CN114021462A - Energy storage lithium battery SOC estimation method, device, equipment and storage medium - Google Patents

Energy storage lithium battery SOC estimation method, device, equipment and storage medium Download PDF

Info

Publication number
CN114021462A
CN114021462A CN202111319575.6A CN202111319575A CN114021462A CN 114021462 A CN114021462 A CN 114021462A CN 202111319575 A CN202111319575 A CN 202111319575A CN 114021462 A CN114021462 A CN 114021462A
Authority
CN
China
Prior art keywords
lithium battery
soc
data
neural network
sample
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
Application number
CN202111319575.6A
Other languages
Chinese (zh)
Inventor
吴金荣
喻晓庆
俞洲彬
王德君
王华明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Zhejiang Electric Power Co Ltd Hangzhou Yuhang District Power Supply Co
Yuhang Branch Of Hangzhou Electric Power Design Institute Co ltd
Hangzhou Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Original Assignee
State Grid Zhejiang Electric Power Co Ltd Hangzhou Yuhang District Power Supply Co
Yuhang Branch Of Hangzhou Electric Power Design Institute Co ltd
Hangzhou Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by State Grid Zhejiang Electric Power Co Ltd Hangzhou Yuhang District Power Supply Co, Yuhang Branch Of Hangzhou Electric Power Design Institute Co ltd, Hangzhou Power Supply Co of State Grid Zhejiang Electric Power Co Ltd filed Critical State Grid Zhejiang Electric Power Co Ltd Hangzhou Yuhang District Power Supply Co
Priority to CN202111319575.6A priority Critical patent/CN114021462A/en
Publication of CN114021462A publication Critical patent/CN114021462A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/385—Arrangements for measuring battery or accumulator variables
    • G01R31/387—Determining ampere-hour charge capacity or SoC
    • 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]
    • G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/04—Ageing analysis or optimisation against ageing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/06—Power analysis or power optimisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Secondary Cells (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)

Abstract

The invention discloses an energy storage lithium battery SOC estimation method, which comprises the following steps: acquiring temperature data and voltage data of a lithium battery to be tested; and identifying and obtaining the SOC value of the lithium battery to be tested based on the temperature data, the voltage data and a neural network model, wherein the neural network model is a model representing the corresponding relation between the SOC value of the lithium battery, the temperature of the lithium battery and the voltage, and the model is obtained in advance through DBN neural network training. When estimating the SOC of lithium cell in this application to the temperature data and the voltage data of lithium cell are as the reference, utilize the neural network model realization that the training of DBN neural network obtained to the estimation of SOC value to promote the accuracy of the SOC value estimation of lithium cell to a certain extent, be favorable to the rational use of lithium cell to promote life. The application also provides an energy storage lithium battery SOC estimation device, equipment and a computer readable storage medium, which have the beneficial effects.

