A method and system for dynamic optimization of a lithium battery separator process

Abstract

The application relates to the field of lithium battery diaphragm, in particular to a lithium battery diaphragm process dynamic optimization method and system. The method comprises the following steps: real-time acquisition of key data such as extrusion equipment parameters, raw material information, environmental temperature and humidity, etc., to ensure the timeliness of the data. In the process of determining the influence degree of environmental temperature and humidity and predicting the predicted thickness of the base film, the data can be quickly processed and the result can be obtained. Once the predicted thickness deviates, the extrusion equipment parameters can be quickly adjusted based on the preset strategy, and an adjustment signal can be generated and transmitted to the equipment to correct the production deviation in time. If the thickness meets the requirements, an extrusion signal can also be quickly generated to maintain production, greatly reducing the generation of defective products caused by monitoring and feedback delay, significantly improving the real-time monitoring and dynamic control capability of the production process, and guaranteeing the efficient and stable operation of lithium battery diaphragm production.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of lithium battery separator, in particular to a lithium battery separator process dynamic optimization method and system. BACKGROUND

[0002] In the field of lithium batteries, with the continuous progress of science and technology, lithium batteries have been widely used in modern society due to their high energy density, long cycle life and other significant advantages. From daily life such as smart phones, tablet computers and other portable electronic devices, to the field of transportation such as electric vehicles and electric bicycles, to the field of energy storage such as large-scale energy storage power stations, lithium batteries play an irreplaceable role. As a key component inside the lithium battery, the lithium battery separator plays an important role in isolating the positive and negative electrodes, preventing short circuits and allowing lithium ions to pass freely, and its performance directly affects the safety, charging and discharging efficiency, cycle life and other core indicators of the lithium battery.

[0003] In the traditional production process of lithium battery separator, the main concern is the adjustment of the extrusion equipment parameters. The operator usually sets the equipment parameters of the extruder according to past experience, but only relying on experience when setting the extrusion equipment parameters does not fully consider the real-time changes of environmental factors, making it difficult to accurately control the thickness of the initial base film. This makes the thickness of the produced base film may deviate from the thickness requirement range, thereby affecting the final quality of the lithium battery separator. SUMMARY

[0004] In order to improve the quality of the generated lithium battery separator, the present application provides a lithium battery separator process dynamic optimization method and system.

[0005] In a first aspect, the present application provides a lithium battery separator process dynamic optimization method, which adopts the following technical solution:

[0006] A lithium battery separator process dynamic optimization method, comprising:

[0007] Obtain the extrusion equipment parameters corresponding to the current extrusion process, the raw material information and the thickness requirement range, and obtain the current environmental temperature and humidity corresponding to the current extrusion process, the raw material information including the raw material addition amount and the raw material parameters, the raw material parameters including the flow index and the additive index;

[0008] Determine the influence degree of the current environmental temperature and humidity on the thickness of the initial base film, the initial base film being the film produced by the current extrusion process;

[0009] Based on the extrusion equipment parameters, the raw material information, the current environmental temperature and humidity, and the influence degree, predict the predicted thickness of the initial base film, and determine whether the predicted thickness is within the thickness requirement range;

[0010] if the predicted thickness is not within the thickness requirement range, adjusting the extrusion equipment parameters based on the predicted thickness, and generating an adjustment signal based on the adjusted extrusion equipment parameters;

[0011] if the predicted thickness is within the thickness requirement range, generating an extrusion signal based on the extrusion equipment parameters.

[0012] By adopting the above technical solution, by real-time acquisition of key data such as extrusion equipment parameters, raw material information, and environmental temperature and humidity, the timeliness of the data is ensured. In the process of determining the influence degree of environmental temperature and humidity and predicting the predicted thickness of the base film, the data can be quickly processed and the result can be obtained. Once the predicted thickness deviates, the extrusion equipment parameters can be quickly adjusted based on the preset strategy, and an adjustment signal can be generated and transmitted to the equipment to correct the production deviation in time, so as to improve the quality of the generated lithium battery separator. If the thickness meets the requirements, an extrusion signal can also be quickly generated to maintain production, greatly reducing the production of defective products caused by monitoring and feedback delay, significantly improving the real-time monitoring and dynamic control capability of the production process, and ensuring the efficient and stable operation of lithium battery separator production.

[0013] In a possible implementation manner, determining the influence degree of the current environmental temperature and humidity on the thickness of the initial base film comprises:

[0014] acquiring historical extrusion data, the historical extrusion data comprising historical extrusion equipment parameters, historical raw material information, historical environmental temperature and humidity, and historical thickness corresponding to each historical extrusion process, the historical thickness being the thickness of the initial base film generated in the historical extrusion process;

[0015] filtering a plurality of groups of target historical extrusion data from the historical extrusion data, and establishing a regression model corresponding to each group of target historical extrusion data, each target historical extrusion data in the group of target historical extrusion data corresponding to different historical environmental temperature and humidity;

[0016] determining a temperature influence curve and a humidity influence curve based on a plurality of the regression models, the temperature influence curve being a curve of influence coefficient changing with temperature, and the humidity influence curve being a curve of influence coefficient changing with humidity;

[0017] determining the influence degree of the current environmental temperature and humidity on the thickness of the initial base film based on the temperature influence curve and the humidity influence curve.

[0018] In a possible implementation manner, predicting the predicted thickness of the initial base film based on the extrusion equipment parameters, the raw material information, the current environmental temperature and humidity, and the influence degree comprises:

[0019] determining an initial thickness corresponding to the raw material information based on the extrusion equipment parameters;

[0020] obtaining an optimal ambient temperature and humidity corresponding to the current extrusion process;

[0021] determining a temperature influence coefficient corresponding to a current ambient temperature and a humidity influence coefficient corresponding to a current ambient humidity based on the optimal ambient temperature and humidity, the current ambient temperature and humidity, and the influence degree;

[0022] predicting a predicted thickness of the initial base film based on the initial thickness, the temperature influence coefficient, and the humidity influence coefficient.

[0023] In a possible implementation, the extrusion equipment parameters include a die exit cross-sectional area, a pulling speed, and a volume of extruded melt per unit time, and the determining of the initial thickness corresponding to the raw material information based on the extrusion equipment parameters includes:

[0024] calculating a product of the die exit cross-sectional area and the pulling speed to obtain a target product, and calculating a ratio of the volume of extruded melt per unit time to the target product to obtain a first thickness;

[0025] determining a first correction amount corresponding to the flow index and a second correction amount corresponding to the additive index, and determining a comprehensive correction amount;

[0026] determining a second thickness corresponding to the raw material information based on the first thickness, the first correction amount, the second correction amount, and the comprehensive correction amount, and determining the second thickness as the initial thickness corresponding to the raw material information.

