CN117637044A - 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 PDFInfo
- Publication number
- CN117637044A CN117637044A CN202311298846.3A CN202311298846A CN117637044A CN 117637044 A CN117637044 A CN 117637044A CN 202311298846 A CN202311298846 A CN 202311298846A CN 117637044 A CN117637044 A CN 117637044A
- Authority
- CN
- China
- Prior art keywords
- lithium ion
- battery
- electrode
- ion concentration
- liquid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 claims abstract description 146
- 229910001416 lithium ion Inorganic materials 0.000 claims abstract description 146
- 239000007791 liquid phase Substances 0.000 claims abstract description 79
- 239000002245 particle Substances 0.000 claims abstract description 66
- 230000004907 flux Effects 0.000 claims abstract description 40
- 230000010287 polarization Effects 0.000 claims abstract description 33
- 239000011148 porous material Substances 0.000 claims abstract description 33
- 238000003062 neural network model Methods 0.000 claims abstract description 16
- 238000009792 diffusion process Methods 0.000 claims description 26
- 239000007790 solid phase Substances 0.000 claims description 25
- 238000004364 calculation method Methods 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 15
- 150000002500 ions Chemical class 0.000 claims 1
- 238000004590 computer program Methods 0.000 description 11
- 238000013528 artificial neural network Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000002035 prolonged effect Effects 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 2
- 238000009830 intercalation Methods 0.000 description 2
- 230000002687 intercalation Effects 0.000 description 2
- 229910052744 lithium Inorganic materials 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000003487 electrochemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Secondary Cells (AREA)
Abstract
The invention relates to a battery voltage prediction method, a battery voltage prediction device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring electrochemical parameters of the battery, and calculating the lithium ion pore wall flux on the surface of the electrode particles based on the electrochemical parameters; inputting the lithium ion pore wall flux into a completely trained LSTM-Res neural network model, outputting the lithium ion concentration on the surface of the electrode particles, and calculating the electromotive force of the battery based on the lithium ion concentration on the surface of the electrode particles; inputting the lithium ion pore wall flux into a completely trained LSTM neural network model, outputting the liquid-phase lithium ion concentration of an electrode end point, and calculating the liquid-phase polarization overpotential based on the liquid-phase lithium ion concentration of the electrode end point; and predicting the battery terminal voltage according to the battery electromotive force and the liquid phase polarization overpotential. The battery voltage prediction method can realize high-precision battery voltage prediction.
Description
Technical Field
The present invention relates to the field of battery modeling technologies, and in particular, to a battery voltage prediction method, a device, an electronic apparatus, and a storage medium.
Background
In order to reduce the use of fossil fuels and reduce the carbon dioxide emission, traffic electrification is imperative. The development of electric vehicles is the key of traffic electrification, and lithium ion batteries are the most important and expensive components on electric vehicles. The battery management system detects the key state of the battery to ensure the safe operation of the battery, and maximize the performance and service life of the battery. In order to accurately observe the internal critical state of the battery, an accurate and rapid battery model is critical to the battery management system.
The equivalent circuit model is widely used in the BMS (Battery Management System ) because of its simple calculation. However, the equivalent circuit model cannot realize high-precision voltage prediction, nor describe electrochemical mechanism inside the lithium ion battery, which limits the monitoring of high-precision multi-state quantity by the BMS. In order to obtain the internal state of the lithium ion battery, a lithium ion battery model based on a physical mechanism needs to be established. The P2D (Pseudo-2D) model is an electrochemical model built according to the internal physical mechanism of the cell, and consists of four coupled partial differential equations and an algebraic equation. Four partial differential equations are used to describe the conservation of mass and charge in the solid and liquid phases of the electrode, and algebraic equations are used to describe the electrochemical reaction between the solid and liquid phases. However, solving these partial differential equations is computationally complex, resulting in the P2D model not being applicable in real-time BMS.
Therefore, how to provide a simplified electrochemical model based on a physical information neural network to realize high-precision voltage prediction and describe the electrochemical mechanism inside a lithium ion battery is a problem to be solved.
Disclosure of Invention
In view of the above, it is necessary to provide a battery voltage prediction method, apparatus, electronic device, and storage medium capable of realizing high-precision battery voltage prediction.
In order to achieve the above object, in a first aspect, the present invention provides a battery voltage prediction method, comprising:
acquiring electrochemical parameters of a battery, and calculating the lithium ion pore wall flux on the surface of electrode particles based on the electrochemical parameters;
inputting the lithium ion pore wall flux into a complete LSTM-Res neural network model, outputting the lithium ion concentration on the surface of electrode particles, and calculating the battery electromotive force based on the lithium ion concentration on the surface of the electrode particles;
inputting the lithium ion pore wall flux into a completely trained LSTM neural network model, outputting the liquid-phase lithium ion concentration of an electrode terminal point, and calculating the liquid-phase polarization overpotential based on the liquid-phase lithium ion concentration of the electrode terminal point;
predicting a cell terminal voltage based on the cell electromotive force and the liquid phase polarization overpotential.
