omitted according to actual needs.

[0124] Example 3

[0125] A computer-readable storage medium according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, the method for recovering lithium cobalt oxide positive electrode materials in waste lithium batteries by the step-by-step pyrolysis method according to the embodiment of the present application described with reference to the above figures can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0126] In addition, according to the implementation of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, the non-transitory machine-readable storage medium stores machine-readable instructions, the machine-readable instructions can be run by a processor to execute instructions corresponding to the method steps provided by the present application, and when the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0127] The methods, apparatuses, and devices of the present application may be implemented in many ways. For example, the methods, apparatuses, and devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers recording media storing programs for executing the method according to the present application.

[0128] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0129] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0130] The above preset parameters or preset thresholds are all set by technicians in this field according to actual conditions or obtained through large-scale data simulation.

[0131] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for recovering lithium cobalt oxide positive electrode materials from waste lithium batteries by cascade pyrolysis, characterized in that: The following steps are involved: Step 1: performing primary pyrolysis on the waste lithium battery within the primary pyrolysis temperature range, wherein the real-time temperature of the primary pyrolysis is adjusted in real time according to the primary temperature adjustment formula to obtain a primary product; Step 2: performing secondary pyrolysis on the primary product within a secondary pyrolysis temperature range; For the secondary pyrolysis process, the secondary formula temperature is calculated according to the secondary temperature formula, and a secondary temperature control model is constructed to predict the secondary real-time predicted temperature; According to the secondary formula temperature and the secondary real-time predicted temperature, real-time adjustment is performed according to the secondary temperature adjustment formula to obtain the secondary product; Step three: perform tertiary pyrolysis on the secondary product within the tertiary pyrolysis temperature range, calculate the tertiary formula temperature of the tertiary pyrolysis process according to the tertiary temperature formula, and construct a tertiary temperature control model to predict the tertiary real-time predicted temperature. According to the tertiary formula temperature and the tertiary real-time predicted temperature, perform real-time adjustment according to the tertiary temperature adjustment formula to obtain lithium cobalt oxide product.

2. The method for recovering lithium cobalt oxide positive electrode materials from waste lithium batteries by cascade pyrolysis according to claim 1, characterized in that: The specific temperature range of the primary pyrolysis temperature range is [200°C, 300°C], the equipment used for the primary pyrolysis is a rotary kiln equipped with a temperature gradient control system, and the atmosphere of the primary pyrolysis adopts an inert gas; The temperature range of the secondary pyrolysis is [500°C, 700°C], the pyrolysis equipment used in the secondary pyrolysis is a vertical reactor equipped with a precise temperature control system, and the pyrolysis atmosphere used is a reducing gas; The temperature range of the three-stage pyrolysis temperature is [800° C., 1000° C.], the equipment used for the three-stage pyrolysis is a tubular furnace equipped with a rapid temperature rise and fall system, and the atmosphere used is oxygen.

3. The method for recovering lithium cobalt oxide positive electrode materials from waste lithium batteries by cascade pyrolysis according to claim 2, characterized in that: The method of performing real-time adjustment according to the primary temperature adjustment formula is: Construct a first-stage temperature adjustment formula based on the preset first-stage initial temperature, real-time gas concentration and process product quality; The method for calculating the secondary temperature of the secondary pyrolysis process according to the secondary temperature formula is: Construct a secondary temperature formula based on the preset secondary initial temperature, primary product quality index and secondary gas concentration ratio; The method for calculating the three-stage temperature according to the three-stage temperature formula for the three-stage pyrolysis process is: A three-stage temperature formula is constructed based on the preset three-stage initial temperature, the first-stage product quality index, the second-stage product quality index and the three-stage gas concentration ratio.

4. The method for recovering lithium cobalt oxide positive electrode materials from waste lithium batteries by cascade pyrolysis according to claim 3, characterized in that: The method of constructing the secondary temperature control model and predicting the secondary real-time predicted temperature is as follows: The secondary temperature control model selects the LSTM model; The prediction of the secondary real-time predicted temperature comprises the following steps: Step 11: Collect secondary training data; the secondary training data includes secondary input sample data and secondary label sample data; Step 12: Model the secondary temperature control model; Step 13: Use the secondary input sample as the input of the secondary temperature control model, use the temperature label as the actual temperature of the secondary temperature control model, use the Adam optimizer to perform back propagation training on the secondary temperature control model, and adjust the model weight; Step 14: According to the data format of the secondary input sample, collect the actual input data in the secondary pyrolysis process, input the actual input data into the secondary temperature control model, and obtain the secondary real-time predicted temperature output by the secondary temperature control model.

5. The method for recovering lithium cobalt oxide positive electrode materials from waste lithium batteries by cascade pyrolysis according to claim 4, characterized in that: The secondary input sample data includes the gas concentration time series composed of the concentrations of CO and CO2 collected in time sequence at fixed time intervals in the historical optimal recovery experience of the secondary pyrolysis process, the volatile concentration time series composed of the concentrations of volatile organic compounds in time sequence, and the temperature time series of the actual temperature in the secondary pyrolysis equipment changing with time. The gas concentration time series, volatile concentration time series and temperature time series in each time length are taken as a group of input samples; The secondary label sample data includes a temperature label corresponding to each group of input samples in the historical optimal recovery experience of the secondary pyrolysis process, and the temperature label is a temperature value of a unit time after the corresponding input sample.

6. The method for recovering lithium cobalt oxide positive electrode materials from waste lithium batteries by cascade pyrolysis according to claim 5, characterized in that: The method of constructing the three-level temperature control model and predicting the three-level real-time predicted temperature is as follows: The three-level real-time prediction temperature selection LSTM model; The prediction of the three-level real-time prediction temperature includes the following steps: Step 21: Collect three-level training data; the three-level training data includes three-level input sample data and three-level label sample data; Step 22: Model the three-stage temperature control model; Step 23: Use the three-level input sample as the input of the three-level temperature control model, use the three-level temperature label as the real temperature of the three-level temperature control model, use the Adam optimizer to perform back propagation training on the three-level temperature control model, and adjust the model weight; Step 24: Collect the three-level actual input data in the three-level pyrolysis process in the data form of the three-level input sample, input the three-level actual input data into the three-level temperature control model, and obtain the three-level real-time predicted temperature output by the three-level temperature control model.

7. The method for recovering lithium cobalt oxide positive electrode materials from waste lithium batteries by cascade pyrolysis according to claim 6, characterized in that: The three-level input sample data includes the corresponding oxygen concentration time series composed of the oxygen concentration collected in time sequence at fixed time lengths in the historical optimal recovery experience of the three-level pyrolysis process, and the temperature time series of the actual temperature in the three-level pyrolysis equipment changing with time. The oxygen concentration time series and temperature time series in each time length are taken as a set of three-level input samples; The three-level label sample data includes a three-level temperature label corresponding to each group of three-level input samples in the historical optimal recovery experience of the three-level pyrolysis process, and the three-level temperature label is a temperature value of a unit time after the corresponding three-level input sample.

8. An electronic device, characterized in that: include: A processor and a memory, wherein: The memory stores a computer program that can be called by the processor; The processor executes the method for recovering lithium cobalt oxide positive electrode materials in waste lithium batteries by the stepwise pyrolysis method as described in any one of claims 1 to 7 in the background by calling the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that: A rewritable computer program is stored thereon; When the computer program is run on a computer device, the computer device executes the method for recovering lithium cobalt oxide positive electrode materials in waste lithium batteries by a cascade pyrolysis method as described in any one of claims 1 to 7 in the background.

Images