CN113933725B - Method for determining state of charge of power battery based on data driving - Google Patents
Method for determining state of charge of power battery based on data driving Download PDFInfo
- Publication number
- CN113933725B CN113933725B CN202111051231.1A CN202111051231A CN113933725B CN 113933725 B CN113933725 B CN 113933725B CN 202111051231 A CN202111051231 A CN 202111051231A CN 113933725 B CN113933725 B CN 113933725B
- Authority
- CN
- China
- Prior art keywords
- data
- battery
- voltage
- charge
- determining
- 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
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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
Abstract
The embodiment of the application provides a method for determining the state of charge of a power battery based on data driving, which can be applied to various scenes, is suitable for both undersampling situations and non-undersampling situations, and is used for acquiring first data of the battery, wherein the first data comprises a plurality of voltage data of the battery, the first data is processed, first characteristics reflecting the change trend of the plurality of voltage data are extracted from complex voltage data to obtain second data, the state of charge of the battery is determined according to the second data, the randomness and the fluctuation of the plurality of voltage data can be reduced, and the accuracy of determining the SOC of the battery is improved.
Description
Technical Field
The application belongs to the technical field of battery state monitoring, and particularly relates to a method for determining the state of charge of a power battery based on data driving.
Background
The power battery is a core component of the electric automobile, and in order to ensure the safety of the electric automobile, it is very important to accurately determine the state of the power battery. The state of charge (SOC) reflects the remaining available power of the battery, and is an important parameter for measuring the state of the power battery.
The current method for determining the SOC of the power battery is a data driving method, the method obtains data such as voltage, current and temperature of the power battery under specific driving conditions through a sensor on the power battery, then the data such as the voltage, the current and the temperature are input into a neural network model, and the SOC of the battery is output by the neural network model. However, under different driving conditions, such as different speeds or different temperatures, the voltages and currents corresponding to the same SOC value are different, so that the electric vehicle has strong volatility and randomness, and the driving conditions which can be simulated when training the neural network model are limited. At this time, it may occur that the actual driving condition is a driving condition which is not simulated when the neural network model is trained, and the SOC accuracy of the power battery obtained under the actual driving condition is low.
Disclosure of Invention
Aiming at the technical problems, the embodiment of the application provides a method for determining the state of charge of a power battery based on data driving, so as to reduce the fluctuation and randomness of data and improve the accuracy of determining the SOC of the power battery.
In a first aspect, an embodiment of the present application provides a method for determining a state of charge of a power battery based on data driving, the method comprising:
acquiring first data of a battery, wherein the first data comprises a plurality of voltage data of the battery;
processing the first data to obtain second data, wherein the second data comprises first characteristics, and the first characteristics reflect the change trend of the plurality of voltage data;
and determining the charge state of the battery according to the second data.
With reference to the first aspect, in some implementations of the first aspect, processing the first data to obtain second data includes: and processing the first data according to an empirical mode decomposition method to obtain second data.
With reference to the first aspect and the foregoing implementation manner, in some implementation manners of the first aspect, after obtaining the second data, the method further includes: obtaining the internal resistance of a battery; correcting the second data according to the internal resistance of the battery to obtain corrected second data;
determining a state of charge of the battery based on the second data, comprising: and determining the charge state of the battery according to the corrected second data.
The second data is corrected, so that the randomness and the fluctuation of the voltage data of the electric automobile under different driving conditions can be further reduced, and the accuracy of determining the battery SOC is improved.
With reference to the first aspect and the foregoing implementation manner, in some implementation manners of the first aspect, determining a state of charge of the battery according to the corrected second data includes: and inputting the corrected second data into a neural network model to obtain the charge state of the battery, wherein the neural network model is used for outputting the charge state of the battery according to the first characteristic.
With reference to the first aspect and the foregoing implementation manner, in certain implementation manners of the first aspect, the second data further includes a second feature, where the second feature is a high frequency component of the plurality of voltage data.
With reference to the first aspect and the foregoing implementation manners, in certain implementation manners of the first aspect, the first data further includes a plurality of current data and a plurality of temperature data of the battery.
With reference to the first aspect and the foregoing implementation manner, in some implementation manners of the first aspect, the second data further includes a third feature, a fourth feature, and temperature data, where the third feature reflects a trend of variation of the plurality of current data, and the fourth feature is a high frequency component of the plurality of current data.
In a second aspect, an embodiment of the present application provides an apparatus for determining a state of charge of a power battery based on data driving, including:
an acquisition unit configured to acquire first data of a battery, the first data including a plurality of voltage data of the battery;
the processing unit is used for processing the first data to obtain second data, the second data comprises first characteristics, and the first characteristics reflect the change trend of the plurality of voltage data; and determining the charge state of the battery according to the second data.
In a third aspect, an embodiment of the present application further provides an electronic device, including a memory and a processor, where the memory stores a computer program, and the processor implements the method according to the first aspect when executing the computer program.
In a fourth aspect, embodiments of the present application also provide a computer readable storage medium storing computer instructions which, when run on a computer, cause the computer to perform the method of the first aspect.
