Method and device for predicting risk of lithium ion battery negative electrode slurry particle agglomeration and electronic equipment

Abstract

The present application relates to the technical field of battery, in particular to a kind of lithium ion battery negative electrode slurry particle agglomeration risk pre-judgment method, pre-judgment device and electronic equipment. By calculating effective carboxyl coverage p eff = n eff / S 总 And normalized steric hindrance index S norm = S norm / S 总 And two are used as independent quantitative index to evaluate slurry agglomeration risk for pre-judgment;The present application first introduces electrostatic repulsion (effective carboxyl coverage) and steric hindrance (steric hindrance index) into the same model, solves the problem that CMC and PAA cannot be quantified uniformly due to different stabilization mechanisms. Slurry stability is visualized by two-dimensional partitioning, and operating personnel can directly determine the risk level according to the calculation results, reducing the dependence on experience.

Description

Technical Field

[0001] This invention relates to the field of battery technology, and in particular to a method, device, and electronic device for predicting the risk of particle agglomeration in lithium-ion battery negative electrode slurry. Background Technology

[0002] The dispersion stability of lithium-ion battery negative electrode slurry directly affects coating quality, electrode consistency, and battery performance. Particle agglomeration in the slurry can lead to process problems such as filter clogging, coating scratches, and electrode powder shedding, and in severe cases, it can cause the entire batch to be scrapped.

[0003] In existing technologies, methods for predicting the risk of slurry agglomeration mainly include: Electrostatic stability can be assessed by Zeta potential, but this method cannot reflect the contribution of steric hindrance, especially for CMC systems, which tend to underestimate their stability. Indirect judgment can be made through viscosity or rheological curves, but there is a lack of quantitative correlation, making it difficult to establish a universal threshold. The method relies on empirical ratios of CMC substitution degree or dosage, but does not consider the differences in surface properties of different graphites (artificial / natural) or the quantification of the synergistic effect of PAA and CMC.

[0004] Therefore, there is an urgent need for a method that can uniformly quantify the dual contributions of electrostatic repulsion and steric hindrance, and is applicable to various binder systems and graphite types for predicting agglomeration risk. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings and defects of the prior art and to provide a method, device and electronic device for predicting the risk of agglomeration of lithium-ion battery negative electrode slurry particles.

[0006] To achieve the above objectives, this application adopts the following solution: A method for predicting the risk of particle agglomeration in lithium-ion battery negative electrode slurry, by calculating the effective carboxyl group coverage. r eff = n eff / S 总 and normalized spatial steric retardation index S norm = S norm / S 总 Both are used as independent quantitative indicators for assessing the risk of slurry agglomeration for prediction; among them, n eff The amount of effective carboxyl group material contributing to all polymers in the slurry; S norm It is the spatial steric retardation index; S总 This represents the total surface area of ​​all solid particles.

[0007] n eff =∑( m k × D k × oh k )in, m k The mass of the component containing carboxyl binder D k The carboxyl density is the density of the carboxyl-containing binder component. oh k The effective weighting coefficient for the carboxyl-containing binder component; preferably, S norm =∑( m j × H j ), m j For the mass of the hydroxyl-containing binder component, H j Hydroxyl density of hydroxyl-containing binder components.

[0008] The binder components of the lithium-ion battery negative electrode slurry are CMC and / or PAA; Preferred, r eff =( m CMC × D CMC × oh CMC + m PAA × D PAA × oh PAA ) / S 总 ,in, m CMC For CMC quality, D CMC The carboxyl group density of CMC oh CMC The effective weighting coefficients for CMC; m PAA For the quality of PAA, D PAA The carboxyl group density of PAA, oh PAA The effective weighting coefficients for PAA; preferably, oh CMC =1.0, oh PAA The initial value ranges from 0.3 to 0.6, and is determined through calibration using historical data. Preferred, S norm = m CMC × H CMC , H CMC =(3- DS ) / (162+81×DS)×1000, H CMC denoted as hydroxyl density of CMC, and DS as the degree of substitution of CMC.

[0009] D CMC , D PAA It can be obtained through titration or calculation. D CMC =DS / (162+81×DS)×1000; D PAA =1000 / 72≈13.89, where DS is the degree of substitution of CMC.

[0010] S 总 =∑( m i × BET i );in, m i The mass of the solid particles. BET i The specific surface area is the solid particle area; preferably, the solid particles include graphite and a conductive agent.

