Energy optimization method and device for light storage type electric vehicle charging station

Abstract

The invention relates to a light storage type electric vehicle charging station energy optimization method and device. The method comprises the following steps: acquiring a real-time charging characteristic parameter, a real-time physical change parameter, a voltage difference physical prediction model and a voltage difference intelligent prediction model of an automobile storage battery; substituting the real-time charging characteristic parameters and the real-time physical change parameters into a voltage difference physical prediction model to obtain voltage difference physical prediction data; inputting the real-time charging characteristic parameters and the real-time physical change parameters into a voltage difference intelligent prediction model to obtain voltage difference intelligent prediction data; according to the voltage difference physical prediction data and the voltage difference intelligent prediction data, predicting the charging state to obtain a storage battery voltage difference prediction curve; and determining a storage battery charging control mode according to a position mapping relation between the storage battery voltage difference prediction curve and each storage battery charging control quadrant. By adopting the method, the safety of the storage battery in the charging process can be effectively improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent charging control technology, and in particular to an energy optimization method and device for a photovoltaic electric vehicle charging station. Background Art

[0002] With the development of computer technology, intelligent control technology for automobile battery charging has emerged. This technology monitors the status of the battery (such as voltage, current, temperature, etc.) in real time through integrated sensors and algorithms, and dynamically adjusts the charging parameters based on these data to achieve the goals of high efficiency, safety and extended battery life. This technology can prevent overcharging and overheating, improve charging efficiency, and adapt to the characteristics of different types of batteries, thereby ensuring that the battery can maintain optimal performance in various usage environments.

[0003] Traditional intelligent control technology for automobile battery charging mainly realizes charging control through fixed charging curves and preset parameters, which are usually based on a preliminary evaluation of battery type and usage conditions. Although they can provide a certain degree of charging optimization to provide charging protection and charging efficiency, traditional methods lack the ability of real-time monitoring and dynamic adjustment during application, and cannot respond to changes in battery status in a timely manner, which can easily lead to overcharging, overheating or undercharging of automobile batteries, resulting in insufficient safety during automobile battery charging. Summary of the invention

[0004] Based on this, it is necessary to provide an energy optimization method, device, computer equipment, computer-readable storage medium and computer program product for a photovoltaic electric vehicle charging station that can effectively improve the safety of the battery charging process in response to the above technical problems.

[0005] In a first aspect, the present application provides an energy optimization method for a photovoltaic storage electric vehicle charging station, comprising:

[0006] Obtaining real-time charging characteristic parameters, real-time physical change parameters, voltage difference physical prediction model and voltage difference intelligent prediction model of the automobile battery;

[0007] Substituting the real-time charging characteristic parameter and the real-time physical change parameter into the voltage difference physical prediction model for solving, to obtain voltage difference physical prediction data;

[0008] Inputting the real-time charging characteristic parameter and the real-time physical change parameter into the voltage difference intelligent prediction model to obtain voltage difference intelligent prediction data;

[0009] Predicting the charging state of the vehicle battery according to the voltage difference physical prediction data and the voltage difference intelligent prediction data to obtain a battery voltage difference prediction curve;

[0010] The battery charging control mode of the vehicle battery is determined according to the position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant; the battery charging control mode is used to optimize the power transmission between the photovoltaic electric vehicle charging station and the vehicle battery; the battery charging control quadrant is the operating conditions corresponding to different battery charging control modes in the battery charging control model of the vehicle battery.

[0011] In a second aspect, the present application also provides an energy optimization device for a photovoltaic electric vehicle charging station, comprising:

[0012] A battery data acquisition module is used to obtain real-time charging characteristic parameters, real-time physical change parameters, voltage difference physical prediction model and voltage difference intelligent prediction model of the automobile battery;

[0013] A voltage difference prediction module, used for substituting the real-time charging characteristic parameter and the real-time physical change parameter into the voltage difference physical prediction model for solving, so as to obtain voltage difference physical prediction data;

[0014] The voltage difference prediction module is further used to input the real-time charging characteristic parameter and the real-time physical change parameter into the voltage difference intelligent prediction model to obtain voltage difference intelligent prediction data;

[0015] The voltage difference prediction module is further used to predict the charging state of the vehicle battery according to the voltage difference physical prediction data and the voltage difference intelligent prediction data, so as to obtain a battery voltage difference prediction curve;

[0016] A battery charging control module is used to determine the battery charging control mode of the vehicle battery according to the position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant; the battery charging control mode is used to optimize the power transmission between the photovoltaic electric vehicle charging station and the vehicle battery; the battery charging control quadrant is the operating conditions corresponding to different battery charging control modes in the battery charging control model of the vehicle battery.

[0017] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0018] Obtaining real-time charging characteristic parameters, real-time physical change parameters, voltage difference physical prediction model and voltage difference intelligent prediction model of the automobile battery;

[0019] Substituting the real-time charging characteristic parameter and the real-time physical change parameter into the voltage difference physical prediction model for solving, to obtain voltage difference physical prediction data;

[0020] Inputting the real-time charging characteristic parameter and the real-time physical change parameter into the voltage difference intelligent prediction model to obtain voltage difference intelligent prediction data;

[0021] Predicting the charging state of the vehicle battery according to the voltage difference physical prediction data and the voltage difference intelligent prediction data to obtain a battery voltage difference prediction curve;

[0022] The battery charging control mode of the vehicle battery is determined according to the position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant; the battery charging control mode is used to optimize the power transmission between the photovoltaic electric vehicle charging station and the vehicle battery; the battery charging control quadrant is the operating conditions corresponding to different battery charging control modes in the battery charging control model of the vehicle battery.

[0023] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0024] Obtaining real-time charging characteristic parameters, real-time physical change parameters, voltage difference physical prediction model and voltage difference intelligent prediction model of the automobile battery;

[0025] Substituting the real-time charging characteristic parameter and the real-time physical change parameter into the voltage difference physical prediction model for solving, to obtain voltage difference physical prediction data;

[0026] Inputting the real-time charging characteristic parameter and the real-time physical change parameter into the voltage difference intelligent prediction model to obtain voltage difference intelligent prediction data;

[0027] Predicting the charging state of the vehicle battery according to the voltage difference physical prediction data and the voltage difference intelligent prediction data to obtain a battery voltage difference prediction curve;

[0028] The battery charging control mode of the vehicle battery is determined according to the position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant; the battery charging control mode is used to optimize the power transmission between the photovoltaic electric vehicle charging station and the vehicle battery; the battery charging control quadrant is the operating conditions corresponding to different battery charging control modes in the battery charging control model of the vehicle battery.

[0029] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0030] Obtaining real-time charging characteristic parameters, real-time physical change parameters, voltage difference physical prediction model and voltage difference intelligent prediction model of the automobile battery;

[0031] Substituting the real-time charging characteristic parameter and the real-time physical change parameter into the voltage difference physical prediction model for solving, to obtain voltage difference physical prediction data;

[0032] Inputting the real-time charging characteristic parameter and the real-time physical change parameter into the voltage difference intelligent prediction model to obtain voltage difference intelligent prediction data;

[0033] Predicting the charging state of the vehicle battery according to the voltage difference physical prediction data and the voltage difference intelligent prediction data to obtain a battery voltage difference prediction curve;

[0034] The battery charging control mode of the vehicle battery is determined according to the position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant; the battery charging control mode is used to optimize the power transmission between the photovoltaic electric vehicle charging station and the vehicle battery; the battery charging control quadrant is the operating conditions corresponding to different battery charging control modes in the battery charging control model of the vehicle battery.

