Energy storage battery charging protection method, device, equipment and storage medium

Abstract

The present invention belongs to the field of battery detection technology and discloses a charging protection method, device, equipment and storage medium for an energy storage battery. The present invention obtains the current charging power of the energy storage battery at the current detection moment, the current battery temperature and the current ambient temperature of the location where the energy storage battery is located, obtains the current heat dissipation efficiency based on the current battery temperature and the current ambient temperature, inputs the current charging power and the current heat dissipation efficiency into a power prediction model to predict the charging power, and obtains the predicted charging power of the energy storage battery at the next detection moment. When the predicted charging power is greater than the preset warning charging power, the current charging power is limited. The present invention determines the temperature dissipation of the current battery during the charging process by judging the temperature reached by the battery due to heat generation during charging and the current ambient temperature, and then predicts and judges the future charging power, and adjusts the current charging power to achieve the purpose of charging protection.

Description

Technical Field

[0001] The present invention relates to the technical field of battery detection, and in particular to a charging protection method, device, equipment and storage medium for an energy storage battery. Background Art

[0002] Energy storage batteries are playing an increasingly important role in our daily lives, whether for home energy storage or outdoor camping. Due to their large capacity, they take a relatively long time to charge, increasing the likelihood of danger during the charging process. Currently, to ensure charging safety, charging voltage or current is typically monitored to ensure they do not exceed the rated current or voltage. However, this protection method has a certain lag and cannot proactively prevent potential dangers.

[0003] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of the present invention is to provide a charging protection method, device, equipment and storage medium for an energy storage battery, aiming to solve the technical problems of charging protection of energy storage batteries in the prior art.

[0005] To achieve the above object, the present invention provides a charging protection method for an energy storage battery, the method comprising the following steps:

[0006] Obtaining the current charging power of the energy storage battery at the current detection time, the current battery temperature, and the current ambient temperature at the location where the energy storage battery is located;

[0007] obtaining a current heat dissipation efficiency according to the current battery temperature and the current ambient temperature;

[0008] Inputting the current charging power and the current heat dissipation efficiency into a power prediction model to predict the charging power, thereby obtaining a predicted charging power of the energy storage battery at the next detection moment;

[0009] When the predicted charging power is greater than the preset warning charging power, the current charging power is limited.

[0010] Optionally, before inputting the current charging power and the current heat dissipation efficiency into a power prediction model to predict the charging power to obtain the predicted charging power of the energy storage battery at the next detection moment, the method further includes:

[0011] Collecting the charging power and battery temperature of the energy storage battery and the ambient temperature of the location where the energy storage battery is located within a preset collection period;

[0012] Obtaining heat dissipation efficiency according to the ambient temperature and the current temperature of the battery;

[0013] combining the charging power and the heat dissipation efficiency to obtain a charging data set;

[0014] An initial prediction model is trained according to the charging data set to obtain a power prediction model.

[0015] Optionally, obtaining the heat dissipation efficiency according to the ambient temperature and the current temperature of the battery includes:

[0016] Obtaining the ambient humidity and ambient temperature at the location of the energy storage battery;

[0017] Obtaining a temperature difference based on the ambient temperature and the current temperature of the battery;

[0018] The heat dissipation efficiency is obtained according to the temperature difference and the ambient humidity.

[0019] Optionally, the training of the initial prediction model according to the charging data set to obtain the power prediction model includes:

[0020] Normalizing the charging data in the charging data set to obtain normalized charging data;

[0021] Arrange the normalized charging data in random order, and input the arranged normalized charging data into an average pooling layer;

[0022] Obtaining a predicted battery temperature based on the heat dissipation efficiency in the charging data set and the current temperature;

[0023] obtaining a normalized matrix according to the predicted battery temperature and the current power;

[0024] Obtaining a correlation coefficient matrix from the standardized matrix;

[0025] Performing dimensionality reduction according to the correlation coefficient matrix to obtain a dimensionality-reduced data set;

[0026] The initial prediction model is trained according to the dimension reduction data set to obtain a power prediction model.

[0027] Optionally, the training the initial prediction model according to the dimension reduction data set to obtain a power prediction model further includes:

[0028] Inputting the dimension-reduced data set into an initial prediction model, causing the initial prediction model to iterate according to a weight coefficient matrix, a bias vector, and an activation function, and recording the number of iterations;

[0029] When the number of iterations is equal to the preset number of iterations, the iteration is stopped to obtain iterative data;

[0030] The iterative data is transmitted to the hidden layer for training to obtain a power prediction model.