[0011] The method for predicting the risk of particle agglomeration in lithium-ion battery negative electrode slurry includes the following steps: 1) obtaining parameter values ​​of the slurry to be predicted; 2) calculating the total surface area of ​​all solid particles based on the parameter values ​​in step 1). S 总 The amount of effective carboxyl groups contributed by all polymers in the slurry n eff Spatial steric retardation index S norm And calculate the effective carboxyl group coverage based on the results. r eff Normalized spatial steric retardation index S norm ;3) with r eff x-axis S normA two-dimensional risk zoning model is constructed using the vertical axis; the formulation to be tested is ( r eff , S norm Substitute the values ​​into the two-dimensional risk zoning model to output the risk prediction results.

[0012] Step 3) involves the following steps: constructing... r eff As the first coordinate, with S norm A two-dimensional partitioning model for the second coordinate system is used, and the coordinate system is divided into a danger zone, a transition zone, and a safe zone; the formula to be tested is... r eff , S norm The landing point is compared with the partition, and the corresponding risk level is output; preferably, the boundary threshold of the partition is obtained by calibrating historical data of at least 10 sets of known stability results with the minimum misclassification rate as the target.

[0013] If the risk level falls within the danger zone, output "high risk" and provide adjustment suggestions: increase CMC or PAA usage, or increase the PAA ratio; If the result falls within the transition zone, the output is "medium risk". It is recommended to optimize the process parameters, such as adjusting the stirring time, pH or formula ratio, and conduct small-scale tests to verify the results. If the risk falls within the safe zone, the output is "low risk," and the process proceeds to slurry preparation.

[0014] The present invention also includes a prediction device for the prediction method described above, comprising: The information acquisition module is used to predict the parameter values ​​of the slurry. The processing module processes the parameter values ​​of the slurry to be predicted to obtain the effective carboxyl group coverage. r eff Normalized spatial steric retardation index S norm ; and with r eff x-axis S norm Construct a two-dimensional risk zoning model using the vertical axis; The judgment module, based on the formula to be tested ( r eff , S norm Substitute the data into a two-dimensional risk zoning model to determine the risk level.

[0015] The present invention also includes an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the prediction method described above.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention is the first to incorporate electrostatic repulsion (effective carboxyl group coverage) and steric hindrance (steric hindrance index) into the same model, solving the problem of the inability to uniformly quantify CMC and PAA due to their different stabilization mechanisms. By visualizing slurry stability through two-dimensional partitioning, operators can directly judge the risk level based on the calculation results, reducing reliance on experience. This solution is applicable to CMC+SBR, CMC+SBR+PAA, and SBR+PAA systems, as well as artificial and natural graphite systems. Threshold parameters can be calibrated using the company's own historical data to achieve personalized adaptation. The model accuracy can be continuously optimized with data accumulation. This method can predict agglomeration risk during the formulation design stage, reducing experimental batches, shortening the development cycle, and reducing raw material waste. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the overall process of the method for predicting the risk of agglomeration of lithium-ion battery negative electrode slurry particles according to the present invention. Figure 2 This is an embodiment of the two-dimensional risk zoning model of the present invention; Figure 3 These are the 3ITT test curves of Embodiments 2 and 5 of the present invention; Figure 4 The thixotropic recovery rates of Embodiments 2 and 5 of the present invention; Figure 5 These are the 3ITT test curves of Embodiments 9 and 10 of the present invention; Figure 6 This refers to the thixotropic recovery rate of Embodiments 9 and 10 of the present invention. Detailed Implementation

[0018] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0019] Figure 1 A method for predicting the risk of particle agglomeration in lithium-ion battery negative electrode slurry is shown, including the following steps: 1) obtaining the parameter values ​​of the slurry to be predicted; Quality of graphite and conductive agents m i (Unit: g or wt%) and specific surface area BET i (Unit: m) 2 / g); CMC quality m CMC (Unit: g or wt%) Degree of substitution DS Carboxyl group density D CMC (Unit: mmol / g), hydroxyl density H CMC (Unit: mmol / g); PAA quality m PAA (Unit: g or wt%), Carboxyl group density D PAA (Unit: mmol / g); Preset CMC effective weighting coefficient oh CMC and PAA effective weighting coefficient oh PAA ,in oh CMC =1.0, oh PAA The initial value ranges from 0.3 to 0.6, and is determined through calibration using historical data. Optionally, obtain SBR quality m SBR And the pH value of the slurry, used for subsequent correction.

