Battery pack equalization circuit and battery pack equalization control method

Abstract

The invention discloses a battery pack equalization circuit and a battery pack equalization control method. The battery pack equalization circuit comprises a battery pack, an equalization module, a switch array, a detection module and a control module, the detection module is connected with each single battery of the battery pack, the control module is connected with the detection module, the equalization module and the switch array, the input end of the equalization module is connected with the whole battery pack, and the output end is connected with the single batteries in the battery pack through the switch array; the detection module is configured to collect the single voltage of each single battery in the battery pack; the control module is configured to determine whether an equalization process needs to be started based on the monomer voltage; and after it is determined that the equalization process needs to be started, the switch array is controlled to communicate the to-be-equalized single batteries to the output end of the equalization module, and the equalization module is controlled to transfer the electric quantity between the whole battery pack and the to-be-equalized single batteries.

Description

Technical Field

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

[0002] In recent years, in order to solve the problem of energy shortage, renewable energy such as wind energy, solar energy, tidal energy, etc. has been vigorously developed around the world. However, new energy is extremely variable and unpredictable. In order to reduce the impact of unstable new energy power generation equipment on the power grid, energy storage technology is used to achieve a stable output power of new energy power generation equipment, among which battery energy storage is widely used.

[0003] In order to meet the requirements of output power, usage capacity and working voltage of the energy storage system, single cells are usually connected in series and parallel to form a battery pack for use. However, due to the different manufacturing processes of single cells, even the same batch of single cells from the same manufacturer will have slight differences in parameters. After a long period of cyclic use, the battery cells in the battery pack will age to different degrees, resulting in increased differences in parameters such as the internal resistance and state of charge of the battery cells, causing the battery pack to have problems with insufficient state of charge or overcharge / over-discharge of the battery cells, which will affect the state of charge and cycle life of the battery pack during use, and may also cause serious safety problems. Therefore, it is urgent to solve the above problems. Summary of the invention

[0004] The object of the present invention is to provide a battery pack balancing circuit and a battery pack balancing control method, which can achieve an active balancing effect by transferring the electricity between the battery pack and the single cells.

[0005] One aspect of the present invention provides a battery pack balancing circuit, comprising: a battery pack, a balancing module, a switch array, a detection module and a control module;

[0006] The detection module is connected to each single cell of the battery pack, the control module is respectively connected to the detection module, the balancing module and the switch array, the input end of the balancing module is connected to the entire battery pack, and the output end is connected to the single cells in the battery pack through the switch array;

[0007] The detection module is configured to: collect the single cell voltage of each single cell in the battery pack;

[0008] The control module is configured to: determine whether to start the balancing process based on the single cell voltage; and after determining that the balancing process needs to be started, control the switch array to connect the single cell to be balanced to the output end of the balancing module, and control the balancing module to transfer the power between the entire battery group and the single cell to be balanced.

[0009] Optionally, the battery pack includes N single cells connected in series, the switch array includes N switch elements connected in series, the battery pack balancing circuit includes N openable and closable loops, the N openable and closable loops are connected in series, and each openable and closable loop includes one single cell and one switch element; N is a positive integer greater than or equal to 2.

[0010] Optionally, the balancing module is a bidirectional DC-DC converter, the detection module is a sensor, and the control module is a microcontroller.

[0011] Another aspect of the present invention provides a battery pack balancing control method, the method comprising:

[0012] Obtaining the cell voltage of each cell in the battery pack;

[0013] Determining whether to start a balancing process based on the cell voltage;

[0014] If the balancing process needs to be started, the cell voltage of each single cell is input into a pre-trained balancing prediction model so that the balancing prediction model outputs a balancing strategy;

[0015] A control signal for performing battery pack balancing control is output according to the balancing strategy.

[0016] Optionally, the balancing strategy includes: balancing time, switching frequency and PWM wave duty cycle of the balancing module, and the on-off state of each switch element in the switch array.

