Method for Extracting and Recycling High-Purity Lithium Carbonate and Iron Phosphate from Waste Lithium Battery Materials

Abstract

The present invention discloses a method for extracting and recycling high-purity lithium carbonate and iron phosphate from waste lithium battery materials, specifically relating to the technical field of extraction and recycling, including: Step 1: In the first extraction stage, obtain the first extraction control index at the moment of T1 + a of the extraction equipment, and obtain the first characteristic data of the leaching solution in the extraction equipment; mark the first extraction control index and the first characteristic data as iron phosphate characteristic data; both T1 and a are integers greater than zero; Step 2: Input the iron phosphate characteristic data into a pre-constructed iron phosphate quality analysis model to obtain the first quality index at the moment of T1 + a; The present invention predicts the extraction state in real time through the quality analysis model and generates a warning for abnormal extraction states; when the extraction equipment is in an abnormal extraction state, the system will automatically generate a regulation instruction and perform regulation according to the optimal regulation strategy to ensure that the extraction process is promptly restored to the normal state, reducing the uncontrollable risks in the operation.

Description

Technical Field

[0001] The present invention relates to the technical field of extraction and recovery, and more specifically, to a method for extracting and recovering high-purity lithium carbonate and iron phosphate from waste lithium battery materials. Background Art

[0002] In the recycling of waste lithium batteries, lithium carbonate and iron phosphate, as important materials in battery manufacturing, have extremely high recycling value. Through an effective extraction and recovery process, not only can high-purity lithium carbonate be extracted from waste batteries, but also the cathode material iron phosphate can be recovered for the preparation of lithium iron phosphate batteries. However, traditional recycling methods have many deficiencies in process control, product purity, and resource utilization rate, such as complex processes, low efficiency, and difficulty in ensuring product purity. Therefore, how to introduce intelligent control throughout the recycling process, precisely manage each link, and ensure high-efficiency recycling while improving product quality has become an important research direction in current waste lithium battery recycling technology.

[0003] In the prior art, a Chinese patent application with the publication number CN117270591A discloses a monitoring method and system for an extraction production line. By obtaining the absorbance of the liquid in each extraction tank at the same set wavelength in real time; mapping the obtained absorbance information to the concentration of the set element in the liquid in each extraction tank, and determining the balance point position according to the distribution of the concentration of the set element in the liquid in each extraction tank; in the case where the balance point position is not the preset position, generating a prompt message for adjusting the process or adjusting the flow rate of the liquid flowing into the extraction tank according to the relationship between the balance point position and the preset position. Although this method can achieve real-time monitoring and control of the extraction production line, through research and application of the above method and the prior art, it is found that the accuracy of this control system is not high, which may lead to over-regulation or under-regulation and cannot maintain a stable process.

[0004] Therefore, the present invention provides a method for extracting and recovering high-purity lithium carbonate and iron phosphate from waste lithium battery materials. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a method for extracting and recovering high-purity lithium carbonate and iron phosphate from waste lithium battery materials to solve the problems raised in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solution: A method for extracting and recovering high-purity lithium carbonate and iron phosphate from waste lithium battery materials, comprising:

[0007] Step 1: In the first extraction stage, obtain the first extraction control index at the moment of T1 + a of the extraction equipment, and obtain the first characteristic data of the leaching solution in the extraction equipment; mark the first extraction control index and the first characteristic data as iron phosphate characteristic data; both T1 and a are integers greater than zero.

[0008] Step 2: Input the ferric phosphate characteristic data into a pre - constructed ferric phosphate quality analysis model to obtain the first quality index at time T1 + a.

[0009] Step 3: Determine whether the extraction equipment is in an abnormal extraction state at time T1 + a according to the first quality index. If an abnormal extraction state occurs, generate an extraction adjustment instruction and jump to Step 4; if no abnormal extraction state occurs, generate a second extraction instruction and jump to Step 5.

[0010] Step 4: Adjust the extraction equipment based on the first quality index according to the extraction adjustment instruction to optimize the extraction process and obtain high - purity ferric phosphate.

[0011] Step 5: Receive the second extraction instruction, obtain the second quality index of the extraction equipment at time T2 + b in the second extraction stage, and determine whether the extraction equipment is in an abnormal extraction state at time T2 + b based on the second quality index; if so, generate a second extraction adjustment instruction and jump to Step 6, if not, continue the extraction until the extraction of lithium carbonate is completed.

[0012] Step 6: Receive the second extraction adjustment instruction, adjust the extraction equipment based on the second quality index to obtain high - purity lithium carbonate.

[0013] Furthermore, the method for obtaining the first extraction control index of the extraction equipment at time T1 + a includes:

[0014] Step a1. Collect the first parameter characteristic data at time T1. The first parameter characteristic data includes the first temperature value, the first pH value, and the first stirring speed; mark the first temperature value, the first pH value, and the first stirring speed as Ws1, Ph1, and Sd1 respectively.

[0015] Step a2. Perform formula - based calculation on the first parameter characteristic data to obtain the first extraction control index at time T1. The calculation formula is:

[0016] θ1=(Ws1×α1 + Ph1×α2+Sd1×α3)+(μ1×Ws1×Ph1);

[0017] In the formula, θ1 represents the first extraction control index at time T1, α1 represents the weight factor of the first temperature value, α2 represents the weight factor of the first pH value, α3 represents the weight factor of the first stirring speed, and μ1 represents the weighted coefficient of the interaction between the first temperature value and the first pH value.

[0018] Step a3. Input the first extraction control index at time T1 into a pre - constructed parameter analysis model to predict the first extraction control index at time T1 + a.

[0019] Further, the method for generating the pre-constructed parameter analysis model includes:

[0020] Obtain historical first extraction control indices, establish an extraction time series set based on the historical first extraction control indices. The extraction time series set includes u historical first extraction control indices, and the time intervals for obtaining the u historical first extraction control indices are equal. The u historical first extraction control indices correspond to a preset time; the unit of the preset time is seconds or minutes.

[0021] Preset a sliding step size and a sliding window length; use the sliding window method to transform the historical first extraction control indices in the extraction time series set into multiple training samples, take the training samples as the input of the recurrent neural network model, predict the first extraction control index after the sliding step size as the output, take the first extraction control index of each training sample as the prediction target, and take the prediction accuracy as the training target to train the recurrent neural network model; generate a parameter analysis model for predicting the first extraction control index at a future time based on the historical first extraction control indices in the extraction time series set; wherein, the recurrent neural network model is an RNN neural network model.

