Battery pack SOC value calculation method, battery pack, energy storage equipment and medium

Abstract

The invention belongs to the technical field of energy storage, and provides a battery pack SOC value calculation method, a battery pack, energy storage equipment and a medium. The method comprises the following steps: acquiring parameter information related to the SOC of the battery pack; building a mathematical model y (t) of the SOC value of the battery pack by using a neural network model according to the parameter information related to the SOC of the battery pack, and calculating an initial SOC value of the battery pack according to the mathematical model y (t); the humidity value of the current moment in the battery pack is obtained, the initial SOC value of the battery pack is corrected according to the humidity value of the current moment in the battery pack and the temperature value T (t) of the current moment of the battery pack, and the effective SOC value of the battery pack is obtained. Therefore, the stability and the safety of SOC calculation in a special environment can be improved, and the control capability of a user on the health state of the battery is enhanced.

Description

Technical Field

[0001] The present application belongs to the field of energy storage technology, and in particular relates to a method for calculating the SOC value of a battery pack, a battery pack, an energy storage device and a medium. Background Art

[0002] The state of charge (SOC) of a battery is an important parameter that describes the operating status of a battery. It is usually expressed as the ratio of the remaining battery power to the actual battery capacity. The battery SOC usually needs to be estimated through parameters such as the battery terminal voltage, charge and discharge current, and internal resistance. Users can use the battery SOC to determine the remaining power, which facilitates the control and management of the battery power.

[0003] During the discharge process of the battery, the battery voltage will decrease as the remaining power decreases. Correspondingly, the SOC will also continue to decrease as the remaining power decreases. However, during the decrease of the SOC, the SOC may drop suddenly. For example, the SOC may drop suddenly from a certain value to zero, resulting in abnormal power consumption and affecting the user's power consumption plan. Summary of the invention

[0004] The purpose of this application is to provide a method for calculating the SOC value of a battery pack, a battery pack, an energy storage device and a medium, aiming to solve the problem that the existing data collector cannot send its own device data to the server in a timely manner, which may cause the loss of important device data in the data collector.

[0005] A first aspect of an embodiment of the present application provides a method for calculating a battery pack SOC value, the method comprising:

[0006] Obtain parameter information related to the SOC of the battery pack; wherein the parameter information includes at least: the voltage value of the battery pack at the current moment, the voltage value at the previous moment, the current value at the current moment, the current value at the previous moment, the SOH value at the current moment, the SOC value at the previous moment, and the temperature value at the current moment;

[0007] Constructing a mathematical model y(t) of the SOC value of the battery pack using a neural network model according to the parameter information related to the SOC of the battery pack, and calculating an initial SOC value of the battery pack according to the mathematical model y(t);

[0008] The humidity value in the battery pack at the current moment is obtained, and the initial SOC value of the battery pack is corrected according to the humidity value in the battery pack at the current moment and the temperature value of the battery pack at the current moment to obtain the effective SOC value of the battery pack.

[0009] By adopting the above technical solutions, the calculation of the battery pack SOC value has been significantly improved. First, accurate data acquisition enables the system to track key parameters such as voltage, current and temperature in real time, ensuring the integrity and accuracy of basic data. Secondly, the complex dynamic changes of SOC are extracted using a neural network model. The model performs well in accuracy and response speed, providing reliable SOC prediction for battery management. This intelligent calculation not only improves the energy efficiency management of the battery, but also extends its service life. Finally, through the correction of environmental factors, such as the dynamic adjustment of SOC by humidity and temperature, the stability and safety of SOC calculation in special environments are further improved. This comprehensive and optimized calculation process not only improves the overall performance of the energy storage system, but also enhances the user's ability to control the health status of the battery.

[0010] A second aspect of an embodiment of the present application provides a device for calculating a battery pack SOC value, the device comprising:

[0011] An acquisition unit, used to acquire parameter information related to the SOC of the battery pack; wherein the parameter information includes at least: the voltage value of the battery pack at the current moment, the voltage value at the previous moment, the current value at the current moment, the current value at the previous moment, the SOH value at the current moment, the SOC value at the previous moment, and the temperature value at the current moment;

[0012] a calculation unit, configured to construct a mathematical model of the SOC value of the battery pack using a neural network model according to parameter information related to the SOC of the battery pack, and calculate an initial SOC value of the battery pack according to the mathematical model;

[0013] The correction unit is used to obtain the humidity value in the battery pack at the current moment, and correct the initial SOC value of the battery pack according to the humidity value in the battery pack at the current moment and the temperature value of the battery pack at the current moment to obtain the effective SOC value of the battery pack.

