CN110850315A - Method and device for estimating state of charge of battery - Google Patents
Method and device for estimating state of charge of battery Download PDFInfo
- Publication number
- CN110850315A CN110850315A CN201911205084.1A CN201911205084A CN110850315A CN 110850315 A CN110850315 A CN 110850315A CN 201911205084 A CN201911205084 A CN 201911205084A CN 110850315 A CN110850315 A CN 110850315A
- Authority
- CN
- China
- Prior art keywords
- battery
- charge
- state
- sample
- model
- 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.)
- Pending
Links
Images
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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
Abstract
The embodiment of the invention provides a method and a device for estimating the state of charge of a battery, which are applied to the technical field of batteries, wherein the method comprises the following steps: obtaining the battery parameters of the target battery at the current moment; and inputting the battery parameters into a preset state of charge estimation model to obtain the state of charge of the target battery at the current moment. Therefore, the accuracy of the state of charge of the battery can be improved by applying the method for estimating the state of charge of the battery provided by the embodiment of the invention.
Description
Technical Field
The invention relates to the technical field of batteries, in particular to a method and a device for estimating the state of charge of a battery.
Background
The State of Charge (SOC) of a power battery is one of important parameters for representing the State of the battery, and accurate measurement of the SOC is a guarantee for reasonably utilizing the battery, improving the service life and efficiency of the battery and reducing the operation cost. Therefore, the research on the efficient and accurate SOC algorithm of the battery, particularly the SOC algorithm suitable for the current popular lithium ion power battery, has important practical significance and application value.
The charging and discharging process of the lithium ion battery of the electric automobile is a nonlinear process with violent change, which puts higher requirements on accurate estimation of the SOC of the battery. In addition, due to the influence of many external factors on the SOC calculation result, the conventional SOC estimation strategy cannot meet the actual use requirement. Therefore, the research on the SOC algorithm of the power battery, which is suitable for complex working conditions, high in precision and high in efficiency is one of the key links in the development process of the electric automobile at present.
Since the SOC of the battery cannot be directly measured, the SOC of the battery at that time can be inferred only by detecting its external characteristics (such as battery voltage, battery current, battery internal resistance, battery temperature, etc.). Currently, the prior art proposes an ampere-hour measurement method, which is a method designed based on the "black box" principle, as the most commonly used SOC estimation method. The method regards the battery as a whole, namely a black box which exchanges energy with the outside of the battery, and records the change of the energy of the black box by integrating the current flowing in and out of the black box in time. The method only needs to meter the electric energy into and out of the battery, and does not need to consider the influence of the change of the internal state of the battery in the black box and other factors. Such as: setting the charge-discharge initial state as SOC0Then, the expression of the SOC of the current state is:
wherein, CNFor rated capacity, I is the battery current and η is the charge-discharge efficiency.
From the above expression, the ampere-hour measurement method has a major problem in application that if the current measurement is not accurate, the charge-discharge initial state SOC will be caused0Large error and further dependence on SOC0The SOC error of each moment obtained by iteration is large, and the error becomes larger and larger after long-term iteration accumulation. In addition, in consideration of the charge-discharge efficiency of the battery, at high temperatureIn the case of severe state and current fluctuations, the error will be larger. It can be seen that the SOC accuracy obtained by the prior art is low.
Disclosure of Invention
The embodiment of the invention aims to provide a method and a device for estimating a battery state of charge, so as to improve the accuracy of the battery state of charge. The specific technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a method for estimating a state of charge of a battery, where the method includes:
obtaining battery parameters of a target battery at the current moment;
inputting the battery parameters into a preset state of charge estimation model to obtain the state of charge of the target battery at the current moment, wherein the state of charge estimation model is a model which is obtained by training a preset battery model by using a first sample battery and is used for estimating the state of charge of the battery at the current moment; the battery model is a model for characterizing the state of charge of the battery determined by the battery state of charge of the battery parameter at each historical time using the battery parameter of the second sample battery based on a linear regression technique.
In one embodiment of the invention, the battery parameters include: open circuit voltage, charge and discharge current, battery temperature and charge and discharge times.
In one embodiment of the invention, the battery model is obtained by:
obtaining sample battery parameters of a second sample battery, wherein the sample battery parameters comprise open-circuit voltage, charge-discharge current, battery temperature and charge-discharge times;
based on a linear regression technology, establishing a battery model of the following expression according to the obtained sample battery parameters;
the expression is:
where M is a battery model for characterizing the state of charge SOC of the battery, f (-) represents a battery model function,
k(xiis) a support vector xiV is open circuit voltage, I is charge-discharge current, T is battery temperature, N is number of charge-discharge cycles, aiFor the weight of the ith sample battery parameter in predicting the state of charge of the sample battery,
the estimated weight of the ith sample battery parameter in predicting the state of charge of the sample battery, and b is the error parameter of the sample battery parameter in estimating the state of charge of the battery.
