Park-oriented multi-scene mobile energy storage battery equipment soc estimation method and system

Abstract

The application discloses a park-oriented multi-scene mobile energy storage battery equipment SOC estimation method and system, comprising the following steps: designing multi-scene experimental conditions of a park mobile energy storage battery, simulating the experimental working condition environment of the battery, and obtaining experimental data generated by the simulation; considering voltage fluctuation in the charging and discharging process of the energy storage battery, collecting and processing the experimental data; using an improved extended Kalman filtering algorithm to estimate the SOC of the collected and processed experimental data, and correcting the actual capacity of the battery in the SOC estimation process in real time; the application performs HPPC testing under different environmental temperatures, different voltage fluctuation rates, working time, intervals and environmental conditions by using a K-means clustering algorithm, collects experimental data, processes the experimental data by using a CNN, estimates the SOC by using an EKF algorithm, optimizes and improves input state parameters of the battery SOC estimation process, and realizes accurate SOC estimation of an industrial park energy storage battery.

Description

Technical Field

[0001] This invention relates to the field of SOC estimation technology, and in particular to a method and system for SOC estimation of mobile energy storage battery devices in multiple scenarios in industrial parks. Background Technology

[0002] Given the uncertainty of new energy output, and the instability of power generation under different geographical environments and application scenarios, corresponding energy storage equipment is needed to ensure a continuous supply of electricity. Lithium-ion batteries have advantages such as long lifespan, high energy density, low self-discharge rate, and wide operating temperature range, and are increasingly widely used in the energy storage field, becoming a major development target in the battery industry. The state of charge (SOC) of a battery refers to the ratio of its real-time remaining capacity to the total capacity of the battery under the same charge and discharge conditions; therefore, it is often used to estimate the remaining usable capacity of a battery.

[0003] Industrial parks, home to numerous enterprises, have a high demand for various energy sources, including cooling, heating, and electricity, as well as energy-intensive public utilities such as gas and water. They also have high requirements for the reliability and quality of supply. Utilizing the flexibility and rapid response of mobile energy storage, by connecting mobile energy storage devices to critical equipment in the park's production processes that have stringent energy requirements, can effectively prevent equipment failures caused by power outages. However, because batteries are complex, closed electrochemical reaction systems, and many factors influence the estimation of State of Charge (SOC), accurate estimation of battery capacity is challenging. Current SOC estimation methods do not accurately meet the requirements of estimation precision and application scenarios, and researchers have been searching for a safe, reliable, and highly accurate estimation method to achieve real-time SOC estimation. Summary of the Invention

[0004] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0005] In view of the aforementioned existing problems, this invention is proposed. Therefore, this invention provides a multi-scenario SOC estimation method for mobile energy storage battery devices in industrial parks, addressing the issues that existing SOC estimation methods that do not differentiate between scenarios cannot meet the estimation needs of multiple scenarios, and that battery aging in energy storage devices can easily affect the accuracy of battery SOC estimation.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a method for estimating the State of Charge (SOC) of mobile energy storage battery devices for multiple scenarios in industrial parks, including:

[0008] Design multi-scenario experimental conditions for mobile energy storage batteries in the park, and simulate the experimental working environment of the batteries to obtain the experimental data generated by the simulation.

[0009] Voltage fluctuations during the charging and discharging process of the energy storage battery are taken into account, and the experimental data are collected and processed.

[0010] The collected and processed experimental data were used to estimate the state of charge (SOC) using an improved extended Kalman filter algorithm, and the actual capacity of the battery was corrected in real time during the SOC estimation process.

[0011] As a preferred embodiment of the SOC estimation method for multi-scenario mobile energy storage battery devices in industrial parks as described in this invention, the method includes: designing multi-scenario experimental conditions for mobile energy storage batteries in industrial parks, simulating the experimental operating environment of the batteries, and obtaining experimental data generated by the simulation, including:

[0012] To control the energy storage battery within its optimal temperature range, the temperature W is selected with a temperature interval step of ΔT. i HPPC test was conducted on the battery module at k different experimental temperatures to simulate the charging and discharging of the battery under various campus space scenario characteristics and conditions, and to obtain experimental data under different load space scenarios.