[0014] A third aspect of an embodiment of the present application provides an energy storage device, the energy storage device comprising:

[0015] Battery pack;

[0016] one or more processors; and

[0017] A memory for storing one or more programs, which, when executed by the one or more processors, enables the energy storage device to implement the method for calculating the SOC value as described in any one of claims 1 to 7.

[0018] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, a method for calculating an SOC value as described in any one of the above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flowchart of a method for calculating the SOC value of a battery pack provided in one embodiment of the present application;

[0020] Figure 2 A schematic diagram of a neural network structure applied to a method for calculating a battery pack SOC value provided in one embodiment of the present application;

[0021] Figure 3 A schematic diagram of the structure of a device for calculating the SOC value of a battery pack provided in one embodiment of the present application;

[0022] Figure 4 A schematic diagram of the structure of an energy storage device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0024] It should be noted that the terms "first" and "second" in the specification, claims and drawings of the present application are used to distinguish similar objects rather than to describe a specific order or sequence.

[0025] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0026] It should also be noted that the method disclosed in the embodiments of the present application or the method shown in the flowchart includes one or more steps for implementing the method. Without departing from the scope of the claims, the execution order of multiple steps can be interchangeable with each other, and some of the steps can also be deleted.

[0027] Some embodiments will be described below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and the state of charge (SOC) of the battery are important parameters for describing the operating state of the battery, which are often expressed as the ratio of the remaining battery power to the actual battery capacity. The battery SOC usually needs to be estimated by parameters such as the battery terminal voltage, charge and discharge current, and internal resistance. Users can judge the remaining power through the battery SOC, which facilitates the control and management of the battery power.

[0028] During the discharge process of the battery, the battery voltage will decrease as the remaining power decreases. Correspondingly, the SOC will also continue to decrease as the remaining power decreases. However, during the decrease of the SOC, the SOC may drop suddenly. For example, the SOC may drop suddenly from a certain value to zero, resulting in abnormal power consumption and affecting the user's power consumption plan.

[0029] The existing SOC calculation method is too simple, resulting in inaccurate calculated SOC value.

[0030] In order to solve the above technical problems, refer to Figure 1 As shown, an embodiment of the present application provides a method for calculating an SOC value, and the method includes steps S100-S300.

[0031] Step S100: Obtain parameter information related to the SOC of the battery pack; wherein the parameter information includes at least: the voltage value V(t) of the battery pack at the current moment, the voltage value V(t-1) at the previous moment, the current value I(t) at the current moment, the current value I(t-1) at the previous moment, the SOH value SOH(t) at the current moment, the SOC value SOC(t-1) at the previous moment, and the temperature value T(t) at the current moment.

[0032] Step S200: construct a mathematical model y(t) of the SOC value of the battery pack using a neural network model according to parameter information related to the SOC of the battery pack, and calculate an initial SOC value of the battery pack according to the mathematical model y(t).

[0033] Step S300: Obtain the current humidity value in the battery pack, and correct the initial SOC value of the battery pack according to the current humidity value in the battery pack and the current temperature value T(t) of the battery pack to obtain the effective SOC value of the battery pack.

[0034] In this embodiment, in step S100, in the energy storage battery pack, in order to accurately obtain the parameter information related to SOC, we can use a high-precision data acquisition system for real-time monitoring. First, the voltage sensor can be installed in the battery pack to realize continuous measurement of voltage changes, and the voltage value V(t) of the battery pack at the current moment and the voltage value V(t-1) at the previous moment can be obtained to capture the charging and discharging dynamics of the energy storage battery pack. At the same time, the Hall effect sensor is placed on the output line of the battery pack to monitor the current flow in real time, and the current value I(t) at the current moment and the current value I(t-1) at the previous moment can be obtained to provide support for the accurate calculation of SOC. The temperature value T(t) of the battery pack at the current moment can be monitored by multi-point thermocouples distributed in the battery pack to help identify changes in thermal characteristics. All parameter data are transmitted to the energy management system (Energy Management System, EMS) in real time through the wireless communication module and stored in the SQL database (Structured Query Language, SQL) for subsequent data analysis and SOC (State of Charge, remaining power) calculation. This method of setting up parameter information acquisition ensures that all data acquired has a high degree of accuracy and completeness.