[0035] The above-mentioned method, device, computer equipment, storage medium and computer program product for energy optimization of a photovoltaic electric vehicle charging station obtain the real-time charging characteristic parameters, real-time physical change parameters, voltage difference physical prediction model and voltage difference intelligent prediction model of the vehicle battery; substitute the real-time charging characteristic parameters and real-time physical change parameters into the voltage difference physical prediction model for solution to obtain voltage difference physical prediction data; input the real-time charging characteristic parameters and real-time physical change parameters into the voltage difference intelligent prediction model to obtain voltage difference intelligent prediction data; predict the charging state of the vehicle battery according to the voltage difference physical prediction data and the voltage difference intelligent prediction data to obtain a battery voltage difference prediction curve; determine the battery charging control mode of the vehicle battery according to the position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant; the battery charging control mode is used to optimize the power transmission between the photovoltaic electric vehicle charging station and the vehicle battery; the battery charging control quadrant is the operating conditions corresponding to different battery charging control modes in the battery charging control model of the vehicle battery.

[0036] By acquiring the charging characteristic parameters and physical change parameters of the car battery in real time and substituting them into the voltage difference physical prediction model and intelligent prediction model for solution, the physical prediction data and intelligent prediction data of the voltage difference can be accurately obtained. This dual prediction method combines the advantages of physical and intelligent algorithms to generate an accurate prediction curve for the voltage difference of the car battery. Based on the position mapping relationship between the prediction curve and each charging control quadrant, the optimal charging control mode of the car battery is dynamically determined, and the charging strategy of the photovoltaic electric vehicle charging station can be accurately adjusted to ensure that the car battery can be charged efficiently and safely under different conditions, thereby effectively improving the safety of the car battery during charging, and significantly extending the life of the car battery, improving the charging efficiency, and improving the reliability and stability of the overall energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 An application environment diagram of an energy optimization method for a photovoltaic storage type electric vehicle charging station in one embodiment;

[0039] Figure 2 A schematic flow chart of an energy optimization method for a photovoltaic storage electric vehicle charging station in one embodiment;

[0040] Figure 3 A schematic diagram of a flow chart of a method for obtaining voltage difference physical prediction data in one embodiment;

[0041] Figure 4 A schematic flow chart of a method for obtaining a battery voltage difference prediction curve in one embodiment;

[0042] Figure 5 A schematic flow chart of a method for determining a battery charging control mode in one embodiment;

[0043] Figure 6 A schematic flow chart of a method for determining a battery charging control mode in another embodiment;

[0044] Figure 7 It is a structural block diagram of an energy optimization device for a photovoltaic storage type electric vehicle charging station in one embodiment;

[0045] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] The energy optimization method of a photovoltaic storage electric vehicle charging station provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The server 104 obtains the real-time charging characteristic parameters, real-time physical change parameters, voltage difference physical prediction model and voltage difference intelligent prediction model of the automobile battery through the terminal 102; substitutes the real-time charging characteristic parameters and real-time physical change parameters into the voltage difference physical prediction model for solution to obtain voltage difference physical prediction data; inputs the real-time charging characteristic parameters and real-time physical change parameters into the voltage difference intelligent prediction model to obtain voltage difference intelligent prediction data; predicts the charging state of the automobile battery according to the voltage difference physical prediction data and the voltage difference intelligent prediction data to obtain a battery voltage difference prediction curve; determines the battery charging control mode of the automobile battery according to the position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant; the battery charging control mode is used to optimize the power transmission between the photovoltaic electric vehicle charging station and the automobile battery; the battery charging control quadrant is the operating conditions corresponding to different battery charging control modes in the battery charging control model of the automobile battery. The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0048] In an exemplary embodiment, Figure 2 As shown, a method for optimizing the energy of a photovoltaic electric vehicle charging station is provided. Figure 1 The server in the example is used to illustrate, including the following steps 202 to 210. Among them:

[0049] Step 202, obtaining real-time charging characteristic parameters, real-time physical change parameters, voltage difference physical prediction model and voltage difference intelligent prediction model of the automobile battery.

[0050] Among them, the real-time charging characteristic parameters can be key electrical parameters that change continuously during the battery charging process, including voltage (Voltage), current (Current), state parameter (State of Charge, SOC), battery capacity (Capacity), charge rate (Charge Rate), discharge rate (Discharge Rate), internal resistance (Internal Resistance), battery health state (State of Health, SOH), battery temperature (Battery Temperature), battery conductivity (Battery Conductance), etc.

[0051] Among them, the real-time physical change parameters can be physical properties that change continuously during the battery charging and discharging process, including temperature (Temperature), electrolyte concentration (Electrolyte Concentration), mechanical stress (MechanicalStress), battery swelling (Battery Swelling), electrode potential (Electrode Potential), heat generation (HeatGeneration), pressure (Pressure), gas generation inside the battery (Gas Generation), ion transport number (IonTransport Number), electrode thickness variation (Electrode Thickness Variation), etc.

[0052] Among them, the voltage difference physical prediction model can be a mathematical model constructed based on the principles of electrochemistry, thermodynamics and mechanics. By obtaining the charging characteristic parameters and physical change parameters of the battery in real time, complex equations (such as the Nernst equation, heat conduction equation and mechanical stress equation) are used to calculate and predict the changes in the voltage difference of the battery in the future.

[0053] Among them, the voltage difference intelligent prediction model can be a model built using machine learning and deep learning algorithms. By inputting real-time charging characteristic parameters and physical change parameters, time series prediction technology (such as LSTM, Transformer, etc.) is used to analyze and learn the complex relationships in the data, thereby predicting the changes in the voltage difference of the battery in the future.

[0054] Specifically, a high-precision sensor network is deployed to obtain real-time charging characteristic parameters (such as voltage, current, SOC) and real-time physical change parameters (such as temperature, electrolyte concentration, mechanical stress) of the automobile battery, and a data transmission system is established to transmit the collected real-time data to the data processing center; at the same time, the voltage difference physical prediction model and the voltage difference intelligent prediction model are retrieved from the storage medium of the server 104 to the data processing center, wherein the voltage difference physical prediction model is constructed on the physical model through historical charging characteristic parameters and historical physical change parameters, and the voltage difference intelligent prediction model is an artificial intelligence model trained through historical charging characteristic parameters and historical physical change parameters.

[0055] Step 204 , substituting the real-time charging characteristic parameters and the real-time physical change parameters into the voltage difference physical prediction model for solving, and obtaining voltage difference physical prediction data.

[0056] Among them, the voltage difference physical prediction data can be the result calculated based on the voltage difference physical prediction model. It inputs the charging characteristic parameters and physical change parameters of the battery in real time, applies relevant equations such as electrochemistry, thermodynamics and mechanics, and predicts the changes in the voltage difference that may occur in the battery in the future.

[0057] Specifically, the real-time charging characteristic parameters (such as voltage, current, SOC) and real-time physical change parameters (such as temperature, electrolyte concentration, mechanical stress) are input into the voltage difference physical prediction model. The voltage difference physical prediction model is based on mathematical and physical models such as the electrochemical reaction kinetics equation, the heat conduction equation, and the mechanical stress equation, and comprehensively calculates the change in the voltage difference of the battery in a specific time period in the future, thereby obtaining detailed voltage difference physical prediction data.

[0058] Among them, the voltage difference physical prediction model includes the battery electrochemical behavior prediction model, the battery electrochemical process prediction model and the battery multi-scale and multi-field prediction model; the voltage difference physical prediction data includes the battery electrochemical process prediction data, the battery electrochemical behavior prediction data and the battery multi-scale and multi-field prediction data.

[0059] The expression of the battery electrochemical process prediction model is:

[0060]

[0061] Among them, the real-time charging characteristic parameters include standard electromotive force, overpotential, current, internal resistance, electrode resistance; the real-time physical change parameters include gas constant, temperature, ion concentration in electrolyte, ion concentration in solid phase; ΔV P2D (t) is the battery electrochemical process prediction data, E 0is the standard electromotive force, R is the gas constant, T is the temperature, F is the Faraday constant, c e (t) is the ion concentration in the electrolyte, c s (t) is the ion concentration in the solid phase, η(t) is the overpotential, I(t) is the current, R int (t) is the internal resistance, R elec (t) is the electrode resistance. Among them, standard electromotive force refers to the electromotive force generated by the battery under standard conditions, which is obtained through experiments or from the material property database; the gas constant represents the constant in the equation of state of matter, and its value is 8.314 J / (mol·K); the temperature represents the temperature in the battery operating environment, in Kelvin (K), measured by a temperature sensor; the Faraday constant represents the charge per mole of electrons, and its value is 96485 C / mol; the ion concentration in the electrolyte represents the concentration of ions in the electrolyte inside the battery, which is measured by using ion concentration measurement technology (such as electrochemical analysis or ion migration number test) after detecting real-time charging characteristic parameters and real-time physical change parameters; the ion concentration in the solid phase represents the ion concentration in the solid electrode phase of the battery, which is measured by detecting real-time The data are measured by ion concentration measurement technology (such as electrochemical analysis or ion migration number test) after the charging characteristic parameters and real-time physical change parameters are measured; overpotential refers to the part of the battery electrode that exceeds the thermodynamic equilibrium potential during the electrochemical reaction. The type of battery is determined by the real-time charging characteristic parameters and real-time physical change parameters, and then the data calculated in the laboratory by experimental electrochemical technology (such as current-voltage curve or potential-current relationship) is retrieved from the server; current refers to the current passing through the battery during operation, which is calculated after detecting the real-time charging characteristic parameters and real-time physical change parameters; internal resistance refers to the impedance inside the battery, and the electrode resistance refers to the impedance of the battery electrode, which is calculated after detecting the real-time charging characteristic parameters and real-time physical change parameters.

[0062] The expression of the battery electrochemical behavior prediction model is:

[0063]

[0064] Among them, the real-time charging characteristic parameters include standard electromotive force, overpotential, current, internal resistance, electrode resistance; the real-time physical change parameters include gas constant, temperature, Faraday constant, ion concentration in electrolyte, ion concentration in solid phase, electrochemical transfer coefficient, exchange current density, and effective surface area of ​​battery; ΔV DFN (t) is the battery electrochemical behavior prediction data, E 0 is the standard electromotive force, R is the gas constant, T is the temperature, F is the Faraday constant, c e (t) is the ion concentration in the electrolyte, c s(t) is the ion concentration in the solid phase, I(t) is the current, R int (t) is the internal resistance, α is the electrochemical transfer coefficient, j0 is the exchange current density, and A(t) is the effective surface area of ​​the battery. The definitions and methods of obtaining the various parameters of the expression of the battery electrochemical behavior prediction model are the same as those of the battery electrochemical process prediction model, so the definitions and methods of obtaining these parameters in the expression of the battery electrochemical process prediction model can be referred to.

[0065] The electrochemical transfer coefficient represents the relationship between the reaction rate and the overpotential. The type of battery is determined by the real-time charging characteristic parameters and the real-time physical change parameters, and then the data obtained by electrochemical experiments and fitting in the laboratory are retrieved from the server; the exchange current density represents the equilibrium current density of the electrochemical reaction. After detecting the real-time charging characteristic parameters and the real-time physical change parameters, the electrochemical testing technology is used, especially the data obtained by the relationship between the electrode reaction rate and the current density; the effective surface area of ​​the battery is calculated by detecting the real-time charging characteristic parameters and the real-time physical change parameters.

[0066] The expression of the battery multi-scale and multi-domain prediction model is:

[0067]

[0068] Among them, the real-time charging characteristic parameters include standard electromotive force, overpotential, current, internal resistance, electrode resistance; the real-time physical change parameters include gas constant, temperature, Faraday constant, ion concentration in electrolyte, ion concentration in solid phase, electrochemical transfer coefficient, exchange current density, effective surface area of ​​battery, mechanical stress, heat generation phase; ΔV MSMD (t) is the multi-scale and multi-field prediction data of the battery, E 0 is the standard electromotive force, R is the gas constant, T is the temperature, F is the Faraday constant, c e (t) is the ion concentration in the electrolyte, c s (t) is the ion concentration in the solid phase, I(t) is the current, R int (t) is the internal resistance, R elec (t) is the electrode resistance, σ(t) is the mechanical stress, Q gen(t) is the heat generation phase, which is composed of Joule heat and reaction heat, and A(t) is the effective surface area of ​​the battery. The definitions and methods of obtaining the various parameters of the expression of the battery electrochemical behavior prediction model are as follows: standard electromotive force, gas constant, temperature, Faraday constant, ion concentration in the electrolyte, ion concentration in the solid phase, current, internal resistance and electrode resistance are the same as those of the battery electrochemical process prediction model, so the definitions and methods of obtaining these parameters in the expression of the battery electrochemical process prediction model can be referred to.

[0069] Mechanical stress refers to the stress generated by mechanical changes such as expansion and contraction of the battery during operation, which is extracted by detecting real-time charging characteristic parameters and real-time physical change parameters; heat generation phase refers to the heat generated during the operation of the battery, which mainly includes Joule heat and reaction heat, and is extracted by detecting real-time charging characteristic parameters and real-time physical change parameters; the definition and acquisition method of the effective surface area of ​​the battery are the same as the effective surface area of ​​the battery in the expression of the battery electrochemical behavior prediction model.

[0070] Step 206 , input the real-time charging characteristic parameters and the real-time physical change parameters into the voltage difference intelligent prediction model to obtain voltage difference intelligent prediction data.

[0071] The voltage difference intelligent prediction data may be the change of the voltage difference of the battery in a future period of time calculated by the voltage difference intelligent prediction model.

[0072] Specifically, real-time charging characteristic parameters (such as voltage, current, SOC) and real-time physical change parameters (such as temperature, electrolyte concentration, mechanical stress) are input into the voltage difference intelligent prediction model. The voltage difference intelligent prediction model uses deep learning algorithms (such as LSTM, Transformer, GNN) to perform time series analysis and pattern recognition on the input data to predict the changes in the voltage difference of the battery in the future, thereby obtaining detailed voltage difference intelligent prediction data.

[0073] The voltage difference intelligent prediction data includes voltage long and short-term memory prediction data, voltage attention mechanism prediction data and voltage graph neural network prediction data; the voltage difference intelligent prediction model includes voltage long and short-term memory prediction model, voltage attention mechanism prediction model and voltage graph neural network prediction model.

[0074] The voltage long short-term memory prediction model is:

[0075] ΔV LSTM (t+1), ΔV LSTM (t+2), ... = LSTM(X t )

[0076] The voltage attention mechanism prediction model is:

[0077] ΔV Transformer (t+1), ΔV Transformer (t+2), ... = Transformer (X t )

[0078] The voltage graph neural network prediction model is:

[0079] ΔV GNN (t+1), ΔV GNN (t+2), ... = GNN(X t )

[0080] Among them, LSTM(X t ) is the voltage long short-term memory prediction data, Transformer (X t ) is the voltage attention mechanism prediction data, GNN(X t ) is the voltage graph neural network prediction data; ΔV LSTM (t+x) is the prediction data of the voltage long-short term memory prediction model at any time, ΔV Transformer (t+x) is the predicted data of the voltage attention mechanism prediction model at any time, ΔV GNN (t+x) is the prediction data of the voltage graph neural network prediction model at any time. The above ΔV LSTM (t+x), ΔV Transformer (t+x) and ΔV GNN (t+x) x The value range is from 1 to N.

[0081] Step 208 , predicting the charging state of the vehicle battery according to the voltage difference physical prediction data and the voltage difference intelligent prediction data, and obtaining a battery voltage difference prediction curve.

[0082] Among them, the battery voltage difference prediction curve can be a curve generated based on the real-time acquired battery data through the prediction results of the physical model and the intelligent model, showing the trend of the change of the battery voltage difference in the future period of time.

[0083] Specifically, the battery electrochemical process prediction data, battery electrochemical behavior prediction data, battery multi-scale and multi-domain prediction data in the voltage difference physical prediction data, and the voltage long and short-term memory prediction data, voltage attention mechanism prediction data and voltage graph neural network prediction data in the voltage difference intelligent prediction data are input into the fusion algorithm, and the prediction accuracy and correlation dynamic adjustment weights of the battery electrochemical behavior prediction model, battery electrochemical process prediction model and battery multi-scale and multi-domain prediction model in the voltage difference physical prediction model, and the voltage long and short-term memory prediction model, voltage attention mechanism prediction model and voltage graph neural network prediction model in the voltage difference intelligent prediction model are adjusted by using weighted averaging, Bayesian optimization and other techniques. Then, the precise calculation results of the physical model and the pattern recognition results of the intelligent model are comprehensively processed and optimized, and the optimized data is combined with interpolation processing to obtain the battery voltage difference prediction curve.

[0084] Step 210 , determining a battery charging control mode of the vehicle battery according to a mapping relationship between the battery voltage difference prediction curve and the positions of each battery charging control quadrant.

[0085] The battery charging control quadrant may be an operating condition corresponding to different battery charging control modes in a battery charging control model of a vehicle battery.

[0086] The battery charging control mode may be a mode in which the battery charging control model is used to control the charging of the battery.

[0087] Specifically, the battery voltage difference prediction curve is positionally mapped with the predefined battery charging control quadrant (such as active balancing, passive balancing, active non-balancing, passive non-balancing) to obtain a position mapping relationship, and the position mapping relationship between the two is used to determine the quadrant where the battery voltage difference prediction curve is located at different time points, or the quadrant where each section of the prediction curve is located, and then the most suitable charging control preset mode is determined according to the corresponding quadrant. If the battery voltage difference prediction curve passes through at least two quadrants, according to the change of the battery voltage difference prediction curve near the coordinate axis between different quadrants, a multi-mode sequential control mode or / and a multi-mode parallel control mode are selected to form a battery charging control mode in combination with a charging control preset mode. Further, the battery charging control mode is used to generate a control instruction for power transmission, and the server 104 in the solar storage electric vehicle charging station transmits power from the solar storage electric vehicle charging station to the vehicle battery according to the battery charging control mode by controlling the power-exclusive terminal in the solar storage electric vehicle charging station.

[0088] In the above-mentioned energy optimization method for a photovoltaic electric vehicle charging station, the real-time charging characteristic parameters, real-time physical change parameters, voltage difference physical prediction model and voltage difference intelligent prediction model of the vehicle battery are obtained; the real-time charging characteristic parameters and real-time physical change parameters are substituted into the voltage difference physical prediction model for solution to obtain voltage difference physical prediction data; the real-time charging characteristic parameters and real-time physical change parameters are input into the voltage difference intelligent prediction model to obtain voltage difference intelligent prediction data; according to the voltage difference physical prediction data and the voltage difference intelligent prediction data, the charging state of the vehicle battery is predicted to obtain a battery voltage difference prediction curve; according to the position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant, the battery charging control mode of the vehicle battery is determined; the battery charging control mode is used to optimize the power transmission between the photovoltaic electric vehicle charging station and the vehicle battery; the battery charging control quadrant is the operating conditions corresponding to different battery charging control modes in the battery charging control model of the vehicle battery.

[0089] By acquiring the charging characteristic parameters and physical change parameters of the car battery in real time and substituting them into the voltage difference physical prediction model and intelligent prediction model for solution, the physical prediction data and intelligent prediction data of the voltage difference can be accurately obtained. This dual prediction method combines the advantages of physical and intelligent algorithms to generate an accurate prediction curve for the voltage difference of the car battery. Based on the position mapping relationship between the prediction curve and each charging control quadrant, the optimal charging control mode of the car battery is dynamically determined, and the charging strategy of the photovoltaic electric vehicle charging station can be accurately adjusted to ensure that the car battery can be charged efficiently and safely under different conditions, thereby effectively improving the safety of the car battery during charging, and significantly extending the life of the car battery, improving the charging efficiency, and improving the reliability and stability of the overall energy management.

[0090] In an exemplary embodiment, Figure 3 As shown, the real-time charging characteristic parameters and the real-time physical change parameters are substituted into the voltage difference physical prediction model for solving, and the voltage difference physical prediction data is obtained, including steps 302 to 306. Among them:

[0091] Step 302 , using a battery electrochemical process prediction model, predicts the electrochemical process of the automobile battery according to real-time charging characteristic parameters and real-time physical change parameters, and obtains battery electrochemical process prediction data.

[0092] Among them, the battery electrochemical process prediction model can be a mathematical model constructed based on electrochemical reaction kinetics, thermodynamics and mass transfer theory.

[0093] The battery electrochemical process prediction data may be a result calculated by a battery electrochemical process prediction model, which reflects changes in voltage difference caused by internal electrochemical reactions of the battery under different charging conditions.

[0094] Specifically, real-time charging characteristic parameters (such as voltage, current, SOC) and real-time physical change parameters (such as temperature, electrolyte concentration, mechanical stress) are input into the battery electrochemical process prediction model, and pseudo-two-dimensional electrochemical process calculation equations and related mathematical formulas are used for calculation to accurately simulate the electrochemical reaction process inside the battery and obtain battery electrochemical process prediction data.

[0095] Among them, the pseudo two-dimensional electrochemical process calculation equation expression of the battery electrochemical process prediction model is:

[0096]

[0097] Among them, the real-time charging characteristic parameters include standard electromotive force, overpotential, current, internal resistance, electrode resistance; the real-time physical change parameters include gas constant, temperature, ion concentration in electrolyte, ion concentration in solid phase; ΔV P2D (t) is the battery electrochemical process prediction data, E 0 is the standard electromotive force, R is the gas constant, T is the temperature, F is the Faraday constant, c e (t) is the ion concentration in the electrolyte, c s (t) is the ion concentration in the solid phase, η(t) is the overpotential, I(t) is the current, R int (t) is the internal resistance, R elec (t) is the electrode resistance.

[0098] Step 304 , using the battery electrochemical behavior prediction model, predict the electrochemical behavior of the automobile battery according to the real-time charging characteristic parameters and the real-time physical change parameters, and obtain battery electrochemical behavior prediction data.

[0099] Among them, the battery electrochemical behavior prediction model can be a mathematical model constructed based on the electrochemical reaction kinetics and combined with mass transfer theory and thermodynamics.

[0100] Among them, the battery electrochemical behavior prediction data can be the result calculated by the battery electrochemical behavior prediction model, reflecting the change of voltage difference caused by the internal electrochemical reaction and material migration of the battery under different charging conditions.

[0101] Specifically, real-time charging characteristic parameters (such as voltage, current, SOC) and real-time physical change parameters (such as temperature, electrolyte concentration, mechanical stress) are input into the battery electrochemical behavior prediction model, and calculations are performed using thermal behavior and interface reaction calculation equations and related mathematical formulas to accurately simulate the electrochemical reaction process inside the battery and obtain battery electrochemical process prediction data.

[0102] The thermal behavior and interface reaction calculation equations of the battery electrochemical behavior prediction model are expressed as follows:

[0103]

[0104] Among them, the real-time charging characteristic parameters include standard electromotive force, overpotential, current, internal resistance, electrode resistance; the real-time physical change parameters include gas constant, temperature, Faraday constant, ion concentration in electrolyte, ion concentration in solid phase, electrochemical transfer coefficient, exchange current density, and effective surface area of ​​battery; ΔV DFN (t) is the battery electrochemical behavior prediction data, E 0 is the standard electromotive force, R is the gas constant, T is the temperature, F is the Faraday constant, c e (t) is the ion concentration in the electrolyte, c s (t) is the ion concentration in the solid phase, I(t) is the current, R int (t) is the internal resistance, α is the electrochemical transfer coefficient, j0 is the exchange current density, and A(t) is the effective surface area of ​​the battery.

[0105] Step 306, using the battery multi-scale and multi-domain prediction model, predict the electrothermal-mechanical coupling of the automobile battery according to the real-time charging characteristic parameters and the real-time physical change parameters, and obtain the battery multi-scale and multi-domain prediction data.

[0106] Among them, the multi-scale and multi-field prediction model of batteries can be constructed by combining theories from multiple fields such as electrochemistry, thermodynamics and mechanics, and is a comprehensive mathematical model used to calculate the electrothermal-mechanical coupling of batteries.

[0107] Among them, the battery multi-scale and multi-field prediction data can be the result calculated by the battery multi-scale and multi-field prediction model, which comprehensively reflects the coupled behaviors of the battery such as electrochemical reaction, thermal conduction and mechanical stress under different charging conditions, and shows the changing trend of the voltage difference caused by the battery performance from micro to macro scales.

[0108] Specifically, the real-time charging characteristic parameters (such as voltage, current, SOC) and real-time physical change parameters (such as temperature, electrolyte concentration, mechanical stress) are input into the battery multi-scale and multi-domain prediction model. The battery multi-scale and multi-domain prediction model combines electrochemical, thermodynamic and mechanical equations, and uses the electrothermal-mechanical coupling calculation equation to comprehensively analyze the reaction process of the battery at different scales and fields to obtain the battery multi-scale and multi-domain prediction data.

[0109] The electrothermal-mechanical coupling calculation equation of the multi-scale and multi-domain prediction model of the battery is expressed as:

[0110]

[0111] Among them, the real-time charging characteristic parameters include standard electromotive force, overpotential, current, internal resistance, electrode resistance; the real-time physical change parameters include gas constant, temperature, Faraday constant, ion concentration in electrolyte, ion concentration in solid phase, electrochemical transfer coefficient, exchange current density, effective surface area of ​​battery, mechanical stress, heat generation phase; ΔV MSMD (t) is the multi-scale and multi-field prediction data of the battery, E 0 is the standard electromotive force, R is the gas constant, T is the temperature, F is the Faraday constant, c e (t) is the ion concentration in the electrolyte, c s (t) is the ion concentration in the solid phase, I(t) is the current, R int (t) is the internal resistance, R elec (t) is the electrode resistance, σ(t) is the mechanical stress, Q gen (t) is the heat generation phase, which consists of Joule heat and reaction heat, and A(t) is the effective surface area of ​​the battery.

[0112] In this embodiment, by respectively using the battery electrochemical process prediction model, the electrochemical behavior prediction model and the multi-scale and multi-field prediction model, a comprehensive prediction is performed based on the real-time charging characteristic parameters and physical change parameters, which can accurately simulate and predict the electrochemical reactions, behavioral changes and electrothermal-mechanical coupling processes inside the battery, and obtain detailed battery electrochemical process prediction data, electrochemical behavior prediction data and multi-scale and multi-field prediction data, thereby providing a scientific and comprehensive basis for optimizing charging strategies, improving battery performance and extending battery life.

[0113] In an exemplary embodiment, Figure 4 As shown, the charging state of the vehicle battery is predicted based on the voltage difference physical prediction data and the voltage difference intelligent prediction data to obtain the battery voltage difference prediction curve, including steps 402 to 404. Among them:

[0114] Step 402, according to the adaptive weighted fusion algorithm of the automobile battery, the battery electrochemical process prediction data, the battery electrochemical behavior prediction data, the battery multi-scale and multi-domain prediction data, the voltage long and short-term memory prediction data, the voltage attention mechanism prediction data and the voltage graph neural network prediction data are weightedly summed to obtain the battery voltage difference fusion data.

[0115] Among them, the adaptive weighted fusion algorithm can be a dynamic optimization technology. It determines the initial weight according to the prediction performance of each model in historical data, and monitors and adjusts the weight of each model in real time in actual applications, so that the model with higher weight contributes more to the final prediction result, so as to combine the advantages of multiple models and provide more accurate and robust prediction results.

[0116] The battery voltage difference fusion data may be the final prediction data obtained by integrating the results of multiple prediction models using an adaptive weighted fusion algorithm, which reflects the change in the voltage difference of the battery under different charging conditions.

[0117] Specifically, in the adaptive weighted fusion algorithm, according to the prediction accuracy of the battery electrochemical behavior prediction model, the battery electrochemical process prediction model, the battery multi-scale multi-domain prediction model, the voltage long short-term memory prediction model, the voltage attention mechanism prediction model and the voltage graph neural network prediction model on historical data, the initial weights of the battery electrochemical process prediction data, the battery electrochemical behavior prediction data, the battery multi-scale multi-domain prediction data, the voltage long short-term memory prediction data, the voltage attention mechanism prediction data and the voltage graph neural network prediction data are calculated respectively. The higher the initial weight value, the better the historical performance of the model. In practical applications, the real-time prediction error of each model is continuously monitored, and the weight is dynamically adjusted according to these errors. By reducing the weight of the prediction data with larger errors and increasing the weight of the prediction data with smaller errors, it is ensured that each prediction data contributes the optimal prediction result according to the current situation during the fusion process, and the weights of different prediction data are obtained. The weighted fusion formula of the adaptive weighted fusion algorithm is further used to weight the battery electrochemical process prediction data, the battery electrochemical behavior prediction data, the battery multi-scale multi-domain prediction data, the voltage long short-term memory prediction data, the voltage attention mechanism prediction data and the voltage graph neural network prediction data to calculate the battery voltage difference fusion data.

[0118] Among them, the weighted fusion formula of the adaptive weighted fusion algorithm is:

[0119] ΔV final (t) = ω1·ΔV P2D (t)+ω2·ΔV DFN (t)+ω3·ΔV MSMD (t)+ω4·ΔV LSTM (t)+ω5·ΔVTransformer (t)+ω6·ΔV GNN (t)

[0120] Where, ΔV final (t) is the battery voltage difference fusion data, ΔV LSTM (t) is the voltage long-term and short-term memory prediction data, ΔV Transformer (t) is the voltage attention mechanism prediction data, ΔV GNN (t) is the voltage graph neural network prediction data, ω1, ω2, ω3, ω4, ω5, and ω6 are the battery electrochemical process prediction data, battery electrochemical behavior prediction data, battery multi-scale and multi-field prediction data, voltage long and short-term memory prediction data, voltage attention mechanism prediction data, and the weights of the voltage graph neural network prediction data, respectively.

[0121] Step 404 , interpolating the battery voltage difference fusion data to obtain a battery voltage difference prediction curve.

[0122] Specifically, an interpolation method (such as linear interpolation, spline interpolation, etc.) is used to smoothly connect discrete prediction data points to generate a continuous voltage change curve, thereby obtaining a battery voltage difference prediction curve.

[0123] In this embodiment, an adaptive weighted fusion algorithm is used to perform weighted summation on the battery electrochemical process prediction data, electrochemical behavior prediction data, multi-scale and multi-field prediction data, voltage long and short-term memory prediction data, voltage attention mechanism prediction data, and voltage graph neural network prediction data, and the advantages of each model are combined to obtain more accurate battery voltage difference fusion data; these fused data are then interpolated to generate a smooth and continuous battery voltage difference prediction curve. This process improves the accuracy and reliability of the prediction, and provides a more accurate and comprehensive scientific basis for optimizing charging strategies and battery management.

[0124] In an exemplary embodiment, Figure 5 As shown, according to the mapping relationship between the battery voltage difference prediction curve and the position of each battery charging control quadrant, the battery charging control mode of the vehicle battery is determined, including steps 502 to 508. Among them:

[0125] Step 502 , determining a preset charging control mode for the vehicle battery according to a mapping relationship between a battery voltage difference prediction curve and positions of each battery charging control quadrant.

[0126] The preset charging control mode may be a charging control strategy and charging control parameters preset in the battery charging control quadrant.

[0127] Specifically, the battery voltage difference prediction curve is positionally mapped with the predefined charging control quadrants, and information that different line segments of the battery voltage difference prediction curve fall into different battery charging control quadrants is determined to match corresponding charging control strategies, such as active balancing, passive balancing, active non-balancing and passive non-balancing, etc., to dynamically determine at least one charging control preset mode that is most suitable for the vehicle battery.

[0128] Step 504 , determining control quadrant transition information of the battery voltage difference prediction curve according to the position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant.

[0129] The control quadrant transition information may refer to the detailed data of the transition point and transition process of the battery voltage difference prediction curve between different charging control quadrants.

[0130] Specifically, the position changes of the battery voltage difference prediction curve near the boundaries of each predefined battery charging control quadrant are analyzed, the transition points and times of the prediction curve between different quadrants are recorded, and the specific information of each transition point is determined, including the transition time, transition voltage and corresponding charging control strategy, so as to generate detailed control quadrant transition information.

[0131] Step 506: Generate a charging control transition mode for the vehicle battery according to the control quadrant transition information.

[0132] Among them, the charging control transition mode can be a specific charging strategy and adjustment steps formulated according to the transition information between different charging control quadrants of the battery voltage difference prediction curve, including the determination of the transition point, the setting of charging parameters during the transition period and the mode switching method.

[0133] Specifically, the control quadrant transition information is analyzed to determine the transition points and corresponding transition conditions of the battery voltage difference prediction curve between different charging control quadrants, and a charging control transition mode for these transition points and transition conditions is generated, including specific transition strategies, adjustment steps and parameter settings.

[0134] Step 508 , according to the development trend of the battery voltage difference prediction curve, the charging control transition mode and the charging control preset mode are combined to obtain the battery charging control mode.

[0135] Specifically, according to the development trend of the battery voltage difference prediction curve, each charging control transition mode and charging control preset mode are sorted in chronological order, and according to the sorting result, each charging control transition mode and charging control preset mode are spliced ​​together to obtain the battery charging control mode.

[0136] In this embodiment, the charging control preset mode is determined by analyzing the position mapping relationship between the battery voltage difference prediction curve and each charging control quadrant, and the control quadrant transition information is generated according to the change of the prediction curve between different quadrants, and then the charging control transition mode is formulated. Finally, these transition modes are combined with the preset mode to form a complete battery charging control mode. This process realizes dynamic adjustment and optimization of the charging strategy, improves the charging efficiency and battery life, and ensures the safety and stability of the charging process.

[0137] In an exemplary embodiment, Figure 6 As shown, when the control quadrant excess information characterizing the battery voltage difference prediction curve oscillates near the coordinate axes of any two different battery charging control quadrants, the method further includes steps 602 to 604. Among them:

[0138] Step 602, determining a multi-mode sequential control mode and / or a multi-mode parallel control mode of the vehicle battery according to the oscillation amplitude and oscillation frequency of the control quadrant transition information.

[0139] Among them, the oscillation amplitude can be the maximum deviation value of the voltage change when the battery voltage difference prediction curve transitions between the control quadrants, which reflects the intensity of the battery voltage fluctuation; the oscillation frequency can be the number of times the battery voltage difference prediction curve transitions between different control quadrants in unit time, which indicates the frequency of voltage changes.

[0140] The multi-mode sequential control mode may be a charging mode in which a plurality of charging control preset modes are executed in sequence.

[0141] The multi-mode parallel control mode may be a charging mode executed by a plurality of charging control preset modes.

[0142] Specifically, the oscillation amplitude and oscillation frequency of the control quadrant transition information are analyzed, and the stability and response characteristics of the battery switching between different charging control modes between different charging control quadrants are evaluated. When the control quadrant transition information represents that the battery voltage difference prediction curve has high-frequency and small-amplitude oscillations between different charging control quadrants, a multi-mode sequential control mode is selected for charging control, that is, the charging modes are switched in sequence in a certain order over time to stabilize the change of the voltage difference; when the control quadrant transition information represents that the battery voltage difference prediction curve has low-frequency and large-amplitude oscillations between different charging control quadrants, a multi-mode parallel control mode is selected for charging control, that is, the change of the voltage difference is stabilized by using multiple different charging modes over time;

[0143] Step 604 , according to the development trend of the battery voltage difference prediction curve, the multi-mode sequential control mode and / or the multi-mode parallel control mode and the charging control preset mode are spliced ​​to obtain the battery charging control mode.

[0144] Specifically, according to the development trend of the battery voltage difference prediction curve, each charging control transition mode and the multi-mode sequential control mode or / and the multi-mode parallel control mode are sorted in chronological order, and according to the sorting result, each charging control transition mode and the charging control preset mode are spliced ​​together to obtain the battery charging control mode.

[0145] In this embodiment, by analyzing the oscillation amplitude and oscillation frequency of the control quadrant transition information, the multi-mode sequential control mode (executing multiple charging control preset modes in sequence) or the multi-mode parallel control mode (executing multiple charging control preset modes simultaneously) of the automobile battery is determined; then, according to the development trend of the battery voltage difference prediction curve, these control modes are spliced ​​with the charging control preset mode to form a comprehensive battery charging control mode. This process realizes flexible adjustment and optimization of the charging strategy, ensures the efficiency and stability of different charging stages, thereby extending the battery life and improving the overall charging performance.

[0146] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0147] Based on the same inventive concept, the embodiment of the present application also provides a device for optimizing an energy storage type electric vehicle charging station for realizing the energy optimization method for an energy storage type electric vehicle charging station involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more energy optimization devices for an energy storage type electric vehicle charging station provided below can refer to the limitations of the energy optimization method for an energy storage type electric vehicle charging station above, and will not be repeated here.

[0148] In an exemplary embodiment, Figure 7As shown, a device for optimizing the energy of a photovoltaic electric vehicle charging station is provided, comprising: a battery data acquisition module 702, a voltage difference prediction module 704 and a battery charging control module 706, wherein:

[0149] The battery data acquisition module 702 is used to acquire the real-time charging characteristic parameters, real-time physical change parameters, voltage difference physical prediction model and voltage difference intelligent prediction model of the automobile battery;

[0150] The voltage difference prediction module 704 is used to substitute the real-time charging characteristic parameters and the real-time physical change parameters into the voltage difference physical prediction model for solving, so as to obtain the voltage difference physical prediction data;

[0151] The voltage difference prediction module 704 is further used to input the real-time charging characteristic parameters and the real-time physical change parameters into the voltage difference intelligent prediction model to obtain the voltage difference intelligent prediction data;

[0152] The voltage difference prediction module 704 is further used to predict the charging state of the vehicle battery according to the voltage difference physical prediction data and the voltage difference intelligent prediction data, and obtain a battery voltage difference prediction curve;

[0153] The battery charging control module 706 is used to determine the battery charging control mode of the vehicle battery according to the position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant; the battery charging control mode is used to optimize the power transmission between the photovoltaic electric vehicle charging station and the vehicle battery; the battery charging control quadrant is the operating conditions corresponding to different battery charging control modes in the battery charging control model of the vehicle battery.

[0154] In one embodiment, the voltage difference prediction module 704 is also used to use the battery electrochemical process prediction model to predict the electrochemical process of the automobile battery according to the real-time charging characteristic parameters and the real-time physical change parameters, and obtain battery electrochemical process prediction data; use the battery electrochemical behavior prediction model to predict the electrochemical behavior of the automobile battery according to the real-time charging characteristic parameters and the real-time physical change parameters, and obtain battery electrochemical behavior prediction data; use the battery multi-scale and multi-domain prediction model to predict the electrothermal-mechanical coupling of the automobile battery according to the real-time charging characteristic parameters and the real-time physical change parameters, and obtain battery multi-scale and multi-domain prediction data.

[0155] In one embodiment, the voltage difference prediction module 704 is also used to perform weighted summation on the battery electrochemical process prediction data, the battery electrochemical behavior prediction data, the battery multi-scale and multi-domain prediction data, the voltage long and short-term memory prediction data, the voltage attention mechanism prediction data and the voltage graph neural network prediction data according to the adaptive weighted fusion algorithm of the automobile battery to obtain the battery voltage difference fusion data; and perform interpolation processing on the battery voltage difference fusion data to obtain the battery voltage difference prediction curve.

[0156] In one embodiment, the battery charging control module 706 is also used to determine the preset charging control mode of the vehicle battery according to the position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant; determine the control quadrant transition information of the battery voltage difference prediction curve according to the position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant; the control quadrant transition information is the change of the battery voltage difference prediction curve near the coordinate axis of any two different battery charging control quadrants; generate the charging control transition mode of the vehicle battery according to the control quadrant transition information; according to the development trend of the battery voltage difference prediction curve, splice the charging control transition mode and the charging control preset mode to obtain the battery charging control mode.

[0157] In one embodiment, the battery charging control module 706 is also used to determine the multi-mode sequential control mode and / or the multi-mode parallel control mode of the vehicle battery according to the oscillation amplitude and oscillation frequency of the control quadrant transition information; the multi-mode sequential control mode is obtained by executing multiple charging control preset modes in sequence; the multi-mode parallel control mode is obtained by executing multiple charging control preset modes together; according to the development trend of the battery voltage difference prediction curve, the multi-mode sequential control mode and / or the multi-mode parallel control mode, and the charging control preset mode are spliced ​​to obtain the battery charging control mode.

[0158] Each module in the above-mentioned photovoltaic storage type electric vehicle charging station energy optimization device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0159] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store server data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for optimizing the energy of a photovoltaic electric vehicle charging station is implemented.

[0160] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0161] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0162] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0163] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0164] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0165] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0166] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0167] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for optimizing the energy of a photovoltaic electric vehicle charging station, characterized in that: The method comprises: Obtaining real-time charging characteristic parameters, real-time physical change parameters, voltage difference physical prediction model and voltage difference intelligent prediction model of the automobile battery; Substituting the real-time charging characteristic parameter and the real-time physical change parameter into the voltage difference physical prediction model for solving, to obtain voltage difference physical prediction data; Inputting the real-time charging characteristic parameter and the real-time physical change parameter into the voltage difference intelligent prediction model to obtain voltage difference intelligent prediction data; Predicting the charging state of the vehicle battery according to the voltage difference physical prediction data and the voltage difference intelligent prediction data to obtain a battery voltage difference prediction curve; The battery charging control mode of the vehicle battery is determined according to the position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant; the battery charging control mode is used to optimize the power transmission between the photovoltaic electric vehicle charging station and the vehicle battery; the battery charging control quadrant is the operating conditions corresponding to different battery charging control modes in the battery charging control model of the vehicle battery.

2. The method according to claim 1, characterized in that The voltage difference physical prediction model includes a battery electrochemical behavior prediction model, a battery electrochemical process prediction model and a battery multi-scale multi-field prediction model; the voltage difference physical prediction data includes battery electrochemical process prediction data, battery electrochemical behavior prediction data and battery multi-scale multi-field prediction data; the real-time charging characteristic parameters and the real-time physical change parameters are substituted into the voltage difference physical prediction model for solving to obtain the voltage difference physical prediction data, including: Using the battery electrochemical process prediction model, according to the real-time charging characteristic parameters and the real-time physical change parameters, the electrochemical process of the automobile battery is predicted to obtain the battery electrochemical process prediction data; Using the battery electrochemical behavior prediction model, the electrochemical behavior of the automobile battery is predicted according to the real-time charging characteristic parameter and the real-time physical change parameter to obtain the battery electrochemical behavior prediction data; The battery multi-scale and multi-domain prediction model is used to predict the electrothermal-mechanical coupling of the automobile battery according to the real-time charging characteristic parameters and the real-time physical change parameters, thereby obtaining the battery multi-scale and multi-domain prediction data.

3. The method according to claim 2, characterized in that The expression of the battery electrochemical process prediction model is: The real-time charging characteristic parameters include standard electromotive force, overpotential, current, internal resistance, and electrode resistance; the real-time physical change parameters include gas constant, temperature, ion concentration in electrolyte, and ion concentration in solid phase; the ΔV P2D (t) is the battery electrochemical process prediction data, the E 0 is the standard electromotive force, R is the gas constant, T is the temperature, F is the Faraday constant, and c e (t) is the ion concentration in the electrolyte, and c s (t) is the ion concentration in the solid phase, η(t) is the overpotential, I(t) is the current, and R int (t) is the internal resistance, the R elec (t) is the electrode resistance.

4. The method according to claim 2, characterized in that: The expression of the battery electrochemical behavior prediction model is: The real-time charging characteristic parameters include standard electromotive force, overpotential, current, internal resistance, and electrode resistance; the real-time physical change parameters include gas constant, temperature, Faraday constant, ion concentration in electrolyte, ion concentration in solid phase, electrochemical transfer coefficient, exchange current density, and effective surface area of ​​battery; the ΔV DFN (t) is the electrochemical behavior prediction data of the battery, and the E 0 is the standard electromotive force, R is the gas constant, T is the temperature, F is the Faraday constant, c e (t) is the ion concentration in the electrolyte, and c s (t) is the ion concentration in the solid phase, I(t) is the current, and R int (t) is the internal resistance, α is the electrochemical transfer coefficient, j0 is the exchange current density, and A(t) is the effective surface area of ​​the battery.

5. The method according to claim 2, characterized in that: The expression of the battery multi-scale and multi-domain prediction model is: The real-time charging characteristic parameters include standard electromotive force, overpotential, current, internal resistance, and electrode resistance; the real-time physical change parameters include gas constant, temperature, Faraday constant, ion concentration in electrolyte, ion concentration in solid phase, electrochemical transfer coefficient, exchange current density, effective surface area of ​​battery, mechanical stress, and heat generation phase; the ΔV MSMD (t) is the multi-scale and multi-domain prediction data of the battery, and the E 0 is the standard electromotive force, R is the gas constant, T is the temperature, F is the Faraday constant, c e (t) is the ion concentration in the electrolyte, and c s (t) is the ion concentration in the solid phase, I(t) is the current, and R int (t) is the internal resistance, the R elec (t) is the electrode resistance, σ(t) is the mechanical stress, and Q gen (t) is the heat generation phase, which consists of Joule heat and reaction heat, and A(t) is the effective surface area of ​​the battery.

6. The method according to claim 2, characterized in that The voltage difference intelligent prediction data includes voltage long-short term memory prediction data, voltage attention mechanism prediction data and voltage graph neural network prediction data; the charging state of the automobile battery is predicted based on the voltage difference physical prediction data and the voltage difference intelligent prediction data to obtain a battery voltage difference prediction curve, including: According to the adaptive weighted fusion algorithm of the automobile battery, the battery electrochemical process prediction data, the battery electrochemical behavior prediction data, the battery multi-scale multi-domain prediction data, the voltage long-short term memory prediction data, the voltage attention mechanism prediction data and the voltage graph neural network prediction data are weightedly summed to obtain battery voltage difference fusion data; Performing interpolation processing on the battery voltage difference fusion data to obtain the battery voltage difference prediction curve; The weighted fusion formula of the adaptive weighted fusion algorithm is: ΔV final (t)=ω1·ΔV P2D (t)+ω2·ΔV DFN (t)+ω3·ΔV MSMD (t)+ω4·ΔV LSTM (t)+ω5·ΔV Transformer (t)+ω6·ΔV GNN (t) Among them, the ΔV final (t) is the battery voltage difference fusion data, the ΔV LSTM (t) is the voltage long-term and short-term memory prediction data, and the ΔV Transformer (t) is the voltage attention mechanism prediction data, the ΔV GNN (t) is the voltage graph neural network prediction data, and ω1, ω2, ω3, ω4, ω5, and ω6 are respectively the battery electrochemical process prediction data, the battery electrochemical behavior prediction data, the battery multi-scale and multi-field prediction data, the voltage long and short-term memory prediction data, the voltage attention mechanism prediction data, and the weights of the voltage graph neural network prediction data.

7. The method according to claim 2, characterized in that The method of determining the battery charging control mode of the vehicle battery according to the position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant includes: Determining a preset charging control mode of the vehicle battery according to a position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant; Determine the control quadrant transition information of the battery voltage difference prediction curve according to the position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant; the control quadrant transition information is the change of the battery voltage difference prediction curve near the coordinate axes of any two different battery charging control quadrants; generating a charging control transition mode of the vehicle battery according to the control quadrant transition information; According to the development trend of the battery voltage difference prediction curve, the charging control transition mode and the charging control preset mode are spliced ​​to obtain the battery charging control mode.

8. The method according to claim 7, characterized in that In the case where the control quadrant transition information indicates that the battery voltage difference prediction curve oscillates near coordinate axes of any two different battery charging control quadrants, the method further includes: Determine the multi-mode sequential control mode and / or the multi-mode parallel control mode of the vehicle battery according to the oscillation amplitude and oscillation frequency of the control quadrant transition information; the multi-mode sequential control mode is obtained by executing a plurality of the charging control preset modes in sequence; the multi-mode parallel control mode is obtained by executing a plurality of the charging control preset modes together; According to the development trend of the battery voltage difference prediction curve, the multi-mode sequential control mode and / or the multi-mode parallel control mode and the charging control preset mode are spliced ​​to obtain the battery charging control mode.

9. An energy optimization device for a photovoltaic electric vehicle charging station, characterized in that: The device comprises: A battery data acquisition module is used to obtain real-time charging characteristic parameters, real-time physical change parameters, voltage difference physical prediction model and voltage difference intelligent prediction model of the automobile battery; A voltage difference prediction module, used for substituting the real-time charging characteristic parameter and the real-time physical change parameter into the voltage difference physical prediction model for solving, so as to obtain voltage difference physical prediction data; The voltage difference prediction module is further used to input the real-time charging characteristic parameter and the real-time physical change parameter into the voltage difference intelligent prediction model to obtain voltage difference intelligent prediction data; The voltage difference prediction module is further used to predict the charging state of the vehicle battery according to the voltage difference physical prediction data and the voltage difference intelligent prediction data, so as to obtain a battery voltage difference prediction curve; A battery charging control module is used to determine the battery charging control mode of the vehicle battery according to the position mapping relationship between the battery voltage difference prediction curve and each battery charging control quadrant; the battery charging control mode is used to optimize the power transmission between the photovoltaic electric vehicle charging station and the vehicle battery; the battery charging control quadrant is the operating conditions corresponding to different battery charging control modes in the battery charging control model of the vehicle battery.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images