[0027] In a possible implementation, the determining of the first correction amount corresponding to the flow index and the second correction amount corresponding to the additive index, and the determining of the comprehensive correction amount include:

[0028] calculating a historical ideal thickness corresponding to each historical extrusion process;

[0029] establishing a basic relationship model, the basic relationship model being wherein T is a historical thickness, is a historical ideal thickness, MI is a flow index, and AI is an additive index;

[0030] training the basic relationship model based on the historical extrusion data to obtain a first function relationship and a second function relationship, and determining a first correction amount corresponding to the first function relationship and a second correction amount corresponding to the second function relationship, the first function relationship being a function relationship between the flow index and a thickness change amount, the second function relationship being a function relationship between the additive index and the thickness change amount, and the thickness change amount being a difference between the historical thickness and the historical ideal thickness.

[0031] determine an interaction degree between the first correction amount and the second correction amount to obtain a comprehensive correction amount.

[0032] In a possible implementation, the extrusion device parameters are adjusted based on the predicted thickness, including:

[0033] a ratio between the predicted thickness and a thickness median value is calculated to obtain a deviation ratio, the thickness median value being a median value corresponding to a thickness requirement range;

[0034] the adjustment strategy is determined based on the deviation ratio, the adjustment strategy including an adjustment parameter and an adjustment parameter amount;

[0035] the extrusion device parameters are adjusted based on the adjustment strategy.

[0036] In a possible implementation, the adjustment strategy is determined based on the deviation ratio, including:

[0037] a direction of adjustment is determined, and it is determined whether the deviation ratio belongs to a first preset deviation ratio threshold range;

[0038] if the deviation ratio belongs to the first preset deviation ratio threshold range, it is determined that the adjustment parameter is a volume of extruded melt per unit time, a first adjusted volume of extruded melt per unit time is determined based on a volume of extruded melt per unit time corresponding to a current time, the predicted thickness and the thickness median value, an adjustment parameter amount is obtained based on the direction of adjustment and the first adjusted volume of extruded melt per unit time, and the adjustment strategy is determined based on the adjustment parameter amount and the adjustment parameter;

[0039] if the deviation ratio does not belong to the first preset deviation ratio threshold range and belongs to a second preset deviation ratio threshold range, it is determined that the adjustment parameter is a die exit cross-sectional area, a first adjusted die exit cross-sectional area is determined based on a die exit cross-sectional area corresponding to the current time, the predicted thickness and the thickness median value, an adjustment parameter amount is obtained based on the direction of adjustment and the first adjusted die exit cross-sectional area, and the adjustment strategy is determined based on the adjustment parameter amount and the adjustment parameter;

[0040] if the deviation ratio does not belong to the second preset deviation ratio threshold range, it is determined that the adjustment parameter is the die exit cross-sectional area and the volume of extruded melt per unit time, a second adjusted volume of extruded melt per unit time and a second adjusted die exit cross-sectional area are determined through an iterative algorithm, an adjustment parameter amount is obtained based on the direction of adjustment, the second adjusted volume of extruded melt per unit time and the second adjusted die exit cross-sectional area, and the adjustment strategy is determined based on the adjustment parameter amount and the adjustment parameter.

[0041] In a second aspect, the application provides a lithium battery separator process dynamic optimization system, which adopts the following technical scheme:

[0042] A lithium battery separator process dynamic optimization system, characterized in that it comprises:

[0043] A lithium battery separator process dynamic optimization device.

[0044] An electronic device configured to perform the lithium battery separator process dynamic optimization method of any one of claims 1-7.

[0045] In a possible implementation, the lithium battery separator process dynamic optimization device comprises:

[0046] An acquisition module configured to acquire extrusion equipment parameters corresponding to a current extrusion process, raw material information, and a thickness requirement range, and to acquire current environmental temperature and humidity corresponding to the current extrusion process, wherein the raw material information comprises raw material addition amount and raw material parameters, and the raw material parameters comprise flow index and additive index.

[0047] A determination module configured to determine an influence degree of the current environmental temperature and humidity on the thickness of an initial base film, wherein the initial base film is a film generated by the current extrusion process.

[0048] A prediction module configured to predict a predicted thickness of the initial base film based on the extrusion equipment parameters, the raw material information, the current environmental temperature and humidity, and the influence degree, and to determine whether the predicted thickness is within the thickness requirement range.

[0049] An adjustment module configured to, if the predicted thickness is not within the thickness requirement range, adjust the extrusion equipment parameters based on the predicted thickness, and generate an adjustment signal based on the adjusted extrusion equipment parameters.

[0050] A generation module configured to, if the predicted thickness is within the thickness requirement range, generate an extrusion signal based on the extrusion equipment parameters.

[0051] In a possible implementation, the electronic device comprises:

[0052] At least one processor;

[0053] A memory;

[0054] At least one application program, wherein the at least one application program is stored in the memory and configured to be executed by the at least one processor, and the at least one application program is configured to perform the method of any one of the above first aspect.

[0055] In a third aspect, the application provides a computer-readable storage medium, which adopts the following technical scheme:

[0056] A computer readable storage medium comprising a computer program stored therein, which is loadable into a processor and causes the execution of the method according to any one of the preceding claims.

[0057] In summary, the present application includes the following beneficial technical effects:

[0058] By acquiring key data such as extrusion equipment parameters, raw material information, and environmental temperature and humidity in real time, the timeliness of the data is ensured. In the process of determining the influence degree of environmental temperature and humidity and predicting the expected thickness of the base film, the data can be quickly processed and the result can be obtained. Once the expected thickness deviates, the extrusion equipment parameters can be quickly adjusted based on the preset strategy, and an adjustment signal can be generated and transmitted to the equipment to timely correct the production deviation, thereby improving the quality of the generated lithium battery separator. If the thickness meets the requirements, the extrusion signal can also be quickly generated to maintain production, greatly reducing the generation of defective products caused by monitoring and feedback delays, significantly improving the real-time monitoring and dynamic control capability of the production process, and ensuring the efficient and stable operation of lithium battery separator production. BRIEF DESCRIPTION OF DRAWINGS

[0059] Figure 1 is a flowchart of a lithium battery separator process dynamic optimization method provided by an embodiment of the present application;

[0060] Figure 2 is a block diagram of a lithium battery separator process dynamic optimization system provided by an embodiment of the present application;

[0061] Figure 3 is a block diagram of a lithium battery separator process dynamic optimization device provided by an embodiment of the present application;

[0062] Figure 4 is a schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0063] The following will be described in conjunction with the accompanying drawings of the embodiments of the present application. - the accompanying drawings Figure 1 - the accompanying drawings Figure 4 The present application will be further described in detail.

[0064] To make the purposes, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0065] For the convenience of understanding the technical solutions proposed in the present application, first of all, several elements to be introduced in the description of the present application are introduced. It should be understood that the following introduction is only for the convenience of understanding these elements in order to understand the content of the embodiments of the present application, and does not necessarily cover all possible cases.