In a fifth aspect, embodiments of the present application also provide a computer program product comprising a computer program for implementing the method according to the first aspect when the computer program product is run on a computer.
According to the method for determining the state of charge of the power battery based on the data driving, provided by the embodiment of the application, the first data of the battery is obtained, the first data comprises a plurality of voltage data of the battery, the first data is processed, the first characteristics reflecting the change trend of the plurality of voltage data are extracted from the complex voltage data, the second data are obtained, the state of charge of the battery is determined according to the second data, the randomness and the fluctuation of the plurality of voltage data can be reduced, and the accuracy of determining the SOC of the battery is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for determining a state of charge of a power battery based on data driving according to an embodiment of the present application;
fig. 2 is a basic structure of an LSTM unit provided in an embodiment of the present application;
FIG. 3 is a neural network framework for SOC estimation according to an embodiment of the present application;
fig. 4 is a data distribution of voltage, current and temperature of the battery at ambient temperature-10 ℃ and 25 ℃ for the US06 operating mode.
FIG. 5 (a) is the pre-compensation voltage residual component corresponding to 60% SOC at ambient temperature-10deg.C, cycle 1, NN, UDDS, LA, 92, HWFET and US06 conditions;
FIG. 5 (b) is the pre-compensation voltage residual component corresponding to 50% SOC at ambient temperature-10deg.C, cycle 1, NN, UDDS, LA, HWFET and US06 conditions;
FIG. 5 (c) is the pre-compensation voltage residual component corresponding to 40% SOC at ambient temperature-10deg.C, cycle 1, NN, UDDS, LA, 92, HWFET and US06 conditions;
FIG. 5 (d) is the compensated voltage residual component corresponding to 60% SOC at ambient temperature-10deg.C, cycle 1, NN, UDDS, LA, 92, HWFET and US06 conditions;
FIG. 5 (e) is the compensated voltage residual component corresponding to 50% SOC at ambient temperature-10deg.C, cycle 1, NN, UDDS, LA, 92, HWFET and US 06;
FIG. 5 (f) is the compensated voltage residual component corresponding to 40% SOC at ambient temperature-10deg.C, cycle 1, NN, UDDS, LA, HWFET and US 06.
FIG. 6 (a) is a graph showing the SOC estimation of the HWFET operating mode at ambient temperature-10℃ using two methods;
FIG. 6 (b) is a graph showing the SOC estimation of the HWFET operating mode at 25℃for two approaches;
FIG. 6 (c) is a graph showing the SOC error for the HWFET operation at ambient temperature-10℃ using two methods;
FIG. 6 (d) is the SOC error result for the HWFET operating mode at 25℃ambient temperature using two methods;
FIG. 7 (a) is the SOC estimation for the US06 condition at ambient temperature-10deg.C using two methods;
FIG. 7 (b) is a graph showing the SOC estimation for the US06 condition at 25℃for two methods;
FIG. 7 (c) is the SOC error for the US06 condition at ambient temperature-10deg.C using two methods;
FIG. 7 (d) is the SOC error for the US06 condition at 25℃ambient temperature using two methods;
FIG. 8 is a schematic view of an apparatus according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The terms "first" and "second" are used below for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the embodiments of the present application, unless otherwise indicated, the meaning of "a plurality" means two or more, and "at least one", "one or more" means one, two or more.
Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.
The battery is used as a highly nonlinear and time-varying system, and the internal parameters of the battery are dynamically changed, so that the SOC of the power battery is difficult to accurately estimate. Currently, the method for determining SOC of a power battery is mainly divided into the following four methods: coulomb counting, open circuit voltage (Open circuit voltage, OCV), model-based, and data-driven based methods. The accuracy of the coulomb counting determination is affected by the initial error of the SOC and the accuracy of the sensor, and accumulated errors are easily formed during long-term use. The open circuit voltage method needs to stand the power battery for a period of time to obtain the accurate OCV, and obtains the corresponding SOC through a table look-up mode, however, the power battery is difficult to be realized in the actual running process of the electric automobile.
Dynamic tracking of the power battery characteristics is achieved through a model based on the method, modeling is conducted on the power battery by combining a Shepherd model, a Unnewehr Universal model and a Nernst model, online parameter identification is conducted through a recursive least square method, SOC is determined through unscented Kalman filtering, whether the SOC is abnormal or not is judged through a detection method based on residual information characteristics, and a covariance matrix reflecting errors is corrected by introducing an adaptive attenuation factor. The method has the defect that when the battery data is in an undersampled state, systematic errors are introduced in discretization processes of model establishment and SOC determination.
And determining the state of charge of the power battery through a neural network model based on a data driving method. Firstly, collecting working condition data of a battery, wherein the working condition data comprises voltage, current, temperature and current electric quantity, calculating an SOC training label of a neural network model according to the current electric quantity and standard electric quantity, carrying out normalization processing on the voltage, the current and the temperature, and training by adopting a bidirectional LSTM (Low-Voltage) Encoder-Decoder structure to obtain the neural network model. When the SOC is determined, the data such as the voltage, the current and the temperature of the power battery under specific driving conditions are obtained through the sensor on the power battery, then the data such as the voltage, the current and the temperature are input into the neural network model, and the SOC of the battery is output by the neural network model.
