System, method, monobloc battery and electric vehicle for optimizing a manufacturing process

Abstract

The embodiment of the application provides a kind of preparation process optimization system, method, monomer battery and electric vehicle, it is related to battery technical field.The optimization system is configured to perform the following steps: determine the historical process parameters of electrode material, historical performance data, raw material characteristics, preparation equipment state and target performance data;According to historical process parameters and historical performance data, a multi-objective optimization model is constructed;According to historical process parameters, raw material characteristics and preparation equipment state, a constraint condition set is constructed;Through multi-objective optimization model and constraint condition set, the target process parameters corresponding to target performance data are determined, and the indication instruction is generated according to the target process parameters.The above scheme, the mapping relationship between process parameters and performance data is established in the multi-objective optimization model, and the target process parameters corresponding to the target performance data are accurately determined according to the multi-objective optimization model, to avoid introducing artificial error, so as to improve the stability of electrode material.

Description

Technical Field

[0001] This application relates to the field of battery technology, and in particular to an optimized system, method, single cell, and electric vehicle for manufacturing process. Background Technology

[0002] In battery manufacturing, the preparation process of electrode materials directly affects the performance of the electrode materials, and thus the performance of the battery.

[0003] In related technologies, adjusting process parameters based on human experience introduces human error. Furthermore, there are no fixed, uniform standards for optimizing process parameters, leading to poor batch-to-batch stability of electrode materials. Summary of the Invention

[0004] This application provides an optimized system, method, single-cell battery, and electric vehicle for the fabrication process, in order to improve the stability of electrode materials.

[0005] In a first aspect, embodiments of this application provide an optimization system for electrode material preparation processes. The optimization system is used to optimize the particle size distribution of the electrode material and is configured to perform the following steps: receiving an optimization request for process parameters; determining historical process parameters, historical performance data, raw material characteristics, preparation equipment status, and target performance data for the electrode material; wherein the historical process parameters are those used in the historical preparation of the electrode material, and the process parameters include at least one of the following: crushing pressure, classifying speed, and feed rate; constructing a multi-objective optimization model based on the historical process parameters and the historical performance data, the multi-objective optimization model representing the mapping relationship between process parameters and performance data; constructing a constraint set based on the historical process parameters, the raw material characteristics, and the preparation equipment status, the constraint set controlling the optimization boundary of the process parameters; determining the target process parameters corresponding to the target performance data through the multi-objective optimization model and the constraint set, and generating an instruction based on the target process parameters, the instruction instructing the electrode material to undergo an air-crushing process according to the target process parameters.

[0006] Secondly, embodiments of this application provide a method for optimizing an electrode material preparation process, comprising: receiving an optimization request for process parameters; determining historical process parameters, historical performance data, raw material characteristics, preparation equipment status, and target performance data of the electrode material; wherein the historical process parameters are process parameters used in the historical preparation of the electrode material, and the process parameters include at least one of the following: crushing pressure, classifying speed, and feed rate; constructing a multi-objective optimization model based on the historical process parameters and the historical performance data, the multi-objective optimization model being used to represent the mapping relationship between process parameters and performance data; constructing a constraint set based on the historical process parameters, the raw material characteristics, and the preparation equipment status, the constraint set being used to control the optimization boundary of the process parameters; determining the target process parameters corresponding to the target performance data through the multi-objective optimization model and the constraint set, and generating an instruction based on the target process parameters, the instruction being used to instruct the electrode material to undergo an air crushing process according to the target process parameters.

[0007] Thirdly, embodiments of this application provide a single-cell battery, which includes at least an electrode material prepared using the target process parameters determined by the optimization method of the preparation process described in the second aspect.

[0008] Fourthly, embodiments of this application provide a battery pack comprising at least two individual cells as described in the third aspect, wherein each individual cell is electrically connected to the other.

[0009] Fifthly, embodiments of this application provide a battery pack, including a housing and at least two battery packs as described in the fourth aspect, each battery pack being disposed within the housing and electrically connected to each other.

[0010] Sixthly, embodiments of this application provide an electric vehicle that includes at least the battery pack described in the fifth aspect.

[0011] In a seventh aspect, embodiments of this application provide an electrical device that includes at least a single battery cell as described in the third aspect.

[0012] Eighthly, embodiments of this application provide an optimization apparatus for an electrode material preparation process, comprising: an acquisition module, configured to receive an optimization request for process parameters, determine historical process parameters, historical performance data, raw material characteristics, preparation equipment status, and target performance data of the electrode material, wherein the historical process parameters are process parameters used in the historical preparation of the electrode material, and the process parameters include at least one of the following: crushing pressure, classifying speed, and feeding rate; a modeling module, configured to construct a multi-objective optimization model based on the historical process parameters and the historical performance data, wherein the multi-objective optimization model is used to represent the mapping relationship between process parameters and performance data; a construction module, configured to construct a constraint set based on the historical process parameters, the raw material characteristics, and the preparation equipment status, wherein the constraint set is used to control the optimization boundary of the process parameters; and a generation module, configured to determine the target process parameters corresponding to the target performance data through the multi-objective optimization model and the constraint set, and generate an instruction based on the target process parameters, wherein the instruction is used to instruct the electrode material to undergo an air crushing process according to the target process parameters.

[0013] Ninthly, embodiments of this application provide an optimization device for electrode material preparation process, comprising: a memory and a processor;

[0014] The memory stores computer-executed instructions;

[0015] The processor executes computer execution instructions stored in the memory, causing the processor to perform the second aspect and / or various possible implementations of the second aspect as described above.

[0016] In a tenth aspect, embodiments of this application provide a non-volatile computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the second aspect and / or various possible implementations of the second aspect as described above.

[0017] Eleventhly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the second aspect and / or various possible implementations of the second aspect as described above.

[0018] The manufacturing process optimization system, method, single cell, and electric vehicle provided in this application establish a multi-objective optimization model that maps process parameters to performance data. Based on the multi-objective optimization model, the target process parameters corresponding to the target performance data are accurately determined, avoiding the introduction of human error and thus improving the stability of electrode materials. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0020] Figure 1 A schematic diagram illustrating an application scenario of an optimized method for electrode material preparation process provided in this application embodiment;

[0021] Figure 2 A schematic flowchart illustrating an optimized method for electrode material preparation process provided in this application embodiment;

[0022] Figure 3 A schematic flowchart illustrating an optimized method for preparing another electrode material according to an embodiment of this application;

[0023] Figure 4 A schematic diagram illustrating the determination of a multi-objective optimization model provided in an embodiment of this application;

[0024] Figure 5 A schematic diagram of an optimized system for electrode material preparation process provided in an embodiment of this application;

[0025] Figure 6 A schematic diagram of the structure of an optimization device for electrode material preparation process provided in an embodiment of this application;

[0026] Figure 7 A schematic diagram of the structure of an optimized apparatus for another electrode material preparation process provided in an embodiment of this application;

[0027] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0028] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0029] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0030] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0031] Furthermore, the technical solution involved in this application, which involves big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.) and the use of artificial intelligence technology for automated decision-making, and makes decisions that have a significant impact on personal rights based on the results of automated decision-making, provides users with corresponding operation entry points for users to choose to agree to or reject the results of automated decision-making; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0032] It should be noted that the optimized system, method, single cell, and electric vehicle of the preparation process described in this application can be used in the field of battery technology, or in any field other than battery technology. The application fields of the optimized system, method, single cell, and electric vehicle of the preparation process described in this application are not limited.

