Battery equalization control method and device, electronic equipment and storage medium

Abstract

The invention discloses a battery equalization control method and device, electronic equipment and a storage medium, and the method comprises the steps: determining historical state parameters of at least two batteries in at least two temperature intervals and at least two equalization resistors, and taking the historical state parameters as training data; training a preset neural network model through the training data to obtain an equilibrium model; burning the equalization model into a controller of a target battery so as to determine an equalization resistance specification value through the equalization model based on a current cell monomer voltage difference of a battery pack where the target battery is located, a current real-time temperature, a current battery cycle index of the target battery and a current battery health state, the target battery being a master control battery and / or a slave control battery; and switching to an equalization resistor matched with the equalization resistor specification value through the controller of the target battery, and starting resistor equalization. The battery equalization decision reliability can be improved, the battery equalization decision cost is reduced, the equalization efficiency is improved, and the service life of the battery is prolonged.

Description

Technical Field

[0001] This invention relates to the field of energy storage technology, and in particular to a battery equalization control method, device, electronic device, and storage medium. Background Technology

[0002] With the development of the energy storage industry, the use of lithium batteries is becoming increasingly widespread. A single lithium battery cell has a low voltage and low energy output, so in practical applications, multiple lithium batteries are connected in series or parallel to obtain a higher voltage and more energy. To prevent battery capacity reduction caused by voltage imbalance, batteries in actual use must have balancing measures. Typically, a portion of the charge is released from the higher-voltage cells to bring their voltage closer to that of the lower-voltage cells, ultimately achieving the effect of equal voltage for each cell.

[0003] However, battery balancing involves issues of balancing efficiency and battery lifespan after balancing. Furthermore, for large-scale energy storage devices, a large number of cells need to be balanced. Therefore, improving balancing efficiency, extending battery lifespan, and reducing the balancing management pressure on the main control module of large-scale energy storage devices have become important issues. Summary of the Invention

[0004] This invention provides a battery balancing control method, device, electronic device, and storage medium to improve the reliability of battery balancing decisions, reduce battery balancing decision costs, and improve balancing efficiency and battery lifespan.

[0005] In a first aspect, embodiments of the present invention provide a battery balancing control method, the method comprising:

[0006] Determine the historical state parameters of at least two batteries under at least two temperature ranges and at least two equalization resistances, respectively, as training data;

[0007] The pre-set neural network model is trained using the training data to obtain a balanced model;

[0008] The equalization model is burned into the controller of the target battery so that the equalization resistor specification value can be determined based on the current cell voltage difference, current real-time temperature, current battery cycle number and current battery health status of the battery pack containing the target battery.

[0009] The target battery is a master control battery and / or a slave control battery;

[0010] The controller of the target battery is switched to a balancing resistor that matches the specification value of the balancing resistor, and resistance balancing is enabled.

[0011] Secondly, embodiments of the present invention also provide a battery balancing control device, the device comprising:

[0012] The training data determination module is used to determine the historical state parameters of at least two batteries under at least two temperature ranges and at least two equalization resistors, respectively, as training data.

[0013] The balanced model training module is used to train a pre-set neural network model using the training data to obtain a balanced model.

[0014] The equalization resistance specification value determination module is used to burn the equalization model into the controller of the target battery, so as to determine the equalization resistance specification value based on the current cell voltage difference, current real-time temperature, current battery cycle number and current battery health status of the battery pack in which the target battery is located.

[0015] The target battery is a master control battery and / or a slave control battery;

[0016] The equalization resistor switching module is used to switch to an equalization resistor that matches the specification value of the equalization resistor through the controller of the target battery, thereby enabling resistance equalization.

[0017] Thirdly, embodiments of the present invention also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the battery equalization control method as described in any of the embodiments of the present invention.

[0018] Fourthly, embodiments of the present invention also provide a storage medium for storing computer-executable instructions, which, when executed by a computer processor, are used to perform the battery equalization control method as described in any of the embodiments of the present invention.