Description

Energy storage lithium battery SOC estimation method, device, equipment and storage medium
Technical Field
The invention relates to the technical field of lithium batteries, in particular to a method, a device and equipment for estimating the SOC of an energy storage lithium battery and a computer readable storage medium.
Background
Along with the continuous consumption of world energy, people pay attention to the development of clean energy and renewable energy, and electrochemical energy storage is an important branch of an electric energy storage mode. The development key of the energy storage station industry lies in an energy storage battery, and compared with other storage batteries, the lithium battery has the advantages of being environment-friendly, durable, low in self-discharge rate and the like, and the lithium battery can be used in the field of power station energy storage due to the advantages of the lithium battery. The SOC (state of charge) is the most basic battery performance index, and accurate estimation of the SOC can not only prevent overcharge and overdischarge of the battery and prolong the service life of the battery, but also is the basis of a battery management system and battery balance control.
At present, the types of estimation methods commonly used for SOC at home and abroad are relatively more, but various defects exist, so that how to accurately and effectively realize the SOC estimation of the lithium battery is one of popular research directions in the industry.
Disclosure of Invention
The invention aims to provide a method, a device and equipment for estimating the SOC of an energy storage lithium battery and a computer readable storage medium, which can improve the accuracy of estimating the SOC value of the lithium battery to a certain extent.
In order to solve the technical problem, the invention provides an energy storage lithium battery SOC estimation method, which comprises the following steps:
obtaining temperature data and voltage data of a lithium battery to be tested;
and identifying and obtaining the SOC value of the lithium battery to be tested based on the temperature data, the voltage data and a neural network model, wherein the neural network model is a model representing the corresponding relation between the SOC value of the lithium battery, the temperature of the lithium battery and the voltage, and the model is obtained in advance through DBN neural network training.
In an optional embodiment of the present application, acquiring temperature data and voltage data of a lithium battery to be tested includes:
acquiring the temperature data and the voltage data which are acquired by the lithium battery to be detected from a plurality of corresponding time points within a preset time period at the current moment;
correspondingly, identifying and obtaining the SOC value of the lithium battery to be tested based on the temperature data, the voltage data and the neural network model, and the method comprises the following steps:
identifying the temperature data and the voltage data corresponding to each time point through the neural network model respectively to obtain an initial SOC value corresponding to each time point;
and performing extended Kalman filtering operation on each initial SOC value to obtain each filtered SOC value, and taking the SOC value corresponding to the current moment as the current SOC value of the lithium battery to be tested.
In an optional embodiment of the present application, the process of pre-training to obtain the neural network model includes:
collecting voltage samples and real-time current data of a lithium battery which is charged from the charge amount of 0 at different temperatures;
obtaining SOC data samples of the lithium battery based on each different charging accumulated time and the real-time current data;
and inputting the temperature sample, the voltage sample and the SOC data sample corresponding to the SOC data sample into a DBN neural network for training to obtain the neural network model.
In an optional embodiment of the present application, after obtaining the SOC data sample of the lithium battery, the method further includes:
normalizing the SOC data samples and the voltage samples for the same temperature sample using a mapminmax function;
correspondingly, inputting the temperature sample, the voltage sample and the SOC data sample corresponding to the SOC data sample into the DBN neural network for training, and obtaining the neural network model, including:
and inputting the temperature sample, the normalized SOC data sample and the normalized voltage sample into a DBN neural network for training to obtain the neural network model.
An energy storage lithium battery SOC estimation device, comprising:
the data acquisition module is used for acquiring and obtaining temperature data and voltage data of the lithium battery to be detected;
and the electric quantity estimation module is used for identifying and obtaining the SOC value of the lithium battery to be detected based on the temperature data, the voltage data and the neural network model, wherein the neural network model is a model representing the corresponding relation between the SOC value of the lithium battery, the temperature of the lithium battery and the voltage, and the model is obtained through DBN neural network training in advance.
In an optional embodiment of the application, the data acquisition module is specifically configured to obtain the temperature data and the voltage data acquired at a plurality of corresponding time points within a preset time period from the current time of the lithium battery to be tested;