[0017] Optionally, outputting a control signal for performing battery pack balancing control according to the balancing strategy includes:

[0018] During the balancing time, a switch array control signal is output according to each opening and closing state in the balancing strategy; wherein the switch array control signal is used to control each switch element in the switch array to open or close, so as to connect the single cell to be balanced to the output end of the balancing module; and

[0019] During the balancing time, a balancing module control signal is output according to the switching frequency and PWM wave duty cycle in the balancing strategy; wherein the balancing module control signal is used to control the switch element of the balancing module to open or close, so that the balancing module transfers the electric quantity between the entire battery pack and the single battery to be balanced; and the input end of the balancing module is connected to the entire battery pack.

[0020] Optionally, obtaining the cell voltage of each cell in the battery pack includes:

[0021] The control detection module collects the single cell voltage of each single cell in the battery pack; wherein the detection module is connected to each single cell of the battery pack;

[0022] The single cell voltage collected by the detection module is obtained.

[0023] Optionally, the equilibrium prediction model includes an input layer, L hidden layers and an output layer connected in sequence; L is a positive integer greater than or equal to 1;

[0024] The step of inputting the cell voltage of each cell into a pre-trained balancing prediction model so that the balancing prediction model outputs a balancing strategy includes:

[0025] Converting the cell voltage of each cell into a vector, recording it as a feature vector, and inputting the feature vector into the input layer;

[0026] Calculate the input vector and output vector of the i-th hidden layer based on the feature vector by the balanced prediction model; i is a positive integer greater than or equal to 1 and less than or equal to L;

[0027] Calculate the input vector and output vector of the output layer based on the output vector of the Lth hidden layer by the balanced prediction model;

[0028] The output vector is converted into the balancing strategy.

[0029] Optionally, the balanced prediction model calculates the input vector and output vector of the i-th hidden layer based on the feature vector through the following formula:

[0030] Z i =W i X i +B i ;

[0031] A i =σ i (Z i );

[0032] Among them, Z i is the input vector of the i-th hidden layer; when i is 1, W i is the weight matrix between the input layer and the first hidden layer, X i is the eigenvector, B i is the bias vector between the input layer and the first hidden layer; when i is not 1, W i is the weight matrix between the i-1th hidden layer and the i-th hidden layer, B i is the bias vector between the i-1th hidden layer and the i-th hidden layer, X iis the output vector of the i-1th hidden layer; A i is the output vector of the i-th hidden layer, σ i is the activation function of the i-th hidden layer.

[0033] Optionally, the balanced prediction model calculates the input vector and output vector of the output layer based on the output vector of the Lth hidden layer through the following formula:

[0034] Z′ L =W′ L A L +B′ L ;

[0035] A′ L =σ′(Z′ L );

[0036] Among them, Z′ L is the input vector of the output layer, W′ L is the weight matrix between the Lth hidden layer and the output layer, A L is the output vector of the Lth hidden layer, B′ L is the bias vector between the Lth hidden layer and the output layer, A′ L is the input vector of the output layer, and σ′ is the activation function of the output layer.

[0037] Optionally, determining whether to start a balancing process based on the cell voltage includes:

[0038] Determine the single cell voltage with the largest voltage and the electric body voltage with the smallest voltage;

[0039] Calculating the voltage difference between the single cell voltage with the largest voltage and the single cell voltage with the smallest voltage;

[0040] If the voltage difference is greater than or equal to a preset voltage threshold, it is determined that the balancing process needs to be started;

[0041] If the voltage difference is less than the voltage threshold, it is determined that there is no need to start the balancing process.

[0042] The battery pack balancing circuit and battery pack balancing control method provided by the present invention add control switches between battery packs and between single cells, modify the connection mode of the single cells in real time according to the status of the single cells, and then realize the transfer of electricity between battery packs and between single cells through a balancing module to achieve an active balancing effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0044] Figure 1 The structure diagram of the battery pack balancing circuit provided by the first embodiment of the present invention is shown;

[0045] Figure 2 A flow chart showing a method for controlling a battery pack balancing circuit according to a second embodiment of the present invention is shown;

[0046] Figure 3 The structure diagram of the balanced prediction model provided by the second embodiment of the present invention is shown. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0048] It should be noted that, in this article, the term "includes", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, if there are descriptions of "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes, and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the different elements and regions in the drawings are only schematically shown, so the present invention is not limited to the sizes and distances shown in the drawings.