[0019] The technical solution of this invention collects historical state parameters of multiple batteries under multiple temperature ranges and multiple balancing resistors to determine training data. Based on this training data, a neural network model is trained to obtain a balancing model. The balancing model is then deployed to the controller of the target battery via programming. During battery power supply, the current cell voltage difference, current real-time temperature, current battery cycle count, and current battery health status of the target battery are input into the balancing model to obtain the balancing resistor specifications output by the model. The controller of the target battery switches to the corresponding balancing resistor to achieve resistance balancing of the battery pack. By training the balancing model, the reliability of battery balancing decisions is improved. By deploying the balancing model in the controllers of each battery in the battery pack, the balancing management pressure and balancing decision cost of the main control module are reduced, improving balancing efficiency and battery lifespan.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a battery balancing control method provided in Embodiment 1 of the present invention;

[0023] Figure 2 This is a flowchart of a battery balancing control method provided in Embodiment 2 of the present invention;

[0024] Figure 3 This is a schematic diagram of the structure of a battery balancing control device provided in Embodiment 3 of the present invention;

[0025] Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. In the embodiments of this application, certain software, components, models, and other existing industry solutions may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solutions of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0028] The acquisition, transmission, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0029] Example 1

[0030] Figure 1 The flowchart below illustrates a battery balancing control method according to Embodiment 1 of the present invention. This embodiment is applicable to battery balancing in battery packs, particularly large energy storage devices. The method can be executed by a battery balancing control device, which can be implemented in hardware and / or software. This battery balancing control device can be configured in an energy storage system and used in conjunction with at least two batteries.

[0031] like Figure 1 As shown, the method includes:

[0032] S110. Determine the historical state parameters of at least two batteries under at least two temperature ranges and at least two equalization resistors, respectively, as training data.

[0033] In this embodiment, in order to train the balanced model, the battery testing equipment is used to conduct full life cycle tests on multiple scenarios and multiple batteries based on a pre-set sampling frequency, so as to provide sufficient training samples for model training.

[0034] Specifically, by setting different temperature ranges, the impact of temperature on battery balancing is fully considered; by setting different balancing resistors, the flexibility and adaptability of the switchable resistor are improved. Historical state parameters can cover multiple dimensions such as temperature, current, and battery cycle count, thus enabling the balancing model trained based on training data to have high reliability in balancing decisions.

[0035] Specifically, S110 can include:

[0036] S111. Determine at least two temperature ranges;

[0037] S112. Within the same temperature range, switch at least two equalization resistors for at least two batteries and determine the historical state parameters during the charging and discharging process.

[0038] The historical state parameters include historical charge and discharge current, historical cell voltage, historical real-time temperature, historical battery cycle count, historical battery health status, historical balancing time, and historical balancing efficiency.

[0039] The historical equalization duration is the difference between the time when the historical individual cell voltage difference is greater than or equal to the voltage difference threshold and the time when the historical individual cell voltage difference is less than the voltage difference threshold. The historical equalization efficiency is the ratio between the difference between the maximum historical individual cell voltage difference and the voltage difference threshold and the equalization duration.

[0040] Specifically, different temperature ranges are predetermined. For example, 0℃-50℃ can be selected as the temperature range that allows battery balancing to be enabled, and the temperature range is divided into 10℃ intervals, resulting in a total of 5 different temperature ranges.

[0041] Within the same temperature range, different balancing resistors are switched for different batteries, and the historical state parameters of the battery charging and discharging process are recorded after the balancing resistor is switched. For example, the balancing resistors can be 10Ω, 20Ω, and 30Ω. Understandably, the balancing current differs with different balancing resistors. For example, correspondingly, with balancing resistors of 10Ω, 20Ω, and 30Ω, the corresponding balancing rates are 0.05C, 0.2C, and 0.5C, respectively, and the corresponding balancing currents are 0.5A, 2A, and 5A, respectively.