the electric quantity estimation module is specifically used for identifying the temperature data and the voltage data corresponding to each time point through the neural network model respectively to obtain an initial SOC value corresponding to each time point; and performing extended Kalman filtering operation on each initial SOC value to obtain each filtered SOC value, and taking the SOC value corresponding to the current moment as the current SOC value of the lithium battery to be tested.
In an optional embodiment of the present application, the method further includes: the training model module is used for collecting voltage samples and real-time current data of the lithium battery which starts to be charged from the charge quantity of 0 at different temperatures; obtaining SOC data samples of the lithium battery based on each different charging accumulated time and the real-time current data; and inputting the temperature sample, the voltage sample and the SOC data sample corresponding to the SOC data sample into a DBN neural network for training to obtain the neural network model.
In an optional embodiment of the present application, the training model module is further configured to, after obtaining the SOC data sample of the lithium battery, normalize the SOC data sample and the voltage sample under the same temperature sample by using a mapminmax function; correspondingly, the temperature sample, the normalized SOC data sample and the normalized voltage sample are input into a DBN neural network for training, and the neural network model is obtained.
An energy storage lithium battery SOC estimation apparatus, comprising:
a memory for storing a computer program;
and the processor is used for executing the calculation program to realize the steps of the energy storage lithium battery SOC estimation method.
A computer-readable storage medium having stored thereon a computer program for execution by a processor to perform the steps of the method for estimating SOC of a energy storing lithium battery as defined in any of the above.
The invention provides an energy storage lithium battery SOC estimation method, which comprises the following steps: acquiring temperature data and voltage data of a lithium battery to be tested; and identifying and obtaining the SOC value of the lithium battery to be tested based on the temperature data, the voltage data and a neural network model, wherein the neural network model is a model representing the corresponding relation between the SOC value of the lithium battery, the temperature of the lithium battery and the voltage, and the model is obtained in advance through DBN neural network training.
When estimating the SOC of the lithium battery in the application, the temperature data and the voltage data of the lithium battery are used as reference, the estimation of the SOC value is realized by the neural network model obtained by the DBN neural network training, the influence of the battery temperature of the lithium battery on the stored charge amount is fully considered, the SOC value is estimated by the neural network model obtained by the deep belief neural network creation, the accuracy of the estimation of the SOC value of the lithium battery is improved to a certain extent, the reasonable use of the lithium battery is facilitated, and the service life of the lithium battery is prolonged.
The application also provides an energy storage lithium battery SOC estimation device, equipment and a computer readable storage medium, which have the beneficial effects.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for estimating the SOC of an energy storage lithium battery according to an embodiment of the present application;
fig. 2 is a block diagram of a structure of an energy storage lithium battery SOC estimation device provided in an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. 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.
The SOC value of the energy storage lithium battery is an important parameter of the lithium battery, and has an important reference value for controlling the charging and discharging of the lithium battery so as to prolong the service life of the lithium battery. At present, in a conventional method for detecting and estimating the SOC value of a lithium battery, the SOC value of the lithium battery is basically estimated by using data related to voltage, current, output power, and the like of the lithium battery, for example, for the lithium battery, the smaller the stored charge amount is, that is, the smaller the SOC value is, the smaller the corresponding voltage value is, and therefore, in most methods for determining the SOC value of the lithium battery at present, this characteristic of the lithium battery is utilized. However, in the process of estimating the SOC value by using this characteristic, the influence of temperature on voltage and the SOC value is often ignored, so that when the lithium battery operates in a high-temperature or extremely cold operating environment, the estimated SOC value has a large deviation.
Therefore, the technical scheme capable of improving the SOC value estimation accuracy of the energy storage lithium battery is provided in the application.
As shown in fig. 1, fig. 1 is a schematic flow chart of a method for estimating SOC of an energy storage lithium battery provided in an embodiment of the present application, where the method for estimating SOC of an energy storage lithium battery may include:
s11: and a neural network model which is obtained by training the DBN neural network and represents the corresponding relation between the SOC value of the lithium battery and the temperature and voltage of the lithium battery in advance.