In one embodiment of the invention, the state of charge estimation model is obtained by:
obtaining sample battery parameters of a first sample battery, wherein the sample battery parameters comprise open-circuit voltage, charge and discharge current, battery temperature and charge and discharge times;
obtaining marking information of the state of charge of a second sample battery;
and training the battery model by using the obtained sample battery parameters based on the labeling information to obtain a state of charge estimation model for estimating the state of charge of a battery at the current moment.
In a second aspect, an embodiment of the present invention provides a battery state of charge estimation apparatus, including:
the battery parameter obtaining module is used for obtaining the battery parameters of the target battery at the current moment;
the state of charge budget module is used for inputting the battery parameters into a preset state of charge estimation model to obtain the state of charge of the target battery at the current moment, wherein the state of charge estimation model is a model which is obtained by training a preset battery model by using a first sample battery and is used for estimating the state of charge of the battery at the current moment; the battery model is a model for characterizing the state of charge of the battery determined by the battery state of charge of the battery parameter at each historical time using the battery parameter of the second sample battery based on a linear regression technique.
In one embodiment of the invention, the battery parameters include: open circuit voltage, charge and discharge current, battery temperature and charge and discharge times.
In one embodiment of the present invention, the apparatus further comprises: a battery model obtaining module, wherein the battery model obtaining module comprises:
the first battery parameter obtaining submodule is used for obtaining sample battery parameters of a second sample battery, wherein the sample battery parameters comprise open-circuit voltage, charge-discharge current, battery temperature and charge-discharge times;
the battery model obtaining submodule is used for establishing a battery model of the following expression according to the obtained sample battery parameters based on a linear regression technology;
the expression is:
where M is a battery model for characterizing the state of charge SOC of the battery, f (-) represents a battery model function,
k(xiis) a support vector xiV is open circuit voltage, I is charge-discharge current, T is battery temperature, N is number of charge-discharge cycles, aiFor the weight of the ith sample battery parameter in predicting the state of charge of the sample battery,the estimated weight of the ith sample battery parameter in predicting the state of charge of the sample battery, and b is the error parameter of the sample battery parameter in estimating the state of charge of the battery.
In one embodiment of the present invention, the apparatus further comprises: a state of charge estimation module, wherein the state of charge estimation module comprises:
the second battery parameter obtaining submodule is used for obtaining sample battery parameters of the first sample battery, wherein the sample battery parameters comprise open-circuit voltage, charge-discharge current, battery temperature and charge-discharge times;
the labeling information obtaining submodule is used for obtaining labeling information of the state of charge of the first sample battery;
and the state of charge estimation model obtaining submodule is used for training the battery model by utilizing the obtained sample battery parameters based on the marking information to obtain a state of charge estimation model for estimating the state of charge of a battery at the current moment.
An embodiment of the present invention provides an electronic device, including: the system comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
the memory is used for storing a computer program;
the processor is configured to implement any one of the steps of the method for estimating the state of charge of the battery when executing the program stored in the memory.
An embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method for estimating a state of charge of a battery according to any one of the above-mentioned steps is implemented.
The method for estimating the state of charge of the battery provided by the embodiment of the invention comprises the steps of obtaining the battery parameters of a target battery at the current moment; and inputting the battery parameters into a preset state of charge estimation model to obtain the state of charge of the target battery at the current moment. Therefore, the accuracy of the state of charge of the battery can be improved by applying the scheme provided by the embodiment of the invention. Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart illustrating a method for estimating a state of charge of a battery according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a process for obtaining a battery model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a battery model acquisition according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating a battery model verification according to an embodiment of the present invention;
FIG. 5 is a schematic flow chart of a state of charge estimation model according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of an apparatus for estimating a state of charge of a battery according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
First, the method for estimating the state of charge of the battery according to the embodiment of the present invention will be described in detail.
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for estimating a state of charge of a battery according to an embodiment of the present invention, including the following steps:
and S101, obtaining the battery parameters of the target battery at the current moment.
The electric charges are positive or negative charges of the object or particles constituting the object, the positively charged particles are called positive charges (the symbol is "+"), and the negatively charged particles are called negative charges (the symbol is "+").
The real-time online SOC estimation method of various battery packs has the defects that the actual use requirement cannot be met. This is mainly because the estimation of the SOC of the battery pack is related to many factors (such as temperature, charging and discharging state at the previous time, polarization effect, battery life, etc.), and has strong nonlinearity, which all bring great difficulty to the real-time online estimation of the SOC. Therefore, in order to improve the accuracy of real-time online estimation of SOC, intensive research on measurement means, battery models, estimation methods, and the like is required.
The battery parameters refer to performance indexes of the battery, such as a charge state, a health state, an internal resistance, a self-discharge rate, a temperature characteristic and the like, and generally comprise open-circuit voltage, a self-discharge rate, battery temperature, charge and discharge current, battery capacity, battery nominal voltage, battery internal resistance, battery charge termination voltage, battery discharge termination voltage, battery self-discharge rate, aging degree and the like.
The open-circuit voltage is a terminal voltage of the battery in an open-circuit state, that is, the open-circuit voltage of the battery is equal to a difference between a positive electrode potential and a negative electrode potential of the battery when the battery is in an open circuit state. The battery is disconnected when no current passes through the two poles.