[0042] Historical charge / discharge current can be measured using a current sensor, and historical cell voltage can be measured using a cell voltage acquisition device or the voltage acquisition chip built into the battery management system. Historical real-time temperature can be measured using a thermometer or infrared thermometer. Historical battery cycle count indicates the number of charge / discharge cycles the battery has undergone. Historical battery health status refers to the battery's historical SOH (State of Health), which can be expressed as the ratio of historical battery cycle count to the rated cycle count, where the rated cycle count could be, for example, 3000 cycles.

[0043] Historical equilibrium duration is the difference between the time it takes for the historical individual cell voltage difference to be greater than or equal to a voltage difference threshold and the time it takes for the historical individual cell voltage difference to be less than the voltage difference threshold. The historical individual cell voltage difference can be calculated as the difference between the maximum individual cell voltage and the average individual cell voltage of the battery pack. It can be understood that a historical individual cell voltage difference less than the voltage difference threshold means that the current individual cell voltage difference within the battery pack is relatively small, and the battery pack can be considered to have reached an equilibrium state. Therefore, the essence of historical equilibrium duration is the time it takes for the battery pack to reach an equilibrium state from an unbalanced state.

[0044] Historical equalization efficiency is the ratio of the difference between the maximum historical voltage difference of a single cell and the voltage difference threshold to the equalization time. In other words, after one equalization time, the historical voltage difference of a single cell is reduced from being greater than or equal to the voltage difference threshold to being less than the voltage difference threshold; that is, the historical voltage difference of a single cell is reduced by the difference between the maximum historical voltage difference and the voltage difference threshold. Therefore, the ratio of the difference between the maximum historical voltage difference of a single cell and the voltage difference threshold to the equalization time is the historical equalization efficiency.

[0045] In this embodiment, the above process is repeated for each temperature range until all temperature ranges are processed. This yields historical state parameters for different batteries under different temperature ranges and different equalization resistances (corresponding to different equalization current rates). This multi-dimensional historical parameter data ensures that the equalization model trained using these historical state parameters has high reliability in equalization decision-making.

[0046] S120. Using the training data, train the pre-set neural network model to obtain a balanced model.

[0047] As the number of battery packs in an energy storage system increases, the battery balancing management burden on the main control module increases, and decision-making efficiency decreases. Therefore, in this embodiment, a balancing model is obtained by pre-training a neural network model. The battery balancing strategy decision is realized through the balancing model, which enables forward-looking balancing decisions. Furthermore, by deploying the neural network model in each battery, the computational load of the main control module is greatly reduced, ensuring low power consumption while improving intelligent adaptation capabilities.

[0048] The neural network model consists of four neurons in the input layer, eight neurons in the hidden layer, and one neuron in the output layer. The inputs to the neural network model are historical cell voltage differences, historical real-time temperatures, historical battery cycle counts, and historical battery health status. The output is the specification value of the equalization resistor.

[0049] Understandably, the battery controller MCU (Microcontroller Unit) has limited resources and capacity. Therefore, this embodiment uses a lightweight neural network model, which can ensure low power consumption while realizing battery balancing strategy decisions and reducing the load on balancing decisions.

[0050] Specifically, the input layer consists of four neurons, processing four parameters: individual cell voltage difference, real-time temperature, battery cycle count, and battery health status. The hidden layer consists of eight neurons, with the activation function expressed by the formula: f(x) = max(0, x), meaning that when the input value x is positive, the output is the input value itself; otherwise, the output is 0. The output layer consists of one neuron, outputting the specified value of the equalization resistor, such as 10Ω, 20Ω, or 30Ω.

[0051] The lightweight neural network model set in this embodiment has a total number of parameters that are about 1 / 1000 of those of the traditional neural network model, which greatly reduces the amount of computation and resource consumption and meets the computing power control requirements of the battery MCU.