The DBN neural network is a deep confidence neural network, and can be used for deeply learning a relational model which can automatically extract more abstract and expressive features from a sample so as to determine complex nonlinear mapping between input data and output data.
In this embodiment, the DBN neural network is adopted to represent the neural network model of the mapping relationship among the temperature, the voltage and the SOC of the lithium battery, so that the accuracy of the neural network model can be ensured.
S12: and obtaining temperature data and voltage data of the lithium battery to be tested.
S13: and identifying and obtaining the SOC value of the lithium battery to be tested based on the temperature data, the voltage data and the neural network model.
For a lithium battery, heat is inevitably generated in the charging and discharging processes, and although various measures are adopted to dissipate heat of the lithium battery in the using process, the temperature of the lithium battery cannot be always kept at a constant temperature; for example, when the mobile phone is used outdoors in winter, the electric quantity displayed on the mobile phone can be rapidly reduced, and when the mobile phone is taken indoors at higher temperature, the electric quantity can be recovered to a certain degree, so that the electric energy output of the lithium battery can be directly influenced by extremely cold temperature.
Therefore, the temperature has great influence on the electric energy output and input of the lithium battery, and for the purpose of more accurately determining the SOC value of the lithium battery, the neural network model of the mapping relation between the SOC values corresponding to the temperature and the voltage is utilized, so that the accuracy of the SOC value of the lithium battery is ensured to a great extent.
In summary, in the application, a deep belief network learning training of the DBN neural network is used to obtain a neural network model representing a mapping relation between the SOC value of the lithium battery and the temperature and the voltage, so that the accuracy of the neural network model is ensured, and the accuracy of the SOC value of the lithium battery determined by using the neural network model is further improved; in addition, when the SOC value is determined, the interference of the temperature on the SOC value estimation is fully considered, the temperature data is also used as one of the reference data for determining the SOC value, the accuracy of the SOC value estimation of the lithium battery is further improved, more reasonable charging and discharging of the lithium battery are facilitated, and the service life of the lithium battery is prolonged.
Based on the above embodiment, in order to further improve the accuracy of SOC value estimation of the lithium battery, the present application further provides another embodiment of the energy storage lithium battery SOC estimation method, where the embodiment may include:
s21: and a neural network model which is obtained by training the DBN neural network and represents the corresponding relation between the SOC value of the lithium battery and the temperature and voltage of the lithium battery in advance.
S22: and acquiring temperature data and voltage data acquired by a plurality of corresponding time points of the lithium battery to be detected within a preset time period from the current moment.
In practical application, the temperature data and the voltage data of the lithium battery to be tested can be continuously monitored and collected, so that the temperature data and the voltage data of each time point from the beginning of the use of the lithium battery to be tested to the current moment are obtained.
S23: and identifying the temperature data and the voltage data corresponding to each time point through a neural network model respectively to obtain an initial SOC value corresponding to each time point.
S24: and performing extended Kalman filtering operation on each initial SOC value to obtain each filtered SOC value, and taking the SOC value corresponding to the current moment as the current SOC value of the lithium battery to be tested.
Generally, the detection of the SOC value of the lithium battery is to estimate and detect the SOC value of the lithium battery at the current moment. However, there is a certain chance between the voltage data and the temperature data measured at a single time, which further causes the accuracy of the estimated SOC value to be low. Therefore, an SOC value is determined for temperature data and voltage data corresponding to each time point in a period of time including the current time, then filtering operation is performed on each SOC value by using an extended Kalman filtering algorithm, influences of factors such as noise or interference on the SOC value are eliminated, and further each filtered SOC value is ensured to be more accurate, so that the accuracy of each SOC value including the SOC value corresponding to the current time is improved, namely the accuracy of the SOC value corresponding to the current time as the current SOC value of the lithium battery to estimate the SOC value is improved.
It should be noted that the kalman filter algorithm has a good correction effect on the error. However, the SOC value changing along with the sampling time point is not linearly changed along with the change of time, filtering operation cannot be directly carried out by adopting Kalman filtering, and the extended Kalman filtering algorithm is characterized in that a linearization step is added in the filter equation derivation process of the Kalman filtering algorithm; during state estimation, performing real-time linear Taylor approximation on the estimation value of the system equation in the previous state; and predicting, namely performing linear Taylor similarity on the measurement equation at the corresponding prediction position to realize filtering operation on the SOC value.
