A method, device, equipment and medium for online estimation of health status of energy storage battery

Abstract

The present invention belongs to the field of electrical engineering technology and discloses a method, device, equipment and medium for online estimation of the health status of an energy storage battery; the method comprises: obtaining the current mid-segment capacity Q of the energy storage battery; now ; Obtain the operating data of the energy storage battery under the current state for a period of time and input it into the pre-trained initial mid-segment capacity prediction model to obtain the initial mid-segment capacity Q of the energy storage battery start ; According to the current mid-segment capacity Q of the energy storage battery now and the initial mid-segment capacity Q of the energy storage battery start Calculate the SOH of the energy storage battery in its current state. This method is based on incremental capacity analysis (ICA) and combines artificial intelligence technology, starting from the electrochemical characteristics of the energy storage battery. The method is more reliable and has higher accuracy.

Description

Technical Field

[0001] The present invention belongs to the field of electrical engineering technology, and in particular relates to a method, device, equipment and medium for online estimation of the health status of an energy storage battery. Background Art

[0002] With the development of energy storage battery technology, it has gradually been introduced as a commonly used energy storage element in electric vehicles, portable electronic devices and various devices with energy storage needs to achieve the storage and conversion of electrical energy. For energy storage batteries, the state of health (SOH) is the most critical state quantity. There is no unified definition of SOH. It is usually defined by the change in energy storage battery capacity and internal resistance. It can quantitatively describe the aging of energy storage batteries. Accurate SOH estimation directly affects the performance of energy storage batteries and provides an important reference for the replacement of aging energy storage batteries. It is of great significance for the optimal performance and safe operation of energy storage batteries.

[0003] Chinese patent application publication number CN115219937A discloses a method for estimating the health status of energy storage batteries with different aging paths based on deep learning, including: obtaining battery charging voltage data under different working conditions of the energy storage battery, inputting it into a battery health estimation model, and outputting the battery health status estimation value under the corresponding working condition; the battery health estimation model is constructed based on a deep neural network and trained twice; the first training: training the battery health estimation model with battery aging experimental data under a certain working condition; the second training: freezing the core network layer parameters of the pre-trained estimation model and calling its model parameters; then training the optimized estimation model with battery aging experimental data under different working conditions to adjust the parameters of its fully connected output layer to obtain the trained battery health estimation model. The present invention can be applied to battery health status estimation under various working conditions and does not require large-scale training data, thereby reducing the difficulty and cost of training the estimation model and increasing the scope of application of the estimation model.

[0004] The data used in the training model of this method is experimental data rather than real operating data, which cannot reflect the actual operating conditions of the actual battery. When the prediction model trained in this way is applied to real scenarios, the prediction accuracy cannot be guaranteed; the only characteristic variable used to train the model is voltage, and the input variable is too simple; the algorithm used belongs to the field of deep learning and has high requirements for hardware configuration; the deep learning algorithm used belongs to artificial intelligence technology, the method is too simple, and does not involve electrochemical principles, so it is not convincing enough. Summary of the Invention

[0005] The purpose of the present invention is to provide a method, device, equipment and medium for online estimation of the health status of energy storage batteries, so as to solve the technical problem that the existing technology has a single input variable and a single method, resulting in an inability to guarantee prediction accuracy.

[0006] Compared with the prior art, the present invention has the following beneficial effects:

[0007] In a first aspect, the present invention provides a method for online estimation of the health status of an energy storage battery, comprising:

[0008] Get the current mid-range capacity Q of the energy storage battery now ;

[0009] Obtain the operating data of the energy storage battery under the current state for a period of time and input it into the pre-trained initial mid-segment capacity prediction model to obtain the initial mid-segment capacity Q of the energy storage battery. start ;

[0010] According to the current mid-segment capacity Q of the energy storage battery now and the initial mid-segment capacity Q of the energy storage battery start Calculate the SOH of the energy storage battery in the current state:

[0011]

[0012] A further improvement of the present invention is that the operating data includes voltage, current and temperature.

[0013] A further improvement of the present invention is that the current mid-segment capacity Q of the energy storage battery now Obtained by the following steps:

[0014] Obtain the IC curve of the energy storage battery and calculate the mid-segment capacity Q of the energy storage battery based on the IC curve now ;

[0015]

[0016] Q(u) represents the battery capacity when the voltage is u; ICA(u) represents the ICA value when the voltage is u; u1 is the voltage corresponding to the second peak of the IC curve, and u2 is selected as the minimum cutoff voltage that all battery cells can reach.