[0013] Where i takes the value (1, 2, ..., k), and k is a constant.

[0014] As a preferred embodiment of the SOC estimation method for multi-scenario mobile energy storage battery devices in industrial parks as described in this invention, the method considers voltage fluctuations during the charging and discharging process of the energy storage battery, including:

[0015] Define α i To meet the application scenarios with different voltage fluctuation rate requirements, β is defined. i The critical values ​​for voltage fluctuation rate ranges under different application scenarios satisfy the following formula:

[0016]

[0017] Considering that the output of mobile energy storage devices varies across different time intervals within the same spatial scenario, let's define T... i To meet the application scenario requirements under different time intervals;

[0018] Based on the above application scenario conditions, experimental data for application scenarios that meet voltage fluctuation rate requirements and different time intervals were obtained.

[0019] Where, δu This represents the load voltage fluctuation rate under different scenarios.

[0020] As a preferred embodiment of the SOC estimation method for multi-scenario mobile energy storage battery devices in parks as described in this invention, the experimental data is processed, including:

[0021] Taking voltage fluctuation range as an example, different voltage fluctuation ranges α are set. i Experimental current data under various application scenarios were obtained. Data conforming to the same spatial and application scenario were classified using the K-means clustering algorithm, resulting in data classification E for different scenarios. i =E(W, α, T);

[0022] Where (W, α, T) ∈ i.

[0023] As a preferred embodiment of the SOC estimation method for multi-scenario mobile energy storage battery devices in parks as described in this invention, the method includes: collecting experimental data, including:

[0024] Definition I i To collect current data for experiments in different spaces and application scenarios within the park, I i As input to a neural network, data is processed using a convolutional neural network, which is defined as follows: The output of the convolutional neural network:

[0025]

[0026] Where, kconv(I i ) represents the data I i The output of the convolutional neural network, n, represents the number of times experimental current data was collected at different spatial locations in the industrial park, forming a method for processing experimental data under multiple scenarios.

[0027] As a preferred embodiment of the SOC estimation method for multi-scenario mobile energy storage battery devices in parks as described in this invention, the method includes: estimating the SOC of collected and processed experimental data using an improved extended Kalman filter algorithm, including:

[0028] The actual battery capacity for each charge-discharge cycle was obtained from the experimental data, and a battery capacity change curve was plotted. ρ is defined as:

[0029] Where Q is the battery capacity change curve, and ρ is the battery capacity change rate;

[0030] Considering battery aging conditions, the battery capacity during discharge cycles needs to be corrected when calculating SOC. The impact of capacity changes on SOC estimation needs to be considered when the following conditions are met, expressed as follows:

[0031]

[0032] Among them, the battery fails due to aging when the battery capacity is lower than ν, and κ is the critical value of the capacity change rate, which is determined by the accuracy requirements of battery SOC estimation.

[0033] Define Q i =[Q1,...,Q n ], Q i State of Charge (SOC) represents the actual battery capacity during each charge and discharge cycle of an energy storage battery. A commonly used expression for SOC is as follows:

[0034]

[0035] Where η is the charge / discharge efficiency, and SOC is the state of charge / discharge. t Let Q be the SOC value at time t. i This refers to the battery capacity.

[0036] As a preferred embodiment of the SOC estimation method for multi-scenario mobile energy storage battery devices in parks as described in this invention, the method includes: real-time correction of the actual battery capacity during the SOC estimation process, including:

[0037]

[0038]

[0039]

[0040] Where, ΔQ i It is the change in battery capacity during each charge-discharge cycle; μ i This represents the error impact factor in calculating capacity changes using the ampere-hour integration method under each scenario; and These represent the start and end times of capacity calibration for each charge-discharge cycle of the battery, ΔSOC. i γ represents the change in SOC during each charge-discharge cycle. i This is the estimation error factor for the SOC estimate in each charge-discharge cycle.

