A battery management system

Abstract

The present invention relates to the field of battery balancing control technology, specifically a battery management system comprising: a state determination unit, the state determination unit being used to obtain the state of charge of each battery in a battery pack according to the ampere-hour integration method, and determining the average state of charge of the battery pack according to the state of charge of each battery in the battery pack; a difference calculation unit, the difference calculation unit being used to determine the difference in state of charge of batteries in the same battery pack according to the state of charge of the battery, and determining the average state of charge difference of battery packs in a battery system according to the average state of charge of the battery pack. The present invention ensures that the energy consumption of each battery during the charging and discharging process tends to be consistent through the functions of intra-group balancing and inter-group balancing. By eliminating the difference in state of charge between batteries, a more even distribution of energy in the battery pack can be achieved, and efficiency loss of individual batteries due to excessive charging and discharging can be avoided, thereby improving the energy utilization efficiency of the battery pack.

Description

Technical Field

[0001] The present invention relates to the technical field of battery balancing control, and in particular to a battery management system. Background Art

[0002] Traditional systems cannot detect differences in battery state of charge in a timely manner, and thus cannot effectively perform balancing corrections. Due to inaccurate battery state of charge, this may cause the battery to be over-discharged or over-charged, affecting battery life and performance. Traditional systems do not clearly distinguish between intra-group balancing and inter-group balancing functions, and may only rely on simple balancing mechanisms, such as voltage-based balancing, which cannot effectively address differences in state of charge between batteries, thereby failing to achieve uniform energy distribution between batteries. This may cause some batteries to be overcharged and discharged, reducing efficiency, thereby shortening the service life of the battery pack and reducing energy utilization efficiency. Traditional systems usually do not have an integrated intelligent temperature control mechanism. Temperature control may only rely on a single temperature sensor, or there is no temperature control strategy for changes in the battery pack's balancing state. When the battery pack is unbalanced, some batteries may generate heat due to overcharging and discharging, but traditional systems may fail to identify these changes in a timely manner and cannot accurately adjust the temperature, causing the battery to overheat or overcool, increasing the risk of battery damage and affecting the safety and performance of the system. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a battery management system.

[0004] The technical solution adopted to solve the above technical problems is: a battery management system, comprising:

[0005] a state determination unit, the state determination unit being configured to obtain the state of charge of each battery in the battery pack according to an ampere-hour integration method, and determine an average state of charge of the battery pack according to the state of charge of each battery in the battery pack;

[0006] a difference calculation unit, the difference calculation unit being configured to determine a difference in state of charge of batteries in the same battery pack based on the state of charge of the battery, and to determine an average state of charge difference of battery packs in the battery system based on the average state of charge of the battery pack;

[0007] a balancing judgment unit, configured to judge whether the battery system and the battery pack are in an unbalanced state based on a state-of-charge difference between batteries in the same battery pack and an average state-of-charge difference between battery packs in the battery system;

[0008] a state balancing unit, configured to perform intra-group balancing on the battery pack when the battery pack is in an unbalanced state, and to perform inter-group balancing on the battery system when the battery system is in an unbalanced state;

[0009] A temperature control unit is used to control the temperature of the battery pack according to a pre-trained temperature control model when the battery pack is balanced within the group.

[0010] Preferably, the calculation formula for the average state of charge of the battery pack is as follows:

[0011] ;

[0012] in, Indicates the battery system The average state of charge of the battery pack, Indicates the battery system The first battery in the The state of charge of each battery, Indicates the battery system The total number of cells in a battery pack;

[0013] The calculation formula for the state of charge difference of the batteries in the same battery pack is as follows:

[0014] ;

[0015] in, Indicates the battery system The first battery in the and The difference in state of charge between the batteries;

[0016] The calculation formula for the average state of charge difference of the battery packs in the battery system is as follows:

[0017] ;

[0018] in, Indicates the battery system and The average state of charge difference between the battery packs.

[0019] Preferably, judging whether the battery system and the battery pack are in an unbalanced state based on the state of charge difference of the batteries in the same battery pack and the average state of charge difference of the battery packs in the battery system includes:

[0020] determining whether the state of charge difference is greater than a preset first threshold, and if so, determining that the battery pack is in an unbalanced state;

[0021] It is determined whether the average state of charge difference of the battery packs in the battery system is greater than a preset second threshold value. If the average state of charge difference is greater than the preset second threshold value, it is determined that the battery system is in an unbalanced state.

