WO2024066053A1 - 锂离子电池浆料黏度预测方法、装置及相关设备 - Google Patents

锂离子电池浆料黏度预测方法、装置及相关设备 Download PDF

Info

Publication number
WO2024066053A1
WO2024066053A1 PCT/CN2022/137800 CN2022137800W WO2024066053A1 WO 2024066053 A1 WO2024066053 A1 WO 2024066053A1 CN 2022137800 W CN2022137800 W CN 2022137800W WO 2024066053 A1 WO2024066053 A1 WO 2024066053A1
Authority
WO
WIPO (PCT)
Prior art keywords
slurry
target
viscosity
data
time period
Prior art date
Application number
PCT/CN2022/137800
Other languages
English (en)
French (fr)
Inventor
杨之乐
周邦昱
郭媛君
刘祥飞
安钊
Original Assignee
深圳先进技术研究院
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳先进技术研究院 filed Critical 深圳先进技术研究院
Publication of WO2024066053A1 publication Critical patent/WO2024066053A1/zh

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N11/00—Investigating flow properties of materials, e.g. viscosity, plasticity; Analysing materials by determining flow properties
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M10/00—Secondary cells; Manufacture thereof
    • H01M10/05—Accumulators with non-aqueous electrolyte
    • H01M10/052—Li-accumulators
    • H01M10/0525—Rocking-chair batteries, i.e. batteries with lithium insertion or intercalation in both electrodes; Lithium-ion batteries
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M10/00—Secondary cells; Manufacture thereof
    • H01M10/05—Accumulators with non-aqueous electrolyte
    • H01M10/058—Construction or manufacture
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02E60/10—Energy storage using batteries