[0049] Embodiment 1

[0050] Figure 1 FIG. 1 shows a structural diagram of a battery pack balancing circuit provided in Embodiment 1 of the present invention. Figure 1As shown, the battery pack balancing circuit includes: a battery pack, a balancing module, a switch array, a detection module and a control module;

[0051] The detection module is connected to each single cell of the battery pack, the control module is respectively connected to the detection module, the balancing module and the switch array, the input end of the balancing module is connected to the entire battery pack, and the output end is connected to the single cells in the battery pack through the switch array;

[0052] The detection module is configured to: collect the single cell voltage of each single cell in the battery pack;

[0053] The control module is configured to: determine whether to start the balancing process based on the single cell voltage; and after determining that the balancing process needs to be started, control the switch array to connect the single cell to be balanced to the output end of the balancing module, and control the balancing module to transfer the power between the entire battery group and the single cell to be balanced.

[0054] The battery pack includes a plurality of electric batteries, which are connected in series and / or in parallel. The input end of the balancing module is connected to the entire battery pack. Specifically, the input end of the balancing module ( Figure 1 The two lines on the left side of the balancing module shown in the figure are respectively connected to the positive and negative poles of the entire battery pack; the output end of the balancing module is connected to the single battery in the battery pack through the switch array. Specifically, the output end of the balancing module is respectively connected to the two ends of the switch array, and one end of each switch element is connected to the positive pole of the single battery, and the other end is connected to the negative pole of the single battery. The switch array includes a plurality of switch elements, and the plurality of switch elements are connected in series and / or in parallel. Controlling the balancing module to transfer the power between the entire battery pack and the single battery to be balanced can be: controlling the balancing module to charge the single battery to be balanced using the overall power of the battery pack.

[0055] As an optional embodiment, the battery pack includes N single cells connected in series, and the switch array includes N switch elements connected in series; N is a positive integer greater than or equal to 2.

[0056] In specific implementation, after the detection module collects the single cell voltage of each single cell in the battery pack, the control module determines whether the balancing flow needs to be started based on the single cell voltage. If it is determined that the balancing process needs to be started, the control module outputs a control signal to adjust the closing state of each switch element in the switch array based on the control signal, so that the single cell to be balanced is connected to the output end of the balancing module, and at the same time controls the switch element of the balancing module based on the control signal, so that the balancing module transfers the electricity between the entire battery pack and the single cell to be balanced.

[0057] For example, the control signal indicates to close the switch elements S1 and S3 in the switch array and to open the switch element S2 at the same time. Then, the single cell 2 is connected to the output end of the balancing module, and the control module controls the balancing module to transfer the power between the battery pack and the single cell 2. Specifically, the balancing module is controlled to charge the single cell 2 with the overall power of the battery pack.

[0058] In order to facilitate understanding of the connection relationship between the switch array and the battery pack in this embodiment, an embodiment can be defined as follows: the battery pack includes N single cells connected in series, the switch array includes N switch elements connected in series, the battery pack balancing circuit includes N openable and closable loops, the N openable and closable loops are connected in series, and each openable and closable loop includes one single cell and one switch element; N is a positive integer greater than or equal to 2.

[0059] The openable circuit is defined as: when the switch element is closed, the circuit is closed; when the switch element is opened, the circuit is opened. Different openable circuits include different single cells and different switch elements.

[0060] As an optional embodiment, the balancing module may be a bidirectional DC-DC converter, the detection module may be a sensor, and the control module may be a microcontroller. Specific circuit examples of the bidirectional DC-DC converter, microcontroller, and sensor may adopt existing technologies, and this application does not limit this.