[0022] Preferably, when the battery pack is in an unbalanced state, performing intra-group balancing on the battery pack includes:

[0023] The battery with the highest state of charge in the same battery pack charges the battery with the lowest state of charge;

[0024] When the difference between the state of charge of the battery with the highest state of charge and the state of charge of the batteries in the same battery pack that do not participate in balancing is less than a third threshold, the batteries in the same battery pack transfer excess state of charge to the battery with the lower state of charge;

[0025] Determine whether the battery pack is in an unbalanced state, and if the battery pack is in an unbalanced state, repeat the above operation;

[0026] When the battery pack is in a balanced state, it is determined whether the battery pack is in a working state. When the battery pack is in a working state, the battery pack is discharged in a balanced manner.

[0027] Preferably, when the battery system is in an unbalanced state, performing inter-group balancing on the battery system includes:

[0028] Determining whether the battery system is in working condition;

[0029] When the battery system is in a working state, determining whether the battery system is in a charging state;

[0030] When the battery system is in a charging state, the battery system is balanced charged according to a pre-trained charging control model.

[0031] Preferably, the charging control model includes a charging optimization model and a deep reinforcement learning model, the charging optimization model includes a first objective function, a second objective function and constraints, and the deep reinforcement learning model is used to solve the charging optimization model to obtain an optimal charging strategy.

[0032] Preferably, the expression of the first objective function is as follows:

[0033] ;

[0034] in, represents the first objective function, express The corresponding number of sampling steps, Indicates the The state of charge at the sampling step, Indicates the target state of charge of the battery pack. Indicates the sampling period;

[0035] The expression of the second objective function is as follows:

[0036] ;

[0037] in, represents the second objective function, Indicates the charging sampling period Time-of-use electricity prices, Indicates the charging current, Indicates charging voltage;

[0038] The constraint condition is expressed as follows:

[0039] ;

[0040] in, Indicates the maximum allowable charging current, Indicates the maximum allowable charging voltage, Indicates the maximum value of the state of charge, Indicates the charging sampling period The temperature of the battery system, represents the maximum allowable battery system temperature, where , Indicates the charging sampling period The surface temperature of the battery system is Indicates the charging sampling period The core temperature of the battery system.

[0041] Preferably, the deep reinforcement learning model is used to solve the charging optimization model to obtain the optimal charging strategy, including:

[0042] Determining a reward function according to the constraints of the charging optimization model, wherein the reward function includes a first reward function, a second reward function, a third reward function, and a fourth reward function;

[0043] Construct a charging strategy network and a strategy evaluation network, wherein the charging strategy network is used to control the charging current of the battery, and the strategy evaluation network is used to evaluate the selection of each charging strategy during training. The hidden layers of the charging strategy network and the strategy evaluation network are both fully connected layers. The first layer of the charging strategy network is a Relu function, and the second layer contains the expectation and variance of the battery charging strategy distribution. The activation function of the expectation part is the Tanh function, and the activation function of the variance part is the SoftPlus function. The strategy evaluation network contains a total of two layers of networks, the activation function of the first layer is the Relu function, and the activation function of the second layer is the Tanh function.

[0044] The charging strategy is updated according to the charging objective function of the charging strategy network, wherein the charging objective function of the charging strategy network is as follows:

[0045] ;

[0046] in, represents the charging objective function of the charging strategy network, Represents the interval Find the mean, Represents the network parameters of the current round charging strategy, Indicates the network parameters of the charging strategy in the last update round, Indicates the current round battery charging strategy, Indicates the battery charging strategy of the previous round, Indicates the battery charging current In battery status The reward function under

[0047] After the training phase, a charging strategy network that maximizes the total reward of the charging round is obtained. The strategy evaluation network used to assist in the training of the strategy network does not participate in the execution phase. The charging strategy network accepts the battery charging status and outputs the probability distribution of the charging strategy.

[0048] Preferably, the first reward function is as follows:

[0049] ;

[0050] in, Indicates the charging sampling period The first reward function when ;

[0051] The second reward function is as follows:

[0052] ;

[0053] in, represents the second reward function, Indicates the highest time-of-use electricity price in the past day;

[0054] The third reward function is as follows:

[0055] ;

[0056] in, represents the third reward function;

[0057] The fourth reward function is as follows:

[0058] ;

[0059] in, represents the fourth reward function.