Definitions

  • the present invention relates to the technical field of slurry performance prediction based on electrical digital data processing, and in particular to a lithium ion battery slurry viscosity prediction method, device and related equipment.
  • Lithium-ion battery slurry is made by evenly dispersing active materials (positive and negative electrode materials), binders, conductive agents, etc. in a solvent by stirring. Viscosity is one of the important factors affecting lithium-ion battery slurry. During the preparation of lithium-ion batteries, the preparation process can be properly regulated based on viscosity.
  • the viscosity of the slurry of lithium-ion batteries during the manufacturing process needs to be obtained after complex settings and measurements using instruments in real time.
  • the viscosity obtained is the actual viscosity at the time of data collection and cannot be predicted for the viscosity at a future time.
  • the problem with the prior art is that the slurry viscosity cannot be predicted, and therefore the viscosity prediction data of the lithium-ion battery slurry during the coating drying period cannot be obtained.
  • the main purpose of the present invention is to provide a method, device and related equipment for predicting the viscosity of lithium-ion battery slurry, aiming to solve the problem that the slurry viscosity cannot be predicted in the prior art and the viscosity prediction data of the lithium-ion battery slurry during the coating drying period cannot be obtained.
  • the first aspect of the present invention provides a method for predicting the viscosity of a lithium-ion battery slurry, wherein the method for predicting the viscosity of a lithium-ion battery slurry comprises:
  • the slurry state data includes processing temperature, processing shear force, processing shear rate and slurry viscosity sequence data in the first time period
  • the slurry viscosity sequence data includes a plurality of different collection moments in the first time period and viscosity data of the target slurry at each of the collection moments
  • the first time period includes a coating time period of the lithium-ion battery
  • the viscosity of the target slurry in the second time period is predicted by a trained slurry viscosity prediction model, and the slurry viscosity prediction data corresponding to the slurry state data at the target temperature, the target shear force and the target shear rate are obtained, wherein the slurry viscosity prediction data includes at least one prediction moment in the second time period and the predicted viscosity corresponding to the prediction moment.
  • the step of obtaining the slurry state data of the target slurry in the first time period includes:
  • the above-mentioned slurry viscosity sequence data is generated according to all the above-mentioned collection moments and their corresponding collection viscosities.
  • the slurry viscosity sequence data is generated according to all the acquisition moments and their corresponding acquisition viscosities, including:
  • the above-mentioned slurry viscosity sequence data is obtained after feature engineering processing is performed on the above-mentioned collection moments and their corresponding collection viscosities according to a preset sequence point time interval and a preset viscosity threshold, wherein the above-mentioned feature engineering processing includes data cleaning and/or data supplementation.
  • the slurry state data further includes the material moisture content corresponding to the target slurry, the material solid content corresponding to the target slurry, air humidity, the number of coating layers and the coating thickness.
  • the slurry viscosity prediction model is trained according to the following steps:
  • the above-mentioned training data includes a plurality of groups of model training data groups, each group of model training data groups includes the slurry state training data of the above-mentioned target slurry in a first time period and the training target temperature, training target shear force, training target shear rate and slurry viscosity annotation data of the above-mentioned target slurry in a second time period;
  • the model parameters of the above-mentioned slurry viscosity prediction model are adjusted, and the above-mentioned step of inputting the slurry state training data, training target temperature, training target shear force and training target shear rate in the training data into the above-mentioned slurry viscosity prediction model is continued until the preset training conditions are met to obtain the trained slurry viscosity prediction model.
  • the slurry viscosity prediction model is an XGBOOST model
  • the preset training condition is that the number of adjustments of the model parameters is not less than 1
  • the slurry viscosity prediction model adjusts the model parameters based on a grid search method and regularization.
  • the above method further includes:
  • the above-mentioned slurry viscosity prediction data is curve data reflecting the corresponding relationship between the prediction time and the predicted viscosity.
  • a second aspect of the present invention provides a device for predicting the viscosity of a lithium-ion battery slurry, wherein the device for predicting the viscosity of a lithium-ion battery slurry comprises:
  • a slurry state data acquisition module used to acquire slurry state data of a target slurry in a first time period, wherein the target slurry is a slurry for preparing a lithium-ion battery, the slurry state data includes a processing temperature, a processing shear force, a processing shear rate, and a slurry viscosity sequence data in the first time period, the slurry viscosity sequence data includes a plurality of different collection moments in the first time period and viscosity data of the target slurry at each of the collection moments, and the first time period includes a coating time period of the lithium-ion battery;
  • a target condition data acquisition module used to acquire a target temperature, a target shear force and a target shear rate of the target slurry in a second period, wherein the second period is after the first period and includes a coating drying period of the lithium-ion battery;
  • the viscosity prediction module is used to predict the viscosity of the target slurry in the second time period according to the target temperature, the target shear force, the target shear rate and the slurry state data through a trained slurry viscosity prediction model, and obtain the slurry viscosity prediction data corresponding to the slurry state data at the target temperature, the target shear force and the target shear rate, wherein the slurry viscosity prediction data includes at least one prediction moment in the second time period and the predicted viscosity corresponding to the prediction moment.
  • a third aspect of the present invention provides an intelligent terminal, which includes a memory, a processor, and a lithium-ion battery slurry viscosity prediction program stored in the memory and executable on the processor.
  • the lithium-ion battery slurry viscosity prediction program is executed by the processor, the steps of any one of the above-mentioned lithium-ion battery slurry viscosity prediction methods are implemented.
  • a fourth aspect of the present invention provides a computer-readable storage medium, on which a lithium-ion battery slurry viscosity prediction program is stored.
  • the lithium-ion battery slurry viscosity prediction program is executed by a processor, the steps of any one of the above-mentioned lithium-ion battery slurry viscosity prediction methods are implemented.
  • the slurry state data of the target slurry in the first time period is obtained, wherein the target slurry is a slurry for preparing a lithium-ion battery, and the slurry state data includes the processing temperature, the processing shear force, the processing shear rate and the slurry viscosity sequence data in the first time period, and the slurry viscosity sequence data includes a plurality of different collection moments in the first time period and the viscosity data of the target slurry at each of the collection moments, and the first time period includes the coating time period of the lithium-ion battery; the target temperature, target shear force and target shear rate of the target slurry in the second time period are obtained, wherein , the second time period is after the first time period, and the second time period includes the coating drying time of the lithium-ion battery; according to the target temperature, the target shear force, the target shear rate and the slurry state data, the viscosity of the
  • the present invention can combine a variety of information (including the collected slurry state data, the target temperature, target shear force and target shear rate in the next time period) to predict the viscosity prediction data of the next time period based on the data of the previous time period, which is conducive to the prediction of the viscosity of lithium-ion slurry during the coating drying period.
  • FIG1 is a schematic flow chart of a method for predicting viscosity of lithium-ion battery slurry provided in an embodiment of the present invention
  • FIG2 is a schematic diagram of a specific flow chart of step S100 in FIG1 according to an embodiment of the present invention.
  • FIG. 3 is a schematic diagram of the structure of a lithium-ion battery slurry viscosity prediction device provided by an embodiment of the present invention.
  • FIG. 4 is a block diagram of the internal structure of a smart terminal provided by an embodiment of the present invention.
  • the term “if” may be interpreted as “when” or “upon” or “in response to determining” or “in response to being classified into,” depending on the context.
  • the phrase “if it is determined” or “if classified into [described condition or event]” may be interpreted as meaning “upon determination” or “in response to determining” or “upon classification into [described condition or event]” or “in response to being classified into [described condition or event],” depending on the context.
  • Lithium-ion battery slurry is made by evenly dispersing active materials (positive and negative electrode materials), binders, conductive agents, etc. in a solvent by stirring. Viscosity is one of the important factors affecting lithium-ion battery slurry. During the preparation of lithium-ion batteries, the preparation process can be properly regulated based on viscosity.
  • viscosity may affect the flow properties of the slurry, and the consistency and level of viscosity will affect the uniformity and coating efficiency of subsequent coating. Too high or too low viscosity is not conducive to electrode coating. Therefore, if the slurry viscosity can be predicted, the preparation process can be properly controlled in advance to obtain the slurry with the viscosity the user wants.
  • the viscosity of the slurry of lithium-ion batteries during the manufacturing process requires complex settings and measurements in real time using instruments.
  • the viscosity obtained is the actual viscosity at the time of data collection and cannot be predicted for the viscosity at future times.
  • the problem with the prior art is that it is impossible to predict the viscosity of the slurry, and therefore it is impossible to obtain the viscosity prediction data of the lithium-ion battery slurry during the coating drying period.
  • the slurry state data of the target slurry in the first time period is obtained, wherein the target slurry is a slurry for preparing a lithium-ion battery, the slurry state data includes a processing temperature, a processing shear force, a processing shear rate and a slurry viscosity sequence data in the first time period, the slurry viscosity sequence data includes a plurality of different collection moments in the first time period and the viscosity data of the target slurry at each of the above-mentioned collection moments, and the first time period includes the coating time period of the lithium-ion battery; the target temperature, target shear force and target viscosity of the target slurry in the second time period are obtained.
  • the second time period is after the first time period, and the second time period includes a coating drying time period of the lithium-ion battery; according to the target temperature, the target shear force, the target shear rate and the slurry state data, the viscosity of the target slurry in the second time period is predicted by a trained slurry viscosity prediction model, and the slurry viscosity prediction data corresponding to the slurry state data at the target temperature, the target shear force and the target shear rate are obtained, wherein the slurry viscosity prediction data includes at least one prediction moment in the second time period and the predicted viscosity corresponding to the prediction moment.
  • the present invention can combine a variety of information (including the collected slurry state data, the target temperature, target shear force and target shear rate in the next time period) to predict the viscosity prediction data of the next time period based on the data of the previous time period, which is conducive to the prediction of the viscosity of lithium-ion slurry during the coating drying period.
  • the user can appropriately control and adjust the subsequent production process according to the predicted viscosity data of the next time period to obtain the desired viscosity, which is conducive to the control of the subsequent process. It is also conducive to improving the efficiency of lithium-ion battery production and the performance of the lithium-ion batteries produced.
  • an embodiment of the present invention provides a method for predicting viscosity of lithium-ion battery slurry. Specifically, the method comprises the following steps:
  • Step S100 obtaining slurry state data of the target slurry within a first time period, wherein the target slurry is a slurry for preparing lithium-ion batteries, the slurry state data includes processing temperature, processing shear force, processing shear rate and slurry viscosity sequence data within the first time period, the slurry viscosity sequence data includes a plurality of different collection moments within the first time period and viscosity data of the target slurry at each of the collection moments, and the first time period includes a coating period of the lithium-ion battery.
  • the target slurry is a slurry for preparing lithium-ion batteries
  • the slurry state data includes processing temperature, processing shear force, processing shear rate and slurry viscosity sequence data within the first time period
  • the slurry viscosity sequence data includes a plurality of different collection moments within the first time period and viscosity data of the target slurry at each of the collection moments
  • the first time period includes a coating period of
  • the target slurry is a slurry for which viscosity prediction is required, and is specifically a slurry for preparing lithium-ion batteries.
  • the slurry state data of the target slurry during the coating period is collected to predict the viscosity of the target slurry during the coating drying period.
  • the target slurry is a non-Newtonian fluid, and data such as shear rate and shear force have a nonlinear relationship with viscosity. Therefore, in this embodiment, viscosity prediction is performed based on a slurry viscosity prediction model.
  • the first time period may include only the moments of the coating stage of the lithium-ion battery, or may include all the moments of the coating stage and part of the moments of the coating drying stage.
  • the first time period includes only the moments of the coating stage as an example for explanation, but it is not a specific limitation.
  • step S100 includes the following specific steps:
  • Step S101 acquiring the processing temperature of the target slurry in the first time period through a temperature sensor.