Further, the electrochemical parameters of the battery at least comprise the following:
electrode particle radius, electrode sheet thickness, electrode sheet area, faraday constant, initial lithium ion concentration of battery, maximum lithium ion, solid phase diffusion coefficient, liquid phase diffusion coefficient, solid phase volume fraction and liquid phase volume fraction.
Further, the calculating the lithium ion pore wall flux on the surface of the electrode particle based on the electrochemical parameter comprises:
wherein ε s,i Is the solid phase volume fraction, F is Faraday constant, A is electrode area, L i For electrode thickness, I is the current applied by the cell, R s,i Is the radius of the electrode particles.
Further, the calculating the battery electromotive force based on the lithium ion concentration on the surface of the electrode particle includes:
wherein U is p (. Cndot.) is a function of the positive open-circuit potential as a function of the stoichiometric ratio of lithium ion concentration, U n (. Cndot.) is a function of the negative open circuit potential as a function of the stoichiometric ratio of lithium ion concentrations,is the lithium ion concentration of the surface of the positive electrode particle, < >>Is the maximum lithium ion concentration of the surface of the positive electrode particle,/-, for example>Is the lithium ion concentration of the surface of the negative electrode particle, +.>Is the maximum lithium ion concentration at the surface of the negative electrode particles.
Further, the calculating the liquid phase polarization overpotential based on the liquid phase lithium ion concentration of the electrode terminal point includes:
wherein,for transmitting the number, there is no dimension, R g Is the ideal gas constant, T is the temperature, c e,p C is the concentration of positive liquid-phase lithium ions at the end of the electrode near the current collector e,n Is the negative liquid-phase lithium ion concentration at the electrode tip near the current collector.
Further, the method further comprises:
an ohmic polarization potential is calculated based on the electrochemical parameter.
Further, the predicting the cell terminal voltage according to the cell electromotive force and the liquid phase polarization overpotential includes:
determining a battery terminal voltage according to the battery electromotive force, the liquid phase polarization overpotential and the ohmic polarization potential:
V cell ＝E+η e +R ohm I
wherein V is cell Is the battery terminal voltage, E is the battery electromotive force, eta e For liquid phase polarization overvoltage, R ohm Ohmic internal resistance is lumped for the battery.
In a second aspect, the present invention also provides a battery voltage prediction apparatus, including:
the parameter acquisition module is used for acquiring electrochemical parameters of the battery and calculating the lithium ion pore wall flux on the surface of the electrode particles based on the electrochemical parameters;
the first calculation module is used for inputting the lithium ion pore wall flux into a completely trained LSTM-Res neural network model, outputting the lithium ion concentration on the surface of the electrode particles, and calculating the battery electromotive force based on the lithium ion concentration on the surface of the electrode particles;
the second calculation module is used for inputting the lithium ion pore wall flux into a completely trained LSTM neural network model, outputting the liquid-phase lithium ion concentration of an electrode endpoint, and calculating the liquid-phase polarization overpotential based on the liquid-phase lithium ion concentration of the electrode endpoint;
and the prediction module is used for predicting the battery terminal voltage according to the battery electromotive force and the liquid phase polarization overpotential.
In a third aspect, the present invention also provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps in the above battery voltage prediction method when executing the computer program.
In a fourth aspect, the present invention also provides a computer storage medium storing a computer program which when executed by a processor implements the steps of the battery voltage prediction method described above.
The beneficial effects of adopting the embodiment are as follows:
according to the invention, initial electrochemical parameters are input into a simplified electrochemical model based on a physical information neural network, the lithium ion pore wall flux on the surface of electrode particles is obtained, then the lithium ion concentration on the surface of the electrode particles is obtained in an LSTM-Res network based on the lithium ion pore wall flux, the liquid-phase lithium ion concentration of an electrode endpoint is obtained in the LSTM network, namely, the LSTM-Res network is utilized to simplify the lithium ion solid-phase diffusion calculation process, the LSTM network is utilized to simplify the lithium ion liquid-phase diffusion calculation process, and finally, the battery terminal voltage is calculated according to the battery open-circuit voltage, the solid-phase diffusion overpotential, the liquid-phase diffusion overpotential and the ohmic internal resistance overpotential. The method not only can realize accurate voltage prediction, but also can output the internal state quantity of the battery, and provides more internal observation quantity of the battery for the battery management system.
Drawings
FIG. 1 is a flowchart of a method for predicting a battery voltage according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an electrochemical model simplified based on a physical information neural network according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating a battery voltage prediction apparatus according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an embodiment of an electronic device according to the present invention.
Detailed Description
Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form a part hereof, and together with the description serve to explain the principles of the invention, and are not intended to limit the scope of the invention.