[0061] The present application utilizes active balancing technology between battery packs and single cells to solve the defects of the prior art. Specifically, the present application adds control switches between battery packs and single cells, modifies the connection mode of the single cells in real time according to the voltage of the single cells, and then uses a balancing module to realize the transfer of power between battery packs and single cells, so as to achieve the effect of active balancing.

[0062] Embodiment 2

[0063] Embodiment 2 of the present invention provides a battery pack balancing control method. In view of the problem of unbalanced power in the single cells of the battery pack during use, this embodiment proposes a method of using a trained balancing prediction model to predict the balancing strategy. This embodiment can modify the connection mode between the single cells according to the current state of the battery pack, and transfer the power in the single cells through the balancing module, thereby solving the problem of unbalanced power in the single cells of the battery pack; at the same time, the balancing prediction model is used to generate a balancing strategy for the balancing module and the switch array, ensuring that the result after balancing can meet the preset balancing performance requirements of the battery pack. Through the balancing control scheme of this embodiment, the consistency of the battery capacity of the single cells of the battery pack can be improved, the discharge performance of the battery pack can be improved, and the service life of the battery pack can be extended.

[0064] Figure 2 FIG. 1 is a flow chart showing a battery pack balancing control method provided in Embodiment 2 of the present invention. The battery pack balancing control method can be applied to the control module of the battery pack balancing circuit in Embodiment 1. Figure 2 As shown, the method includes:

[0065] Step S1, obtaining the cell voltage of each cell in the battery pack.

[0066] The battery pack includes a plurality of single cells, which are connected in series and / or in parallel.

[0067] As an optional embodiment, step S1 includes:

[0068] The control detection module collects the single cell voltage of each single cell in the battery pack; wherein the detection module is connected to each single cell of the battery pack;

[0069] The single cell voltage collected by the detection module is obtained.

[0070] The detection module is connected to the control module, and the detection module can be a sensor, preferably a voltage sensor.

[0071] The single cell voltage of the single cell battery is collected by using a voltage sensor and the like, and the result is transmitted to the control module.

[0072] Step S2: determining whether to start a balancing process based on the cell voltage.

[0073] The purpose of this embodiment is to monitor the cell voltage of the battery cells in the battery pack in real time and determine whether the maximum and minimum values ​​of the voltage of the battery cells in the battery pack reach the preset equalization threshold. If the threshold is reached, the equalization process is started based on these cell voltages to achieve the preset equalization performance.

[0074] As an optional embodiment, step S2 includes:

[0075] Determine the single cell voltage with the largest voltage and the electric body voltage with the smallest voltage;

[0076] Calculating the voltage difference between the single cell voltage with the largest voltage and the single cell voltage with the smallest voltage;

[0077] If the voltage difference is greater than or equal to a preset voltage threshold, it is determined that the balancing process needs to be started;

[0078] If the voltage difference is less than the voltage threshold, it is determined that there is no need to start the balancing process.

[0079] As an optional embodiment, step S2 includes:

[0080] Determine whether there are any two monomer voltages whose difference is greater than or equal to a preset voltage threshold value among the collected monomer voltages;

[0081] If so, it is determined that the balancing process needs to be started;

[0082] If not, it is determined that there is no need to initiate the balancing process.

[0083] Step S3: if the balancing process needs to be started, the single cell voltage of each single cell is input into a pre-trained balancing prediction model, so that the balancing prediction model outputs a balancing strategy.

[0084] The balancing strategy includes: balancing time, switching frequency and PWM wave duty cycle of the balancing module, and the on-off state of each switch element in the switch array.

[0085] By using the pre-trained equalization prediction model to generate the equalization strategy, the preset battery pack equalization performance can be achieved without designing a complex control algorithm, which simplifies the design of the active equalization control algorithm and avoids complex control logic. By using the voltage of the single battery in the battery pack collected in real time as the input of the equalization prediction model and generating control signals in real time, the battery cells in the battery pack can be effectively prevented from being over-equalized or incompletely equalized.