[0031] Optionally, after transmitting the iterative data to the hidden layer for training to obtain a power prediction model, the method further includes:

[0032] Inputting a test data set into the power prediction model to obtain a test prediction value;

[0033] Comparing the test prediction value with the true value in the test data set to obtain an error value;

[0034] Obtaining a compensation coefficient according to the error value and the true value;

[0035] The power prediction model is calibrated according to the compensation coefficient to obtain a calibrated power prediction model.

[0036] Optionally, when the predicted charging power reaches a preset warning charging power, limiting the current charging power includes:

[0037] Obtaining excess power based on the predicted charging power and the preset warning charging power;

[0038] Obtaining a limiting voltage according to the excess power and the current temperature of the energy storage battery;

[0039] The current charging voltage is adjusted to a safe voltage according to the limit voltage, and the current charging power is limited.

[0040] In addition, to achieve the above-mentioned object, the present invention further provides a charging protection device for an energy storage battery, the charging protection device for the energy storage battery comprising:

[0041] A battery detection module is used to obtain the current charging power of the energy storage battery at the current detection time, the current battery temperature, and the current ambient temperature of the location where the energy storage battery is located;

[0042] an environment detection module, configured to obtain a current heat dissipation efficiency based on the current battery temperature and the current ambient temperature;

[0043] a power prediction module, configured to input the current charging power and the current heat dissipation efficiency into a power prediction model to predict the charging power, thereby obtaining a predicted charging power of the energy storage battery at the next detection moment;

[0044] The charging protection module is used to limit the current charging power when the predicted charging power is greater than the preset warning charging power.

[0045] In addition, to achieve the above-mentioned objectives, the present invention also proposes a charging protection device for an energy storage battery, wherein the charging protection device for the energy storage battery comprises: a memory, a processor, and a charging protection program for the energy storage battery stored in the memory and executable on the processor, wherein the charging protection program for the energy storage battery is configured to implement the steps of the charging protection method for the energy storage battery as described above.

[0046] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a charging protection program for an energy storage battery is stored. When the charging protection program for the energy storage battery is executed by a processor, the steps of the charging protection method for the energy storage battery described above are implemented.

[0047] The present invention obtains the current charging power, current battery temperature, and current ambient temperature of the energy storage battery at the current detection moment, obtains the current heat dissipation efficiency based on the current battery temperature and the current ambient temperature, inputs the current charging power and the current heat dissipation efficiency into a power prediction model to predict the charging power, and obtains the predicted charging power of the energy storage battery at the next detection moment. When the predicted charging power is greater than the preset warning charging power, the current charging power is limited. The present invention determines the temperature loss of the current battery during the charging process and the heat generation of the current power by judging the temperature reached due to heat generation during battery charging and the current ambient temperature, thereby predicting and judging the future charging power and adjusting the current charging power to achieve the purpose of charging protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a structural diagram of a charging protection device for an energy storage battery in a hardware operating environment involved in an embodiment of the present invention;

[0049] Figure 2 This is a flow chart of a first embodiment of a charging protection method for an energy storage battery according to the present invention;

[0050] Figure 3 A schematic diagram of the corresponding relationship between battery power and charging power in an embodiment of a charging protection method for an energy storage battery of the present invention;

[0051] Figure 4 This is a flow chart of a first embodiment of a charging protection method for an energy storage battery according to the present invention;

[0052] Figure 5 This is a structural block diagram of the first embodiment of the charging protection device for the energy storage battery of the present invention.

[0053] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0054] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0055] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of the charging protection device for the energy storage battery in the hardware operating environment involved in the embodiment of the present invention.

[0056] like Figure 1 As shown, the charging protection device of the energy storage battery may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 1003 may optionally include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0057] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the charging protection device of the energy storage battery, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0058] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a charging protection program for the energy storage battery.

[0059] exist Figure 1In the charging protection device of the energy storage battery shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the charging protection device of the energy storage battery of the present invention can be set in the charging protection device of the energy storage battery. The charging protection device of the energy storage battery calls the charging protection program of the energy storage battery stored in the memory 1005 through the processor 1001 and executes the charging protection method of the energy storage battery provided in the embodiment of the present invention.

[0060] The embodiment of the present invention provides a charging protection method for an energy storage battery, referring to Figure 2 , Figure 2 The figure is a flow chart of a first embodiment of a charging protection method for an energy storage battery according to the present invention.

[0061] In this embodiment, the charging protection method of the energy storage battery includes the following steps:

[0062] Step S10: obtaining the current charging power of the energy storage battery at the current detection moment, the current battery temperature, and the current ambient temperature of the location where the energy storage battery is located.