[0020] 2) Calculate the total surface area of ​​all solid particles. S 总 (Unit: m) 2 ); S 总 =∑( m k × BET i (1); The amount of effective carboxyl groups contributed by all polymers in the slurry n eff (Unit: mmol); n eff = m CMC × D CMC × oh CMC + m PAA × D PAA × oh PAA (2) in: D CMC =DS / (162+81×DS)×1000; D PAA =1000 / 72≈13.89, or determined by titration.

[0021] Spatial resistance index S norm (Unit: mmol) S index = m CMC × H CMC (3) in: H CMC =(3- DS ) / (162+81×DS)×1000 The effective carboxyl group coverage was calculated based on the results. r eff (Unit: mmol / m²) 2 ); r eff = n eff / S 总 (4) Normalized spatial steric retardation index S norm (Unit: mmol / m²) 2 ); S norm = S index / S 总 (5) 3) with r eff x-axis S norm A two-dimensional risk zoning model is constructed for the vertical axis; the coordinate system is divided into three regions: a danger zone, a safe zone, and a transition zone (between the danger zone and the safe zone). The boundaries of the three regions are defined using historical data.

[0022] Calibration method: Take at least 10 sets of historical slurry data with known stability results (smooth / blocked) and calculate their respective... r eff and S norm To minimize the misclassification rate, the optimal partition boundaries are determined using grid search or optimization algorithms. Separate threshold parameter libraries are established for both artificial and natural graphite.

[0023] The following explanation uses specific historical slurry data.

[0024] Example 1: Obtain the slurry formulation and raw material properties. The material ratio of the slurry formulation is: Graphite 1: Conductive Agent 1: CMC 1: SBR 1 = 97.0%: 0.5%: 1.2%: 1.3%; the total surface area of ​​Graphite 1 and Conductive Agent 1 is... S 总 It is 1.729m 2 / g, CMC1 degree of substitution 0.95, CMC1 carboxyl effective density 0.028mmol / m 2 Spatial resistance index S norm It is 0.060 mmol / m 2 This slurry is a mass-production formula and has never experienced slurry agglomeration issues.

[0025] Example 2: Obtain the slurry formulation and raw material properties. The material ratio of the slurry formulation is: Graphite 2: Conductive Agent 2: CMC1: SBR1 = 96.2%: 1.0%: 1.2%: 1.6%; the total surface area of ​​Graphite 2 and Conductive Agent 2 is... S 总 It is 2.231m 2 / g, CMC1 degree of substitution 0.95, CMC1 carboxyl effective density 0.021mmol / m 2 Spatial resistance index S norm It is 0.046 mmol / m 2 The coated slurry filter element is severely clogged.

[0026] Example 3: Obtain the slurry formulation and raw material properties. The material ratio of the slurry formulation is: graphite 3: conductive agent 1: CMC1: SBR1 = 96.2%: 1.0%: 1.2%: 1.6%; the total surface area of ​​graphite 3 and conductive agent 1 is... S 总 It is 1.995m 2 / g, CMC1 degree of substitution 0.95, CMC1 carboxyl effective density 0.024mmol / m 2 Spatial resistance index S norm It is 0.052 mmol / m 2 The filter element is clogged due to the coating slurry.

[0027] Example 4: Obtaining the slurry formulation and raw material properties. The material ratio of the slurry formulation is: graphite 3: conductive agent 2: CMC1: SBR1 = 96.2%: 1.0%: 1.2%: 1.6%; the total surface area of ​​graphite 3 and conductive agent 2... S 总 It is 1.965m 2 / g, CMC1 degree of substitution 0.95, CMC1 carboxyl effective density 0.024mmol / m2 Spatial resistance index S norm It is 0.052 mmol / m 2 The filter element is clogged due to the coating slurry.

[0028] Example 5: Obtaining the slurry formulation and raw material properties. The material ratio of the slurry formulation is: Graphite 2: Conductive Agent 2: CMC1: SBR1 = 96.2%: 0.8%: 1.4%: 1.6%; the total surface area of ​​Graphite 2 and Conductive Agent 2... S 总 It is 2.108m 2 / g, CMC1 degree of substitution 0.95, CMC1 carboxyl effective density 0.026mmol / m 2 Spatial resistance index S norm It was 0.057 mmol / m 2 The coated slurry filter element does not clog, but the pipeline shakes at the tail end of the high mixing chamber, and the filter element pressure is relatively high.

