CN117007978A - Battery voltage prediction method and device, electronic equipment and storage medium - Google Patents

Battery voltage prediction method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN117007978A
CN117007978A CN202311281574.6A CN202311281574A CN117007978A CN 117007978 A CN117007978 A CN 117007978A CN 202311281574 A CN202311281574 A CN 202311281574A CN 117007978 A CN117007978 A CN 117007978A
Authority
CN
China
Prior art keywords
voltage
ndc
electrode
fnn
simulation module
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.)
Granted
Application number
CN202311281574.6A
Other languages
Chinese (zh)
Other versions
CN117007978B (en
Inventor
刘承皓
朱勇
李来龙
曹治
张斌
任立兵
刘明义
王晓龙
王建星
赵珈卉
孙悦
刘涵
刘辰星
孙周婷
杨超然
平小凡
成前
王娅宁
周敬伦
段召容
雷浩东
李�昊
杨名昊
荆鑫
吴琼
叶林
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.)
Huaneng Clean Energy Research Institute
Huaneng Lancang River Hydropower Co Ltd
Original Assignee
Huaneng Clean Energy Research Institute
Huaneng Lancang River Hydropower 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 Huaneng Clean Energy Research Institute, Huaneng Lancang River Hydropower Co Ltd filed Critical Huaneng Clean Energy Research Institute
Priority to CN202311281574.6A priority Critical patent/CN117007978B/en
Publication of CN117007978A publication Critical patent/CN117007978A/en
Application granted granted Critical
Publication of CN117007978B publication Critical patent/CN117007978B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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]
    • G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
    • 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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/30—Circuit design
    • G06F30/36—Circuit design at the analogue level
    • G06F30/367—Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0499—Feedforward networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Geometry (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Medical Informatics (AREA)
  • Secondary Cells (AREA)

Abstract

The disclosure provides a battery voltage prediction method, a device, an electronic device and a storage medium, wherein the method comprises the following steps: acquiring a battery temperature time sequence, initial model parameters, a current time sequence, a first FNN voltage prediction model, a second FNN voltage prediction model and an NDC voltage prediction model; inputting the battery temperature time sequence, the current time sequence and the initial model parameters into a first FNN voltage prediction model, obtaining NDC model parameters, and configuring the NDC voltage prediction model; inputting the electrode voltage and current time sequence into a second FNN voltage prediction model to obtain a FNN predicted voltage; the target predicted voltage is determined based on the NDC predicted voltage and the FNN predicted voltage. And the target prediction voltage is determined through the simultaneous prediction of the NDC and the FNN and based on the prediction result, and the prediction effect is improved by combining simulation and neural network prediction, so that the continuous description of the operation behavior of the battery can be realized.