[0052] Specifically, S120 may further include: training a pre-set neural network model based on the training data and a pre-set model training objective until the accuracy of the balancing resistor output by the neural network model is greater than or equal to a preset accuracy threshold, thereby obtaining a balancing model; the model training objective includes the maximum battery cycle count being greater than or equal to a cycle count threshold, and maximizing balancing efficiency.

[0053] During the training of the equalization model, the training objective is set to ensure that the maximum number of battery cycles is greater than or equal to a cycle count threshold. For example, the cycle count threshold can be set to 3000, while simultaneously maximizing equalization efficiency. This model training objective allows the battery MCU to extend battery life and improve equalization efficiency while making battery equalization decisions based on the equalization model.

[0054] When training a model based on the training objective, if the model accuracy reaches the preset requirement, that is, the accuracy of the selected equalization resistor is greater than or equal to the preset accuracy threshold, such as 90%, then the model training is stopped and the model at this time is used as the equalization model.

[0055] S130. The equalization model is burned into the controller of the target battery so that the equalization resistor specification value is determined based on the current cell voltage difference, current real-time temperature, current battery cycle number and current battery health status of the battery pack containing the target battery.

[0056] In this embodiment, the target battery is either the master-controlled battery or the slave-controlled battery. Regardless of whether the battery is a master-controlled or slave-controlled battery, the balancing model is programmed into the target MCU, enabling local deployment of the balancing model on the battery. Each battery possesses battery balancing decision-making capabilities and can perform its own balancing control. Compared to existing technologies that rely on the master-controlled battery for battery balancing decisions, this reduces the computational load and management burden on the master-controlled battery, improving the overall balancing decision-making efficiency of the energy storage system. It is particularly suitable for large-scale energy storage systems with a large number of battery packs.

[0057] Similarly, in the model inference process of the equalization model, four types of parameters are used as inputs to the equalization model: the current cell voltage difference of the target battery in the battery pack during the actual operation of the target battery, the current real-time temperature, the current battery cycle number of the target battery, and the current battery health status. Finally, the optimal equalization resistance specification value output by the equalization model is obtained.

[0058] S140. Using the controller of the target battery, switch to the equalization resistor that matches the specification value of the equalization resistor and enable resistance equalization.

[0059] After the equalization model outputs the equalization resistor specification value, the target battery's MCU controls the switching to the corresponding equalization resistor to start resistance equalization.

[0060] Furthermore, it can monitor in real time the change in the current cell voltage difference of the battery pack containing the target battery after the start-up resistor equalization, until the current cell voltage difference of the battery pack containing the target battery is less than or equal to the preset voltage difference threshold, at which point it is considered that the battery pack containing the target battery has reached the equalization state and the equalization operation is stopped.

[0061] The technical solution of this invention collects historical state parameters of multiple batteries under multiple temperature ranges and multiple balancing resistors to determine training data. Based on this training data, a neural network model is trained to obtain a balancing model. The balancing model is then deployed to the controller of the target battery via programming. During battery power supply, the current cell voltage difference, current real-time temperature, current battery cycle count, and current battery health status of the target battery are input into the balancing model to obtain the balancing resistor specifications output by the model. The controller of the target battery switches to the corresponding balancing resistor to achieve resistance balancing of the battery pack. By training the balancing model, the reliability of battery balancing decisions is improved. By deploying the balancing model in the controllers of each battery in the battery pack, the balancing management pressure and balancing decision cost of the main control module are reduced, improving balancing efficiency and battery lifespan.

[0062] Example 2

[0063] Figure 2 This is a flowchart of a battery balancing control method provided in Embodiment 2 of the present invention. Based on the above embodiments, the present invention further specifies the process of achieving battery balancing of the target battery based on the balancing model.

[0064] like Figure 2 As shown, the method includes:

[0065] S210. Determine the historical state parameters of at least two batteries under at least two temperature ranges and at least two equalization resistors, respectively, as training data.