  • Step S102 obtaining the processing shear force and processing shear efficiency of the target slurry in the first time period through a rheometer.
  • Step S103 monitoring the viscosity of the target slurry by means of the rheometer to obtain the sampled viscosities at a plurality of different sampled moments within the first time period.
  • Step S104 generating the above-mentioned slurry viscosity sequence data according to all the above-mentioned collection moments and their corresponding collection viscosities.
  • the processing temperature is measured by a pre-set temperature sensor, and the processing shear force and processing shear efficiency are measured by a pre-set rheometer.
  • the viscosity of the target slurry is continuously detected by the rheometer during the first period, and the collected viscosity at multiple different collection times during the first period is collected.
  • feature engineering processing can be performed first to reduce the probability of errors in the collected data. For example, obviously erroneous data can be deleted, and time points that are too close can be eliminated.
  • the above-mentioned slurry viscosity sequence data is generated based on all the above-mentioned collection moments and their corresponding collection viscosities, including: obtaining the above-mentioned slurry viscosity sequence data after performing feature engineering processing on the above-mentioned collection moments and their corresponding collection viscosities according to a preset sequence point time interval and a preset viscosity threshold, wherein the above-mentioned feature engineering processing includes data cleaning and/or data supplementation.
  • the above-mentioned feature engineering processing is a pre-set data standardization processing process, which can convert the collected data into a standard data format.
  • the number of data in the required slurry viscosity sequence data and the time interval between each collection moment can be pre-set, so as to delete the redundant moments according to the time interval.
  • the viscosity of the missing moment can be obtained by simulating the viscosity corresponding to the two collection moments before and after it and supplemented into the sequence data.
  • the viscosity values of the two collection moments before and after the missing moment are weighted averaged according to the time interval between the missing moment and the two collection moments before and after, and used as the viscosity of the missing moment.
  • data with obviously abnormal viscosity values in the collected data sequence can also be deleted (for example, when the viscosity shows an obvious mutation, it may be that the rheometer measurement is incorrect, and the incorrect data needs to be eliminated).
  • more accurate and easier to analyze and process slurry viscosity sequence data can be obtained, which is conducive to improving the efficiency of lithium-ion battery slurry viscosity prediction.
  • the slurry state data also includes the material moisture content corresponding to the target slurry, the material solid content corresponding to the target slurry, air humidity, the number of coating layers and the coating thickness, so that more information can be further combined to improve the accuracy of the prediction of the viscosity of the lithium-ion battery slurry.
  • the slurry state data can also include other specific data, which are not specifically limited here.
  • Step S200 obtaining the target temperature, target shear force and target shear rate of the target slurry in a second time period, wherein the second time period is after the first time period, and the second time period includes a coating drying period of the lithium-ion battery.
  • the above-mentioned second time period is a time period in which viscosity prediction is required
  • the target temperature, target shear force and target shear rate are the temperature, shear force and shear rate planned to be used when processing the target slurry in the second time period.
  • the above-mentioned target temperature, target shear force and target shear rate can be preset, or can be input by the user in real time or adjusted according to actual needs, and are not specifically limited here.
  • the above-mentioned target temperature, target shear force and target shear rate can also be the same as the processing temperature, processing shear force and processing shear rate in the first time period.
  • Step S300 based on the target temperature, the target shear force, the target shear rate and the slurry state data, predict the viscosity of the target slurry in the second time period through the trained slurry viscosity prediction model, and obtain the slurry viscosity prediction data corresponding to the slurry state data at the target temperature, the target shear force and the target shear rate, wherein the slurry viscosity prediction data includes at least one prediction moment in the second time period and the predicted viscosity corresponding to the prediction moment.
  • the target temperature, the target shear force, the target shear rate and the slurry state data are used as input data of the slurry viscosity prediction model, and the slurry viscosity prediction is performed through the slurry viscosity prediction model, and the viscosity prediction data is obtained according to the output data of the model.
  • the output data of the model can be directly used as the viscosity prediction data.
  • the output of the slurry viscosity prediction model is the curve data corresponding to time and viscosity, and the corresponding viscosity prediction data can be selected from the curve data, for example, the convergence value of the viscosity is obtained as the viscosity prediction data.
  • the slurry viscosity prediction data includes at least one prediction moment in the second time period and the predicted viscosity corresponding to the prediction moment.
  • the slurry viscosity prediction data is also a time series data, which includes multiple prediction moments and the predicted viscosity corresponding to each prediction moment. It should be noted that the first prediction moment in the slurry viscosity prediction data is the next moment of the last acquisition moment in the first time period.
  • the slurry viscosity prediction model is trained according to the following steps:
  • the above-mentioned training data includes a plurality of groups of model training data groups, each group of model training data groups includes the slurry state training data of the above-mentioned target slurry in a first time period and the training target temperature, training target shear force, training target shear rate and slurry viscosity annotation data of the above-mentioned target slurry in a second time period;
  • the model parameters of the above-mentioned slurry viscosity prediction model are adjusted, and the above-mentioned step of inputting the slurry state training data, training target temperature, training target shear force and training target shear rate in the training data into the above-mentioned slurry viscosity prediction model is continued until the preset training conditions are met to obtain the trained slurry viscosity prediction model.
  • the category of specific data contained in the slurry state training data in the training data is consistent with the category of specific data in the slurry state data collected when performing viscosity prediction.
  • the above-mentioned preset training conditions are pre-set conditions for stopping model training, which may include the number of iterations reaching a preset iteration threshold, or the loss value calculated by a pre-set loss function based on the slurry state training data and the slurry viscosity annotation data is less than a preset loss threshold.
  • the slurry viscosity prediction model may be a neural network model.
  • the slurry viscosity prediction model is an XGBOOST model
  • the preset training condition is that the number of model parameter adjustments is not less than 1
  • the slurry viscosity prediction model adjusts model parameters based on a grid search method and regularization.
  • the XGBOOST model is used in this embodiment, and only one iteration is required, which is conducive to improving the efficiency of model training, thereby improving the efficiency of viscosity prediction.
  • the above lithium-ion battery slurry viscosity prediction method also includes:
  • the leveling time corresponding to the above-mentioned target slurry in the above-mentioned coating drying period is obtained by calculating the slurry viscosity prediction data corresponding to the above-mentioned slurry state data at the above-mentioned target temperature, the above-mentioned target shear force and the above-mentioned target shear rate; wherein the above-mentioned slurry viscosity prediction data is curve data reflecting the corresponding relationship between the prediction time and the predicted viscosity.
  • the leveling time is the time it takes for the leveling agent coating to flow and dry during the film-forming process, and then gradually form a flat, smooth and uniform coating.
  • the relationship between viscosity, shear force, shear efficiency and time can be established, so that the leveling time and performance of the target slurry during film drying can be predicted based on the change in viscosity.
  • the production efficiency of lithium-ion batteries can be predicted, so as to determine whether the current conditions can meet the production efficiency requirements.
  • the target temperature corresponding to the second period is increased.
  • Other specific control processes may also be pre-set, which are not specifically limited here.
  • an alarm message may be sent to promptly remind the user of the difference in viscosity, so as to facilitate the user to adjust the plan in time and reduce losses.
  • a variety of information can be combined to achieve the prediction of viscosity data for the next time period based on the data of the previous time period, which is beneficial to the prediction of the viscosity of the lithium ion slurry during the coating drying period.
  • the user can appropriately control and adjust the subsequent production process according to the predicted viscosity data of the next time period to obtain the desired viscosity, which is conducive to the control of the subsequent process. It is also conducive to improving the efficiency of lithium-ion battery production and the performance of the lithium-ion batteries produced.
  • an embodiment of the present invention further provides a lithium-ion battery slurry viscosity prediction device, and the above-mentioned lithium-ion battery slurry viscosity prediction device includes:
  • the slurry state data acquisition module 410 is used to obtain the slurry state data of the target slurry within the first time period, wherein the above-mentioned target slurry is a slurry used to prepare lithium-ion batteries, and the above-mentioned slurry state data includes processing temperature, processing shear force, processing shear rate and slurry viscosity sequence data within the above-mentioned first time period, and the above-mentioned slurry viscosity sequence data includes multiple different collection moments within the above-mentioned first time period and the viscosity data of the above-mentioned target slurry at each of the above-mentioned collection moments, and the above-mentioned first time period includes the coating time period of the above-mentioned lithium-ion batteries.
  • the target condition data acquisition module 420 is used to obtain the target temperature, target shear force and target shear rate of the target slurry in the second time period, wherein the second time period is after the first time period and includes the coating drying time period of the lithium-ion battery.
  • the viscosity prediction module 430 is used to predict the viscosity of the target slurry in the second time period according to the target temperature, the target shear force, the target shear rate and the slurry state data through a trained slurry viscosity prediction model, and obtain the slurry viscosity prediction data corresponding to the slurry state data at the target temperature, the target shear force and the target shear rate, wherein the slurry viscosity prediction data includes at least one prediction moment in the second time period and the predicted viscosity corresponding to the prediction moment.
  • the specific functions of the above-mentioned lithium-ion battery slurry viscosity prediction device and its various modules can refer to the corresponding description in the above-mentioned lithium-ion battery slurry viscosity prediction method, which will not be repeated here.
  • each module of the above-mentioned lithium-ion battery slurry viscosity prediction device is not unique and is not specifically limited here.
  • the present invention also provides an intelligent terminal, and its principle block diagram can be shown in Figure 4.
  • the above intelligent terminal includes a processor and a memory.
  • the memory of the intelligent terminal includes a lithium-ion battery slurry viscosity prediction program, and the memory provides an environment for the operation of the lithium-ion battery slurry viscosity prediction program.
  • the steps of any of the above lithium-ion battery slurry viscosity prediction methods are implemented.
  • the above intelligent terminal may also include other functional modules or units, which are not specifically limited here.
  • FIG. 4 is only a block diagram of a partial structure related to the solution of the present invention, and does not constitute a limitation on the smart terminal to which the solution of the present invention is applied.
  • the smart terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
  • An embodiment of the present invention further provides a computer-readable storage medium, on which a lithium-ion battery slurry viscosity prediction program is stored.
  • a lithium-ion battery slurry viscosity prediction program is executed by a processor, the steps of any lithium-ion battery slurry viscosity prediction method provided in the embodiment of the present invention are implemented.
  • the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the above-mentioned device can be divided into different functional units or modules to complete all or part of the functions described above.
  • the functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.
  • the disclosed device/intelligent terminal and method can be implemented in other ways.
  • the device/intelligent terminal embodiments described above are only schematic, for example, the division of the above modules or units is only a logical function division, and in actual implementation, other division methods can be used, for example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.
  • the above integrated modules/units are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above embodiment method, and can also be completed by instructing the relevant hardware through a computer program.
  • the above computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above method embodiments can be implemented.
  • the above computer program includes computer program code, and the above computer program code can be in source code form, object code form, executable file or some intermediate form.
  • the above computer-readable medium can include: any entity or device that can carry the above computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the above computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Chemical & Material Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Manufacturing & Machinery (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Electrochemistry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Analytical Chemistry (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Artificial Intelligence (AREA)
  • Biochemistry (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Materials Engineering (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Battery Electrode And Active Subsutance (AREA)