[0033] Figure 1 This is a schematic diagram illustrating an application scenario of an optimization method for electrode material preparation process provided in this application embodiment. The scenario illustrated is as follows: the process parameters for preparing electrode materials directly affect the performance data of the electrode materials. The process parameters are optimized based on the performance data until the performance data corresponding to the optimized process parameters meets the battery requirements.

[0034] For example, the preparation process of electrode materials includes an air jet milling process. The goal of the air jet milling process is to pulverize the sintered electrode material block into powder that meets the process requirements through high-speed air jet impact and control of the speed of the classifier wheel. Powder data directly affects the electrochemical performance of the electrode material. Powder data includes, for example, particle size distribution and particle gradation.

[0035] Current industry demands for high-performance batteries (such as fast charging capability, low-temperature adaptability, and long cycle life) place more stringent requirements on powder data. For example, taking lithium-ion batteries as an example, an excessively wide particle size distribution may lead to agglomeration or voids in the electrode material during processing, affecting lithium-ion transport efficiency; while an excessively narrow particle size distribution may reduce the specific surface area of ​​the electrode material, limiting electrochemical activity. Therefore, optimizing process parameters in air jet milling is of great significance for improving the performance of electrode materials.

[0036] In related technologies, operators determine process parameters based on manual experience or subjective judgment. Differences in operation between different shifts or by different operators can lead to poor stability of the electrode material. For example, when the hardness of blocky materials fluctuates, operators need to adjust the airflow pressure based on experience, but the lack of quantitative basis easily leads to batch-to-batch variations in electrode material.

[0037] The method for optimizing the electrode material preparation process provided in this application aims to solve the above-mentioned technical problems in related technologies.

[0038] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0039] Figure 2 A flowchart illustrating an optimized method for electrode material preparation in this application embodiment is provided. The method includes the following steps:

[0040] S201. Receive a request for optimization of process parameters, determine the historical process parameters, historical performance data, raw material characteristics, preparation equipment status and target performance data of the electrode material. The historical process parameters are the process parameters used in the historical preparation of the electrode material. The process parameters include at least one of the following: crushing pressure, classifying speed and feeding rate.

[0041] Among them, the optimization method for electrode material preparation process can be executed by an optimization system for electrode material preparation process, and the optimization system is used to optimize the particle size distribution of electrode material.

[0042] For example, the electrode material is the electrode material specified in the optimization request. The electrode material is used to prepare the electrode of a battery (e.g., a lithium-ion battery). The electrode material includes, but is not limited to, at least one of the following: lithium iron phosphate, nickel-cobalt-manganese ternary, lithium cobalt oxide, lithium manganese oxide, etc.

[0043] For example, historical process parameters refer to the process parameters used in the historical production of electrode materials. These include, for instance, temperature, power, feed rate, crushing pressure, classifying speed, and feed rate.

[0044] For example, historical performance data refers to the actual performance of electrode materials prepared using historical process parameters. Examples include particle size distribution, powder tap density, powder compaction density, and electrochemical performance.

[0045] For example, raw material properties refer to the inherent attributes of the raw materials used to prepare the electrode materials. These include, for instance, the initial moisture content, initial particle size, and purity of the raw materials. Process parameters are constrained based on the characteristics of the raw materials to avoid mismatches between the process parameters and the raw materials.

[0046] For example, the equipment status refers to the current state of the equipment used to prepare electrode materials. This could include rated operating conditions, maximum operating conditions, or wear conditions. The equipment status constrains process parameters to prevent them from exceeding the equipment's operating limits.

[0047] For example, the target performance data optimization request specifies the final desired electrode material performance.

[0048] S202. Based on historical process parameters and historical performance data, construct a multi-objective optimization model. The multi-objective optimization model is used to represent the mapping relationship between process parameters and performance data.

[0049] For example, multi-objective optimization models are used to establish a mapping relationship between process parameters and performance data. That is, given a set of process parameters, the multi-objective optimization model can accurately map the electrode material properties that can be obtained by preparing the material according to these parameters.

[0050] For example, the performance data includes multiple types, and the multi-objective optimization model calculates the performance data of the electrode material for each type through multiple objective functions to accurately reflect the performance of each type.

[0051] Using scenario examples, it can be illustrated that human experience cannot accurately capture the relationship between subtle changes in process parameters and performance changes, while multi-objective optimization models can quantify this relationship using a large amount of raw data, thus avoiding errors in human judgment.

[0052] S203. Based on historical process parameters, raw material characteristics, and preparation equipment status, construct a set of constraints. The set of constraints is used to control the optimization boundary of process parameters.

[0053] For example, the constraint set is used to define the upper and lower limits of the process parameters that can be adjusted. The constraint set determined based on historical process parameters, raw material characteristics, and the status of the preparation equipment represents the range of process parameters that can be objectively achieved under the current process production conditions.

[0054] Using scenario examples, optimizing process parameters to improve the performance of electrode materials involves selecting achievable process parameters. Constraints are applied through a set of conditions to ensure the feasibility of the final target process parameters, thereby enhancing the reliability of the electrode materials.

[0055] S204. Through a multi-objective optimization model and a set of constraints, determine the target process parameters corresponding to the target performance data, and generate instruction commands based on the target process parameters. The instruction commands are used to instruct the electrode material to undergo an air-crushing process according to the target process parameters.

[0056] For example, the target performance data is input into a multi-objective optimization model, and the multi-objective optimization model performs calculations and filtering within the constraint set to finally obtain a set of optimal and feasible process parameters, i.e., the target process parameters.

[0057] With the help of scenario examples, the constraint set can be used to filter out process parameters that are outside the range of raw material compatibility, equipment safety, and process stability.

[0058] For example, target process parameters are used to ensure that the electrode material achieves target performance data. Instructions corresponding to the target process parameters are generated to instruct the electrode material to be prepared according to the target process parameters during the preparation process, ensuring that the prepared electrode material achieves the expected target performance data.

[0059] With scenario examples, the process of determining target process parameters minimizes human intervention and is driven by models and constraints. This avoids subjective errors from human experience while ensuring the feasibility and stability of process parameters. The produced electrode materials achieve the target performance data, and exhibit good batch-to-batch stability.