[0060] Preferably, the temperature control model adopts a BP neural network and a PID control algorithm, wherein the input layer neuron variables of the BP neural network are the actual output temperature value, the expected output temperature value, the system error and the control quantity. According to the BP neural network input variables, the input and output of the intermediate layer node of the BP neural network are obtained using the Sigmoid function, and the input and output of the output layer are determined according to the input and output of the intermediate layer node, wherein the output of the output layer is the proportional gain, integral gain and differential gain of the PID control algorithm, and the PID control algorithm calculates the PID control quantity according to the output of the output layer, discretizes the PID control quantity to obtain a PID control increment, and controls the fan according to the PID control increment, wherein the input and output expressions of the intermediate layer node are as follows:

[0061] ;

[0062] in, represents the input of the middle layer node, represents the weighted coefficient between the input layer neurons and the intermediate layer neurons, represents the input layer neuron variable, represents the output of the middle layer node, represents the Sigmoid function, represents the number of neurons in the middle layer;

[0063] The input and output expressions of the output layer are as follows:

[0064] ;

[0065] in, represents the input of the output layer, represents the weight coefficient between the intermediate neurons and the output layer neurons, represents the output of the output layer, Represents the non-negative Sigmoid function;

[0066] The calculation formula of the PID control increment is as follows:

[0067] ;

[0068] in, Represents the PID control increment, that is Indicates the fan speed. 、 and represents the proportional gain, integral gain and differential gain, Indicates the deviation between the actual output and the expected output.

[0069] The beneficial effects of the present invention are as follows: (1) The present invention obtains the state of charge of each battery in the battery pack by the ampere-hour integration method, and determines whether the battery pack is in a balanced state based on the battery state of charge difference. The system can timely detect the state imbalance problem of the battery pack and make corrections. The balance of the battery directly affects its charging and discharging efficiency and service life. The balanced battery pack can effectively avoid damage caused by excessive discharge or charging of some batteries, thereby improving the performance of the overall battery system and extending the service life; (2) The present invention ensures that the energy consumption of each battery in the charging and discharging process tends to be consistent through the functions of intra-group balancing and inter-group balancing. By eliminating the difference in state of charge between batteries, the energy of the battery pack can be more evenly distributed, and the efficiency loss of individual batteries caused by excessive charging and discharging can be avoided, thereby improving the energy utilization efficiency of the battery pack; (3) When the battery pack enters an unbalanced state, the temperature control unit of the present invention performs temperature control according to the pre-trained temperature control model. When the battery pack is unbalanced, some batteries may generate heat due to excessive charging and discharging. The system avoids overheating or overcooling of the battery through intelligent temperature control, prevents battery damage or overheating caused by excessive temperature, ensures that the battery operates within the optimal temperature range, and further improves safety and performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 This is a schematic diagram of the system architecture of the overall system in an embodiment of the present invention.

[0071] Reference numerals: 1. state determination unit; 2. difference calculation unit; 3. balance judgment unit; 4. state balance unit; 5. temperature control unit. DETAILED DESCRIPTION

[0072] Example 1, as Figure 1 As shown, the present invention proposes a battery management system, comprising:

[0073] A state determination unit 1 is configured to obtain the state of charge of each battery in the battery pack according to an ampere-hour integration method, and determine the average state of charge of the battery pack according to the state of charge of each battery in the battery pack;

[0074] The difference calculation unit 2 is used to determine the difference in state of charge of batteries in the same battery pack according to the state of charge of the battery, and to determine the difference in average state of charge of battery packs in the battery system according to the average state of charge of the battery pack;

[0075] The balancing judgment unit 3 is used to judge whether the battery system and the battery pack are in an unbalanced state based on the difference in state of charge of the batteries in the same battery pack and the difference in average state of charge of the battery packs in the battery system;

[0076] The state balancing unit 4 is used to balance the battery pack within the group when the battery pack is in an unbalanced state, and to balance the battery system between groups when the battery system is in an unbalanced state;

[0077] The temperature control unit 5 is used to control the temperature of the battery pack according to a pre-trained temperature control model when the battery pack is balanced within the group.