The self-discharge rate is also called charge retention capacity, and refers to the retention capacity of the electric quantity stored in the battery under a certain condition when the battery is in an open circuit state.
The battery temperature is a battery surface heating phenomenon caused by chemical, electrochemical change, electron transfer, substance transmission and the like of an internal structure of the battery when the battery is used.
The charge and discharge current is the product of the rated capacity and the charge and discharge rate of the battery, wherein the charge and discharge rate is used for representing the charge and discharge capacity rate of the battery, for example: 1C represents the current intensity when the battery is completely charged and discharged for one hour, that is, the one-hour continuous charging and discharging manner of the chargeable and dischargeable battery is performed in units of the nominal capacity of the battery, for example: a cell capacity of 2200MAH, then when discharged with a current of 2200MA, 1C discharge mode. In addition, there are 2C, 3C, and the like, which are methods for obtaining the magnitude of the detected actual capacity of the battery.
The aging degree is how long the battery can be used once to measure the aging degree of the battery, and the aging degree of the battery can also be represented by using the charging and discharging times.
The State of Charge (SOC) of a power battery is one of important parameters for representing the State of the battery, and accurate measurement of the SOC is a guarantee for reasonably utilizing the battery, improving the service life and efficiency of the battery and reducing the operation cost.
S102, inputting the battery parameters into a preset state of charge estimation model to obtain the state of charge of the target battery at the current moment, wherein the state of charge estimation model is a model which is obtained by training a preset battery model by using a first sample battery and is used for estimating the state of charge of one battery at the current moment; the battery model is a model for characterizing the state of charge of the battery determined by the battery state of charge of the battery parameter at each historical time using the battery parameter of the second sample battery based on a linear regression technique.
The first sample battery and the second sample battery may be the same sample battery, or different sample batteries, or may be partially the same sample battery, or partially different sample batteries, which is not limited in this embodiment.
The SOC estimation model can obtain the output value of the SOC of the target battery at the current moment by inputting the sample battery as an input value into the battery model, and determines whether the parameters of the battery model need to be adjusted for retraining by inputting the output value and the actual battery parameter value of the first sample battery into the loss model and judging whether the loss model converges.
And performing linear regression on the battery parameters of each first sample battery to obtain a battery model representing the state of charge of one battery.
Through research, many factors influencing the accurate measurement of the SOC are found, wherein the open-circuit voltage, the temperature, the charge-discharge current aging degree and the like are closely related to the SOC. Neglecting the effect of any one of these factors in the estimation of SOC will make the estimated SOC error larger.
In addition, the aging degree of the battery can be represented by selecting the charging and discharging times.
Experiments show that the SOC of the battery has a relatively obvious corresponding relation with the open-circuit voltage. The self-recovery phenomenon occurs after the discharge pulse is stopped, and the battery voltage rapidly rises in a short time, but a certain time is required for the recovery to a stable open circuit voltage, and the length of the time is closely related to the SOC state before the discharge is stopped, the magnitude of the operating current, and the rate of change of the operating current. Through experiments, the corresponding relation between the open-circuit voltage and the SOC required by the model and the corresponding relation between the open-circuit voltage and the self-recovery effect can be obtained.
The ambient temperature has a large influence on the SOC of the battery. The lower the ambient temperature, the less the amount of dischargeable electricity and the lower the discharge efficiency. Through a large number of experiments, the corresponding relation between the temperature factor in the SOC model and the SOC can be established.
The charge-discharge efficiency is also closely related to the battery SOC. Generally, the charge/discharge efficiency of a battery decreases with an increase in charge/discharge current, i.e., the efficiency is high in charge/discharge at a small current and is low in charge/discharge at a large current. If the charge-discharge efficiency change caused by the current change is not considered, a large error occurs in the measured electric quantity. Based on the above analysis, it is necessary to consider the influence of the charge and discharge current on the battery SOC.
The number of times of charge and discharge of the battery is also one of the important factors that affect the SOC estimation. In the initial stage of the battery, the dischargeable electric quantity is reduced rapidly along with the increase of the cycle life of the battery; after a certain cycle life is reached, the trend of the dischargeable electricity quantity descending is slowed down along with the increase of the cycle life of the battery, and the characteristic of the dischargeable electricity quantity tending to be flat is shown; in the later period of the battery use, the dischargeable electric quantity is reduced rapidly along with the increase of the cycle life of the battery, and the aging acceleration phenomenon occurs. If the influence of the aging factors of the battery is not considered, the SOC error estimated in the initial stage and the later stage of the use of the battery reaches about 20 percent, and obviously, the charging and discharging times of the battery are also important factors influencing the SOC estimation.
Through the above analysis, in an embodiment of the present invention, the battery parameters may include: open circuit voltage, charge and discharge current, battery temperature and charge and discharge times.
In this embodiment, the open circuit voltage, the charge and discharge current, the battery temperature, and the number of charge and discharge are all battery parameters, but the battery parameters are not limited to the open circuit voltage, the charge and discharge current, the battery temperature, and the number of charge and discharge, and may include other parameters.