[0022] Further, the first feature data includes iron ion concentration, viscosity of the leaching solution, and impurity percentage of the leaching solution; the iron ion concentration is directly analyzed by a concentration analysis device; the viscosity of the leaching solution is measured by a rotational viscometer or a capillary viscometer.

[0023] The method for obtaining the impurity percentage of the leaching solution includes:

[0024] Step b1. Collect a leaching solution sample and analyze the impurity ion concentration through a concentration analysis device; the impurity ion concentration includes the concentrations of copper, zinc, and lithium ions.

[0025] Step b2. Calculate the mass of the impurity ions: m i = C i × V, where m i represents the mass of the i-th impurity ion, C i represents the concentration of the i-th impurity ion; V represents the volume of the leaching solution sample.

[0026] Step b3. Accumulate the masses of all impurity ions to obtain the total mass of the impurities: m 总 = ∑m i .

[0027] Step b4. Obtain the total mass M 浸出液 of the leaching solution sample, and calculate the impurity percentage Zbf according to the total mass m 总 of the impurities and the total mass M 浸出液 of the leaching solution sample:

[0028] Further, the method for generating the pre - constructed iron phosphate quality analysis model includes:

[0029] Convert each group of iron phosphate characteristic data into the form of a first feature vector. All the elements of the first feature vectors are used as the input of the iron phosphate quality analysis model. The iron phosphate quality analysis model takes the first quality index predicted by each group of iron phosphate characteristic data as the output, takes the actual first quality index corresponding to each group of iron phosphate characteristic data as the prediction target, and takes minimizing the sum of the first prediction accuracies of all predicted first quality indices as the training target; where the calculation formula for the first prediction accuracy is: Z1=(a n -y n ) 2 , where n is the number of each group of iron phosphate characteristic data, Z1 is the first prediction accuracy, a n is the predicted first quality index corresponding to the nth group of iron phosphate characteristic data, and y n is the actual first quality index corresponding to the nth group of iron phosphate characteristic data; train the iron phosphate quality analysis model until the sum of the first prediction accuracies reaches convergence and then stop training; the iron phosphate quality analysis model is a deep neural network model or a deep belief network model.

[0030] Further, the method for determining whether the extraction equipment is in an abnormal extraction state at time T1 + a includes:

[0031] Mark the first quality index at time T1 + a predicted by the iron phosphate quality analysis model as Zls. And preset a first index threshold, where the preset first index threshold includes S1 and S2, and S1 > S2.

[0032] Compare the first quality index with the preset first index threshold.

[0033] If Zls > S1 or Zls < S2, it is determined that the extraction equipment is in an abnormal extraction state at time T1 + a.

[0034] If S1 ≥ Zls ≥ S2, it is determined that the extraction equipment is in a normal extraction state at time T1 + a, continue the extraction with the first parameter characteristic data corresponding to the first extraction control index, and enter the second extraction stage.

[0035] Further, the method for adjusting the extraction equipment based on the first quality index includes:

[0036] Input the first parameter characteristic data corresponding to the first quality index into the pre - constructed digital twin model for simulation to obtain the optimal adjustment strategy.

[0037] The method for obtaining the optimal adjustment strategy includes:

[0038] Step c1. Obtain the first parameter characteristic data of the extraction equipment. Take the first pH value and the first stirring speed in the first parameter characteristic data as fixed quantities, the first temperature value as a variable, and take the current parameter value of the first temperature value as W.

[0039] Step c2. Let W = W + D1, and record the first quality index under the parameter value W, where D1 is a natural number greater than zero.

[0040] Step c3. Repeat step c2 in a loop. When W is equal to the preset first temperature threshold, obtain G first quality indices under the first temperature parameter value, and jump to step c4, where G is an integer greater than zero.

[0041] Step c4. Take the first temperature value and the first stirring speed as fixed quantities, the first pH value as a variable, and take the current parameter value of the first pH value as U.

[0042] Step c5. Reset W, let U = U + D2, and record the first quality index under the parameter value U, where D2 is a natural number greater than zero.

[0043] Step c6. Repeat step c5 in a loop. When U is equal to the preset first pH threshold, obtain H first quality indices under the first pH parameter value, where H is an integer greater than zero.

[0044] Step c7. Take the first temperature value and the first pH value as fixed quantities, the first stirring speed as a variable, and take the current parameter value of the first stirring speed as F.

[0045] Step c8. Reset U, let F = F + D3, and record the first quality index under the parameter value F, where D3 is a natural number greater than zero.

[0046] Step c9. Repeat step c8 in a loop. When F is equal to the preset first stirring speed threshold, obtain K first quality indices under the first stirring speed parameter value, where K is an integer greater than zero.

[0047] Step c10. Mark the G first quality indices under the first temperature parameter value, the H first quality indices under the first pH parameter value, and the K first quality indices under the first stirring speed parameter value as the first extraction control data. Perform cumulative fusion on the first extraction control data to obtain L first quality indices, and sort the L first quality indices from largest to smallest in terms of numerical value.

[0048] Step c11. Take the first temperature value, the first pH value, and the first stirring speed of the extraction equipment corresponding to the first quality index with the largest numerical value in the sorting as the optimal adjustment strategy.

[0049] Further, in the first extraction stage, the value range of the first temperature value in the first parameter characteristic data is [40°C, 60°C], the value range of the first pH value is [3, 5], and the value range of the first stirring speed is [100 rpm, 300 rpm]; in the second extraction stage, the value range of the second temperature value in the second parameter characteristic data is [50°C, 70°C], the value range of the second pH value is [8, 10], and the value range of the second stirring speed is [50 rpm, 150 rpm].

[0050] Further, the method for obtaining the second quality index at the T2 + b moment of the extraction equipment includes:

[0051] Obtain the second extraction control index at the T2 + b moment of the extraction equipment and the second characteristic data of the extraction mixture in the extraction equipment, and label them as lithium carbonate characteristic data; the second characteristic data includes lithium ion concentration, viscosity of the extraction mixture, and impurity percentage.

[0052] Input the lithium carbonate characteristic data into a pre - constructed lithium carbonate quality analysis model to obtain the second quality index at the T2 + b moment.