Based on any of the above embodiments, in another optional embodiment of the present application, the process of obtaining the neural network model for training may include:
s31: and collecting voltage samples and real-time current data of the lithium battery which is charged from the charge quantity of 0 at different temperatures.
S32: and obtaining SOC data samples of the lithium battery based on each different charging accumulated time and real-time current data.
For the quantity of the charge quantity stored in the lithium battery, the charge quantity needs to be obtained by calculating the time integral based on the current of the lithium battery, and in order to obtain a more accurate SOC data sample, the lithium battery can be charged under the condition that the electric quantity of the lithium battery is completely exhausted, so that the SOC value determined by the current integral in different accumulated time lengths during the charging of the lithium battery is obtained.
In addition, in the lithium battery, as the number of times of charging increases, the maximum amount of charge that can be stored also changes, and accordingly, the relationship between the voltage of the lithium battery and the amount of stored charge also changes to some extent. Therefore, when sample data is collected, the collection of a plurality of lithium batteries which are not charged and discharged for times can be considered as the lithium battery samples for collecting the data samples.
In addition, in order to avoid realizing the detection of each lithium battery sample under different temperatures by the heat generation of the battery sample when the lithium battery sample data is collected, the temperature of the whole lithium battery sample is relatively concentrated. The lithium battery can be manually attached to a radiator with a temperature adjusting function, so that voltage data and SOC data samples of the lithium battery samples are measured at different temperatures ranging from 0 ℃ to 100 ℃.
Optionally, after obtaining the SOC data sample of the lithium battery, the SOC data sample and the voltage sample at the same temperature sample may be further normalized by using a mapminmax function.
After the SOC data sample and the voltage sample are subjected to normalization operation, the normalized sample is used for neural network training, so that interference of accidental errors of the sample data on a training result is avoided.
S33: and inputting the temperature sample, the voltage sample and the SOC data sample corresponding to the SOC data sample into the DBN neural network for training to obtain a neural network model.
The neural network model training process is specifically as follows:
(1) establishing and self-training an RBM:
the RBM comprises 1 visual layer and 1 hidden layer, wherein the visual layer and the hidden layer are symmetrically connected in two directions, the units in the same layer are not connected, the hidden unit can acquire the high-order correlation of the input visual unit, and the states of all the units are binary variables and can only take 0 or 1. For an RBM, the probability that its visible layer v and hidden layer h are in a certain state is given by the energy function E (v, h) — Σmamvm-∑nbnhn-∑mnvmhnwmnDetermining; wherein v ismAnd hnRespectively visible element m and hidden element n, wmnIs a visual unit vmAnd an implicit Unit hnThe connection weight value a betweenmAnd bnAre correspondingly biased.
The joint probability distribution p (v, h) of the visual layer v and the hidden layer h based on the energy function can be expressed as:
Figure BDA0003344732120000091
wherein Z ═ Σv,hexp (-E (v, h)) is a normalization factor. Thus, the probability p (v) that an RBM is assigned to a visual layer v is:
Figure BDA0003344732120000092
in RBM, since there is no connection between cells in the same layer, cell h is impliednThe conditional probability distribution of (a) is: p (h)n＝1|v)＝σ(bn+∑mvmwmn). Similarly, visual element viThe conditional probability distribution of (a) is: p (v)m＝1|h)＝σ(am+∑nhnwmn) Wherein σ (x) ═ 1/(1+ exp (-x))Is a Sigmoid function.
The training goal of the RBM is to obtain and generate new weights, and w represents the weights between the visual layer and the hidden layer. RBM is typically trained using the CD algorithm to obtain the network parameter θ ═ wmn,am,bnThe method comprises the following specific steps:
setting parameters such as training times, sample subset number and the like, and randomly initializing network parameters of the RBM; training the mth sample subset for multiple rounds, and updating network parameters after each training is finished until the maximum training times are reached; and repeating the training of the next sample subset until all the sample subsets are trained, storing the network parameters of the RBM, and finishing the training.
It should be noted that each sample subset includes a set of temperature samples, voltage samples, and SOC data samples.
In the following, the energy storage lithium battery SOC estimation device provided by the embodiment of the invention is introduced, and the energy storage lithium battery SOC estimation device described below and the energy storage lithium battery SOC estimation method described above may be referred to correspondingly.