[0035] In this embodiment, reference Figure 2 As shown, in step S200, a neural network model is used to construct a mathematical model y(t) of the SOC value of the battery pack. A dedicated neural network model can be developed. The neural network model includes: an input layer, a hidden layer, and an output layer. The mathematical model y(t) is used to predict the SOC of the energy storage battery. The input layer data used by the mathematical model include the voltage value V(t) of the battery pack at the current moment, the voltage value V(t-1) at the previous moment, the current value I(t) at the current moment, the current value I(t-1) at the previous moment, the SOH value SOH(t) at the current moment, the SOC value SOC(t-1) at the previous moment, and the temperature value T(t) at the current moment, etc., to capture complex dynamic changes. By training a large amount of data from historical charge and discharge cycles, the neural network adopts a network architecture and optimization methods suitable for energy storage applications, such as ReLU activation function and Adam optimization algorithm, to ensure that the model is robust and reliable. After multiple trainings, the model achieved an SOC prediction accuracy of less than 1% on the validation data set. After training, the model is integrated into the energy management system to read sensor data in real time and output the current initial SOC value, which is crucial to ensure the effective management and optimized operation of the energy storage system.

[0036] In this embodiment, in step S300, the humidity value of the battery pack at the current moment is introduced into the correction process of the energy storage battery SOC. To achieve this purpose, a SHT31D humidity sensor is arranged inside the battery, and the humidity data is transmitted through I 2 The C interface is regularly sent to the control unit. The data and temperature information are used together to correct the SOC calculation, and a correction model can be established to dynamically adjust the initial SOC value.

[0037] For example, when the humidity value at the current moment is higher than the first humidity threshold and the temperature value T(t) at the current moment is rising, the initial SOC value can be reduced by the first threshold to warn of possible thermal failure risks. By adjusting the model parameters in response to different environmental conditions, this correction mechanism not only improves the accuracy of SOC prediction, but also provides guarantees for the safe and efficient operation of the energy storage system.

[0038] In this embodiment, by implementing this three-step method, the calculation of the SOC value of the energy storage battery pack is significantly improved. First, accurate data acquisition enables the system to track key parameters such as voltage, current and temperature in real time, ensuring the integrity and accuracy of the basic data. Secondly, the complex dynamic changes of SOC are extracted using a neural network model. The model performs well in accuracy and response speed, providing reliable SOC prediction for battery management. This intelligent calculation not only improves the energy efficiency management of the battery, but also extends its service life. Finally, through the correction of environmental factors, such as the dynamic adjustment of SOC by humidity and temperature, the stability and safety of SOC calculation in special environments are further improved. This comprehensive and optimized calculation process not only improves the overall performance of the energy storage system, but also enhances the user's ability to control the health status of the battery.

[0039] In one embodiment, a mathematical model y(t) of the SOC value of the battery pack is constructed using a neural network model according to parameter information related to the SOC of the battery pack, including: determining the number of input layer nodes, the number of hidden layer nodes, and the number of output layer nodes of the neural network model according to the parameter information related to the SOC of the battery pack; the mathematical model y(t) of the SOC value of the battery pack is:

[0040]

[0041] Among them, w j (t) is the weight connecting the jth hidden layer node to the output layer node, O j (t) is the output of the jth hidden layer node, b is the threshold of the output layer node, w ji (t) is the weight connecting the i-th input layer node to the j-th hidden layer node, x i (t) is the input of the i-th node in the input layer, a jis the threshold of the jth hidden layer node, F is the hidden layer activation function, and y(t) is the output of the output layer node.

[0042] In this embodiment, according to the parameter information related to the battery pack SOC, the number of input layer nodes m of the neural network model is determined to be 7, the number of hidden layer nodes n is 12, and the number of output layer nodes is 1. In the calculation of the battery pack SOC, the design of the neural network model and the selection of parameters are crucial. The number of input layer nodes is set to 7 to fully reflect the battery status and environmental parameters, including current and historical voltage, current, temperature, humidity, as well as SOH, SOC, etc. The number of hidden layer nodes is set to 12, providing sufficient capacity to capture the complex nonlinear relationship between these input variables, thereby improving the accuracy of model prediction. The output layer uses 1 node to output the final SOC prediction value. This design makes the model concise and efficient, meeting the needs of real-time computing.

[0043] In one embodiment, this neural network model is used to calculate the SOC of the battery pack. The 7 nodes of the input layer receive real-time data from different sensors: 2 voltage value data, 2 current value data, 1 SOH value data, 1 SOC value data and 1 temperature data are digitized and input into the system. In order to obtain the best model performance, the constructed neural network is initialized for training, and the weights of the hidden layer and the output layer are continuously updated through convolution and back propagation using the operating data of the past year. The ReLU activation function is selected in this process, which can effectively solve the problem of gradient disappearance. The training results show that the model can predict the SOC within an error range of ±1%. In actual operation, this model is integrated into the energy management system (EMS). Through real-time data input and analysis, the SOC is corrected in real time, which improves the ability to prevent over-discharge, extends battery life, and improves the operating efficiency of the entire power station.

