CN116609686B - Battery cell consistency assessment method based on cloud platform big data - Google Patents
Battery cell consistency assessment method based on cloud platform big data Download PDFInfo
- Publication number
- CN116609686B CN116609686B CN202310417467.5A CN202310417467A CN116609686B CN 116609686 B CN116609686 B CN 116609686B CN 202310417467 A CN202310417467 A CN 202310417467A CN 116609686 B CN116609686 B CN 116609686B
- Authority
- CN
- China
- Prior art keywords
- charge
- battery
- equivalent circuit
- circuit model
- power equivalent
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000036541 health Effects 0.000 claims abstract description 52
- 238000011217 control strategy Methods 0.000 claims abstract description 29
- 230000008569 process Effects 0.000 claims abstract description 25
- 238000011156 evaluation Methods 0.000 claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 230000006399 behavior Effects 0.000 claims description 5
- 238000004088 simulation Methods 0.000 claims description 5
- 239000000470 constituent Substances 0.000 claims description 3
- 238000013079 data visualisation Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 4
- 238000007599 discharging Methods 0.000 description 8
- 238000012360 testing method Methods 0.000 description 7
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 4
- 229910001416 lithium ion Inorganic materials 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 239000003792 electrolyte Substances 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000012885 constant function Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000006479 redox reaction Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000005303 weighing Methods 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- G01R31/387—Determining ampere-hour charge capacity or SoC
- G01R31/388—Determining ampere-hour charge capacity or SoC involving voltage measurements
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/389—Measuring internal impedance, internal conductance or related variables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
Abstract
The invention discloses a battery cell consistency assessment method based on cloud platform big data, which comprises the following steps: s1, establishing a cloud platform to be connected with a BMS battery management system, and establishing a battery power equivalent circuit model; s2, importing the parameter data into a battery power equivalent circuit model, and simulating the charge and discharge process of each battery cell by using the battery power equivalent circuit model to generate a corresponding charge and discharge curve; s3, comparing the generated charge-discharge curve with an actual charge-discharge curve obtained by the BMS battery management system, and evaluating the charge state and the health state of each battery cell; and S4, formulating an optimized charge-discharge control strategy based on a prediction model through the evaluation results of the charge state and the health state of each battery cell. The battery power model can output the time sequence of the charge state and the health state of each battery core, understand the state change of the battery and make corresponding decisions.
Description
Technical Field
The invention relates to the field of battery cell evaluation, in particular to a cell consistency evaluation method based on cloud platform big data.
Background
Along with the development of lithium ion battery technology, the application range of the lithium ion battery is wider and wider, and the lithium ion battery is widely applied to the fields of electric vehicles, large power sources and energy storage besides portable electronic products. Except for small portable electronic products, other applications all require the battery voltage to be higher than the voltage of the existing single battery, for example, a pure electric vehicle requires the battery voltage to reach more than 100V, an electric bicycle requires 36 or 48V, and the prepared single batteries are required to be combined for use due to high power output and high capacity. However, due to differences in raw materials, production processes, production batches and manufacturing technologies, the single batteries of the same model and specification have differences in performance parameters such as voltage, capacity, attenuation rate thereof, internal resistance, time-dependent change rate in the charging and discharging processes thereof, service life, self-discharging rate and the like. These differences not only affect the determination of the SOC state of the assembled battery, but more importantly affect the performance and cycle life of the battery, and may even cause safety problems.
The problem of consistency of the battery pack refers to the inconsistency of performance parameters among all single batteries in the battery pack, and mainly comprises the aspects of battery voltage, SOC, ohmic internal resistance, capacity, temperature and the like. Although the batteries are screened before being grouped according to different performance parameters of each single battery. However, it is still impossible to ensure that all the battery cells are completely consistent, and initial inconsistencies may increase cumulatively with the increase of the number of charge and discharge cycles. Resulting in greater differences in the individual cell states (soc, voltage, internal resistance, etc.). Studies have shown that without the protection of the equalization devices. Even though the battery cells may be cycled more than 1000 times. The number of cycles of the battery pack may be less than 200 times. It can be seen that the problem of uniformity among the cells is a major cause of deterioration in the performance of the battery. And (5) effectively evaluating the consistency characterization parameters. Has important significance for battery system management, operation and economy analysis.
The battery pack is composed of a plurality of battery cells, and when the capacity/internal resistance/voltage and other parameters of one battery cell are greatly different from those of other battery cells connected in series and parallel, the problems of capacity loss, service life loss, internal resistance increase and the like can occur. Therefore, the requirement of consistency of the battery cells is important, and the battery cells need to be subjected to consistency screening before assembly. The existing consistency screening of the lithium battery is basically in the aspect of finished batteries, the manufacturing cost of the battery is finished at the moment, and the screened battery with poor consistency cannot be used, so that waste is caused.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides a battery cell consistency assessment method based on cloud platform big data, which aims to overcome the technical problems existing in the related art.
For this purpose, the invention adopts the following specific technical scheme:
a battery cell consistency assessment method based on cloud platform big data comprises the following steps:
s1, establishing a cloud platform to be connected with a BMS battery management system, receiving parameter data uploaded by a battery pack, and establishing a battery power equivalent circuit model;
s2, importing the parameter data into a battery power equivalent circuit model, and simulating the charge and discharge process of each battery cell by using the battery power equivalent circuit model to generate a corresponding charge and discharge curve;
s3, comparing the generated charge-discharge curve with an actual charge-discharge curve obtained by the BMS battery management system, and evaluating the charge state and the health state of each battery cell based on the average absolute error analysis deviation;
and S4, visualizing the evaluation result through the evaluation result of the charge state and the health state of each battery cell, and formulating an optimized charge and discharge control strategy based on the prediction model.
Further, the parameter data comprise real-time voltage data and real-time temperature data of the total voltage, current, state of charge, health state and single battery cells of the battery pack.