[0041] Secondly, this invention provides a multi-scenario mobile energy storage battery device SOC estimation system for industrial parks, comprising:

[0042] The data acquisition module is used to collect data from battery devices in experimental scenarios or different spaces;

[0043] The data processing module uses the K-means clustering algorithm to classify and calculate the experimental data generated by the battery equipment;

[0044] The data algorithm module uses an improved extended Kalman filter algorithm to estimate the SOC of the collected and processed experimental data.

[0045] The scenario simulation module is used to simulate the current, voltage, and capacity data of energy storage batteries under different application scenarios.

[0046] Thirdly, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement any step of the above-described method.

[0047] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any step of the above-described method.

[0048] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention designs experimental conditions for multiple application scenarios of mobile energy storage batteries in industrial parks, while considering the impact of voltage fluctuations on the collected data under different scenarios during the charging and discharging of individual energy storage cells. It uses the K-means clustering algorithm to set environmental conditions for multiple scenarios in the park, and conducts hybrid pulse power characterization (HPPC) tests on batteries under different ambient temperatures, voltage fluctuation rates, working times, intervals, and environmental conditions. The experimental data is collected, processed using a convolutional neural network (CNN), and the State of Charge (SOC) is estimated using an extended Kalman filter (EKF) algorithm. The input state parameters of the battery SOC estimation process are optimized and improved to achieve accurate SOC estimation for energy storage batteries in industrial parks. Attached Figure Description

[0049] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0050] Figure 1 This is a flowchart illustrating the overall process of a multi-scenario mobile energy storage battery device SOC estimation method for industrial parks, as described in one embodiment of the present invention.

[0051] Figure 2This is a schematic diagram of the SOC calculation capacity correction considering capacity decay in the SOC estimation method for multi-scenario mobile energy storage battery devices in parks according to an embodiment of the present invention.

[0052] Figure 3 This diagram illustrates the experimental data processing method for a multi-scenario mobile energy storage battery device SOC estimation method for industrial parks, as described in one embodiment of the present invention. Detailed Implementation

[0053] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0054] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0055] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0056] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0057] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0058] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0059] Example 1

[0060] Reference Figures 1 to 3 This is the first embodiment of the present invention, which provides a method for estimating the State of Charge (SOC) of mobile energy storage battery devices in multiple scenarios for industrial parks, including:

[0061] S1. Design multi-scenario experimental conditions for mobile energy storage batteries in the park, and simulate the experimental working environment of mobile energy storage batteries to obtain the experimental data generated by the simulation.

[0062] Furthermore, the multi-scenario experimental conditions for designing mobile energy storage batteries in the park include:

[0063] To control the energy storage battery within its optimal temperature range, the temperature W is selected with a temperature interval step of ΔT. i HPPC test was conducted on the battery module at k different experimental temperatures to simulate the charging and discharging of the battery under various campus space scenario characteristics and conditions, and to obtain experimental data under different load space scenarios.

[0064] Where i takes the value (1, 2, ..., k), and k is a constant;

[0065] S2. Consider the voltage fluctuations during the charging and discharging process of the energy storage battery, and collect and process the experimental data.

[0066] Furthermore, define α i To meet the application scenarios with different voltage fluctuation rate requirements, β is defined. i The critical values ​​for voltage fluctuation rate ranges under different application scenarios satisfy the following formula:

[0067]

[0068] Considering that the output of mobile energy storage devices varies across different time intervals within the same spatial scenario, let's define T... i To meet the application scenario requirements under different time intervals;

[0069] Based on the above application scenario conditions, experimental data for application scenarios that meet voltage fluctuation rate requirements and different time intervals were obtained.