It can be seen that the battery parameters of the embodiment include open-circuit voltage, charge and discharge current, battery temperature and charge and discharge times, and the state of charge estimation model trained by the open-circuit voltage, the charge and discharge current, the battery temperature and the charge and discharge times and the established battery model are closer to a real battery, so that the accuracy of estimating the state of charge of the battery can be improved.
Therefore, according to the estimation method of the state of charge of the battery provided by the embodiment of the invention, the battery parameters of the target battery at the current moment are obtained; and inputting the battery parameters into a preset state of charge estimation model to obtain the state of charge of the target battery at the current moment. Therefore, the accuracy of the state of charge of the battery can be improved by applying the scheme provided by the embodiment of the invention.
In an embodiment of the present invention, as shown in fig. 2, the battery model may be obtained through S1021 to S1022, specifically:
s1021, obtaining sample battery parameters of a second sample battery, wherein the sample battery parameters comprise open-circuit voltage, charge and discharge current, battery temperature and charge and discharge times;
the sample battery parameters are corresponding to each first sample battery.
The sample battery parameters may be sample battery parameters at different historical times.
Illustratively, s second sample cells are provided, namely a sample cell 1, a sample cell 2, … … and a sample cell s, wherein s is a positive integer.
The open circuit voltage, the charge and discharge current, the battery temperature and the number of charge and discharge at the history time of the sample battery 1, the open circuit voltage, the charge and discharge current, the battery temperature and the number of charge and discharge at the history time of the sample battery 2, … …, the open circuit voltage, the charge and discharge current, the battery temperature and the number of charge and discharge at the history time of the sample battery s are obtained.
In order to make the present embodiment easier to understand, now referring to fig. 3 as an example for description, as shown in fig. 3, the sample battery parameters, i.e., open-circuit voltage, charge-discharge current, battery temperature and charge-discharge frequency, of the second sample battery on the left side in fig. 3, and the battery SOC on the right side are the battery state of charge corresponding to the left sample battery parameter at the same time, and based on a linear regression technique, a battery model for representing the battery state of charge is established by using the left sample battery parameter and the right sample battery SOC, that is, the correlation mapping relationship between the battery parameters and the SOC in different states can be obtained.
After the battery model is established, in order to improve the accuracy of the model, the established battery model is verified, as shown in fig. 4, in order to improve the accuracy, a sample battery different from a second sample battery may be used, a sample battery parameter of the sample battery and a state of charge at the same time as the sample battery parameter are used, the sample battery parameter is input into the established battery model, a state of charge at the same time as the sample battery parameter output by the battery model is obtained, whether the state of charge at the same time as the actual state of charge at the same time of the sample battery parameter output by the battery model is verified, if yes, the established battery model is feasible, and if not, the established battery model is revised again to make the established battery model feasible.
S1022, based on the linear regression technology, according to the obtained sample battery parameters, a battery model of the following expression is established;
the expression is:
where M is a battery model for characterizing the state of charge SOC of the battery, f (-) represents a battery model function,
k(xiis) a support vector xiV is open circuit voltage, I is charge-discharge current, T is battery temperature, N is number of charge-discharge cycles, aiFor the weight of the ith sample battery parameter in predicting the state of charge of the sample battery,
the estimated weight of the ith sample battery parameter in predicting the state of charge of the sample battery, and b is the error parameter of the sample battery parameter in estimating the state of charge of the battery.
In the above expression, (V, I, T, N) is the input parameter of f (-),
and b are known parameters of f (-) respectively.
The support vector can be understood as: in the support vector machine, a few training sample points which are closest to the hyperplane and meet a preset condition.
The support vector machine is a generalized linear classifier for binary classification of data in a supervised learning mode, and a decision boundary of the support vector machine is a maximum margin hyperplane for solving learning samples.
For sample battery parameters of a first sample battery, based on a linear regression technology, setting an estimation equation of the SoC as follows:
f(x)＝wΦ(x)+b (1)
wherein, f (-) represents a battery model function, w and b represent the importance degree parameter of each sample battery parameter when estimating the battery charge state, b represents the error parameter of the sample battery parameter when estimating the battery charge state, phi (-) represents the high-order transformation function of the support quantity corresponding to the sample battery parameter, and x is the input parameter.
Statistical learning method based on small samples, the purpose of which is to find suitable parameters w and b such that the error R of regressionreg(f) Minimum, wherein, regression error Rreg(f) Comprises the following steps:
where Γ [ · ] in equation (2) is a cost function, C is a penalty, C is a constant, and the vector w is represented by equation (3).
In the formula (3), n represents the total amount of the supported sample battery parameter; phi (x)i) Represents the support amount xiHigher order transformation function of, xiFor the supported amount of the ith supported sample battery parameter,
the handle type (3) is substituted into the formula (1) with
In the formula (4), x is a sample battery parameter, k (x)iAnd x) is a kernel function. Kernel function k (x)iX) makes the low-dimensional spatial data linearly separable in the high-dimensional space after a certain mapping Φ.