Further, the establishing the cloud platform accessing the BMS battery management system, receiving parameter data uploaded by the battery pack, and establishing the battery power equivalent circuit model comprises the following steps:
s11, selecting a cloud computing service provider and building a cloud platform environment;
s12, accessing the BMS battery management system by using a Modbus communication protocol;
s13, data communication between the cloud platform environment and the BMS battery management system is carried out, parameter data uploaded by the battery pack are received, and the parameter data are stored in a cloud database;
s14, establishing a battery power equivalent circuit model according to specific constitution and parameter data of the battery pack, and analyzing the characteristics of voltage, current, power, charge state and health state of the battery pack;
and S15, establishing a MARS model, and optimizing parameter data of a battery power equivalent circuit model by using the MARS model according to the real-time voltage data and the real-time temperature data of the battery pack.
Further, the method for establishing a battery power equivalent circuit model according to the specific composition and parameter data of the battery pack and analyzing the characteristics of the voltage, current, power, charge state and health state of the battery pack comprises the following steps:
s141, determining constituent components of the battery pack according to the number, the connection mode and the model information of the battery cells, and reading parameter data uploaded by the battery pack in the cloud data;
s142, selecting a P2D model to establish a circuit model according to the actual situation of the battery pack;
s143, importing the acquired parameter data of each cell into a circuit model, and constructing a battery power equivalent circuit model of the battery pack;
s144, judging the service life and the health state of the battery pack through analysis of the charge state characteristics;
s145, judging the service life, the capacity decay rate and the damage condition of the battery cell of the battery pack through analysis of the health state characteristics.
Further, the method comprises the following steps:
in the method, in the process of the invention,voltage prediction variables of battery power equivalent circuit model parameter data;
current prediction variables of battery power equivalent circuit model parameter data;
power prediction variables of battery power equivalent circuit model parameter data;
predicting variables for the charge states of the battery power equivalent circuit model parameter data;
predicting variables for the health states of the battery power equivalent circuit model parameter data;
a o open circuit voltage in the battery power equivalent circuit model;
b o open circuit current in the battery power equivalent circuit model;
c o open circuit power in the battery power equivalent circuit model;
d o open circuit charge state in the battery power equivalent circuit model;
e o open state of health in the battery power equivalent circuit model;
a m 、b m 、c m 、d m e m Respectively weighing the mth parameter data in the battery power equivalent circuit model;
S m (x) The method comprises the steps of (1) performing a function of mth parameter data in a battery power equivalent circuit model;
m is the number of parameter data;
m is the number of basis functions in each input variable.
Further, the establishing the MARS model, and optimizing the parameter data of the battery power equivalent circuit model by using the MARS model according to the real-time voltage data and the real-time temperature data of the battery pack comprises the following steps:
s151, collecting real-time voltage data and real-time temperature data of the battery pack;
s152, establishing an initial battery power equivalent circuit model;
s153, taking voltage data and temperature data as input, taking actual current as output, and training and optimizing by using a MARS model to obtain new battery power equivalent circuit model parameter data;
and S154, inputting the optimized battery power equivalent circuit model parameter data into the original battery power equivalent circuit model to finish the parameter data optimization of the battery power equivalent circuit model.
Further, the step of importing the parameter data into a battery power equivalent circuit model, and using the battery power equivalent circuit model to simulate the charge and discharge process of each cell, and generating a corresponding charge and discharge curve includes the following steps:
s21, determining parameter data of a battery power equivalent circuit model, and importing the parameter data of the battery pack into the battery power equivalent circuit model;
s22, simulating the charge and discharge process of each battery cell by using a battery power equivalent circuit model;
s23, in the simulation process, recording parameter data of voltage, current and charge state in a charge-discharge curve of each battery cell;
s24, generating a corresponding charge-discharge curve according to the voltage, current and charge state parameter data in the charge-discharge curve of each cell.
Further, the comparing the generated charge-discharge curve with an actual charge-discharge curve obtained by the BMS battery management system, and analyzing the deviation based on the average absolute error, and evaluating the charge state and the health state of each cell includes the following steps:
s31, acquiring an actual charge-discharge curve obtained by the BMS battery management system, and comparing the actual charge-discharge curve with the generated charge-discharge curve;
s32, determining a time range to be compared, selecting the same time point in the charge-discharge curves according to the time range, and recording the voltage value or the current value of the two curves at the same time point;
s33, for each time point, calculating the absolute value of the difference of the two curves at the time point;
and S34, summing the difference values at all the time points, and dividing the sum by the time points to obtain the value of the average absolute error.
Further, the calculating, for each time point, the absolute value of the difference between the two curves at that time point includes the steps of:
s331, determining a time range of a curve to be compared, and selecting the same time point;
s332, recording a voltage value or a current value of an actual charge-discharge curve at the time point, and recording the voltage value or the current value of the generated charge-discharge curve at the time point;
s333, subtracting the generated charge-discharge curve voltage value from the actual charge-discharge curve voltage value to calculate the absolute value of the difference between the two curves at the time point;
s334, repeating the steps S331-S333 until all the selected time points are compared.
Further, the step of visualizing the evaluation result through the evaluation result of the charge state and the health state of each cell and formulating an optimized charge-discharge control strategy based on the prediction model comprises the following steps:
s41, collecting evaluation result data of the charge state and the health state of each battery cell according to the evaluation result;
s42, utilizing a data visualization tool to visually display the charge state and the health state data of the battery cell;
s43, predicting the future charge and discharge behaviors of the battery pack based on the prediction model;
s44, an optimized charge and discharge control strategy is formulated according to the prediction result and the charge and discharge performance characteristics of the battery pack;
s45, applying the formulated charge and discharge control strategy to the battery pack, and implementing the corresponding control strategy.