[0066] The lithium battery separator is an inner layer component of the lithium battery. In the structure of the lithium battery, the separator is one of the key inner layer components. The performance of the separator determines the interface structure, internal resistance, etc. of the battery, and directly affects the capacity, cycle and safety performance, etc. of the battery. The separator with excellent performance plays an important role in improving the comprehensive performance of the battery. The main function of the separator is to separate the positive and negative electrodes of the battery to prevent short circuit caused by the contact of the two electrodes. In addition, the separator also has the function of allowing the electrolyte ions to pass through.

[0067] In the production process of the lithium battery separator, the raw material is first melted and extruded by an extruder to form an initial base film. Then, the initial base film is stretched or coated. Before the extrusion process, the parameters of the extrusion equipment are generally set, and then the extrusion equipment is started to generate the initial base film.

[0068] Referring to Figure 1 The embodiments of the present application provide a lithium battery separator process dynamic optimization method, which is executed by an electronic device. The method comprises:

[0069] In step S101, the extrusion equipment parameters corresponding to the current extrusion process, the raw material information and the thickness requirement range are obtained, and the current environment temperature and humidity corresponding to the current extrusion process are obtained.

[0070] The raw material information includes the raw material addition amount and the raw material parameters, and the raw material parameters include the flow index and the additive index. Specifically, the raw material addition amount is the specific quantity of various raw materials added in the production process, and different addition amounts will affect the performance and production process of the separator. The flow index is an index for measuring the flow performance of polyolefin and other raw materials in the molten state. The higher the value, the better the flowability, which has an important influence on the melt flow and base film forming in the extrusion process. The additive index is an index for reflecting the comprehensive influence of the characteristics and content of the additive on the performance of the raw material. The additive can improve the thermal stability, mechanical properties, etc. of the separator, and the change of the index will change the processing and product performance of the raw material.

[0071] Specifically, the electronic device obtains data in real time by connecting with sensors and management systems on the production line. Specifically, the electronic device is connected with sensors built in the extrusion equipment to obtain extrusion equipment parameters such as extrusion temperature, pressure, die gap, and pulling speed; obtains raw material information such as raw material addition amount, flow index, and additive index from the raw material management system; collects the environmental temperature and humidity of the production workshop through the temperature and humidity sensor; at the same time, the electronic device reads the thickness requirement range of the lithium battery separator from the production task work order or the quality management system. The thickness requirement range is the allowable fluctuation interval of the product thickness according to the design standard and use requirement of the lithium battery separator, and only the separator within the range meets the quality requirement.

[0072] Step S102, determining the influence degree of the current environmental temperature and humidity on the thickness of the initial base film.

[0073] The initial base film is the film generated in the current extrusion process.

[0074] Specifically, the pre-established environmental temperature and humidity-thickness influence model can be called, which is obtained based on a large amount of historical production data through data analysis and machine learning algorithm training. The electronic device inputs the current collected environmental temperature and humidity data into the model, and the environmental temperature and humidity-thickness model outputs the influence coefficient of the current environmental temperature and humidity on the thickness of the initial base film after calculation, which represents the influence degree. For example, the greater the influence coefficient, the more significant the influence of the environmental temperature and humidity on the thickness of the base film. The influence degree is an index quantitatively describing the change of the current environmental temperature and humidity on the thickness of the initial base film.

[0075] More specifically, in the embodiment, determining the influence degree of the current environmental temperature and humidity on the thickness of the initial base film includes: obtaining historical extrusion data, the historical extrusion data including historical extrusion equipment parameters, historical raw material information, historical environmental temperature and humidity, and historical thickness corresponding to each historical extrusion process, the historical thickness being the thickness of the initial base film generated in the historical extrusion process; selecting a plurality of groups of target historical extrusion data from the historical extrusion data, and establishing a regression model corresponding to each group of target historical extrusion data, the historical environmental temperature and humidity corresponding to each target historical extrusion data in the target historical extrusion data group being different; determining a temperature influence curve and a humidity influence curve based on the plurality of regression models, the temperature influence curve being an influence coefficient curve changing with temperature, and the humidity influence curve being an influence coefficient curve changing with humidity; determining the influence degree of the current environmental temperature and humidity on the thickness of the initial base film based on the temperature influence curve and the humidity influence curve.

[0076] Specifically, all lithium battery separator extrusion records in a certain period (for example, 12 months) are called from the production database through the data interface, and each historical extrusion record contains: historical extrusion equipment parameters, historical raw material information, historical environment temperature and humidity, and corresponding historical thickness. The obtained historical extrusion data is preliminarily cleaned to eliminate outliers, and finally a data set containing multiple valid data is formed to obtain historical extrusion data.

[0077] Further, based on the historical extrusion equipment parameters, historical raw material information, historical environment temperature and humidity, and historical thickness of the historical extrusion data, historical equipment parameter consistent and historical raw material information consistent but historical environment temperature and humidity different historical extrusion sub-data are extracted from the historical extrusion data as a target historical extrusion data group, so as to obtain multiple target historical extrusion data groups. Each data in each target extrusion data group is a target historical extrusion data.

[0078] Further, for multiple target historical extrusion data groups, a multiple linear regression model can be used to fit the relationship between thickness and equipment parameters and raw material parameters. Specifically, the regression model is established as historical thickness=A0+A1 historical extrusion equipment parameters+A2 historical raw material information+A3 historical environment temperature+A4 historical environment humidity, wherein A0, A1, A2, A3 and A4 are regression coefficients. The influence coefficients of temperature and humidity on thickness (i.e. the coefficients of temperature and humidity variables in the regression equation) are extracted from each regression model, and the influence coefficients of each temperature and humidity interval are plotted into a scatter plot. The relationship between the temperature influence coefficient and the temperature and the relationship between the humidity influence coefficient and the humidity are fitted by a quadratic polynomial, respectively, to obtain two smooth curves: the temperature influence coefficient=a1 T 2 +b1 T+c1, and the humidity influence coefficient=a2 H 2 +b2 H+c2.

[0079] Further, the current temperature is substituted into the temperature influence curve equation to calculate the temperature influence coefficient, and the current humidity is substituted into the humidity influence curve equation to obtain the humidity influence coefficient. Combined with the average thickness of the historical data, the comprehensive influence value of the current temperature and humidity on the thickness is calculated to obtain the influence degree of the current environment temperature and humidity on the thickness of the initial base film.

[0080] Step S103, based on the extrusion equipment parameters, raw material information, current environment temperature and humidity, and influence degree, the predicted thickness of the initial base film is predicted, and it is judged whether the predicted thickness is within the thickness requirement range.

