Battery state of charge calibration method, device and computer equipment

Abstract

The present application relates to a calibration method, device and computer equipment for battery state of charge. The method includes: obtaining the battery cluster state of charge, maintenance time and current calibration time of a multi-cluster DC battery cabinet; when the current calibration time of the multi-cluster DC battery cabinet is lower than the preset time threshold, the battery cluster state of charge is the preset state of charge, and the maintenance time of the multi-cluster DC battery cabinet in the battery cluster state of charge is greater than the preset time, the multi-cluster DC battery cabinet is calibrated for the state of charge through a cloud-based passive state of charge calibration strategy; conversely, the multi-cluster DC battery cabinet is calibrated for the state of charge through an active state of charge calibration strategy; after the calibration process is completed, the battery cluster state of charge of the multi-cluster DC battery cabinet and the maintenance time of the multi-cluster DC battery cabinet in the battery cluster state of charge are updated. The use of this method can improve the accuracy of SOC calibration when multiple clusters of batteries are connected in parallel.

Description

Technical Field

[0001] The present application relates to the technical field of energy storage battery control for electrochemical energy storage, and in particular to a method, device and computer equipment for calibrating the state of charge of a battery. Background Art

[0002] In the frequency modulation application scenario, when multiple clusters of DC battery cabinets are connected in parallel in the energy storage system, the lithium iron phosphate battery often cannot be fully charged and discharged and can only be charged and discharged in the voltage platform area. Due to the difference in current sampling error between clusters, current bias difference, battery consistency, and the inability to reach the conditions for OCV-SOC (open circuit voltage-state of charge, SOC) curve calibration, the system is prone to large SOC (state of charge) value calculation errors after a period of operation. Therefore, it is necessary to calibrate the state of charge to reduce the calculation error of the battery state of charge.

[0003] The traditional battery state of charge calibration method is to integrate the dynamic change of the battery ampere-hour during the charging and discharging process; then synchronously read the dynamic change of the battery ampere-hour during the charging and discharging process, and manage and count the remaining ampere-hour data of the battery based on the dynamic change of the battery ampere-hour, so as to calculate the SOC value of the battery and calibrate the SOC value. However, this technology can only calibrate the SOC of a single battery. Secondly, when multiple clusters of batteries are connected in parallel and work in a frequency modulation scenario, the battery working SOC is at 40%-60% (voltage platform area) for a long time, and the accumulated error caused by long-term operation cannot be achieved through the calibration strategy. SOC accuracy calibration results in poor SOC calibration accuracy when multiple clusters of batteries are connected in parallel. Summary of the invention

[0004] Based on this, it is necessary to provide a battery state of charge calibration method, device, computer equipment, computer readable storage medium and computer program product to address the above technical problems.

[0005] In a first aspect, the present application provides a method for calibrating a battery state of charge, comprising:

[0006] Acquire the battery cluster charge state of a multi-cluster DC battery cabinet, the duration for which the multi-cluster DC battery cabinet is in the battery cluster charge state, and the current calibration time of the multi-cluster DC battery cabinet;

[0007] When the current calibration time of the multi-cluster DC battery cabinet is lower than the preset time threshold, the battery cluster state of charge is the preset state of charge, and the maintenance time of the multi-cluster DC battery cabinet in the battery cluster state of charge is longer than the preset time, the multi-cluster DC battery cabinet is calibrated for the state of charge through the cloud-based passive state of charge calibration strategy;

[0008] When the current calibration time of the multi-cluster DC battery cabinet is higher than the preset time threshold, the battery cluster state of charge is the preset state of charge, and the maintenance time of the multi-cluster DC battery cabinet in the battery cluster state of charge is longer than the preset time, the multi-cluster DC battery cabinet is subjected to a state of charge calibration process through an active state of charge calibration strategy;

[0009] After the calibration process is completed, the battery cluster charge states of the multi-cluster DC battery cabinet and the duration for which the multi-cluster DC battery cabinet is in the battery cluster charge state are updated.

[0010] Optionally, the step of performing charge state calibration processing on the multi-cluster DC battery cabinets by using a cloud-based passive charge state calibration strategy includes:

[0011] Obtaining full battery data of a multi-cluster DC battery cabinet at all times, and judging whether the multi-cluster DC battery cabinet meets a charge state calibration condition based on the current full battery data;

[0012] When the multi-cluster DC battery cabinet meets the charge state calibration condition, based on the current battery full quantity data, the current charge state of the multi-cluster DC battery cabinet is calculated by a charge state identification model;

[0013] The current state of charge is sent to a local state calibration unit via the cloud, and based on the current state of charge, the state of charge calibration process is performed on the multi-cluster DC battery cabinet via the local state calibration unit.