[0053] Further, the method for generating the lithium carbonate quality analysis model includes:

[0054] Convert each group of lithium carbonate characteristic data into the form of a second feature vector, and use all the elements of the second feature vectors as the input of the lithium carbonate quality analysis model. The lithium carbonate quality analysis model takes the second quality index predicted by each group of lithium carbonate characteristic data as the output, takes the actual second quality index corresponding to each group of lithium carbonate characteristic data as the prediction target, and takes minimizing the sum of the second prediction accuracies of all predicted second quality indexes as the training target; among them, the calculation formula for the second prediction accuracy is: Z2 = (b m -s m ) 2 , where m is the number of each group of lithium carbonate characteristic data, Z2 is the second prediction accuracy, b m is the predicted second quality index corresponding to the m - th group of lithium carbonate characteristic data, and s m is the actual second quality index corresponding to the m - th group of lithium carbonate characteristic data; train the lithium carbonate quality analysis model until the sum of the second prediction accuracies reaches convergence and then stop training; the lithium carbonate quality analysis model is a deep neural network model or a deep belief network model.

[0055] Further, the method for obtaining the second extraction control index at the T2 + b moment of the extraction equipment includes:

[0056] Step d1. Collect the second parameter characteristic data at time T2. The second parameter characteristic data includes the second temperature value, the second pH value, and the second stirring speed. Mark the second temperature value, the second pH value, and the second stirring speed as Ws2, Ph2, and Sd2 respectively.

[0057] Step d2. Based on the first extraction control index, perform a formula calculation on the second parameter characteristic data to obtain the second extraction control index at time T2. The calculation formula is:

[0058] θ2 = θ1 - (Ws2 × β1 + Ph2 × β2 + Sd2 × β3) + (μ2 × Ws2 × Ph2).

[0059] In the formula, θ2 represents the second extraction control index, β1 represents the weight factor of the second temperature value, β2 represents the weight factor of the second pH value, β3 represents the weight factor of the second stirring speed, and μ2 represents the weighted coefficient of the interaction between the second temperature value and the second pH value.

[0060] Step d3. Input the second extraction control index at time T2 into the pre-constructed parameter analysis model to predict the second extraction control index at time T2 + b.

[0061] Further, the method for determining whether the extraction equipment is in an abnormal extraction state at time T2 + b includes:

[0062] Mark the second quality index at time T2 + b predicted by the quality analysis model of lithium carbonate as Zlz; and preset a second index threshold, where the preset second index threshold includes Y1 and Y2, and Y1 > Y2.

[0063] Compare the second quality index with the preset second index threshold.

[0064] If Zlz > Y1 or Zls < Y2, it is determined that the extraction equipment is in an abnormal extraction state at time T2 + b.

[0065] If Y1 ≥ Zlz ≥ Y2, it is determined that the extraction equipment is in a normal extraction state at time T2 + b, and continue to complete the extraction with the second parameter characteristic data corresponding to the second extraction control index to obtain high-purity lithium carbonate.

[0066] The technical effects and advantages of the present invention:

[0067] 1. By obtaining the first extraction control index and the first characteristic data of the extraction equipment at time T1 + a and inputting them into the iron phosphate quality analysis model, the separation effect of iron phosphate in the first extraction stage can be predicted in real time. By obtaining the second extraction control index and the second characteristic data of the extraction equipment at time T2 + b and inputting them into the lithium carbonate quality analysis model, the separation effect of lithium carbonate in the second extraction stage can be predicted in real time. Based on different extraction stages and precise extraction control methods, the error in the operation process can be effectively reduced, ensuring the best temperature, pH value, and stirring speed during the extraction process, thereby improving the purity and recovery rate of the product.

[0068] 2. The present invention predicts the extraction state in real time through a quality analysis model and generates a warning for abnormal extraction states. When the extraction equipment is in an abnormal extraction state, the system automatically generates an adjustment instruction and adjusts according to the optimal adjustment strategy to ensure that the extraction process promptly returns to the normal state, reducing the uncontrollable risks in the operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 Flow chart of the method for extracting and recovering high-purity lithium carbonate and iron phosphate from waste lithium battery materials in Example 1;

[0070] Figure 2 Flow chart of the method for obtaining the first extraction control index of the extraction equipment at time T1 + a in Example 1;

[0071] Figure 3 Flow chart of the method for obtaining the impurity percentage of the leaching solution in Example 1;

[0072] Figure 4 Flow chart of the method for obtaining the optimal adjustment strategy in Example 1. DETAILED DESCRIPTION OF THE INVENTION

[0073] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a 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 those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0074] In addition, the attached drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0075] It should be understood that although terms such as "first" and "second" may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0076] Embodiment 1

[0077] Please refer to Figure 1 As shown, this embodiment discloses a method for extracting and recycling high-purity lithium carbonate and iron phosphate from waste lithium battery materials, including:

[0078] Step 1: In the first extraction stage, obtain the first extraction control index at the T1 + a moment of the extraction device, and obtain the first characteristic data of the leaching solution in the extraction device; mark the first extraction control index and the first characteristic data as iron phosphate characteristic data; both T1 and a are integers greater than zero.

[0079] It should be understood that: the extraction device is a solvent extractor for preparing high-purity lithium carbonate and iron phosphate, and the solvent extractor at least includes components such as a leaching reaction kettle, a pH automatic control system, a temperature control system, a filtration and centrifugation device, and an automatic stirring system; among them, the leaching reaction kettle is used to mix waste lithium battery materials with a solvent for preliminary dissolution and reaction; the pH automatic control system is used to monitor and adjust the pH value of the solution to ensure the separation conditions of iron phosphate and lithium carbonate; the temperature control system consists of a heating and cooling system, and dynamically adjusts the temperature in the leaching reaction kettle according to the feedback of the temperature sensor to ensure the best precipitation conditions; the filtration and centrifugation device is used to separate the solid substances after precipitation, such as iron phosphate and lithium carbonate; the automatic stirring system is used to ensure the uniform mixing of the extractant and waste battery materials to prevent precipitation or insufficient local reaction. The leaching solution contains the useful components dissolved in the solid substances (such as iron ions and lithium ions) and undissolved impurities.

[0080] It should be noted that in the first extraction stage, a first extractant with a preset concentration is added to the leachate, and D2EHPA (di(2-ethylhexyl)phosphoric acid) is selected as the selective extractant for iron. The purpose of setting the first extraction stage is to optimize the precipitation efficiency of iron phosphate under different conditions, avoid the generation of impurities, improve the product purity, and at the same time ensure the stability and high recovery rate of this extraction stage. The conditions of the first extraction stage (such as pH value, temperature and stirring speed) are precisely controlled for the leachate to ensure the purity of the best iron phosphate extraction.