Fig. 2 is a block diagram of a structure of an energy storage lithium battery SOC estimation device according to an embodiment of the present invention, where the energy storage lithium battery SOC estimation device according to fig. 2 may include:
the data acquisition module 100 is used for acquiring temperature data and voltage data of the lithium battery to be detected;
and the electric quantity estimation module 200 is configured to identify and obtain the SOC value of the lithium battery to be tested based on the temperature data, the voltage data and a neural network model, wherein the neural network model is a model representing a corresponding relationship between the SOC value of the lithium battery and the temperature and the voltage of the lithium battery, and is obtained in advance through DBN neural network training.
In an optional embodiment of the application, the data acquisition module is specifically configured to obtain the temperature data and the voltage data acquired at a plurality of corresponding time points within a preset time period from the current time of the lithium battery to be tested;
the electric quantity estimation module is specifically used for identifying the temperature data and the voltage data corresponding to each time point through the neural network model respectively to obtain an initial SOC value corresponding to each time point; and performing extended Kalman filtering operation on each initial SOC value to obtain each filtered SOC value, and taking the SOC value corresponding to the current moment as the current SOC value of the lithium battery to be tested.
In an optional embodiment of the present application, the method further includes: the training model module is used for collecting voltage samples and real-time current data of the lithium battery which starts to be charged from the charge quantity of 0 at different temperatures; obtaining SOC data samples of the lithium battery based on each different charging accumulated time and the real-time current data; and inputting the temperature sample, the voltage sample and the SOC data sample corresponding to the SOC data sample into a DBN neural network for training to obtain the neural network model.
In an optional embodiment of the present application, the training model module is further configured to, after obtaining the SOC data sample of the lithium battery, normalize the SOC data sample and the voltage sample under the same temperature sample by using a mapminmax function; correspondingly, the temperature sample, the normalized SOC data sample and the normalized voltage sample are input into a DBN neural network for training, and the neural network model is obtained.
The energy storage lithium battery SOC estimation device of this embodiment is used to implement the energy storage lithium battery SOC estimation method, so the specific implementation manner in the energy storage lithium battery SOC estimation device can be seen in the foregoing embodiments of the energy storage lithium battery SOC estimation method, and the specific implementation manner may refer to the description of each corresponding embodiment, and is not described herein again.
The application also discloses an embodiment of an energy storage lithium battery SOC estimation device, which may include:
a memory for storing a computer program;
and the processor is used for executing the calculation program to realize the steps of the energy storage lithium battery SOC estimation method.
The method for estimating the SOC of the energy storage lithium battery executed by the processor comprises the following steps:
obtaining temperature data and voltage data of a lithium battery to be tested; and identifying and obtaining the SOC value of the lithium battery to be tested based on the temperature data, the voltage data and a neural network model, wherein the neural network model is a model representing the corresponding relation between the SOC value of the lithium battery, the temperature of the lithium battery and the voltage, and the model is obtained in advance through DBN neural network training.
The processor in the embodiment obtains the neural network model by utilizing deep confidence neural network training, fully considers the influence of temperature on the charging and discharging process of the lithium battery, and finally determines the SOC value of the lithium battery by utilizing the neural network model according to the temperature parameter and the voltage parameter, so that the accuracy of determining the SOC value is ensured, the reasonable use of the lithium battery is facilitated, and the service life of the lithium battery is prolonged.
The present application further provides a computer-readable storage medium, in which a computer program is stored, where the computer program is executed by a processor to implement the steps of the method for estimating SOC of an energy storage lithium battery as described in any of the above.
The computer-readable storage medium may include: random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
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. Furthermore, 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 elements inherent in the list. 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. In addition, parts of the above technical solutions provided in the embodiments of the present application, which are consistent with the implementation principles of corresponding technical solutions in the prior art, are not described in detail so as to avoid redundant description.
The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.