In the description of the present invention, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. Furthermore, the meaning of "a plurality of" means two or more, unless specifically defined otherwise. Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The invention provides a battery voltage prediction method, a battery voltage prediction device, electronic equipment and a storage medium. In practical engineering application, the lithium ion battery electrochemical model based on a physical mechanism is difficult to apply to a battery management system due to the limitation of the operation speed of the battery management system. The voltage prediction precision of the equivalent circuit model based on experience is low, and the internal state quantity of the battery cannot be output, so that the battery management system is limited to observe the state of the battery. Therefore, the invention provides a simplified electrochemical model based on a physical information neural network, which simplifies the electrode solid-phase diffusion calculation process by utilizing an LSTM-Res network and simplifies the electrode liquid-phase diffusion calculation process by utilizing the LSTM network. The model has the advantages of high calculation speed and high prediction accuracy, and can output internal intermediate state quantities of the battery, such as positive and negative solid-phase lithium ion concentration, liquid-phase lithium ion concentration, positive and negative solid-phase lithium intercalation interval and the like. The model can be conveniently applied to an Arduino development board, the monitoring of multiple state quantities of the battery is realized, the operation safety of the battery is ensured, and the service life of the battery is prolonged.
Specific embodiments are described in detail below:
referring to fig. 1, fig. 1 is a flowchart of an embodiment of a battery voltage prediction method according to the present invention, and a battery voltage prediction method according to an embodiment of the present invention is disclosed, including:
step S101: acquiring electrochemical parameters of the battery, and calculating the lithium ion pore wall flux on the surface of the electrode particles based on the electrochemical parameters;
step S102: inputting the lithium ion pore wall flux into a completely trained LSTM-Res neural network model, outputting the lithium ion concentration on the surface of the electrode particles, and calculating the electromotive force of the battery based on the lithium ion concentration on the surface of the electrode particles;
step S103: inputting the lithium ion pore wall flux into a completely trained LSTM neural network model, outputting the liquid-phase lithium ion concentration of an electrode end point, and calculating the liquid-phase polarization overpotential based on the liquid-phase lithium ion concentration of the electrode end point;
step S104: and predicting the battery terminal voltage according to the battery electromotive force and the liquid phase polarization overpotential.
According to the invention, initial electrochemical parameters are input into a simplified electrochemical model based on a physical information neural network, the lithium ion pore wall flux on the surface of electrode particles is obtained, then the lithium ion concentration on the surface of the electrode particles is obtained in an LSTM-Res network based on the lithium ion pore wall flux, the liquid-phase lithium ion concentration of an electrode endpoint is obtained in the LSTM network, namely, the LSTM-Res network is utilized to simplify the lithium ion solid-phase diffusion calculation process, the LSTM network is utilized to simplify the lithium ion liquid-phase diffusion calculation process, and finally, the battery terminal voltage is calculated according to the battery open-circuit voltage, the solid-phase diffusion overpotential, the liquid-phase diffusion overpotential and the ohmic internal resistance overpotential. The method not only can realize accurate voltage prediction, but also can output the internal state quantity of the battery, and provides more internal observation quantity of the battery for the battery management system.
In addition, the simplified electrochemical model based on the physical information neural network provided by the invention is simple in calculation and easy to realize, and can be applied to an Arduino development board to realize rapid and accurate monitoring of the internal state of the battery. Therefore, the safe operation of the battery is ensured, the service life of the battery is prolonged, and the service performance of the battery is maximized.
In one embodiment of the invention, the electrochemical parameters of the battery include at least the following:
electrode particle radius, electrode sheet thickness, electrode sheet area, faraday constant, initial lithium ion concentration of battery, maximum lithium ion, solid phase diffusion coefficient, liquid phase diffusion coefficient, solid phase volume fraction and liquid phase volume fraction.
In one embodiment of the invention, calculating the lithium ion pore wall flux of the electrode particle surface based on electrochemical parameters comprises:
wherein ε s,i Is the solid phase volume fraction, F is Faraday constant, A is electrode area, L i For electrode thickness, I is the current applied by the cell, R s,i Is the radius of the electrode particles.
It is understood that the initial electrochemical parameters of the model include electrode particle radius, electrode sheet thickness, electrode sheet area, faraday constant, initial lithium ion concentration of the battery, maximum lithium ion, solid phase diffusion coefficient, liquid phase diffusion coefficient, solid phase volume fraction, and liquid phase volume fraction. The electrode particle surface lithium ion flux can be calculated by electrochemical parameters, wherein the electrode particle surface lithium ion flux is related to the current applied by the battery, i.e. when the battery is discharged, the current I is defined as negative (I < 0). Therefore, the lithium ion pore wall flux flowing into the electrode particles is positive, and the lithium ion pore wall flux flowing out of the electrode particles is negative.