[0063] It should be noted that the executor of this embodiment is the charging protection device of the energy storage battery, wherein the charging protection device of the energy storage battery has functions such as data processing, data communication and program running. The charging protection device of the energy storage battery can be an integrated controller, a control computer and other devices. Of course, it can also be other devices with similar functions, and this embodiment does not limit this.

[0064] It can be understood that the current charging power refers to the charging power at the detection time during the battery charging process. The charging power can be obtained directly or by obtaining the current charging voltage and charging current. The current battery temperature refers to the temperature of the battery at the detection time. The current ambient temperature refers to the surrounding ambient temperature when the battery is charging.

[0065] It should be understood that when energy storage batteries are charging, due to the internal resistance of the energy storage batteries, a certain amount of heat will be generated during charging. The continuous accumulation of heat will cause the temperature of the battery to continue to rise. If the rate of heat accumulation inside the battery is higher than the rate of heat dissipation during the battery charging process, the temperature inside the battery will continue to rise, which may lead to dangerous situations such as battery explosion.

[0066] In a specific implementation, the charging protection device can monitor the energy storage battery currently being charged, and can collect relevant parameters of the battery according to a preset collection frequency. For example, the charging device can detect the charging power, current charging temperature, and current ambient temperature of the energy storage battery once per second. Of course, the collection frequency for detecting the energy storage battery can be reasonably set according to actual conditions, preferably once per second. When collecting the current charging power of the energy storage battery, the charging current and charging voltage at this time can be obtained, and the current charging power can be obtained based on the relationship between power, current and voltage; in addition, the temperature of the energy storage battery being charged and the ambient temperature in the current charging environment can be obtained through the temperature sensing device of the charging protection device. Reference Figure 3 , Figure 3 The corresponding relationship between battery power and charging power. When obtaining the charging power of the energy storage battery, you can first obtain the current battery power of the battery, and then determine the current charging power based on the corresponding relationship between the remaining battery power and the charging power.

[0067] Step S20: obtaining a current heat dissipation efficiency according to the current battery temperature and the current ambient temperature.

[0068] It should be noted that heat dissipation efficiency refers to the efficiency of heat transfer from a higher temperature object to a lower temperature object during heat exchange. Since the charging environment of the energy storage battery is a daily charging environment with many changes, the heat dissipation efficiency will vary greatly with different charging time and location.

[0069] In practice, heat dissipation is a specific manifestation of heat transfer, specifically the transfer of heat from a high-temperature object to a low-temperature object. Before the energy storage battery begins charging, it remains in a stable environment for a long time, and the battery temperature is consistent with the current ambient temperature. When the energy storage battery begins charging, heat begins to form inside the battery, causing the battery temperature to gradually rise. As the temperature rises, some heat is transferred to the surrounding environment, causing the battery temperature to drop. When charging under normal conditions, the rate of heat generation is higher than the rate of heat dissipation. Overall, the battery temperature rises slowly. As the battery and ambient temperatures continue to rise, the temperature difference between the two gradually increases, the rate of heat transfer also increases, and the heat dissipation efficiency also increases. Therefore, at a certain detection moment, since the current ambient temperature and the current charging temperature of the battery can be obtained, the temperature difference between the current charging temperature and the ambient temperature can be calculated. Factors related to heat dissipation efficiency also depend on the heat transfer medium. Under normal charging conditions, when no heat dissipation device is attached, the heat transfer medium is air. The heat transfer coefficient of air can be found and used based on existing records to calculate the heat dissipation efficiency. The specific calculation formula is:

[0070]

[0071] Where η is the heat dissipation efficiency, k is the heat transfer coefficient, S is the contact area, ΔT is the temperature difference between the current charging temperature and the ambient temperature, and Δt is the detection time interval.

[0072] Furthermore, the step S20 further includes the following steps:

[0073] Obtaining the ambient humidity and ambient temperature at the location of the energy storage battery;

[0074] Obtaining a temperature difference based on the ambient temperature and the current temperature of the battery;

[0075] The heat dissipation efficiency is obtained according to the temperature difference and the ambient humidity.

[0076] It is understandable that the charging environment of the battery is not static. Due to the charging location and the current weather conditions, the actual heat dissipation capacity of the air is different. Therefore, the actual heat dissipation efficiency needs to be further determined.