[0029] Example 6: Obtain the slurry formulation and raw material properties. The material ratio of the slurry formulation is: graphite 4: conductive agent 2: CMC1: SBR1 = 96.2%: 1.0%: 1.2%: 1.6%; the total surface area of ​​graphite 4 and conductive agent 2 is... S 总 It is 2.222m 2 / g, CMC1 degree of substitution 0.95, CMC1 carboxyl effective density 0.021mmol / m 2 Spatial resistance index S norm It is 0.046 mmol / m 2 The coated slurry filter element is severely clogged.

[0030] Example 7: Obtain the slurry formulation and raw material properties. The material ratio of the slurry formulation is: graphite 5: conductive agent 1: CMC2: SBR2: PAA1 = 96.1%: 1.2%: 0.7%: 1.4%: 0.6%; preset PAA effective weighting coefficient. oh PAA =0.6, the total surface area of ​​graphite 5 and conductive agent 1 S 总 It is 2.075m 2 / g, the degree of substitution of CMC1 is 0.95, and the effective density of carboxyl groups of CMC2 and PAA1 is 0.037 mmol / m³. 2 Spatial resistance index S norm It was 0.029 mmol / m 2 The filter element with the coating slurry was not clogged, but the pressure was too high, resulting in coating scratches.

[0031] Example 8: Obtain the slurry formulation and raw material properties: Graphite 6: Conductive Agent 1: CMC2: SBR2: PAA1 = 96.1%: 1.2%: 0.7%: 1.4%: 0.6%; preset PAA effective weighting coefficient. oh PAA =0.6, the total surface area of ​​graphite 6 and conductive agent 1 S 总 It is 1.751m 2 / g, the degree of substitution of CMC1 is 0.95, and the effective density of carboxyl groups of CMC2 and PAA1 is 0.044 mmol / m². 2 Spatial resistance index S norm It was 0.034 mmol / m 2 This solution is a mass production solution, and there has never been a problem with slurry agglomeration.

[0032] Example 9: Obtaining slurry formulation and raw material properties: Graphite 7: Conductive agent 1: CMC2: SBR1: PAA1 = 96.1%: 1.2%: 0.7%: 1.4%: 0.6%; preset PAA effective weighting coefficient. oh PAA =0.6, the total surface area of ​​graphite 7 and conductive agent 1 S 总 It is 1.957m 2 / g, the degree of substitution of CMC1 is 0.95, and the effective density of the carboxyl groups of CMC2 and PAA1 is 0.040 mmol / m³. 2 Spatial resistance index S norm It was 0.031 mmol / m 2 The coated filter element became clogged.

[0033] Example 10: Obtaining slurry formulation and raw material properties: Graphite 7: Conductive agent 1: CMC2: SBR1: PAA1 = 95.8%: 1.2%: 1%: 1.4%: 0.6%; preset effective weighting coefficient for PAA. oh PAA =0.6, the total surface area of ​​graphite 7 and conductive agent 1 S 总 It is 1.954m 2 / g, the degree of substitution of CMC1 is 0.95, and the effective density of the carboxyl groups of CMC2 and PAA1 is 0.046 mmol / m³. 2 Spatial resistance index S norm It is 0.044 mmol / m 2 The coated filter element became clogged.

[0034] Example 11: Obtain the slurry formulation and raw material properties: Graphite 8: Conductive Agent 1: CMC2: SBR1: PAA1 = 96.1%: 1.2%: 0.7%: 1.4%: 0.6%; preset PAA effective weighting coefficient. oh PAA =0.6, the total surface area of ​​graphite 8 and conductive agent 1 S 总 It is 2.192m 2 / g, the degree of substitution of CMC1 is 0.95, and the effective density of CMC2 and PAA1 carboxyl groups is 0.036 mmol / m³. 2 Spatial resistance index S norm It is 0.025 mmol / m 2 The coated filter element became clogged.

[0035] Example 12: Obtain the slurry formulation and raw material properties: Graphite 9: Conductive agent 2: SBR 2: PAA 2 = 96.0%: 1.2%: 1.4%: 1.4%; preset the effective weighting coefficient of PAA. oh PAA =0.6, the total surface area of ​​graphite 9 and conductive agent 2 S 总 It is 2.333m 2 / g, CMC1 degree of substitution 0.95, PAA2 carboxyl effective density 0.05mmol / m 2 Spatial resistance index S norm 0 mmol / m 2 The coated filter element was not clogged.