[0066] S220. Using the training data, train the pre-set neural network model to obtain an equilibrium model.

[0067] S230. The equalization model is burned into the controller of the target battery.

[0068] The training of the equalization model and the process of local battery deployment have been described in the above embodiments, and will not be repeated here.

[0069] S240. Determine the current cell voltage difference of the battery pack containing the target battery.

[0070] The current voltage difference of a single cell reflects the difference in voltage between the cells in the battery pack containing the target battery. The larger the current voltage difference of a single cell, the worse the voltage balance among the cells in the battery pack containing the target battery.

[0071] In an optional embodiment, determining the current cell voltage difference of the battery pack containing the target battery may include: determining the average voltage and maximum voltage of each cell in the battery pack containing the target battery, and using the difference between the maximum voltage and the average voltage as the current cell voltage difference of the battery pack containing the target battery.

[0072] In another optional embodiment, determining the current cell voltage difference of the battery pack containing the target battery may further include: determining the minimum and maximum voltages of each cell in the battery pack containing the target battery, and using the difference between the maximum and minimum voltages as the current cell voltage difference of the battery pack containing the target battery.

[0073] S250. If it is determined that the voltage difference of the current individual cell is greater than or equal to the voltage difference threshold, then the equalization model is used to determine the equalization resistor specification value based on the current individual cell voltage difference, the current real-time temperature, the current battery cycle number of the target battery, and the current battery health status.

[0074] When the voltage difference between individual cells is greater than or equal to the voltage difference threshold, it indicates that the voltage imbalance of the battery pack containing the target battery is relatively high, and balancing measures need to be taken.

[0075] The voltage difference threshold can be a predetermined fixed value or it can be dynamically determined during the operation of the battery pack.

[0076] Specifically, the voltage difference threshold can be calculated using the following formula: ;in, Indicates the voltage difference threshold. This represents the equalization activation voltage reference value, which can be determined based on the average voltage of the battery pack, for example, it could be 10mV, 20mV, etc. This represents a temperature baseline value, such as 25℃, which can be flexibly adjusted according to the region, weather, and season. This indicates the current real-time temperature. The temperature coefficient can be determined based on the current real-time temperature. For example, when the current real-time temperature is less than 0°C, the temperature coefficient can be set to 2; when the current real-time temperature is greater than or equal to 0°C and less than 40°C, the temperature coefficient can be set to 1; and when the current real-time temperature is greater than 40°C, the temperature coefficient can be set to 0.5. express coefficient, This indicates the current battery health status, which is the ratio of the current battery cycle count to the rated battery cycle count. For example, when SOH is greater than or equal to 80%, the SOH coefficient can be set to 10; when SOH is greater than or equal to 60% but less than 80%, the SOH coefficient can be set to 15; and when SOH is less than 60%, the SOH coefficient can be set to 20.

[0077] Based on the above formula, the voltage difference threshold is dynamically calculated in real time, and the current individual cell voltage difference obtained from real-time monitoring is compared to determine whether battery balancing needs to be activated.

[0078] S260. Using the controller of the target battery, switch to a balancing resistor that matches the specification value of the balancing resistor and enable resistance balancing.

[0079] In a specific application scenario, taking a battery pack containing four batteries as an example, covering the battery's 0-3000 cycle counts, and the temperature range covering -10℃ to 45℃ with each 5℃ interval as a temperature range, within the same temperature range, the battery pack is sequentially switched with 10Ω, 20Ω and 30Ω equalization resistors, which is equivalent to applying equalization currents of 0.05C rate (0.5A), 0.2C rate (2A) and 0.5C rate (5A) to synchronously simulate the charging and discharging process.