However, under different driving conditions (i.e. different working conditions), such as different speeds or different temperatures, the voltages and currents corresponding to the same SOC value are different, so that the electric vehicle has strong volatility and randomness, and under low temperature or high power, the volatility of the voltages is aggravated, and the driving conditions which can be simulated when training the neural network model are limited. At this time, it may occur that the actual driving condition is a driving condition which is not simulated when the neural network model is trained, and the SOC accuracy of the power battery obtained under the actual driving condition is low. Although higher SOC accuracy can be achieved by deepening network complexity, this can lead to problems of increased computation time and adverse network convergence.
The SOC of the power battery can be obtained in real time by adopting a coulomb counting method on the electric automobile, in order to correct the accumulated error of the SOC, data such as voltage, current, temperature and the like collected by the sensor can be transmitted to the data platform, then the SOC of the battery is determined on the basis of a data driving method, and the determined SOC on the data platform and the determined SOC on the electric automobile are compared and corrected. Because of limited data allowed on a transmission link and limited storage space of a data platform in actual situations, the technical specification of the GBT 32960.3-2016 electric vehicle remote service and management system part 3 communication protocol and data format clearly shows that the time period for allowing reporting data should not exceed 30s at maximum in the normal running process of the electric vehicle. Currently, the time interval of data on a data platform is typically between 10s and 30s. In addition, because the fluctuation frequency of the battery data is higher and the sampling theorem is not satisfied, the data on the data platform often has larger time intervals and is in undersampling condition, the detailed information of the battery data is reduced, and the accuracy of estimating the SOC of the power battery by using the data driving method is reduced. Hereinafter, the "power battery" will be simply referred to as "battery".
Aiming at the problems, the embodiment of the application provides a method for determining the state of charge of a power battery based on data driving, which comprises the steps of firstly acquiring original data such as voltage, current and temperature of the battery through a sensor, then processing the original data, extracting characteristics reflecting the change trend of the original data, characteristics reflecting detailed information and the like from the original data, so as to reduce the randomness and the fluctuation of the original data; and then, the battery SOC is determined according to the extracted characteristics, so that the accuracy of determining the battery SOC is improved. In addition, the extracted characteristics can be corrected, so that the randomness and the fluctuation of the original data of the electric automobile under different driving conditions are further reduced, and the accuracy of determining the SOC of the battery is improved.
The method provided by the embodiment of the application can be used for undersampling situations and non-undersampling situations. Taking the undersampling case as an example, a method 100 for determining the state of charge of a power battery based on data driving according to an embodiment of the present application is described with reference to fig. 1. As shown in fig. 1, the method 100 includes:
s101: first data of a battery is acquired, the first data including a plurality of voltage data of the battery.
S102: and processing the first data to obtain second data, wherein the second data comprises first characteristics, and the first characteristics reflect the change trend of the plurality of voltage data.
S103: and determining the charge state of the battery according to the second data.
Firstly, acquiring first data of a battery from a data platform, wherein the first data comprises a plurality of voltage data of the battery, and further comprises other data such as a plurality of current data and a plurality of temperature data, namely the first data can be composed of (voltage, current and temperature), wherein the plurality of data are data corresponding to a plurality of moments in a period of time, and the first data can be composed of a plurality of data corresponding to a plurality of moments in time series X k The k represents the time. The data platform stores the original data of the voltage, the current, the temperature and the like of the battery, which are acquired by the sensor.
Then, in the embodiment of the application, the first data can be processed by using a wavelet transformation method or an empirical mode decomposition (Empirical mode decomposition, EMD) method and the like to obtain the second data.
The explanation will be given taking empirical mode decomposition as an example.
Given a time sequence X k (k=1, 2, …, N), the procedure of the EMD treatment is as follows:
(1) identifying a time series X k Sequentially obtaining a time sequence X through a cubic spline interpolation function k Upper envelope u of (2) k And a lower envelope line l k . Calculating the average envelope curve ml of the upper and lower envelope curves by the method (1) k 。
(2) From time series X k Subtracting the mean envelope ml from k Acquisition of a new time sequence hl k As shown in formula (2).
hl k ＝X k -ml k (2)
(3) Determining a time sequence hl k Whether the eigenmode function (Intrinsic mode functions, IMFs). One characteristic is: the number of the local extreme points and the zero crossing points is at most 1; another characteristic is: the average value of the upper and lower envelopes constituted by the local extremum is 0. If time sequence hl k Satisfying the above two characteristics, the time sequence hl is k Defined as an IMF, and uses the residual term r calculated by equation (3) k Instead of time series X k . And then repeating the steps (1) to (3).
r k ＝X k -hl k (3)
If time sequence hl k Not satisfying the two characteristics of the IMFs, the time sequence hl k On the basis of the step (1) to the step (2), and then further executing the step (3).
Repeating the above process until the termination condition of the iterative process is satisfied. The termination condition is determined according to the cauchy convergence criterion as shown in equation (4).