[0086] In practical applications, the voltage of a single cell is often used to measure the state of charge of the battery. Therefore, the collected voltage value of the single cell is used as the input signal of the balancing prediction model so that the balancing prediction model outputs a balancing strategy, and the control module outputs a corresponding control signal according to the balancing strategy.

[0087] As an optional embodiment, the balanced prediction model includes an input layer, L hidden layers and an output layer connected in sequence; L is a positive integer greater than or equal to 1;

[0088] Step S3 includes:

[0089] Converting the cell voltage of each cell into a vector, recording it as a feature vector, and inputting the feature vector into the input layer;

[0090] Calculate the input vector and output vector of the i-th hidden layer based on the feature vector by the balanced prediction model; i is a positive integer greater than or equal to 1 and less than or equal to L;

[0091] Calculate the input vector and output vector of the output layer based on the output vector of the Lth hidden layer by the balanced prediction model;

[0092] The output vector is converted into the balancing strategy.

[0093] As an optional embodiment, the balanced prediction model calculates the input vector and output vector of the i-th hidden layer based on the feature vector through the following formula:

[0094] Z i =W i X i +B i ;

[0095] A i =σ i (Z i );

[0096] Among them, Z i is the input vector of the i-th hidden layer; when i is 1, W i is the weight matrix between the input layer and the first hidden layer, X i is the eigenvector, B i is the bias vector between the input layer and the first hidden layer; when i is not 1, W i is the weight matrix between the i-1th hidden layer and the i-th hidden layer, B i is the bias vector between the i-1th hidden layer and the i-th hidden layer, X i is the output vector of the i-1th hidden layer; A i is the output vector of the i-th hidden layer, σ i is the activation function of the i-th hidden layer.

[0097] As an optional embodiment, the balanced prediction model calculates the input vector and output vector of the output layer based on the output vector of the Lth hidden layer through the following formula:

[0098] Z′ L =W′ L A L +B′ L ;

[0099] A′ L =σ′(Z′ L );

[0100] Among them, Z′ L is the input vector of the output layer, W′ L is the weight matrix between the Lth hidden layer and the output layer, A L is the output vector of the Lth hidden layer, B′ L is the bias vector between the Lth hidden layer and the output layer, A′ L is the input vector of the output layer, and σ′ is the activation function of the output layer.

[0101] This embodiment also provides a training method for a balancing prediction model for outputting a balancing strategy of a battery pack balancing circuit, wherein the balancing prediction model can be obtained by training a BP neural network. The BP neural network model is trained using training samples of a specific battery pack until the output signal can meet the preset balancing performance requirements of the battery pack. The structure of the BP neural network is: an input layer, L hidden layers, and an output layer, where L is an integer greater than or equal to 1. For example, Figure 3 As shown in the figure, the input layer has n nodes, the output layer has m nodes, and each hidden layer has h nodes. The input signal of each node is weighted and then the output signal is generated through the activation function.

[0102] In the process of training the BP neural network, for a training sample X = (x_1, x_2, ..., x_n), the forward propagation calculates the output of each node. Among them, the input of each training sample is a group of single-cell voltages of single-cell electric bodies, and the output value is the balancing time, the switching frequency and PWM wave duty cycle of the switch elements of the balancing module, and the opening and closing state of each switch element in the switch array. For different battery packs, repeated experiments of various situations are required to obtain training samples to train the BP neural network.

[0103] The calculation formula for data transmission from the input layer to the output layer during the training process is consistent with the above-mentioned equilibrium prediction model and will not be described here. During the training process, the BP neural network continuously updates the weight value and bias value to improve the accuracy of the output. Specifically, assuming that the actual output of the output layer is y and the target output is t, the mean squared error (MSE) is:

[0104]

[0105] Where E is the error sum of squares, y i is the actual output of the ith node in the output layer, t i is the target output corresponding to the i-th node, and m is the number of nodes in the output layer.

[0106] Calculate the error term for each node in the output layer:

[0107]

[0108] in, is the error term of the i-th node in the output layer, The activation function of the output layer is The derivative at is the input vector corresponding to the i-th node in the output layer.