[0017] A further improvement of the present invention is that the IC curve is obtained by the following steps:

[0018] Acquire real operating data of the energy storage battery; the real operating data of the energy storage battery includes voltage, current, and temperature;

[0019] Based on the actual operating data of the energy storage battery, the charging capacity of the energy storage battery is calculated by the ampere-hour integration method, and a first curve graph is drawn with the charging capacity as the horizontal axis and the battery voltage as the vertical axis, the first curve graph having a first curve;

[0020] exchanging the horizontal and vertical coordinates of the first curve graph to obtain a second curve graph having a second curve;

[0021] The second curve is derived based on the voltage to obtain an IC curve with the ordinate being the ICA value and the abscissa being the battery voltage.

[0022] A further improvement of the present invention is that the pre-trained initial mid-segment capacity prediction model is obtained by the following steps:

[0023] Using artificial intelligence algorithms, a regression model is established to reflect the relationship between the initial mid-segment capacity of the battery and the battery operating parameters;

[0024] Collect the actual operating data of the battery in its initial operating state and organize it into input and output data sets; the input features include the voltage, current, and temperature of the battery cell; calculate the initial mid-segment capacity Q by integration start Organize it into the output of the training data set and use it as the predicted target value of the model;

[0025] The regression model is trained based on the organized input and output data sets; the initial mid-segment capacity Q is obtained. start Initial mid-segment capacity prediction model.

[0026] A further improvement of the present invention is that the artificial intelligence algorithm is an artificial intelligence algorithm with regression prediction function.

[0027] A further improvement of the present invention is that the artificial intelligence algorithm is XGboost.

[0028] In a second aspect, the present invention provides an online estimation device for the health status of an energy storage battery, comprising:

[0029] Acquisition module, used to obtain the current mid-segment capacity Q of the energy storage battery now ;

[0030] The prediction module is used to obtain the operating data of the energy storage battery under the current state for a period of time and input it into the pre-trained initial mid-segment capacity prediction model to obtain the initial mid-segment capacity Q of the energy storage battery. start ;

[0031] The estimation module is used to estimate the current mid-segment capacity Q of the energy storage battery. now and the initial mid-segment capacity Q of the energy storage battery start Calculate the SOH of the energy storage battery in the current state:

[0032]

[0033] In a third aspect, the present invention provides an electronic device comprising a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the method for online estimation of the health status of an energy storage battery.

[0034] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the method for online estimation of the health status of an energy storage battery is implemented.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The present invention provides a method, device, equipment and medium for online estimation of the health status of an energy storage battery, the method comprising: obtaining the current mid-segment capacity Q of the energy storage battery; now ; Obtain the operating data of the energy storage battery under the current state for a period of time and input it into the pre-trained initial mid-segment capacity prediction model to obtain the initial mid-segment capacity Q of the energy storage battery start ; According to the current mid-segment capacity Q of the energy storage battery now and the initial mid-segment capacity Q of the energy storage battery start Calculate the SOH of the energy storage battery in the current state. The method of the present invention comprehensively considers the battery operation data including voltage, current and temperature as input, which is more multivariate and stable than the input variables of the prior art; the input data is input into the pre-trained initial mid-segment capacity prediction model to obtain the initial mid-segment capacity Q of the energy storage battery. start ; According to the current mid-segment capacity Q of the energy storage battery now and the initial mid-segment capacity Q of the energy storage battery start Calculate the SOH of the energy storage battery in its current state; the present invention is based on incremental capacity analysis (ICA) and combines artificial intelligence technology, starting from the electrochemical essential characteristics of the energy storage battery. The method is more reliable and has higher accuracy.

[0037] The method of the present invention is widely applicable to practical applications such as peak shaving and frequency modulation. The model training uses real-world operating data, making it more suitable for real-world applications and achieving higher prediction accuracy than models trained using experimental data. The method of the present invention is robust to variations in depth of discharge (DoD), charge current, and temperature, meeting the requirements of real-world energy storage batteries. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings, which constitute part of the present invention, are intended to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are intended to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0039] Figure 1 It is the IC curve flow chart;

[0040] Figure 2 This is a schematic diagram of ICA mid-section capacity calculation;

[0041] Figure 3 A schematic flow chart of an online estimation method for the health status of an energy storage battery according to the present invention;

[0042] Figure 4 This is a structural block diagram of an online estimation device for the health status of an energy storage battery according to the present invention;

[0043] Figure 5 This is a structural block diagram of an electronic device of the present invention. DETAILED DESCRIPTION

[0044] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that, in the absence of conflict, the embodiments and features of the embodiments of the present invention can be combined with each other.