Wherein r is k,last And r k,current The residual terms of the last iteration and the current iteration, respectively. In the embodiment of the present application, the value may be set to 0.2.
After the iteration is finished, a residual component R can be obtained k ，R k Reflecting time series X k The trend of the change in (2) can also be obtained as a time series X k Is characterized by a time series X k Intrinsic vibration modes. Original time series X k Can pass through IMFs and residual component R k The reconstruction is performed as shown in formula (5).
When time series X k For voltage data, IMFs and residual components of the voltage can be obtained, the residual components of the voltage corresponding to the first bitAnd (3) sign. IMFs of the voltage are high frequency components of the plurality of voltage data, corresponding to the second feature. When time series X k For current data, IMFs and residual components of the current can be obtained, the residual components of the current corresponding to the third feature. IMFs of the current are high frequency components of the plurality of current data, corresponding to the fourth feature.
When the first data includes a plurality of voltage data, the second data includes a residual component of the voltage and may further include IMFs of the voltage. When the first data further includes a plurality of current data, the second data may further include a residual component of the current and IMFs of the current. In addition, when the first data further includes a plurality of temperature data, the second data further includes temperature data.
The second data is then input into a pre-trained neural network model, i.e., the SOC of the battery can be determined.
However, under different working conditions, certain deviation still exists between voltage residual components obtained through EMD processing corresponding to the same SOC, and the deviation is caused by different distribution conditions of current data under different working conditions.
The compensation strategy is specifically described below.
In consideration of the undersampling condition, a complex model can introduce systematic deviation in the discretization process, and the embodiment of the application adopts an internal resistance model to model the power battery, and a corresponding measurement equation of the model is shown as a formula (6).
U k ＝OCV k +I k R internal +α k (6)
Wherein U is k Is the voltage at time k, I k Current at time k, OCV k Is the open circuit voltage at time k, R internal Is the internal resistance of the battery alpha k Is the k moment error term, obeys standard normal distribution.
Since the voltage residual component is a voltage trend quantity, the low-frequency information reflecting the voltage can be regarded as a base of the voltage, and other voltages IMFs are subjected to original voltage signal reconstruction on the basis. During charge and discharge, OCV changes relatively slowly, belonging to the low frequency component. In addition, the current distribution of the operating mode can be regarded as a fluctuation in an average current, and the average voltage across the internal resistance also belongs to the low-frequency component. Therefore, in the embodiment of the present application, the voltage residual component is equivalent to the sum of the OCV and the average voltage across the internal resistance as shown in the formula (7).
Wherein R is k,v Is the voltage residual component at time k,is the average current over a period of time, beta k Is the k moment error term, obeys standard normal distribution.
Subtracting the equation (6) from the equation (7) can obtain a linear regression equation for identifying the internal resistance parameter, as shown in the equation (8).
Wherein delta is k ＝U k -R k,v ，γ k Is the k moment error term, obeys standard normal distribution.
The algorithm of the parameter identification can be a least square method, and the optimal estimation of the internal resistance is obtained on line through a formula (9) by combining the current data acquired by the formula (8) and the actual sensor.
Wherein, the liquid crystal display device comprises a liquid crystal display device,Y＝[Δ 1 ,Δ 2 ,…,Δ N ] T ，/>is the current I 1 To I N Is used for the average value of (a),is the optimal estimation result of the internal resistance of the battery.
The voltage residual component is compensated by the average voltage on the internal resistance, and the OCV-like quantity is obtained as shown in a formula (10).
Wherein R is k,v,c Is the voltage residual component after the k time compensation.
The residual component of the voltage is compensated, namely the second data is corrected, so that the aggregation degree of different working conditions is further improved, namely the similarity of the corresponding data under different working conditions and the same SOC is further improved, namely the difference of the battery data of the electric automobile under different operation working conditions is reduced, the randomness and the fluctuation of the battery data are reduced, and meanwhile, the correlation of the data and the SOC is ensured.
At this time, the corrected second data includes the compensated voltage residual component, and may further include voltage IMFs, current residual component, current IMFs, and temperature data. And inputting the corrected second data into the neural network model to determine the SOC of the battery, so that the accuracy of the result is further improved. The neural network can effectively simulate the dynamic characteristics of the battery through network layer stacking and nonlinear activation functions, and the method provided by the application can obtain higher SOC accuracy without deepening network complexity due to the fact that the randomness and fluctuation of the original data are reduced.
Because SOC estimation is a time series prediction task, the improved version of the cyclic neural network (Recurrent neural network, RNN) is used for training and predicting the SOC by using the Long-term and short-term memory neural network (Long-short term memory, LSTM) in the embodiment of the application, so that gradient disappearance and gradient explosion phenomena in the back propagation process are prevented.