[0077] In a specific implementation, when the ambient temperature of the energy storage battery is obtained, the current ambient humidity can also be detected. The ambient humidity can reflect the water vapor content in the air in the current environment. Since the specific heat capacity of water is greater than that of air, when the humidity in the air increases, its heat dissipation ability will be stronger. When calculating the heat dissipation efficiency, the temperature difference between the battery and the environment at this time can be calculated based on the ambient temperature and the current temperature of the battery. At the same time, the actual heat transfer coefficient of the current environment can be determined based on the heat transfer coefficient of the air, the heat transfer coefficient of the water, and the current ambient humidity. The specific implementation method is: determine the water vapor content in the current air based on the obtained ambient humidity, and then obtain the molar fraction of water vapor in the air based on the water vapor content. At the same time, the molar fraction of dry air in the air can also be obtained. The actual heat transfer coefficient in the current environment is obtained based on the molar fraction of dry air in the air, the molar fraction of water vapor in the air, and the heat transfer coefficient between dry air and water vapor. The calculation formula for the actual heat transfer coefficient is:

[0078]

[0079] Among them, K is the actual heat transfer coefficient, N a is the mole fraction of dry air in air, N w is the mole fraction of water vapor in the air, k a is the heat transfer coefficient of dry air, k w is the heat transfer coefficient of moist air, A aw is the dry air-water vapor combination factor, A wais the water vapor-dry air combination factor. After obtaining the actual heat transfer coefficient, the current heat transfer coefficient can be substituted into the heat dissipation efficiency calculation formula to obtain the heat dissipation efficiency under the current environment.

[0080] Step S30: Inputting the current charging power and the current heat dissipation efficiency into a power prediction model to predict the charging power, thereby obtaining the predicted charging power of the energy storage battery at the next detection moment.

[0081] It should be noted that the power prediction model is a neural network model obtained through training, which can predict the charging power at the next detection time based on the current charging power and the current heat dissipation efficiency.

[0082] In a specific implementation, the power prediction model can perform power prediction based on the received current charging power and the current heat dissipation power. The specific implementation method is as follows: based on the heat dissipation efficiency and the current temperature of the battery, the temperature of the battery at a future moment can be predicted. This embodiment uses the prediction of the next detection moment as an example for explanation. When performing the battery temperature at the next detection moment, it is necessary to treat the current detection moment as static, that is, the heat dissipation efficiency will not change within the next detection cycle. At this time, the predicted temperature for the next detection moment can be calculated based on the current heat dissipation efficiency and the current temperature of the battery. Based on the predicted temperature as a reference, a predicted temperature difference can be obtained based on the predicted temperature and the current temperature. The change in the internal resistance of the battery is calculated based on the predicted temperature difference, and then the change in voltage or current during the charging process is obtained. Since the charging mode of the battery changes from constant current to constant voltage during the charging process, another changed voltage value or current value is determined based on the current charging mode. The current charging mode of the battery can be determined by monitoring historical voltage or current data. If the voltage begins to become a fixed value or the current begins to change, it can be considered that the charging mode has changed. When the internal resistance of the battery changes, it will cause one of the physical quantities of voltage or current during the charging process to change. Taking the constant voltage mode as an example, when the temperature rises, the internal resistance of the battery will decrease, and the decrease in the internal resistance of the battery will cause the charging current to increase. According to the power calculation method, when the voltage is constant, the increase in current will lead to an increase in power. If the voltage increases, the risk of battery charging will increase. Therefore, the change in the internal resistance of the battery is obtained based on the change in temperature, and the power at the next detection moment can be predicted.

[0083] Step S40: When the predicted charging power is greater than the preset warning charging power, the current charging power is limited.

[0084] It should be noted that, since the battery charging power may fluctuate, in order to avoid being too sensitive to the battery charging protection, the warning charging power will be set slightly larger than the current normal charging power when setting the warning charging power. The specific numerical setting is set and adjusted according to actual needs, and this embodiment does not limit this.

[0085] In a specific implementation, the power prediction model generates a predicted charging power after predicting the power at the next detection moment. After obtaining the predicted charging power, the current predicted charging power needs to be determined. If the current predicted charging power value exceeds the preset warning charging power, the current charging voltage or charging current can be adaptively limited to slightly reduce the battery charging power, thereby accelerating the heat dissipation of the battery and ensuring the safety of battery charging. In addition, when the predicted charging power exceeds the preset warning charging power, an alarm can be issued to alert technicians to conduct troubleshooting and evacuate unauthorized personnel, further ensuring personal safety.

[0086] Furthermore, the step S40 further includes the following steps:

[0087] Obtaining excess power based on the predicted charging power and the preset warning charging power;

[0088] Obtaining a limiting voltage according to the excess power and the current temperature of the energy storage battery;

[0089] The current charging voltage is adjusted to a safe voltage according to the limit voltage, and the current charging power is limited.