Description

Battery voltage prediction method and device, electronic equipment and storage medium
Technical Field
The disclosure relates to the technical field of battery safety, and in particular relates to a battery voltage prediction method, a battery voltage prediction device, electronic equipment and a storage medium.
Background
Along with the continuous development of battery technology, batteries are widely applied in the energy field, and the living aspects of the batteries are spread, and the batteries are gradually aged in the use process, and the capacity of the batteries is gradually reduced, so that the normal use of the batteries is affected.
The current battery capacity prediction method is roughly divided into a traditional method and a machine learning method, wherein the traditional method is used for predicting the battery capacity by combining a corresponding formula after charging and discharging for a period of time; the machine learning method generally predicts through a support vector machine, a Gaussian regression process, a deep learning network and the like, and has good prediction effect. The operability of the lithium ion battery in the working process is improved, a stable and self-adaptive model is needed to describe the behavior of the lithium ion battery, and the current vast majority of models are subjected to open-loop modeling only through fitting and cannot continuously and stably describe the behavior of the battery.
Disclosure of Invention
The present disclosure aims to solve, at least to some extent, one of the technical problems in the related art.
To this end, it is an object of the present disclosure to propose a battery voltage prediction method.
A second object of the present disclosure is to provide a battery voltage prediction apparatus.
A third object of the present disclosure is to propose an electronic device.
A fourth object of the present disclosure is to propose a non-transitory computer readable storage medium.
A fifth object of the present disclosure is to propose a computer programme product.
To achieve the above object, an embodiment of a first aspect of the present disclosure provides a battery voltage prediction method, including: acquiring a battery temperature time sequence, initial model parameters and a current time sequence, and acquiring a first feed-forward neural network FNN voltage prediction model, a second FNN voltage prediction model and a nonlinear double-capacitor NDC voltage prediction model; inputting the battery temperature time sequence, the current time sequence and the initial model parameters into the first FNN voltage prediction model to obtain NDC model parameters, and configuring the NDC voltage prediction model based on the NDC model parameters; acquiring electrode voltage and NDC predicted voltage of the NDC voltage prediction model, and inputting the electrode voltage and the current time sequence into a second FNN voltage prediction model to acquire FNN predicted voltage; a target predicted voltage is determined based on the NDC predicted voltage and the FNN predicted voltage.
According to one embodiment of the present disclosure, the nonlinear double capacitance NDC voltage prediction model includes: the device comprises an electrode simulation module and an electrolyte simulation module, wherein the electrode simulation module and the electrolyte simulation module are connected in series.
According to one embodiment of the present disclosure, the battery voltage prediction method further includes:
according to one embodiment of the disclosure, the model formula of the nonlinear double capacitance NDC voltage prediction model is:wherein (1)>To output positive voltage +.>For outputting the negative voltage>For outputting the electrolyte voltage->For the analog positive voltage of the electrode analog module, < > is>For the analog negative voltage of the electrode analog module, < >>For the simulated electrolyte voltage of the electrolyte simulation module, < > a->For the simulated current, a is a first model parameter and B is a second model parameter.
According to one embodiment of the disclosure, the first model parameter obtaining formula is:wherein said->For the positive capacitance of the electrode simulation module, the +.>For the negative capacitance value of the electrode simulation module, the +.>For the positive resistance of the electrode simulation module, the +.>For the negative resistance value of the electrode simulation module, the +.>For the impedance value of the electrolyte simulation module, the +.>And A is the first model parameter for the capacitance value of the electrolyte simulation module.
According to one embodiment of the disclosure, the second model parameter obtaining formula is:wherein said->For the positive capacitance of the electrode simulation module, the +.>For the negative capacitance value of the electrode simulation module, the +.>For the positive resistance of the electrode simulation module, the +.>For the negative resistance value of the electrode simulation module, the +.>And B is the second model parameter for the capacitance value of the electrolyte simulation module.
According to one embodiment of the present disclosure, the obtaining the NDC prediction voltage of the NDC voltage prediction model includes: acquiring the internal resistance of a battery, and determining the internal resistance voltage based on the internal resistance of the battery; and subtracting the electrode voltage from the electrolyte voltage and the internal resistance voltage in sequence to obtain the NDC predicted voltage.