Claims (10)

1. An energy storage lithium battery SOC estimation method is characterized by comprising the following steps:
obtaining temperature data and voltage data of a lithium battery to be tested;
and identifying and obtaining the SOC value of the lithium battery to be tested based on the temperature data, the voltage data and a neural network model, wherein the neural network model is a model representing the corresponding relation between the SOC value of the lithium battery, the temperature of the lithium battery and the voltage, and the model is obtained in advance through DBN neural network training.
2. The method for estimating the SOC of the energy storage lithium battery as claimed in claim 1, wherein the collecting and obtaining the temperature data and the voltage data of the lithium battery to be measured comprises:
acquiring the temperature data and the voltage data which are acquired by the lithium battery to be detected from a plurality of corresponding time points within a preset time period at the current moment;
correspondingly, identifying and obtaining the SOC value of the lithium battery to be tested based on the temperature data, the voltage data and the neural network model, and the method comprises the following steps:
identifying the temperature data and the voltage data corresponding to each time point through the neural network model respectively to obtain an initial SOC value corresponding to each time point;
and performing extended Kalman filtering operation on each initial SOC value to obtain each filtered SOC value, and taking the SOC value corresponding to the current moment as the current SOC value of the lithium battery to be tested.
3. The energy storage lithium battery SOC estimation method of claim 1, wherein the process of pre-training to obtain the neural network model comprises:
collecting voltage samples and real-time current data of a lithium battery which is charged from the charge amount of 0 at different temperatures;
obtaining SOC data samples of the lithium battery based on each different charging accumulated time and the real-time current data;
and inputting the temperature sample, the voltage sample and the SOC data sample corresponding to the SOC data sample into a DBN neural network for training to obtain the neural network model.
4. The method for estimating the SOC of the energy storage lithium battery as claimed in claim 3, further comprising, after obtaining the SOC data sample of the lithium battery:
normalizing the SOC data samples and the voltage samples for the same temperature sample using a mapminmax function;
correspondingly, inputting the temperature sample, the voltage sample and the SOC data sample corresponding to the SOC data sample into the DBN neural network for training, and obtaining the neural network model, including:
and inputting the temperature sample, the normalized SOC data sample and the normalized voltage sample into a DBN neural network for training to obtain the neural network model.
5. An energy storage lithium battery SOC estimation device is characterized by comprising:
the data acquisition module is used for acquiring and obtaining temperature data and voltage data of the lithium battery to be detected;
and the electric quantity estimation module is used for identifying and obtaining the SOC value of the lithium battery to be detected based on the temperature data, the voltage data and the neural network model, wherein the neural network model is a model representing the corresponding relation between the SOC value of the lithium battery, the temperature of the lithium battery and the voltage, and the model is obtained through DBN neural network training in advance.
6. The energy storage lithium battery SOC estimation device of claim 5, wherein the data acquisition module is specifically configured to obtain the temperature data and the voltage data acquired at a plurality of corresponding time points within a preset time period from a current time of the lithium battery to be measured;
the electric quantity estimation module is specifically used for identifying the temperature data and the voltage data corresponding to each time point through the neural network model respectively to obtain an initial SOC value corresponding to each time point; and performing extended Kalman filtering operation on each initial SOC value to obtain each filtered SOC value, and taking the SOC value corresponding to the current moment as the current SOC value of the lithium battery to be tested.
7. The energy storage lithium battery SOC estimation apparatus of claim 5, further comprising: the training model module is used for collecting voltage samples and real-time current data of the lithium battery which starts to be charged from the charge quantity of 0 at different temperatures; obtaining SOC data samples of the lithium battery based on each different charging accumulated time and the real-time current data; and inputting the temperature sample, the voltage sample and the SOC data sample corresponding to the SOC data sample into a DBN neural network for training to obtain the neural network model.
8. The energy storage lithium battery SOC estimation apparatus of claim 7, wherein the training model module is further configured to normalize the SOC data sample and the voltage sample at the same temperature sample using a mapminmax function after obtaining the SOC data sample of the lithium battery; correspondingly, the temperature sample, the normalized SOC data sample and the normalized voltage sample are input into a DBN neural network for training, and the neural network model is obtained.
9. An energy storage lithium battery SOC estimation device, comprising:
a memory for storing a computer program;
a processor for executing the calculation program to implement the steps of the energy storage lithium battery SOC estimation method according to any one of claims 1 to 4.
10. A computer-readable storage medium, in which a computer program is stored, which computer program is executable by a processor to implement the steps of the method for estimating SOC of an energy storing lithium battery as claimed in any one of claims 1 to 4.
CN202111319575.6A 2021-11-09 2021-11-09 Energy storage lithium battery SOC estimation method, device, equipment and storage medium Pending CN114021462A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111319575.6A CN114021462A (en) 2021-11-09 2021-11-09 Energy storage lithium battery SOC estimation method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111319575.6A CN114021462A (en) 2021-11-09 2021-11-09 Energy storage lithium battery SOC estimation method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114021462A true CN114021462A (en) 2022-02-08