[0080] At a frequency of 1 Hz, the following data were collected: charging and discharging current, individual cell voltages of the four batteries, real-time temperature of the four batteries, battery cycle count, battery health status, balancing time, and balancing efficiency. This data was used as training data to train a pre-defined neural network model. The neural network model adopted a lightweight design. The input layer consisted of four neurons, corresponding to the individual cell voltage difference, real-time temperature, battery cycle count, and battery health status, respectively. The hidden layer consisted of eight neurons using the ReLU activation function, and the output layer consisted of one neuron, outputting the specified value of the balancing resistor (10Ω, 20Ω, or 30Ω).

[0081] The model is trained until the model's accuracy in selecting the equalization resistor exceeds a pre-set accuracy threshold, and the single inference decision time is less than 1ms, thereby ensuring the accuracy of battery equalization decisions while adapting to the needs of real-time decision-making.

[0082] The equalization model is deployed to the MCU of each battery. During battery operation, the current status is collected in real time, including the current SOH = 60% (current battery cycle count 1200 / rated battery cycle count 3000), the current individual cell voltages of the four batteries are 3.65V, 3.72V, 3.68V, and 3.70V respectively, the average voltage is 3.6875V, and the current individual cell voltage difference is 3.72-3.6875=32.5mV. The temperature of the four batteries, T1-T4, is 35℃.

[0083] At this time, the preset parameters Set to 15mv Set to 25℃ The corresponding value is 1. The corresponding number is 15.

[0084] Based on the voltage difference threshold calculation formula, the voltage difference threshold is calculated to be 15 + 1 × (35 - 25) + 15 × (1 - 60%) = 31mV. The current single-cell voltage difference of 32.5mV is greater than the voltage difference threshold of 31mV, thus meeting the battery equalization activation condition.

[0085] The current single-cell voltage difference of 32.5mV, the current real-time average temperature of 35℃, the current battery cycle count of 1200, and the current battery health status of 60% are input into the balancing model, and the balancing model outputs a balancing resistance of 20Ω.

[0086] The MCU controls the MOSFET to switch to the equalization resistor of 20Ω and monitors the change in the voltage difference of the current cell in real time. When the voltage difference of the current cell is less than the voltage difference threshold of 31mV, the equalization is stopped.

[0087] The technical solution in this embodiment incorporates multi-dimensional parameters such as temperature, voltage, and cycle count for balancing decisions, ensuring the reliability of these decisions. A balancing model is deployed in the MCU of each battery, significantly reducing the computational load on the main control battery and improving the balancing decision efficiency of the energy storage system. Furthermore, the balancing resistors determined by the balancing model are flexible and controllable; using different balancing resistors in different balancing processes can improve balancing efficiency and battery life.

[0088] Example 3

[0089] Figure 3 This is a schematic diagram of a battery balancing control device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes:

[0090] The training data determination module 310 is used to determine the historical state parameters of at least two batteries under at least two temperature ranges and at least two equalization resistors, respectively, as training data.

[0091] The equilibrium model training module 320 is used to train a pre-set neural network model using the training data to obtain an equilibrium model.

[0092] The equalization resistance specification value determination module 330 is used to burn the equalization model into the controller of the target battery, so as to determine the equalization resistance specification value based on the current cell voltage difference, current real-time temperature, current battery cycle number and current battery health status of the battery pack in which the target battery is located through the equalization model.

[0093] The target battery is a master control battery and / or a slave control battery;

[0094] The equalization resistor switching module 340 is used to switch to an equalization resistor that matches the specification value of the equalization resistor through the controller of the target battery, and to enable resistance equalization.

[0095] The technical solution of this invention collects historical state parameters of multiple batteries under multiple temperature ranges and multiple balancing resistors to determine training data. Based on this training data, a neural network model is trained to obtain a balancing model. The balancing model is then deployed to the controller of the target battery via programming. During battery power supply, the current cell voltage difference, current real-time temperature, current battery cycle count, and current battery health status of the target battery are input into the balancing model to obtain the balancing resistor specifications output by the model. The controller of the target battery switches to the corresponding balancing resistor to achieve resistance balancing of the battery pack. By training the balancing model, the reliability of battery balancing decisions is improved. By deploying the balancing model in the controllers of each battery in the battery pack, the balancing management pressure and balancing decision cost of the main control module are reduced, improving balancing efficiency and battery lifespan.