According to one embodiment of the disclosure, the electric quantity calculation formula of the nonlinear double-capacitance NDC voltage prediction model is:wherein said->For the positive capacitance value of the electrode simulation module, theFor the negative capacitance value of the electrode simulation module, the +.>For the positive resistance value of the electrode simulation module, theFor the negative resistance value of the electrode simulation module, the +.>Is the electric quantity.
To achieve the above object, a second aspect of the present disclosure provides a battery voltage prediction apparatus, including: the acquisition module is used for acquiring a battery temperature time sequence, initial model parameters and a current time sequence, and acquiring a first FNN voltage prediction model, a second FNN voltage prediction model and a nonlinear double-capacitor NDC voltage prediction model; the configuration module is used for inputting the battery temperature time sequence, the current time sequence and the initial model parameters into the first FNN voltage prediction model to obtain NDC model parameters, and configuring the NDC voltage prediction model based on the NDC model parameters; the prediction module is used for acquiring electrode voltage and NDC predicted voltage of the NDC voltage prediction model, and inputting the electrode voltage and the current time sequence into a second FNN voltage prediction model to acquire FNN predicted voltage; and the determining module is used for determining a target predicted voltage based on the NDC predicted voltage and the FNN predicted voltage.
To achieve the above object, an embodiment of a third aspect of the present disclosure provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to implement a battery voltage prediction method according to an embodiment of the first aspect of the present disclosure.
To achieve the above object, a fourth aspect embodiment of the present disclosure proposes a non-transitory computer-readable storage medium storing computer instructions for implementing the battery voltage prediction method according to the first aspect embodiment of the present disclosure.
To achieve the above object, an embodiment of a fifth aspect of the present disclosure proposes a computer program product comprising a computer program for implementing a battery voltage prediction method according to an embodiment of the first aspect of the present disclosure when being executed by a processor.
The NDC voltage prediction model and the second FNN voltage prediction model are used for simultaneously predicting, the target prediction voltage is determined based on the prediction result, the simulation prediction and the neural network prediction can be combined simultaneously, the prediction effect is improved, and meanwhile, continuous description of the operation behavior of the battery can be realized by establishing the model.
Drawings
FIG. 1 is a schematic diagram of a battery voltage prediction method according to one embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a simulation circuit of a nonlinear double capacitance NDC voltage prediction model;
FIG. 3 is a circuit diagram of an electrode simulation module;
FIG. 4 is a circuit diagram of an electrolyte simulation module;
FIG. 5 is a schematic diagram of another battery voltage prediction method of an embodiment of the present disclosure;
FIG. 6 is a schematic diagram of a battery voltage prediction apparatus according to one embodiment of the present disclosure;
fig. 7 is a schematic diagram of an electronic device according to one embodiment of the present disclosure.
Detailed Description
Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present disclosure and are not to be construed as limiting the present disclosure.
Fig. 1 is a schematic diagram of an exemplary embodiment of a battery voltage prediction method according to the present disclosure, as shown in fig. 1, the battery voltage prediction method includes the following steps:
s101, acquiring a battery temperature time sequence, initial model parameters and a current time sequence, and acquiring a first FNN voltage prediction model, a second FNN voltage prediction model and a nonlinear double-capacitor NDC voltage prediction model.
The battery voltage prediction method of the embodiment of the application can be applied to the scene of battery power voltage, and the execution subject of the battery voltage prediction of the embodiment of the application can be the battery voltage prediction device of the embodiment of the application, and the battery voltage prediction device can be arranged on electronic equipment.
The first feedforward neural network (feedforward neural network, FNN) voltage prediction model and the second FNN voltage prediction model are trained in advance and can be changed according to actual design requirements, and are not limited in any way. The FNN model is one type of artificial neural network. The feedforward neural network adopts a unidirectional multilayer structure. Wherein each layer includes a number of neurons. In such a neural network, each neuron may receive a signal from a previous layer of neurons and generate an output to the next layer. The 0 th layer is called an input layer, the last layer is called an output layer, and other intermediate layers are called hidden layers (or hidden layers and hidden layers). The hidden layer can be one layer or multiple layers.