As shown in fig. 2, the basic structure of the LSTM unit provided in the embodiment of the present application includes an input gate i, a forgetting gate f, a control gate c, and an output gate o. Formulas (11) through (16) describe the workflow of the LSTM cell.
i k ＝sigm(W x,i x k +W h,i h k-1 +b i ) (11)
f k ＝sigm(W x,f x k +W h,f h k-1 +b f ) (12)
o k ＝sigm(W x,o x k +W h,o h k-1 +b o ) (13)
c k ＝tanh(W x,c x k +W h,c h k-1 +b c ) (14)
C k ＝f k ⊙C k-1 +i k ⊙c k (15)
h k ＝o t ⊙tanh(C k ) (16)
Wherein x is k Is the input of time step k (k=1, 2, …, N), h k Is the hidden layer output of time step k, C k Is the LSTM cell state for time step k. W and b are the weight matrix and bias, respectively. sigm is a sigmoid function that can convert values to a range of 0 to 1, and tanh is a hyperbolic tangent function that can convert values to a range of-1 to 1. The gate vectors of equations (11) through (14) determine the information that the LSTM cells memorize updated, forgotten and output. Finally, the LSTM cell state and hidden layer state are updated by formulas (15) to (16).
In the embodiment of the application, the input of the neural network model comprises the compensated voltage residual component, the voltage IMFs, and also comprises the current residual component, the current IMFs and the ambient temperature. Connecting each feature at k time as input vector x of time step k during input k 。
Fig. 3 is a framework of SOC estimation provided by an embodiment of the present application, N is the input sequence length,the time corresponding to the nth data is time step N. h is a 0 And C 0 The initial values of the LSTM cell state and hidden layer output, respectively. SOC (State of Charge) N Is the SOC estimate for time step N. The input information of each time step is transmitted through the hidden layer output and the LSTM unit state, and the past information can be fully used currently. Hidden layer output h for time step N N And through the combination of the full connection network (Full connected network, FCN), the FCN outputs an estimation result of the SOC after passing through a sigmoid function.
In summary, the embodiment of the application provides a method for determining the state of charge of a power battery based on data driving, which is based on feature extraction of original data of the battery by EMD to obtain voltage IMFs and residual components and current IMFs and residual components, so that randomness and volatility of the original data are reduced.
And the internal resistance of the power battery is identified in real time by utilizing a least square method, and the voltage residual component is compensated by the average voltage of the internal resistance, so that the data difference of the electric automobile under different operation working conditions is further reduced.
The method provided by the embodiment Of the application is suitable for both undersampling and non-undersampling, can ensure good accuracy when being applied to a data platform, calibrate the SOC on the electric automobile, and can also provide reference for estimating the capacity (SOH) Of the storage battery according to the data Of the platform. In addition, the method can be used for other equipment with undersampling condition, and the accuracy of the equipment SOC estimation is improved.
The accuracy of the method provided by the embodiments of the present application is described below in conjunction with experimental data.
And in the experiment, undersampled battery data on the simulation data platform is simulated by using the downsampled laboratory working condition data. Laboratory operating condition data includes 9 operating conditions, cycle 1-4, neural Network (NN), urban power meter travel plan (Urban dynamometer driving schedule, UDDS), unified driving plan (Unified driving schedule, LA 92), highway fuel-efficient driving plan (highway fuel economy test, HWFET), and aggressive driving plan (high acceleration aggressive driving schedule, US 06), respectively. Cycle 1-4 is obtained by randomly mixing the working conditions of NN, UDDS, LA, HWFET, US06 and the like.
The experimental object in the embodiment of the application is a loose NCR18650PF ternary lithium battery, and the main performance parameters are shown in Table 1.
TABLE 1 NCR18650PF Performance parameters
| Nominal capacity | 2900mAh |
| Nominal voltage | 3.6V |
| Minimum/maximum voltage | 2.5V/4.2V |
| Standard charging current | 1.35A |
| Maximum sustained discharge current | 10A |
The specific experimental steps are as follows:
(1) and acquiring first data, and framing a time sequence of voltage, current and temperature by adopting a sliding window with the size of N.
For example, taking undersampled data with a sampling interval of 10s as an example, when N is 20 and the sliding step is 5, data of 0 th second, 10 th second, 20 th second, … … th and 200 th seconds are taken as a first group of data, and data of 50 th second, 60 th second, 70 th second, … … th and 250 th seconds are taken as a second group of data.
(2) The second data is acquired, and the voltage IMFs and the residual components, the current IMFs and the residual components are acquired using the EMD decomposition voltage and current signals, and in addition, the second data includes temperature data.
(3) And (3) establishing a linear regression equation for identifying the internal resistance parameters based on the formula (8), acquiring an optimal solution of the internal resistance based on a least square method through the formula (9), and compensating a voltage residual component by adopting the formula (10).
(4) The 9 working condition data sets are divided into a training set and a testing set, wherein the HWFET and US06 working conditions are the testing set, and the other working conditions are the training set. The training set and the test set are normalized.
(5) Setting the time step and the hidden layer size of the LSTM model, and training the model by using a training set. In the training process, an adam algorithm is adopted in the parameter optimization process, the training step length is 2000, the learning rate is set to 0.01, and the batch size is set to 256.
(6) The comparison analysis is based on the SOC estimation result of the LSTM of the first data (hereinafter referred to as standard LSTM), and the SOC estimation result of the LSTM of the second data (hereinafter referred to as new feature LSTM).