[0045] The following detailed description is an exemplary description and is intended to provide further detailed description of the present invention. Unless otherwise indicated, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present invention belongs. The terms used in the present invention are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention.

[0046] Energy storage batteries age over multiple charge and discharge cycles and are monitored using a battery management system (BMS). This paper develops an online method for estimating the health status of energy storage batteries based on incremental capacity analysis (ICA) and artificial intelligence technology.

[0047] The sensors required to determine SoH should be as simple as possible to ensure that the BMS remains cost-effective. This invention utilizes only existing BMS measurements of voltage, current, and temperature. This approach exploits the battery's response characteristics under actual operating conditions. Classical methods typically use the state of charge as the basis for analysis because this state is much easier to control than the discharge state. Therefore, it is necessary to obtain as much information as possible from the current, voltage, and temperature measurements during the battery's charging phase.

[0048] Incremental capacity analysis is an electrochemical technique that obtains information about the internal state of a battery simply by measuring its voltage and current. The incremental capacity (IC) represents the change in capacity associated with a voltage step. The IC curve equation is:

[0049]

[0050] Q represents the charging capacity, U Cell Representing the battery voltage, each peak of the incremental capacity curve has a unique shape, intensity, and position, characterizing the electrochemical processes occurring within the battery. Because the battery voltage varies within a range of only 150mV when the state of charge changes from 10% to 90%, direct voltage analysis is inaccurate for determining any battery state for this battery technology. Therefore, online capacity estimation using incremental capacity analysis (ICA) is more effective.

[0051] Example 1

[0052] The present invention provides an online estimation method for the state of health of an energy storage battery. The method is based on incremental capacity analysis (ICA) and innovatively integrates an artificial intelligence algorithm to perform online estimation of the state of health of the energy storage battery. The integral area of ​​the curve between u1 and u2 is used as the characteristic factor for SOH estimation. The method specifically includes the following steps:

[0053] S1: Obtain the actual operating data of the energy storage battery, including the actual measured values ​​of voltage, current, and temperature;

[0054] S2: Based on the actual operating data of the energy storage battery, the charging capacity of the energy storage battery is calculated by the ampere-hour integration method, and a first curve graph is drawn with the charging capacity as the horizontal axis and the battery voltage as the vertical axis, the first curve graph having a first curve;

[0055] S3: swapping the horizontal and vertical coordinates of the first curve graph obtained in step S2 to obtain a second curve graph having a second curve;

[0056] S4: Derivative the second curve obtained in step S3 based on the voltage to obtain an IC curve with the ordinate being the ICA value and the abscissa being the battery voltage. The calculation formula is as follows:

[0057]

[0058] Among them, U cell Indicates the voltage of the battery cell; Q(U cell ) indicates that the voltage of the battery cell is U cell capacity when ICA(U cell ) indicates that the voltage of the battery cell is U cell ICA allows analysis of the shape of the voltage curve (slope and platform) rather than the absolute value. Figure 1 The figure shows the steps of obtaining the IC curve from step S1 to step S4.

[0059] S5: Estimate the SOH of the energy storage battery based on the ICA mid-segment capacity (curve integral area between u1 and u2) and apply ICA. Therefore, calculate the curve integral area Q between u1 and u2 now Represents the current mid-segment capacity, Q now The calculation formula is as follows:

[0060]

[0061] like Figure 2 As shown, Q(u) represents the capacity of the battery when the voltage is u; ICA(u) represents the ICA value of the battery when the voltage is u; u1 is the voltage value corresponding to the second peak of the IC curve, and u2 is selected as the minimum cut-off voltage that all battery cells can reach.