[0060] The electrode material preparation process optimization method provided in this application embodiment receives a process parameter optimization request, determines the historical process parameters, historical performance data, raw material characteristics, preparation equipment status, and target performance data of the electrode material. The historical process parameters are those used in the historical preparation of the electrode material, and include at least one of the following: crushing pressure, classifying speed, and feed rate. Based on the historical process parameters and historical performance data, a multi-objective optimization model is constructed to represent the mapping relationship between process parameters and performance data. Based on the historical process parameters, raw material characteristics, and preparation equipment status, a constraint set is constructed to control the optimization boundary of the process parameters. Through the multi-objective optimization model and the constraint set, the target process parameters corresponding to the target performance data are determined, and an instruction is generated based on the target process parameters. The instruction is used to instruct the electrode material to undergo an air crushing process according to the target process parameters. This scheme establishes a multi-objective optimization model for the mapping relationship between process parameters and performance data, accurately determines the target process parameters corresponding to achieving the target performance data based on the multi-objective optimization model, avoids introducing human error, and thus improves the stability of the electrode material.

[0061] Based on any of the above embodiments, the following, in conjunction with Figure 3 The detailed process of optimizing the electrode material preparation technology is explained.

[0062] Figure 3 This is a schematic flowchart illustrating an optimized method for preparing another electrode material, as provided in an embodiment of this application. Figure 3 As shown, the method includes:

[0063] S301. Receive a request for optimization of process parameters, determine the historical process parameters, historical performance data, raw material characteristics, preparation equipment status and target performance data of the electrode material. The historical process parameters are the process parameters used in the historical preparation of the electrode material. The process parameters include at least one of the following: crushing pressure, classifying speed and feeding rate.

[0064] It should be noted that the execution process of S301 is the same as that of S201, and will not be repeated here.

[0065] S302. Remove invalid parameters from historical process parameters to obtain valid process parameters, and remove invalid data from historical performance data to obtain valid performance data.

[0066] The historical performance data includes powder data and electrochemical performance data of the electrode materials.

[0067] The powder data includes particle gradation parameters based on a multi-level particle gradation strategy. These parameters include the mass fraction, median particle size, and standard deviation of particle size for each particle level.

[0068] Optionally, particle size distribution parameters can be expressed using the following formula:

[0069]

[0070] in, Let i represent the mass fraction of the i-th level particles, where i = 1, 2, 3. This represents the median particle size of the i-th order particles. This represents the standard deviation of the particle size of the i-th order of particles.

[0071] For example, a multi-level particle gradation strategy involves dividing the electrode material powder into multiple particle levels (e.g., large particles, medium particles, small particles, etc.) according to particle size, and achieving the optimal physical properties of the powder by adjusting the combination of different particle levels.

[0072] Mass fraction represents the percentage of the mass of a certain grade of particles out of the total mass of all grades of particles, and characterizes the proportion between different grades of particles.

[0073] The median particle size represents the particle size value at which the cumulative particle size distribution of a certain level reaches 50%, and characterizes the average size of particles at that level.

[0074] The standard deviation of particle size indicates the degree of dispersion in the particle size distribution of a certain level of particles, and characterizes the uniformity of particle size at that level.

[0075] With a scenario example, when powders of a single particle size are stacked, numerous pores form between the particles, resulting in low packing density. Multi-level particle gradation, however, significantly reduces porosity by having large particles form the framework and medium / small particles fill the gaps, thus greatly increasing both the loose packing density and tap density of the powder. Higher packing density means that more active material can be accommodated within the same electrode volume, directly increasing the volumetric energy density of the battery.

[0076] For example, before building the model, the acquired historical process parameters and historical performance data are preprocessed and invalid values ​​are removed.

[0077] Based on scenario examples, data exhibiting obvious acquisition anomalies, missing values, exceeding reasonable process ranges, or unrelated to changes in electrode material properties are defined as invalid and discarded. Only data that accurately and stably reflects the correspondence between the preparation process and material properties are retained, yielding valid process parameters and effective performance data. This data-driven approach ensures the reliability of subsequent model training and fitting, thereby improving the accuracy of the target process parameters.

[0078] S303, Determine multiple performance index types.

[0079] For example, the performance index type is a dimension for evaluating the performance of electrode materials.

[0080] For example, the performance data of electrode materials are clearly divided into two major types according to their physical nature and characterization dimensions: powder data and electrochemical performance data.

[0081] Optional, powder data, including but not limited to at least one of the following: particle size distribution, powder tap density, powder compaction density, etc.

[0082] Optionally, electrochemical performance data may include, but are not limited to, at least one of the following: specific capacity of electrode material, initial charge-discharge efficiency, cycle life, rate discharge performance, AC impedance, polarization voltage, etc.

[0083] One feasible approach is to determine multiple performance index types by: determining the equipment type of the preparation equipment; and determining multiple performance index types based on raw material characteristics, equipment type, and target performance data.

[0084] For example, the equipment type refers to the category of equipment used in the preparation of this electrode material (e.g., ball milling equipment or sintering equipment). Different equipment can control and focus on different categories of performance indicators.

[0085] For example, the characteristics of the raw material determine which performance indicators need to be monitored. The target performance data determines which performance indicators ultimately need to be achieved.

[0086] With the help of scenario examples, if the cycle life of any raw material fluctuates significantly under different process parameters, then the cycle life should be the focus, and the process parameters should be optimized based on the cycle life to improve the performance of the electrode material.

[0087] In this feasible implementation method, the performance index type is determined by integrating multiple dimensions, replacing manual selection of performance index type based on experience, avoiding the introduction of human error, and thus improving the stability of electrode materials.

[0088] S304. Based on multiple performance index types, effective process parameters, and effective performance data, regression analysis and data fitting are performed to obtain the first mapping model between process parameters and powder data, and the second mapping model between process parameters and electrochemical performance.

[0089] The first mapping model and the second mapping model each include at least one performance metric type.

[0090] For example, the first mapping model is used to represent the mapping relationship between process parameters and powder data.

[0091] For example, the second mapping model is used to represent the mapping relationship between process parameters and electrochemical performance data.

[0092] Optionally, the first mapping model can be a model with packing density as the objective function or a model with granularity distribution as the objective function. The objective function for packing density is expressed based on the Funk-Dinger close-packing theory:

[0093]

[0094] in, This represents the objective function for packing density. This represents the tap density. This represents the theoretical density. Stacking efficiency.

[0095]

[0096] in, This represents the mass fraction of the i-th level particles. This represents the mass fraction of particles in the j-th order. This represents the mass fraction of the i-th level particles. This represents the mass fraction of the j-th particle. represents the packing coefficient between particles of level i and level j, and n represents the total number of particle levels.