It should be noted that, the nonlinear double capacitor (Nonlinear dual capacitor, NDC) voltage prediction model is a simulation model, and a simulation circuit of the simulation model is designed in advance and can be changed according to actual design requirements, which is not limited in any way.
In the embodiment of the disclosure, the battery temperature time sequence, the initial model parameters, and the current time sequence are set in advance, and can be changed according to actual design requirements, which is not limited in any way.
The battery temperature time sequence is a sequence of battery temperature and time stamp corresponding to the battery temperature, and the sequence may include data of a plurality of time stamps.
The initial model parameters may include a variety of parameters, not limited in any way herein, and may include, for example, initial charge, initial resistance, initial capacitance, and the like.
The current time sequence is a sequence of current values and time stamps corresponding to the current values, and the sequence can comprise data of a plurality of time stamps.
S102, inputting the battery temperature time sequence, the current time sequence and the initial model parameters into a first FNN voltage prediction model to obtain NDC model parameters, and configuring the NDC voltage prediction model based on the NDC model parameters.
In an embodiment of the present disclosure, the first FNN voltage prediction model is used to generate NDC model parameters of the NDC model. The model parameters may include, without limitation, resistance values, capacitance values, current values, and the like of the NDC model, for example.
In the embodiment of the disclosure, after the NDC model parameters are obtained, the corresponding values in the NDC voltage prediction model may be changed based on the NDC model parameters, so as to modify the current NDC voltage prediction model into a model that meets the current simulation needs.
S103, electrode voltage and NDC predicted voltage of the NDC voltage prediction model are obtained, and the electrode voltage and current time sequence is input into the second FNN voltage prediction model to obtain FNN predicted voltage.
In the embodiment of the disclosure, the electrode voltage of the NDC voltage prediction model may be obtained through a simulation experiment. The electrode voltage may be a positive electrode voltage or a negative electrode voltage, and is not limited in any way.
S104, determining a target predicted voltage based on the NDC predicted voltage and the FNN predicted voltage.
It should be noted that, the method for determining the target predicted voltage based on the NDC predicted voltage and the FNN predicted voltage may be various, and is not limited in any way.
Alternatively, the target predicted voltage may be calculated from the NDC predicted voltage and the FNN predicted voltage by a voltage algorithm which is designed in advance and may be changed as needed, without any limitation.
Alternatively, the NDC predicted voltage and the FNN predicted voltage may be multiplied by the weight values and summed to obtain the target predicted voltage. The weight value is set in advance, and can be changed according to actual design requirements, and is not limited in any way.
It can be appreciated that the target predicted voltage can be continuously obtained as long as the input data is continuously provided for the NDC voltage prediction model and the second FNN voltage prediction model.
In the embodiment of the disclosure, firstly, a battery temperature time sequence, initial model parameters and a current time sequence are acquired, a first feedforward neural network FNN voltage prediction model, a second FNN voltage prediction model and a nonlinear double-capacitance NDC voltage prediction model are acquired, then the battery temperature time sequence, the current time sequence and the initial model parameters are input into the first FNN voltage prediction model to acquire NDC model parameters, the NDC voltage prediction model is configured based on the NDC model parameters, then electrode voltage and NDC prediction voltage of the NDC voltage prediction model are acquired, the electrode voltage and the current time sequence are input into the second FNN voltage prediction model to acquire FNN prediction voltage, and finally, a target prediction voltage is determined based on the NDC prediction voltage and the FNN prediction voltage. Therefore, the NDC voltage prediction model and the second FNN voltage prediction model are used for simultaneously predicting, the target prediction voltage is determined based on the prediction result, the simulation prediction and the neural network prediction can be combined simultaneously, the prediction effect is improved, and meanwhile, the continuous description of the operation behavior of the battery can be realized by establishing the model.
In an embodiment of the present disclosure, as shown in fig. 2, the nonlinear double capacitance NDC voltage prediction model includes an electrode simulation module and an electrolyte simulation module, wherein the electrode simulation module and the electrolyte simulation module are connected in series.
It should be noted that, the electrode simulation module is used for representing the positive and negative electrodes of the battery, and the electrolyte simulation module is used for representing the electrolyte of the battery, so that the NDC voltage prediction model can realize the simulation of the overall operation of the battery.