[0062] S6: The initial mid-range capacity of the battery (Q start ) prediction model, input the operating data (voltage, current, temperature) of the energy storage battery under the current state for a period of time into the initial mid-segment capacity prediction model to obtain the initial mid-segment capacity Q of the energy storage battery start , so that the SOH of the energy storage battery in the current state can be estimated. The formula is as follows:

[0063]

[0064] Build the initial mid-range capacity of the battery (Q start )Prediction model:

[0065] Since the actual operation of energy storage projects will be affected by two factors, the initial mid-range capacity of the battery (Q start ) is one of the innovations of the present invention. On the one hand, it is difficult to obtain the initial operating data of the actual energy storage project, so it is impossible to calculate the initial mid-segment capacity (Q start ); On the other hand, even if the initial mid-segment capacity (Q start ), but the battery will have various operating conditions during subsequent operation. The initial mid-segment capacity (Q start ) will also undergo various changes in the future, and it cannot truly reflect the initial capacity state of the battery, so the above method cannot be used to estimate SOH.

[0066] Therefore, one of the key technologies of the present invention is to realize the initial mid-segment capacity (Q start ). Model training is performed based on the previously organized input and output datasets:

[0067] Step 101: Using, but not limited to, an artificial intelligence algorithm with regression prediction capabilities, such as XGboost, to establish a regression model reflecting the relationship between the initial mid-segment capacity of the battery and the battery operating parameters;

[0068] Step 102: Collect the actual operating data of the battery in the initial operating state and organize it into input and output data sets; the input features include the voltage, current, and temperature of the battery cell; calculate the capacity difference between u1 and u2 (initial mid-segment capacity Q start ) The output of the training data set is used as the predicted target value of the model;

[0069] Step 103: Based on the sorted input and output data sets, the regression model is trained to obtain the initial mid-segment capacity (Q start )’s initial mid-segment capacity prediction model;

[0070] Step 104: Verify the accuracy of the initial mid-segment capacity prediction model. If the error between the predicted effect parameter and the preset effect parameter is less than a preset threshold, it is considered that the initial mid-segment capacity prediction model is accurate and meets expectations.

[0071] When predicting the initial mid-segment capacity of the battery (Q start ), calculate Q now The SOH of the energy storage battery during actual operation can be estimated using the following formula:

[0072]

[0073] Example 2

[0074] See also Figure 3 As shown, the present invention provides an online estimation method for the health status of an energy storage battery, comprising:

[0075] S100, obtain the current mid-segment capacity Q of the energy storage battery now ;

[0076] S200, obtain the operating data of the energy storage battery under the current state for a period of time and input it into the pre-trained initial mid-segment capacity prediction model to obtain the initial mid-segment capacity Q of the energy storage battery. start ;

[0077] S300, based on the current mid-segment capacity Q of the energy storage battery now and the initial mid-segment capacity Q of the energy storage battery start Calculate the SOH of the energy storage battery in the current state:

[0078]

[0079] In a specific embodiment, the operating data includes voltage, current and temperature.

[0080] In one embodiment: the current mid-segment capacity Q of the energy storage battery now Obtained by the following steps:

[0081] Obtain the IC curve of the energy storage battery and calculate the mid-segment capacity Q of the energy storage battery based on the IC curve now ;

[0082]

[0083] Q(u) represents the battery capacity when the voltage is u; ICA(u) represents the ICA value when the voltage is u; u1 is the voltage corresponding to the second peak of the IC curve, and u2 is selected as the minimum cutoff voltage that all battery cells can reach.

[0084] In one embodiment, the IC curve is obtained by the following steps:

[0085] Acquire real operating data of the energy storage battery; the real operating data of the energy storage battery includes voltage, current, and temperature;

[0086] Based on the actual operating data of the energy storage battery, the charging capacity of the energy storage battery is calculated by the ampere-hour integration method, and a first curve graph is drawn with the charging capacity as the horizontal axis and the battery voltage as the vertical axis, the first curve graph having a first curve;

[0087] exchanging the horizontal and vertical coordinates of the first curve graph to obtain a second curve graph having a second curve;

[0088] The second curve is derived based on the voltage to obtain an IC curve with the ordinate being the ICA value and the abscissa being the battery voltage.

[0089] In one embodiment, the pre-trained initial mid-segment capacity prediction model is obtained by the following steps:

[0090] Using artificial intelligence algorithms, a regression model is established to reflect the relationship between the initial mid-segment capacity of the battery and the battery operating parameters;

[0091] Collect the actual operating data of the battery in its initial operating state and organize it into input and output data sets; the input features include the voltage, current, and temperature of the battery cell; calculate the initial mid-segment capacity Q by integration start Organize it into the output of the training data set and use it as the predicted target value of the model;

[0092] The regression model is trained based on the organized input and output data sets; the initial mid-segment capacity Q is obtained. start Initial mid-segment capacity prediction model.