In the process of charging and discharging the battery, parameters such as open-circuit voltage V, charging and discharging current I, temperature T, charging and discharging times N and the like are considered, and a battery model can be established as
Wherein each oneAs corresponding to kernel function k (x)iX), at the start of training, the appropriate kernel function form, penalty C, and error-free radius ξ need to be selected.
The error-free radius ξ may be set according to a user acceptable range in practical applications.
It can be seen that, in the present embodiment, a battery model of the above expression is established according to the sample battery parameters of the first sample battery based on the linear regression technology, where the model is determined based on the open-circuit voltage, the charge-discharge current, the temperature, and the number of charge-discharge times as the sample battery parameters.
In an embodiment of the present invention, as shown in fig. 5, a state of charge estimation model can be obtained through S1023 to S1025, specifically:
and S1023, obtaining sample battery parameters of the first sample battery, wherein the sample battery parameters comprise open-circuit voltage, charge-discharge current, temperature and charge-discharge times.
The sample cell parameters are corresponding to each first sample cell.
The sample battery parameters may be sample battery parameters at different historical times.
Illustratively, j first sample cells, namely a sample cell 1, a sample cell 2, … … and a sample cell j are provided, and j is a positive integer.
The open circuit voltage, the charge and discharge current, the battery temperature and the number of charge and discharge at the history time of the sample battery 1, the open circuit voltage, the charge and discharge current, the battery temperature and the number of charge and discharge at the history time of the sample battery 2, … …, the open circuit voltage, the charge and discharge current, the battery temperature and the number of charge and discharge at the history time of the sample battery j are obtained.
And S1024, obtaining marking information of the state of charge of the first sample battery.
The labeled information may be the actual state of charge of each sample battery of the first sample battery at each historical time.
And S1025, training the battery model by using the obtained sample battery parameters based on the labeling information to obtain a state of charge estimation model for estimating the state of charge of a battery at the current moment.
And taking the sample battery parameters corresponding to the second sample battery as a training set, and adjusting the model parameters of the battery model by using the training set to obtain a state of charge estimation model for estimating the state of charge of the battery at the current moment as an output value.
The state of charge estimation model can be verified by using sample battery parameters different from those of the second sample battery as a verification set, so that a more accurate state of charge estimation model is obtained.
Based on the limited number of the sample batteries, the state of charge estimation model can be verified by using part of sample battery parameters of the second sample battery and part of sample battery parameters of the sample batteries different from the second sample battery as a verification set, so as to obtain a more accurate state of charge estimation model.
As can be seen, in the embodiment, the battery model is trained by using the obtained sample battery parameters based on the obtained labeling information, so as to obtain a state of charge estimation model for estimating the state of charge of a battery at the current time. The state of charge estimation model is obtained by training a battery model based on open-circuit voltage, charge-discharge current, battery temperature and charge-discharge times as sample battery parameters, so that the accuracy of battery state of charge estimation can be improved by the state of charge estimation model.
Corresponding to the estimation method of the state of charge of the battery, the embodiment of the invention also provides an estimation device of the state of charge of the battery.
Referring to fig. 6, fig. 6 is a schematic structural diagram of an apparatus for estimating a state of charge of a battery according to an embodiment of the present invention, where the apparatus may include:
a battery parameter obtaining module 401, configured to obtain a battery parameter of the target battery at the current time;
the state of charge budgeting module 402 is configured to input the battery parameters into a preset state of charge estimation model to obtain the state of charge of the target battery at the current time, where the state of charge estimation model is a model obtained by training a preset battery model by using a first sample battery and is used for estimating the state of charge of one battery at the current time; the battery model is a model determined using battery parameters of a second sample battery based on a linear regression technique.
In one embodiment of the present invention, the battery parameters may include: open circuit voltage, charge and discharge current, battery temperature and charge and discharge times.
In an embodiment of the present invention, the apparatus may further include: a battery model obtaining module, wherein the battery model obtaining module comprises:
a first battery parameter obtaining submodule for obtaining sample battery parameters of a second sample battery, wherein the sample battery parameters include: open circuit voltage, charge-discharge current, battery temperature and charge-discharge times;
the battery model obtaining submodule is used for establishing a battery model SOC of the following expression according to the obtained sample battery parameters based on a linear regression technology;
the expression is:
where M is a battery model for characterizing the state of charge SOC of the battery, f (-) represents a battery model function,
k(xiis) a support vector xiV is open circuit voltage, I is charge-discharge current, T is battery temperature, N is number of charge-discharge cycles, aiFor the weight of the ith sample battery parameter in predicting the state of charge of the sample battery,
predicting the charge state of the sample battery for the ith sample battery parameterThe estimated weight at state, b is the error parameter of the sample battery parameter when estimating the battery state of charge.