[0044] In one embodiment, the mathematical model y(t) is set as:

[0045] The weight w connecting the jth hidden layer node to the output layer node j (t), the threshold b of the output layer node, the weight w connecting the i-th input layer node to the j-th hidden layer node ji (t), and the threshold a of the jth hidden layer node j The specific parameters can be set in a pre-set manner.

[0046] In one embodiment, the weight w connecting the jth hidden layer node to the output layer node is j(t), these weights represent the influence of each hidden layer node on the output result. The weights are initialized by preliminary assumptions or based on historical data. The threshold b of the output layer node is used to adjust the activation level of the neuron, which is extracted from statistical historical data and dynamically adjusted during the model training process. The weight w connecting the i-th input layer node to the j-th hidden layer node ji (t), this weight reflects how the input parameters affect the hidden layer. The initialization can be done by random distribution, Xavier initialization, etc. to ensure the stability of the convergence process. The threshold a of the jth hidden layer node j The specific parameters of are used to adjust the responsiveness of each node in the hidden layer, and are usually preset based on experience or through trial and error.

[0047] In the application scenario of an energy storage battery pack, this mathematical model y(t) is used to improve the accuracy of SOC calculation. In the early stage of model building, a large number of experimental simulations were carried out to analyze the impact of various weights and threshold configurations on the accuracy of SOC prediction. The weights and thresholds were preliminarily set through historical operating data and cross-validation. The hidden layer adopts a 12-node structure and is continuously optimized within 200 charge and discharge cycles. The results show that the error range is about ±1%. Finally, the model is deployed in the intelligent energy management system, which can continue to self-adjust according to the battery performance during real-time operation, providing a long-term and reliable SOC evaluation mechanism.

[0048] In one embodiment, the initial SOC value of the battery pack is corrected according to the humidity value in the battery pack at the current moment and the temperature value T(t) of the battery pack at the current moment to obtain the effective SOC value of the battery pack, including:

[0049] According to the humidity value in the battery pack at the current moment and the temperature value T(t) of the battery pack at the current moment, the SOC correction mathematical model G(t) is constructed as follows:

[0050] G(t)=y(t)+β;

[0051] Among them, β is the correction model established according to the humidity value at the current moment and the temperature value T(t) at the current moment;

[0052] The modified model β is:

[0053]

[0054] Among them, H(t) is the humidity value at the current moment, T(t) is the temperature value T(t) at the current moment, ε1 is the correction factor of the SOC value, ε2 is the development coefficient of the humidity value at the current moment, and ε3 is the proportional coefficient of the humidity value at the current moment.

[0055] In this embodiment, temperature and humidity are used as correction conditions for the battery SOC because these two environmental factors have a profound impact on battery performance and life. Changes in temperature will directly affect the internal chemical reactions of the battery and the state of the electrolyte. At high temperatures, the chemical reactions of the battery are accelerated, which will accelerate its aging and capacity decay; while in low temperature environments, it may cause the battery activity to decrease and the output capacity to decrease. Changes in humidity are also not to be ignored. High humidity may cause condensation water to accumulate inside the battery, causing potential risks such as corrosion and circuit short circuits. Therefore, the introduction of temperature and humidity correction in the SOC calculation not only greatly improves the accuracy of SOC evaluation, but also the error range after optimization is within ±0.5%, which can more truly reflect the immediate state of the battery, and is crucial for adjusting the battery's charge and discharge strategy, thereby optimizing its performance and increasing its service life. In addition, this correction strategy also improves the safety of the system, reduces the risks to the battery caused by extreme environments, and ensures that the equipment can still operate stably and efficiently under a wide range of conditions. Through these measures, the reliability and efficiency of the energy storage system have been significantly improved, laying a safe foundation for long-term application.

[0056] In one embodiment, the method further includes: establishing a mathematical model F(X) of the hidden layer activation function:

[0057]

[0058] Among them, x is The value of .

[0059] Specifically, in this embodiment, based on the combination of dynamic neural network and adaptive weight particle swarm algorithm, weight coefficients and thresholds are added to each element from the input layer to the hidden layer and from the hidden layer to the output layer, and some calculations are increased to improve the accuracy of the results. By setting the mathematical model F(X) of the hidden layer activation function as a piecewise function, the problem of deep learning can be solved regardless of whether x is positive or negative, especially in the deep network. The advantages of simplicity and high computational efficiency and the lack of learning if the input is negative, the gradient is zero, and this part of the neurons may no longer learn, introduces an exponential function form when the input is negative.