The beneficial effects of the invention are as follows:
1. the invention adopts the battery power equivalent circuit model to consider the influence of various physical processes in the battery, such as electrolyte concentration, polar plate thickness, temperature, pressure and the like, so the behavior of the battery can be more accurately described, the distribution parameters in the battery power model can be adjusted according to the physical state in the battery, so different battery designs and working conditions can be more flexibly dealt with, the application range of the battery power model can be expanded by increasing the description of the physical processes in the battery, such as redox reaction, electrode deformation and the like, and the battery power model can output the time sequence of the charge state and the health state of each battery core, so the state change of the battery can be intuitively known and corresponding decisions can be made.
2. According to the invention, the difference between the generated charge-discharge curve and the actual charge-discharge curve can be analyzed by comparing the charge-discharge curve and the actual charge-discharge curve, and the charge state and the health state of each battery cell are estimated based on the average absolute error analysis deviation, so that the accuracy of a model prediction result is estimated; the charge and discharge states of each battery cell can be tracked and analyzed by recording the voltage value or the current value of the two curves at the same time point and calculating the absolute value of the difference of the two curves at the time point, so that support is provided for the follow-up optimization of the charge and discharge control strategy; the charge state and the health state of each battery cell can be evaluated based on the average absolute error analysis deviation, so that frequent physical detection and test cost is avoided, and cost and time expenditure are reduced; the actual charge and discharge curves obtained by the BMS battery management system are obtained in real time and compared with the generated charge and discharge curves, so that the charge and discharge state of each battery cell can be analyzed in real time, and support is provided for real-time monitoring and management of the battery.
3. The invention visualizes the evaluation results of the battery charge state and the health state, so that the data are more visual and easier to understand, and the user can monitor and manage the state of the battery pack conveniently. In addition, the charging and discharging control strategy optimized through the prediction model can help a user to better manage the charging and discharging process of the battery pack, prolong the service life of the battery pack and improve the performance and safety of the battery pack. Meanwhile, an optimized charge and discharge control strategy formulated based on the prediction model can be adjusted according to the real-time state of the battery pack, so that the battery pack is always in an optimal state, and the efficiency and stability of the battery pack are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for evaluating cell consistency based on cloud platform big data according to an embodiment of the present invention.
Detailed Description
For the purpose of further illustrating the various embodiments, the present invention provides the accompanying drawings, which are a part of the disclosure of the present invention, and which are mainly used to illustrate the embodiments and, together with the description, serve to explain the principles of the embodiments, and with reference to these descriptions, one skilled in the art will recognize other possible implementations and advantages of the present invention, wherein elements are not drawn to scale, and like reference numerals are generally used to designate like elements.
According to the embodiment of the invention, a battery cell consistency assessment method based on cloud platform big data is provided.
The invention will be further described with reference to the accompanying drawings and the specific embodiments, as shown in fig. 1, a method for evaluating consistency of a battery cell based on big data of a cloud platform according to an embodiment of the invention, where the method for evaluating consistency of a battery cell includes the following steps:
s1, establishing a cloud platform to be connected with a BMS battery management system, receiving parameter data uploaded by a battery pack, and establishing a battery power equivalent circuit model;
in one embodiment, the parameter data includes real-time voltage data and real-time temperature data for the total voltage, current, state of charge, state of health, and cell of the battery pack.
In one embodiment, the establishing the cloud platform accessing the BMS battery management system, receiving the parameter data uploaded by the battery pack, and establishing the battery power equivalent circuit model includes the following steps:
s11, selecting a cloud computing service provider and building a cloud platform environment;
s12, accessing the BMS battery management system by using a Modbus communication protocol;
s13, data communication between the cloud platform environment and the BMS battery management system is carried out, parameter data uploaded by the battery pack are received, and the parameter data are stored in a cloud database;
s14, establishing a battery power equivalent circuit model according to specific constitution and parameter data of the battery pack, and analyzing the characteristics of voltage, current, power, charge state and health state of the battery pack;
and S15, establishing a MARS model, and optimizing parameter data of a battery power equivalent circuit model by using the MARS model according to the real-time voltage data and the real-time temperature data of the battery pack.
Specifically, constructing a battery power equivalent circuit model includes the following steps: acquiring voltage, current, temperature and other data of the battery under different working conditions by using professional testing equipment to acquire a large amount of battery testing data; preprocessing the collected battery test data, including noise removal, interpolation, filtering and other processing, so as to facilitate the subsequent modeling; determining parameters in the equivalent circuit model, including resistance, capacitance, inductance and the like, according to the experimental data and the selected equivalent circuit model type; fitting the battery test data with parameters of the battery power equivalent circuit model by using a regression analysis or machine learning method to obtain a final equivalent circuit model; the new test data is used for verifying and adjusting the model, so that the accuracy and the reliability of the model are ensured; the constructed battery power equivalent circuit model is applied to a battery management system and used for the aspects of state estimation and prediction, charge and discharge control and the like of the battery.
In one embodiment, the method for establishing a battery power equivalent circuit model according to the specific composition and parameter data of the battery pack and analyzing the characteristics of the voltage, current, power, charge state and health state of the battery pack comprises the following steps:
s141, determining constituent components of the battery pack according to the number, the connection mode and the model information of the battery cells, and reading parameter data uploaded by the battery pack in the cloud data;
s142, selecting a P2D model to establish a circuit model according to the actual situation of the battery pack;
s143, importing the acquired parameter data of each cell into a circuit model, and constructing a battery power equivalent circuit model of the battery pack;
s144, judging the service life and the health state of the battery pack through analysis of the charge state characteristics;
s145, judging the service life, the capacity decay rate and the damage condition of the battery cell of the battery pack through analysis of the health state characteristics.
In one embodiment, the building formula for building the MARS model is:
in the method, in the process of the invention,voltage prediction variables of battery power equivalent circuit model parameter data; />Current prediction variables of battery power equivalent circuit model parameter data;
work for battery power equivalent circuit model parameter dataA rate prediction variable;
predicting variables for the charge states of the battery power equivalent circuit model parameter data;
predicting variables for the health states of the battery power equivalent circuit model parameter data;
a o open circuit voltage in the battery power equivalent circuit model;
b o open circuit current in the battery power equivalent circuit model;
c o open circuit power in the battery power equivalent circuit model;
d o open circuit charge state in the battery power equivalent circuit model;
e o open state of health in the battery power equivalent circuit model;
a m 、b m 、c m 、d m e m Respectively weighing the mth parameter data in the battery power equivalent circuit model;
S m (x) The method comprises the steps of (1) performing a function of mth parameter data in a battery power equivalent circuit model;
m is the number of parameter data;
m is the number of basis functions in each input variable.