[0078] In the present invention, the state of charge of each battery in the battery pack is obtained by the ampere-hour integration method, and the average state of charge of the battery pack is calculated based on these data; the ampere-hour integration method is a commonly used battery SOC estimation method. By accumulating the charge and discharge current of the battery and combining it with the initial power of the battery, the current state of charge of the battery can be calculated; the SOC difference between each battery in the battery pack and the state of charge difference of the battery pack as a whole are identified. If the SOC difference of some batteries in the battery pack is too large, it may affect the overall performance of the battery pack. By calculating these differences, the health status of the battery can be evaluated; the balance state of the battery pack and the battery system as a whole is analyzed. If the SOC difference between some batteries in the battery pack is large, or there is a significant SOC difference between different battery packs, then the battery pack is in an unbalanced state. At this time, the system needs to take measures to balance the battery. Within the battery pack, balancing methods usually reduce the SOC difference between batteries by adjusting the charge and discharge status of the battery, or using bypass current (current flowing from high-charge batteries to low-charge batteries). Intra-pack balancing can be achieved by adjusting the charging strategy of each battery through the battery management system. When there are SOC differences between different battery packs in the entire battery system, balancing is required between the battery packs. This usually involves allocating power among different battery packs so that the SOC of each battery pack is as close as possible, thereby improving the efficiency of the overall battery system and avoiding excessive discharge or overcharging of some battery packs. The performance and life of the battery are greatly affected by temperature. Excessively high or low temperatures will have a negative impact on the battery, which may cause capacity decay, overheating, and even danger. Through the temperature control unit, the system can monitor the temperature of the battery pack in real time and maintain the battery within the ideal operating temperature range by cooling or heating. The unit uses a pre-trained temperature control model to intelligently adjust the temperature according to the battery pack status and environmental conditions to optimize the battery's operating state.

[0079] In the second embodiment, a battery management system proposed by the present invention is provided. Compared with the first embodiment, this embodiment further includes: a calculation formula for the average state of charge of the battery pack is as follows:

[0080] ;

[0081] in, Indicates the battery system The average state of charge of the battery pack, Indicates the battery system The first battery in the The state of charge of each battery, Indicates the battery system The total number of cells in a battery pack;

[0082] The formula for calculating the difference in state of charge of batteries in the same battery pack is as follows:

[0083] ;

[0084] in, Indicates the battery system The first battery in the and The difference in state of charge between the batteries;

[0085] The calculation formula for the average state of charge difference of the battery packs in the battery system is as follows:

[0086] ;

[0087] in, Indicates the battery system and The average state of charge difference between the battery packs.

[0088] In an optional embodiment, determining whether the battery system and the battery pack are in an unbalanced state based on the state of charge difference between batteries in the same battery pack and the average state of charge difference between battery packs in the battery system includes:

[0089] determining whether the state of charge difference is greater than a preset first threshold, and if so, determining that the battery pack is in an unbalanced state;

[0090] It is determined whether the average state of charge difference of the battery packs in the battery system is greater than a preset second threshold value. If the average state of charge difference is greater than the preset second threshold value, it is determined that the battery system is in an unbalanced state.

[0091] It should be noted that the state of charge (SOC) difference of a battery pack refers to the maximum difference in SOC values between different batteries in the pack. Assuming that there are multiple batteries in a battery pack, the SOC value of each battery is monitored in real time by the battery management system. When the SOC difference between these batteries is too large, it means that the batteries in the battery pack have not reached a balanced state. If the maximum SOC difference (state of charge difference) within the battery pack exceeds a preset first threshold, the system will determine that the battery pack is in an unbalanced state. This first threshold is usually set during the battery design phase based on battery characteristics and performance requirements, such as 0.5% or 1%. The selection of this threshold needs to consider the battery pack type, operating conditions, and the strictness of the balance requirements. If the average SOC difference between different battery packs in the battery system exceeds a preset second threshold, the system will determine that the entire battery system is in an unbalanced state. The setting of the second threshold may be adjusted based on factors such as the characteristics of different battery packs and load requirements. If the SOC difference exceeds this threshold, the system needs to balance the battery packs to ensure that the SOC of different battery packs is as consistent as possible.

[0092] In an optional embodiment, when the battery pack is in an unbalanced state, performing intra-group balancing on the battery pack includes:

[0093] The battery with the highest state of charge in the same battery pack charges the battery with the lowest state of charge;

[0094] When the difference between the state of charge of the battery with the highest state of charge and the state of charge of the batteries in the same battery pack that do not participate in balancing is less than a third threshold, the batteries in the same battery pack transfer excess state of charge to the battery with the lower state of charge;

[0095] Determine whether the battery pack is in an unbalanced state. If the battery pack is in an unbalanced state, repeat the above operation;

[0096] When the battery pack is in a balanced state, it is determined whether the battery pack is in a working state. If the battery pack is in a working state, the battery pack is discharged in a balanced manner.