[0081] Specifically, the base film thickness prediction model can be used for calculation. The base film thickness prediction model integrates the principles of fluid mechanics, the relationship formula between the material characteristics and the base film thickness, and the parameter calibration combined with historical production data. The electronic device takes the obtained extrusion equipment parameters, material information, current environmental temperature and humidity, and influence degree data as model inputs, and the model outputs the predicted thickness of the initial base film after complex calculation and analysis. Then, after the predicted thickness, the predicted thickness can be judged to determine whether the current extrusion equipment parameters are feasible. Specifically, the electronic device compares the predicted thickness with the thickness requirement range obtained from the production task to determine whether the predicted thickness falls within the range.

[0082] More specifically, in the present embodiment, based on the extrusion equipment parameters, material information, current environmental temperature and humidity, and influence degree, the predicted thickness of the initial base film is predicted, including: based on the extrusion equipment parameters, determining the initial thickness corresponding to the material information; obtaining the optimal environmental temperature and humidity corresponding to the current extrusion process; based on the optimal environmental temperature and humidity, the current environmental temperature and humidity, and the influence degree, determining the temperature influence coefficient corresponding to the current environmental temperature and the humidity influence coefficient corresponding to the current environmental humidity; based on the initial thickness, the temperature influence coefficient and the humidity influence coefficient, predicting the predicted thickness of the initial base film.

[0083] After obtaining the extrusion equipment parameters, the thickness prediction model based on the principles of fluid mechanics and historical data can be called to predict the initial thickness corresponding to the current material information, and the optimal environmental parameters corresponding to the current production task can be queried from the process knowledge base.

[0084] Further, according to the obtained optimal temperature and humidity (such as 23°C, 50% RH) and the current environmental temperature and humidity (such as 25°C, 45% RH), the temperature and humidity influence curve is calculated. Specifically, the current temperature is substituted into the temperature influence curve equation to calculate the temperature influence coefficient. Similarly, the current humidity is substituted into the humidity influence curve equation to calculate the humidity influence coefficient. Further, after obtaining the initial thickness, the temperature influence coefficient and the humidity influence coefficient, the predicted thickness of the initial base film can be calculated according to the formula: predicted thickness = initial thickness + humidity influence coefficient (current humidity - optimal humidity) + temperature influence coefficient (current temperature - optimal humidity).

[0085] More specifically, the extrusion equipment parameters can include a die exit cross-sectional area, a haul-off speed, and an extrusion melt volume per unit time, based on the extrusion equipment parameters, determining the initial thickness corresponding to the raw material information includes: calculating the product of the die exit cross-sectional area and the haul-off speed to obtain a target product, and calculating the ratio of the extrusion melt volume per unit time to the target product to obtain a first thickness; determining a first correction amount corresponding to the flow index and a second correction amount corresponding to the additive index, and determining a comprehensive correction amount; based on the first thickness, the first correction amount, the second correction amount, and the comprehensive correction amount, determining a second thickness corresponding to the raw material information, and determining the second thickness as the initial thickness corresponding to the raw material information.

[0086] Since the raw material melt generally flows uniformly at the die exit, the die exit cross-sectional area and the haul-off speed can be multiplied to obtain a target product, and the extrusion melt volume per unit time can be divided by the target product to obtain a first thickness.

[0087] Further, since the flow index and the additive index of the raw material will both affect the thickness of the initial base film to a certain extent, a first correction amount corresponding to the flow index can be determined, and a second correction amount corresponding to the additive index can be determined. At the same time, considering the interaction of the flow index and the additive index, a comprehensive correction amount can be calculated, and the first thickness and each correction amount can be superimposed to calculate a second thickness, which is the initial thickness.

[0088] More specifically, determining the first correction amount corresponding to the flow index and the second correction amount corresponding to the additive index, and determining the comprehensive correction amount includes: calculating a historical ideal thickness corresponding to each historical extrusion process; establishing a basic relationship model, the basic relationship model is wherein T is a historical thickness, is a historical ideal thickness, MI is a flow index, and AI is an additive index; based on the historical extrusion data, the basic relationship model is trained to obtain a first function relationship and a second function relationship, and a first correction amount corresponding to the first function relationship and a second correction amount corresponding to the second function relationship are determined, the first function relationship is a function relationship between the flow index and the thickness change amount, the second function relationship is a function relationship between the additive index and the thickness change amount, and the thickness change amount is the difference between the historical thickness and the historical ideal thickness; determining the interaction degree between the first correction amount and the second correction amount to obtain the comprehensive correction amount.

[0089] Specifically, the equipment parameters (die exit cross-sectional area, haul-off speed, and extrusion melt volume per unit time) of each historical extrusion process are extracted from the historical extrusion data and substituted into the formula: historical ideal thickness = historical extrusion melt volume per unit time / (historical die exit cross-sectional area the historical ideal thickness corresponding to each historical extrusion process is obtained.

[0090] Further, the following mathematical model is constructed to describe the thickness variation law: , the thickness variation amount AT of each historical data is calculated. 理想 , and the corresponding MI and AI values are extracted. Specifically, the relationship between AT and MI, AI can be fitted using polynomial regression: AT MI =c1MI+c2MI 2 +c3MI 3 AT AI =d1AI+d2AI 2 +d3AI 3 , and the coefficients ci and di are solved by the least square method to obtain the first function relationship and the second function relationship. Specifically, the process of determining the correction amount can be: substituting the current flow index MI 当前 into the first function relationship to obtain the first correction amount; substituting the current additive index AI into the second function relationship to obtain the second correction amount.

[0091] Further, the data points in which the flow index and the additive index deviate from the standard values at the same time (for example, MI>3.2 and AI<1.9) are screened out from the historical data, and a multiple regression model is used to fit the influence of the interaction term on the thickness: AT 交互 =k 交互 (MI-MI0) (AI-AI0), where MI0 and AI0 are standard values, k 交互 is the interaction coefficient, which is solved by the least square method.

[0092] In step S104, if the predicted thickness is not within the thickness requirement range, the extrusion equipment parameters are adjusted based on the predicted thickness, and an adjustment signal is generated based on the adjusted extrusion equipment parameters.

[0093] When it is judged that the predicted thickness does not meet the requirements, the parameter adjustment strategy can be started. The electronic device selects to adjust the parameters such as the die gap, the extrusion pressure or the pulling speed according to the size of the gap between the predicted thickness and the thickness requirement range, the characteristics of the raw materials, the characteristics of the equipment adjustment, and other factors. For example, if the predicted thickness is greater than the requirement range and the gap is large, the die gap is preferentially reduced; if the gap is small, the extrusion pressure is fine-tuned. The adjusted extrusion equipment parameter value can be calculated through the pre-set calculation formula and rule, and the adjusted parameter is converted into a corresponding electrical signal or digital signal, i.e. an adjustment signal, which is sent to the control system of the extrusion equipment to realize automatic adjustment of the equipment parameters.

[0094] Specifically, in the embodiment, the extrusion equipment parameters are adjusted based on the predicted thickness, including: calculating a ratio between the predicted thickness and a thickness median value, to obtain a deviation ratio, the thickness median value being a median value corresponding to the thickness requirement range; determining an adjustment strategy based on the deviation ratio, the adjustment strategy including an adjustment parameter and an adjustment parameter amount; and adjusting the extrusion equipment parameters based on the adjustment strategy.