Abstract

本发明公开了一种锂离子电池浆料黏度预测方法、装置及相关设备，方法包括：获取目标浆料在第一时段内的浆料状态数据，目标浆料是用于制备锂离子电池的浆料，浆料状态数据包括处理温度、处理剪切力、处理剪切速率及上述第一时段内的浆料黏度序列数据，第一时段包括上述锂离子电池的涂布时段；获取目标浆料在第二时段的目标温度、目标剪切力和目标剪切速率，第二时段在第一时段之后，第二时段包括涂膜干燥时段；根据目标温度、目标剪切力、目标剪切速率以及浆料状态数据，通过已训练的浆料黏度预测模型对目标浆料在第二时段内的黏度进行预测，并获得对应的浆料黏度预测数据。本发明有利于实现对锂离子浆料在涂膜干燥时段的黏度的预测。

Description

锂离子电池浆料黏度预测方法、装置及相关设备 技术领域
本发明涉及基于电数字数据处理的浆料性能预测技术领域，尤其涉及的是一种锂离子电池浆料黏度预测方法、装置及相关设备。
 背景技术
随着科学技术的发展，锂离子电池的应用越来越广泛。锂离子电池浆料由活性物质（正负极材料）、黏结剂、导电剂等，通过搅拌的方式均匀分散于溶剂中制备而成。黏度是影响锂离子电池浆料的重要因素之一，在锂离子电池制备的过程中可以基于黏度对制备过程进行适当地调控。
现有技术中，锂离子电池的在制作过程中的浆料黏度需要实时使用仪器进行复杂设置和测量后才能获得，获得的黏度是进行数据采集的时刻的实际黏度而无法对未来时刻的黏度进行预测。现有技术的问题在于，不能实现浆料黏度的预测，因此也无法获得锂离子电池浆料在涂膜干燥时段的黏度预测数据。
因此，现有技术还有待改进和发展。
 技术问题
本发明的主要目的在于提供一种锂离子电池浆料黏度预测方法、装置及相关设备，旨在解决现有技术中不能实现浆料黏度的预测，无法获得锂离子电池浆料在涂膜干燥时段的黏度预测数据的问题。
 技术解决方案
为了实现上述目的，本发明第一方面提供一种锂离子电池浆料黏度预测方法，其中，上述锂离子电池浆料黏度预测方法包括：
获取目标浆料在第一时段内的浆料状态数据，其中，上述目标浆料是用于制备锂离子电池的浆料，上述浆料状态数据包括处理温度、处理剪切力、处理剪切速率以及上述第一时段内的浆料黏度序列数据，上述浆料黏度序列数据包括上述第一时段内的多个不同的采集时刻以及上述目标浆料在各上述采集时刻的黏度数据，上述第一时段包括上述锂离子电池的涂布时段；
获取上述目标浆料在第二时段内的目标温度、目标剪切力和目标剪切速率，其中，上述第二时段在上述第一时段之后，且上述第二时段包括上述锂离子电池的涂膜干燥时段；
根据上述目标温度、上述目标剪切力、上述目标剪切速率以及上述浆料状态数据，通过已训练的浆料黏度预测模型对上述目标浆料在上述第二时段内的黏度进行预测，并获得上述浆料状态数据在上述目标温度、上述目标剪切力和上述目标剪切速率下对应的浆料黏度预测数据，其中，上述浆料黏度预测数据包括上述第二时段内的至少一个预测时刻以及上述预测时刻对应的预测黏度。
可选的，上述获取目标浆料在第一时段内的浆料状态数据，包括：
通过温度传感器采集获取上述目标浆料在上述第一时段内的处理温度；
通过流变仪采集获取上述目标浆料在上述第一时段内的处理剪切力和处理剪切效率；
通过上述流变仪对上述目标浆料的黏度进行监测，获得在上述第一时段内的多个不同采集时刻的采集黏度；
根据所有上述采集时刻及其对应的采集黏度生成上述浆料黏度序列数据。
可选的，上述根据所有上述采集时刻及其对应的采集黏度生成上述浆料黏度序列数据，包括：
根据预设的序列点时间间隔和预设的黏度阈值对上述采集时刻及其对应的采集黏度进行特征工程处理后获得上述浆料黏度序列数据，其中，上述特征工程处理包括数据清洗和/或数据补充。
可选的，上述浆料状态数据还包括上述目标浆料对应的物料湿含量、上述目标浆料对应的物料固含量、空气湿度、涂布层数和涂布厚度。
可选的，上述浆料黏度预测模型根据如下步骤进行训练：
将训练数据中的浆料状态训练数据、训练目标温度、训练目标剪切力和训练目标剪切速率输入上述浆料黏度预测模型，通过上述浆料黏度预测模型输出上述浆料状态训练数据在上述训练目标温度、上述训练目标剪切力和上述训练目标剪切速率下的浆料黏度预测数据，其中，上述训练数据包括多组模型训练数据组，每一组模型训练数据组包括上述目标浆料在第一时段内的浆料状态训练数据以及上述目标浆料在第二时段内的训练目标温度、训练目标剪切力、训练目标剪切速率和浆料黏度标注数据；
根据上述浆料状态训练数据对应的浆料黏度标注数据和上述浆料状态训练数据对应的浆料黏度预测数据，对上述浆料黏度预测模型的模型参数进行调整，并继续执行上述将训练数据中的浆料状态训练数据、训练目标温度、训练目标剪切力和训练目标剪切速率输入上述浆料黏度预测模型的步骤，直至满足预设训练条件，以得到已训练的浆料黏度预测模型。
可选的，上述浆料黏度预测模型是XGBOOST模型，上述预设训练条件为模型参数的调整次数不小于1，上述浆料黏度预测模型基于网格搜索法和正则化进行模型参数调整。
可选的，上述方法还包括：
根据上述浆料状态数据在上述目标温度、上述目标剪切力和上述目标剪切速率下对应的浆料黏度预测数据计算获取上述目标浆料在上述涂膜干燥时段对应的流平时间；
其中，上述浆料黏度预测数据是体现预测时刻和预测黏度之间对应关系的曲线数据。
本发明第二方面提供一种锂离子电池浆料黏度预测装置，其中，上述锂离子电池浆料黏度预测装置包括：
浆料状态数据获取模块，用于获取目标浆料在第一时段内的浆料状态数据，其中，上述目标浆料是用于制备锂离子电池的浆料，上述浆料状态数据包括处理温度、处理剪切力、处理剪切速率以及上述第一时段内的浆料黏度序列数据，上述浆料黏度序列数据包括上述第一时段内的多个不同的采集时刻以及上述目标浆料在各上述采集时刻的黏度数据，上述第一时段包括上述锂离子电池的涂布时段；
目标条件数据获取模块，用于获取上述目标浆料在第二时段内的目标温度、目标剪切力和目标剪切速率，其中，上述第二时段在上述第一时段之后，且上述第二时段包括上述锂离子电池的涂膜干燥时段；
黏度预测模块，用于根据上述目标温度、上述目标剪切力、上述目标剪切速率以及上述浆料状态数据，通过已训练的浆料黏度预测模型对上述目标浆料在上述第二时段内的黏度进行预测，并获得上述浆料状态数据在上述目标温度、上述目标剪切力和上述目标剪切速率下对应的浆料黏度预测数据，其中，上述浆料黏度预测数据包括上述第二时段内的至少一个预测时刻以及上述预测时刻对应的预测黏度。
本发明第三方面提供一种智能终端，上述智能终端包括存储器、处理器以及存储在上述存储器上并可在上述处理器上运行的锂离子电池浆料黏度预测程序，上述锂离子电池浆料黏度预测程序被上述处理器执行时实现上述任意一种锂离子电池浆料黏度预测方法的步骤。
本发明第四方面提供一种计算机可读存储介质，上述计算机可读存储介质上存储有锂离子电池浆料黏度预测程序，上述锂离子电池浆料黏度预测程序被处理器执行时实现上述任意一种锂离子电池浆料黏度预测方法的步骤。
 有益效果
由上可见，本发明方案中，获取目标浆料在第一时段内的浆料状态数据，其中，上述目标浆料是用于制备锂离子电池的浆料，上述浆料状态数据包括处理温度、处理剪切力、处理剪切速率以及上述第一时段内的浆料黏度序列数据，上述浆料黏度序列数据包括上述第一时段内的多个不同的采集时刻以及上述目标浆料在各上述采集时刻的黏度数据，上述第一时段包括上述锂离子电池的涂布时段；获取上述目标浆料在第二时段内的目标温度、目标剪切力和目标剪切速率，其中，上述第二时段在上述第一时段之后，且上述第二时段包括上述锂离子电池的涂膜干燥时段；根据上述目标温度、上述目标剪切力、上述目标剪切速率以及上述浆料状态数据，通过已训练的浆料黏度预测模型对上述目标浆料在上述第二时段内的黏度进行预测，并获得上述浆料状态数据在上述目标温度、上述目标剪切力和上述目标剪切速率下对应的浆料黏度预测数据，其中，上述浆料黏度预测数据包括上述第二时段内的至少一个预测时刻以及上述预测时刻对应的预测黏度。
与现有技术只能实时采集锂离子电池浆料的实际黏度的方案相比，本发明中可以结合多种信息（包括采集获得的浆料状态数据、在下一个时间段内的目标温度、目标剪切力和目标剪切速率），实现根据前一个时段的数据预测获得后一个时段的黏度预测数据，有利于实现对锂离子浆料在涂膜干燥时段的黏度的预测。
 附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其它的附图。
图1是本发明实施例提供的一种锂离子电池浆料黏度预测方法的流程示意图；
图2是本发明实施例图1中步骤S100的具体流程示意图；
图3是本发明实施例提供的一种锂离子电池浆料黏度预测装置的结构示意图；
图4是本发明实施例提供的一种智能终端的内部结构原理框图。
 本发明的实施方式
以下描述中，为了说明而不是为了限定，提出了诸如特定系统结构、技术之类的具体细节，以便透彻理解本发明实施例。然而，本领域的技术人员应当清楚，在没有这些具体细节的其它实施例中也可以实现本发明。在其它情况下，省略对众所周知的系统、装置、电路以及方法的详细说明，以免不必要的细节妨碍本发明的描述。
应当理解，当在本说明书和所附权利要求书中使用时，术语“包括”指示所描述特征、整体、步骤、操作、元素和/或组件的存在，但并不排除一个或多个其它特征、整体、步骤、操作、元素、组件和/或其集合的存在或添加。
还应当理解，在本申请说明书中所使用的术语仅仅是出于描述特定实施例的目的而并不意在限制本申请。如在本申请说明书和所附权利要求书中所使用的那样，除非上下文清楚地指明其它情况，否则单数形式的“一”、“一个”及“该”意在包括复数形式。