The experimental results are analyzed as follows.
Fig. 4 is a data distribution of voltage, current and temperature of the battery at ambient temperature-10 ℃ and 25 ℃ for the US06 operating mode.
Fig. 5 (a) and (d) are the compensation front-to-back voltage residual components corresponding to 60% soc for Cycle 1, NN, UDDS, LA, HWFET and US06 conditions at ambient temperature-10 ℃.
Fig. 5 (b) and (e) are the compensation front-to-back voltage residual components corresponding to 50% soc for Cycle 1, NN, UDDS, LA, HWFET and US06 conditions at ambient temperature-10 ℃.
Fig. 5 (c) and (f) are the compensation front-to-back voltage residual components corresponding to 40% soc for Cycle 1, NN, UDDS, LA, HWFET and US06 conditions at ambient temperature-10 ℃.
The degree of aggregation of the different operating mode data is measured here by the standard deviation of the voltage residual component. Table 2 shows the standard deviations of the residual components of the voltages before and after compensation corresponding to 20% SOC to 80% SOC at ambient temperature-10deg.C, cycle 1, NN, UDDS, LA, 92, HWFET and US06 conditions, with an SOC interval of 10%. std vr And std cvr The standard deviation of the residual voltage components before and after the compensation under different working conditions is respectively calculated. As can be seen from fig. 5 and table 2, in the low temperature environment, the standard deviation of the voltage residual component after compensation is generally reduced, the polymerization degree of data in different working conditions is improved, and the effectiveness of the compensation strategy is proved.
TABLE 2 Standard deviation of residual components of voltages before and after Compensation for different conditions under different SOCs at ambient temperature-10deg.C
FIGS. 6 and 7 are the SOC estimation results and error comparisons for the HWFET and US06 conditions at ambient temperature-10℃ and 25℃, respectively, using the two methods. The two methods are new feature LSTM and standard LSTM, respectively. Table 3 gives the estimation error statistics for both methods.
As can be seen from fig. 6, 7 and table 3, when the ambient temperature is normal temperature, a better SOC estimation accuracy can be obtained based on both the new characteristic LSTM and the standard LSTM. When the ambient temperature is low, the estimation result based on the new feature LSTM is better than the estimation result of the standard LSTM, which is caused by the improved degree of aggregation of the different operating conditions by the new feature (second data).
It can be seen that, in the SOC estimation results of HWFET and US06 under 4 ambient temperature conditions obtained based on standard LSTM, the Root Mean Square Error (RMSE) maximum is 3.7% and the maximum absolute error (MaxAE) maximum is 5.4%; of the SOC estimates of HWFET and US06 at 4 ambient temperature conditions based on the new feature LSTM, RMSE maximum is 2.2% and MaxAE maximum is 5.6%. The above results fully demonstrate the stability of the methods presented in the examples of the present application at different ambient temperatures.
TABLE 3 SOC estimation error statistics for two methods
The device and the electronic equipment provided by the embodiment of the application are described below.
Fig. 8 is a device for training a model according to an embodiment of the present application, where the device 800 includes an obtaining unit 801 and a processing unit 802.
An acquiring unit 801 is configured to acquire first data of a battery, where the first data includes a plurality of voltage data of the battery.
A processing unit 802, configured to process the first data to obtain second data, where the second data includes a first feature, and the first feature reflects a trend of variation of the plurality of voltage data; and determining the charge state of the battery according to the second data.
In particular, the processing unit 802 is further configured to process the first data according to an empirical mode decomposition method, so as to obtain second data.
In particular, the processing unit 802 is further configured to obtain an internal resistance of the battery; correcting the second data according to the internal resistance of the battery to obtain corrected second data; and determining the charge state of the battery according to the corrected second data.
In particular, the processing unit 802 is further configured to input the modified second data into a neural network model, to obtain a state of charge of the battery, where the neural network model is configured to output the state of charge of the battery according to the first feature.
In particular, the second data further comprises a second feature, the second feature being a high frequency component of the plurality of voltage data.
In particular, the first data also includes a plurality of current data and a plurality of temperature data of the battery
In particular, the second data further includes a third feature reflecting a trend of variation of the plurality of current data, a fourth feature being a high frequency component of the plurality of current data, and temperature data.
It should be appreciated that the apparatus 800 of embodiments of the present application may be implemented by an application-specific integrated circuit (application-specific integrated circuit, ASIC), a programmable logic device (programmable logic device, PLD), which may be a complex program logic device (complex programmable logical device, CPLD), a field-programmable gate array (field-programmable gate array, FPGA), a general-purpose array logic (generic array logic, GAL), or any combination thereof. The method shown in fig. 1 may be implemented by software, and when the method shown in fig. 1 is implemented by software, the apparatus 800 and its respective modules may be software modules.