[0095] After obtaining the predicted thickness and the thickness requirement range, a median value of the thickness requirement range can be calculated as a thickness median value, and the predicted thickness is divided by the thickness median value to obtain a deviation ratio, and the adjustment parameter and the adjustment parameter amount are determined according to the deviation ratio. The adjustment parameter can be at least one of the die exit cross-sectional area and the extrusion melt volume per unit time.

[0096] After obtaining the adjustment parameter and the adjustment parameter amount, the adjustment parameter amount can be converted into a control signal (such as a 4-20 mA current signal or a digital instruction) and sent to the die gap adjusting mechanism.

[0097] More specifically, in the embodiment, the adjustment strategy is determined based on the deviation ratio, including: determining an adjustment direction, and judging whether the deviation ratio belongs to a first preset deviation ratio threshold range; if the deviation ratio belongs to the first preset deviation ratio threshold range, determining that the adjustment parameter is the extrusion melt volume per unit time, and determining a first adjusted extrusion melt volume per unit time based on the extrusion melt volume per unit time corresponding to the current time, the predicted thickness, and the thickness median value, obtaining the adjustment parameter amount based on the adjustment direction and the first adjusted extrusion melt volume per unit time, and determining the adjustment strategy based on the adjustment parameter amount and the adjustment parameter; if the deviation ratio does not belong to the first preset deviation ratio threshold range and belongs to a second preset deviation ratio threshold range, determining that the adjustment parameter is the die exit cross-sectional area, and determining a first adjusted die exit cross-sectional area based on the die exit cross-sectional area corresponding to the current time, the predicted thickness, and the thickness median value, obtaining the adjustment parameter amount based on the adjustment direction and the first adjusted die exit cross-sectional area, and determining the adjustment strategy based on the adjustment parameter amount and the adjustment parameter; and if the deviation ratio does not belong to the second preset deviation ratio threshold range, determining that the adjustment parameter is the die exit cross-sectional area and the extrusion melt volume per unit time, and determining a second adjusted extrusion melt volume per unit time and a second adjusted die exit cross-sectional area by an iterative algorithm, obtaining the adjustment parameter amount based on the adjustment direction, the second adjusted extrusion melt volume per unit time, and the second adjusted die exit cross-sectional area, and determining the adjustment strategy based on the adjustment parameter amount and the adjustment parameter.

[0098] The adjustment direction includes "increasing thickness" or "decreasing thickness". Two preset deviation ratio threshold ranges are preset, and the minimum value of the first preset deviation ratio threshold range is greater than the minimum value of the second preset deviation threshold range (the minimum value in the two ranges), for example: the first preset deviation ratio threshold range is 0.97≤deviation ratio≤1.03; and the second preset deviation ratio threshold range is 0.94≤deviation ratio<0.97 or 1.03<deviation ratio≤1.06.

[0099] Specifically, the adjustment direction is calculated: if the deviation ratio<1 (the predicted thickness<the thickness median)→the adjustment direction is "increasing thickness"; if the deviation ratio>1 (the predicted thickness>the thickness median)→the adjustment direction is "decreasing thickness", and it is judged whether the deviation ratio belongs to the first preset deviation ratio threshold range.

[0100] Since the adjustment of the die outlet cross-sectional area is suitable for large adjustment, and the adjustment of the extrusion melt volume per unit time is suitable for small adjustment, if the deviation ratio belongs to the first preset deviation ratio threshold range, the adjustment parameter is determined to be the extrusion melt volume per unit time, and the target extrusion melt volume is calculated according to the formula: target extrusion melt volume=current extrusion melt volume the thickness median / the predicted thickness, the target extrusion melt volume is calculated, and the difference between the target extrusion melt volume and the current extrusion melt volume is calculated to obtain the adjustment parameter amount (a positive number means increasing, and a negative number means decreasing), so as to obtain the adjustment strategy of the adjustment parameter being the extrusion melt volume per unit time and the adjustment parameter amount. It is worth noting that since there may be a certain gap between the respective device parameters of the extruders that do not pass, the extrusion melt volume per unit time can be adjusted by changing the screw speed (the screw speed is proportional to the extrusion melt volume per unit time), or the extrusion melt volume per unit time of the extruder can be adjusted in other ways. In this embodiment, only the adjusted extrusion melt volume per unit time is given, and the extrusion melt volume per unit time can be adjusted according to a manner well known to those skilled in the art, and the present embodiment does not limit this.

[0101] If the deviation ratio does not belong to the first preset deviation ratio threshold range, it is judged whether the deviation ratio belongs to the second preset deviation ratio threshold range, if the deviation ratio belongs to the second preset deviation ratio threshold range, the adjustment parameter is determined to be the die outlet cross-sectional area, and the target die outlet cross-sectional area is calculated according to the formula: target die outlet cross-sectional area=current die outlet cross-sectional area The target die exit cross-sectional area is calculated by dividing the median thickness by the expected thickness. The difference between the target and current die exit cross-sectional areas is then calculated to determine the adjustment parameter (positive values ​​indicate an increase, negative values ​​indicate a decrease). This yields the adjustment strategy, which uses the die exit cross-sectional area as the adjustment parameter and the adjustment amount. Specifically, the die exit cross-sectional area of ​​the extruder can be adjusted by changing the die clearance (the die exit area is proportional to the die clearance; die exit cross-sectional area = die width). The die head gap (where the die head width is a fixed value) is given in this embodiment. Only the adjusted die head exit cross-sectional area is given. The die head exit cross-sectional area can be adjusted in a way known to those skilled in the art. This application embodiment does not limit this.

[0102] If the deviation ratio exceeds the second range, the adjustment parameters are determined to be the die exit cross-sectional area and the volume of extruded melt per unit time, i.e., joint adjustment. Specifically, the iteration parameters are initialized with the current parameter value, i.e., the initial search point is set to the current parameter value (Q). 当前 A 当前 The objective function is to minimize the thickness error: f(Q, A) = Where Q is the extruded melt volume, A is the die exit cross-sectional area, and v is the traction speed. Furthermore, the gradient descent method can be used, with the basic constraint: Q∈[Q... min Q max ],A∈[A min A max In each iteration, Q and A are adjusted to make f(Q, A) approach 0. After multiple iterations, the optimal solution Q is obtained. 目标 and A 目标 .

[0103] Step S105: If the expected thickness is within the required range, an extrusion signal is generated based on the extrusion equipment parameters.

[0104] When the expected thickness is confirmed to be within the specified thickness requirement range, it indicates that the current extrusion equipment parameters are set reasonably and can produce an initial base film that meets quality requirements. At this point, the current extrusion equipment parameters can be encoded and encapsulated to generate an extrusion signal. This signal contains all the equipment parameter information for normal operation. The electronic equipment sends the extrusion signal to the extrusion equipment's control system, instructing the equipment to continue stable operation according to the current parameters to ensure the continuity of the production process and the stability of product quality.