还应当进一步理解，在本申请说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合，并且包括这些组合。
如在本说明书和所附权利要求书中所使用的那样，术语“如果”可以依据上下文被解释为“当…时”或“一旦”或“响应于确定”或“响应于分类到”。类似的，短语“如果确定”或“如果分类到[所描述条件或事件]”可以依据上下文被解释为意指“一旦确定”或“响应于确定”或“一旦分类到[所描述的条件或事件]”或“响应于分类到[所描述条件或事件]”。
下面结合本发明实施例的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明的一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。
在下面的描述中阐述了很多具体细节以便于充分理解本发明，但是本发明还可以采用其它不同于在此描述的其它方式来实施，本领域技术人员可以在不违背本发明内涵的情况下做类似推广，因此本发明不受下面公开的具体实施例的限制。
随着科学技术的发展，锂离子电池的应用越来越广泛。锂离子电池浆料由活性物质（正负极材料）、黏结剂、导电剂等，通过搅拌的方式均匀分散于溶剂中制备而成。黏度是影响锂离子电池浆料的重要因素之一，在锂离子电池制备的过程中可以基于黏度对制备过程进行适当地调控。
例如，黏度可能影响浆料的流动性能、黏度的一致性和高低会影响后续涂布时的均匀性和涂布效率，黏度过高或过低都不利于进行极片涂布。因此如果能进行浆料黏度的预测就能够对制备过程进行适当地预先控制，获得用户想要的黏度的浆料。
现有技术中，锂离子电池的在制作过程中的浆料黏度需要实时使用仪器进行复杂设置和测量后才能获得，获得的黏度是进行数据采集的时刻的实际黏度而无法对未来时刻的黏度进行预测。现有技术的问题在于，不能实现浆料黏度的预测，因此也无法获得锂离子电池浆料在涂膜干燥时段的黏度预测数据。从而也无法帮助用户根据预测的黏度对后续的生产制备过程预先进行调控，不利于提高锂离子电池生产的效果。例如，不利于进行后续生产工艺的控制，也无法预测出后续的流平时间，不利于基于流平时间进行生产控制。
为了解决上述多个问题中的至少一个问题，本发明方案中，获取目标浆料在第一时段内的浆料状态数据，其中，上述目标浆料是用于制备锂离子电池的浆料，上述浆料状态数据包括处理温度、处理剪切力、处理剪切速率以及上述第一时段内的浆料黏度序列数据，上述浆料黏度序列数据包括上述第一时段内的多个不同的采集时刻以及上述目标浆料在各上述采集时刻的黏度数据，上述第一时段包括上述锂离子电池的涂布时段；获取上述目标浆料在第二时段内的目标温度、目标剪切力和目标剪切速率，其中，上述第二时段在上述第一时段之后，且上述第二时段包括上述锂离子电池的涂膜干燥时段；根据上述目标温度、上述目标剪切力、上述目标剪切速率以及上述浆料状态数据，通过已训练的浆料黏度预测模型对上述目标浆料在上述第二时段内的黏度进行预测，并获得上述浆料状态数据在上述目标温度、上述目标剪切力和上述目标剪切速率下对应的浆料黏度预测数据，其中，上述浆料黏度预测数据包括上述第二时段内的至少一个预测时刻以及上述预测时刻对应的预测黏度。
与现有技术只能实时采集锂离子电池浆料的实际黏度的方案相比，本发明中可以结合多种信息（包括采集获得的浆料状态数据、在下一个时间段内的目标温度、目标剪切力和目标剪切速率），实现根据前一个时段的数据预测获得后一个时段的黏度预测数据，有利于实现对锂离子浆料在涂膜干燥时段的黏度的预测。
从而也使得用户可以根据预测获得的下一个时间段的黏度预测数据对后续的生产工艺进行适当地控制和调整以获得用户想要的黏度，即有利于进行后续工艺的控制。进而也有利于提高生产锂离子电池的效率以及生产获得的锂离子电池的性能。
示例性方法
如图1所示，本发明实施例提供一种锂离子电池浆料黏度预测方法，具体的，上述方法包括如下步骤：
步骤S100，获取目标浆料在第一时段内的浆料状态数据，其中，上述目标浆料是用于制备锂离子电池的浆料，上述浆料状态数据包括处理温度、处理剪切力、处理剪切速率以及上述第一时段内的浆料黏度序列数据，上述浆料黏度序列数据包括上述第一时段内的多个不同的采集时刻以及上述目标浆料在各上述采集时刻的黏度数据，上述第一时段包括上述锂离子电池的涂布时段。
具体的，上述目标浆料是需要进行黏度预测的浆料，且具体为用于制备锂离子电池的浆料。本实施例中，采集目标浆料在涂布时段的浆料状态数据，以对目标浆料在涂膜干燥时段的黏度进行预测。
进一步的，上述目标浆料是非牛顿流体，剪切速率、剪切力等数据与黏度之间呈非线性关系，因此本实施例中基于浆料黏度预测模型进行黏度预测。
需要说明的是，上述第一时段可以仅包括锂离子电池的涂布阶段的各个时刻，也可以包括涂布阶段的所有时刻和涂膜干燥阶段的部分时刻。本实施例中以第一时段仅包括涂布阶段的各个时刻为例进行说明，但不作为具体限定。
具体的，如图2所示，上述步骤S100包括如下具体步骤：
步骤S101，通过温度传感器采集获取上述目标浆料在上述第一时段内的处理温度。
步骤S102，通过流变仪采集获取上述目标浆料在上述第一时段内的处理剪切力和处理剪切效率。
步骤S103，通过上述流变仪对上述目标浆料的黏度进行监测，获得在上述第一时段内的多个不同采集时刻的采集黏度。
步骤S104，根据所有上述采集时刻及其对应的采集黏度生成上述浆料黏度序列数据。
具体的，本实施例中，通过预先设置的温度传感器进行处理温度的测量，通过预先设置的流变仪进行处理剪切力和处理剪切效率的测量。同时，在第一时段内通过流变仪对目标浆料的黏度进行持续检测，并采集获得第一时段内的多个不同采集时刻的采集黏度。对于获取的采集黏度，可以先进行特征工程处理，以降低采集数据出现错误的概率。例如，可以删除明显有误的数据，剔除时间过近的时间点等。
具体的，本实施例中，上述根据所有上述采集时刻及其对应的采集黏度生成上述浆料黏度序列数据，包括：根据预设的序列点时间间隔和预设的黏度阈值对上述采集时刻及其对应的采集黏度进行特征工程处理后获得上述浆料黏度序列数据，其中，上述特征工程处理包括数据清洗和/或数据补充。
具体的，上述特征工程处理是预先设置的数据标准化处理过程，可以将采集的数据转换成标准的数据格式。例如，可以预先设置需要的浆料黏度序列数据中的数据个数、每一个采集时刻之间的时间间隔，从而根据时间间隔删除多余的时刻，对于缺失的时刻，则可以根据其前后两个采集时刻对应的黏度模拟计算获得该缺失时刻的黏度并补充进序列数据中，例如根据缺失时刻与前后两个采集时刻之间的时间间隔对前后两个采集时刻的黏度值进行加权平均计算并作为缺失时刻的黏度。在一种应用场景中，还可以删除采集的数据序列中黏度值明显异常的数据（例如黏度出现明显突变时可能是流变仪测量有误，需要剔除有误的数据）。如此，经过特征工程处理之后可以获得更准确并且更便于分析处理的浆料黏度序列数据，有利于提高锂离子电池浆料黏度预测的效率。
可选的，上述浆料状态数据还包括上述目标浆料对应的物料湿含量、上述目标浆料对应的物料固含量、空气湿度、涂布层数和涂布厚度，从而可以进一步结合更多信息，提高锂离子电池浆料黏度预测的准确性。进一步的，上述浆料状态数据还可以包括其它具体数据，在此不作具体限定。
步骤S200，获取上述目标浆料在第二时段内的目标温度、目标剪切力和目标剪切速率，其中，上述第二时段在上述第一时段之后，且上述第二时段包括上述锂离子电池的涂膜干燥时段。
其中，上述第二时段是需要进行黏度预测的时段，目标温度、目标剪切力和目标剪切速率是在第二时段中对目标浆料进行处理时计划使用的温度、剪切力和剪切速率。上述目标温度、目标剪切力和目标剪切速率可以预先设置，也可以由用户实时输入或根据实际需求进行调整，在此不作具体限定。在一种应用场景中，上述目标温度、目标剪切力和目标剪切速率也可以与第一时段中的处理温度、处理剪切力和处理剪切速率相同。在另一种应用场景中，用户想预测在第涂膜干燥时段中采用另一个温度进行处理会对黏度带来什么影响时可以通过调整目标温度并进行黏度预测来实现，从而可以方便用户知晓处理过程中的调整会带来什么影响，从而实现对目标浆料的更好的处理。
步骤S300，根据上述目标温度、上述目标剪切力、上述目标剪切速率以及上述浆料状态数据，通过已训练的浆料黏度预测模型对上述目标浆料在上述第二时段内的黏度进行预测，并获得上述浆料状态数据在上述目标温度、上述目标剪切力和上述目标剪切速率下对应的浆料黏度预测数据，其中，上述浆料黏度预测数据包括上述第二时段内的至少一个预测时刻以及上述预测时刻对应的预测黏度。
本实施例中，将上述目标温度、上述目标剪切力、上述目标剪切速率以及上述浆料状态数据作为浆料黏度预测模型的输入数据，通过浆料黏度预测模型进行浆料黏度预测，根据该模型的输出数据获得黏度预测数据。在一种应用场景中，可以直接将该模型的输出数据作为黏度预测数据。在另一种应用场景中，上述浆料黏度预测模型的输出是时间与黏度对应的曲线数据，可以从曲线数据中选择获取对应的黏度预测数据，例如获取黏度的收敛值作为黏度预测数据。
具体的，上述浆料黏度预测数据包括上述第二时段内的至少一个预测时刻以及上述预测时刻对应的预测黏度。本实施例中，上述浆料黏度预测数据也是一个时间序列数据，其中包括多个预测时刻以及各个预测时刻对应的预测黏度。需要说明的是，浆料黏度预测数据中的第一个预测时刻是第一时段中最后一个采集时刻的下一时刻。
本实施例中，上述浆料黏度预测模型根据如下步骤进行训练：