[0093] In a specific embodiment: the artificial intelligence algorithm is an artificial intelligence algorithm with regression prediction function.

[0094] In a specific implementation: the artificial intelligence algorithm is XGboost.

[0095] Example 3

[0096] See also Figure 4 As shown, the present invention provides an online estimation device for the health status of an energy storage battery, comprising:

[0097] Acquisition module, used to obtain the current mid-segment capacity Q of the energy storage battery now ;

[0098] The prediction module is used to obtain the operating data of the energy storage battery under the current state for a period of time and input it into the pre-trained initial mid-segment capacity prediction model to obtain the initial mid-segment capacity Q of the energy storage battery. start ;

[0099] The estimation module is used to estimate the current mid-segment capacity Q of the energy storage battery. now and the initial mid-segment capacity Q of the energy storage battery start Calculate the SOH of the energy storage battery in the current state:

[0100]

[0101] In a specific embodiment, the operating data includes voltage, current and temperature.

[0102] In one embodiment: the current mid-segment capacity Q of the energy storage battery now Obtained by the following steps:

[0103] Obtain the IC curve of the energy storage battery and calculate the mid-segment capacity Q of the energy storage battery based on the IC curve now ;

[0104]

[0105] Q(u) represents the battery capacity when the voltage is u; ICA(u) represents the ICA value when the voltage is u; u1 is the voltage corresponding to the second peak of the IC curve, and u2 is selected as the minimum cutoff voltage that all battery cells can reach.

[0106] In one embodiment, the IC curve is obtained by the following steps:

[0107] Acquire real operating data of the energy storage battery; the real operating data of the energy storage battery includes voltage, current, and temperature;

[0108] Based on the actual operating data of the energy storage battery, the charging capacity of the energy storage battery is calculated by the ampere-hour integration method, and a first curve graph is drawn with the charging capacity as the horizontal axis and the battery voltage as the vertical axis, the first curve graph having a first curve;

[0109] exchanging the horizontal and vertical coordinates of the first curve graph to obtain a second curve graph having a second curve;

[0110] The second curve is derived based on the voltage to obtain an IC curve with the ordinate being the ICA value and the abscissa being the battery voltage.

[0111] In one embodiment, the pre-trained initial mid-segment capacity prediction model is obtained by the following steps:

[0112] Using artificial intelligence algorithms, a regression model is established to reflect the relationship between the initial mid-segment capacity of the battery and the battery operating parameters;

[0113] Collect the actual operating data of the battery in its initial operating state and organize it into input and output data sets; the input features include the voltage, current, and temperature of the battery cell; calculate the initial mid-segment capacity Q by integration start Organize it into the output of the training data set and use it as the predicted target value of the model;

[0114] The regression model is trained based on the organized input and output data sets; the initial mid-segment capacity Q is obtained. start Initial mid-segment capacity prediction model.

[0115] In a specific embodiment: the artificial intelligence algorithm is an artificial intelligence algorithm with regression prediction function.

[0116] In a specific implementation: the artificial intelligence algorithm is XGboost.

[0117] Example 4

[0118] See also Figure 5 As shown, the present invention also provides an electronic device 100 for implementing an online estimation method for the health status of an energy storage battery; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0119] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the method for online estimating the health status of an energy storage battery described in Example 1 or 2 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 may mainly include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area may store data (such as audio data) created based on the use of the electronic device 100. In addition, the memory 101 may include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device.

[0120] The at least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100 and connects various parts of the entire electronic device 100 using various interfaces and lines.

[0121] The memory 101 in the electronic device 100 stores a plurality of instructions to implement an online estimation method for the health status of an energy storage battery. The processor 102 can execute the plurality of instructions to implement:

[0122] Get the current mid-range capacity Q of the energy storage battery now ;

[0123] Obtain the operating data of the energy storage battery under the current state for a period of time and input it into the pre-trained initial mid-segment capacity prediction model to obtain the initial mid-segment capacity Q of the energy storage battery. start ;

[0124] According to the current mid-segment capacity Q of the energy storage battery nowand the initial mid-segment capacity Q of the energy storage battery start Calculate the SOH of the energy storage battery in the current state:

[0125]