In one embodiment of the present invention, calculating the battery electromotive force based on the lithium ion concentration of the electrode particle surface includes:
wherein U is p (. Cndot.) is a function of the positive open-circuit potential as a function of the stoichiometric ratio of lithium ion concentration, U n (. Cndot.) is a function of the negative open circuit potential as a function of the stoichiometric ratio of lithium ion concentrations,is the lithium ion concentration of the surface of the positive electrode particle, < >>Is the maximum lithium ion concentration of the surface of the positive electrode particle,/-, for example>Is the lithium ion concentration of the surface of the negative electrode particle, +.>Is the maximum lithium ion concentration at the surface of the negative electrode particles.
It should be noted that the deep learning model has been successfully applied in the fields of computer vision and natural language processing, and can completely approximate any complex nonlinear relationship. Training a conventional neural network requires input data and tag data, the network mapping the input to the output. However, the internal tag state quantity of the lithium ion battery is difficult to obtain. The internal state data of the lithium ion battery can be calculated by a physical mechanism equation in the lithium ion battery thanks to the physical information in the lithium ion battery. Partial differential equations used in electrochemical models to describe conservation of solid and liquid phase species can be solved faster and more accurately with the help of physical information neural networks. Therefore, the invention provides a simplified electrochemical model based on a physical information neural network, which can be used for improving the calculation complexity of the model and improving the calculation accuracy of the traditional battery model.
To reduce the computational complexity of the P2D model, it can be applied in real-time BMS. The invention provides an electrochemical model which can be applied to real-time BMS, and the model utilizes an LSTM-Res network to simplify the solid-phase diffusion process of electrode particles, namely, the lithium ion pore wall flux is input into a fully trained LSTM-Res neural network model, and the lithium ion concentration on the surface of the electrode particles is output. Referring to fig. 2, fig. 2 is a schematic diagram of an electrochemical model simplified based on a physical information neural network according to an embodiment of the present invention, wherein the electrochemical model includes electrode particle solid-phase diffusion and liquid-phase diffusion processes.
Specifically, the method comprises the steps of firstly obtaining the residual lithium ion concentration of a positive electrode lithium ion hole wall flux, then inputting the positive electrode lithium ion hole wall flux into an LSTM network, and superposing the positive electrode lithium ion hole wall flux and the residual lithium ion concentration of the positive electrode after full connection network and regression input to obtain the lithium ion concentration on the surface of positive electrode particles; and similarly, obtaining the residual lithium ion concentration of the negative electrode lithium ion hole wall flux, inputting the negative electrode lithium ion hole wall flux into an LSTM network, and overlapping the residual lithium ion concentration of the negative electrode after full connection network and regression input to obtain the lithium ion concentration on the surface of the negative electrode particles. And finally, calculating the electromotive force of the battery according to the lithium ion concentration on the surface of the electrode particles output by the LSTM-Res network:
wherein U is p (. Cndot.) is a function of the positive open-circuit potential as a function of the stoichiometric ratio of lithium ion concentration, U n (. Cndot.) is a function of the negative open circuit potential as a function of the stoichiometric ratio of lithium ion concentrations,is the lithium ion concentration of the surface of the positive electrode particle, < >>Is the maximum lithium ion concentration of the surface of the positive electrode particle,/-, for example>Is the lithium ion concentration of the surface of the negative electrode particle, +.>Is the maximum lithium ion concentration at the surface of the negative electrode particles.
In one embodiment of the invention, calculating the liquid phase polarization overpotential based on the liquid phase lithium ion concentration of the electrode endpoint includes:
wherein,for transmitting the number, there is no dimension, R g Is the ideal gas constant, T is the temperature, c e,p C is the concentration of positive liquid-phase lithium ions at the end of the electrode near the current collector e,n Is the negative liquid-phase lithium ion concentration at the electrode tip near the current collector.
It can be understood that the electrochemical model in the invention also utilizes the LSTM network to simplify the electrode particle liquid phase diffusion process, namely, the lithium ion pore wall flux is input into the LSTM neural network model with complete training, and the liquid phase lithium ion concentration of the electrode end point is output.
Specifically, referring to fig. 2, the pore wall fluxes of positive and negative lithium ions are respectively input into an LSTM network, and after passing through the fully connected network, the positive and negative liquid-phase lithium ion concentrations at the ends of the electrodes near the current collector are output in a regression manner. And finally, calculating the liquid phase polarization overpotential according to the liquid phase lithium ion concentration at the electrode end point output by the LSTM network:
wherein,for transmitting the number, there is no dimension, R g Is the ideal gas constant, T is the temperature, c e,p C is the concentration of positive liquid-phase lithium ions at the end of the electrode near the current collector e,n Is the negative liquid-phase lithium ion concentration at the electrode tip near the current collector.
In one embodiment of the present invention, the method further comprises:
ohmic polarization potential was calculated based on electrochemical parameters.