Family

ID=80062807

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111319575.6A Pending CN114021462A (en) 2021-11-09 2021-11-09 Energy storage lithium battery SOC estimation method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114021462A (en)

Similar Documents

Publication Publication Date Title
Tian et al. Deep neural network battery charging curve prediction using 30 points collected in 10 min
CN111323719A (en) Method and system for online determination of health state of power battery pack of electric automobile
CN113253116A (en) Lithium ion battery state of charge estimation method and storage medium
CN107741568B (en) Lithium battery SOC estimation method based on state transition optimization RBF neural network
CN113702843B (en) Lithium battery parameter identification and SOC estimation method based on suburb optimization algorithm
CN113917334B (en) Battery health state estimation method based on evolution LSTM self-encoder
CN108872869B (en) Lithium ion battery degradation classification method based on BP neural network
CN110988695A (en) Power battery health state evaluation method and device, storage medium and electronic equipment
CN113128672B (en) Lithium ion battery pack SOH estimation method based on transfer learning algorithm
CN113484774B (en) Lithium battery pack capacity estimation method based on temperature calibration and neural network
CN109901072B (en) Retired battery parameter detection method based on historical data and laboratory test data
US20230305073A1 (en) Method and apparatus for providing a predicted aging state of a device battery based on a predicted usage pattern
CN116609676B (en) Method and system for monitoring state of hybrid energy storage battery based on big data processing
CN116953547A (en) Energy storage battery health evaluation method, system, equipment and storage medium
CN114280490A (en) Lithium ion battery state of charge estimation method and system
Chen et al. A novel battery health indicator and PSO-LSSVR for LiFePO4 battery SOH estimation during constant current charging
CN114609523A (en) Online battery capacity detection method, electronic equipment and storage medium
CN115600728A (en) Annual carbon emission estimation method and device for power battery
CN115994441A (en) Big data cloud platform online battery life prediction method based on mechanism information
CN115308608A (en) All-vanadium redox flow battery voltage prediction method, device and medium
CN116047308A (en) Lithium battery SOC estimation method based on PID control and DEKF
CN114879070A (en) Battery state evaluation method and related equipment
CN114545275A (en) Indirect prediction method for remaining service life of lithium ion battery
CN112946480A (en) Lithium battery circuit model simplification method for improving SOC estimation real-time performance
CN117113026A (en) Zinc-bromine flow battery SOC (state of charge) evaluation method based on linear regression prediction

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