[0070] Where, δ uLoad voltage fluctuation rate under different scenarios;

[0071] S3, Reference Figure 3 The processing of experimental data includes: taking the voltage fluctuation rate range as an example, setting different voltage fluctuation ranges α i Experimental current data under various application scenarios were obtained. Data conforming to the same spatial and application scenario were classified using the K-means clustering algorithm, resulting in data classification E for different scenarios. i＝ E(W, α, T);

[0072] Where (W, α, T) ∈ i;

[0073] The collected and processed experimental data were used to estimate the state of charge (SOC) using an improved extended Kalman filter algorithm, and the actual capacity of the battery was corrected in real time during the SOC estimation process.

[0074] It should be noted that the K-means clustering algorithm is used because K-means clustering has better clustering effect and faster convergence speed. The main parameter that needs to be tuned is only the number of clusters k, which can better achieve the division of different scenarios.

[0075] S4. Data collection for experiments includes: Definition I i To collect current data for experiments in different spaces and application scenarios within the park, I i As input to a neural network, data is processed using a convolutional neural network, which is defined as follows: The output of the convolutional neural network:

[0076]

[0077] Where, kconv(I i ) represents the data I i The output of the convolutional neural network, n, represents the number of times experimental current data was collected at different spatial locations in the industrial park, forming a method for processing experimental data under multiple scenarios.

[0078] S5. The collected and processed experimental data are used to estimate the State of Charge (SOC) using the improved extended Kalman filter algorithm, referencing... Figure 2 ,include:

[0079] The actual battery capacity for each charge-discharge cycle was obtained from experimental data, and a battery capacity change curve was plotted. ρ is defined as:

[0080] Where Q is the battery capacity change curve, and ρ is the battery capacity change rate;

[0081] It should be noted that the experimental data include charge / discharge current, voltage, average battery surface temperature, and capacity; the improved extended Kalman filter algorithm can make the average absolute error of the SOC estimation result less than 2%.

[0082] Considering battery aging conditions, the battery capacity during discharge cycles needs to be corrected when calculating SOC. The impact of capacity changes on SOC estimation needs to be considered when the following conditions are met, expressed as follows:

[0083]

[0084] Among them, the battery fails due to aging when the battery capacity is lower than ν, and κ is the critical value of the capacity change rate, which is determined by the accuracy requirements of battery SOC estimation.

[0085] It should be noted that the battery capacity needs to be corrected during SOC calculation in order to reduce the amount of calculation.

[0086] Define Q i =[Q1,...,Q n ], Q i State of Charge (SOC) represents the actual battery capacity during each charge and discharge cycle of an energy storage battery. A commonly used expression for SOC is as follows:

[0087]

[0088] Where η is the charge / discharge efficiency, and SOC is the state of charge / discharge. t Let Q be the SOC value at time t. i Battery capacity;

[0089] Real-time correction of the actual battery capacity during SOC estimation, including:

[0090]

[0091]

[0092]

[0093] Where, ΔQ i It is the change in battery capacity during each charge-discharge cycle; μ i This represents the error impact factor in calculating capacity changes using the ampere-hour integration method under each scenario; and These represent the start and end times of capacity calibration for each charge-discharge cycle of the battery, ΔSOC. i γ represents the change in SOC during each charge-discharge cycle. i The estimation error factor for the SOC estimate in each charge-discharge cycle;

[0094] It should be noted that, considering that the state of charge of a battery is related to the actual capacity of the battery in each charge-discharge cycle, mobile energy storage batteries will encounter the problem of battery capacity decay during operation; therefore, the actual capacity of the battery in each charge-discharge cycle is calibrated based on battery experimental data under different scenarios, and the calibration formula is corrected to obtain a more accurate picture of the actual battery capacity change.

[0095] Furthermore, this embodiment also provides a multi-scenario mobile energy storage battery device SOC estimation system for industrial parks, including:

[0096] The data acquisition module is used to collect data from battery devices in experimental scenarios or different spaces;

[0097] The data processing module uses the K-means clustering algorithm to classify and calculate the experimental data generated by the battery equipment;

[0098] The data algorithm module uses an improved extended Kalman filter algorithm to estimate the SOC of the collected and processed experimental data.