[0060] In one embodiment, the data of the battery pack's current voltage value V(t), the previous voltage value V(t-1), the current current value I(t), the previous current value I(t-1), the current SOH value SOH(t), the previous SOC value SOC(t-1), and the current temperature value T(t) all need to be entered into Perform calculations. When the result is greater than 0, use the calculated value directly. When the calculated value is less than or equal to 0, use the value as x in e. (x-1)We use a piecewise function as the activation function of the hidden layer. This activation function ensures that the network can learn even if the input is negative. Specifically, when the input is negative, we introduce (x-1) . This design avoids the "dead neuron" problem and improves the performance of the model in the negative sample learning process. In practical applications, this enhanced design significantly improves the training efficiency and learning effect of the network, especially when processing highly diverse data sets, making the model have better generalization ability and stability.

[0061] In one embodiment, a mathematical model F(X) of the hidden layer activation function is established:

[0062]

[0063] Among them, x is The value of .

[0064] Specifically, in this embodiment, regardless of whether the value of x is calculated to be positive or negative, an activation function model is used, which can simplify the establishment of the model, simplify the calculation steps, and make the design and implementation of the neural network more intuitive. Secondly, a single activation function is usually more efficient in calculation, reducing the computational overhead in the reasoning process, thereby improving the response speed and overall performance of the system. This feature is particularly important in resource-constrained environments. In addition, the use of a single activation function can improve the stability of the network training process. Maintaining a consistent incentive mechanism means that the gradient update process is also more unified, which helps to increase the convergence speed and reduce the instability that may be encountered during training. A single activation function provides a consistent gradient direction to help the model reach the optimization goal faster in iterations. In terms of overall design, this method is both elegant and more efficient, making it the preferred strategy for developers in many situations.

[0065] In one embodiment, the weight w connecting the jth hidden layer node to the output layer node is j (t), the weight w connecting the i-th input layer node to the j-th hidden layer node ji (t), the threshold value b of the output layer node, the threshold value a of the jth hidden layer node j The determination method of is determined by particle swarm algorithm.

[0066] In this embodiment, in the SOC prediction model of the battery pack, we use the particle swarm algorithm to optimize the weights and thresholds of the neural network. First, initialize multiple particles, each particle represents a possible combination of weights and thresholds. The fitness of each particle is evaluated by calculating the error of the combination for SOC prediction.

[0067] In one embodiment, the model inputs the collected voltage, current, temperature and other data into the network, and the hidden layer processes them using optimized weights and thresholds to output the predicted SOC value. The particle swarm algorithm iteratively updates the model based on its performance in real data. Each particle adjusts its position and speed based on its own historical best position (pBest) and global best position (gBest) to seek the optimal parameter combination.

[0068] Through hundreds of iterations, the particle swarm algorithm successfully found the best weights and thresholds, which significantly reduced the SOC prediction error and significantly improved the accuracy of the model. This optimization enables the battery management system to effectively predict the SOC under different environmental conditions, improving the reliability and life of the battery operation. Through the application of the particle swarm algorithm, the SOC prediction of the battery pack has become more accurate, providing strong support for the efficient management of electric vehicles and energy storage systems.

[0069] In one embodiment, specifically, in this solution, the input layer has 7 neurons, the hidden layer has 12 neurons, and the output layer has 1 neuron, so the number of weight coefficients that need to be determined is 84.

[0070] This scheme uses the particle swarm method to determine the weight coefficients of each parameter. In the standard particle swarm optimization algorithm, each particle represents a possible solution in the solution space (that is, the position of a particle represents a set of weight coefficients), and the particle updates its position and speed by tracking the individual historical best position and the historical best position of the entire group.

[0071] For example, we need to constantly update w in the above j (t), w ji (t) (represents each weight coefficient) to improve the accuracy of our calculation results. Update the individual speed and position of the particle swarm according to the following formula:

[0072] v i，j (t+1)=WV i，j (t)+c1r1(P i，j -x i，j (t))+c2r2(P g，j -x i，j (t));

[0073] x i，j (t+1)=x i，j (t)+v i，j (t+1),j=1,2,…,d;

[0074] Among them, v i，j (t+1) represents the speed at time t+1, x i，j(t+1) represents the position at the corresponding time t+1, c1 and c2 are positive learning factors, c1 is set to 1.5, c2 can be set to 2.0, r1 and r2 are random numbers (for example, any random numbers can be used), assuming that in the d-dimensional search space, x = (x1, x2, ..., x n ) is a population of n particles, where x i =(x i1 , x i2 , ..., x id ) is a d-dimensional vector, which represents the position of the i-th particle in the d-dimensional space and also represents a potential solution to the problem (i.e., the position of a particle represents a set of weight coefficients). i =(v i1 , v i2 , ..., v id ) represents the velocity of the ith particle. i =(p i1 , p i2 , ..., p id ) and p g =(p g1 , p g2 , ..., p gd ) are the extreme value of the ith particle and the global extreme value of the population, respectively.