[0096] Based on the above embodiments, optionally, the training data determination module 310 includes:

[0097] Temperature range determination unit, used to determine at least two temperature ranges;

[0098] The historical state parameter determination unit is used to switch at least two equalization resistors for at least two batteries within the same temperature range and determine the historical state parameters during the charging and discharging process.

[0099] The historical state parameters include historical charge and discharge current, historical cell voltage, historical real-time temperature, historical battery cycle count, historical battery health status, historical balancing time, and historical balancing efficiency.

[0100] The historical equalization duration is the difference between the time when the historical individual cell voltage difference is greater than or equal to the voltage difference threshold and the time when the historical individual cell voltage difference is less than the voltage difference threshold. The historical equalization efficiency is the ratio between the difference between the maximum historical individual cell voltage difference and the voltage difference threshold and the equalization duration.

[0101] Based on the above embodiments, optionally, the input layer of the neural network model includes four neurons, the hidden layer includes eight neurons, and the output layer includes one neuron;

[0102] The neural network model takes historical cell voltage difference, historical real-time temperature, historical battery cycle count, and historical battery health status as input, and outputs the specifications of the equalization resistor.

[0103] Based on the above embodiments, optionally, the equalization model training module 320 includes:

[0104] The equalization model training unit is used to train a pre-set neural network model based on the training data and a pre-set model training objective until the accuracy of the equalization resistor output by the neural network model is greater than or equal to a preset accuracy threshold, thus obtaining the equalization model.

[0105] The model training objectives include ensuring that the maximum number of battery cycles is greater than or equal to a cycle count threshold, and maximizing balanced efficiency.

[0106] Based on the above embodiments, optionally, the equalization resistor specification value determination module 330 includes:

[0107] The current cell voltage difference determination unit is used to determine the current cell voltage difference of the battery pack in which the target battery is located.

[0108] The equalization resistor specification value determination unit is used to determine the equalization resistor specification value based on the current cell voltage difference, current real-time temperature, current battery cycle number and current battery health status of the battery pack containing the target battery, if it is determined that the current cell voltage difference is greater than or equal to the voltage difference threshold.

[0109] Based on the above embodiments, optionally, the current cell voltage difference determination unit is specifically used for:

[0110] Determine the average voltage and maximum voltage of each cell in the battery pack containing the target battery, and use the difference between the maximum voltage and the average voltage as the current cell voltage difference of the battery pack containing the target battery.

[0111] Based on the above embodiments, optionally, the voltage difference threshold is calculated using the following formula:

[0112] ;

[0113] in, Indicates the voltage difference threshold. This indicates the equalization start voltage reference value. Indicates the temperature coefficient. This indicates the current real-time temperature. Indicates the temperature reference value. express coefficient, This indicates the current battery health status, which is the ratio of the current battery cycle count to the rated battery cycle count.

[0114] The battery balancing control device provided in this embodiment of the invention can execute the battery balancing control method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0115] Example 4

[0116] Figure 4 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0117] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0118] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0119] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as battery balancing control methods.

[0120] In some embodiments, the battery balancing control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the battery balancing control method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the battery balancing control method by any other suitable means (e.g., by means of firmware).

[0121] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0122] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable battery equalization control device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0123] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0124] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0125] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0126] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0127] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0128] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A battery balancing control method, characterized in that, include: Determine the historical state parameters of at least two batteries under at least two temperature ranges and at least two equalization resistances, respectively, as training data; The pre-set neural network model is trained using the training data to obtain a balanced model; The equalization model is burned into the controller of the target battery so that the equalization resistor specification value can be determined based on the current cell voltage difference, current real-time temperature, current battery cycle number and current battery health status of the battery pack containing the target battery. The target battery is a master control battery and / or a slave control battery; The controller of the target battery is switched to a balancing resistor that matches the specification value of the balancing resistor, and resistance balancing is enabled.