[0081] Please refer to Figure 2 As shown, specifically, the method for obtaining the first extraction control index at the T1 + a moment of the extraction equipment includes:

[0082] Step a1. Collect the first parameter characteristic data at the T1 moment. The first parameter characteristic data includes the first temperature value, the first pH value and the first stirring speed; mark the first temperature value, the first pH value and the first stirring speed as Ws1, Ph1 and Sd1 respectively.

[0083] It should be noted that the first temperature value is collected through the temperature sensor connected in the temperature control system; the first pH value is collected through the pH meter connected in the pH automatic control system.

[0084] Step a2. Perform formula calculation on the first parameter characteristic data to obtain the first extraction control index at the T1 moment. Its calculation formula is:

[0085] θ1 = (Ws1 × α1 + Ph1 × α2 + Sd1 × α3) + (μ1 × Ws1 × Ph1).

[0086] In the formula, θ1 represents the first extraction control index at the T1 moment, α1 represents the weight factor of the first temperature value, α2 represents the weight factor of the first pH value, α3 represents the weight factor of the first stirring speed, and μ1 represents the weighted coefficient of the interaction between the first temperature value and the first pH value.

[0087] It should be noted that the larger the value of μ1, the more significant the influence of the interaction between the first temperature value and the first pH value on the extraction efficiency; the larger the value of the first parameter characteristic data, the larger the first extraction control index. On the contrary, the smaller the value of the first parameter characteristic data, the smaller the first extraction control index. The calculation of the first extraction control index is a dimensionless calculation.

[0088] It should be further noted that: the weight factor can be set according to the actual situation. The weight factor reflects the influence degree of each first parameter characteristic data on the actual extraction purity of the extraction equipment. Those skilled in the art can preset the corresponding weight factor according to the influence degree of each first parameter characteristic data on the actual extraction purity of the extraction equipment, so as to accurately evaluate the purity of the actually extracted iron phosphate by the extraction equipment.

[0089] Step a3. Input the first extraction control index at time T1 into the pre-constructed parameter analysis model to predict the first extraction control index at time T1 + a.

[0090] Among them, the generation method of the pre-constructed parameter analysis model includes:

[0091] Obtain the historical first extraction control index, and establish an extraction time series set based on the historical first extraction control index. The extraction time series set includes u historical first extraction control indexes. The time intervals for obtaining the u historical first extraction control indexes are equal, and the u historical first extraction control indexes correspond to a preset time; the unit of the preset time can be seconds or minutes, which is specifically set by the staff.

[0092] Preset the sliding step length and the sliding window length according to the actual experience of the staff; use the sliding window method to convert the historical first extraction control indexes in the extraction time series set into multiple training samples, use the training samples as the input of the recurrent neural network model, predict the first extraction control index after the sliding step length as the output, use the first extraction control index of each training sample as the prediction target, and use the prediction accuracy as the training target to train the recurrent neural network model; generate a parameter analysis model for predicting the first extraction control index at a future time based on the historical first extraction control indexes in the extraction time series set; among them, the recurrent neural network model is an RNN neural network model.

[0093] Among them, the first characteristic data includes the iron ion concentration, the viscosity of the leaching solution, and the impurity percentage of the leaching solution.

[0094] It should be noted that: the iron ion concentration is directly analyzed by a concentration analysis device; the higher the iron ion concentration, the more iron content is extracted from the leaching solution in the first extraction stage, which helps to judge the effect and efficiency of iron phosphate extraction; the viscosity of the leaching solution is measured by a rotational viscometer or a capillary viscometer; a higher viscosity affects the fluidity and mass transfer efficiency, and also indicates the presence of a higher solid suspension (iron phosphate). The concentration analysis device includes an ICP-OES or AAS device.

[0095] Please refer to Figure 3 As shown, among them, the method for obtaining the impurity percentage of the leaching solution includes:

[0096] Step b1. Collect the leaching solution sample and analyze the impurity ion concentration through a concentration analysis device; the impurity ion concentration includes the concentrations of copper, zinc, and lithium ions.

[0097] Step b2. Calculate the mass of the impurity ions: m i = C i × V, where m i represents the mass of the i-th impurity ion, C i represents the concentration of the i-th impurity ion; V represents the volume of the leaching solution sample;

[0098] Step b3. Accumulate the masses of all impurity ions to obtain the total mass of the impurities: m 总 = ∑m i ;

[0099] Step b4. Obtain the total mass M 浸出液 of the leaching solution sample. According to the total mass m 总 of the impurities and the total mass M 浸出液 of the leaching solution sample, calculate the impurity percentage Zbf:

[0100] It should be noted that the total mass M 浸出液 of the leaching solution sample is measured in advance by an electronic balance and pre-stored in the system database.

[0101] Step 2: Input the iron phosphate characteristic data into a pre-constructed iron phosphate quality analysis model to obtain the first quality index at time T1 + a.

[0102] In implementation, the generation method of the pre-constructed iron phosphate quality analysis model includes:

[0103] Convert each group of iron phosphate characteristic data into the form of a first feature vector. All elements of the first feature vectors are used as the input of the iron phosphate quality analysis model. The iron phosphate quality analysis model takes the first quality index predicted by each group of iron phosphate characteristic data as the output, takes the actual first quality index corresponding to each group of iron phosphate characteristic data as the prediction target, and takes minimizing the sum of the first prediction accuracies of all predicted first quality indexes as the training target.

[0104] It should be noted that: the first quality index specifically refers to the purity of the iron phosphate extracted and recovered in the first extraction stage, which is measured and obtained by methods such as ICP-OES (Inductively Coupled Plasma Optical Emission Spectrometry), XRF (X-ray Fluorescence Spectrometry), etc.

[0105] Among them, the calculation formula for the first prediction accuracy is: Z1 = (a n - y n ) 2, where n is the number of each group of iron phosphate characteristic data, Z1 is the first prediction accuracy, and a n is the predicted first quality index corresponding to the nth group of iron phosphate characteristic data, and y n is the actual first quality index corresponding to the nth group of iron phosphate characteristic data; the iron phosphate quality analysis model is trained until the sum of the first prediction accuracies reaches convergence and then the training stops.

[0106] It should be noted that: the iron phosphate quality analysis model is a deep neural network model or a deep belief network model.