[0097] The simplified objective function for packing density can be:

[0098]

[0099] in, Represents the actual distribution modulus. Indicates weight, This indicates the particle size at which the cumulative volume fraction in the particle size distribution reaches 90%. This indicates the particle size at which the cumulative volume fraction in the particle size distribution reaches 10%.

[0100] Optionally, the objective function for particle size distribution can be expressed by the following formula:

[0101]

[0102] in, Let N represent the objective function for particle size distribution, N represent the total number of particle size intervals divided in the particle size distribution test, and k represent the index of the particle size interval. This represents the weight of the k-th particle size interval. Indicates particle size The actual cumulative distribution of powder at the location (e.g., volume or mass fraction). Indicates particle size Cumulative distribution of powder targets at the location.

[0103] Optionally, the cumulative target distribution can be a bimodal distribution:

[0104]

[0105] in, This represents the cumulative function of the standard normal distribution.

[0106] Optionally, the objective function of the second mapping model can be:

[0107]

[0108] in, Indicates overall electrochemical performance, This represents the performance coefficient based on the rate of increase. Indicates electronic conductivity, α represents the polarization resistance, and β and γ represent the weights.

[0109] Based on the above implementation methods, by constructing separate models independently, the mutual interference between the influence mechanisms of powder physical properties and electrochemical properties is avoided, thereby improving the accuracy of target process parameters.

[0110] S305. Couple the first mapping model and the second mapping model to obtain a multi-objective optimization model.

[0111] For example, the coupled model is no longer limited to a single performance dimension, but can simultaneously receive process parameter inputs and synchronously output powder performance prediction results and electrochemical performance prediction results, thereby achieving integrated characterization of the multi-dimensional performance of electrode materials.

[0112] Based on the above implementation methods, a first mapping model and a second mapping model are established and coupled to form a multi-objective optimization model that can simultaneously take into account the mapping relationship between powder performance and electrochemical performance. This eliminates the need to rely on human experience to balance multi-dimensional performance indicators, avoids introducing human error, and thus improves the stability of electrode materials.

[0113] One feasible implementation method is to couple the model as follows: determine the target application scenario of the electrode material and the mapping relationship between the application scenario and the weights; determine the first weight and the second weight according to the target application scenario and the mapping relationship; and perform weighted calculation on the first mapping model and the second mapping model according to the first weight and the second weight to obtain a multi-objective optimization model.

[0114] For example, different application scenarios emphasize different types of performance, and corresponding weights are configured for different application scenarios. For instance, power batteries emphasize rate performance and cycle life, energy storage batteries emphasize high energy density, and consumer electronics batteries emphasize specific capacity performance.

[0115] For example, the first weight is the weight corresponding to the first mapping model, and the second weight is the weight corresponding to the second mapping model. The importance of the first and second mapping models in the multi-objective optimization model is balanced through the first and second weights.

[0116] Optionally, the overall objective function of the multi-objective optimization model can be expressed by the following formula:

[0117]

[0118] in, Describe the overall objective function. , , These represent the weights of each objective function.

[0119] It should be noted that the parameters in the overall objective function of this application are only examples.

[0120] In this feasible implementation, through weighted coupling, the multi-objective optimization model can take into account both powder performance and electrochemical performance in an appropriate proportion according to the specific application scenario, thereby avoiding the introduction of human error and improving the stability of the electrode material.

[0121] A feasible implementation method can be used to determine the multi-objective optimization model, including: performing a weighted calculation on the first mapping model and the second mapping model according to the first weight and the second weight to obtain the model to be verified; selecting verification data that did not participate in the model construction from the effective performance data; determining the actual process parameters corresponding to the verification data from the effective process parameters; inputting the verification data into the model to be verified to obtain the predicted process parameters; determining the prediction deviation value based on the predicted process parameters and the actual process parameters; and determining the model to be verified as the multi-objective optimization model if the prediction deviation value is less than or equal to the first deviation value threshold.

[0122] For example, the actual process parameters are the preparation process parameters corresponding to the electrode material for which the verification data is obtained.

[0123] Below, in conjunction with Figure 4 The determination of the multi-objective optimization model is explained.

[0124] Figure 4 This is a schematic diagram illustrating a multi-objective optimization model provided in an embodiment of this application. Figure 4As shown, regression analysis and data fitting are performed on partial data corresponding to multiple performance index types from the effective performance data and effective process parameters to obtain a first mapping model and a second mapping model. The first and second mapping models are then weighted and coupled to obtain the model to be validated. Data from the effective performance data that did not participate in regression analysis and data fitting are selected as validation data. The validation data are substituted into the model to be validated to obtain predicted process parameters. The predicted process parameters are compared with the actual process parameters corresponding to the validation data to validate the model. This process continues until validation is successful, at which point the current model to be validated is determined as a multi-objective optimization model.

[0125] With the help of scenario examples, by selecting data that was not involved in the model building as validation data, we can ensure that the validation results are not affected by the modeling data.

[0126] Optionally, if the validation fails, regression analysis, data fitting, and model validation are performed iteratively.

[0127] In this feasible implementation, the effectiveness of the model is determined by comparing the quantified prediction deviation value with the first deviation value threshold, replacing the subjective judgment of the model quality by humans, avoiding the introduction of human error, and thus improving the stability of the electrode material.

[0128] S306. Based on historical process parameters, raw material characteristics, and preparation equipment status, construct a set of constraints. The set of constraints is used to control the optimization boundary of process parameters.

[0129] One feasible implementation method involves constructing a constraint set as follows: Based on historical fluctuation data corresponding to historical process parameters, determine the fluctuation range of the process parameters and define the fluctuation range as a process stability constraint; determine the adjustment range of the first process parameter corresponding to the raw material characteristics and define the first process parameter adjustment range as a raw material compatibility constraint; based on the state of the preparation equipment, determine the adjustment range of the second process parameter for safe operation of the preparation equipment and define the second process parameter adjustment range as an equipment safety constraint; and construct a constraint set based on the process stability constraint, the raw material compatibility constraint, and the equipment safety constraint.

[0130] For example, historical fluctuation data represents the actual fluctuation range, fluctuation amplitude, and dispersion of various process parameters (such as ball milling time, sieve aperture, sintering temperature, etc.) during the historical electrode material preparation process (such as the maximum value, minimum value, standard deviation, etc. of historical ball milling time).

[0131] Optionally, abnormal fluctuations (such as extreme parameter values ​​caused by equipment failure or human error) can be removed from historical fluctuation data to determine the fluctuation range of process parameters that can operate stably and ensure the consistency of electrode material performance, and this fluctuation range can be used as a process stability constraint.

[0132] With the help of scenario examples, the process stability constraint is used to limit the fluctuation range of process parameters, avoid sudden changes in process parameters that could cause large fluctuations in electrode material performance, and improve the stability of the preparation process optimization.