[0036] Example 13: Obtaining slurry formulation and raw material properties: Graphite 9: Conductive agent 3: SBR2: PAA2 = 96.1%: 1.2%: 1.4%: 1.3%; preset effective weighting coefficient for PAA. oh PAA =0.6, the total surface area of ​​graphite 9 and conductive agent 3 S 总 It is 3.414m 2 / g, CMC1 degree of substitution 0.95, PAA2 carboxyl effective density 0.032mmol / m 2 Spatial resistance index S norm 0 mmol / m 2 The coated filter element became clogged.

[0037] The historical slurry data of the 10 sets of known stability results (smooth / blocked) from Examples 1-4, 6-9, and 11-13 were used to obtain... Figure 2A two-dimensional risk zoning model is used to determine the optimal boundary. For the CMC dispersion system, the effective density of hydroxyl groups is... r eff Distributed in (0, 0.025], spatial steric hindrance index S norm The area within (0.045, 0.054) is considered a danger zone. r eff Distributed in (0.025, 0.027), S norm The distribution in (0.054, 0.058) is a transitional region. r eff Distributed in (0.027, 0.03], S norm The distribution within (0.058, 0.07) is considered a safe zone; for the PAA+CMC dispersion system, r eff Distributed in (0.03, 0.036], S norm The distribution within (0.02, 0.026) is considered a safe zone. r eff Distributed in (0.036, 0.04], S norm The distribution in (0.026, 0.032) is a transitional region. r eff Distributed in (0.04, 0.048), S norm The distribution within (0.032, 0.045) is considered a safe zone; for PAA dispersion systems, only... r eff One parameter, at 0.048 mmol / m -2 The value is the boundary; values ​​less than this value are considered dangerous, and values ​​greater than this value are considered safe.

[0038] The formula to be tested ( r eff , S norm Substitute the values ​​into the two-dimensional risk zoning model to output the risk prediction results.

[0039] If the risk level falls within the danger zone, output "high risk" and provide adjustment suggestions: increase CMC or PAA usage, or increase the PAA ratio; If the result falls within the transition zone, the output is "medium risk". It is recommended to optimize the process parameters, such as adjusting the stirring time, pH or formula ratio, and conduct small-scale tests to verify the results. If the risk falls within the safe zone, the output is "low risk," and the process proceeds to slurry preparation.

[0040] Example 5 uses the same system as Example 2. Based on the two-dimensional risk zoning model, Example 5 adjusts the formulation based on Example 2 and conducts a three-stage thixotropic test (3ITT) on the slurry. Figure 3 ), Figure 4 The reduced thixotropic recovery rate in Example 5 indicates improved slurry processing performance. Example 10 adjusts the formulation based on Example 9 and performs a three-stage thixotropic test (3ITT) on the slurry. Figure 5 ), Figure 6 The thixotropic recovery rate of Example 10 is slightly reduced, indicating that the coating process adaptability of the slurry of Example 10 is improved.

[0041] The present invention also includes a prediction device for the prediction method described above, comprising: The information acquisition module is used to predict the parameter values ​​of the slurry. The processing module processes the parameter values ​​of the slurry to be predicted to obtain the effective carboxyl group coverage. r eff Normalized spatial steric retardation index S norm ; and with r eff x-axis S norm Construct a two-dimensional risk zoning model using the vertical axis; The judgment module, based on the formula to be tested ( r eff , S norm Substitute the data into a two-dimensional risk zoning model to determine the risk level.

[0042] The present invention also includes an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the prediction method described above.

[0043] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. It will be apparent to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, the embodiments should be regarded as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, it is intended that all variations falling within the meaning and scope of the equivalents of the claims be included within the invention.

[0044] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. A method for predicting the risk of particle agglomeration in lithium-ion battery negative electrode slurry, characterized in that, By calculating the effective carboxyl group coverage ρ eff = n eff / S 总 and normalized spatial steric retardation index S norm = S norm / S 总 Both are used as independent quantitative indicators for assessing the risk of slurry agglomeration for prediction; among them, n eff The amount of effective carboxyl group material contributing to all polymers in the slurry; S norm It is the spatial steric retardation index; S 总 This represents the total surface area of ​​all solid particles.