In one possible implementation, fig. 3 and 4 are circuit diagrams of an electrode simulation module and an electrolyte simulation module, respectively. Wherein,R b is the resistance of the positive electrode, and the negative electrode,R s is the resistance of the negative electrode,C b is the capacitance of the positive electrode, and the negative electrode,C s is the capacitance of the negative electrode,R 0 is the internal resistance of the battery,C 1 is an electrolyte capacitor.
Based on fig. 3 and 4, the model formula of the NDC voltage prediction model is:
wherein,to output positive voltage +.>For outputting the negative voltage>In order to output the voltage of the electrolyte,for simulating the positive voltage of the electrode simulation module, < >>For the simulated negative voltage of the electrode simulation module, +.>Simulated electrolyte voltage for electrolyte simulation module, < >>For the simulated current, a is a first model parameter and B is a second model parameter.
The acquisition formula of the first model parameters is as follows:
wherein,for the positive capacitance of the electrode simulation module, < >>For the negative capacitance of the electrode simulation module, +.>For the positive resistance value of the electrode simulation module, < >>For the negative resistance value of the electrode simulation module, +.>Impedance value for electrolyte simulation module, +.>And A is a first model parameter, which is the capacitance value of the electrolyte simulation module.
The acquisition formula of the second model parameters is as follows:
wherein,for the positive capacitance of the electrode simulation module, < >>For the negative capacitance of the electrode simulation module, +.>For the positive resistance value of the electrode simulation module, < >>For the negative resistance value of the electrode simulation module, +.>And B is a second model parameter, wherein the capacitance value of the electrolyte simulation module is the capacitance value of the electrolyte simulation module.
In the above embodiment, the NDC predicted voltage of the NDC voltage prediction model is obtained, which may be further explained by fig. 3, and the method includes:
s501, obtaining the internal resistance of the battery, and determining the internal resistance voltage based on the internal resistance of the battery.
In the embodiment of the present disclosure, the calculation formula of the internal resistance of the battery is:
wherein,、/>、/>、/>and->The SOC is the electric quantity, which is an extra-constant number. It should be noted that->、/>、/>、/>Andthe design is designed in advance, and can be changed according to actual design requirements, and is not limited in any way.
After the internal resistance of the battery is obtained, the internal resistance voltage may be obtained by multiplying the current time series by the internal resistance voltage.
S502, subtracting the electrode voltage from the electrolyte voltage and the internal resistance voltage in sequence to obtain an NDC predicted voltage.
In the embodiment of the present disclosure, the formula for obtaining the NDC predicted voltage is:
wherein,predicting voltage for NDC +.>For electrode voltage>For electrolyte voltage, < >>Is an internal resistance voltage.
In the embodiment of the disclosure, the battery power can also be determined through a nonlinear double-capacitor NDC voltage prediction model, and the calculation formula is as follows:
wherein,for the positive capacitance of the electrode simulation module, < >>For the negative capacitance of the electrode simulation module, +.>For the positive resistance value of the electrode simulation module, < >>For the negative resistance value of the electrode simulation module, +.>Is the electric quantity.
The NDC voltage prediction model and the second FNN voltage prediction model are used for simultaneously predicting, the target prediction voltage is determined based on the prediction result, the simulation prediction and the neural network prediction can be combined simultaneously, the prediction effect is improved, and meanwhile, continuous description of the operation behavior of the battery can be realized by establishing the model.
In correspondence with the battery voltage prediction methods provided in the above-described several embodiments, an embodiment of the present disclosure further provides a battery voltage prediction apparatus, and since the battery voltage prediction apparatus provided in the embodiment of the present disclosure corresponds to the battery voltage prediction method provided in the above-described several embodiments, implementation of the battery voltage prediction method described above is also applicable to the battery voltage prediction apparatus provided in the embodiment of the present disclosure, and will not be described in detail in the following embodiments.
Fig. 6 is a schematic diagram of a battery voltage prediction apparatus according to the present disclosure, as shown in fig. 6, the battery voltage prediction apparatus 600 includes: the acquisition module 610, the configuration module 620, the prediction module 630, and the determination module 640.
The acquiring module 610 is configured to acquire a battery temperature time sequence, an initial model parameter, a current time sequence, and a first feedforward neural network FNN voltage prediction model, a second FNN voltage prediction model, and a nonlinear double capacitance NDC voltage prediction model.