将训练数据中的浆料状态训练数据、训练目标温度、训练目标剪切力和训练目标剪切速率输入上述浆料黏度预测模型，通过上述浆料黏度预测模型输出上述浆料状态训练数据在上述训练目标温度、上述训练目标剪切力和上述训练目标剪切速率下的浆料黏度预测数据，其中，上述训练数据包括多组模型训练数据组，每一组模型训练数据组包括上述目标浆料在第一时段内的浆料状态训练数据以及上述目标浆料在第二时段内的训练目标温度、训练目标剪切力、训练目标剪切速率和浆料黏度标注数据；
根据上述浆料状态训练数据对应的浆料黏度标注数据和上述浆料状态训练数据对应的浆料黏度预测数据，对上述浆料黏度预测模型的模型参数进行调整，并继续执行上述将训练数据中的浆料状态训练数据、训练目标温度、训练目标剪切力和训练目标剪切速率输入上述浆料黏度预测模型的步骤，直至满足预设训练条件，以得到已训练的浆料黏度预测模型。
需要说明的是，训练数据中的浆料状态训练数据中包含的具体数据的类别与进行黏度预测时采集的浆料状态数据中的具体数据的类别保持一致。上述预设训练条件是预先设置的停止模型训练的条件，可以包括迭代次数达到预设的迭代阈值，或者根据浆料状态训练数据和浆料黏度标注数据，通过预先设置的损失函数计算出的损失值小于预设的损失阈值。
在一种应用场景中，上述浆料黏度预测模型可以是神经网络模型。本实施例中，上述浆料黏度预测模型是XGBOOST模型，上述预设训练条件为模型参数的调整次数不小于1，上述浆料黏度预测模型基于网格搜索法和正则化进行模型参数调整。具体的，本实施例中使用XGBOOST模型，且仅需要进行1次迭代，有利于提高模型训练的效率，从而可以提高黏度预测的效率。
进一步的，上述锂离子电池浆料黏度预测方法还包括：
根据上述浆料状态数据在上述目标温度、上述目标剪切力和上述目标剪切速率下对应的浆料黏度预测数据计算获取上述目标浆料在上述涂膜干燥时段对应的流平时间；其中，上述浆料黏度预测数据是体现预测时刻和预测黏度之间对应关系的曲线数据。
其中，流平时间是流平剂涂料在干燥成膜过程中形成一个流动及干燥成膜过程，然后逐步形成一个平整、光滑、均匀的涂膜的时间。基于上述浆料黏度预测模型以及对应的浆料黏度预测过程可以建立黏度、剪切力、剪切效率和时间之间的关系，从而可以根据黏度的变化预测目标浆料在进行涂膜干燥时的流平时间和性能，基于流平时间可以预测锂离子电池的成产效率，从而判断当前的条件是否能满足生产效率的需求。
在另一种应用场景中，还可以根据预测出的黏度预测数据判断对于第二时段内目标温度、目标剪切力和目标剪切速率的设置是否合适，且可以根据预设的目标黏度和对应的黏度预测数据对上述第二时段内目标温度、目标剪切力和目标剪切速率进行调整，以使得第二时段的黏度尽量贴近目标黏度。
例如在预测出的黏度小于用户想要的黏度时，增大第二时段对应的目标温度，还可以预先设置其它具体控制过程，在此不作具体限定。进一步的，还可以在预测出的黏度与用户想要的黏度的差值大于预设的阈值时发送告警信息，及时提醒用户黏度出现差异，以方便用户及时调整方案，降低损失。
由上可见，本实施例中，可以结合多种信息（包括采集获得的浆料状态数据、在下一个时间段内的目标温度、目标剪切力和目标剪切速率），实现根据前一个时段的数据预测获得后一个时段的黏度预测数据，有利于实现对锂离子浆料在涂膜干燥时段的黏度的预测。
从而也使得用户可以根据预测获得的下一个时间段的黏度预测数据对后续的生产工艺进行适当地控制和调整以获得用户想要的黏度，即有利于进行后续工艺的控制。进而也有利于提高生产锂离子电池的效率以及生产获得的锂离子电池的性能。
示例性设备
如图3中所示，对应于上述锂离子电池浆料黏度预测方法，本发明实施例还提供一种锂离子电池浆料黏度预测装置，上述锂离子电池浆料黏度预测装置包括：
浆料状态数据获取模块410，用于获取目标浆料在第一时段内的浆料状态数据，其中，上述目标浆料是用于制备锂离子电池的浆料，上述浆料状态数据包括处理温度、处理剪切力、处理剪切速率以及上述第一时段内的浆料黏度序列数据，上述浆料黏度序列数据包括上述第一时段内的多个不同的采集时刻以及上述目标浆料在各上述采集时刻的黏度数据，上述第一时段包括上述锂离子电池的涂布时段。
目标条件数据获取模块420，用于获取上述目标浆料在第二时段内的目标温度、目标剪切力和目标剪切速率，其中，上述第二时段在上述第一时段之后，且上述第二时段包括上述锂离子电池的涂膜干燥时段。
黏度预测模块430，用于根据上述目标温度、上述目标剪切力、上述目标剪切速率以及上述浆料状态数据，通过已训练的浆料黏度预测模型对上述目标浆料在上述第二时段内的黏度进行预测，并获得上述浆料状态数据在上述目标温度、上述目标剪切力和上述目标剪切速率下对应的浆料黏度预测数据，其中，上述浆料黏度预测数据包括上述第二时段内的至少一个预测时刻以及上述预测时刻对应的预测黏度。
具体的，本实施例中，上述锂离子电池浆料黏度预测装置及其各模块的具体功能可以参照上述锂离子电池浆料黏度预测方法中的对应描述，在此不再赘述。
需要说明的是，上述锂离子电池浆料黏度预测装置的各个模块的划分方式并不唯一，在此也不作为具体限定。
基于上述实施例，本发明还提供了一种智能终端，其原理框图可以如图4所示。上述智能终端包括处理器及存储器。该智能终端的存储器包括锂离子电池浆料黏度预测程序，存储器为锂离子电池浆料黏度预测程序的运行提供环境。该锂离子电池浆料黏度预测程序被处理器执行时实现上述任意一种锂离子电池浆料黏度预测方法的步骤。需要说明的是，上述智能终端还可以包括其它功能模块或单元，在此不作具体限定。
本领域技术人员可以理解，图4中示出的原理框图，仅仅是与本发明方案相关的部分结构的框图，并不构成对本发明方案所应用于其上的智能终端的限定，具体地智能终端可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
本发明实施例还提供一种计算机可读存储介质，上述计算机可读存储介质上存储有锂离子电池浆料黏度预测程序，上述锂离子电池浆料黏度预测程序被处理器执行时实现本发明实施例提供的任意一种锂离子电池浆料黏度预测方法的步骤。
应理解，上述实施例中各步骤的序号大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本发明实施例的实施过程构成任何限定。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将上述装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。实施例中的各功能单元、模块可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中，上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。另外，各功能单元、模块的具体名称也只是为了便于相互区分，并不用于限制本发明的保护范围。上述装置中单元、模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述或记载的部分，可以参见其它实施例的相关描述。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各实例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟是以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。
在本发明所提供的实施例中，应该理解到，所揭露的装置/智能终端和方法，可以通过其它的方式实现。例如，以上所描述的装置/智能终端实施例仅仅是示意性的，例如，上述模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以由另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个装置，或一些特征可以忽略，或不执行。
上述集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读存储介质中。基于这样的理解，本发明实现上述实施例方法中的全部或部分流程，也可以通过计算机程序来指令相关的硬件来完成，上述计算机程序可存储于一计算机可读存储介质中，该计算机程序在被处理器执行时，可实现上述各个方法实施例的步骤。其中，上述计算机程序包括计算机程序代码，上述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。上述计算机可读介质可以包括：能够携带上述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器（ROM，Read-Only Memory）、随机存取存储器（RAM，Random Access Memory）、电载波信号、电信信号以及软件分发介质等。需要说明的是，上述计算机可读存储介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减。
以上所述实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解；其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不是相应技术方案的本质脱离本发明各实施例技术方案的精神和范围，均应包含在本发明的保护范围之内。