[0133] For example, based on the characteristics of the raw materials, the reasonable adjustment range of process parameters is analyzed and determined. For instance, if the initial particle size of the raw material is coarse, a minimum threshold for ball milling time needs to be defined to ensure that the raw material can be ground to the required particle size; if the purity of the raw material is low, the adjustment range of the sintering temperature needs to be defined to avoid excessively high temperatures leading to impurity precipitation and performance deterioration. Raw material compatibility constraints ensure that the process parameters are compatible with the characteristics of the raw materials, avoiding substandard performance or material waste due to mismatch between parameters and raw materials.

[0134] For example, based on the rated operating parameters, safe operating limits, and current operating conditions of the preparation equipment, a second process parameter adjustment range is determined to ensure the safe, stable, and long-term operation of the equipment. For instance, the rotational speed of a ball mill must not exceed its rated speed; otherwise, it will lead to accelerated equipment wear and malfunctions. Equipment safety constraints are used to mitigate safety hazards and equipment failures caused by process parameters exceeding the equipment's capabilities.

[0135] In this feasible implementation method, the fluctuation range is quantified based on historical real data, which replaces the manual setting of parameter fluctuation range based on experience. This can avoid the introduction of human error and thus improve the stability of electrode materials.

[0136] One feasible implementation method is to construct a constraint set by the following steps: constructing equality constraint terms and inequality constraint terms based on the constraint forms corresponding to process stability constraint terms, raw material compatibility constraint terms, and equipment safety constraint terms; summarizing the equality constraint terms and inequality constraint terms to obtain the constraint set; wherein, equality constraint terms are used to represent constraints that satisfy equality relationships, and inequality constraint terms are used to represent constraints that satisfy numerical range requirements.

[0137] For example, equality constraints may include mass conservation constraints, granularity continuity constraints, etc.

[0138] Optionally, the mass conservation constraint term can be represented by the following formula:

[0139]

[0140] in, This represents the mass conservation constraint, which states that the total mass of all particles in the powder is 100%, to avoid situations that do not conform to the law of mass conservation.

[0141] Optionally, the granularity continuity constraint term can be represented by the following formula:

[0142]

[0143]

[0144] in, , This indicates a particle size continuity constraint, meaning the median particle size of particles of different size classes in the powder is distributed in a gradient according to a preset proportional relationship. 3 represents the proportion; no specific proportional value is specified.

[0145] For example, inequality constraints may include particle size range constraints, mass fraction constraints, distribution width constraints, critical particle size point constraints, and process parameter constraints.

[0146] Optionally, the particle size range constraint term can be represented by the following formula:

[0147]

[0148]

[0149]

[0150] Among them, 10, 30, 3, 0.3, and 1.5 represent the boundary values ​​of the particle size range. By limiting the median particle size of multi-stage particles to a reasonable range, the gradation imbalance caused by excessively large or small particle sizes can be avoided.

[0151] Optionally, the quality fraction constraint term can be represented by the following formula:

[0152]

[0153]

[0154]

[0155] Here, 20%, 50%, 30%, 60%, and 10% represent the boundary values ​​for mass fraction. These boundary values ​​are used to prevent an imbalance in the proportion of multi-level particles, which could lead to increased porosity and decreased bulk density.

[0156] Optionally, the distribution width constraint term can be represented by the following formula:

[0157]

[0158] Here, 1.2 and 2.0 represent the boundary values ​​of the particle size standard deviation. These boundary values ​​are used to prevent uneven particle size distribution at each particle size level.

[0159] Optionally, the critical particle size constraint term can be represented by the following formula:

[0160]

[0161]

[0162]

[0163] Specifically, a lower limit of fine particle size is constrained by 0.2 to prevent agglomeration caused by excessive fine particles. An upper limit of coarse particle size is constrained by 35 to prevent uneven electrode material coating caused by excessive coarse particles. Span represents the particle size distribution span, controlling the overall particle size distribution span to ensure batch-to-batch consistency of powder performance.

[0164] Optionally, the process parameter constraints, taking sand milling as an example, can be represented by the following formula:

[0165]

[0166] in, The input values ​​are: P (specific energy input), t (power output), m (working time), and m (mass of raw materials). This indicates the maximum specific energy input limit of the sand milling equipment. By limiting the energy input of the sand milling process within the equipment's capacity, overload operation that could lead to equipment damage or excessive energy consumption is avoided, while ensuring that the sand milling effect meets expectations.

[0167] In this feasible implementation, by clearly distinguishing between equality constraints (for quantitative relationships) and inequality constraints (for numerical range requirements), the structure of the constraint set is clearly hierarchical. This ensures that each type of constraint accurately corresponds to its physical meaning and technical objective, guaranteeing that the constraint system better aligns with the actual laws governing electrode material fabrication, avoiding the introduction of human error, and thus improving the stability of the electrode material.

[0168] S307. Input the constraint set into the multi-objective optimization model to obtain the feasible solution boundary of the process parameters.

[0169] For example, when a complete set of constraints is input into a multi-objective optimization model, the model will automatically parse all constraints and select the parameter range that simultaneously satisfies all constraints such as process stability, raw material compatibility, and equipment safety from all theoretically possible combinations of process parameters, thus forming the feasible solution boundary of the process parameters.

[0170] With the help of scenario examples, the feasible solution boundary clarifies which combinations of process parameters are physically reasonable and production-feasible, excluding parameter combinations that exceed equipment capacity, violate physical laws, or lead to performance runaway.

[0171] S308. Based on the target performance data, the multi-objective optimization model is globally optimized within the feasible solution boundary using an optimization algorithm to obtain multiple predicted process parameters. The performance data corresponding to each predicted process parameter is greater than or equal to the target performance data.

[0172] For example, by using a global optimization algorithm to replace the traditional trial-and-error parameter tuning method that relies on human experience, it is possible to traverse all potential optimal solutions within the feasible solution boundary and find a more accurate and efficient combination of process parameters than human experience.

[0173] S309. Determine the target process parameters based on multiple predicted process parameters.

[0174] For example, generating multiple predicted process parameters that meet the target performance provides a flexible selection space, allowing the user to choose the most suitable target process parameter from among them. For instance, based on the characteristics of raw materials in different batches, equipment operating conditions, or cost requirements, the optimal parameter can be selected from multiple predicted parameters, ensuring that performance targets are met while improving the flexibility and adaptability of process optimization.

[0175] Based on the above implementation methods, subjective human judgment, experience blind spots, and trial-and-error errors are eliminated, improving the accuracy of target process parameters and thus enhancing the stability of electrode materials.

[0176] One feasible implementation method is to determine the target process parameters by: determining the operating condition stability corresponding to each predicted process parameter; and determining the target process parameter from multiple predicted process parameters based on the performance data and operating condition stability corresponding to each predicted process parameter.