[0105] The embodiment of the application provides a lithium battery diaphragm process dynamic optimization method, which acquires key data such as extrusion equipment parameters, raw material information, and environmental temperature and humidity in real time, ensures the timeliness of the data, quickly processes the data and obtains results in the process of determining the influence degree of the environmental temperature and humidity and predicting the predicted thickness of the base film, and quickly adjusts the extrusion equipment parameters based on a preset strategy and generates an adjustment signal to be transmitted to the equipment once the predicted thickness deviates, so as to timely correct the production deviation and improve the quality of the generated lithium battery diaphragm; if the thickness meets the requirements, the extrusion signal can also be quickly generated to maintain the production, greatly reduces the generation of defective products caused by monitoring and feedback delays, significantly improves the real-time monitoring and dynamic control capability of the production process, and guarantees the efficient and stable operation of the lithium battery diaphragm production.

[0106] Referring to Figure 2 , the lithium battery diaphragm formula dynamic optimization system 2 can specifically include a lithium battery diaphragm formula dynamic optimization device 21 and an electronic device 22.

[0107] More specifically, referring to Figure 3 , the lithium battery diaphragm formula dynamic optimization device 21 can specifically include a front-end data acquisition module 211, a first analysis module 212, a back-end data acquisition module 213, a second analysis module 214, and a fault judgment module 215, wherein:

[0108] A lithium battery diaphragm process dynamic optimization device 21 includes:

[0109] The acquisition module 211 is configured to acquire extrusion equipment parameters corresponding to a current extrusion process, raw material information, and a thickness requirement range, and acquire current environmental temperature and humidity corresponding to the current extrusion process, wherein the raw material information includes a raw material addition amount and raw material parameters, and the raw material parameters include a flow index and an additive index.

[0110] The determination module 212 is configured to determine an influence degree of the current environmental temperature and humidity on the thickness of an initial base film, wherein the initial base film is a film generated by the current extrusion process.

[0111] The prediction module 213 is configured to predict a predicted thickness of the initial base film based on the extrusion equipment parameters, the raw material information, the current environmental temperature and humidity, and the influence degree, and determine whether the predicted thickness is within the thickness requirement range.

[0112] The adjustment module 214 is configured to adjust the extrusion equipment parameters based on the predicted thickness if the predicted thickness is not within the thickness requirement range, and generate an adjustment signal based on the adjusted extrusion equipment parameters.

[0113] The generation module 215 is configured to generate an extrusion signal based on the extrusion equipment parameters if the predicted thickness is within the thickness requirement range.

[0114] In a possible implementation of the embodiment, when determining the influence degree of the current environment temperature and humidity on the thickness of the initial base film, the determining module 212 is specifically configured to:

[0115] obtain historical extrusion data, the historical extrusion data including historical extrusion device parameters, historical raw material information, historical environment temperature and humidity, and historical thickness corresponding to each historical extrusion process, the historical thickness being the thickness of the initial base film generated by the historical extrusion process;

[0116] select a plurality of groups of target historical extrusion data from the historical extrusion data, and establish a regression model corresponding to each group of target historical extrusion data, the historical environment temperature and humidity corresponding to each target historical extrusion data in the group of target historical extrusion data being different;

[0117] based on the plurality of regression models, determine a temperature influence curve and a humidity influence curve, the temperature influence curve being a curve of the influence coefficient changing with the temperature, and the humidity influence curve being a curve of the influence coefficient changing with the humidity;

[0118] based on the temperature influence curve and the humidity influence curve, determine the influence degree of the current environment temperature and humidity on the thickness of the initial base film.

[0119] In a possible implementation of the embodiment, when predicting the predicted thickness of the initial base film based on the extrusion device parameters, the raw material information, the current environment temperature and humidity, and the influence degree, the predicting module 213 is specifically configured to:

[0120] based on the extrusion device parameters, determine an initial thickness corresponding to the raw material information;

[0121] obtain an optimal environment temperature and humidity corresponding to the current extrusion process;

[0122] based on the optimal environment temperature and humidity, the current environment temperature and humidity, and the influence degree, determine a temperature influence coefficient corresponding to the current environment temperature and a humidity influence coefficient corresponding to the current environment humidity;

[0123] based on the initial thickness, the temperature influence coefficient, and the humidity influence coefficient, predict the predicted thickness of the initial base film.

[0124] In a possible implementation of the embodiment, the extrusion device parameters include an outlet cross-sectional area of a die, a pulling speed, and a volume of extruded melt per unit time, and when determining the initial thickness corresponding to the raw material information based on the extrusion device parameters, the predicting module 213 is specifically configured to:

[0125] calculate a product of the outlet cross-sectional area of the die and the pulling speed to obtain a target product, and calculate a ratio of the volume of the extruded melt per unit time to the target product to obtain a first thickness;

[0126] determine a first correction quantity corresponding to the flow index and a second correction quantity corresponding to the additive index, and determine a comprehensive correction quantity;

[0127] determine a second thickness corresponding to the raw material information based on the first thickness, the first correction quantity, the second correction quantity, and the comprehensive correction quantity, and determine the second thickness as the initial thickness corresponding to the raw material information.

[0128] In a possible implementation of the embodiment, the prediction module 213, when determining the first correction quantity corresponding to the flow index and the second correction quantity corresponding to the additive index, and determining the comprehensive correction quantity, is specifically configured to:

[0129] calculate a historical ideal thickness corresponding to each historical extrusion process;

[0130] establish a basic relationship model, the basic relationship model being wherein T is the historical thickness, is the historical ideal thickness, MI is the flow index, and AI is the additive index;

[0131] train the basic relationship model based on the historical extrusion data, to obtain a first function relationship and a second function relationship, and determine a first correction quantity corresponding to the first function relationship and a second correction quantity corresponding to the second function relationship, the first function relationship being a function relationship between the flow index and a thickness change quantity, the second function relationship being a function relationship between the additive index and the thickness change quantity, and the thickness change quantity being a difference between the historical thickness and the historical ideal thickness;

[0132] determine an interaction degree between the first correction quantity and the second correction quantity, to obtain the comprehensive correction quantity.

[0133] In a possible implementation of the embodiment, the adjustment module 214, when adjusting the extrusion equipment parameters based on the predicted thickness, is specifically configured to:

[0134] calculate a ratio between the predicted thickness and a thickness median value, to obtain a deviation ratio, the thickness median value being a median value corresponding to a thickness requirement range;

[0135] determine an adjustment strategy based on the deviation ratio, the adjustment strategy including an adjustment parameter and an adjustment parameter quantity;

[0136] adjust the extrusion equipment parameters based on the adjustment strategy.