Predicting a cell terminal voltage from a cell electromotive force and a liquid phase polarization overpotential, comprising:
determining the cell terminal voltage according to the cell electromotive force, the liquid phase polarization overpotential and the ohmic polarization potential:
V cell ＝E+η e +R ohm I
wherein V is cell Is the battery terminal voltage, E is the battery electromotive force, eta e For liquid phase polarization overvoltage, R ohm Ohmic internal resistance is lumped for the battery.
The invention simplifies the electrode solid-phase diffusion calculation process by utilizing an LSTM-Res network, simplifies the electrode liquid-phase diffusion process by utilizing the LSTM network, and finally calculates the battery terminal voltage according to the battery open-circuit voltage, the solid-phase diffusion overpotential, the liquid-phase diffusion overpotential and the ohmic internal resistance overpotential. The built electrochemical model is simple in calculation and easy to realize, not only can the open-circuit voltage of the battery be accurately predicted, but also the internal intermediate state quantity of the battery can be predicted, including the lithium ion concentration on the surfaces of positive and negative electrode particles, the lithium ion concentration on the liquid phase of positive and negative electrode points and the lithium intercalation interval of positive and negative electrodes, and the electrochemical model can be applied to an Arduino development board, so that the monitoring of the multi-state quantity of the battery is realized, the operation safety of the battery is ensured, and the service life of the battery is prolonged.
In order to better implement the battery voltage prediction method according to the embodiment of the present invention, referring to fig. 3, fig. 3 is a schematic structural diagram of an embodiment of a battery voltage prediction device according to the present invention, and the embodiment of the present invention provides a battery voltage prediction device 300, which includes:
the parameter acquisition module 301 is configured to acquire an electrochemical parameter of the battery, and calculate a lithium ion pore wall flux on the surface of the electrode particle based on the electrochemical parameter;
the first calculation module 302 is configured to input a lithium ion pore wall flux into a well-trained LSTM-Res neural network model, output a lithium ion concentration on the surface of the electrode particle, and calculate a battery electromotive force based on the lithium ion concentration on the surface of the electrode particle;
the second calculation module 303 is configured to input the lithium ion pore wall flux into a well-trained LSTM neural network model, output a liquid-phase lithium ion concentration of an electrode endpoint, and calculate a liquid-phase polarization overpotential based on the liquid-phase lithium ion concentration of the electrode endpoint;
a prediction module 304, configured to predict a battery terminal voltage according to the battery electromotive force and the liquid phase polarization overpotential.
What needs to be explained here is: the device 300 provided in the foregoing embodiments may implement the technical solutions described in the foregoing method embodiments, and the specific implementation principles of the foregoing modules or units may be referred to the corresponding content in the foregoing method embodiments, which is not described herein again.
Based on the battery voltage prediction method, the embodiment of the invention further provides an electronic device, which comprises: a processor and a memory, and a computer program stored in the memory and executable on the processor; the steps in the battery voltage prediction method of each of the above embodiments are implemented when the processor executes the computer program.
A schematic structural diagram of an electronic device 400 suitable for use in implementing embodiments of the present invention is shown in fig. 4. The electronic device in the embodiment of the present invention may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a car-mounted terminal (e.g., car navigation terminal), etc., and a stationary terminal such as a digital TV, a desktop computer, etc. The electronic device shown in fig. 4 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments of the invention.
An electronic device includes: a memory and a processor, where the processor may be referred to as a processing device 401 hereinafter, the memory may include at least one of a Read Only Memory (ROM) 402, a Random Access Memory (RAM) 403, and a storage device 408 hereinafter, as shown in detail below:
as shown in fig. 4, the electronic device 400 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 401, which may perform various suitable actions and processes according to a program stored in a Read Only Memory (ROM) 402 or a program loaded from a storage means 408 into a Random Access Memory (RAM) 403. In the RAM403, various programs and data necessary for the operation of the electronic device 400 are also stored. The processing device 401, the ROM402, and the RAM403 are connected to each other by a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
In general, the following devices may be connected to the I/O interface 405: input devices 406 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 407 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 408 including, for example, magnetic tape, hard disk, etc.; and a communication device 409. The communication means 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. While fig. 4 shows an electronic device 400 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.
In particular, according to embodiments of the present invention, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program embodied on a non-transitory computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via communications device 409, or from storage 408, or from ROM 402. The above-described functions defined in the method of the embodiment of the present invention are performed when the computer program is executed by the processing means 401.
Based on the above battery voltage prediction method, the embodiments of the present invention further provide a computer readable storage medium storing one or more programs, where the one or more programs may be executed by one or more processors to implement the steps in the battery voltage prediction method according to the above embodiments.
Those skilled in the art will appreciate that all or part of the flow of the methods of the embodiments described above may be accomplished by way of a computer program to instruct associated hardware, where the program may be stored on a computer readable storage medium. Wherein the computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory, etc.