Claims (10)

  1. 一种锂离子电池浆料黏度预测方法，其特征在于，所述方法包括：
    获取目标浆料在第一时段内的浆料状态数据，其中，所述目标浆料是用于制备锂离子电池的浆料，所述浆料状态数据包括处理温度、处理剪切力、处理剪切速率以及所述第一时段内的浆料黏度序列数据，所述浆料黏度序列数据包括所述第一时段内的多个不同的采集时刻以及所述目标浆料在各所述采集时刻的黏度数据，所述第一时段包括所述锂离子电池的涂布时段；
    获取所述目标浆料在第二时段内的目标温度、目标剪切力和目标剪切速率，其中，所述第二时段在所述第一时段之后，且所述第二时段包括所述锂离子电池的涂膜干燥时段；
    根据所述目标温度、所述目标剪切力、所述目标剪切速率以及所述浆料状态数据，通过已训练的浆料黏度预测模型对所述目标浆料在所述第二时段内的黏度进行预测，并获得所述浆料状态数据在所述目标温度、所述目标剪切力和所述目标剪切速率下对应的浆料黏度预测数据，其中，所述浆料黏度预测数据包括所述第二时段内的至少一个预测时刻以及所述预测时刻对应的预测黏度。
  2. 根据权利要求1所述的锂离子电池浆料黏度预测方法，其特征在于，所述获取目标浆料在第一时段内的浆料状态数据，包括：
    通过温度传感器采集获取所述目标浆料在所述第一时段内的处理温度；
    通过流变仪采集获取所述目标浆料在所述第一时段内的处理剪切力和处理剪切效率；
    通过所述流变仪对所述目标浆料的黏度进行监测，获得在所述第一时段内的多个不同采集时刻的采集黏度；
    根据所有所述采集时刻及其对应的采集黏度生成所述浆料黏度序列数据。
  3. 根据权利要求2所述的锂离子电池浆料黏度预测方法，其特征在于，所述根据所有所述采集时刻及其对应的采集黏度生成所述浆料黏度序列数据，包括：
    根据预设的序列点时间间隔和预设的黏度阈值对所述采集时刻及其对应的采集黏度进行特征工程处理后获得所述浆料黏度序列数据，其中，所述特征工程处理包括数据清洗和/或数据补充。
  4. 根据权利要求1所述的锂离子电池浆料黏度预测方法，其特征在于，所述浆料状态数据还包括所述目标浆料对应的物料湿含量、所述目标浆料对应的物料固含量、空气湿度、涂布层数和涂布厚度。
  5. 根据权利要求1所述的锂离子电池浆料黏度预测方法，其特征在于，所述浆料黏度预测模型根据如下步骤进行训练：
    将训练数据中的浆料状态训练数据、训练目标温度、训练目标剪切力和训练目标剪切速率输入所述浆料黏度预测模型，通过所述浆料黏度预测模型输出所述浆料状态训练数据在所述训练目标温度、所述训练目标剪切力和所述训练目标剪切速率下的浆料黏度预测数据，其中，所述训练数据包括多组模型训练数据组，每一组模型训练数据组包括所述目标浆料在第一时段内的浆料状态训练数据以及所述目标浆料在第二时段内的训练目标温度、训练目标剪切力、训练目标剪切速率和浆料黏度标注数据；
    根据所述浆料状态训练数据对应的浆料黏度标注数据和所述浆料状态训练数据对应的浆料黏度预测数据，对所述浆料黏度预测模型的模型参数进行调整，并继续执行所述将训练数据中的浆料状态训练数据、训练目标温度、训练目标剪切力和训练目标剪切速率输入所述浆料黏度预测模型的步骤，直至满足预设训练条件，以得到已训练的浆料黏度预测模型。
  6. 根据权利要求5所述的锂离子电池浆料黏度预测方法，其特征在于，所述浆料黏度预测模型是XGBOOST模型，所述预设训练条件为模型参数的调整次数不小于1，所述浆料黏度预测模型基于网格搜索法和正则化进行模型参数调整。
  7. 根据权利要求1-6任意一项所述的锂离子电池浆料黏度预测方法，其特征在于，所述方法还包括：
    根据所述浆料状态数据在所述目标温度、所述目标剪切力和所述目标剪切速率下对应的浆料黏度预测数据计算获取所述目标浆料在所述涂膜干燥时段对应的流平时间；
    其中，所述浆料黏度预测数据是体现预测时刻和预测黏度之间对应关系的曲线数据。
  8. 一种锂离子电池浆料黏度预测系统，其特征在于，所述系统包括：
    浆料状态数据获取模块，用于获取目标浆料在第一时段内的浆料状态数据，其中，所述目标浆料是用于制备锂离子电池的浆料，所述浆料状态数据包括处理温度、处理剪切力、处理剪切速率以及所述第一时段内的浆料黏度序列数据，所述浆料黏度序列数据包括所述第一时段内的多个不同的采集时刻以及所述目标浆料在各所述采集时刻的黏度数据，所述第一时段包括所述锂离子电池的涂布时段；
    目标条件数据获取模块，用于获取所述目标浆料在第二时段内的目标温度、目标剪切力和目标剪切速率，其中，所述第二时段在所述第一时段之后，且所述第二时段包括所述锂离子电池的涂膜干燥时段；
    黏度预测模块，用于根据所述目标温度、所述目标剪切力、所述目标剪切速率以及所述浆料状态数据，通过已训练的浆料黏度预测模型对所述目标浆料在所述第二时段内的黏度进行预测，并获得所述浆料状态数据在所述目标温度、所述目标剪切力和所述目标剪切速率下对应的浆料黏度预测数据，其中，所述浆料黏度预测数据包括所述第二时段内的至少一个预测时刻以及所述预测时刻对应的预测黏度。
  9. 一种智能终端，其特征在于，所述智能终端包括存储器、处理器以及存储在所述存储器上并可在所述处理器上运行的锂离子电池浆料黏度预测程序，所述锂离子电池浆料黏度预测程序被所述处理器执行时实现如权利要求1-7任意一项所述锂离子电池浆料黏度预测方法的步骤。
  10. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有锂离子电池浆料黏度预测程序，所述锂离子电池浆料黏度预测程序被处理器执行时实现如权利要求1-7任意一项所述锂离子电池浆料黏度预测方法的步骤。
PCT/CN2022/137800 2022-09-28 2022-12-09 锂离子电池浆料黏度预测方法、装置及相关设备 WO2024066053A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211190483.7 2022-09-28
CN202211190483.7A CN115274025B (zh) 2022-09-28 2022-09-28 锂离子电池浆料黏度预测方法、装置及相关设备