[0097] It should be noted that when the SOC of a certain battery is the highest in the group and the SOC of another battery is the lowest in the group, the battery with the highest SOC will charge the battery with the lowest SOC to narrow the SOC difference between them. This method can effectively help the SOCs of the batteries in the battery pack to be consistent, thereby improving the performance of the battery pack and extending the battery life; if some batteries in the group do not participate in balancing (that is, their SOC difference is less than the preset third threshold), then the remaining batteries (batteries with higher SOC) will transfer the excess state of charge to the batteries with lower SOC, which means that the state of charge in the battery pack is adjusted between the batteries to ensure that all batteries operate within a reasonable SOC range; when the battery pack is in an unbalanced state, the system will repeatedly perform the above-mentioned charging and energy transfer operations until the battery pack reaches a balanced state. This repeated adjustment process can prevent the batteries from balancing. In the working state, the balanced discharge of the battery pack means that the battery pack will adjust the SOC difference of each battery in the battery pack to ensure that the load and power output between the batteries are balanced during the discharge process; the balanced discharge operation will ensure that the SOC of each battery in the battery pack is kept as consistent as possible during the discharge process, thereby avoiding damage to individual batteries due to excessive discharge during the discharge process. In addition, balanced discharge also helps to improve the overall efficiency of the battery pack and ensure that the battery pack can output power stably during operation. In some cases, when the SOC difference of some batteries is small and they do not participate in balancing, the system will use the transfer of excess power to transfer the excess power from the high SOC battery to the low SOC battery. This method can not only improve the balance of the battery pack, but also avoid damage to the battery due to overcharging or over-discharging.

[0098] In an optional embodiment, when the battery system is in an unbalanced state, inter-group balancing is performed on the battery system, including:

[0099] Determine whether the battery system is in working condition;

[0100] When the battery system is in working state, it is determined whether the battery system is in charging state;

[0101] When the battery system is in a charging state, the battery system is balanced charged according to a pre-trained charging control model.

[0102] It should be noted that when judging the charging status: when the battery is in working condition, it is necessary to further judge whether it is in charging condition. This is usually achieved in the following ways: Current direction: whether the battery is charging can be judged by the current sensor. If the current flows from the charging device to the battery, it means that the battery is in charging condition; Battery voltage change: if the battery voltage gradually rises and is within the normal charging voltage range, it means that the battery is charging; Charging device status: the working status of the battery charger can also reflect whether the battery is in charging condition. If the charger is turned on and is providing current to the battery, the battery is in charging condition; Working status judgment: the working status of the battery system can be evaluated by the following indicators: Battery voltage: the voltage range of the battery should be within the specified range during normal operation. If the voltage is too low or too high, it may mean that the battery is no longer in normal working condition; Battery temperature: too high or too low temperature will affect the working condition of the battery. If the battery temperature exceeds or falls below the set range, over-temperature protection may be triggered, causing the battery to stop working; Current sensor: Whether the battery system is in a discharging or charging state can be judged by the magnitude of the current. If the current is zero, it may indicate that the battery system is not in a working state; Fault monitoring: If there is any fault in the battery system, such as communication failure, battery module failure, etc., it will also cause it to fail to work normally.

[0103] In an optional embodiment, the charging control model includes a charging optimization model and a deep reinforcement learning model. The charging optimization model includes a first objective function, a second objective function and constraints. The deep reinforcement learning model is used to solve the charging optimization model to obtain an optimal charging strategy.

[0104] It should be noted that the electrical optimization model describes the goals of the battery charging process through mathematical models and objective functions, and finds the optimal charging strategy based on these objective functions; Deep Reinforcement Learning (DRL) is an algorithm that combines deep learning and reinforcement learning. It can gradually learn the optimal strategy through experience accumulation in environmental interaction. In battery charging control, the deep reinforcement learning model can be used to solve the charging optimization model, especially in complex charging scenarios and dynamic environments, where it has significant advantages.