[0107] Step 3: Determine whether the extraction equipment is in an abnormal extraction state at the moment of T1 + a according to the first quality index. If an abnormal extraction state occurs, generate an extraction adjustment instruction and jump to Step 4; if no abnormal extraction state occurs, generate a second extraction instruction and jump to Step 5.

[0108] In implementation, the method for determining whether the extraction equipment is in an abnormal extraction state at the moment of T1 + a includes:

[0109] Mark the first quality index of the moment of T1 + a predicted by the iron phosphate quality analysis model as Zls. And preset a first index threshold, where the preset first index threshold includes S1 and S2, and S1 > S2.

[0110] Compare the first quality index with the preset first index threshold.

[0111] If Zls > S1 or Zls < S2, it is determined that the extraction equipment is in an abnormal extraction state at the moment of T1 + a.

[0112] If S1 ≥ Zls ≥ S2, it is determined that the extraction equipment is in a normal extraction state at the moment of T1 + a, continue to complete the extraction with the first parameter characteristic data corresponding to the first extraction control index, and enter the second extraction stage.

[0113] It should be noted that: the preset first index threshold is obtained by personnel in the technical field multiple times in the first extraction stage to obtain iron phosphate characteristic data. Each time, Q groups of iron phosphate characteristic data are obtained, the mean value of the Q groups of iron phosphate characteristic data is calculated, the first quality index corresponding to the mean value of the iron phosphate characteristic data is predicted through the iron phosphate quality analysis model, the multiple first quality indexes are sorted, the maximum value among the multiple first quality indexes is taken as the maximum value of the first index threshold, and the minimum value among the multiple first quality indexes is taken as the minimum value of the first index threshold; the range between the minimum value of the first index threshold and the maximum value of the first index threshold is the preset first index threshold.

[0114] Step 4: Adjust the extraction equipment based on the first quality index according to the extraction adjustment instruction to optimize the extraction process and obtain high-purity iron phosphate.

[0115] In a specific embodiment, the method for adjusting the extraction equipment based on the first quality index includes:

[0116] Input the first parameter characteristic data corresponding to the first quality index into a pre-constructed digital twin model for simulation to obtain the optimal adjustment strategy.

[0117] It should be noted that: the pre-constructed digital twin model is specifically a virtual simulation model of the production workshop, which is generated based on various historical measured data of the production workshop and is updated with real-time data and model based on a number of sensors. The various historical measured data include physical data, equipment operation parameters, object structure data, etc.; the pre-constructed digital twin model is realized relying on existing digital twin construction technologies, such as ANSYS, Azure DigiT1al T1wins, SiemensMindsphere, etc. Therefore, the present invention will not be elaborated too much here.

[0118] Please refer to Figure 4 As shown, specifically, the method for obtaining the optimal adjustment strategy includes:

[0119] Step c1. Obtain the first parameter characteristic data of the extraction equipment, take the first pH value and the first stirring speed in the first parameter characteristic data as fixed quantities, the first temperature value as a variable, and take the current parameter value of the first temperature value as W.

[0120] Step c2. Let W = W + D1, and record the first quality index at the parameter value W, where D1 is a natural number greater than zero.

[0121] Step c3. Repeat step c2 in a loop. When W is equal to the preset first temperature threshold, obtain G first quality indexes at the first temperature parameter value, and jump to step c4, where G is an integer greater than zero.

[0122] Step c4. Take the first temperature value and the first stirring speed as fixed quantities, the first pH value as a variable, and take the current parameter value of the first pH value as U.

[0123] Step c5. Reset W, let U = U + D2, and record the first quality index at the parameter value U, where D2 is a natural number greater than zero.

[0124] Step c6. Repeat step c5 in a loop. When U is equal to the preset first pH threshold, obtain H first quality indexes at the first pH parameter value, where H is an integer greater than zero.

[0125] Step c7. Take the first temperature value and the first pH value as fixed quantities, the first stirring speed as a variable, and take the current parameter value of the first stirring speed as F.

[0126] Step c8. Reset U, let F = F + D3, and record the first quality index under the parameter value F, where D3 is a natural number greater than zero;

[0127] Step c9. Repeat step c8 in a loop. When F is equal to the preset first stirring speed threshold, obtain K first quality indexes under the first stirring speed parameter value, where K is an integer greater than zero.

[0128] Step c10. Mark the G first quality indexes under the first temperature parameter value, the H first quality indexes under the first pH parameter value, and the K first quality indexes under the first stirring speed parameter value as the first extraction control data. Accumulate and fuse the first extraction control data to obtain L first quality indexes, and sort the L first quality indexes from largest to smallest in value.

[0129] Step c11. Take the first temperature value, the first pH value, and the first stirring speed of the extraction equipment corresponding to the first quality index with the largest value in the sorting as the optimal adjustment strategy.

[0130] It should be noted that: the value range of the first temperature value is [40°C, 60°C], the value range of the first pH value is [3, 5], and the value range of the first stirring speed is [100 rpm, 300 rpm]. The current parameter values of the above steps are simulated starting from the minimum value of the corresponding parameter values until the optimal adjustment strategy is obtained.

[0131] Step 5: Receive the second extraction instruction, obtain the second quality index at the T2 + b moment of the extraction equipment in the second extraction stage, and determine whether the extraction equipment is in an abnormal extraction state at the T2 + b moment based on the second quality index; if so, generate a second extraction adjustment instruction and jump to step 6, if not, continue the extraction until the extraction of lithium carbonate is completed.

[0132] It should be noted that: in the second extraction stage, a second extractant with a preset concentration is added to the leaching solution from which iron phosphate has been extracted, and it is marked as the extraction mixture. Among them, the second extractant is a sodium carbonate solution (Na2CO3) as a selective extractant for lithium. The purpose of setting the second extraction stage is to optimize the precipitation efficiency of lithium carbonate under different chemical conditions, avoid the generation of impurities, improve the product purity, and at the same time ensure the stability and high recovery rate of this extraction stage. The conditions (such as pH value, temperature, and stirring speed) of the second extraction stage will be precisely controlled for the extraction mixture, so as to ensure the best extraction purity of lithium carbonate.

[0133] In practice, the method for obtaining the second quality index at the T2 + b moment of the extraction equipment includes:

[0134] Obtain the second extraction control index at the T2 + b moment of the extraction equipment and the second characteristic data of the extraction mixture in the extraction equipment, and mark them as lithium carbonate characteristic data; the second characteristic data includes lithium ion concentration, viscosity of the extraction mixture, and impurity percentage.