[0075] Each particle position x i The corresponding fitness value can be calculated according to the objective function, and the individual speed and position p_best can be updated according to the following formula. W is the inertia weight, which determines how much the particle inherits the speed of the previous particle at the next moment. The W value is fixed in the classic particle swarm algorithm. Since a larger W is conducive to the algorithm to pick out the local optimal point, it is convenient for global search, while a smaller W is conducive to improving the search accuracy. Through reasonable initialization and intelligent adaptive strategies, it can be improved by the adaptive weight method. During the algorithm, the nonlinear dynamic inertia coefficient formula is used to adjust the inertia weight, so that the particles can move closer to the optimal search area at the maximum speed to find a global optimal fitness g_best.

[0076] In one embodiment, the inertia weight W is determined by the following model:

[0077]

[0078] Where T is the total number of iterations, t is the current number of iterations, and W max is the maximum limit of the inertia weight, which is generally set to 0.9. min It is the minimum limit of inertia weight, which is generally taken as 0.4.

[0079] In one embodiment, the inertia weight W is determined by the following model:

[0080]

[0081] In one embodiment, the inertia weight W is determined by the following model:

[0082]

[0083] In this embodiment, this inertia weight model is used to control the search capability of the particle swarm algorithm. max Smoothly decreases to W min , the model can maintain a large search range in the early stage, improve the global search capability, and enhance the accuracy and convergence speed of local search in the later stage. This design not only improves the accuracy of SOC prediction, but also ensures that the particle swarm algorithm is always in an optimized state during the entire iteration process, making the SOC prediction of the battery pack more stable and accurate.

[0084] In one embodiment, a method for obtaining the SOC value SOC(t-1) at the previous moment is: integrating the current value I(t-1) at the previous moment, obtaining the amount of charge or discharge at the previous moment after integration, determining the change in the SOC of the battery pack based on the ratio of the amount of charge or discharge and the capacity of the battery pack, and determining the SOC value SOC(t-1) of the battery pack at the previous moment according to the change in SOC.

[0085] In one embodiment, we use the current integration method to accurately calculate the SOC value SOC(t-1) at the previous moment. Specifically, by installing a Hall effect current sensor at the output end of the battery pack to monitor the current in real time, the current change data per second can be accurately recorded. Then, numerical integration is performed to accurately calculate the charging or discharging power of the battery in a specific time period. Then, these power changes are compared with the total capacity of the battery pack to determine the change in SOC. By subtracting this change from the current SOC value, we can deduce the SOC value SOC(t-1) at the previous moment. This calculation method not only improves the estimation accuracy of SOC, but also ensures the continuity of SOC data, thereby optimizing the battery charging and discharging strategy. Accurate SOC information is of great help in extending battery life and optimizing energy management. With this precise method, the battery pack can maintain efficient and safe operation under various usage conditions, reduce the risks of over-discharge or overcharging, and provide users with more reliable and lasting power support.

[0086] The present application also provides a battery pack SOC value calculation device 100, referring to Figure 3 As shown, the computing device includes: an acquisition unit 110 , a computing unit 120 and a correction unit 130 .

[0087] The acquisition unit 110 is used to acquire parameter information related to the SOC of the battery pack; wherein the parameter information at least includes: a voltage value V(t) of the battery pack at a current moment, a voltage value V(t-1) at a previous moment, a current value I(t) at a current moment, a current value I(t-1) at a previous moment, a SOH value SOH(t) at a current moment, a SOC value SOC(t-1) at a previous moment, and a temperature value T(t) at a current moment;

[0088] A calculation unit 120, configured to construct a mathematical model y(t) of the SOC value of the battery pack using a neural network model according to parameter information related to the SOC of the battery pack, and calculate an initial SOC value of the battery pack according to the mathematical model y(t);

[0089] The correction unit 130 is used to obtain the humidity value in the battery pack at the current moment, and correct the initial SOC value of the battery pack according to the humidity value in the battery pack at the current moment and the temperature value T(t) of the battery pack at the current moment to obtain the effective SOC value of the battery pack.