The present invention is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present invention are intended to be included in the scope of the present invention.
Claims (10)
1. A battery voltage prediction method, comprising:
acquiring electrochemical parameters of a battery, and calculating the lithium ion pore wall flux on the surface of electrode particles based on the electrochemical parameters;
inputting the lithium ion pore wall flux into a complete LSTM-Res neural network model, outputting the lithium ion concentration on the surface of electrode particles, and calculating the battery electromotive force based on the lithium ion concentration on the surface of the electrode particles;
inputting the lithium ion pore wall flux into a completely trained LSTM neural network model, outputting the liquid-phase lithium ion concentration of an electrode terminal point, and calculating the liquid-phase polarization overpotential based on the liquid-phase lithium ion concentration of the electrode terminal point;
predicting a cell terminal voltage based on the cell electromotive force and the liquid phase polarization overpotential.
2. The method of claim 1, wherein the electrochemical parameters of the battery include at least the following:
electrode particle radius, electrode sheet thickness, electrode sheet area, faraday constant, initial lithium ion concentration of battery, maximum lithium ion, solid phase diffusion coefficient, liquid phase diffusion coefficient, solid phase volume fraction and liquid phase volume fraction.
3. The method of claim 2, wherein calculating the lithium ion pore wall flux of the electrode particle surface based on the electrochemical parameter comprises:
wherein ε s,i Is the solid phase volume fraction, F is Faraday constant, A is electrode area, L i For electrode thickness, I is the current applied by the cell, R s,i Is the radius of the electrode particles.
4. The battery voltage prediction method according to claim 3, wherein the calculating the battery electromotive force based on the lithium ion concentration of the electrode particle surface comprises:
wherein U is p (. Cndot.) is positive open potential with lithiumFunction of ion concentration stoichiometry change, U n (. Cndot.) is a function of the negative open circuit potential as a function of the stoichiometric ratio of lithium ion concentrations,is the lithium ion concentration of the surface of the positive electrode particle, < >>Is the maximum lithium ion concentration of the surface of the positive electrode particle,/-, for example>Is the lithium ion concentration of the surface of the negative electrode particle, +.>Is the maximum lithium ion concentration at the surface of the negative electrode particles.
5. The battery voltage prediction method according to claim 3, wherein the calculating the liquid phase polarization overpotential based on the liquid phase lithium ion concentration of the electrode terminal includes:
wherein,for transmitting the number, there is no dimension, R g Is the ideal gas constant, T is the temperature, c e,p C is the concentration of positive liquid-phase lithium ions at the end of the electrode near the current collector e,n Is the negative liquid-phase lithium ion concentration at the electrode tip near the current collector.
6. The battery voltage prediction method according to claim 1, characterized in that the method further comprises:
an ohmic polarization potential is calculated based on the electrochemical parameter.
7. The battery voltage prediction method according to claim 6, wherein the predicting a battery terminal voltage from the battery electromotive force and the liquid-phase polarization overpotential comprises:
determining a battery terminal voltage according to the battery electromotive force, the liquid phase polarization overpotential and the ohmic polarization potential:
V cell ＝E+η e +R ohm I
wherein V is cell Is the battery terminal voltage, E is the battery electromotive force, eta e For liquid phase polarization overvoltage, R ohm Ohmic internal resistance is lumped for the battery.
8. A battery voltage prediction apparatus, comprising:
the parameter acquisition module is used for acquiring electrochemical parameters of the battery and calculating the lithium ion pore wall flux on the surface of the electrode particles based on the electrochemical parameters;
the first calculation module is used for inputting the lithium ion pore wall flux into a completely trained LSTM-Res neural network model, outputting the lithium ion concentration on the surface of the electrode particles, and calculating the battery electromotive force based on the lithium ion concentration on the surface of the electrode particles;
the second calculation module is used for inputting the lithium ion pore wall flux into a completely trained LSTM neural network model, outputting the liquid-phase lithium ion concentration of an electrode endpoint, and calculating the liquid-phase polarization overpotential based on the liquid-phase lithium ion concentration of the electrode endpoint;
and the prediction module is used for predicting the battery terminal voltage according to the battery electromotive force and the liquid phase polarization overpotential.
9. An electronic device comprising a memory and a processor, wherein the memory is configured to store a program; the processor, coupled to the memory, is configured to execute the program stored in the memory to implement the steps in the battery voltage prediction method according to any one of the preceding claims 1 to 7.