[0135] Input the lithium carbonate characteristic data into a pre - constructed lithium carbonate quality analysis model to obtain the second quality index at the T2 + b moment.

[0136] It should be noted that: the method for obtaining the second characteristic data is the same as that for obtaining the first characteristic data, and will not be repeated here. It is worth noting that: the impurity ion concentration of the mixture includes the concentrations of copper, zinc, and iron ions.

[0137] Among them, the method for generating the lithium carbonate quality analysis model includes:

[0138] Convert each group of lithium carbonate characteristic data into the form of a second characteristic vector. All elements of the second characteristic vectors are used as the input of the lithium carbonate quality analysis model. The lithium carbonate quality analysis model takes the second quality index predicted by each group of lithium carbonate characteristic data as the output, takes the actual second quality index corresponding to each group of lithium carbonate characteristic data as the prediction target, and takes minimizing the sum of the second prediction accuracies of all predicted second quality indices as the training target.

[0139] It should be noted that: the second quality index specifically refers to the purity of the lithium carbonate recovered by extraction in the second extraction stage, which is measured and obtained by methods such as ICP - OES (Inductively Coupled Plasma Optical Emission Spectrometry), XRF (X - Ray Fluorescence Spectrometry), etc.

[0140] Among them, the calculation formula for the second prediction accuracy is: Z2=(b m - s m ) 2 , where m is the number of each group of lithium carbonate characteristic data, Z2 is the second prediction accuracy, b m is the predicted second quality index corresponding to the m - th group of lithium carbonate characteristic data, and s m is the actual second quality index corresponding to the m - th group of lithium carbonate characteristic data; train the lithium carbonate quality analysis model until the sum of the second prediction accuracies reaches convergence and then stop training; the lithium carbonate quality analysis model is any one of a deep neural network model or a deep belief network model.

[0141] Among them, the method for obtaining the second extraction control index at the T2 + b moment of the extraction equipment includes:

[0142] Step d1. Collect the second parameter characteristic data at time T2. The second parameter characteristic data includes the second temperature value, the second pH value, and the second stirring speed. Mark the second temperature value, the second pH value, and the second stirring speed as Ws2, Ph2, and Sd2 respectively.

[0143] It should be noted that: the second temperature value is collected through the temperature sensor connected in the temperature control system; the second pH value is collected through the pH meter connected in the pH automatic control system.

[0144] Step d2. Based on the first extraction control index, perform formula calculation on the second parameter characteristic data to obtain the second extraction control index at time T2. The calculation formula is:

[0145] θ2 = θ1 - (Ws2 × β1 + Ph2 × β2 + Sd2 × β3) + (μ2 × Ws2 × Ph2).

[0146] In the formula, θ2 represents the second extraction control index, β1 represents the weight factor of the second temperature value, β2 represents the weight factor of the second pH value, β3 represents the weight factor of the second stirring speed, and μ2 represents the weighted coefficient of the interaction between the second temperature value and the second pH value.

[0147] It should be noted that: the larger the value of μ2, the more significant the influence of the interaction between temperature and pH value on the extraction efficiency. The calculation of the second extraction control index is a dimensionless calculation.

[0148] It should be further noted that: the weight factor can be set according to the actual situation. The weight factor reflects the influence degree of each second parameter characteristic data on the actual extraction purity of the extraction equipment. Those skilled in the art can preset the corresponding weight factor according to the influence degree of each second parameter characteristic data on the actual extraction purity of the extraction equipment, so as to accurately evaluate the purity of the actually extracted lithium carbonate by the extraction equipment.

[0149] Step d3. Input the second extraction control index at time T2 into the pre-constructed parameter analysis model to predict the second extraction control index at time T2 + b.

[0150] In implementation, the method for determining whether the extraction equipment is in an abnormal extraction state at time T2 + b includes:

[0151] Mark the second quality index at time T2 + b predicted by the quality analysis model of lithium carbonate as Zlz. And preset the second index threshold. The preset second index threshold includes Y1 and Y2, and Y1 > Y2.

[0152] Compare the second quality index with the preset second index threshold.

[0153] If Zlz > Y1 or Zls < Y2, it is determined that the extraction equipment is in an abnormal extraction state at time T2 + b.

[0154] If Y1 ≥ Zlz ≥ Y2, it is determined that the extraction equipment is in a normal extraction state at time T2 + b, and continue to complete the extraction with the second parameter characteristic data corresponding to the second extraction control index to obtain high-purity lithium carbonate.

[0155] Step 6: Receive the second extraction adjustment instruction, adjust the extraction equipment based on the second quality index, and obtain high-purity lithium carbonate.

[0156] It should be noted that: the method of adjusting the extraction equipment based on the second quality index is the same as that of adjusting the extraction equipment based on the first quality index in Step 4, and will not be elaborated here. It is worth noting that in the second extraction stage, the value range of the second temperature value in the second parameter characteristic data is [50°C, 70°C], the value range of the second pH value is [8, 10], and the value range of the second stirring speed is [50 rpm, 150 rpm]. The same as in Step 4, the current parameter value starts from the minimum value for simulation until the optimal adjustment strategy is obtained.

[0157] In this embodiment, by obtaining the first extraction control index and the first characteristic data of the extraction equipment at time T1 + a and inputting them into the iron phosphate quality analysis model, the separation effect of iron phosphate in the first extraction stage can be predicted in real time. By obtaining the second extraction control index and the second characteristic data of the extraction equipment at time T2 + b and inputting them into the lithium carbonate quality analysis model, the separation effect of lithium carbonate in the second extraction stage can be predicted in real time. Based on different extraction stages and precise extraction control methods, the errors in the operation process can be effectively reduced, ensuring the best temperature, pH value, and stirring speed during the extraction process, thereby improving the purity and recovery rate of the product.

[0158] In this embodiment, the extraction state is predicted in real time through the quality analysis model, and a warning for the abnormal extraction state is generated. When the extraction equipment is in an abnormal extraction state, the system will automatically generate an adjustment instruction and adjust according to the optimal adjustment strategy to ensure that the extraction process is promptly restored to the normal state, reducing the uncontrollable risks in the operation.