[0177] For example, for each predicted process parameter that meets the performance requirements, its corresponding operating condition stability is evaluated. Operating condition stability refers to the ability of process parameters to maintain the stability of electrode material performance in the face of uncontrollable factors such as fluctuations in raw material properties, changes in equipment status, and environmental disturbances during actual production.

[0178] Optionally, the evaluation method can be based on historical production data, simulation models, etc. For example, analyze the sensitivity of the predicted process parameters to fluctuations in raw material humidity and purity; evaluate the performance retention rate of the predicted process parameters under equipment speed and temperature fluctuations; and statistically analyze the probability of the predicted process parameters causing performance deviations in past batches. The lower the sensitivity, the higher the performance retention rate, and the smaller the probability of deviations, the better the operating stability of the corresponding predicted process parameters.

[0179] For example, the optimal target process parameters are determined by combining comprehensive performance data and operating condition stability.

[0180] In this feasible implementation method, objective operational stability assessment replaces subjective human judgment, avoiding the blind spots of experience and subjective biases when manually selecting process parameters, thereby improving the stability of electrode materials.

[0181] One feasible implementation method, after determining the target process parameters, further includes: obtaining the actual performance data corresponding to the target process parameters; determining whether the deviation between the actual performance data and the target performance data is greater than or equal to a second deviation threshold; if so, updating the multi-objective optimization model based on the target process parameters and the actual performance data to obtain an updated model.

[0182] This can be achieved by updating the controller to perform iterative updates of the model.

[0183] For example, after the target process parameters are executed in actual production and the electrode material is prepared, the actual performance data (including powder properties, electrochemical properties, etc.) corresponding to that batch of products are collected.

[0184] For example, the actual performance data is compared with the set target performance data to obtain the deviation value, and it is determined whether the deviation value is greater than or equal to the second deviation value threshold to verify the accuracy of the multi-objective optimization model.

[0185] To illustrate with a scenario example, if the judgment result is yes, meaning the actual performance deviates too much from the target performance and does not meet the accuracy requirements, then the target process parameters used in this instance and the corresponding actual performance data are used as new sample data to correct and update the multi-objective optimization model, resulting in an updated optimization model, which is then used for the next batch of process parameter optimization.

[0186] In this feasible implementation, by iteratively updating the multi-objective optimization model, the multi-objective optimization model can be adapted to the fluctuations in actual production, thereby improving the reliability of the electrode material.

[0187] Figure 5 This is a schematic diagram of the structure of an optimized system for electrode material preparation process provided in an embodiment of this application.

[0188] like Figure 5As shown, the data layer controller comprehensively senses and collects historical process parameters and performance data, providing data support for subsequent model construction and optimization. The model controller transforms historical process parameters and performance data into a computable multi-objective optimization model through experimental design. The optimization controller, based on the set target performance data and under the premise of satisfying constraints, searches for target process parameters. Real-time optimization engines using intelligent algorithms such as genetic algorithms and particle swarm optimization can efficiently find the optimal process parameters by traversing feasible solutions. The update controller sends the target process parameters output by the optimization controller to the production equipment for actual execution. Real-time data collection during the production process enables model self-learning and correction, improving the model's predictive accuracy.

[0189] This application provides a single-cell battery, which includes at least electrode material. The electrode material is prepared using target process parameters determined by an optimization method for the preparation process.

[0190] Based on the above implementation methods, a multi-objective optimization model is established to map the relationship between process parameters and performance data. The target process parameters corresponding to the target performance data are accurately determined according to the multi-objective optimization model, avoiding the introduction of human error and thus improving the stability of electrode materials.

[0191] This application provides a battery pack comprising at least two of the above-described individual cells, each of which is electrically connected to the other.

[0192] Based on the above implementation methods, a multi-objective optimization model is established to map the relationship between process parameters and performance data. The target process parameters corresponding to the target performance data are accurately determined according to the multi-objective optimization model, avoiding the introduction of human error and thus improving the stability of electrode materials.

[0193] This application provides a battery pack, including a housing and at least two battery packs as described above, each battery pack being disposed within the housing and electrically connected to each other.

[0194] Based on the above implementation methods, a multi-objective optimization model is established to map the relationship between process parameters and performance data. The target process parameters corresponding to the target performance data are accurately determined according to the multi-objective optimization model, avoiding the introduction of human error and thus improving the stability of electrode materials.

[0195] This application provides an electric vehicle that includes at least the aforementioned battery pack.

[0196] Based on the above implementation methods, a multi-objective optimization model is established to map the relationship between process parameters and performance data. The target process parameters corresponding to the target performance data are accurately determined according to the multi-objective optimization model, avoiding the introduction of human error and thus improving the stability of electrode materials.

[0197] This application provides an electrical device that includes at least the aforementioned single battery cell.

[0198] Based on the above implementation methods, a multi-objective optimization model is established to map the relationship between process parameters and performance data. The target process parameters corresponding to the target performance data are accurately determined according to the multi-objective optimization model, avoiding the introduction of human error and thus improving the stability of electrode materials.

[0199] Figure 6 This is a schematic diagram of an optimized apparatus for electrode material preparation process provided in an embodiment of this application. Figure 6 As shown, the optimization device 60 for the electrode material preparation process may include: an acquisition module 61, a modeling module 62, a construction module 63, and a generation module 64.

[0200] The acquisition module 61 is used to receive optimization requests for process parameters, determine the historical process parameters, historical performance data, raw material characteristics, preparation equipment status and target performance data of the electrode material. The historical process parameters are the process parameters used in the historical preparation of the electrode material. The process parameters include at least one of the following: crushing pressure, classifying speed and feeding rate.

[0201] Modeling module 62 is used to construct a multi-objective optimization model based on historical process parameters and historical performance data. The multi-objective optimization model is used to represent the mapping relationship between process parameters and performance data.

[0202] Module 63 is used to construct a set of constraints based on historical process parameters, raw material characteristics, and preparation equipment status. The set of constraints is used to control the optimization boundary of process parameters.

[0203] The generation module 64 is used to determine the target process parameters corresponding to the target performance data through a multi-objective optimization model and a set of constraints, and to generate instruction commands based on the target process parameters. The instruction commands are used to instruct the electrode material to undergo an air crushing process according to the target process parameters.

[0204] Optionally, module 61 can be executed. Figure 2 S201 in the embodiment.

[0205] Optionally, modeling module 62 can execute Figure 2 S202 in the embodiment.

[0206] Optionally, builder module 63 can execute Figure 2 S203 in the embodiment.

[0207] Optionally, the generation module 64 can be executed. Figure 2 S204 in the embodiment.

[0208] It should be noted that the optimized device for electrode material preparation process shown in the embodiments of this application can execute the technical solution shown in the above method embodiments, and its implementation principle and beneficial effects are similar, so they will not be described again here.