The configuration module 620 is configured to input the battery temperature time sequence, the current time sequence and the initial model parameters into the first FNN voltage prediction model to obtain NDC model parameters, and configure the NDC voltage prediction model based on the NDC model parameters.
The prediction module 630 is configured to obtain an electrode voltage and an NDC predicted voltage of the NDC voltage prediction model, and input the electrode voltage and the current time sequence into the second FNN voltage prediction model to obtain a FNN predicted voltage.
A determining module 640 for determining a target predicted voltage based on the NDC predicted voltage and the FNN predicted voltage.
A nonlinear double capacitance NDC voltage prediction model comprising: the device comprises an electrode simulation module and an electrolyte simulation module, wherein the electrode simulation module and the electrolyte simulation module are connected in series.
The model formula of the nonlinear double-capacitance NDC voltage prediction model is as follows:wherein,to output positive voltage +.>For outputting the negative voltage>For outputting the electrolyte voltage->For simulating the positive voltage of the electrode simulation module, < >>For the simulated negative voltage of the electrode simulation module, +.>Simulated electrolyte voltage for electrolyte simulation module, < >>For the simulated current, a is a first model parameter and B is a second model parameter.
The acquisition formula of the first model parameters is as follows:wherein (1)>For the positive capacitance of the electrode simulation module, < >>For the negative capacitance of the electrode simulation module, +.>For the positive resistance value of the electrode simulation module, < >>For the negative resistance value of the electrode simulation module, +.>Impedance value for electrolyte simulation module, +.>And A is a first model parameter, which is the capacitance value of the electrolyte simulation module.
The acquisition formula of the second model parameters is as follows:wherein (1)>For the positive capacitance of the electrode simulation module, < >>For the negative capacitance of the electrode simulation module, +.>For the positive resistance value of the electrode simulation module, < >>For the negative resistance value of the electrode simulation module, +.>And B is a second model parameter, wherein the capacitance value of the electrolyte simulation module is the capacitance value of the electrolyte simulation module.
Obtaining an NDC prediction voltage of the NDC voltage prediction model, comprising: acquiring the internal resistance of the battery, and determining the internal resistance voltage based on the internal resistance of the battery; and subtracting the electrode voltage from the electrolyte voltage and the internal resistance voltage in sequence to obtain an NDC predicted voltage.
The electric quantity calculation formula of the nonlinear double-capacitor NDC voltage prediction model is as follows:wherein (1)>For the positive capacitance of the electrode simulation module, < >>For the negative capacitance of the electrode simulation module, +.>For the positive resistance value of the electrode simulation module, < >>For the negative resistance value of the electrode simulation module, +.>Is the electric quantity.
The NDC voltage prediction model and the second FNN voltage prediction model are used for simultaneously predicting, the target prediction voltage is determined based on the prediction result, the simulation prediction and the neural network prediction can be combined simultaneously, the prediction effect is improved, and meanwhile, continuous description of the operation behavior of the battery can be realized by establishing the model.
In order to implement the above embodiments, the embodiments of the present disclosure further provide an electronic device 700, as shown in fig. 7, where the electronic device 700 includes: the processor 701 and a memory 702 communicatively coupled to the processors, the memory 702 storing instructions executable by the at least one processor, the instructions being executable by the at least one processor 701 to implement a battery voltage prediction method as an embodiment of the first aspect of the present disclosure.
To achieve the above-described embodiments, the embodiments of the present disclosure also propose a non-transitory computer-readable storage medium storing computer instructions for causing a computer to implement the battery voltage prediction method as the embodiments of the first aspect of the present disclosure.
To achieve the above embodiments, the embodiments of the present disclosure also propose a computer program product comprising a computer program which, when executed by a processor, implements a battery voltage prediction method as the embodiments of the first aspect of the present disclosure.
In the description of the present disclosure, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present disclosure and simplifying the description, and do not indicate or imply that the device or element being referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present disclosure.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a 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 present disclosure, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Although embodiments of the present disclosure have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the present disclosure, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the present disclosure.