2. The method for predicting the risk of particle agglomeration in lithium-ion battery negative electrode slurry according to claim 1, characterized in that, n eff =∑( m k × D k × ω k )in, m k The mass of the component containing carboxyl binder D k The carboxyl density is the density of the carboxyl-containing binder component. ω k The effective weighting coefficient for the carboxyl-containing binder component; preferably, S norm =∑( m j × H j ), m j For the mass of the hydroxyl-containing binder component, H j Hydroxyl density of hydroxyl-containing binder components.

3. The method for predicting the risk of particle agglomeration in lithium-ion battery negative electrode slurry according to claim 1, characterized in that, The binder components of the lithium-ion battery negative electrode slurry are CMC and / or PAA; Preferred, ρ eff =( m CMC × D CMC × ω CMC + m PAA × D PAA × ω PAA ) / S 总 ,in, m CMC For CMC quality, D CMC The carboxyl group density of CMC ω CMC The effective weighting coefficients for CMC; m PAA For the quality of PAA, D PAA The carboxyl group density of PAA, ω PAA The effective weighting coefficients for PAA; preferably, ω CMC =1.0, ω PAA The initial value ranges from 0.3 to 0.6, and is determined through calibration using historical data. Preferred, S norm = m CMC × H CMC , H CMC =(3- DS ) / (162+81×DS)×1000, H CMC denoted as hydroxyl density of CMC, and DS as the degree of substitution of CMC.

4. The method for predicting the risk of particle agglomeration in lithium-ion battery negative electrode slurry according to claim 3, characterized in that, D CMC , D PAA Measured by titration; Or it can be obtained through calculation. D CMC =DS / (162+81×DS)×1000; D PAA =1000 / 72≈ 13.89, where DS is the degree of substitution of CMC.

5. The method for predicting the risk of particle agglomeration in lithium-ion battery negative electrode slurry according to claim 1, characterized in that, S 总 =∑( m i × BET i )； in, m i The mass of the solid particles. BET i The specific surface area is the solid particle area; preferably, the solid particles include graphite and a conductive agent.

6. The method for predicting the risk of particle agglomeration in lithium-ion battery negative electrode slurry according to claim 1, characterized in that, The steps include: 1) Obtaining the parameter values ​​of the slurry to be predicted; 2) Calculate the total surface area of ​​all solid particles based on the parameter values ​​from step 1). S 总 The amount of effective carboxyl groups contributed by all polymers in the slurry n eff Spatial steric retardation index S norm And calculate the effective carboxyl group coverage based on the results. ρ eff Normalized spatial steric retardation index S norm ;3) with ρ eff x-axis S norm A two-dimensional risk zoning model is constructed using the vertical axis; the formulation to be tested is ( ρ eff , S norm Substitute the values ​​into the two-dimensional risk zoning model to output the risk prediction results.

7. The method for predicting the risk of particle agglomeration in lithium-ion battery negative electrode slurry according to claim 6, characterized in that, Step 3) involves the following steps: constructing... ρ eff As the first coordinate, with S norm A two-dimensional partitioning model for the second coordinate system is used, dividing the coordinate system into a danger zone, a transition zone, and a safe zone; the formula to be tested is... ρ eff , S norm The landing point is compared with the partition, and the corresponding risk level is output; preferably, the boundary threshold of the partition is obtained by calibrating historical data of at least 10 sets of known stability results with the minimum misclassification rate as the target.

8. The method for predicting the risk of particle agglomeration in lithium-ion battery negative electrode slurry according to claim 7, characterized in that, If it falls into the danger zone, output "high risk" and give adjustment suggestions: increase the amount of CMC or PAA, or increase the proportion of PAA; If the result falls within the transition zone, the output is "medium risk". It is recommended to optimize the process parameters, such as adjusting the stirring time, pH or formula ratio, and conduct small-scale tests to verify the results. If the risk falls within the safe zone, output "low risk" and proceed to slurry preparation.

9. A prediction device for the prediction method according to any one of claims 1-8, characterized in that, include: The information acquisition module is used to predict the parameter values ​​of the slurry. The processing module processes the parameter values ​​of the slurry to be predicted to obtain the effective carboxyl group coverage. ρ eff Normalized spatial steric retardation index S norm ; and with ρ eff x-axis S norm Construct a two-dimensional risk zoning model using the vertical axis; The judgment module, based on the formula to be tested ( ρ eff , S norm Substitute the data into a two-dimensional risk zoning model to determine the risk level.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the prediction method according to claims 1-8.

Images