Fig. 9 is a schematic structural diagram of an electronic device 900 according to an embodiment of the present application. As shown in fig. 9, the device 900 includes a processor 901, a memory 902, a communication interface 903, and a bus 904. The processor 901, the memory 902, and the communication interface 903 communicate via the bus 904, or may communicate via other means such as wireless transmission. The memory 902 is configured to store instructions and the processor 901 is configured to execute the instructions stored by the memory 902. The memory 902 stores program code 9021, and the processor 901 may invoke the program code 9021 stored in the memory 902 to perform the method shown in fig. 1.
It should be appreciated that in embodiments of the present application, processor 901 may be a CPU, and processor 901 may also be other general purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or any conventional processor or the like.
The memory 902 may include read only memory and random access memory and provide instructions and data to the processor 901. The memory 902 may also include non-volatile random access memory. The memory 902 may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and direct memory bus RAM (DR RAM).
The bus 904 may include a power bus, a control bus, a status signal bus, and the like in addition to a data bus. But for clarity of illustration, the various buses are labeled as bus 904 in fig. 9.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments 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 or executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of 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. The semiconductor medium may be a solid state disk (solid state drive, SSD).
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (9)
1. A method of determining a state of charge of a power battery based on data actuation, the method comprising:
acquiring first data of a battery, wherein the first data comprises a plurality of voltage data of the battery;
processing the first data to obtain second data, wherein the second data comprises first characteristics, the first characteristics reflect the change trend of the plurality of voltage data, and the change trend of the voltage data is represented by voltage residual components;
obtaining the internal resistance and average current of the battery, wherein the average current is the average current in a preset time period;
determining an average voltage based on the internal resistance and the average current;
compensating the voltage residual component based on the average voltage to obtain corrected second data;
and determining the charge state of the battery according to the corrected second data.
2. The method of claim 1, wherein processing the first data to obtain second data comprises:
and processing the first data according to an empirical mode decomposition method to obtain the second data.
3. The method of claim 1, wherein said determining the state of charge of the battery from the modified second data comprises:
and inputting the corrected second data into a neural network model to obtain the state of charge of the battery, wherein the neural network model is used for outputting the state of charge of the battery according to the first characteristic.
4. A method according to any one of claims 1 to 3, wherein the second data further comprises a second feature, the second feature being a high frequency component of the plurality of voltage data.
5. A method according to any one of claims 1 to 3, wherein the first data further comprises a plurality of current data and a plurality of temperature data of the battery.
6. The method of claim 5, wherein the second data further comprises a third characteristic reflecting a trend of the plurality of current data, a fourth characteristic being a high frequency component of the plurality of current data, and temperature data.
7. An apparatus for determining a state of charge of a power battery based on data actuation, the apparatus comprising:
an acquisition unit configured to acquire first data of a battery, the first data including a plurality of voltage data of the battery;
the processing unit is used for processing the first data to obtain second data, the second data comprises first characteristics, the first characteristics reflect the change trend of the plurality of voltage data, and the change trend of the voltage data is represented by voltage residual components; obtaining the internal resistance and average current of the battery, wherein the average current is the average current in a preset time period; determining an average voltage based on the internal resistance and the average current; compensating the voltage residual component based on the average voltage to obtain corrected second data; and determining the charge state of the battery according to the corrected second data.
8. An electronic device, comprising: a memory storing a computer program and a processor implementing the method of any one of claims 1 to 6 when the computer program is executed by the processor.
9. A computer readable storage medium storing computer instructions which, when run on an electronic device, cause the electronic device to perform the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111051231.1A CN113933725B (en) | 2021-09-08 | 2021-09-08 | Method for determining state of charge of power battery based on data driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111051231.1A CN113933725B (en) | 2021-09-08 | 2021-09-08 | Method for determining state of charge of power battery based on data driving |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113933725A CN113933725A (en) | 2022-01-14 |
| CN113933725B true CN113933725B (en) | 2023-09-12 |
Family
ID=79275349
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111051231.1A Active CN113933725B (en) | 2021-09-08 | 2021-09-08 | Method for determining state of charge of power battery based on data driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113933725B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114579644B (en) * | 2022-05-06 | 2022-07-22 | 中国汽车技术研究中心有限公司 | Method, apparatus and medium for battery efficient charging data identification based on deep learning |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106154168A (en) * | 2016-04-01 | 2016-11-23 | 储盈新能源科技（上海）有限公司 | The method for estimating charge state of power cell of data-driven |