[0209] Based on the above implementation methods, a multi-objective optimization model is established to map the relationship between process parameters and performance data. The target process parameters corresponding to the target performance data are accurately determined according to the multi-objective optimization model, avoiding the introduction of human error and thus improving the stability of electrode materials.

[0210] In one possible implementation, modeling module 62 is specifically used for:

[0211] Invalid parameters are removed from historical process parameters to obtain valid process parameters; invalid data is removed from historical performance data to obtain valid performance data.

[0212] Determine multiple performance metric types;

[0213] Based on multiple performance index types, effective process parameters, and effective performance data, regression analysis and data fitting are performed to obtain a first mapping model between process parameters and powder data and a second mapping model between process parameters and electrochemical performance. The first mapping model and the second mapping model each include at least one performance index type.

[0214] By coupling the first mapping model and the second mapping model, a multi-objective optimization model is obtained.

[0215] In one possible implementation, modeling module 62 is specifically used for:

[0216] Determine the type of equipment used in the preparation process;

[0217] Based on the characteristics of raw materials, equipment type, and target performance data, multiple performance index types are determined.

[0218] In one possible implementation, modeling module 62 is specifically used for:

[0219] Determine the target application scenarios for electrode materials and the mapping relationship between application scenarios and weights;

[0220] Based on the target application scenario and mapping relationship, determine the first weight and the second weight;

[0221] Based on the first weight and the second weight, the first mapping model and the second mapping model are weighted and calculated to obtain the multi-objective optimization model.

[0222] In one possible implementation, modeling module 62 is specifically used for:

[0223] Based on the first weight and the second weight, the first mapping model and the second mapping model are weighted and calculated to obtain the model to be verified.

[0224] Select validation data that was not used in model building from the effective performance data;

[0225] Determine the actual process parameters corresponding to the validation data from the effective process parameters;

[0226] Input the verification data into the model to be verified to obtain the predicted process parameters;

[0227] The predicted deviation value is determined based on the predicted process parameters and the actual process parameters;

[0228] If the prediction deviation is less than or equal to the first deviation threshold, the model to be verified is determined as a multi-objective optimization model.

[0229] In one possible implementation, the construction module 63 is specifically used for:

[0230] The fluctuation range is defined as a process stability constraint.

[0231] Determine the adjustment range of the first process parameter corresponding to the characteristics of the raw material, and define the adjustment range of the first process parameter as the raw material adaptation constraint.

[0232] Based on the status of the preparation equipment, determine the adjustment range of the second process parameter for safe operation of the preparation equipment, and define the adjustment range of the second process parameter as the equipment safety constraint.

[0233] A set of constraints is constructed based on process stability constraints, raw material compatibility constraints, and equipment safety constraints.

[0234] In one possible implementation, the construction module 63 is specifically used for:

[0235] Based on the constraint forms corresponding to the process stability constraint, raw material compatibility constraint, and equipment safety constraint, construct equality constraint terms and inequality constraint terms respectively;

[0236] By summing up the equality constraints and inequality constraints, we obtain the constraint set.

[0237] Among them, the equality constraint term is used to represent the constraint that satisfies the equality relationship, and the inequality constraint term is used to represent the constraint that satisfies the numerical range requirement.

[0238] In one possible implementation, generation module 64 is specifically used for:

[0239] By inputting the set of constraints into the multi-objective optimization model, the feasible solution boundary of the process parameters is obtained.

[0240] Based on the target performance data, the multi-objective optimization model is globally optimized within the feasible solution boundary using an optimization algorithm to obtain multiple predicted process parameters. The performance data corresponding to each predicted process parameter is greater than or equal to the target performance data.

[0241] The target process parameters are determined based on multiple predicted process parameters.

[0242] In one possible implementation, generation module 64 is specifically used for:

[0243] Determine the operating condition stability corresponding to each predicted process parameter;

[0244] Based on the performance data and operating stability corresponding to each predicted process parameter, the target process parameter is determined from multiple predicted process parameters.

[0245] Figure 7 This is a schematic diagram of an optimized apparatus for another electrode material preparation process provided in an embodiment of this application. Figure 6 Based on the illustrated embodiments, as Figure 7 As shown, the optimization device 60 for the electrode material preparation process also includes an update module 65.

[0246] Update module 65, used for:

[0247] Obtain the actual performance data corresponding to the target process parameters;

[0248] Determine whether the deviation between the actual performance data and the target performance data is greater than or equal to the second deviation threshold. If so, update the multi-objective optimization model based on the target process parameters and the actual performance data to obtain the updated model.

[0249] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 8 As shown, the electronic device includes:

[0250] The electronic device includes a processor 291 and a memory 292; it may also include a communication interface 293 and a bus 294. The processor 291, memory 292, and communication interface 293 can communicate with each other via the bus 294. The communication interface 293 can be used for information transmission. The processor 291 can invoke logical instructions stored in the memory 292 to execute the methods of the above embodiments.

[0251] Furthermore, the logic instructions in the aforementioned memory 292 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0252] The memory 292, as a non-volatile computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this application. The processor 291 executes functional applications and data processing by running the software programs, instructions, and modules stored in the memory 292, that is, it implements the methods in the above-described method embodiments.

[0253] The memory 292 may include a program storage area and a data storage area. The program storage area may store the operating system and application programs required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 292 may include high-speed random access memory and may also include non-volatile memory.

[0254] Based on the above implementation methods, a multi-objective optimization model is established to map the relationship between process parameters and performance data. The target process parameters corresponding to the target performance data are accurately determined according to the multi-objective optimization model, avoiding the introduction of human error and thus improving the stability of electrode materials.

[0255] This application provides a non-volatile computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method as described in the foregoing embodiments.

[0256] Based on the above implementation methods, a multi-objective optimization model is established to map the relationship between process parameters and performance data. The target process parameters corresponding to the target performance data are accurately determined according to the multi-objective optimization model, avoiding the introduction of human error and thus improving the stability of electrode materials.

[0257] This application provides a computer program product, including a computer program that, when executed by a processor, implements the method as described in the foregoing embodiments.

[0258] Based on the above implementation methods, a multi-objective optimization model is established to map the relationship between process parameters and performance data. The target process parameters corresponding to the target performance data are accurately determined according to the multi-objective optimization model, avoiding the introduction of human error and thus improving the stability of electrode materials.

[0259] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0260] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps; they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages, which do not necessarily complete at the same time but can be executed at different times. The execution order of these sub-steps or stages is also not necessarily sequential but can be alternated or carried out in turn with other steps or at least some of the sub-steps or stages of other steps.

[0261] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0262] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0263] When integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. The processor can be any suitable hardware processor, such as CPU, GPU, FPGA, DSP, and ASIC. The storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0264] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to related technologies, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0265] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0266] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the claims.