[0137] In a possible implementation of the embodiment, the adjustment module 214, when determining the adjustment strategy based on the deviation ratio, is specifically configured to:

[0138] determine an adjustment direction, and determine whether the deviation ratio belongs to a first preset deviation ratio threshold range;

[0139] If the deviation ratio belongs to the first preset deviation ratio threshold range, the adjustment parameter is determined as the extrusion melt volume per unit time, and based on the extrusion melt volume per unit time corresponding to the current time, the predicted thickness, and the thickness median value, a first adjusted extrusion melt volume per unit time is determined, and based on the adjustment direction and the first adjusted extrusion melt volume per unit time, an adjustment parameter amount is obtained, and based on the adjustment parameter amount and the adjustment parameter, an adjustment strategy is determined.

[0140] If the deviation ratio does not belong to the first preset deviation ratio threshold range and belongs to the second preset deviation ratio threshold range, the adjustment parameter is determined as the die outlet cross-sectional area, and based on the die outlet cross-sectional area corresponding to the current time, the predicted thickness, and the thickness median value, a first adjusted die outlet cross-sectional area is determined, and based on the adjustment direction and the first adjusted die outlet cross-sectional area, an adjustment parameter amount is obtained, and based on the adjustment parameter amount and the adjustment parameter, an adjustment strategy is determined.

[0141] If the deviation ratio does not belong to the second preset deviation ratio threshold range, the adjustment parameters are determined as the die outlet cross-sectional area and the extrusion melt volume per unit time, and the second adjusted extrusion melt volume per unit time and the second adjusted die outlet cross-sectional area are determined through an iterative algorithm, and based on the adjustment direction, the second adjusted extrusion melt volume per unit time, and the second adjusted die outlet cross-sectional area, an adjustment parameter amount is obtained, and based on the adjustment parameter amount and the adjustment parameter, an adjustment strategy is determined.

[0142] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0143] Referring to Figure 4 , the embodiments of the present application also introduce an electronic device from the perspective of a physical device, such as Figure 4 , as shown in Figure 4 , the electronic device 22 shown in the figure includes a processor 221 and a memory 223. Wherein, the processor 221 and the memory 223 are connected, such as through a bus 222. Optionally, the electronic device 22 can also include a transceiver 224. It should be noted that in actual application, the transceiver 224 is not limited to one, and the structure of the electronic device 22 does not constitute a limitation on the embodiments of the present application.

[0144] The processor 221 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic device, transistor logic device, hardware component or any combination thereof. It can implement or execute the various exemplary logical blocks, modules and circuits described in connection with the disclosure. The processor 221 can also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0145] The bus 222 can include a path for transmitting information between the above-mentioned components. The bus 222 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 222 can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, Figure 4 Only one thick line is used in the middle, but it does not mean that there is only one bus or one type of bus.

[0146] The memory 223 can be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, an optical disk storage (including a compact disk, a laser disk, an optical disk, a digital versatile disk, a Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer, but not limited thereto.

[0147] The memory 223 is configured to store application program codes for implementing the solutions of the present application, and the processor 221 is configured to execute the application program codes stored in the memory 223.

[0148] The electronic device includes, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a PMP (Portable Multimedia Player), a car terminal (e.g., a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like, and can also be a server or the like. Figure 4 The electronic device shown is merely an example and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0149] The embodiments of the present application provide a computer readable storage medium, which has stored thereon a computer program, and when the computer program is run on a computer, the computer can execute the corresponding content in the foregoing method embodiments.

[0150] It should be understood that, although each step in the flowchart of the accompanying drawings is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other sequences. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or sub-steps or stages of other steps.

[0151] The above is only some of the embodiments of the present application, and it should be noted that, for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A method for dynamic optimization of a lithium battery separator process, characterized in that, The method comprises the following steps: obtaining extrusion equipment parameters, raw material information and thickness requirement range corresponding to a current extrusion process, and obtaining current environmental temperature and humidity corresponding to the current extrusion process, wherein the raw material information comprises raw material addition amount and raw material parameters, and the raw material parameters comprise flow index and additive index; determining the influence degree of the current environmental temperature and humidity on the thickness of an initial base film, wherein the initial base film is a film generated by the current extrusion process; based on the extrusion equipment parameters, the raw material information, the current environmental temperature and humidity and the influence degree, predicting the expected thickness of the initial base film, and determining whether the expected thickness is within the thickness requirement range; if the expected thickness is not within the thickness requirement range, adjusting the extrusion equipment parameters based on the expected thickness, and generating an adjustment signal based on the adjusted extrusion equipment parameters; if the expected thickness is within the thickness requirement range, generating an extrusion signal based on the extrusion equipment parameters; adjusting the extrusion equipment parameters based on the expected thickness, comprising: calculating the ratio between the expected thickness and a thickness median value to obtain a deviation ratio, wherein the thickness median value is a median value corresponding to the thickness requirement range; determining an adjustment strategy based on the deviation ratio, wherein the adjustment strategy comprises an adjustment parameter and an adjustment parameter amount; adjusting the extrusion equipment parameters based on the adjustment strategy; determining the adjustment strategy based on the deviation ratio, comprising: determining an adjustment direction, and determining whether the deviation ratio belongs to a first preset deviation ratio threshold range; if the deviation ratio belongs to the first preset deviation ratio threshold range, determining that the adjustment parameter is the extrusion melt volume per unit time, determining a first adjusted extrusion melt volume per unit time based on the extrusion melt volume per unit time corresponding to the current time, the expected thickness and the thickness median value, obtaining the adjustment parameter amount based on the adjustment direction and the first adjusted extrusion melt volume per unit time, and determining the adjustment strategy based on the adjustment parameter amount and the adjustment parameter; if the deviation ratio does not belong to the first preset deviation ratio threshold range and belongs to a second preset deviation ratio threshold range, determining that the adjustment parameter is the die exit cross-sectional area, determining a first adjusted die exit cross-sectional area based on the die exit cross-sectional area corresponding to the current time, the expected thickness and the thickness median value, obtaining the adjustment parameter amount based on the adjustment direction and the first adjusted die exit cross-sectional area, and determining the adjustment strategy based on the adjustment parameter amount and the adjustment parameter; if the deviation ratio does not belong to the second preset deviation ratio threshold range, determining that the adjustment parameter is the die exit cross-sectional area and the extrusion melt volume per unit time, determining a second adjusted extrusion melt volume per unit time and a second adjusted die exit cross-sectional area through an iterative algorithm, obtaining the adjustment parameter amount based on the adjustment direction, the second adjusted extrusion melt volume per unit time and the second adjusted die exit cross-sectional area, and determining the adjustment strategy based on the adjustment parameter amount and the adjustment parameter.