[0099] The scenario simulation module is used to simulate the current, voltage, and capacity data of energy storage batteries under different application scenarios.

[0100] This embodiment also provides a computer device applicable to the SOC estimation method for multi-scenario mobile energy storage battery devices in industrial parks, including:

[0101] The system includes a memory and a processor. The memory stores computer-executable instructions, and the processor executes these instructions to implement the SOC estimation method for multi-scenario mobile energy storage battery devices in parks, as proposed in the above embodiments.

[0102] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0103] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the SOC estimation method for multi-scenario mobile energy storage battery devices in parks as proposed in the above embodiments.

[0104] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0105] Example 2

[0106] Referring to Table 1, the second embodiment of the present invention provides a method for estimating the State of Charge (SOC) of mobile energy storage battery devices for multiple scenarios in industrial parks, including:

[0107] The beneficial effects of the K-means clustering algorithm used in this invention are demonstrated through tabular data and scenario simulations.

[0108] Table 1 Comparison of algorithms in various scenarios

[0109] Scene Accuracy Time (s) K-means clustering algorithm Other clustering algorithms Scene 1 92.5％ 10 0.054 0.072 Scene 2 88.3％ 12 0.059 0.077 Scene 3 95.1％ 8 0.052 0.075 Scene 4 91.2％ 11 0.056 0.08

[0110] Configure the scene environment and parameters as follows:

[0111] Scenario 1: In a peak charging scenario, the charging power is set to 100kW, the grid load capacity is 170kW, the charging time is 1.5 hours, and the charging efficiency is 93%.

[0112] Scenario 2: In the off-peak charging scenario, the charging power is set to 100kW, the grid load capacity is 170kW, the charging time is 3 hours, and the charging efficiency is 95%.

[0113] Scenario 3: In the energy storage scenario, the maximum allowable energy storage power is 150kW, the grid load capacity is 220kW, the energy storage time is 3 hours, and the energy storage efficiency is 91%.

[0114] Scenario 4: In the discharge scenario, the maximum allowable discharge power is 170kW, the grid load capacity is 220kW, the discharge time is 2 hours, and the discharge efficiency is 95%.

[0115] In Table 1, accuracy represents the algorithm's estimation precision of the SOC value, and time represents the running time of the clustering algorithm. The comparison between the K-means clustering algorithm and other clustering algorithms is based on the same dataset and the same number of clusters in different scenarios. It can be seen that the K-means clustering algorithm can achieve higher accuracy in all scenarios and is also relatively fast. This is because the K-means clustering algorithm has low computational complexity, is easy to implement, and can quickly converge to a local optimum. In addition, the K-means clustering algorithm often performs better on datasets with spherical cluster shapes. Since the SOC estimation of mobile energy storage battery devices usually involves multiple parameters and has the characteristics of spherical cluster shape, the K-means clustering algorithm performs better in this scenario, which can bring higher accuracy to the energy storage battery device SOC estimation method of this invention.

[0116] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for estimating the State of Charge (SOC) of mobile energy storage battery devices in multiple scenarios within a park, characterized in that... include: Design multi-scenario experimental conditions for mobile energy storage batteries in the park, and simulate the experimental working environment of the batteries to obtain the experimental data generated by the simulation. Considering voltage fluctuations during the charging and discharging process of energy storage batteries, including: definition To meet the application scenarios with different voltage fluctuation rate requirements, β is defined. i The critical values ​​for voltage fluctuation rate ranges under different application scenarios satisfy the following formula: Considering that the output of mobile energy storage devices varies across different time intervals within the same spatial scenario, let's define T... i To meet the application scenario requirements under different time intervals; Based on the above application scenario conditions, experimental data for application scenarios that meet voltage fluctuation rate requirements and different time intervals were obtained. in, Load voltage fluctuation rate under different scenarios; The experimental data were collected and processed. The collected and processed experimental data were used to estimate the state of charge (SOC) using an improved extended Kalman filter algorithm, and the actual capacity of the battery was corrected in real time during the SOC estimation process. The real-time correction of the battery's actual capacity during the SOC estimation process includes: in, It is the change in battery capacity during each charge-discharge cycle; This represents the error impact factor in calculating capacity changes using the ampere-hour integration method under each scenario; and These represent the start and end times of capacity calibration for each charge-discharge cycle of the battery, respectively. This represents the change in SOC during each charge-discharge cycle. This is the estimation error factor for the SOC estimate in each charge-discharge cycle.