2. The method according to claim 1, characterized in that, Determine the historical state parameters of at least two batteries under at least two temperature ranges and at least two equalization resistances, including: Define at least two temperature ranges; Within the same temperature range, at least two equalization resistors are switched for at least two batteries, and historical state parameters during the charging and discharging process are determined. The historical state parameters include historical charge and discharge current, historical cell voltage, historical real-time temperature, historical battery cycle count, historical battery health status, historical balancing time, and historical balancing efficiency. The historical equalization duration is the difference between the time when the historical individual cell voltage difference is greater than or equal to the voltage difference threshold and the time when the historical individual cell voltage difference is less than the voltage difference threshold. The historical equalization efficiency is the ratio between the difference between the maximum historical individual cell voltage difference and the voltage difference threshold and the equalization duration.

3. The method according to claim 1, characterized in that, The neural network model has an input layer consisting of four neurons, a hidden layer consisting of eight neurons, and an output layer consisting of one neuron. The neural network model takes historical cell voltage difference, historical real-time temperature, historical battery cycle count, and historical battery health status as input, and outputs the specifications of the equalization resistor.

4. The method according to claim 3, characterized in that, The pre-set neural network model is trained using the training data to obtain an equilibrium model, including: Using the training data, based on the pre-set model training objective, the pre-set neural network model is trained until the accuracy of the balancing resistor output by the neural network model is greater than or equal to the pre-set accuracy threshold, thus obtaining the balancing model. The model training objectives include ensuring that the maximum number of battery cycles is greater than or equal to a cycle count threshold, and maximizing balanced efficiency.

5. The method according to claim 1, characterized in that, Based on the current cell voltage difference, current real-time temperature, current battery cycle count, and current battery health status of the target battery, the equalization resistor specification value is determined using the equalization model, including: Determine the current individual cell voltage difference of the battery pack containing the target battery; If it is determined that the voltage difference of the current individual cell is greater than or equal to the voltage difference threshold, then the equalization model determines the equalization resistor specification value based on the current individual cell voltage difference of the battery pack containing the target battery, the current real-time temperature, the current battery cycle count of the target battery, and the current battery health status.

6. The method according to claim 5, characterized in that, Determining the current individual cell voltage difference of the battery pack containing the target battery includes: Determine the average voltage and maximum voltage of each cell in the battery pack containing the target battery, and use the difference between the maximum voltage and the average voltage as the current cell voltage difference of the battery pack containing the target battery.

7. The method according to claim 5, characterized in that, The voltage difference threshold is calculated using the following formula: ； in, Indicates the voltage difference threshold. This indicates the equalization start voltage reference value. Indicates the temperature coefficient. This indicates the current real-time temperature. Indicates the temperature reference value. express coefficient, This indicates the current battery health status, which is the ratio of the current battery cycle count to the rated battery cycle count.

8. A battery balancing control device, characterized in that, include: The training data determination module is used to determine the historical state parameters of at least two batteries under at least two temperature ranges and at least two equalization resistors, respectively, as training data. The balanced model training module is used to train a pre-set neural network model using the training data to obtain a balanced model. The equalization resistance specification value determination module is used to burn the equalization model into the controller of the target battery, so as to determine the equalization resistance specification value based on the current cell voltage difference, current real-time temperature, current battery cycle number and current battery health status of the battery pack in which the target battery is located. The target battery is a master control battery and / or a slave control battery; The equalization resistor switching module is used to switch to an equalization resistor that matches the specification value of the equalization resistor through the controller of the target battery, thereby enabling resistance equalization.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the battery equalization control method as described in any one of claims 1-7.

10. A storage medium for storing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the battery equalization control method as described in any one of claims 1-7.

Images