2. The lithium battery separator process dynamic optimization method of claim 1, wherein, determining the influence degree of the current environmental temperature and humidity on the thickness of the initial base film, comprising: obtain historical extrusion data, the historical extrusion data including historical extrusion equipment parameters, historical raw material information, historical environment temperature and humidity, and historical thickness corresponding to each historical extrusion process, the historical thickness being a thickness of an initial base film generated by the historical extrusion process; screen a plurality of target historical extrusion data groups from the historical extrusion data, each target historical extrusion data in the target historical extrusion data group corresponding to different historical environment temperature and humidity; determine a temperature influence curve and a humidity influence curve based on the plurality of regression models, the temperature influence curve being an influence coefficient curve changing with temperature, and the humidity influence curve being an influence coefficient curve changing with humidity; determine an influence degree of the current environment temperature and humidity on the thickness of the initial base film based on the temperature influence curve and the humidity influence curve.

3. The lithium battery separator process dynamic optimization method of claim 2, wherein, predict the predicted thickness of the initial base film based on the extrusion equipment parameters, the raw material information, the current environment temperature and humidity, and the influence degree, including: determine an initial thickness corresponding to the raw material information based on the extrusion equipment parameters; obtain an optimal environment temperature and humidity corresponding to the current extrusion process; determine a temperature influence coefficient corresponding to the current environment temperature and a humidity influence coefficient corresponding to the current environment humidity based on the optimal environment temperature and humidity, the current environment temperature and humidity, and the influence degree; predict the predicted thickness of the initial base film based on the initial thickness, the temperature influence coefficient, and the humidity influence coefficient.

4. The lithium battery separator process dynamic optimization method of claim 3, wherein, The extrusion equipment parameters include a die exit cross-sectional area, a pulling speed, and a volume of extruded solution per unit time, wherein determining the initial thickness corresponding to the raw material information based on the extrusion equipment parameters includes: calculating a product of the die exit cross-sectional area and the pulling speed to obtain a target product, and calculating a ratio of the volume of extruded solution per unit time to the target product to obtain a first thickness; determining a first correction amount corresponding to the flow index and a second correction amount corresponding to the additive index, and determining a comprehensive correction amount; determining a second thickness corresponding to the raw material information based on the first thickness, the first correction amount, the second correction amount, and the comprehensive correction amount, and determining the second thickness as the initial thickness corresponding to the raw material information.

5. The lithium battery separator process dynamic optimization method of claim 4, wherein, The determination of the first correction amount corresponding to the flow index and the second correction amount corresponding to the additive index, and the determination of the comprehensive correction amount, include: calculating a historical ideal thickness corresponding to each historical extrusion process; establishing a base relationship model, the base relationship model being where T is the historical thickness, is the historical ideal thickness, MI is the flow index, and AI is the additive index; training the basic relationship model based on the historical extrusion data to obtain a first function relationship and a second function relationship, and determining a first correction amount corresponding to the first function relationship and a second correction amount corresponding to the second function relationship, the first function relationship being a function relationship between the flow index and the thickness change amount, the second function relationship being a function relationship between the additive index and the thickness change amount, and the thickness change amount being a difference between the historical thickness and the historical ideal thickness; Determine the degree of interaction between the first correction amount and the second correction amount to obtain a comprehensive correction amount.

6. A lithium battery separator process dynamic optimization system characterized by, Comprise: The lithium battery separator process dynamic optimization device; Electronic equipment, the electronic equipment is used for executing the lithium battery separator process dynamic optimization method of any one of claims 1-5.

7. The lithium battery separator process dynamic optimization system of claim 6, wherein, The lithium battery separator process dynamic optimization device comprises: An acquisition module is configured to acquire extrusion equipment parameters corresponding to a current extrusion process, raw material information, and a thickness requirement range, and to acquire current environmental temperature and humidity corresponding to the current extrusion process. The raw material information includes raw material addition amount and raw material parameters, and the raw material parameters include flow index and additive index. A determination module is configured to determine the degree of influence of the current environmental temperature and humidity on the thickness of an initial base film, which is a film generated by the current extrusion process. A prediction module is configured to predict a predicted thickness of the initial base film based on the extrusion equipment parameters, the raw material information, the current environmental temperature and humidity, and the degree of influence, and to determine whether the predicted thickness is within the thickness requirement range. An adjustment module is configured to, if the predicted thickness is not within the thickness requirement range, adjust the extrusion equipment parameters based on the predicted thickness, and generate an adjustment signal based on the adjusted extrusion equipment parameters. A generation module is configured to, if the predicted thickness is within the thickness requirement range, generate an extrusion signal based on the extrusion equipment parameters. When adjusting the extrusion equipment parameters based on the predicted thickness, the adjustment module is configured to: Calculate the ratio between the predicted thickness and a thickness median value to obtain a deviation ratio, the thickness median value being a median value corresponding to the thickness requirement range. Determine an adjustment strategy based on the deviation ratio, the adjustment strategy including an adjustment parameter and an adjustment parameter amount. Adjust the extrusion equipment parameters based on the adjustment strategy. When determining the adjustment strategy based on the deviation ratio, the adjustment module is configured to: Determine an adjustment direction and determine whether the deviation ratio belongs to a first preset deviation ratio threshold range. If the deviation ratio belongs to the first preset deviation ratio threshold range, determine that the adjustment parameter is the volume of extrusion melt per unit time, determine a first adjusted volume of extrusion melt per unit time based on the volume of extrusion melt per unit time corresponding to the current time, the predicted thickness, and the thickness median value, obtain the adjustment parameter amount based on the adjustment direction and the first adjusted volume of extrusion melt per unit time, and determine the adjustment strategy based on the adjustment parameter amount and the adjustment parameter. If the deviation ratio does not belong to the first preset deviation ratio threshold range and belongs to a second preset deviation ratio threshold range, determine that the adjustment parameter is the die exit cross-sectional area, determine a first adjusted die exit cross-sectional area based on the die exit cross-sectional area corresponding to the current time, the predicted thickness, and the thickness median value, obtain the adjustment parameter amount based on the adjustment direction and the first adjusted die exit cross-sectional area, and determine the adjustment strategy based on the adjustment parameter amount and the adjustment parameter. If the deviation ratio does not belong to the second preset deviation ratio threshold range, it is determined that the adjustment parameter is the die exit cross-sectional area and the volume of the extruded solution per unit time, and the second adjusted volume of the extruded solution per unit time and the second adjusted die exit cross-sectional area are determined through an iterative algorithm, and based on the adjustment direction, the second adjusted volume of the extruded solution per unit time and the second adjusted die exit cross-sectional area, the adjustment parameter amount is obtained, and based on the adjustment parameter amount and the adjustment parameter, the adjustment strategy is determined.

8. The lithium battery separator process dynamic optimization system of claim 6 or 7, wherein, The electronic device includes: at least one processor; a memory; at least one application program, wherein the at least one application program is stored in the memory and is configured to be executed by the at least one processor, and the at least one application program is configured to execute the lithium battery diaphragm process dynamic optimization method of any one of claims 1-5.

Images