In one embodiment, the establishing the MARS model, and optimizing the parameter data of the battery power equivalent circuit model by using the MARS model according to the real-time voltage data and the real-time temperature data of the battery pack includes the following steps:
s151, collecting real-time voltage data and real-time temperature data of the battery pack;
s152, establishing an initial battery power equivalent circuit model;
s153, taking voltage data and temperature data as input, taking actual current as output, and training and optimizing by using a MARS model to obtain new battery power equivalent circuit model parameter data;
and S154, inputting the optimized battery power equivalent circuit model parameter data into the original battery power equivalent circuit model to finish the parameter data optimization of the battery power equivalent circuit model.
In particular, the P2D model refers to a "perforated two-dimensional" model, as it models the battery cells as a layered structure with air perforations and 2D geometry. The P2D model is based on electrochemical thermodynamics and conservation of mass, taking into account interactions between the anode and cathode of the cell and diffusion and migration processes between the electrode and electrolyte. The P2D model can be used to predict parameters such as voltage, current, temperature, and state of a lithium ion battery, and is widely used in battery design, performance optimization, and control strategy formulation.
MARS (Multivariate Adaptive Regression Splines, multivariate adaptive regression spline) is a non-parametric regression method used to model the non-linear relationship between variables. It can adapt to different types and forms of data and improve the fit and predictive power of the model while maintaining the model interpretability. The basic idea of the MARS model is to divide the data into a number of local regions, each fitted with a basis function. The basis functions include both constant functions and piecewise polynomial functions (PWL). The piecewise polynomial function is formed by splicing a plurality of polynomial functions, and coefficients of each polynomial function can be automatically learned by an algorithm. The MARS model is built in two stages: a forward phase and a backward phase. The forward phase starts with a simple constant function, increasing one basis function at a time until a predetermined number of basis functions is reached or a certain stopping criterion is met. The backward stage reduces the model and improves generalization by gradually deleting unnecessary basis functions. The MARS model is capable of adaptively processing non-linear and high-dimensional data, has good interpretability, and can be used for classification and regression problems, etc. In a battery management system, a MARS model can be used to build a battery equivalent circuit model and dynamically optimize based on real-time battery data.
S2, importing the parameter data into a battery power equivalent circuit model, and simulating the charge and discharge process of each battery cell by using the battery power equivalent circuit model to generate a corresponding charge and discharge curve;
in one embodiment, the step of importing the parameter data into a battery power equivalent circuit model and using the battery power equivalent circuit model to simulate the charge and discharge process of each cell, and generating the corresponding charge and discharge curve includes the following steps:
s21, determining parameter data of a battery power equivalent circuit model, and importing the parameter data of the battery pack into the battery power equivalent circuit model;
s22, simulating the charge and discharge process of each battery cell by using a battery power equivalent circuit model;
s23, in the simulation process, recording parameter data of voltage, current and charge state in a charge-discharge curve of each battery cell;
s24, generating a corresponding charge-discharge curve according to the voltage, current and charge state parameter data in the charge-discharge curve of each cell.
Specifically, the specific parameter data and input/output parameters of the battery power equivalent circuit model, and the specific form and parameter data of the MARS model used in the invention can be adjusted and optimized according to specific conditions. Meanwhile, when the battery power equivalent circuit model is used for simulating the battery charging and discharging process, the influence of various factors on the battery performance, such as temperature, discharging rate and the like, needs to be considered so as to improve the accuracy and reliability of the model.
S3, comparing the generated charge-discharge curve with an actual charge-discharge curve obtained by the BMS battery management system, and evaluating the charge state and the health state of each battery cell based on the average absolute error analysis deviation;
in one embodiment, the comparing the generated charge-discharge curve with the actual charge-discharge curve obtained by the BMS battery management system, and analyzing the deviation based on the average absolute error, and evaluating the charge state and the health state of each cell includes the following steps:
s31, acquiring an actual charge-discharge curve obtained by the BMS battery management system, and comparing the actual charge-discharge curve with the generated charge-discharge curve;
s32, determining a time range to be compared, selecting the same time point in the charge-discharge curves according to the time range, and recording the voltage value or the current value of the two curves at the same time point;
s33, for each time point, calculating the absolute value of the difference of the two curves at the time point;
and S34, summing the difference values at all the time points, and dividing the sum by the time points to obtain the value of the average absolute error.
In one embodiment, said calculating, for each point in time, the absolute value of the difference of the two curves at that point in time comprises the steps of:
s331, determining a time range of a curve to be compared, and selecting the same time point;
s332, recording a voltage value or a current value of an actual charge-discharge curve at the time point, and recording the voltage value or the current value of the generated charge-discharge curve at the time point;
s333, subtracting the generated charge-discharge curve voltage value from the actual charge-discharge curve voltage value to calculate the absolute value of the difference between the two curves at the time point;
s334, repeating the steps S331-S333 until all the selected time points are compared.
Specifically, the Mean Absolute Error (MAE) is an indicator that measures the error between two consecutive variables. It calculates the average of the absolute error between the predicted value and the actual value. When comparing the generated charge-discharge curve with the actual charge-discharge curve, the deviation between the two curves can be analyzed using the average absolute error. The method comprises the following specific steps: and acquiring an actual charge-discharge curve and a generated charge-discharge curve, determining a time range to be compared, selecting the same time point in the charge-discharge curve according to the time range, and recording the voltage value or the current value of the two curves at the same time point. For each time point, the absolute value of the difference of the two curves at that time point is calculated. The differences at all time points are summed and divided by the number of time points to obtain the value of the average absolute error. And analyzing the value of the average absolute error, and judging the deviation between the two curves. And (3) evaluating the charge state and the health state of each battery cell according to the analysis result, and further formulating an optimized charge and discharge control strategy.