[0090] It should be noted that the excess power refers to the difference between the predicted charging power and the warning charging power at the current moment, that is, the power value that exceeds the warning charging power.

[0091] In a specific implementation, the predicted charging power is subtracted from the warning charging power at the current moment to obtain the excess power, and the current battery internal resistance is obtained based on the current battery temperature. Since the temperature change will not occur suddenly, it can be assumed that the internal resistance of the battery will not change during this time. Therefore, when the voltage is constant, the corresponding current is also a fixed value. Therefore, when the charging power is limited, the charging voltage of the battery can be adjusted, and the excess voltage can be obtained based on the excess power and the current charging current. The excess voltage is the voltage value that makes the current charging power exceed the warning charging power. When performing voltage limitation, the current charging voltage can be subtracted from the excess voltage. The obtained voltage can be called a safe voltage, which realizes the charging power limitation of the energy storage battery and realizes charging protection.

[0092] This embodiment obtains the current charging power, current battery temperature, and current ambient temperature of the energy storage battery at the current detection moment, obtains the current heat dissipation efficiency based on the current battery temperature and the current ambient temperature, inputs the current charging power and the current heat dissipation efficiency into a power prediction model to predict the charging power, and obtains the predicted charging power of the energy storage battery at the next detection moment. When the predicted charging power is greater than the preset warning charging power, the current charging power is limited. The present invention determines the temperature loss of the current battery during the charging process and the heat generation of the current power by judging the temperature reached due to heat generation during battery charging and the current ambient temperature, thereby predicting and judging the future charging power and adjusting the current charging power to achieve the purpose of charging protection.

[0093] In addition, an embodiment of the present invention further provides a storage medium storing a charging protection program for an energy storage battery. When the charging protection program for the energy storage battery is executed by a processor, the steps of the charging protection method for the energy storage battery described above are implemented.

[0094] Reference Figure 4 , Figure 4 This is a flow chart of a second embodiment of a charging protection method for an energy storage battery according to the present invention.

[0095] In this embodiment, the energy storage battery charging protection method further includes the following steps before step S30:

[0096] Step S301: collecting the charging power and battery temperature of the energy storage battery and the ambient temperature of the location where the energy storage battery is located within a preset collection period;

[0097] Step S302: obtaining heat dissipation efficiency according to the ambient temperature and the current temperature of the battery;

[0098] Step S303: combining the charging power and the heat dissipation efficiency to obtain a charging data set;

[0099] Step S304: training the initial prediction model according to the charging data set to obtain a power prediction model.

[0100] It should be noted that the collection period refers to the time interval between two detection times, and the charging data set refers to the heat dissipation efficiency obtained for the current battery temperature and the current ambient temperature during the charging process. The charging data set contains the current charging power of the battery and the corresponding heat dissipation efficiency, describing their corresponding relationship.

[0101] In a specific implementation, the temperature difference between the acquired ambient temperature and the current temperature of the battery is obtained, and the current heat dissipation efficiency is obtained by the above-mentioned calculation of the heat dissipation efficiency. At the same time, the current remaining battery capacity of the battery can be obtained, and the current actual charging power is obtained according to the correspondence between the remaining battery capacity and the charging power. The current charging power and the current heat dissipation efficiency are corresponded one by one, and several correspondences are combined to obtain a charging data set. The charging data set is input as the training value of the model into the initial prediction model for training, thereby obtaining a power prediction model.

[0102] Furthermore, training the initial prediction model on the charging data set to obtain a power prediction model includes the following steps:

[0103] Normalizing the charging data in the charging data set to obtain normalized charging data;

[0104] Arrange the normalized charging data in random order, and input the arranged normalized charging data into an average pooling layer;

[0105] Obtaining a predicted battery temperature based on the heat dissipation efficiency in the charging data set and the current temperature;

[0106] obtaining a normalized matrix according to the predicted battery temperature and the current power;

[0107] Obtaining a correlation coefficient matrix from the standardized matrix;

[0108] Performing dimensionality reduction according to the correlation coefficient matrix to obtain a dimensionality-reduced data set;

[0109] The initial prediction model is trained according to the dimension reduction data set to obtain a power prediction model.

[0110] In a specific implementation, the charging data in the charging data set is first normalized, and the charging data in the charging data set is mapped to a decimal between 0 and 1. The specific calculation method is to traverse the charging data in the charging data set and find the maximum and minimum values ​​therein. After obtaining the maximum and minimum values, the formula can be used to calculate the charging data.