Publications (1)

Publication Number Publication Date
WO2024066053A1 true WO2024066053A1 (zh) 2024-04-04

Family

ID=83756917

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/137800 WO2024066053A1 (zh) 2022-09-28 2022-12-09 锂离子电池浆料黏度预测方法、装置及相关设备

Country Status (2)

Country Link
CN (1) CN115274025B (zh)
WO (1) WO2024066053A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115274025B (zh) * 2022-09-28 2022-12-06 深圳先进技术研究院 锂离子电池浆料黏度预测方法、装置及相关设备
CN117872167B (zh) * 2024-03-12 2024-05-14 深圳市杰维工业设备有限公司 一种电池性能影响因素分析方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190323324A1 (en) * 2018-04-20 2019-10-24 Chevron U.S.A. Inc. Partitioning polymer into phases of a microemulsion system
CN110679014A (zh) * 2017-09-28 2020-01-10 株式会社Lg化学 预测电极浆料的工艺性和选择电极粘合剂的方法
CN111737874A (zh) * 2020-06-28 2020-10-02 湖南御家化妆品制造有限公司 一种面膜液粘度预测方法、装置、设备及可读存储介质
CN115046889A (zh) * 2021-03-08 2022-09-13 本田技研工业株式会社 粘度测定系统以及粘度测定方法
CN115274025A (zh) * 2022-09-28 2022-11-01 深圳先进技术研究院 锂离子电池浆料黏度预测方法、装置及相关设备

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113720732B (zh) * 2021-08-20 2022-09-13 中南大学 负极浆料稳定性的预测方法、系统及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110679014A (zh) * 2017-09-28 2020-01-10 株式会社Lg化学 预测电极浆料的工艺性和选择电极粘合剂的方法
US20190323324A1 (en) * 2018-04-20 2019-10-24 Chevron U.S.A. Inc. Partitioning polymer into phases of a microemulsion system
CN111737874A (zh) * 2020-06-28 2020-10-02 湖南御家化妆品制造有限公司 一种面膜液粘度预测方法、装置、设备及可读存储介质
CN115046889A (zh) * 2021-03-08 2022-09-13 本田技研工业株式会社 粘度测定系统以及粘度测定方法
CN115274025A (zh) * 2022-09-28 2022-11-01 深圳先进技术研究院 锂离子电池浆料黏度预测方法、装置及相关设备

Also Published As

Publication number Publication date
CN115274025A (zh) 2022-11-01
CN115274025B (zh) 2022-12-06

Similar Documents

Publication Publication Date Title
WO2024066053A1 (zh) 锂离子电池浆料黏度预测方法、装置及相关设备
US11408942B2 (en) Method for predicting service life of retired power battery
WO2024077754A1 (zh) 储能电池健康状态预测方法、装置及智能终端
CN114114049B (zh) 一种基于样本迁移的锂离子电池寿命预测方法
CN112578298A (zh) 电池温度估算方法、装置、电子设备及存储介质
WO2024066055A1 (zh) 一种双向锂离子电池的寿命预测与状态估计方法
WO2023226355A1 (zh) 基于多源感知的双向锂离子电池故障检测方法及系统
WO2023231356A1 (zh) 一种基于光纤光栅传感器的锂离子电池荷电状态估计方法
CN117577977B (zh) 退役电池包整包再利用控制方法
WO2024060753A1 (zh) 一种基于拼接因子的电化学模型参数辨识方法和系统
CN109033619A (zh) 一种18650型锂电池放电循环的瞬态温度模型建模方法
WO2024055546A1 (zh) 动力电池回收量预测方法、装置及介质
CN204030697U (zh) 基于动态soc估算系统的电池管理系统
CN114035052B (zh) 一种基于能量窗的soc区间标定方法、系统及介质
CN116165547A (zh) 锂电池的电压计算与修正方法及系统、装置、存储介质
Zhang et al. Capacity fading knee-point recognition method and life prediction for lithium-ion batteries using segmented capacity degradation model
WO2024073890A1 (zh) 电池析锂窗口的获取方法、装置、设备、介质和程序产品
CN114636887B (zh) 脱嵌电极板对的状态检测方法、一致性检测方法及装置
CN116794529A (zh) 一种电池微短路检测方法及装置
CN116504322A (zh) 电化学模型获取方法、装置、终端和存储介质
CN105720634A (zh) 一种自学习的充电功率电流控制方法及系统
CN104569840A (zh) 电池单体的老化检测方法和装置
Li et al. Control-oriented implementation and model order reduction of a lithium-ion battery electrochemical model
WO2024207275A1 (zh) 退役电池的梯次利用方法、装置、设备及存储介质
JP2024046206A (ja) 全固体電池の検査方法および検査システム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22960648

Country of ref document: EP

Kind code of ref document: A1