[0109] Calculate the error term for each node in the hidden layer:

[0110]

[0111] in, is the error term of the ith node in the lth hidden layer, is the error term of the jth node in the l+1th hidden layer, h l+1 is the number of nodes in the l+1th hidden layer, is the weight matrix between the jth node and the ith node in the l+1th hidden layer, is the activation function of the hidden layer. The derivative at is the input vector of the ith node in the lth hidden layer.

[0112] Update the weight matrix according to the error term:

[0113]

[0114] Update the bias vector:

[0115]

[0116] in, is the output vector of the ith node in the l-1th hidden layer; η is the preset learning rate, which is used to control the update step size; is the bias vector of the i-th node in the l-th hidden layer.

[0117] Iteratively train the BP neural network and repeat the above steps of forward propagation, error calculation, error back propagation and weight update until the error meets the predetermined threshold or reaches the maximum number of iterations.

[0118] Step S4: outputting a control signal for performing battery pack balancing control according to the balancing strategy.

[0119] The control signal is used to control the switch array to connect the single cell to be balanced to the output end of the balancing module, and control the balancing module to transfer the power between the entire battery pack and the single cell to be balanced. Specifically, the control module controls the switch elements of the balancing module and the switch devices in the switch array according to the control signal and the balancing time, so as to change the connection mode of the single cell in the battery pack and the buck-boost value of the balancing module, and balance the battery cells that need to be balanced.

[0120] As an optional embodiment, step S4 includes:

[0121] During the balancing time, a switch array control signal is output according to each opening and closing state in the balancing strategy; wherein the switch array control signal is used to control each switch element in the switch array to open or close, so as to connect the single cell to be balanced to the output end of the balancing module; and

[0122] During the balancing time, a balancing module control signal is output according to the switching frequency and PWM wave duty cycle in the balancing strategy; wherein the balancing module control signal is used to control the switch element of the balancing module to open or close, so that the balancing module transfers the electric quantity between the entire battery pack and the single battery to be balanced; and the input end of the balancing module is connected to the entire battery pack.

[0123] As an optional embodiment, the method further includes:

[0124] After the balancing time is exceeded, a first stop control signal and a second stop control signal are output, wherein the first stop control signal is used to control the disconnection of each switch element of the switch array, and the second stop control signal is used to control the disconnection of the switch element of the balancing module, so that the balancing module stops balancing the battery group.

[0125] The present invention uses a pre-trained balancing prediction model to output a balancing strategy, and does not require the control module to frequently calculate. The control module monitors the single cell voltage of the single cell in the battery pack in real time. When the current single cell needs to be balanced, the pre-trained balancing prediction model is used to output the balancing strategy; when balancing is not required, the control module only performs real-time monitoring, and does not need to perform calculations related to the balancing prediction model all the time. This means that the control module can obtain the balancing strategy required to achieve the preset balancing performance after one calculation, without the need for continuous logical judgment and calculation, which greatly saves the real-time performance overhead of the control module, and does not require a high-performance control module to meet the needs.

[0126] It should be understood by those skilled in the art that the modules or steps of the above-mentioned embodiments of the present invention can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than that here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the embodiments of the present invention are not limited to any specific combination of hardware and software.

[0127] It should be noted that the serial numbers of the embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0128] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method.

[0129] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A battery pack balancing circuit, characterized in that: include: Battery pack, balancing module, switch array, detection module and control module; The detection module is connected to each single cell of the battery pack, the control module is respectively connected to the detection module, the balancing module and the switch array, the input end of the balancing module is connected to the entire battery pack, and the output end is connected to the single cells in the battery pack through the switch array; The detection module is configured to: collect the single cell voltage of each single cell in the battery pack; The control module is configured to: determine whether to start a balancing process based on the cell voltage; After determining that the balancing process needs to be started, the switch array is controlled to connect the single cell to be balanced to the output end of the balancing module, and the balancing module is controlled to transfer the electricity between the entire battery group and the single cell to be balanced.