Claims (10)

1. A battery voltage prediction method, comprising:
acquiring a battery temperature time sequence, initial model parameters and a current time sequence, and acquiring a first feed-forward neural network FNN voltage prediction model, a second FNN voltage prediction model and a nonlinear double-capacitor NDC voltage prediction model;
inputting the battery temperature time sequence, the current time sequence and the initial model parameters into the first FNN voltage prediction model to obtain NDC model parameters, and configuring the NDC voltage prediction model based on the NDC model parameters;
acquiring electrode voltage and NDC predicted voltage of the NDC voltage prediction model, and inputting the electrode voltage and the current time sequence into a second FNN voltage prediction model to acquire FNN predicted voltage;
a target predicted voltage is determined based on the NDC predicted voltage and the FNN predicted voltage.
2. The method of claim 1, wherein the nonlinear double capacitance NDC voltage prediction model comprises:
the device comprises an electrode simulation module and an electrolyte simulation module, wherein the electrode simulation module and the electrolyte simulation module are connected in series.
3. The method of claim 2, wherein the model formula of the nonlinear double capacitance NDC voltage prediction model is:
wherein,to output positive voltage +.>For outputting the negative voltage>For outputting the electrolyte voltage->For the analog positive voltage of the electrode analog module, < > is>For the analog negative voltage of the electrode analog module, < >>Mould for the electrolyte simulation moduleQuasi-electrolyte voltage, < >>For the simulated current, a is a first model parameter and B is a second model parameter.
4. A method according to claim 3, wherein the first model parameter is obtained by the formula:
wherein the saidFor the positive capacitance of the electrode simulation module, the +.>For the negative capacitance value of the electrode simulation module, the +.>For the positive resistance of the electrode simulation module, the +.>For the negative resistance value of the electrode simulation module, the +.>For the impedance value of the electrolyte simulation module, the +.>And A is the first model parameter for the capacitance value of the electrolyte simulation module.
5. A method according to claim 3, wherein the second model parameters are obtained by the formula:
wherein the saidFor the positive capacitance of the electrode simulation module, the +.>For the negative capacitance value of the electrode simulation module, the +.>For the positive resistance of the electrode simulation module, the +.>For the negative resistance value of the electrode simulation module, the +.>And B is the second model parameter for the capacitance value of the electrolyte simulation module.
6. The method of any one of claims 1-5, wherein the obtaining the NDC prediction voltage of the NDC voltage prediction model comprises:
acquiring the internal resistance of a battery, and determining the internal resistance voltage based on the internal resistance of the battery;
and subtracting the electrode voltage from the electrolyte voltage and the internal resistance voltage in sequence to obtain the NDC predicted voltage.
7. The method of claim 2, wherein the power calculation formula of the nonlinear double capacitance NDC voltage prediction model is:
wherein the saidFor the positive capacitance of the electrode simulation module, the +.>For the negative capacitance value of the electrode simulation module, the +.>For the positive resistance of the electrode simulation module, the +.>For the negative resistance value of the electrode simulation module, the +.>Is the electric quantity.
8. A battery voltage prediction apparatus, comprising:
the acquisition module is used for acquiring a battery temperature time sequence, initial model parameters and a current time sequence, and acquiring a first FNN voltage prediction model, a second FNN voltage prediction model and a nonlinear double-capacitor NDC voltage prediction model;
the configuration module is used for inputting the battery temperature time sequence, the current time sequence and the initial model parameters into the first FNN voltage prediction model to obtain NDC model parameters, and configuring the NDC voltage prediction model based on the NDC model parameters;
the prediction module is used for acquiring electrode voltage and NDC predicted voltage of the NDC voltage prediction model, and inputting the electrode voltage and the current time sequence into a second FNN voltage prediction model to acquire FNN predicted voltage;
and the determining module is used for determining a target predicted voltage based on the NDC predicted voltage and the FNN predicted voltage.
9. An electronic device, comprising a memory and a processor;
wherein the processor runs a program corresponding to executable program code stored in the memory by reading the executable program code for implementing the method according to any one of claims 1-7.
10. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1-7.
CN202311281574.6A 2023-10-07 2023-10-07 Battery voltage prediction method and device, electronic equipment and storage medium Active CN117007978B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311281574.6A CN117007978B (en) 2023-10-07 2023-10-07 Battery voltage prediction method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311281574.6A CN117007978B (en) 2023-10-07 2023-10-07 Battery voltage prediction method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN117007978A true CN117007978A (en) 2023-11-07
CN117007978B CN117007978B (en) 2024-01-30