[0159] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0160] Finally, the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. Method for extracting and recycling high-purity lithium carbonate and iron phosphate from waste lithium battery materials, characterized in that, Including: Step 1: In the first extraction stage, obtain the first extraction control index at the moment of T1 + a of the extraction equipment, and obtain the first characteristic data of the leaching solution in the extraction equipment; Mark the first extraction control index and the first characteristic data as ferric phosphate characteristic data; Both T1 and a are integers greater than zero, and the first characteristic data includes ferric ion concentration, viscosity of the leaching solution, and impurity percentage of the leaching solution; Step 2: Input the ferric phosphate characteristic data into a pre-constructed ferric phosphate quality analysis model to obtain the first quality index at the moment of T1 + a; Step 3: Determine whether the extraction equipment is in an abnormal extraction state at the moment of T1 + a according to the first quality index. If an abnormal extraction state occurs, generate an extraction adjustment instruction and jump to Step 4; If no abnormal extraction state occurs, generate a second extraction instruction and jump to Step 5; Step 4: According to the extraction adjustment instruction, adjust the extraction equipment based on the first quality index to optimize the extraction process and obtain high-purity ferric phosphate; Step 5: Receive the second extraction instruction, obtain the second quality index at the moment of T2 + b of the extraction equipment in the second extraction stage, and determine whether the extraction equipment is in an abnormal extraction state at the moment of T2 + b based on the second quality index; if so, generate a second extraction adjustment instruction and jump to Step 6, if not, continue the extraction until the extraction of lithium carbonate is completed; Step 6: Receive the second extraction adjustment instruction, adjust the extraction equipment based on the second quality index to obtain high-purity lithium carbonate; The method for obtaining the first extraction control index at the moment of T1 + a of the extraction equipment includes: Step a1. Collect the first parameter characteristic data at the moment of T1. The first parameter characteristic data includes the first temperature value, the first pH value, and the first stirring speed; mark the first temperature value, the first pH value, and the first stirring speed as Ws1, Ph1, and Sd1 respectively; Step a2. Perform formulaic calculation on the first parameter characteristic data to obtain the first extraction control index at the moment of T1. The calculation formula is: θ1 = (Ws1 × α1 + Ph1 × α2 + Sd1 × α3) + (μ1 × Ws1 × Ph1); In the formula, θ1 represents the first extraction control index at the moment of T1, α1 represents the weight factor of the first temperature value, α2 represents the weight factor of the first pH value, α3 represents the weight factor of the first stirring speed, and μ1 represents the weighting coefficient of the interaction between the first temperature value and the first pH value; Step a3. Input the first extraction control index at the moment of T1 into a pre-constructed parameter analysis model to predict the first extraction control index at the moment of T1 + a; The method for obtaining the second quality index at the moment of T2 + b of the extraction equipment includes: Obtain the second extraction control index at the moment of T2 + b of the extraction equipment and the second characteristic data of the extraction mixture in the extraction equipment, and mark them as lithium carbonate characteristic data; the second characteristic data includes lithium ion concentration, viscosity of the extraction mixture, and impurity percentage; Input the lithium carbonate characteristic data into a pre-constructed lithium carbonate quality analysis model to obtain the second quality index at the moment of T2 + b; The method for obtaining the second extraction control index at the T2 + b moment of the extraction equipment includes: Step d1. Collect the second parameter characteristic data at the T2 moment. The second parameter characteristic data includes the second temperature value, the second pH value, and the second stirring speed. Mark the second temperature value, the second pH value, and the second stirring speed as Ws2, Ph2, and Sd2 respectively; Step d2. Based on the first extraction control index, perform formula calculation on the second parameter characteristic data to obtain the second extraction control index at the T2 moment. The calculation formula is: θ2 = θ1 - (Ws2 × β1 + Ph2 × β2 + Sd2 × β3) + (μ2 × Ws2 × Ph2); In the formula, θ2 represents the second extraction control index, β1 represents the weight factor of the second temperature value, β2 represents the weight factor of the second pH value, β3 represents the weight factor of the second stirring speed, and μ2 represents the weighted coefficient of the interaction between the second temperature value and the second pH value; Step d3. Input the second extraction control index at the T2 moment into the pre - constructed parameter analysis model to predict the second extraction control index at the T2 + b moment.

2. The method for extracting and recycling high-purity lithium carbonate and iron phosphate from waste lithium battery materials according to claim 1, characterized in that, The generation method of the pre - constructed parameter analysis model includes: Obtain the historical first extraction control index, and establish an extraction time - series set based on the historical first extraction control index. The extraction time - series set includes u historical first extraction control indexes. The time intervals for obtaining the u historical first extraction control indexes are equal, and the u historical first extraction control indexes correspond to a preset time. The unit of the preset time is seconds or minutes; Preset the sliding step size and the sliding window length. Use the sliding window method to convert the historical first extraction control indexes in the extraction time - series set into multiple training samples. Take the training samples as the input of the recurrent neural network model, predict the first extraction control index after the sliding step size as the output, take the first extraction control index of each training sample as the prediction target, and take the prediction accuracy as the training target to train the recurrent neural network model. Generate a parameter analysis model for predicting the first extraction control index at a future time based on the historical first extraction control indexes in the extraction time - series set. Among them, the recurrent neural network model is an RNN neural network model.

3. The method for extracting and recycling high-purity lithium carbonate and iron phosphate from waste lithium battery materials according to claim 2, wherein The concentration of iron ions is directly analyzed by a concentration analysis device; the viscosity of the leaching solution is measured by a rotational viscometer or a capillary viscometer; The method for obtaining the impurity percentage of the leaching solution includes: Step b1. Collect a leaching solution sample and analyze the impurity ion concentration through a concentration analysis device. The impurity ion concentration includes the concentrations of copper, zinc, and lithium ions; Step b2. Calculate the mass of the impurity ions: m i = C i × V, where m i represents the mass of the i-th impurity ion, C i represents the concentration of the i-th impurity ion; V represents the volume of the leachate sample; Step b3. Accumulate the masses of all impurity ions to obtain the total mass of impurities: m 总 = ∑m i ; Step b4. Obtain the total mass M of the leachate sample 浸出液 , according to the total mass m of the impurities 总 and the total mass M of the leachate sample 浸出液 , calculate the impurity percentage Zbf:

4. The method for extracting and recycling high-purity lithium carbonate and iron phosphate from waste lithium battery materials according to claim 3, wherein, The generation method of the pre - constructed ferric phosphate quality analysis model includes: Convert each set of iron phosphate characteristic data into the form of a first feature vector. The elements of all the first feature vectors are used as the input of the iron phosphate quality analysis model. The iron phosphate quality analysis model takes the first quality index predicted by each set of iron phosphate characteristic data as the output, uses the actual first quality index corresponding to each set of iron phosphate characteristic data as the prediction target, and takes minimizing the sum of the first prediction accuracies of all the predicted first quality indexes as the training target. Among them, the calculation formula for the first prediction accuracy is: Z1 = (a n - y n ) 2 , where n is the number of each set of iron phosphate characteristic data, Z1 is the first prediction accuracy, a n is the predicted first quality index corresponding to the nth set of iron phosphate characteristic data, and y n is the actual first quality index corresponding to the nth set of iron phosphate characteristic data. Train the iron phosphate quality analysis model until the sum of the first prediction accuracies reaches convergence and then stop training. The iron phosphate quality analysis model is a deep neural network model or a deep belief network model.