2. The battery pack equalization circuit according to claim 1, characterized in that: The battery pack includes N single cells connected in series, the switch array includes N switch elements connected in series, the battery pack balancing circuit includes N openable and closable loops, the N openable and closable loops are connected in series, and each openable and closable loop includes one single cell and one switch element; N is a positive integer greater than or equal to 2.

3. The battery pack equalization circuit according to claim 1, characterized in that: The balancing module is a bidirectional DC-DC converter, the detection module is a sensor, and the control module is a microcontroller.

4. A battery pack balancing control method, characterized in that: The method comprises: Obtaining the cell voltage of each cell in the battery pack; Determining whether to start a balancing process based on the cell voltage; If the balancing process needs to be started, the cell voltage of each single cell is input into a pre-trained balancing prediction model so that the balancing prediction model outputs a balancing strategy; A control signal for performing battery pack balancing control is output according to the balancing strategy.

5. The battery pack balancing control method according to claim 4, characterized in that: The balancing strategy includes: balancing time, switching frequency and PWM wave duty cycle of the balancing module, and the on-off state of each switch element in the switch array.

6. The battery pack balancing control method according to claim 5, characterized in that: Outputting a control signal for performing battery pack balancing control according to the balancing strategy includes: During the balancing time, a switch array control signal is output according to each opening and closing state in the balancing strategy; wherein the switch array control signal is used to control each switch element in the switch array to open or close, so as to connect the single cell to be balanced to the output end of the balancing module; and During the balancing time, a balancing module control signal is output according to the switching frequency and PWM wave duty cycle in the balancing strategy; wherein the balancing module control signal is used to control the switch element of the balancing module to open or close, so that the balancing module transfers the electric quantity between the entire battery pack and the single battery to be balanced; and the input end of the balancing module is connected to the entire battery pack.

7. The battery pack balancing control method according to claim 4, characterized in that: The step of obtaining the cell voltage of each cell in the battery pack includes: The control detection module collects the single cell voltage of each single cell in the battery pack; wherein the detection module is connected to each single cell of the battery pack; The single cell voltage collected by the detection module is obtained.

8. The battery pack balancing control method according to claim 4, characterized in that: The balanced prediction model includes an input layer, L hidden layers and an output layer connected in sequence; L is a positive integer greater than or equal to 1; The step of inputting the cell voltage of each cell into a pre-trained balancing prediction model so that the balancing prediction model outputs a balancing strategy includes: Converting the cell voltage of each cell into a vector, recording it as a feature vector, and inputting the feature vector into the input layer; Calculate the input vector and output vector of the i-th hidden layer based on the feature vector by the balanced prediction model; i is a positive integer greater than or equal to 1 and less than or equal to L; Calculate the input vector and output vector of the output layer based on the output vector of the Lth hidden layer by the balanced prediction model; The output vector is converted into the balancing strategy.

9. The battery pack balancing control method according to claim 8, characterized in that: The balanced prediction model calculates the input vector and output vector of the i-th hidden layer based on the feature vector through the following formula: Z i =W i X i +B i ; A i =σ i (Z i ); Among them, Z i is the input vector of the i-th hidden layer; when i is 1, W i is the weight matrix between the input layer and the first hidden layer, X i is the eigenvector, B i is the bias vector between the input layer and the first hidden layer; when i is not 1, W i is the weight matrix between the i-1th hidden layer and the i-th hidden layer, B i is the bias vector between the i-1th hidden layer and the i-th hidden layer, X i is the output vector of the i-1th hidden layer; A i is the output vector of the i-th hidden layer, σ i is the activation function of the i-th hidden layer.

10. The battery pack balancing control method according to claim 4, characterized in that: The determining whether to start the balancing process based on the cell voltage includes: Determine the single cell voltage with the largest voltage and the electric body voltage with the smallest voltage; Calculating the voltage difference between the single cell voltage with the largest voltage and the single cell voltage with the smallest voltage; If the voltage difference is greater than or equal to a preset voltage threshold, it is determined that the balancing process needs to be started; If the voltage difference is less than the voltage threshold, it is determined that there is no need to start the balancing process.

Images