[0111]

[0112] Normalize the data, where Y is the normalized data, X is the currently selected data, and X max is the maximum value in the charging data, X minThe minimum value in the charging data. The normalized data is arranged in random order, and the charging data of the battery is disrupted to avoid the failure of the prediction model training due to the regularity of the charging data. Discrete data is used for training to improve the training accuracy of the prediction model. After the normalized charging data is arranged in random order, the normalized data are input into the average pooling layer one by one, and the preset pooling window is used to move on the average pooling layer according to the preset step size to obtain the average value of each pooling layer, wherein the pooling window is preferably a 2×2 pooling window, and the step size is preferably 1, wherein the size and step size of the pooling window can be set according to actual conditions, and this embodiment does not impose any restrictions on this. After the average pooling layer, the current temperature in the obtained pooled value is simulated with the heat dissipation efficiency. It is assumed that the heat dissipation efficiency remains unchanged during the current heat dissipation process, and then the predicted temperature at the next moment at the current moment is obtained. After obtaining the predicted temperature, the predicted temperature is combined with the current power to obtain a matrix, and the matrix is ​​standardized to obtain a standardized matrix, which can significantly reduce the number of data processing times and speed up the matrix convergence. After obtaining the standardized matrix, according to the formula

[0113]

[0114] Calculate the correlation coefficient matrix R of the standardized matrix = (r ij ) m×n , where x i and y i are the predicted temperature and heat dissipation efficiency of the i-th data, and is the mean of the predicted temperature and the mean of the heat dissipation efficiency, n is the number of data, and r is the correlation coefficient between the predicted temperature and the heat dissipation efficiency, where |r| ≤ 1. When obtaining the correlation coefficient matrix, due to the high data dimension, the data dimension can be reduced. When reducing the dimension, the main data can be selected as the reduced-dimensional data by calculating the contribution rate and the cumulative contribution rate. The reduced-dimensional data is then used as the training value input value of the model to obtain the power prediction model.

[0115] Furthermore, when training the initial prediction model to obtain the power prediction model, the following steps are also included:

[0116] Inputting the dimension-reduced data set into an initial prediction model, causing the initial prediction model to iterate according to a weight coefficient matrix, a bias vector, and an activation function, and recording the number of iterations;

[0117] When the number of iterations is equal to the preset number of iterations, the iteration is stopped to obtain iterative data;

[0118] The iterative data is transmitted to the hidden layer for training to obtain a power prediction model.

[0119] In the specific implementation, the initial prediction model includes an input layer, a hidden layer and an output layer. The hidden layer contains a weight coefficient matrix, a bias vector and an activation function. For the initial prediction model, the input layer first obtains the reduced-dimensional data as the model input value, where the reduced-dimensional data includes charging power and heat dissipation efficiency. In the weight coefficient matrix, the weight value around the center value is first determined according to the preset fuzzy radius. The weight sum of the surrounding 8 data can be calculated first. When the weight sum is not 1, each weight value needs to be divided by the weight sum to obtain the final weight matrix. When training the model, the intermediate values ​​in the training process are shifted according to the bias vector to ensure the accuracy of the training. In addition, the activation function can use the Sigmoid function to map the variables to between (0,1). Each such process can be called an iteration. When making predictions for the initial prediction model, the predicted value obtained in the previous round can be re-input as a new input value into the prediction model for training until the number of completed iterations is equal to the preset number of iterations, and the power prediction model is obtained.

[0120] Furthermore, after the iterative data is transmitted to the hidden layer to train the power prediction model, the following steps are also included:

[0121] Inputting a test data set into the power prediction model to obtain a test prediction value;

[0122] Comparing the test prediction value with the true value in the test data set to obtain an error value;

[0123] Obtaining a compensation coefficient according to the error value and the true value;

[0124] The power prediction model is calibrated according to the compensation coefficient to obtain a calibrated power prediction model.

[0125] In a specific implementation, the power prediction model obtained after training is tested, and the input values ​​in the test data set are input into the power prediction model. A set of predicted power values ​​can be obtained through the power prediction model. The predicted power values ​​are compared with the true values ​​in the test data set to obtain error values. The error values ​​are tested to obtain a preset tolerance interval. If the predicted power value is within the preset tolerance interval, it means that the current predicted value meets expectations. If the current power prediction value is not within the preset tolerance interval, it means that there is a large error in the predicted value of the current power prediction model. At this time, it is necessary to obtain an error value based on the predicted value and the true value. When verifying again, the quality of the prediction model can be described based on the mean absolute error and the goodness of fit. The specific formula is as follows:

[0126]

[0127]

[0128] Among them, MAE is the mean absolute error, R 2 is the goodness of fit, n is the number of data in the test data set, is the test prediction value, y i is the true value of power, The smaller the MAE value is, the higher the R 2 The closer the value is to 1, the more accurate the prediction result is. The mean absolute error and the goodness of fit are compared with the preset tolerance interval. If they are within the tolerance interval, the current power prediction model is used as the final power prediction model. If they are not within the tolerance interval, the weight coefficient is corrected according to the error value and retrained until the predicted value of the power prediction model is within an acceptable range.