[0090] The device for calculating the SOC value of a battery pack provided in this embodiment can execute the above method embodiment. Its implementation principle is similar to some specific implementation methods and technical effects of the method for calculating the SOC value in the above embodiment, and will not be repeated here.

[0091] The present application also provides an energy storage device, referring to Figure 4 As shown, the energy storage device 200 includes: a battery pack 201; one or more processors; and a memory, the memory being used to store one or more programs. When the one or more programs are executed by one or more processors, the energy storage device implements a method for calculating an SOC value such as any one of the above.

[0092] In one embodiment, reference Figure 4 As shown, the energy storage device 200 may include, but is not limited to, a battery pack 201, a memory 202, a processor 203, an input / output (I / O) interface 204, a bus 205, and a communication module 206. The processor 203 is coupled to the communication module 206, the memory 202, and the I / O interface 204 via the bus 205.

[0093] The communication module 206 may include a wired communication module and / or a wireless communication module. The wired communication module may provide one or more wired communication solutions such as Universal Serial Bus (USB), Controller Area Network (CAN), etc. The wireless communication module may provide one or more wireless communication solutions such as Wireless Fidelity (Wi-Fi), Bluetooth (BT), mobile communication network, Frequency Modulation (FM), near field communication technology (NFC), infrared technology (IR), etc.

[0094] The memory 202 can be used to store computer-readable instructions and / or modules. The processor 203 implements various functions of the energy storage device 200 by running or executing the computer-readable instructions and / or modules stored in the memory 202 and calling the data stored in the memory 202. The memory 202 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the energy storage device 200, etc. The memory 202 can include non-volatile and volatile memories, such as: a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other storage devices.

[0095] The memory 202 may be an external memory and / or an internal memory of the energy storage device 200. Furthermore, the memory 202 may be a memory in a physical form, such as a memory stick, a TF card (Trans-flash Card), and the like.

[0096] The processor 203 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 203 is the computing core and control center of the energy storage device 200, and uses various interfaces and lines to connect various parts of the entire energy storage device 200, and executes the operating system of the energy storage device 200 and various installed applications, program codes, etc.

[0097] Exemplarily, the computer-readable instructions may be divided into one or more modules / sub-modules / units, one or more modules / sub-modules / units are stored in the memory 202, and executed by the processor 203 to complete the present application. One or more modules / sub-modules / units may be a series of computer-readable instruction segments capable of completing a specific function, and the computer-readable instruction segments are used to describe the execution process of the computer-readable instructions in the energy storage device 200.

[0098] If the module / unit integrated in the energy storage device 200 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and the computer-readable instructions that can be completed by instructing the relevant hardware through computer-readable instructions can be stored in a computer-readable storage medium, and when the computer-readable instructions are executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented.

[0099] The computer-readable instructions include computer-readable instruction codes, which may be in source code form, object code form, executable files, or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer-readable instruction codes, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM).

[0100] The memory 202 in the energy storage device 200 stores computer-readable instructions, and the processor 203 can execute the computer-readable instructions stored in the memory 202 to implement the transportation path planning method in the above embodiment.

[0101] Specifically, the specific implementation method of the processor 203 for the above-mentioned computer-readable instructions can refer to the description of the relevant steps in the above-mentioned embodiments, which will not be repeated here.

[0102] The I / O interface 204 is used to provide a channel for user input or output. For example, the I / O interface 204 can be used to connect various input and output devices, such as a controller, an inverter, a storage device, a smart device, a mouse, a keyboard, a touch device, a display screen, etc., so that the user can enter information or visualize the information.

[0103] The bus 205 is at least used to provide a channel for mutual communication among the battery pack 201 , the communication module 206 , the memory 202 , the processor 203 , and the I / O interface 204 in the energy storage device 200 .

[0104] It is understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the energy storage device 200. In other embodiments of the present application, the energy storage device 200 may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0105] An embodiment of the present application further provides a computer-readable storage medium, which stores at least one instruction. When the at least one instruction is executed by a processor, a method for calculating an SOC value as described above is implemented.

[0106] The computer-readable storage medium may be the internal memory of the energy storage device 200 of the above-mentioned embodiment, such as the hard disk or memory of the energy storage device 200. The computer-readable storage medium may also be an external storage device of the energy storage device 200, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the energy storage device 200.

[0107] In one embodiment, the computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the energy storage device 200, etc.