2. The SOC estimation method for multi-scenario mobile energy storage battery devices in industrial parks as described in claim 1, characterized in that, Design multi-scenario experimental conditions for mobile energy storage batteries in the park, and simulate the experimental operating environment of the batteries to obtain experimental data generated by the simulation, including: To control the energy storage battery within its optimal temperature range, the temperature W is selected with a temperature interval step of ΔT. i HPPC test was conducted on the battery module at k different experimental temperatures to simulate the charging and discharging of the battery under various campus space scenario characteristics and conditions, and to obtain experimental data under different load space scenarios. Where i takes the value (1, 2, ..., k), and k is a constant.

3. The SOC estimation method for multi-scenario mobile energy storage battery devices in industrial parks as described in claim 1 or 2, characterized in that, The experimental data were processed, including: Taking voltage fluctuation range as an example, different voltage fluctuation ranges are set. Experimental current data under various application scenarios were obtained. Data conforming to the same spatial and application scenario were classified using the K-means clustering algorithm, resulting in data classification E for different scenarios. i= E(W, α, T); Among them, (W, α, T) ∈ i.

4. The SOC estimation method for multi-scenario mobile energy storage battery devices in industrial parks as described in claim 3, characterized in that, The experimental data was collected, including: Definition I i To collect current data for experiments in different spaces and application scenarios within the park, I i As input to a neural network, data is processed using a convolutional neural network, which is defined as follows: The output of the convolutional neural network: in, I represents the data i The output of the convolutional neural network, n, represents the number of times experimental current data was collected at different spatial locations in the industrial park, forming a method for processing experimental data under multiple scenarios.

5. The SOC estimation method for multi-scenario mobile energy storage battery devices in industrial parks as described in claim 4, characterized in that, The collected and processed experimental data were used to estimate the State of Charge (SOC) using an improved extended Kalman filter algorithm, including: The actual battery capacity for each charge-discharge cycle was obtained from the experimental data, and a battery capacity change curve was plotted. The following definitions were also established. Represented as: in, This is a curve showing the change in battery capacity. This represents the rate of change in battery capacity. Considering battery aging conditions, the battery capacity during discharge cycles needs to be corrected when calculating SOC. The impact of capacity changes on SOC estimation needs to be considered when the following conditions are met, expressed as follows: Among them, the battery capacity is lower than Battery aging and failure This is the critical value for the rate of change of capacity, determined by the accuracy requirements for battery SOC estimation. definition , State of Charge (SOC) represents the actual battery capacity during each charge and discharge cycle of an energy storage battery. A commonly used expression for SOC is as follows: Where η is the charge / discharge efficiency. Let SOC be the value at time t. This refers to the battery capacity.

6. A multi-scenario mobile energy storage battery device SOC estimation system for industrial parks, based on the SOC estimation method for multi-scenario mobile energy storage battery devices for industrial parks as described in any one of claims 1 to 5, characterized in that, include: The data acquisition module is used to collect data from battery devices in experimental scenarios or different spaces; The data processing module uses the K-means clustering algorithm to classify and calculate the experimental data generated by the battery equipment; The data algorithm module uses an improved extended Kalman filter algorithm to estimate the SOC of the collected and processed experimental data. The scenario simulation module is used to simulate the current, voltage, and capacity data of energy storage batteries under different application scenarios.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images