S4, visualizing the evaluation result through the evaluation result of the charge state and the health state of each battery cell, and formulating an optimized charge-discharge control strategy based on a prediction model;
in one embodiment, the method for visualizing the evaluation result through the evaluation result of the charge state and the health state of each cell and formulating the optimized charge-discharge control strategy based on the prediction model comprises the following steps:
s41, collecting evaluation result data of the charge state and the health state of each battery cell according to the evaluation result;
s42, utilizing a data visualization tool to visually display the charge state and the health state data of the battery cell;
s43, predicting the future charge and discharge behaviors of the battery pack based on the prediction model;
s44, an optimized charge and discharge control strategy is formulated according to the prediction result and the charge and discharge performance characteristics of the battery pack;
s45, applying the formulated charge and discharge control strategy to the battery pack, and implementing the corresponding control strategy.
Specifically, a charge state and a health state prediction result of each cell are obtained based on the prediction model. And analyzing the prediction result of each cell to determine which cells need to be charged or discharged preferentially and the charge and discharge rate to be controlled. And (3) according to the charge and discharge performance characteristics of the battery pack, a charge and discharge control strategy is formulated, including charge and discharge rate, charge and discharge time, charge and discharge capacity and the like. And performing simulation calculation aiming at different charge and discharge control strategies, and evaluating the effect of the charge and discharge control strategies in practical application. And (3) adjusting the charge-discharge control strategy according to the simulation calculation result, and verifying and optimizing until the optimal charge-discharge control strategy is obtained.
In summary, by means of the above technical solution of the present invention, the present invention adopts the battery power equivalent circuit model to consider the influence of various physical processes inside the battery, such as the concentration of electrolyte, the thickness of the electrode plate, the temperature, the pressure, etc., so that the behavior of the battery can be described more accurately, the distribution parameters in the battery power model can be adjusted according to the physical state inside the battery, so that different battery designs and working conditions can be dealt with more flexibly, the battery power model can expand the application range thereof by increasing the description of the physical processes inside the battery, such as considering the redox reaction, electrode deformation, etc., and the battery power model can output the time sequence of the state of charge and the state of health of each battery, so that the state change of the battery can be known intuitively, and corresponding decisions can be made; according to the invention, the difference between the generated charge-discharge curve and the actual charge-discharge curve can be analyzed by comparing the charge-discharge curve and the actual charge-discharge curve, and the charge state and the health state of each battery cell are estimated based on the average absolute error analysis deviation, so that the accuracy of a model prediction result is estimated; the charge and discharge states of each battery cell can be tracked and analyzed by recording the voltage value or the current value of the two curves at the same time point and calculating the absolute value of the difference of the two curves at the time point, so that support is provided for the follow-up optimization of the charge and discharge control strategy; the charge state and the health state of each battery cell can be evaluated based on the average absolute error analysis deviation, so that frequent physical detection and test cost is avoided, and cost and time expenditure are reduced; the actual charge and discharge curves obtained by the BMS battery management system are obtained in real time and compared with the generated charge and discharge curves, so that the charge and discharge state of each battery cell can be analyzed in real time, and support is provided for real-time monitoring and management of the battery; the invention visualizes the evaluation results of the battery charge state and the health state, so that the data are more visual and easier to understand, and the user can monitor and manage the state of the battery pack conveniently. In addition, the charging and discharging control strategy optimized through the prediction model can help a user to better manage the charging and discharging process of the battery pack, prolong the service life of the battery pack and improve the performance and safety of the battery pack. Meanwhile, an optimized charge and discharge control strategy formulated based on the prediction model can be adjusted according to the real-time state of the battery pack, so that the battery pack is always in an optimal state, and the efficiency and stability of the battery pack are improved.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (7)
1. The battery cell consistency assessment method based on the cloud platform big data is characterized by comprising the following steps of:
s1, establishing a cloud platform to be connected with a BMS battery management system, receiving parameter data uploaded by a battery pack, and establishing a battery power equivalent circuit model;
s2, importing the parameter data into a battery power equivalent circuit model, and simulating the charge and discharge process of each battery cell by using the battery power equivalent circuit model to generate a corresponding charge and discharge curve;
s3, comparing the generated charge-discharge curve with an actual charge-discharge curve obtained by the BMS battery management system, and evaluating the charge state and the health state of each battery cell based on the average absolute error analysis deviation;
s4, visualizing the evaluation result through the evaluation result of the charge state and the health state of each battery cell, and formulating an optimized charge-discharge control strategy based on a prediction model;
the method for establishing the cloud platform is connected with the BMS battery management system, receives parameter data uploaded by the battery pack, and establishes a battery power equivalent circuit model, and comprises the following steps:
s11, selecting a cloud computing service provider and building a cloud platform environment;
s12, accessing the BMS battery management system by using a Modbus communication protocol;
s13, data communication between the cloud platform environment and the BMS battery management system is carried out, parameter data uploaded by the battery pack are received, and the parameter data are stored in a cloud database;
s14, establishing a battery power equivalent circuit model according to specific constitution and parameter data of the battery pack, and analyzing the characteristics of voltage, current, power, charge state and health state of the battery pack;
s15, establishing a MARS model, and optimizing parameter data of a battery power equivalent circuit model by utilizing the MARS model according to the real-time voltage data and the real-time temperature data of the battery pack;
the method for establishing the battery power equivalent circuit model according to the specific constitution and parameter data of the battery pack and analyzing the characteristics of the voltage, the current, the power, the charge state and the health state of the battery pack comprises the following steps:
s141, determining constituent components of the battery pack according to the number, the connection mode and the model information of the battery cells, and reading parameter data uploaded by the battery pack in the cloud data;
s142, selecting a P2D model to establish a circuit model according to the actual situation of the battery pack;
s143, importing the acquired parameter data of each cell into a circuit model, and constructing a battery power equivalent circuit model of the battery pack;
s144, judging the service life and the health state of the battery pack through analysis of the charge state characteristics;
s145, judging the service life, capacity attenuation rate and damage condition of the battery cell of the battery pack through analysis of the health state characteristics;
the method comprises the steps of importing parameter data into a battery power equivalent circuit model, simulating the charge and discharge process of each battery cell by using the battery power equivalent circuit model, and generating a corresponding charge and discharge curve, wherein the method comprises the following steps of:
s21, determining parameter data of a battery power equivalent circuit model, and importing the parameter data of the battery pack into the battery power equivalent circuit model;
s22, simulating the charge and discharge process of each battery cell by using a battery power equivalent circuit model;
s23, in the simulation process, recording parameter data of voltage, current and charge state in a charge-discharge curve of each battery cell;
s24, generating a corresponding charge-discharge curve according to the voltage, current and charge state parameter data in the charge-discharge curve of each cell.