In an embodiment of the present invention, the apparatus may further include: a state of charge estimation module, wherein the state of charge estimation module comprises:
the second battery parameter obtaining submodule is used for obtaining sample battery parameters of the first sample battery, wherein the sample battery parameters comprise open-circuit voltage, charge-discharge current, battery temperature and charge-discharge times;
the labeling information obtaining submodule is used for obtaining labeling information of the state of charge of the first sample battery;
and the state of charge estimation model obtaining submodule is used for training the battery model by utilizing the obtained sample battery parameters based on the marking information to obtain a state of charge estimation model for estimating the state of charge of a battery at the current moment.
Therefore, the device for estimating the state of charge of the battery provided by the embodiment of the invention obtains the battery parameters of the target battery at the current moment; and inputting the battery parameters into a preset state of charge estimation model to obtain the state of charge of the target battery at the current moment. Therefore, the accuracy of the state of charge of the battery can be improved by applying the scheme provided by the embodiment of the invention.
An embodiment of the present invention further provides an electronic device, referring to fig. 7, where fig. 7 is a structural diagram of the electronic device according to the embodiment of the present invention, including: the system comprises a processor 501, a communication interface 502, a memory 503 and a communication bus 504, wherein the processor 501, the communication interface 502 and the memory 503 are communicated with each other through the communication bus 504;
a memory 503 for storing a computer program;
the processor 501 is configured to implement the steps of any of the above methods for estimating the state of charge of the battery when executing the program stored in the memory 503.
Specifically, the method for estimating the state of charge of the battery includes:
obtaining battery parameters of a target battery at the current moment;
inputting the battery parameters into a preset state of charge estimation model to obtain the state of charge of the target battery at the current moment, wherein the state of charge estimation model is a model which is obtained by training a preset battery model by using a first sample battery and is used for estimating the state of charge of the battery at the current moment; the battery model is based on a linear regression technique, and a model for characterizing the state of charge of the battery is determined using the battery parameters of the second sample battery.
Therefore, the electronic device provided by the embodiment is implemented by obtaining the battery parameters of the target battery at the current moment; and inputting the battery parameters into a preset state of charge estimation model to obtain the state of charge of the target battery at the current moment. Therefore, the accuracy of the state of charge of the battery can be improved by applying the scheme provided by the embodiment of the invention.
The above-mentioned embodiment of estimating the state of charge of the battery is the same as the method for estimating the state of charge of the battery provided in the foregoing embodiment of the method, and the details are not repeated here.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component.
In yet another embodiment of the present invention, a computer-readable storage medium is provided, which stores instructions that, when executed on a computer, cause the computer to perform the method for estimating the state of charge of a battery according to any one of the above embodiments.
In yet another embodiment of the present invention, there is provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform any of the above described methods of estimating a state of charge of a battery.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the device, the electronic device and the readable storage medium embodiments, since they are substantially similar to the method embodiments, the description is simple, and the relevant points can be referred to the partial description of the method embodiments.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (10)
1. A method of estimating state of charge of a battery, the method comprising:
obtaining battery parameters of a target battery at the current moment;
inputting the battery parameters into a preset state of charge estimation model to obtain the state of charge of the target battery at the current moment, wherein the state of charge estimation model is a model which is obtained by training a preset battery model by using a first sample battery and is used for estimating the state of charge of the battery at the current moment; the battery model is a model for characterizing the state of charge of the battery determined by the battery state of charge of the battery parameter at each historical time using the battery parameter of the second sample battery based on a linear regression technique.
2. The method of claim 1, wherein the battery parameters comprise: open circuit voltage, charge and discharge current, battery temperature and charge and discharge times.
3. The method of claim 2, wherein the battery model is obtained by:
obtaining sample battery parameters of a second sample battery, wherein the sample battery parameters comprise open-circuit voltage, charge-discharge current, battery temperature and charge-discharge times;
based on a linear regression technology, establishing a battery model of the following expression according to the obtained sample battery parameters and the battery charge state of the second sample battery at each historical moment;
the expression is:
where M is a battery model for characterizing the state of charge SOC of the battery, f (-) represents a battery model function,
k(xiis) a support vector xiV is open circuit voltage, I is charge-discharge current, T is battery temperature, N is number of charge-discharge cycles, aiFor the weight of the ith sample battery parameter in predicting the state of charge of the sample battery,
the estimated weight of the ith sample battery parameter in predicting the state of charge of the sample battery, and b is the error parameter of the sample battery parameter in estimating the state of charge of the battery.
4. The method of claim 3, wherein the state of charge estimation model is obtained by:
obtaining sample battery parameters of a first sample battery, wherein the sample battery parameters comprise open-circuit voltage, charge and discharge current, battery temperature and charge and discharge times;
obtaining marking information of the state of charge of a second sample battery;
and training the battery model by using the obtained sample battery parameters based on the labeling information to obtain a state of charge estimation model for estimating the state of charge of a battery at the current moment.
5. An apparatus for estimating a state of charge of a battery, the apparatus comprising:
the battery parameter obtaining module is used for obtaining the battery parameters of the target battery at the current moment;
the state of charge budget module is used for inputting the battery parameters into a preset state of charge estimation model to obtain the state of charge of the target battery at the current moment, wherein the state of charge estimation model is a model which is obtained by training a preset battery model by using a first sample battery and is used for estimating the state of charge of the battery at the current moment; the battery model is a model for characterizing the state of charge of the battery determined by the battery state of charge of the battery parameter at each historical time using the battery parameter of the second sample battery based on a linear regression technique.