[0129] Reference Figure 5 , Figure 5 This is a structural block diagram of the first embodiment of the charging protection device for the energy storage battery of the present invention.

[0130] like Figure 5 As shown, the charging protection device of the energy storage battery proposed in the embodiment of the present invention includes:

[0131] The battery detection module 10 is used to obtain the current charging power of the energy storage battery at the current detection time, the current battery temperature and the current ambient temperature of the location where the energy storage battery is located;

[0132] An environment detection module 20 is configured to obtain a current heat dissipation efficiency based on the current battery temperature and the current ambient temperature;

[0133] a power prediction module 30 for inputting the current charging power and the current heat dissipation efficiency into a power prediction model to predict the charging power, thereby obtaining a predicted charging power of the energy storage battery at the next detection moment;

[0134] The charging protection module 40 is configured to limit the current charging power when the predicted charging power is greater than the preset warning charging power.

[0135] This embodiment obtains the current charging power, current battery temperature, and current ambient temperature of the energy storage battery at the current detection moment, obtains the current heat dissipation efficiency based on the current battery temperature and the current ambient temperature, inputs the current charging power and the current heat dissipation efficiency into a power prediction model to predict the charging power, and obtains the predicted charging power of the energy storage battery at the next detection moment. When the predicted charging power is greater than the preset warning charging power, the current charging power is limited. The present invention determines the temperature loss of the current battery during the charging process and the heat generation of the current power by judging the temperature reached due to heat generation during battery charging and the current ambient temperature, thereby predicting and judging the future charging power and adjusting the current charging power to achieve the purpose of charging protection.

[0136] In one embodiment, the power prediction module 30 is further used to collect the charging power, battery temperature and ambient temperature of the energy storage battery within a preset collection period; obtain the heat dissipation efficiency based on the ambient temperature and the current temperature of the battery; combine the charging power and the heat dissipation efficiency to obtain a charging data set; and train an initial prediction model based on the charging data set to obtain a power prediction model.

[0137] In one embodiment, the environmental detection module 20 is further used to obtain the ambient humidity and ambient temperature of the location of the energy storage battery; obtain the temperature difference based on the ambient temperature and the current temperature of the battery; and obtain the heat dissipation efficiency based on the temperature difference and the ambient humidity.

[0138] In one embodiment, the power prediction module 30 is further used to normalize the charging data in the charging data set to obtain normalized charging data; perform random arrangement according to the normalized charging data, and input the arranged normalized charging data into an average pooling layer; obtain a predicted battery temperature according to the heat dissipation efficiency in the charging data set and the current temperature; obtain a normalized matrix according to the predicted battery temperature and the current power; obtain a correlation coefficient matrix from the normalized matrix; perform dimensionality reduction according to the correlation coefficient matrix to obtain a reduced dimensionality data set; and train the initial prediction model according to the reduced dimensionality data set to obtain a power prediction model.

[0139] In one embodiment, the power prediction module 30 is also used to input the dimensionality reduction data set into the initial prediction model, so that the initial prediction model is iterated according to the weight coefficient matrix, the bias vector, and the activation function, and the number of iterations is recorded; when the number of iterations is equal to the preset number of iterations, the iteration is stopped to obtain iterative data; the iterative data is transmitted to the hidden layer for training to obtain a power prediction model.

[0140] In one embodiment, the power prediction module 30 is further used to input a test data set into the power prediction model to obtain a test prediction value; compare the test prediction value with the true value in the test data set to obtain an error value; obtain a compensation coefficient based on the error value and the true value; and calibrate the power prediction model based on the compensation coefficient to obtain a calibrated power prediction model.

[0141] In one embodiment, the charging protection module 40 is further used to obtain excess power based on the predicted charging power and the preset warning charging power; obtain a limiting voltage based on the excess power and the current temperature of the energy storage battery; and adjust the current charging voltage to a safe voltage based on the limiting voltage to limit the current charging power.

[0142] It should be understood that the above is only an example and does not constitute any limitation to the technical solution of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any limitation on this.

[0143] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the embodiment scheme, and no limitation is made here.