10. A computer readable storage medium storing a computer readable program or instructions which, when executed by a processor, is capable of carrying out the steps of the battery voltage prediction method according to any one of the preceding claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311298846.3A CN117637044A (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 |
|---|---|---|---|
| CN202311298846.3A CN117637044A (en) | 2023-10-07 | 2023-10-07 | Battery voltage prediction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117637044A true CN117637044A (en) | 2024-03-01 |
Family
ID=90022394
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311298846.3A Pending CN117637044A (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) | CN117637044A (en) |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104899439A (en) * | 2015-06-02 | 2015-09-09 | 吉林大学 | Mechanism modeling method for lithium ion battery |
| CN105891724A (en) * | 2016-05-05 | 2016-08-24 | 南京航空航天大学 | On-line estimation method for state of charge of lithium ion battery based on extended single particle model |
| US20180143259A1 (en) * | 2016-11-22 | 2018-05-24 | Samsung Electronics Co., Ltd. | Method and apparatus for estimating state of battery |
| US20200355750A1 (en) * | 2019-05-08 | 2020-11-12 | Tata Consultancy Services Limited | Method and system for remaining useful life prediction of lithium based batteries |
| CN112083346A (en) * | 2020-08-03 | 2020-12-15 | 山东大学 | LSTM-based parallel battery pack internal current distribution estimation method and system |
| US20210132151A1 (en) * | 2019-10-07 | 2021-05-06 | Samsung Sdi Co., Ltd. | Method and apparatus for estimating state of health of battery |
| CN113779794A (en) * | 2021-09-13 | 2021-12-10 | 山东大学 | Lithium ion battery SOP estimation method and system considering microcosmic constraint |
| US20220065934A1 (en) * | 2020-09-01 | 2022-03-03 | Samsung Electronics Co., Ltd. | Method and apparatus with battery state estimation |
| WO2022101769A1 (en) * | 2020-11-13 | 2022-05-19 | Kpit Technologies Limited | A hybrid system and method for estimating state of charge of a battery |
| CN114547903A (en) * | 2022-02-28 | 2022-05-27 | 骆驼集团武汉光谷研发中心有限公司 | Method for predicting cycle life of lithium battery based on electrochemical-thermal coupling model |
| US20220223848A1 (en) * | 2021-01-11 | 2022-07-14 | Posi Energy-Silicon Power, Llc | Lithium-ion battery with thin crystalline anode and methods of making same |
| CN114942392A (en) * | 2022-04-14 | 2022-08-26 | 中国长江三峡集团有限公司 | Electrochemical aging mechanism and data-driven SOH estimation method for energy storage lithium battery |
| CN115632179A (en) * | 2022-12-20 | 2023-01-20 | 国网天津市电力公司电力科学研究院 | Intelligent quick charging method and system for lithium ion battery |
| CN115712987A (en) * | 2022-10-27 | 2023-02-24 | 天津大学 | Solving method of lithium ion transmission model of lithium battery composite electrode based on neural network |
| CN115825746A (en) * | 2022-09-19 | 2023-03-21 | 阿里巴巴（中国）有限公司 | Estimation method and device for battery state of lithium battery |
| CN116184214A (en) * | 2023-02-20 | 2023-05-30 | 同济大学 | Online rapid prediction method and device for service life of power battery for vehicle and storage medium |
| CN116381510A (en) * | 2023-05-08 | 2023-07-04 | 合肥工业大学 | Method, system and storage medium for predicting residual life of lithium battery |
-
2023
- 2023-10-07 CN CN202311298846.3A patent/CN117637044A/en active Pending
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104899439A (en) * | 2015-06-02 | 2015-09-09 | 吉林大学 | Mechanism modeling method for lithium ion battery |
| CN105891724A (en) * | 2016-05-05 | 2016-08-24 | 南京航空航天大学 | On-line estimation method for state of charge of lithium ion battery based on extended single particle model |
| US20180143259A1 (en) * | 2016-11-22 | 2018-05-24 | Samsung Electronics Co., Ltd. | Method and apparatus for estimating state of battery |
| US20200355750A1 (en) * | 2019-05-08 | 2020-11-12 | Tata Consultancy Services Limited | Method and system for remaining useful life prediction of lithium based batteries |
| US20210132151A1 (en) * | 2019-10-07 | 2021-05-06 | Samsung Sdi Co., Ltd. | Method and apparatus for estimating state of health of battery |
| CN112083346A (en) * | 2020-08-03 | 2020-12-15 | 山东大学 | LSTM-based parallel battery pack internal current distribution estimation method and system |
| US20220065934A1 (en) * | 2020-09-01 | 2022-03-03 | Samsung Electronics Co., Ltd. | Method and apparatus with battery state estimation |
| WO2022101769A1 (en) * | 2020-11-13 | 2022-05-19 | Kpit Technologies Limited | A hybrid system and method for estimating state of charge of a battery |
| US20220223848A1 (en) * | 2021-01-11 | 2022-07-14 | Posi Energy-Silicon Power, Llc | Lithium-ion battery with thin crystalline anode and methods of making same |