[0105] In an optional embodiment, the expression of the first objective function is as follows:

[0106] ;

[0107] in, represents the first objective function, express The corresponding number of sampling steps, Indicates the The state of charge at the sampling step, Indicates the target state of charge of the battery pack. Indicates the sampling period;

[0108] The expression of the second objective function is as follows:

[0109] ;

[0110] in, represents the second objective function, Indicates the charging sampling period Time-of-use electricity prices, Indicates the charging current, Indicates charging voltage;

[0111] The constraint expressions are as follows:

[0112] ;

[0113] in, Indicates the maximum allowable charging current, Indicates the maximum allowable charging voltage, Indicates the maximum value of the state of charge, Indicates the charging sampling period The temperature of the battery system, represents the maximum allowable battery system temperature, where , Indicates the charging sampling period The surface temperature of the battery system is Indicates the charging sampling period The core temperature of the battery system.

[0114] In an optional embodiment, a deep reinforcement learning model is used to solve a charging optimization model to obtain an optimal charging strategy, including:

[0115] Determining a reward function according to the constraints of the charging optimization model, wherein the reward function includes a first reward function, a second reward function, a third reward function, and a fourth reward function;

[0116] Construct a charging strategy network and a strategy evaluation network. The charging strategy network is used to control the battery charging current, and the strategy evaluation network is used to evaluate each charging strategy selection during training. The hidden layers of the charging strategy network and the strategy evaluation network are both fully connected layers. The first layer of the charging strategy network is a Relu function, and the second layer contains the expectation and variance of the battery charging strategy distribution. The activation function of the expectation part is the Tanh function, and the activation function of the variance part is the SoftPlus function. The strategy evaluation network consists of two layers. The activation function of the first layer is the Relu function, and the activation function of the second layer is the Tanh function.

[0117] The charging strategy is updated according to the charging objective function of the charging strategy network, where the charging objective function of the charging strategy network is as follows:

[0118] ;

[0119] in, represents the charging objective function of the charging strategy network, Represents the interval Find the mean, Represents the network parameters of the current round charging strategy, Indicates the network parameters of the charging strategy in the last update round, Indicates the current round battery charging strategy, Indicates the battery charging strategy of the previous round, Indicates the battery charging current In battery status The reward function under

[0120] After the training phase, a charging strategy network that maximizes the total reward of the charging round is obtained. The strategy evaluation network used to assist in the training of the strategy network does not participate in the execution phase. The charging strategy network accepts the battery charging status and outputs the probability distribution of the charging strategy.

[0121] It's important to note that the charging policy network is responsible for generating a probability distribution of charging current and adjusting the charging policy based on the current state. The policy evaluation network is responsible for evaluating the performance of each charging policy. The evaluation network's role is to "score" the selected charging policy to help the charging policy network update. During the training phase, the charging policy network and the policy evaluation network are trained together. The charging policy network generates a distribution of charging current, and the policy evaluation network scores the policies, guiding the charging policy network to update parameters. During the inference phase (i.e., the execution phase), the charging policy network outputs a probability distribution of charging policies based on the battery's state of charge and executes the corresponding charging operation.

[0122] In an optional embodiment, the first reward function is as follows:

[0123] ;

[0124] in, Indicates the charging sampling period The first reward function when ;

[0125] The second reward function is as follows:

[0126] ;

[0127] in, represents the second reward function, Indicates the highest time-of-use electricity price in the past day;

[0128] The third reward function is as follows:

[0129] ;

[0130] in, represents the third reward function;

[0131] The fourth reward function is as follows:

[0132] ;

[0133] in, represents the fourth reward function.

[0134] In an optional embodiment, the temperature control model adopts a BP neural network and a PID control algorithm, wherein the input layer neuron variables of the BP neural network are the actual output temperature value, the expected output temperature value, the system error and the control quantity. According to the BP neural network input variables, the input and output of the BP neural network intermediate layer node are obtained using the Sigmoid function, and the input and output of the output layer are determined according to the input and output of the intermediate layer node, wherein the output of the output layer is the proportional gain, integral gain and differential gain of the PID control algorithm, and the PID control algorithm calculates the PID control quantity according to the output of the output layer, discretizes the PID control quantity to obtain the PID control increment, and controls the fan according to the PID control increment, wherein the expressions of the input and output of the intermediate layer node are as follows:

[0135] ;

[0136] in, represents the input of the middle layer node, represents the weighted coefficient between the input layer neurons and the intermediate layer neurons, represents the input layer neuron variable, represents the output of the middle layer node, represents the Sigmoid function, represents the number of neurons in the middle layer;

[0137] The input and output expressions of the output layer are as follows:

[0138] ;

[0139] in, represents the input of the output layer, represents the weight coefficient between the intermediate neurons and the output layer neurons, represents the output of the output layer, Represents the non-negative Sigmoid function;

[0140] The calculation formula for PID control increment is as follows:

[0141] ;

[0142] in, Represents the PID control increment, that is Indicates the fan speed. 、 and represents the proportional gain, integral gain and differential gain, Indicates the deviation between the actual output and the expected output.