[0108] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0109] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0110] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0111] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

[0112] Each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0113] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Claims

1. A method for calculating the SOC value of a battery pack, characterized in that: The method comprises: Obtain parameter information related to the SOC of the battery pack; wherein the parameter information includes at least: the voltage value of the battery pack at the current moment, the voltage value at the previous moment, the current value at the current moment, the current value at the previous moment, the SOH value at the current moment, the SOC value at the previous moment, and the temperature value at the current moment; Constructing a mathematical model y(t) of the SOC value of the battery pack using a neural network model according to the parameter information related to the SOC of the battery pack, and calculating an initial SOC value of the battery pack according to the mathematical model y(t); The humidity value in the battery pack at the current moment is obtained, and the initial SOC value of the battery pack is corrected according to the humidity value in the battery pack at the current moment and the temperature value of the battery pack at the current moment to obtain the effective SOC value of the battery pack.

2. The method for calculating the SOC value of a battery pack according to claim 1, characterized in that: The method of constructing a mathematical model y(t) of the battery pack SOC value by using a neural network model according to the parameter information related to the battery pack SOC includes: Determine the number of input layer nodes, the number of hidden layer nodes, and the number of output layer nodes of the neural network model according to the parameter information related to the SOC of the battery pack; The mathematical model y(t) of the battery pack SOC value is: Among them, w j (t) is the weight connecting the jth hidden layer node to the output layer node, O j (t) is the output of the jth hidden layer node, b is the threshold of the output layer node, w ji (t) is the weight connecting the i-th input layer node to the j-th hidden layer node, x i (t) is the input of the i-th node in the input layer, a j is the threshold of the jth hidden layer node, F is the hidden layer activation function, and y(t) is the output of the output layer node.

3. The method for calculating the SOC value of a battery pack according to claim 1, characterized in that: The correcting the initial SOC value of the battery pack according to the humidity value in the battery pack at the current moment and the temperature value of the battery pack at the current moment to obtain the effective SOC value of the battery pack includes: The SOC correction mathematical model G(t) is constructed according to the humidity value in the battery pack at the current moment and the temperature value of the battery pack at the current moment: G(t)=y(t)+β; Among them, β is the correction model established according to the humidity value and the temperature value at the current moment; The modified model β is: Among them, H(t) is the humidity value at the current moment, T(t) is the temperature value at the current moment, ε1 is the correction factor of the SOC value, ε2 is the development coefficient of the humidity value at the current moment, and ε3 is the proportional coefficient of the humidity value at the current moment.

4. The method for calculating the SOC value of a battery pack according to claim 2, characterized in that: The method further comprises: Establish the mathematical model F(X) of the hidden layer activation function, Among them, x is The value of .

5. The method for calculating the SOC value of a battery pack according to claim 2, characterized in that: Establish the mathematical model F(X) of the hidden layer activation function, Among them, x is The value of .

6. The method for calculating the SOC value of a battery pack according to claim 2, characterized in that: The weight w connecting the jth hidden layer node to the output layer node j (t), the weight w connecting the i-th input layer node to the j-th hidden layer node ji (t), the threshold value b of the output layer node, the threshold value a of the jth hidden layer node j The determination method of is determined by particle swarm algorithm.

7. The method for calculating the SOC value of a battery pack according to claim 1, characterized in that: The method for obtaining the SOC value at the previous moment is: integrating the current value at the previous moment, obtaining the amount of charge or discharge at the previous moment after integration, determining the change in the SOC of the battery pack based on the ratio of the amount of charge or discharge and the capacity of the battery pack, and determining the SOC value of the battery pack at the previous moment according to the change in the SOC.

8. A device for calculating the SOC value of a battery pack, characterized in that: The computing device comprises: An acquisition unit, used to acquire parameter information related to the SOC of the battery pack; wherein the parameter information includes at least: the voltage value of the battery pack at the current moment, the voltage value at the previous moment, the current value at the current moment, the current value at the previous moment, the SOH value at the current moment, the SOC value at the previous moment, and the temperature value at the current moment; a calculation unit, configured to construct a mathematical model y(t) of the SOC value of the battery pack using a neural network model according to parameter information related to the SOC of the battery pack, and calculate an initial SOC value of the battery pack according to the mathematical model y(t); The correction unit is used to obtain the humidity value in the battery pack at the current moment, and correct the initial SOC value of the battery pack according to the humidity value in the battery pack at the current moment and the temperature value of the battery pack at the current moment to obtain the effective SOC value of the battery pack.

9. An energy storage device, characterized in that: The energy storage device comprises: Battery pack; one or more processors; and A memory for storing one or more programs, which, when executed by the one or more processors, enables the energy storage device to implement the method for calculating the SOC value as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the method for calculating the SOC value according to any one of claims 1 to 7 is implemented.

Images