[0144] In addition, it should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0145] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0146] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, or of course by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0147] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A charging protection method for an energy storage battery, characterized in that: The charging protection method of the energy storage battery includes: Obtaining the current charging power of the energy storage battery at the current detection time, the current battery temperature, and the current ambient temperature at the location where the energy storage battery is located; obtaining a current heat dissipation efficiency according to the current battery temperature and the current ambient temperature; Inputting the current charging power and the current heat dissipation efficiency into a power prediction model to predict the charging power, thereby obtaining a predicted charging power of the energy storage battery at the next detection moment; When the predicted charging power is greater than the preset warning charging power, the current charging power is limited.

2. The method according to claim 1, wherein Before inputting the current charging power and the current heat dissipation efficiency into a power prediction model to predict the charging power to obtain the predicted charging power of the energy storage battery at the next detection moment, the method further includes: Collecting the charging power and battery temperature of the energy storage battery and the ambient temperature of the location where the energy storage battery is located within a preset collection period; Obtaining heat dissipation efficiency according to the ambient temperature and the current temperature of the battery; combining the charging power and the heat dissipation efficiency to obtain a charging data set; An initial prediction model is trained according to the charging data set to obtain a power prediction model.

3. The method according to claim 2, wherein The obtaining of the heat dissipation efficiency according to the ambient temperature and the current temperature of the battery includes: Obtaining the ambient humidity and ambient temperature at the location of the energy storage battery; Obtaining a temperature difference based on the ambient temperature and the current temperature of the battery; The heat dissipation efficiency is obtained according to the temperature difference and the ambient humidity.

4. The method according to claim 2, wherein The training of the initial prediction model according to the charging data set to obtain the power prediction model includes: Normalizing the charging data in the charging data set to obtain normalized charging data; Arrange the normalized charging data in random order, and input the arranged normalized charging data into an average pooling layer; Obtaining a predicted battery temperature based on the heat dissipation efficiency in the charging data set and the current temperature; Obtaining a standardized matrix according to the predicted battery temperature and the current charging power; Obtaining a correlation coefficient matrix from the standardized matrix; Performing dimensionality reduction according to the correlation coefficient matrix to obtain a dimensionality-reduced data set; The initial prediction model is trained according to the dimension reduction data set to obtain a power prediction model.

5. The method according to claim 4, wherein The step of training the initial prediction model according to the dimension reduction data set to obtain a power prediction model further includes: Inputting the dimension-reduced data set into an initial prediction model, causing the initial prediction model to iterate according to a weight coefficient matrix, a bias vector, and an activation function, and recording the number of iterations; When the number of iterations is equal to the preset number of iterations, the iteration is stopped to obtain iterative data; The iterative data is transmitted to the hidden layer for training to obtain a power prediction model.

6. The method according to claim 5, wherein After the iterative data is transmitted to the hidden layer for training to obtain a power prediction model, the method further includes: Inputting a test data set into the power prediction model to obtain a test prediction value; Comparing the test prediction value with the true value in the test data set to obtain an error value; Obtaining a compensation coefficient according to the error value and the true value; The power prediction model is calibrated according to the compensation coefficient to obtain a calibrated power prediction model.

7. The method according to any one of claims 1 to 6, wherein When the predicted charging power reaches the preset warning charging power, limiting the current charging power includes: Obtaining excess power based on the predicted charging power and the preset warning charging power; Obtaining a limiting voltage according to the excess power and the current temperature of the energy storage battery; The current charging voltage is adjusted to a safe voltage according to the limit voltage, and the current charging power is limited.

8. A charging protection device for an energy storage battery, characterized in that: The charging protection device of the energy storage battery includes: A battery detection module is used to obtain the current charging power of the energy storage battery at the current detection time, the current battery temperature, and the current ambient temperature of the location where the energy storage battery is located; an environment detection module, configured to obtain a current heat dissipation efficiency based on the current battery temperature and the current ambient temperature; a power prediction module, configured to input the current charging power and the current heat dissipation efficiency into a power prediction model to predict the charging power, thereby obtaining a predicted charging power of the energy storage battery at the next detection moment; The charging protection module is used to limit the current charging power when the predicted charging power is greater than the preset warning charging power.

9. A charging protection device for an energy storage battery, characterized in that: The device includes: a memory, a processor, and a charging protection program for an energy storage battery stored in the memory and executable on the processor. The charging protection program for the energy storage battery is configured to implement the steps of the charging protection method for the energy storage battery according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a charging protection program for the energy storage battery. When the charging protection program for the energy storage battery is executed by the processor, the steps of the charging protection method for the energy storage battery according to any one of claims 1 to 7 are implemented.

Images