[0143] It should be noted that the PID control increment is calculated based on the difference between the control quantity at the current moment and the control quantity at the previous moment; based on the calculated PID control increment, the fan control quantity (such as fan speed) will be adjusted. The basic purpose of fan control is to help the system achieve more accurate temperature control by changing the fan speed. The change of the fan control quantity should be as smooth as possible to avoid excessive temperature fluctuations.

[0144] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited thereto. Various changes can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of the present invention.

Claims

1. A battery management system, characterized in that: include: A state determination unit (1), the state determination unit (1) is used to obtain the state of charge of each battery in the battery pack according to the ampere-hour integration method, and determine the average state of charge of the battery pack according to the state of charge of each battery in the battery pack; A difference calculation unit (2), the difference calculation unit (2) is used to determine the difference in state of charge of batteries in the same battery pack according to the state of charge of the battery, and to determine the difference in average state of charge of battery packs in the battery system according to the average state of charge of the battery pack; A balancing judgment unit (3), the balancing judgment unit (3) is used to judge whether the battery system and the battery pack are in an unbalanced state based on the state of charge difference of the batteries in the same battery pack and the average state of charge difference of the battery packs in the battery system; A state balancing unit (4), the state balancing unit (4) is used to perform intra-group balancing on the battery pack when the battery pack is in an unbalanced state, and to perform inter-group balancing on the battery system when the battery system is in an unbalanced state; A temperature control unit (5), the temperature control unit (5) being used to control the temperature of the battery pack according to a pre-trained temperature control model when the battery pack is being balanced within the pack; The temperature control model adopts a BP neural network and a PID control algorithm, wherein the input layer neuron variables of the BP neural network are the actual output temperature value, the expected output temperature value, the system error, and the control quantity. According to the BP neural network input variables, the Sigmoid function is used to obtain the input and output of the intermediate layer node of the BP neural network. The input and output of the output layer are determined according to the input and output of the intermediate layer node. The output of the output layer is the proportional gain, integral gain, and differential gain of the PID control algorithm. The PID control algorithm calculates the PID control quantity according to the output of the output layer, discretizes the PID control quantity to obtain a PID control increment, and controls the fan according to the PID control increment. The input and output expressions of the intermediate layer node are as follows: ； in, represents the input of the middle layer node, represents the weighted coefficient between the input layer neurons and the intermediate layer neurons, represents the input layer neuron variable, represents the output of the middle layer node, represents the Sigmoid function, represents the number of neurons in the middle layer; The input and output expressions of the output layer are as follows: ； in, represents the input of the output layer, represents the weight coefficient between the intermediate neurons and the output layer neurons, represents the output of the output layer, Represents the non-negative Sigmoid function; The calculation formula of the PID control increment is as follows: ； in, Represents the PID control increment, that is Indicates the fan speed. 、 and represents the proportional gain, integral gain and differential gain, Indicates the deviation between the actual output and the expected output.

2. A battery management system according to claim 1, characterized in that: The calculation formula of the average state of charge of the battery pack is as follows: ； in, Indicates the battery system The average state of charge of the battery pack, Indicates the battery system The first battery in the The state of charge of each battery, Indicates the battery system The total number of cells in a battery pack; The calculation formula for the state of charge difference of the batteries in the same battery pack is as follows: ； in, Indicates the battery system The first battery in the and The difference in state of charge between the batteries; The calculation formula for the average state of charge difference of the battery packs in the battery system is as follows: ； in, Indicates the battery system and The average state of charge difference between the battery packs.