2. The method for evaluating the consistency of cells based on the big data of the cloud platform according to claim 1, wherein the parameter data comprises real-time voltage data and real-time temperature data of total voltage, current, state of charge, health state and single cells of the battery pack.
3. The method for evaluating the consistency of cells based on big data of a cloud platform according to claim 1, wherein the building formula for building a MARS model is as follows:
in the method, in the process of the invention,voltage prediction variables of battery power equivalent circuit model parameter data; />Current prediction variables of battery power equivalent circuit model parameter data;
power prediction variables of battery power equivalent circuit model parameter data;
predicting variables for the charge states of the battery power equivalent circuit model parameter data; />Predicting variables for the health states of the battery power equivalent circuit model parameter data; ao is the open circuit voltage in the battery power equivalent circuit model;
bo is the open circuit current in the battery power equivalent circuit model;
co is the open circuit power in the battery power equivalent circuit model;
do is the open state of charge in the battery power equivalent circuit model;
eo is the open state of health in the battery power equivalent circuit model;
am, bm, cm, dm and em are respectively the weight of the mth parameter data in the battery power equivalent circuit model;
S m (x) The method comprises the steps of (1) performing a function of mth parameter data in a battery power equivalent circuit model;
m is the number of parameter data;
m is the number of basis functions in each input variable.
4. The method for evaluating the consistency of the battery cells based on the big data of the cloud platform according to claim 1, wherein the establishing the MARS model and optimizing the parameter data of the battery power equivalent circuit model by using the MARS model according to the real-time voltage data and the real-time temperature data of the battery pack comprises the following steps:
s151, collecting real-time voltage data and real-time temperature data of the battery pack;
s152, establishing an initial battery power equivalent circuit model;
s153, taking voltage data and temperature data as input, taking actual current as output, and training and optimizing by using a MARS model to obtain new battery power equivalent circuit model parameter data;
and S154, inputting the optimized battery power equivalent circuit model parameter data into the original battery power equivalent circuit model to finish the parameter data optimization of the battery power equivalent circuit model.
5. The method for evaluating the consistency of the battery cells based on the cloud platform big data according to claim 1, wherein the comparing the generated charge-discharge curve with the actual charge-discharge curve obtained by the BMS battery management system, and evaluating the charge state and the health state of each battery cell based on the average absolute error analysis deviation comprises the following steps:
s31, acquiring an actual charge-discharge curve obtained by the BMS battery management system, and comparing the actual charge-discharge curve with the generated charge-discharge curve;
s32, determining a time range to be compared, selecting the same time point in the charge-discharge curves according to the time range, and recording the voltage value or the current value of the two curves at the same time point;
s33, for each time point, calculating the absolute value of the difference of the two curves at the time point;
and S34, summing the difference values at all the time points, and dividing the sum by the time points to obtain the value of the average absolute error.
6. The method for evaluating the consistency of cells based on big data of a cloud platform according to claim 5, wherein for each time point, calculating the absolute value of the difference between two curves at the time point comprises the following steps:
s331, determining a time range of a curve to be compared, and selecting the same time point;
s332, recording a voltage value or a current value of an actual charge-discharge curve at the time point, and recording the voltage value or the current value of the generated charge-discharge curve at the time point;
s333, subtracting the generated charge-discharge curve voltage value from the actual charge-discharge curve voltage value to calculate the absolute value of the difference between the two curves at the time point;
s334, repeating the steps S331-S333 until all the selected time points are compared.