[0267] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A system for optimizing a preparation process, characterized in that, The optimization system is used to optimize the particle size distribution of the electrode material, and the optimization system is configured to perform the following steps: Receive a request to optimize process parameters, determine the historical process parameters, historical performance data, raw material characteristics, preparation equipment status, and target performance data of the electrode material. The historical process parameters are the process parameters used in the historical preparation of the electrode material. The process parameters include at least one of the following: crushing pressure, classifying speed, and feeding rate. Based on the historical process parameters and the historical performance data, a multi-objective optimization model is constructed, which is used to represent the mapping relationship between process parameters and performance data. Based on the historical process parameters, the raw material characteristics, and the state of the preparation equipment, a set of constraints is constructed, which is used to control the optimization boundary of the process parameters. The target process parameters corresponding to the target performance data are determined by the multi-objective optimization model and the set of constraints, and an instruction is generated based on the target process parameters. The instruction is used to instruct the electrode material to undergo an air crushing process according to the target process parameters.

2. The system according to claim 1, characterized in that, The historical performance data includes powder data and electrochemical performance data of the electrode material; the powder data includes particle size distribution parameters based on a multi-level particle size distribution strategy, and the particle size distribution parameters include the mass fraction, median diameter, and standard deviation of particle size for each particle size distribution. The steps for constructing the multi-objective optimization model specifically include: Invalid parameters are removed from historical process parameters to obtain valid process parameters; invalid data is removed from historical performance data to obtain valid performance data. Determine multiple performance metric types; Based on the multiple performance index types, the effective process parameters, and the effective performance data, regression analysis and data fitting are performed to obtain a first mapping model between process parameters and powder data and a second mapping model between process parameters and electrochemical performance. The first mapping model and the second mapping model each include at least one performance index type. The first mapping model and the second mapping model are coupled to obtain the multi-objective optimization model.

3. The system according to claim 2, characterized in that, The step of determining multiple performance index types specifically includes: Determine the type of equipment used in the preparation process; Based on the characteristics of the raw materials, the type of equipment, and the target performance data, multiple performance index types are determined.

4. The system according to claim 2, characterized in that, The step of coupling the first mapping model and the second mapping model to obtain the multi-objective optimization model specifically includes: Determine the target application scenarios for the electrode material and the mapping relationship between the application scenarios and the weights; Based on the target application scenario and the mapping relationship, determine the first weight and the second weight; The first mapping model and the second mapping model are weighted and calculated based on the first weight and the second weight to obtain the multi-objective optimization model.

5. The system according to claim 4, characterized in that, The weighted calculation step of the first mapping model and the second mapping model specifically includes: Based on the first weight and the second weight, the first mapping model and the second mapping model are weighted and calculated to obtain the model to be verified. Select validation data that was not involved in model construction from the effective performance data; Determine the actual process parameters corresponding to the verification data from the effective process parameters; The verification data is input into the model to be verified to obtain the predicted process parameters; The prediction deviation value is determined based on the predicted process parameters and the actual process parameters; If the prediction deviation value is determined to be less than or equal to the first deviation value threshold, the model to be verified is determined as the multi-objective optimization model.

6. The system according to claim 1, characterized in that, The step of constructing the constraint set specifically includes: Based on the historical fluctuation data corresponding to the historical process parameters, the fluctuation range of the process parameters is determined, and the fluctuation range is defined as the process stability constraint. Determine the adjustment range of the first process parameter corresponding to the characteristics of the raw material, and define the adjustment range of the first process parameter as the raw material adaptation constraint. Based on the state of the preparation equipment, determine the adjustment range of the second process parameter for safe operation of the preparation equipment, and define the adjustment range of the second process parameter as a safety constraint item for the equipment. The constraint set is constructed based on the process stability constraint, raw material compatibility constraint, and equipment safety constraint.

7. The system according to claim 6, characterized in that, The step of constructing the constraint set specifically includes: Based on the constraint forms corresponding to the process stability constraint, raw material compatibility constraint, and equipment safety constraint, respectively, construct equality constraint terms and inequality constraint terms; The set of constraints is obtained by summing the equality constraints and inequality constraints. The equality constraint term is used to represent constraints that satisfy equality relationships, and the inequality constraint term is used to represent constraints that satisfy numerical range requirements.

8. The system according to claim 1, characterized in that, The step of determining the target process parameters corresponding to the target performance data specifically includes: By inputting the set of constraints into the multi-objective optimization model, the feasible solution boundary of the process parameters is obtained; Based on the target performance data, the multi-objective optimization model is globally optimized within the feasible solution boundary using an optimization algorithm to obtain multiple predicted process parameters. The performance data corresponding to each predicted process parameter is greater than or equal to the target performance data. The target process parameters are determined based on the multiple predicted process parameters.

9. The system according to claim 8, characterized in that, The step of determining the target process parameter based on the plurality of predicted process parameters specifically includes: Determine the operating condition stability corresponding to each of the predicted process parameters; The target process parameter is determined from the plurality of predicted process parameters based on the performance data and operating stability corresponding to each predicted process parameter.

10. The system according to any one of claims 1-9, characterized in that, The optimization system for the preparation process is also configured to perform the following steps: Obtain the actual performance data corresponding to the target process parameters; Determine whether the deviation between the actual performance data and the target performance data is greater than or equal to a second deviation threshold. If so, update the multi-objective optimization model based on the target process parameters and the actual performance data to obtain an updated model.

11. An optimization method for a preparation process, characterized in that, include: Receive a request to optimize process parameters, determine the historical process parameters, historical performance data, raw material characteristics, preparation equipment status, and target performance data of the electrode material. The historical process parameters are the process parameters used in the historical preparation of the electrode material. The process parameters include at least one of the following: crushing pressure, classifying speed, and feeding rate. Based on the historical process parameters and the historical performance data, a multi-objective optimization model is constructed, which is used to represent the mapping relationship between process parameters and performance data. Based on the historical process parameters, the raw material characteristics, and the state of the preparation equipment, a set of constraints is constructed, which is used to control the optimization boundary of the process parameters. The target process parameters corresponding to the target performance data are determined by the multi-objective optimization model and the set of constraints, and an instruction is generated based on the target process parameters. The instruction is used to instruct the electrode material to undergo an air crushing process according to the target process parameters.

12. A single-cell battery, characterized in that, It includes at least an electrode material, which is prepared using the target process parameters determined by the optimization method of the preparation process described in claim 11.

13. A battery pack, characterized in that, It includes at least two individual cells as described in claim 12, each of which is electrically connected to the other.

14. A battery pack, characterized in that, It includes a housing and at least two battery packs as described in claim 13, each of the battery packs being disposed within the housing and electrically connected to each other.

15. An electric vehicle, characterized in that, It includes at least the battery pack as described in claim 14.

16. An electrical appliance, characterized in that, It includes at least the single cell as described in claim 12.

Images