| CN113779794A (en) * | 2021-09-13 | 2021-12-10 | 山东大学 | Lithium ion battery SOP estimation method and system considering microcosmic constraint |
| CN114547903A (en) * | 2022-02-28 | 2022-05-27 | 骆驼集团武汉光谷研发中心有限公司 | Method for predicting cycle life of lithium battery based on electrochemical-thermal coupling model |
| CN114942392A (en) * | 2022-04-14 | 2022-08-26 | 中国长江三峡集团有限公司 | Electrochemical aging mechanism and data-driven SOH estimation method for energy storage lithium battery |
| CN115825746A (en) * | 2022-09-19 | 2023-03-21 | 阿里巴巴（中国）有限公司 | Estimation method and device for battery state of lithium battery |
| CN115712987A (en) * | 2022-10-27 | 2023-02-24 | 天津大学 | Solving method of lithium ion transmission model of lithium battery composite electrode based on neural network |
| CN115632179A (en) * | 2022-12-20 | 2023-01-20 | 国网天津市电力公司电力科学研究院 | Intelligent quick charging method and system for lithium ion battery |
| CN116184214A (en) * | 2023-02-20 | 2023-05-30 | 同济大学 | Online rapid prediction method and device for service life of power battery for vehicle and storage medium |
| CN116381510A (en) * | 2023-05-08 | 2023-07-04 | 合肥工业大学 | Method, system and storage medium for predicting residual life of lithium battery |
Non-Patent Citations (5)
| Title |
|---|
| JIXIANG LI: "Predicting the State of Health of Lithium Battery Based on Improved LSTM-RNN", 2023 INTERNATIONAL SYMPOSIUM ON INTELLIGENT ROBOTICS AND SYSTEMS (ISOIRS), 31 August 2023 (2023-08-31) * |
| 崔鹰飞;陈则王;: "基于单粒子模型的锂离子电池荷电状态估计", 机械制造与自动化, no. 04, 10 August 2018 (2018-08-10) * |
| 明彤彤;王凯;田冬冬;徐松;田浩含;: "基于LSTM神经网络的锂离子电池荷电状态估算", 广东电力, no. 03, 25 March 2020 (2020-03-25) * |
| 李文启;高东学;李朝晖;饶宇飞;顾波;: "基于LSTM-NPKDE的锂离子电池SOC预测与不确定分析", 电器与能效管理技术, no. 05, 30 May 2020 (2020-05-30) * |
| 韩雪冰: "车用锂离子电池机理模型与状态估计研究", CNKI优秀博士学位论文全文库, 15 May 2016 (2016-05-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xiong et al. | An electrochemical model based degradation state identification method of Lithium-ion battery for all-climate electric vehicles application | |
| KR102233614B1 (en) | Auxiliary battery management system | |
| JP6738433B2 (en) | Battery management system with multiple observers | |
| Lyu et al. | A lead-acid battery's remaining useful life prediction by using electrochemical model in the Particle Filtering framework | |
| KR102233608B1 (en) | Auxiliary battery management system | |
| Leng et al. | A practical framework of electrical based online state-of-charge estimation of lithium ion batteries | |
| US8878549B2 (en) | AC impedance measuring device | |
| US10686321B2 (en) | Secondary battery management | |
| CN113702845B (en) | Retired lithium battery core parameter evaluation method and equipment | |
| CN112949101B (en) | Method, device, equipment and medium for acquiring pulse charging and discharging maximum current of battery | |
| CN109946622B (en) | Lithium deposition prediction method and device for lithium ion battery | |
| Wang et al. | State-of-art survey of fractional order modeling and estimation methods for lithium-ion batteries | |
| Shi et al. | Physics-based fractional-order model and parameters identification of liquid metal battery | |
| Selvabharathi et al. | Experimental analysis on battery based health monitoring system for electric vehicle | |
| Wu et al. | A collaborative estimation scheme for lithium-ion battery state of charge and state of health based on electrochemical model | |
| Guo et al. | Nonlinear state-variable method for solving physics-based li-ion cell model with high-frequency inputs | |
| Schmitt et al. | State-of-health estimation by virtual experiments using recurrent decoder–encoder based lithium-ion digital battery twins trained on unstructured battery data | |
| CN117637044A (en) | Battery voltage prediction method and device, electronic equipment and storage medium | |
| WO2023169134A1 (en) | Battery soh value calculation model generation method, battery soh value calculation method, apparatus, and system | |
| Gu et al. | A Polak-Ribiere-Polyak conjugate gradient algorithm optimized broad learning system for lithium-ion battery state of health estimation | |
| CN116564425A (en) | Modeling method for digital twin model of lithium ion battery | |
| Moura et al. | Better batteries through electrochemistry | |
| US11710859B2 (en) | Techniques for controlling charging and/or discharging of batteries using a tanks-in-series model | |
| Zhao et al. | Online state of health estimation with deep learning frameworks based on short and random battery charging data segments | |
| CN114355222A (en) | Battery state of health estimation method and device based on voltage curve and readable medium |
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 |