7. The method for evaluating the consistency of the cells based on the cloud platform big data according to claim 1, wherein the step of visualizing the evaluation result through the evaluation result of the charge state and the health state of each cell and formulating the optimized charge-discharge control strategy based on the prediction model comprises the following steps:
s41, collecting evaluation result data of the charge state and the health state of each battery cell according to the evaluation result;
s42, utilizing a data visualization tool to visually display the charge state and the health state data of the battery cell;
s43, predicting the future charge and discharge behaviors of the battery pack based on the prediction model;
s44, an optimized charge and discharge control strategy is formulated according to the prediction result and the charge and discharge performance characteristics of the battery pack;
s45, applying the formulated charge and discharge control strategy to the battery pack, and implementing the corresponding control strategy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310417467.5A CN116609686B (en) | 2023-04-18 | 2023-04-18 | Battery cell consistency assessment method based on cloud platform big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310417467.5A CN116609686B (en) | 2023-04-18 | 2023-04-18 | Battery cell consistency assessment method based on cloud platform big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116609686A CN116609686A (en) | 2023-08-18 |
| CN116609686B true CN116609686B (en) | 2024-01-05 |
Family
ID=87680804
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310417467.5A Active CN116609686B (en) | 2023-04-18 | 2023-04-18 | Battery cell consistency assessment method based on cloud platform big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116609686B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117129899B (en) * | 2023-08-31 | 2024-05-10 | 重庆跃达新能源有限公司 | Battery health state prediction management system and method |
Citations (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103077291A (en) * | 2013-01-25 | 2013-05-01 | 华北电力大学 | Battery charge and discharge process digital simulation method capable of setting initial state of charge |
| CN108544925A (en) * | 2018-04-02 | 2018-09-18 | 北京理工大学 | Battery management system |
| CN110456279A (en) * | 2019-08-15 | 2019-11-15 | 长安大学 | A kind of power battery cloud management system based on data-driven model |
| CN111007417A (en) * | 2019-12-06 | 2020-04-14 | 重庆大学 | Battery pack SOH and RUL prediction method and system based on inconsistency evaluation |
| CN111027165A (en) * | 2019-07-19 | 2020-04-17 | 北京航空航天大学 | Power battery pack management system and method based on digital twinning |
| WO2020115761A1 (en) * | 2018-12-06 | 2020-06-11 | Sosaley Technologies Pvt. Ltd. | Cloud-based battery management system to predict battery life and battery health |
| CN112331941A (en) * | 2020-11-20 | 2021-02-05 | 中国科学技术大学 | Cloud auxiliary battery management system and method |
| CN112433169A (en) * | 2020-11-25 | 2021-03-02 | 北京理工新源信息科技有限公司 | Cloud power battery health degree evaluation system and method |
| CN112711892A (en) * | 2020-12-07 | 2021-04-27 | 深圳先进技术研究院 | Cloud battery management system and method based on digital twin and block chain technology |
| CN112732443A (en) * | 2021-01-12 | 2021-04-30 | 徐州普罗顿氢能储能产业研究院有限公司 | Energy storage power station state evaluation and operation optimization system based on edge calculation |
| CN112838631A (en) * | 2020-12-31 | 2021-05-25 | 上海玫克生储能科技有限公司 | Dynamic charging management and control device for power battery and charging diagnosis method for power battery |
| CN112883531A (en) * | 2019-11-29 | 2021-06-01 | 比亚迪股份有限公司 | Lithium ion battery data processing method, computer device and storage medium |
| CN112881930A (en) * | 2021-01-19 | 2021-06-01 | 北京昆兰新能源技术有限公司 | Energy storage battery health management prediction method and system based on Internet of things |
| CN112946499A (en) * | 2021-02-04 | 2021-06-11 | 芜湖楚睿智能科技有限公司 | Lithium battery health state and charge state joint estimation method based on machine learning |
| CN113075554A (en) * | 2021-03-26 | 2021-07-06 | 国网浙江省电力有限公司电力科学研究院 | Lithium ion battery pack inconsistency identification method based on operation data |
| CN113176505A (en) * | 2021-04-30 | 2021-07-27 | 重庆长安新能源汽车科技有限公司 | On-line estimation method and device for state of charge and state of health of vehicle-mounted power battery and storage medium |
| CN113419187A (en) * | 2021-06-08 | 2021-09-21 | 上海交通大学 | Lithium ion battery health estimation method |
| CN113671382A (en) * | 2021-09-06 | 2021-11-19 | 中国科学院电工研究所 | Battery energy storage system state estimation method based on cloud-end digital twinning |
| CN113835032A (en) * | 2021-09-15 | 2021-12-24 | 北京理工新源信息科技有限公司 | Remote fault diagnosis and early warning system for pure electric vehicle |
| CN114035072A (en) * | 2021-11-11 | 2022-02-11 | 重庆大学 | Battery pack multi-state joint estimation method based on cloud edge cooperation |
| CN114152884A (en) * | 2021-12-29 | 2022-03-08 | 联方云天科技(北京)有限公司 | Intelligent evaluation and dynamic adjustment method based on BMS big data of lithium battery pack |
| KR20220099415A (en) * | 2021-01-06 | 2022-07-13 | 연세대학교 산학협력단 | Apparatus and method for improving high speed charging efficiency of battery based on Artificial Neural Network |
| KR20220125445A (en) * | 2021-03-05 | 2022-09-14 | 연세대학교 산학협력단 | Battery Management System, Apparatus and Method for Providing Adaptive Model Therefor |
| WO2022253038A1 (en) * | 2021-06-02 | 2022-12-08 | 上海玫克生储能科技有限公司 | Method and system for predicting state of health of lithium battery on basis of elastic network, and device and medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3995346A1 (en) * | 2020-11-10 | 2022-05-11 | Tata Consultancy Services Limited | Method and system for optimizing operation of battery pack of an electric vehicle |
-
2023
- 2023-04-18 CN CN202310417467.5A patent/CN116609686B/en active Active
Patent Citations (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103077291A (en) * | 2013-01-25 | 2013-05-01 | 华北电力大学 | Battery charge and discharge process digital simulation method capable of setting initial state of charge |
| CN108544925A (en) * | 2018-04-02 | 2018-09-18 | 北京理工大学 | Battery management system |
| WO2020115761A1 (en) * | 2018-12-06 | 2020-06-11 | Sosaley Technologies Pvt. Ltd. | Cloud-based battery management system to predict battery life and battery health |