[0126] Example 5

[0127] If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0128] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0129] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0130] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0131] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for online estimation of the health status of an energy storage battery, characterized in that: include: Get the current mid-range capacity Q of the energy storage battery now ; Obtain the operating data of the energy storage battery under the current state for a period of time and input it into the pre-trained initial mid-segment capacity prediction model to obtain the initial mid-segment capacity Q of the energy storage battery. start ; According to the current mid-segment capacity Q of the energy storage battery now and the initial mid-segment capacity Q of the energy storage battery start Calculate the SOH of the energy storage battery in the current state: ； The current mid-range capacity of the energy storage battery is Q now Obtained by the following steps: Obtain the IC curve of the energy storage battery and calculate the mid-segment capacity Q of the energy storage battery based on the IC curve now ; Q ( u ) indicates the battery voltage is u capacity when ICA ( u ) indicates the battery voltage is u The ICA value at this time; u1 is the voltage value corresponding to the second peak of the IC curve, and u2 is selected as the minimum cut-off voltage that all battery cells can reach; The pre-trained initial mid-segment capacity prediction model is obtained through the following steps: Using artificial intelligence algorithms, a regression model is established to reflect the relationship between the initial mid-segment capacity of the battery and the battery operating parameters; Collect the actual operating data of the battery in its initial operating state and organize it into input and output data sets; Input characteristics include voltage, current, and temperature of the battery cell; Calculate the initial mid-segment capacity Q by integration start Organize it into the output of the training data set and use it as the predicted target value of the model; The regression model is trained based on the organized input and output data sets; the initial mid-segment capacity Q is obtained. start Initial mid-segment capacity prediction model.

2. The method for online estimation of the health status of an energy storage battery according to claim 1, characterized in that: The operating data includes voltage, current and temperature.

3. The method for online estimation of the health status of an energy storage battery according to claim 1, characterized in that: The IC curve is obtained by the following steps: Acquire real operating data of the energy storage battery; the real operating data of the energy storage battery includes voltage, current, and temperature; Based on the actual operating data of the energy storage battery, the charging capacity of the energy storage battery is calculated by the ampere-hour integration method, and a first curve graph is drawn with the charging capacity as the horizontal axis and the battery voltage as the vertical axis, the first curve graph having a first curve; exchanging the horizontal and vertical coordinates of the first curve graph to obtain a second curve graph having a second curve; The second curve is derived based on the voltage to obtain an IC curve with the ordinate being the ICA value and the abscissa being the battery voltage.

4. The method for online estimation of the health status of an energy storage battery according to claim 1, characterized in that: The artificial intelligence algorithm is an artificial intelligence algorithm with regression prediction function.

5. The method for online estimation of the health status of an energy storage battery according to claim 2, characterized in that: The artificial intelligence algorithm is XGboost.

6. An online estimation device for the health status of an energy storage battery, characterized in that: include: Acquisition module, used to obtain the current mid-segment capacity Q of the energy storage battery now ; The prediction module is used to obtain the operating data of the energy storage battery under the current state for a period of time and input it into the pre-trained initial mid-segment capacity prediction model to obtain the initial mid-segment capacity Q of the energy storage battery. start ; The estimation module is used to estimate the current mid-segment capacity Q of the energy storage battery. now and the initial mid-segment capacity Q of the energy storage battery start Calculate the SOH of the energy storage battery in the current state: ； The current mid-range capacity of the energy storage battery is Q now Obtained by the following steps: Obtain the IC curve of the energy storage battery and calculate the mid-segment capacity Q of the energy storage battery based on the IC curve now ; Q ( u ) indicates the battery voltage is u capacity when ICA ( u ) indicates the battery voltage is u The ICA value at this time; u1 is the voltage value corresponding to the second peak of the IC curve, and u2 is selected as the minimum cut-off voltage that all battery cells can reach; The pre-trained initial mid-segment capacity prediction model is obtained through the following steps: Using artificial intelligence algorithms, a regression model is established to reflect the relationship between the initial mid-segment capacity of the battery and the battery operating parameters; Collect the actual operating data of the battery in its initial operating state and organize it into input and output data sets; Input characteristics include voltage, current, and temperature of the battery cell; Calculate the initial mid-segment capacity Q by integration start Organize it into the output of the training data set and use it as the predicted target value of the model; The regression model is trained based on the organized input and output data sets; the initial mid-segment capacity Q is obtained. start Initial mid-segment capacity prediction model.

7. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement an online estimation method for the health status of an energy storage battery as claimed in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, an online estimation method for the health status of an energy storage battery according to any one of claims 1 to 5 is implemented.

Images