5. The method for extracting and recycling high-purity lithium carbonate and iron phosphate from waste lithium battery materials according to claim 4, characterized in that, The method for determining whether the extraction equipment is in an abnormal extraction state at the T1 + a moment includes: Mark the first quality index at the T1 + a moment predicted by the ferric phosphate quality analysis model as Zls; and preset the first index threshold. The preset first index threshold includes S1 and S2, where S1 > S2; Compare the first quality index with the preset first index threshold; If Zls > S1 or Zls < S2, it is determined that the extraction equipment is in an abnormal extraction state at time T1 + a; If S1 ≥ Zls ≥ S2, it is determined that the extraction equipment is in a normal extraction state at time T1 + a, and continue to complete the extraction with the first parameter characteristic data corresponding to the first extraction control index, and enter the second extraction stage.

6. The method for extracting and recycling high-purity lithium carbonate and iron phosphate from waste lithium battery materials according to claim 1, wherein, The method for adjusting the extraction equipment based on the first quality index includes: Input the first parameter characteristic data corresponding to the first quality index into a pre-constructed digital twin model for simulation to obtain the optimal adjustment strategy; The method for obtaining the optimal adjustment strategy includes: Step c1. Obtain the first parameter characteristic data of the extraction equipment, take the first pH value and the first stirring speed in the first parameter characteristic data as fixed quantities, the first temperature value as a variable, and take the current parameter value of the first temperature value as W; Step c2. Let W = W + D1, and record the first quality index at the parameter value W, where D1 is a natural number greater than zero; Step c3. Repeat step c2 in a loop. When W is equal to the preset first temperature threshold, obtain G first quality indexes at the first temperature parameter value, and jump to step c4, where G is an integer greater than zero; Step c4. Take the first temperature value and the first stirring speed as fixed quantities, the first pH value as a variable, and take the current parameter value of the first pH value as U; Step c5. Reset W, let U = U + D2, and record the first quality index at the parameter value U, where D2 is a natural number greater than zero; Step c6. Repeat step c5 in a loop. When U is equal to the preset first pH threshold, obtain H first quality indexes at the first pH parameter value, where H is an integer greater than zero; Step c7. Take the first temperature value and the first pH value as fixed quantities, the first stirring speed as a variable, and take the current parameter value of the first stirring speed as F; Step c8. Reset U, let F = F + D3, and record the first quality index at the parameter value F, where D3 is a natural number greater than zero; Step c9. Repeat step c8 in a loop. When F is equal to the preset first stirring speed threshold, obtain K first quality indexes at the first stirring speed parameter value, where K is an integer greater than zero; Step c10. Mark the G first quality indexes at the first temperature parameter value, the H first quality indexes at the first pH parameter value, and the K first quality indexes at the first stirring speed parameter value as the first extraction control data, perform cumulative fusion on the first extraction control data to obtain L first quality indexes, and sort the L first quality indexes from largest to smallest; Step c11. Take the first temperature value, the first pH value, and the first stirring speed of the extraction equipment corresponding to the first quality index with the largest value in the sorting as the optimal adjustment strategy.

7. The method for extracting and recycling high-purity lithium carbonate and iron phosphate from waste lithium battery materials according to claim 6, characterized in that, In the first extraction stage, the value range of the first temperature value in the first parameter characteristic data is [40°C, 60°C], the value range of the first pH value is [3, 5], and the value range of the first stirring speed is [100 rpm, 300 rpm]; in the second extraction stage, the value range of the second temperature value in the second parameter characteristic data is [50°C, 70°C], the value range of the second pH value is [8, 10], and the value range of the second stirring speed is [50 rpm, 150 rpm].

8. The method for extracting and recycling high-purity lithium carbonate and iron phosphate from waste lithium battery materials according to claim 7, characterized in that, The method for generating the lithium carbonate quality analysis model includes: Convert each set of lithium carbonate characteristic data into the form of a second feature vector, and use the elements of all the second feature vectors as the input of the lithium carbonate quality analysis model. The lithium carbonate quality analysis model takes the second quality index predicted by each set of lithium carbonate characteristic data as the output, uses the actual second quality index corresponding to each set of lithium carbonate characteristic data as the prediction target, and takes minimizing the sum of the second prediction accuracies of all the predicted second quality indexes as the training target; wherein, the calculation formula of the second prediction accuracy is: Z2 = (b m -s m ) 2 , where m is the number of each set of lithium carbonate characteristic data, Z2 is the second prediction accuracy, b m is the predicted second quality index corresponding to the m-th set of lithium carbonate characteristic data, and s m is the actual second quality index corresponding to the m-th set of lithium carbonate characteristic data; train the lithium carbonate quality analysis model until the sum of the second prediction accuracies reaches convergence and then stop training; the lithium carbonate quality analysis model is a deep neural network model or a deep belief network model.

9. The method for extracting and recycling high-purity lithium carbonate and iron phosphate from waste lithium battery materials according to claim 1, wherein The method for determining whether the extraction equipment is in an abnormal extraction state at time T2 + b includes: Mark the second quality index at time T2 + b predicted by the lithium carbonate quality analysis model as Zlz; and preset a second index threshold, the preset second index threshold includes Y1 and Y2, Y1 > Y2; Compare the second quality index with the preset second index threshold; If Zlz > Y1 or Zls < Y2, it is determined that the extraction equipment is in an abnormal extraction state at time T2 + b; If Y1 ≥ Zlz ≥ Y2, it is determined that the extraction equipment is in a normal extraction state at time T2 + b, and continue to complete the extraction with the second parameter characteristic data corresponding to the second extraction control index to obtain high-purity lithium carbonate.

Images