6. The apparatus of claim 5, wherein the battery parameters comprise: open circuit voltage, charge and discharge current, battery temperature and charge and discharge times.
7. The apparatus of claim 6, further comprising: a battery model obtaining module, wherein the battery model obtaining module comprises:
the first battery parameter obtaining submodule is used for obtaining sample battery parameters of a second sample battery, wherein the sample battery parameters comprise open-circuit voltage, charge-discharge current, battery temperature and charge-discharge times;
the battery model obtaining submodule is used for establishing a battery model of the following expression according to the obtained sample battery parameters based on a linear regression technology;
the expression is:
where M is a battery model for characterizing the state of charge SOC of the battery, f (-) represents a battery model function,
k(xiis) a support vector xiV is open circuit voltage, I is charge-discharge current, T is battery temperature, N is number of charge-discharge cycles, aiFor the weight of the ith sample battery parameter in predicting the state of charge of the sample battery,
the estimated weight of the ith sample battery parameter in predicting the state of charge of the sample battery, and b is the error parameter of the sample battery parameter in estimating the state of charge of the battery.
8. The apparatus of claim 7, further comprising: a state of charge estimation module, wherein the state of charge estimation module comprises:
the second battery parameter obtaining submodule is used for obtaining sample battery parameters of the first sample battery, wherein the sample battery parameters comprise open-circuit voltage, charge-discharge current, battery temperature and charge-discharge times;
the labeling information obtaining submodule is used for obtaining labeling information of the state of charge of the first sample battery;
and the state of charge estimation model obtaining submodule is used for training the battery model by utilizing the obtained sample battery parameters based on the marking information to obtain a state of charge estimation model for estimating the state of charge of a battery at the current moment.
9. An electronic device, comprising: the system comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
the memory is used for storing a computer program;
the processor, when executing the program stored in the memory, implementing the steps of the method for estimating battery state of charge according to any one of claims 1-4.
10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, carries out the steps of the method for estimating a state of charge of a battery according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911205084.1A CN110850315A (en) | 2019-11-29 | 2019-11-29 | Method and device for estimating state of charge of battery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911205084.1A CN110850315A (en) | 2019-11-29 | 2019-11-29 | Method and device for estimating state of charge of battery |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110850315A true CN110850315A (en) | 2020-02-28 |
Family
ID=69606714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911205084.1A Pending CN110850315A (en) | 2019-11-29 | 2019-11-29 | Method and device for estimating state of charge of battery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110850315A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112051511A (en) * | 2020-08-26 | 2020-12-08 | 华中科技大学 | Power battery state of health estimation method and system based on multichannel technology |
| CN112798962A (en) * | 2021-03-15 | 2021-05-14 | 东莞新能安科技有限公司 | Battery hysteresis model training method, and method and device for estimating battery SOC |
| CN117595261A (en) * | 2024-01-19 | 2024-02-23 | 石家庄科林电气股份有限公司 | Optical storage micro-grid energy management strategy optimization method and device and electronic equipment |
| CN118444196A (en) * | 2024-07-05 | 2024-08-06 | 浙江地芯引力科技有限公司 | Battery health state prediction method, device, electronic equipment and program product |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102680907A (en) * | 2012-05-31 | 2012-09-19 | 浙江大学 | Battery charging stress optical coefficient (SOC) detection method in photovoltaic system |
| CN106772065A (en) * | 2016-11-25 | 2017-05-31 | 国电南瑞科技股份有限公司 | Micro-capacitance sensor energy storage SOC estimation method and system based on least square method supporting vector machine |
| CN108139446A (en) * | 2015-10-15 | 2018-06-08 | 江森自控科技公司 | For predicting the battery test system of cell testing results |
| CN108279383A (en) * | 2017-11-30 | 2018-07-13 | 深圳市科列技术股份有限公司 | battery life predicting method, battery data server and battery data processing system |
| CN108549036A (en) * | 2018-05-03 | 2018-09-18 | 太原理工大学 | Ferric phosphate lithium cell life-span prediction method based on MIV and SVM models |
| CN108544925A (en) * | 2018-04-02 | 2018-09-18 | 北京理工大学 | Battery management system |
| CN108805217A (en) * | 2018-06-20 | 2018-11-13 | 山东大学 | A kind of health state of lithium ion battery method of estimation and system based on support vector machines |
| CN110196395A (en) * | 2018-02-26 | 2019-09-03 | 中国商用飞机有限责任公司 | Battery SOC estimation method |
-
2019
- 2019-11-29 CN CN201911205084.1A patent/CN110850315A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102680907A (en) * | 2012-05-31 | 2012-09-19 | 浙江大学 | Battery charging stress optical coefficient (SOC) detection method in photovoltaic system |