| CN111027165A (en) * | 2019-07-19 | 2020-04-17 | 北京航空航天大学 | Power battery pack management system and method based on digital twinning |
| CN110456279A (en) * | 2019-08-15 | 2019-11-15 | 长安大学 | A kind of power battery cloud management system based on data-driven model |
| CN112883531A (en) * | 2019-11-29 | 2021-06-01 | 比亚迪股份有限公司 | Lithium ion battery data processing method, computer device and storage medium |
| CN111007417A (en) * | 2019-12-06 | 2020-04-14 | 重庆大学 | Battery pack SOH and RUL prediction method and system based on inconsistency evaluation |
| CN112331941A (en) * | 2020-11-20 | 2021-02-05 | 中国科学技术大学 | Cloud auxiliary battery management system and method |
| CN112433169A (en) * | 2020-11-25 | 2021-03-02 | 北京理工新源信息科技有限公司 | Cloud power battery health degree evaluation system and method |
| CN112711892A (en) * | 2020-12-07 | 2021-04-27 | 深圳先进技术研究院 | Cloud battery management system and method based on digital twin and block chain technology |
| CN112838631A (en) * | 2020-12-31 | 2021-05-25 | 上海玫克生储能科技有限公司 | Dynamic charging management and control device for power battery and charging diagnosis method for power battery |
| KR20220099415A (en) * | 2021-01-06 | 2022-07-13 | 연세대학교 산학협력단 | Apparatus and method for improving high speed charging efficiency of battery based on Artificial Neural Network |
| CN112732443A (en) * | 2021-01-12 | 2021-04-30 | 徐州普罗顿氢能储能产业研究院有限公司 | Energy storage power station state evaluation and operation optimization system based on edge calculation |
| CN112881930A (en) * | 2021-01-19 | 2021-06-01 | 北京昆兰新能源技术有限公司 | Energy storage battery health management prediction method and system based on Internet of things |
| CN112946499A (en) * | 2021-02-04 | 2021-06-11 | 芜湖楚睿智能科技有限公司 | Lithium battery health state and charge state joint estimation method based on machine learning |
| KR20220125445A (en) * | 2021-03-05 | 2022-09-14 | 연세대학교 산학협력단 | Battery Management System, Apparatus and Method for Providing Adaptive Model Therefor |
| CN113075554A (en) * | 2021-03-26 | 2021-07-06 | 国网浙江省电力有限公司电力科学研究院 | Lithium ion battery pack inconsistency identification method based on operation data |
| CN113176505A (en) * | 2021-04-30 | 2021-07-27 | 重庆长安新能源汽车科技有限公司 | On-line estimation method and device for state of charge and state of health of vehicle-mounted power battery and storage medium |
| WO2022253038A1 (en) * | 2021-06-02 | 2022-12-08 | 上海玫克生储能科技有限公司 | Method and system for predicting state of health of lithium battery on basis of elastic network, and device and medium |
| CN113419187A (en) * | 2021-06-08 | 2021-09-21 | 上海交通大学 | Lithium ion battery health estimation method |
| CN113671382A (en) * | 2021-09-06 | 2021-11-19 | 中国科学院电工研究所 | Battery energy storage system state estimation method based on cloud-end digital twinning |
| CN113835032A (en) * | 2021-09-15 | 2021-12-24 | 北京理工新源信息科技有限公司 | Remote fault diagnosis and early warning system for pure electric vehicle |
| CN114035072A (en) * | 2021-11-11 | 2022-02-11 | 重庆大学 | Battery pack multi-state joint estimation method based on cloud edge cooperation |
| CN114152884A (en) * | 2021-12-29 | 2022-03-08 | 联方云天科技(北京)有限公司 | Intelligent evaluation and dynamic adjustment method based on BMS big data of lithium battery pack |
Non-Patent Citations (4)
| Title |
|---|
| Cloud Platform-Oriented Electrical Vehicle Abnormal Battery Cell Detection and Pack Consistency Evaluation With Big Data: Devising an Early-Warning System for Latent Risks;Peng Liu，et.;< IEEE Industry Applications Magazine>;全文 * |
| Data-Driven Fault Diagnosis in Battery Systems Through Cross-Cell Monitoring;Michael Schmid;<IEEE SENSORS JOURNAL>;全文 * |
| 基于云平台的电池管理系统设计与实现;赵熙等;《机械与电子》;全文 * |
| 基于数据挖掘的动力电池一致性与健康状态研究;李一帆;《中国优秀硕士学位论文全文数据库》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116609686A (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Guo et al. | Online estimation of SOH for lithium-ion battery based on SSA-Elman neural network | |
| CN114372417A (en) | Electric vehicle battery health state and remaining life evaluation method based on charging network | |
| CN109001640B (en) | Data processing method and device for power battery | |
| CN111948560A (en) | Lithium battery health state estimation method based on multi-factor evaluation model | |
| CN110941929A (en) | Battery health state assessment method based on ARMA and Elman neural network combined modeling | |
| CN110082682B (en) | Lithium battery state of charge estimation method | |
| CN112904219B (en) | Big data-based power battery health state prediction method | |
| CN116609686B (en) | Battery cell consistency assessment method based on cloud platform big data | |
| AU2021101964A4 (en) | Artificial intelligence based smart electric vehicle battery management system | |
| CN116609676B (en) | Method and system for monitoring state of hybrid energy storage battery based on big data processing | |
| CN114114038A (en) | Lithium battery SOC and available capacity joint estimation method under full-life and full-temperature conditions | |
| CN115586444A (en) | Lithium battery residual life prediction method based on VMD and BP neural network | |
| CN109299552A (en) | A kind of appraisal procedure and its assessment system of battery power status | |
| Long et al. | Multi-parameter optimization method for remaining useful life prediction of lithium-ion batteries | |
| CN114280490B (en) | Lithium ion battery state of charge estimation method and system | |
| Xue et al. | Battery degradation modelling and prediction with combination of machine learning and semi-empirical methods | |
| Chen et al. | State of health estimation of lithium-ion batteries based on equivalent circuit model and data-driven method | |
| Cao et al. | A flexible battery capacity estimation method based on partial voltage curves and polynomial fitting | |
| CN110232432B (en) | Lithium battery pack SOC prediction method based on artificial life model | |
| CN112327169B (en) | Lithium battery residual life prediction method | |
| Singh et al. | State of charge estimation techniques of Li-ion battery of electric vehicles | |
| US20230305073A1 (en) | Method and apparatus for providing a predicted aging state of a device battery based on a predicted usage pattern | |
| CN117420442A (en) | MNQ-LSTM-based battery remaining life prediction method | |
| CN115951225A (en) | Battery equalization optimization capacity estimation method and device | |
| Zhang et al. | The early prediction of lithium-ion battery remaining useful life using a novel long short-term memory network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |