A method and system for implementing energy storage charging strategy based on ultra-capacitive coupled lithium battery

Abstract

The present invention relates to the field of charging control technology, and discloses a method and system for implementing an energy storage charging strategy based on a supercapacitor coupled lithium battery. The method comprises: collecting current and temperature data and performing preliminary analysis; establishing a temperature prediction model and optimizing the temperature prediction model parameters; obtaining the cumulative temperature parameter based on the cumulative effect of the temperature; and monitoring and regulating the temperature based on the prediction results, and dynamically adjusting the charging strategy. A temperature prediction model is constructed, and nonlinear and integral terms are used to enable the model to more accurately describe the trend of temperature changes with current. The battery temperature is monitored in real time based on the prediction results, and the charging strategy is dynamically adjusted to optimize the charging method. When the temperature approaches the upper limit, overheating is avoided by reducing the charging current, thereby protecting the battery and extending the battery life.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage charging strategy control, and in particular to a method and system for implementing an energy storage charging strategy based on a supercapacitor coupled lithium battery. Background Art

[0002] For thermal power units, long-term frequency regulation leads to increased coal consumption, reduced reliability, and shortened operating life. Furthermore, high-quality, efficient frequency-regulating power sources are scarce, and coal-fired thermal power units remain the primary source of frequency regulation. Coupled with the demand for large-scale renewable energy grid integration, environmental pressures restricting unit regulation capabilities, and the "heat-based electricity" problem for heating units, the demand for power frequency regulation is further increasing. However, the performance of the auxiliary frequency regulation and energy storage equipment currently used in thermal power plants cannot meet the efficiency and reliability requirements of the units themselves, affecting the ability to obtain grid subsidies and resulting in low economic benefits.

[0003] In response to these problems, the existing technology has proposed an energy storage system with a supercapacitor coupled lithium battery. The generator set is a rotating large-capacity active and reactive source, while the energy storage system can be regarded as a static relatively small-capacity power generator. The main difference between the two lies in their output range and response characteristics. The former has a large output range but a slow response speed, while the latter has a relatively small capacity but a fast response speed. The coordinated operation of the two can significantly improve the execution effect of the thermal power unit on the AGC instructions of the power grid. By utilizing the ability of the energy storage system to quickly adjust the output power, using the thermal power unit as the basic unit to respond to the AGC instructions, supplemented by the energy storage system as a supplementary fast response unit, the unit output and the energy storage system output are combined and sent to the power grid as the total system output, which can achieve the purpose of improving the AGC performance of the unit. Single lithium battery energy storage or single supercapacitor energy storage

[0004] It's impossible to simultaneously meet the high power density required for primary frequency regulation and the high energy density required for secondary frequency regulation. Hybrid energy storage technology, combining the two, can complement each other's strengths and improve system performance. In the hybrid energy storage system's control strategy, supercapacitors are prioritized. For small commands, the supercapacitors respond entirely; for large commands, the supercapacitors respond at full power, with lithium batteries serving as a supplement. This allows for shallower charge and discharge depths in the lithium battery, further extending its lifespan.

[0005] However, charging time and temperature are two conflicting objectives during the lithium battery charging process. Shortening charging time can reduce the response time of the energy storage system, but this requires increasing the charging current, which also causes the battery temperature to rise. Excessive temperature rise can cause battery safety issues, while excessive energy loss will lead to reduced energy utilization efficiency and increased costs. Summary of the Invention

[0006] In view of the above-mentioned problems, the present invention is proposed.

[0007] Therefore, the technical problem solved by the present invention is: how to shorten the charging time while ensuring the temperature is as low as possible.

[0008] To solve the above technical problems, the present invention provides the following technical solutions: a method for implementing an energy storage charging strategy based on a supercapacitor coupled lithium battery, comprising:

[0009] Collect current and temperature data and conduct preliminary analysis;

[0010] Establish a temperature prediction model and optimize the parameters of the temperature prediction model;

[0011] Obtain the cumulative term parameters of temperature based on the cumulative effect of temperature;

[0012] Monitor and adjust the temperature based on the prediction results, and dynamically adjust the charging strategy.

[0013] As a preferred solution of the method for implementing the energy storage charging strategy based on the super-capacitor coupled lithium battery of the present invention, the preliminary analysis includes: assuming that the lithium battery needs to be charged, the magnitude of the charging current is I(t), and the temperature naturally rises as the charging progresses. The relationship between current and temperature is expressed as follows:

[0014]

[0015] Where T represents the surface temperature of the lithium-ion battery; m represents the battery mass; C h Indicates the thermal capacity of the battery; It represents the temperature rise coefficient of the battery open circuit voltage. Experiments have shown that the temperature rise coefficient is almost unaffected by temperature. I represents current; R0 represents internal resistance; U1 and U2 represent voltage coefficients; h represents heat transfer coefficient; A represents a constant to be determined; T ope Indicates operating temperature;

[0016] The prediction formula for optimizing the relationship between current and temperature is expressed as:

[0017]

[0018] Among them, A, B, C, and D represent constants to be determined; represents the integral index; I(t) represents the current changing with time.

[0019] As a preferred solution of the method for implementing the energy storage charging strategy based on the supercapacitor coupled lithium battery of the present invention, wherein: the temperature prediction model parameters include confirming ABCD and Based on the existing data on lithium battery current and temperature detection, N sets of data with one-to-one correspondence between current value and temperature value are selected; the temperature prediction model formula is expressed as:

[0020] T=AI 3 (t)+BI 2 (t)+CI(t)

[0021] Randomly generate 200 sets of [ABC], and input N sets of current into the formula for each set of [ABC]. Obtain the calculated temperature values ​​corresponding to the N sets. Calculate the root mean square prediction error (RMSE) between the temperature values ​​and the actual temperature values, expressed as:

[0022]

[0023] Where N represents the sample size, y n and Represent the actual value and predicted value at time n respectively; find the group with the smallest RMSE among m groups [ABC], assuming that the value of group j [ABC] [A j B j C j ], the corresponding RMSE is the smallest, then select [A j B j C j ], to [A j B j C j ] to perform further parameter optimization.

[0024] As a preferred solution of the method for implementing the energy storage charging strategy based on the supercapacitor coupled lithium battery of the present invention, wherein: the optimization operation includes: j B j C j ]Parameters are optimized;

[0025] B j =rand(min(sigmoid(A j ),tanh(A j )),max(sigmoid(A j ),tanh(A j )))

[0026] Among them, Sigmoid() and tanh() represent activation functions;

[0027]

[0028] Wherein, k represents the number of cycles, and the initial k=1;

[0029] After the optimization is completed, use the new [A j B j C j] Determine whether RMSE is reduced by 30%. If not, perform the second step of optimization, define RMSE as the loss function, and perform optimization iteration until the parameters meet the RMSE reduction to the required threshold.

[0030] As a preferred solution of the energy storage charging strategy implementation method based on the supercapacitor coupled lithium battery of the present invention, wherein: the cumulative parameter for obtaining the temperature includes D and The source is the temperature accumulation term caused by the cumulative effect of temperature. During the charging process, the current changes from I a Evenly rise to I b , at this time the temperature changes from T a to T b ; Record the 100 points where the current and temperature correspond to each other during this process, expressed as (I1, T1), (I2, T2), (I3, T3)..., (I 100 ,T 100 );

[0031] The time sampling interval is Δt; the optimized [A j B j C j ] Put I1, I2, I3, ..., I 100 , substitute into the temperature prediction model formula T = AI 3 (t)+BI 2 (t)+CI(t), and calculate the corresponding T'1, T'2, T'3, ..., T' 100 ; Actual values ​​T1, T2, T3, ..., T 100 with T'1, T'2, T'3, ..., T' 100 The difference is expressed as [Δ1, Δ2, Δ3, ..., Δ 100 ], the difference is caused by the cumulative effect of temperature.

[0032] As a preferred solution of the method for implementing the energy storage charging strategy based on the supercapacitor coupled lithium battery of the present invention, wherein: the temperature monitoring and adjustment according to the prediction results includes:

[0033]

[0034] Among them, b represents the rate of increase of current. Using the cumulative effect formula, we can solve a set of D and The relationship formula is expressed as:

[0035]

[0036] In [Δ1,Δ2,Δ3,...,Δ 100 ] to find the minimum value Δ min , let Δmin Corresponding According to the minimum value calculation formula:

[0037]

[0038] You can solve D min ,make Solve all right Find the mean, which is the final Mean.

[0039] As a preferred solution of the method for implementing the energy storage charging strategy based on the super-capacitor coupled lithium battery of the present invention, the dynamic adjustment of the charging strategy includes: assuming that charging starts now, the change of the charging current over time is I=bt, and the upper limit of the battery temperature is Tmax; deducing the relationship between current and temperature based on the prediction formula, the formula is expressed as follows:

[0040]

[0041] Analyze when the temperature reaches Tmax, and assume that t is calculated according to this formula max When time reaches Tmax, then at t max -The charging current is automatically reduced at δt. The formula for confirming δt is expressed as:

[0042]

[0043] At this time, the charging current changes from I(t)=bt to I(t)=e -qt , where q represents a coefficient that controls current attenuation.

[0044] A system for implementing an energy storage charging strategy based on a supercapacitor coupled lithium battery using any of the methods described in the present invention, comprising:

[0045] The data analysis module collects the current and temperature data of the lithium battery during the charging process, analyzes the relationship between the current and temperature during the charging process, and determines the preliminary parameter range for the temperature prediction model;

[0046] Prediction model module, which builds a temperature prediction model, fits the model using the collected data, and optimizes the parameters;

[0047] Parameter acquisition module, records the data generated during the charging process, calculates the temperature accumulation item, and obtains the accumulation effect parameters;

[0048] The charging strategy adjustment module monitors the temperature of the lithium battery in real time to ensure that it does not exceed the set temperature limit. When the predicted temperature is about to be reached, the charging current is adjusted in advance.

[0049] A computer device comprises: a memory and a processor; the memory stores a computer program, comprising: the steps of implementing any one of the methods of the present invention when the processor executes the computer program.

[0050] A computer-readable storage medium stores a computer program thereon, comprising: steps of implementing any one of the methods of the present invention when the computer program is executed by a processor.

[0051] The present invention has the following beneficial effects: A temperature prediction model is constructed that utilizes nonlinear and integral terms to more accurately describe the temperature-current relationship. Based on the prediction results, the model monitors battery temperature in real time and dynamically adjusts the charging strategy to optimize the charging method. When the temperature approaches the upper limit, the charging current is reduced to avoid overheating, thereby protecting the battery and extending its lifespan. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0053] Figure 1 This is an overall flow chart of a method for implementing an energy storage charging strategy based on a supercapacitor coupled lithium battery provided by the first embodiment of the present invention;

[0054] Figure 2 A schematic diagram of charging control in a method for implementing an energy storage charging strategy based on a super-capacitor coupled lithium battery provided in a second embodiment of the present invention. DETAILED DESCRIPTION

[0055] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0056] Example 1, reference Figure 1 , as one embodiment of the present invention, provides a method for implementing an energy storage charging strategy based on a supercapacitor coupled lithium battery, comprising:

[0057] S1: Collect current and temperature data and perform preliminary analysis.

[0058] Furthermore, current and temperature data are collected and analyzed initially. By establishing a formula for the relationship between current and temperature, basic data can be provided for subsequent optimization.

[0059] Furthermore, preliminary analysis can reveal the initial relationship between current and temperature, helping to identify the influencing factors. This step is important because it provides direction for subsequent optimization and identifies the parameters that require focus.

[0060] Furthermore, the preliminary analysis includes assuming that the lithium battery needs to be charged, the charging current is I(t), and the temperature naturally rises as the charging progresses. The relationship between current and temperature is expressed as follows:

[0061]

[0062] Where T represents the surface temperature of the lithium-ion battery; m represents the battery mass; C h Indicates the thermal capacity of the battery; It represents the temperature rise coefficient of the battery open circuit voltage. Experiments have shown that the temperature rise coefficient is almost unaffected by temperature. I represents current; R0 represents internal resistance; U1 and U2 represent voltage coefficients; h represents heat transfer coefficient; A represents a constant to be determined; T ope Indicates operating temperature.

[0063] Furthermore, the prediction formula for optimizing the relationship between current and temperature is expressed as:

[0064]

[0065] Among them, A, B, C, and D represent constants to be determined; represents the integral index; I(t) represents the current changing with time.

[0066] It should be noted that by collecting current and temperature data, an optimization model is used to accurately predict the temperature changes of lithium-ion batteries. Key steps in this process include preliminary data analysis and the application of optimized prediction formulas. By setting scientific and reasonable parameters, the accuracy of temperature prediction can be significantly improved, thereby achieving safer and more efficient battery charging management.

[0067] S2: Establish a temperature prediction model and optimize the temperature prediction model parameters.

[0068] Furthermore, the temperature prediction model parameters include confirming ABCD and Based on the existing data on lithium battery current and temperature detection, 1000 sets of data with one-to-one correspondence between current value and temperature value were selected; the temperature prediction model formula is expressed as:

[0069] T=AI 3 (t)+BI2 (t)+CI(t)

[0070] Furthermore, 200 sets of [ABC] are randomly generated, and each set of [ABC] inputs 1000 sets of current into the formula; 1000 sets of corresponding calculated temperature values ​​are obtained; the root mean square prediction error (RMSE) between the temperature values ​​and the actual temperature values ​​is calculated, and the formula is expressed as:

[0071]

[0072] Where N represents the sample size, y n and Represent the actual value and predicted value at time n respectively; find the group with the smallest RMSE among the 200 groups [ABC], assuming that the value of group j [AB C] [A j B j C j ], the corresponding RMSE is the smallest, then select [A j B j C j ], to [A j B j C j ] to perform further parameter optimization.

[0073] Furthermore, the optimization operation includes [A j B j C j ] parameters for further optimization.

[0074] B j =rand(min(sigmoid(A j ), tanh(A j )), max(sigmoid(A j ), tanh(A j )))

[0075] Among them, Sigmoid() and tanh() represent activation functions.

[0076]

[0077] Wherein, k represents the number of cycles, and the initial k=1.

[0078] Furthermore, after the optimization is completed, the new [A j B j C j ] Determine whether RMSE is reduced by 30%. If not, perform the second step of optimization, define RMSE as the loss function, and perform optimization iteration until the parameters meet the RMSE reduction to the required threshold.

[0079] Furthermore, through key steps such as randomly generating an initial parameter set, calculating the RMSE to select the optimal parameter set, and gradually optimizing the parameters, they successfully achieved high-precision prediction of lithium battery temperature. Each step not only considers the nonlinear relationship between parameters but also utilizes activation functions and smooth optimization methods to ensure the stability and effectiveness of parameter adjustment. These innovative optimization steps enable the temperature prediction model to achieve higher accuracy and reliability, providing precise temperature predictions in practical applications, effectively preventing battery overheating and improving battery safety and lifespan.

[0080] It should be noted that by randomly generating initial parameters, we can search the parameter space extensively and avoid being trapped in local optima. Calculating the RMSE can assess the prediction accuracy of each parameter set, ensuring that the optimal parameter set is selected. Increasing the diversity of model initialization increases the likelihood of finding the global optimal solution.

[0081] S3: Calculate the cumulative term parameters of temperature based on the cumulative effect of temperature.

[0082] Furthermore, the cumulative parameters for obtaining temperature include D and The source is the temperature accumulation term caused by the cumulative effect of temperature. During the charging process, the current changes from I a Evenly rise to I b , at this time the temperature changes from T a ; to T b ; Record the 100 points where the current and temperature correspond to each other during this process, expressed as (I1, T1), (I2, T2), (I3, T3)..., (I 100 ,T 100 ).

[0083] Furthermore, the time sampling interval is Δt; using the optimized [A j B j C j ] Put I1, I2, I3, ..., I 100 , substitute into the temperature prediction model formula T = AI 3 (t)+BI 2 (t)+CI(t), and calculate the corresponding T'1, T'2, T'3, ..., T' 100 ; Actual values ​​T1, T2, T3, ..., T 100 with T'1, T'2, T'3, ..., T' 100 The difference is expressed as [Δ1, Δ2, Δ3, ..., Δ 100 ], the difference is caused by the cumulative effect of temperature.

[0084] It should be noted that the challenge of temperature control during lithium battery charging is resolved through precise temperature prediction and dynamic adjustment of the charging strategy. The combination of the cumulative effect formula and the dynamic adjustment strategy makes the charging process safer and more efficient. Conventional charging methods struggle to monitor temperature changes in real time, which can easily lead to battery overheating. By calculating the temperature accumulation term parameter and predicting temperature changes in real time, the present invention provides a precise temperature control method, significantly reducing the risk of overheating and improving charging efficiency.

[0085] S4: Monitor and adjust the temperature based on the prediction results, and dynamically adjust the charging strategy.

[0086] Furthermore, temperature monitoring and adjustment based on the prediction results include obtaining the temperature accumulation parameter and establishing a relationship formula between it and current, which can more accurately describe the temperature change during the charging process. The formula is expressed as follows:

[0087]

[0088] Among them, b represents the rate of increase of current. Using the cumulative effect formula, we can solve a set of D and The relationship formula is expressed as:

[0089]

[0090] Furthermore, in [Δ1,Δ2,Δ3,...,Δ 100 ] to find the minimum value Δ min , let Δ min Corresponding According to the minimum value calculation formula:

[0091]

[0092] Furthermore, we can solve D min ,make Solve all right Find the mean, which is the final Mean.

[0093] Furthermore, the dynamic adjustment of the charging strategy includes assuming that charging starts now, the change of the charging current over time is I=bt, and the upper limit of the battery temperature is Tmax; the current and temperature relationship prediction formula is derived, and the formula is expressed as follows:

[0094]

[0095] Furthermore, we analyze when the temperature reaches Tmax. If the temperature reaches Tmax according to this formula, the charging current will be automatically reduced at the time tmax-δt. The formula for confirming δt is expressed as:

[0096]

[0097] Furthermore, the charging current changes from I(t)=bt to I(t)=e -qt , where q represents a coefficient that controls current attenuation.

[0098] It should be noted that existing technologies typically use fixed current or simple temperature monitoring methods, which are difficult to cope with the complex temperature changes during the charging process. This invention uses the cumulative effect and dynamic adjustment strategy to provide a more intelligent and precise temperature control method, ensuring the safety and efficiency of the charging process.

[0099] On the other hand, this embodiment also provides an energy storage charging strategy implementation system based on a supercapacitor coupled lithium battery, which includes:

[0100] The data analysis module collects the current and temperature data of the lithium battery during the charging process, analyzes the relationship between the current and temperature during the charging process, and determines the preliminary parameter range for the temperature prediction model.

[0101] The prediction model module establishes a temperature prediction model, fits the model using the collected data, and performs parameter optimization.

[0102] The parameter acquisition module records the point data generated during the charging process, calculates the temperature accumulation item, and obtains the accumulation effect parameters.

[0103] The charging strategy adjustment module monitors the temperature of the lithium battery in real time to ensure that it does not exceed the set temperature limit. When the predicted temperature is about to be reached, the charging current is adjusted in advance.

[0104] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0105] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0106] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0107] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0108] Example 2, reference Figure 2 , which is an embodiment of the present invention, provides a method for implementing an energy storage charging strategy based on a super-capacitor coupled lithium battery. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0109] Test preparation and implementation process, this test aims to verify the collection, analysis, model establishment and optimization of current and temperature data, obtain the temperature accumulation effect parameters, and perform temperature monitoring and adjustment based on the predicted results. The temperature and current control curve is as follows Figure 2 As shown, the charging strategy can be effectively and dynamically adjusted.

[0110] The test used a certain brand of lithium-ion battery module, the charging device was an intelligent charger, the collection device was a high-precision data collector, and the test object was the lithium-ion battery module.

[0111] Equipment: Smart charger: Sets different charging current rates; High-precision data logger: Records current and temperature data; Temperature sensor: Attached to the battery surface, monitors temperature in real time.

[0112] Test environment: The room temperature is controlled at 25℃ and kept constant.

[0113] Data Collection and Preliminary Analysis,At the beginning of the experiment, the smart charger charged at the preset,charging current rate,bbb,. The data logger recorded the battery’s charging current and,surface temperature every 30 seconds, for a total of 1000 sets of data points.

[0114] Table 1 Charging effect comparison table

[0115]

[0116] As can be seen from Table 1, the present invention has significant improvements in charging speed and temperature control compared to the prior art solutions.

[0117] Table 2 Comparison of some experimental data

[0118]

[0119] Analysis of the tabular data shows that the present invention has significant advantages in temperature prediction and control during battery charging. The difference ΔT between the actual temperature and the predicted temperature mostly fluctuates within the range of ±0.1°C, indicating that the temperature prediction model has high accuracy.

[0120] The temperature prediction model built using the collected current and temperature data accurately predicts battery surface temperature changes with minimal error, demonstrating the model's reliability and practicality. The optimized parameter D accurately describes the cumulative temperature effect, enabling more precise temperature control and preventing battery damage caused by rapid temperature increases. Based on the temperature prediction results, the charging current can be adjusted promptly to prevent the battery temperature from exceeding the upper safety limit, Tmax. This dynamic charging strategy effectively improves the safety and efficiency of the charging process.

[0121] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for implementing an energy storage charging strategy based on a supercapacitor coupled lithium battery, characterized in that: include: Collect current and temperature data and conduct preliminary analysis; Establish a temperature prediction model and optimize the parameters of the temperature prediction model; For the lithium battery detection current and temperature data, select N sets of data with one-to-one correspondence between current value and temperature value; the temperature prediction model formula is expressed as: T=AI 3 (t)+BI 2 (t)+CI(t) Randomly generate m groups [ABC], and each group [ABC] inputs N groups of current into the formula; obtain the calculated temperature values ​​corresponding to the N groups; calculate the root mean square prediction error RMSE between the temperature value and the actual temperature value, which is expressed as: Where N represents the sample size, y n and Represent the actual value and predicted value at time n respectively; find the group with the smallest RMSE among m groups [ABC], assuming that the value of group j [ABC] [A j B j C j ], the corresponding RMSE is the smallest, then select [A j B j C j ], to [A j B j C j ]Do parameter optimization processing; Obtain the cumulative term parameters of temperature based on the cumulative effect of temperature; The cumulative parameters for obtaining the temperature include D and The source is the temperature accumulation term caused by the cumulative effect of temperature. During the charging process, the current changes from I a Evenly rise to I b , at this time the temperature changes from T a to T b , record the 100 points where the current and temperature correspond to each other during this process, expressed as (I1, T1), (I2, T2), (I3, T3)…, (I 100 ,T 100 ); The time sampling interval is Δt; the optimized [A j B j C j ] Put I1, I2, I3, ..., I 100 , Substitute into the temperature prediction model formula T = AI 3 (t)+BI 2 (t)+CI(t), and calculate the corresponding T'1, T'2, T'3, ..., T' 100 ; Actual values ​​T1, T2, T3, ..., T 100 with T'1, T'2, T'3, ..., T' 100 The difference is expressed as [Δ1,Δ2,Δ3,...,Δ 100 ], the difference is caused by the cumulative effect of temperature; Monitor and adjust temperature based on prediction results, and dynamically adjust charging strategies; The temperature monitoring and adjustment according to the prediction results includes obtaining the temperature accumulation item parameter of the cumulative effect according to the difference formula generated by the cumulative effect of the temperature. The difference formula is expressed as: I(t)=bt Among them, b represents the rate of increase of current. Using the cumulative effect formula, we can solve a set of D and The relationship formula is expressed as: In [Δ1,Δ2,Δ3,…,Δ 100 ] to find the minimum value Δ min , let Δ min Corresponding According to the minimum value calculation formula: You can solve D min ,make Solve all right Find the mean, which is the final Mean.

2. The method for implementing the energy storage charging strategy based on the supercapacitor coupled lithium battery according to claim 1, characterized in that The optimization operation includes: j B j C j ]Parameters are optimized; B j =rand(min(sigmoid(A j ),tanh(A j )),max(sigmoid(A j ),tanh(A j ))) Among them, Sigmoid() and tanh() represent activation functions; Wherein, k represents the number of cycles, and the initial k=1; After the optimization is completed, use the new [A j B j C j ] Determine whether RMSE is reduced by 30%. If not, perform the second step of optimization, define RMSE as the loss function, and perform optimization iteration until the parameters meet the RMSE reduction to the required threshold.

3. The method for implementing an energy storage charging strategy based on a supercapacitor coupled lithium battery according to claim 2, wherein: The preliminary analysis includes assuming that the lithium battery needs to be charged, the charging current is I(t), and the temperature naturally rises as charging progresses. The relationship between current and temperature is expressed as follows: Where T represents the surface temperature of the lithium-ion battery; m represents the battery mass; C h Indicates the thermal capacity of the battery; It represents the temperature rise coefficient of the battery open circuit voltage. Experiments have shown that the temperature rise coefficient is almost unaffected by temperature. I represents current; R0 represents internal resistance; U1 and U2 represent voltage coefficients; h represents heat transfer coefficient; A represents a constant to be determined; T ope Indicates operating temperature; The dynamic adjustment charging strategy includes assuming that charging starts now, the change of charging current over time is I=bt, and the upper limit of battery temperature is Tmax; deducing a prediction formula based on the relationship between current and temperature, which is expressed as: Analyze when the temperature reaches Tmax, and assume that t is calculated according to this formula max When time reaches Tmax, then at t max -The charging current is automatically reduced at δt. The formula for confirming δt is expressed as: At this time, the charging current changes from I(t)=bt to I(t)=e -qt , where q represents a coefficient that controls current attenuation.

4. A system for implementing an energy storage charging strategy based on a supercapacitor coupled lithium battery using the method according to any one of claims 1 to 3, characterized in that: The data analysis module collects the current and temperature data of the lithium battery during the charging process, analyzes the relationship between the current and temperature during the charging process, and determines the preliminary parameter range for the temperature prediction model; Prediction model module, which builds a temperature prediction model, fits the model using the collected data, and optimizes the parameters; Parameter acquisition module, records the data generated during the charging process, calculates the temperature accumulation item, and obtains the accumulation effect parameters; The charging strategy adjustment module monitors the temperature of the lithium battery in real time to ensure that it does not exceed the set temperature limit. When the predicted temperature is about to be reached, the charging current is adjusted in advance.

5. A computer device comprising: A memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the method for implementing the energy storage charging strategy based on the super-capacitor coupled lithium battery as described in any one of claims 1-3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the method for implementing an energy storage charging strategy based on a super-capacitor coupled lithium battery as described in any one of claims 1 to 3 are implemented.

Images