| CN108139446A (en) * | 2015-10-15 | 2018-06-08 | 江森自控科技公司 | For predicting the battery test system of cell testing results |
| CN106772065A (en) * | 2016-11-25 | 2017-05-31 | 国电南瑞科技股份有限公司 | Micro-capacitance sensor energy storage SOC estimation method and system based on least square method supporting vector machine |
| CN108279383A (en) * | 2017-11-30 | 2018-07-13 | 深圳市科列技术股份有限公司 | battery life predicting method, battery data server and battery data processing system |
| CN110196395A (en) * | 2018-02-26 | 2019-09-03 | 中国商用飞机有限责任公司 | Battery SOC estimation method |
| CN108544925A (en) * | 2018-04-02 | 2018-09-18 | 北京理工大学 | Battery management system |
| CN108549036A (en) * | 2018-05-03 | 2018-09-18 | 太原理工大学 | Ferric phosphate lithium cell life-span prediction method based on MIV and SVM models |
| CN108805217A (en) * | 2018-06-20 | 2018-11-13 | 山东大学 | A kind of health state of lithium ion battery method of estimation and system based on support vector machines |
Non-Patent Citations (1)
| Title |
|---|
| 裴晟等: "基于支持向量回归的电池SOC 估计方法研究", 《电源技术》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112051511A (en) * | 2020-08-26 | 2020-12-08 | 华中科技大学 | Power battery state of health estimation method and system based on multichannel technology |
| CN112798962A (en) * | 2021-03-15 | 2021-05-14 | 东莞新能安科技有限公司 | Battery hysteresis model training method, and method and device for estimating battery SOC |
| CN112798962B (en) * | 2021-03-15 | 2024-04-30 | 东莞新能安科技有限公司 | Battery hysteresis model training method, method and device for estimating battery SOC |
| CN117595261A (en) * | 2024-01-19 | 2024-02-23 | 石家庄科林电气股份有限公司 | Optical storage micro-grid energy management strategy optimization method and device and electronic equipment |
| CN117595261B (en) * | 2024-01-19 | 2024-03-26 | 石家庄科林电气股份有限公司 | Optical storage micro-grid energy management strategy optimization method and device and electronic equipment |
| CN118444196A (en) * | 2024-07-05 | 2024-08-06 | 浙江地芯引力科技有限公司 | Battery health state prediction method, device, electronic equipment and program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | Extreme learning machine-based thermal model for lithium-ion batteries of electric vehicles under external short circuit | |
| Xu et al. | Life prediction of lithium-ion batteries based on stacked denoising autoencoders | |
| Chen et al. | State-of-charge estimation of lithium-ion batteries based on improved H infinity filter algorithm and its novel equalization method | |
| WO2022253038A1 (en) | Method and system for predicting state of health of lithium battery on basis of elastic network, and device and medium | |
| Ouyang et al. | Improved parameters identification and state of charge estimation for lithium-ion battery with real-time optimal forgetting factor | |
| CN110850315A (en) | Method and device for estimating state of charge of battery | |
| CN109991554B (en) | Battery electric quantity detection method and device and terminal equipment | |
| Zhang et al. | State of health estimation of lithium-ion batteries based on modified flower pollination algorithm-temporal convolutional network | |
| Feng et al. | State of health estimation of large-cycle lithium-ion batteries based on error compensation of autoregressive model | |
| CN111812515A (en) | XGboost model-based lithium ion battery state of charge estimation | |
| Takyi-Aninakwa et al. | A hybrid probabilistic correction model for the state of charge estimation of lithium-ion batteries considering dynamic currents and temperatures | |
| Mian Qaisar | A proficient Li-ion battery state of charge estimation based on event-driven processing | |
| CN113219357A (en) | Battery pack health state calculation method and system and electronic equipment | |
| CN113657360A (en) | Lithium battery health state estimation method, device, equipment and readable storage medium | |
| CN113128672A (en) | Lithium ion battery pack SOH estimation method based on transfer learning algorithm | |
| Chen et al. | State of health estimation for lithium-ion battery based on particle swarm optimization algorithm and extreme learning machine | |
| Lavety et al. | A dynamic battery model and parameter extraction for discharge behavior of a valve regulated lead-acid battery | |
| Ramezani-al et al. | A novel combined online method for SOC estimation of a Li-Ion battery with practical and industrial considerations | |
| CN112733427A (en) | Method for establishing negative electrode potential estimation model of lithium ion battery and computer equipment | |
| Sahoo et al. | Transfer learning based generalized framework for state of health estimation of Li-ion cells | |
| Savargaonkar et al. | A novel neural network with gaussian process feedback for modeling the state-of-charge of battery cells | |
| Lazreg et al. | Lithium-ion battery pack modeling using accurate OCV model: Application for SoC and SoH estimation | |
| Tao et al. | State of charge estimation of lithium Batteries: Review for equivalent circuit model methods | |
| Monirul et al. | Accurate SOC estimation of ternary lithium-ion batteries by HPPC test-based extended Kalman filter | |
| Dong et al. | State of health estimation and remaining useful life estimation for Li-ion batteries based on a hybrid kernel function relevance vector machine |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200228 |
|
| RJ01 | Rejection of invention patent application after publication |