3. A battery management system according to claim 2, characterized in that: Determining whether the battery system and the battery pack are in an unbalanced state based on the state of charge difference of the batteries in the same battery pack and the average state of charge difference of the battery packs in the battery system includes: determining whether the state of charge difference is greater than a preset first threshold, and if so, determining that the battery pack is in an unbalanced state; It is determined whether the average state of charge difference of the battery packs in the battery system is greater than a preset second threshold value. If the average state of charge difference is greater than the preset second threshold value, it is determined that the battery system is in an unbalanced state.

4. A battery management system according to claim 3, characterized in that: When the battery pack is in an unbalanced state, performing intra-group balancing on the battery pack includes: The battery with the highest state of charge in the same battery pack charges the battery with the lowest state of charge; When the difference between the state of charge of the battery with the highest state of charge and the state of charge of the batteries in the same battery pack that do not participate in balancing is less than a third threshold, the batteries in the same battery pack transfer excess state of charge to the battery with the lower state of charge; Determine whether the battery pack is in an unbalanced state, and if the battery pack is in an unbalanced state, repeat the above operation; When the battery pack is in a balanced state, it is determined whether the battery pack is in a working state. When the battery pack is in a working state, the battery pack is discharged in a balanced manner.

5. A battery management system according to claim 4, characterized in that: When the battery system is in an unbalanced state, performing inter-group balancing on the battery system includes: Determining whether the battery system is in working condition; When the battery system is in a working state, determining whether the battery system is in a charging state; When the battery system is in a charging state, the battery system is balanced charged according to a pre-trained charging control model.

6. A battery management system according to claim 5, characterized in that: The charging control model includes a charging optimization model and a deep reinforcement learning model. The charging optimization model includes a first objective function, a second objective function and constraints. The deep reinforcement learning model is used to solve the charging optimization model to obtain an optimal charging strategy.

7. A battery management system according to claim 6, characterized in that: The expression of the first objective function is as follows: ； in, represents the first objective function, express The corresponding number of sampling steps, Indicates the The state of charge at the sampling step, Indicates the target state of charge of the battery pack. Indicates the sampling period; The expression of the second objective function is as follows: ； in, represents the second objective function, Indicates the charging sampling period Time-of-use electricity prices, Indicates the charging current, Indicates charging voltage; The constraint condition is expressed as follows: ； in, Indicates the maximum allowable charging current, Indicates the maximum allowable charging voltage, Indicates the maximum value of the state of charge, Indicates the charging sampling period The temperature of the battery system, represents the maximum allowable battery system temperature, where , Indicates the charging sampling period The surface temperature of the battery system is Indicates the charging sampling period The core temperature of the battery system.

8. A battery management system according to claim 7, characterized in that: The deep reinforcement learning model is used to solve the charging optimization model to obtain the optimal charging strategy, including: Determining a reward function according to the constraints of the charging optimization model, wherein the reward function includes a first reward function, a second reward function, a third reward function, and a fourth reward function; Construct a charging strategy network and a strategy evaluation network, wherein the charging strategy network is used to control the charging current of the battery, and the strategy evaluation network is used to evaluate the selection of each charging strategy during training. The hidden layers of the charging strategy network and the strategy evaluation network are both fully connected layers. The first layer of the charging strategy network is a Relu function, and the second layer contains the expectation and variance of the battery charging strategy distribution. The activation function of the expectation part is the Tanh function, and the activation function of the variance part is the SoftPlus function. The strategy evaluation network contains a total of two layers of networks, the activation function of the first layer is the Relu function, and the activation function of the second layer is the Tanh function. The charging strategy is updated according to the charging objective function of the charging strategy network, wherein the charging objective function of the charging strategy network is as follows: ； in, represents the charging objective function of the charging strategy network, Represents the interval Find the mean, Represents the network parameters of the current round charging strategy, Indicates the network parameters of the charging strategy in the last update round, Indicates the current round battery charging strategy, Indicates the battery charging strategy of the previous round, Indicates the battery charging current In battery status The reward function under After the training phase, a charging strategy network that maximizes the total reward of the charging round is obtained. The strategy evaluation network used to assist in the training of the strategy network does not participate in the execution phase. The charging strategy network accepts the battery charging status and outputs the probability distribution of the charging strategy.

9. A battery management system according to claim 8, characterized in that: The first reward function is as follows: ； in, Indicates the charging sampling period The first reward function when ; The second reward function is as follows: ； in, represents the second reward function, Indicates the highest time-of-use electricity price in the past day; The third reward function is as follows: ； in, represents the third reward function; The fourth reward function is as follows: ； in, represents the fourth reward function.

Images