Family

ID=88565759

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311281574.6A Active CN117007978B (en) 2023-10-07 2023-10-07 Battery voltage prediction method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117007978B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101067644A (en) * 2007-04-20 2007-11-07 杭州高特电子设备有限公司 Storage battery performance analytical expert diagnosing method
CN110129832A (en) * 2019-06-21 2019-08-16 广西大学 A kind of Multipurpose Optimal Method of aluminium electrolysis process tank voltage
CN113097995A (en) * 2021-03-17 2021-07-09 河北工业大学 Alternating current-direct current hybrid power distribution network optimized operation method considering multiple time scales
CN113689039A (en) * 2021-08-25 2021-11-23 南昌师范学院 Lithium ion battery RUL time sequence prediction method
CN115308608A (en) * 2022-08-02 2022-11-08 武汉理工大学 All-vanadium redox flow battery voltage prediction method, device and medium
CN115983084A (en) * 2022-11-23 2023-04-18 西北工业大学 Method, system, equipment and terminal for predicting remaining service life of fuel cell
WO2023130776A1 (en) * 2022-01-07 2023-07-13 国网浙江省电力有限公司电力科学研究院 Method and system for predicting working condition health status of battery in energy storage power station

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101067644A (en) * 2007-04-20 2007-11-07 杭州高特电子设备有限公司 Storage battery performance analytical expert diagnosing method
CN110129832A (en) * 2019-06-21 2019-08-16 广西大学 A kind of Multipurpose Optimal Method of aluminium electrolysis process tank voltage
CN113097995A (en) * 2021-03-17 2021-07-09 河北工业大学 Alternating current-direct current hybrid power distribution network optimized operation method considering multiple time scales
CN113689039A (en) * 2021-08-25 2021-11-23 南昌师范学院 Lithium ion battery RUL time sequence prediction method
WO2023130776A1 (en) * 2022-01-07 2023-07-13 国网浙江省电力有限公司电力科学研究院 Method and system for predicting working condition health status of battery in energy storage power station
CN115308608A (en) * 2022-08-02 2022-11-08 武汉理工大学 All-vanadium redox flow battery voltage prediction method, device and medium
CN115983084A (en) * 2022-11-23 2023-04-18 西北工业大学 Method, system, equipment and terminal for predicting remaining service life of fuel cell

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
SAKSHI SHARMA: "Neural Network based State of Charge Prediction of Lithium-ion Battery", 2022 IEEE 2ND INTERNATIONAL CONFERENCE ON SUSTAINABLE ENERGY AND FUTURE ELECTRIC TRANSPORTATION *
王海新 等: "基于新型智能算法对太阳能无人机光伏组件电压预测控制研究", 《太阳能学报》, vol. 42, no. 4, pages 175 - 179 *

Also Published As

Publication number Publication date
CN117007978B (en) 2024-01-30

Similar Documents

Publication Publication Date Title
Wang et al. Modeling and state-of-charge prediction of lithium-ion battery and ultracapacitor hybrids with a co-estimator
EP3748380B1 (en) Battery capacity prediction system using charge and discharge cycles of a battery to predict capacity variations, and associated method
He et al. Online state-of-health estimation of lithium-ion batteries using Dynamic Bayesian Networks
Marie-Francoise et al. Supercapacitor thermal-and electrical-behaviour modelling using ANN
JP7095110B2 (en) Battery status estimation method
JP5743857B2 (en) Method and apparatus for simulating a battery in real time
JP3935099B2 (en) Internal state detection system for power storage device for vehicle
Wu et al. On-line supercapacitor dynamic models for energy conversion and management
CN109001640B (en) Data processing method and device for power battery
CN112149345B (en) Battery management method and device, computer equipment and storage medium
CN115632179B (en) Intelligent quick charging method and system for lithium ion battery
El Ghossein et al. Survey on electrical modeling methods applied on different battery types
KR102090476B1 (en) a BMS optimizing system using a cloud system and big data
KR20180057266A (en) Method and apparatus for estimating state of battery
Lei et al. Residual capacity estimation for ultracapacitors in electric vehicles using artificial neural network
Fendri et al. Dynamic model to follow the state of charge of a lead-acid battery connected to photovoltaic panel
CN117007978B (en) Battery voltage prediction method and device, electronic equipment and storage medium
CN110232432A (en) A kind of lithium battery group SOC prediction technique based on artificial life model
CN117169723A (en) Battery evaluation system based on multi-model fusion
Raël et al. A mathematical lithium-ion battery model implemented in an electrical engineering simulation software
CN114264967A (en) Method and system for rapidly estimating retired battery residual energy based on capacity loss mechanism
CN114441969A (en) Battery state of charge estimation method and device
CN113495215A (en) Virtual battery cell system, operation method thereof and twin battery
CN116933569B (en) Multi-scale mixed model construction method and device for energy storage digital twin body
Zhang et al. Joint estimation of state-of-charge and state-of-power for hybrid supercapacitors using fractional-order adaptive unscented Kalman filter

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