| EP3410139A1 (en) * | 2017-05-29 | 2018-12-05 | Magneti Marelli S.p.A. | Method for estimating the current and the state of charge of a battery pack or cell, without direct detection of current under operating conditions |
| CN110941929A (en) * | 2019-12-06 | 2020-03-31 | 长沙理工大学 | Battery health state assessment method based on ARMA and Elman neural network combined modeling |
| CN111220921A (en) * | 2020-01-08 | 2020-06-02 | 重庆邮电大学 | Lithium battery capacity estimation method based on improved convolution-long-and-short-term memory neural network |
| CN112630662A (en) * | 2020-12-30 | 2021-04-09 | 南京航空航天大学 | Power battery SOH estimation method based on data driving and multi-parameter fusion |
| CN112782594A (en) * | 2020-12-24 | 2021-05-11 | 杭州电子科技大学 | Method for estimating SOC (state of charge) of lithium battery by data-driven algorithm considering internal resistance |
| CN113033104A (en) * | 2021-03-31 | 2021-06-25 | 浙江大学 | Lithium battery state of charge estimation method based on graph convolution |
| 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 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150081237A1 (en) * | 2013-09-19 | 2015-03-19 | Seeo, Inc | Data driven/physical hybrid model for soc determination in lithium batteries |
| US10209314B2 (en) * | 2016-11-21 | 2019-02-19 | Battelle Energy Alliance, Llc | Systems and methods for estimation and prediction of battery health and performance |
| US11626062B2 (en) * | 2020-02-18 | 2023-04-11 | Google Llc | System and method for modulating an array of emissive elements |
-
2021
- 2021-09-08 CN CN202111051231.1A patent/CN113933725B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106154168A (en) * | 2016-04-01 | 2016-11-23 | 储盈新能源科技（上海）有限公司 | The method for estimating charge state of power cell of data-driven |
| EP3410139A1 (en) * | 2017-05-29 | 2018-12-05 | Magneti Marelli S.p.A. | Method for estimating the current and the state of charge of a battery pack or cell, without direct detection of current under operating conditions |
| CN110941929A (en) * | 2019-12-06 | 2020-03-31 | 长沙理工大学 | Battery health state assessment method based on ARMA and Elman neural network combined modeling |
| CN111220921A (en) * | 2020-01-08 | 2020-06-02 | 重庆邮电大学 | Lithium battery capacity estimation method based on improved convolution-long-and-short-term memory neural network |
| CN112782594A (en) * | 2020-12-24 | 2021-05-11 | 杭州电子科技大学 | Method for estimating SOC (state of charge) of lithium battery by data-driven algorithm considering internal resistance |
| CN112630662A (en) * | 2020-12-30 | 2021-04-09 | 南京航空航天大学 | Power battery SOH estimation method based on data driving and multi-parameter fusion |
| 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 |
| CN113033104A (en) * | 2021-03-31 | 2021-06-25 | 浙江大学 | Lithium battery state of charge estimation method based on graph convolution |
Non-Patent Citations (1)
| Title |
|---|
| SOC estimation based on data driven exteaded Kalman filter algorithm for power battery of electric vehicle and plug-in electric vehicle;Fang Liu et al.;Journal of Central South University;第26卷(第6期);第1402-1415页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113933725A (en) | 2022-01-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xiong et al. | A data-driven multi-scale extended Kalman filtering based parameter and state estimation approach of lithium-ion polymer battery in electric vehicles | |
| CN113156321B (en) | Estimation method of lithium ion battery state of charge (SOC) | |
| CN109669132B (en) | Battery state of charge estimation method based on variational Bayesian filtering | |
| Li et al. | A wavelet transform‐adaptive unscented Kalman filter approach for state of charge estimation of LiFePo4 battery | |
| Sun et al. | A sequential capacity estimation for the lithium-ion batteries combining incremental capacity curve and discrete Arrhenius fading model | |
| Liu et al. | State of health estimation of power batteries based on multi-feature fusion models using stacking algorithm | |
| CN111426957B (en) | SOC estimation optimization method for power battery under simulated vehicle working condition | |
| Ouyang et al. | A novel state of charge estimation method for lithium-ion batteries based on bias compensation | |
| CN112379270B (en) | Rolling time domain estimation method for state of charge of power battery of electric automobile | |
| CN111458661A (en) | Power distribution network line variation relation diagnosis method, device and system | |
| Ren et al. | Novel co‐estimation strategy based on forgetting factor dual particle filter algorithm for the state of charge and state of health of the lithium‐ion battery | |
| CN114290960A (en) | Method and device for acquiring battery health degree of power battery and vehicle | |
| CN113933725B (en) | Method for determining state of charge of power battery based on data driving | |
| CN104076284B (en) | The tracking of battery charge state SOC and device | |
| Xing et al. | Lithium-ion battery state-of-charge estimation based on a dual extended Kalman filter and BPNN correction | |
| CN114371408A (en) | Estimation method of battery charge state, and extraction method and device of charging curve | |
| Zhao et al. | A state of health estimation framework based on real-world electric vehicles operating data | |
| CN113391216A (en) | Method and device for estimating available capacity of lead-acid battery based on response surface design | |
| Wei et al. | Multiscale dynamic construction for abnormality detection and localization of Li-ion batteries | |
| Havangi | Adaptive robust unscented Kalman filter with recursive least square for state of charge estimation of batteries | |
| Wang et al. | A flexible method for state-of-health estimation of lithium battery energy storage system | |
| He et al. | A SOE estimation method for lithium batteries considering available energy and recovered energy | |
| Hatherall et al. | Remaining discharge energy estimation for lithium-ion batteries using pattern recognition and power prediction | |
| CN117665620A (en) | New energy automobile data-based battery health evaluation method | |
| CN116593917A (en) | Lithium battery health state estimation method based on time-frequency double-flow characteristic characterization |
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 |