[0014] Optionally, judging whether the multi-cluster DC battery cabinet meets the state of charge calibration condition based on the current full battery data includes:

[0015] Based on the battery full quantity data, identifying the battery voltage value of the multi-cluster DC battery cabinet, the battery current value of the multi-cluster DC battery cabinet, and the battery temperature value of the multi-cluster DC battery cabinet;

[0016] Based on the battery voltage value, the battery current value, and the battery temperature value, an initial state of charge recognition model is trained, and when the number of training times of the initial state of charge recognition model is less than a preset number of training times, returning to execute the step of obtaining current full battery data of the multi-cluster DC battery cabinet;

[0017] When the training times of the initial state of charge recognition model is not less than the preset training times, the initial state of charge recognition model obtained by the last iteration is used as the target state of charge recognition model, and it is determined that the multi-cluster DC battery cabinet meets the state of charge calibration condition.

[0018] Optionally, the step of performing charge state calibration processing on the multi-cluster DC battery cabinets by using an active charge state calibration strategy includes:

[0019] In a multi-cluster DC battery cabinet, randomly selecting a target single cluster of batteries and isolating a battery scheduling response mode of the target single cluster of batteries;

[0020] Controlling the target battery cluster to perform power-on processing through a power-on control unit, and when the highest cell voltage of the target battery cluster reaches a full charge calibration voltage threshold, replacing the current state of charge of the target battery cluster based on a preset state of charge calibration value to obtain a new state of charge of the target battery cluster;

[0021] Based on the new state of charge, the state of charge calibration process is performed on the target single cluster battery, and the battery scheduling response mode of the target single cluster battery is restored;

[0022] In the multi-cluster DC battery cabinet, the target single cluster batteries that have not been screened as target single cluster batteries are rescreened, and the battery scheduling response method step of isolating the target single cluster batteries is returned to execute until all single cluster batteries have completed the state of charge calibration processing, and it is determined that the multi-cluster DC battery cabinet has completed the state of charge calibration processing.

[0023] Optionally, before replacing the current state of charge of the target single cluster battery based on the preset state of charge calibration value to obtain a new state of charge of the target single cluster battery, the method further includes:

[0024] Based on the battery specification information of the target single-cluster battery, identifying the minimum continuous charging value of the target single-cluster battery, and based on the minimum continuous charging value, performing continuous charging processing on the target single-cluster battery through the power-on control unit;

[0025] The current battery voltage value of the target single-cluster battery is detected, and when the current battery voltage value is lower than the full calibration voltage threshold, the step of returning to the step of detecting the current battery voltage value of the target single-cluster battery is executed until the current battery voltage value is equal to the full calibration voltage threshold, and it is determined that the highest single cell voltage of the target single-cluster battery reaches the full calibration voltage threshold.

[0026] Optionally, updating the battery cluster charge states of the multi-cluster DC battery cabinets and the duration for which the multi-cluster DC battery cabinets are in the battery cluster charge states includes:

[0027] Identifying a current state of charge of the multi-cluster DC battery cabinet, and replacing the battery cluster state of charge of the multi-cluster DC battery cabinet with the current state of charge;

[0028] The maintenance time is reset to zero, completing the task of updating the maintenance time of the multi-cluster DC battery cabinet in the battery cluster charge state.

[0029] In a second aspect, the present application also provides a battery state of charge calibration device, comprising:

[0030] An acquisition module, used to acquire the battery cluster charge state of a multi-cluster DC battery cabinet, the duration for which the multi-cluster DC battery cabinet is in the battery cluster charge state, and the current calibration time of the multi-cluster DC battery cabinet;

[0031] A first calibration module is used to perform a state of charge calibration process on the multi-cluster DC battery cabinet through a cloud-based passive state of charge calibration strategy when the current calibration time of the multi-cluster DC battery cabinet is lower than a preset time threshold, the state of charge of the battery cluster is a preset state of charge, and the maintenance time of the multi-cluster DC battery cabinet in the battery cluster state of charge is greater than a preset time;

[0032] A first calibration module is used to perform a state of charge calibration process on the multi-cluster DC battery cabinet through an active state of charge calibration strategy when the current calibration time of the multi-cluster DC battery cabinet is higher than the preset time threshold, the state of charge of the battery cluster is the preset state of charge, and the maintenance time of the multi-cluster DC battery cabinet in the battery cluster state of charge is longer than the preset time;

[0033] The updating module is used to update the battery cluster charge state of the multi-cluster DC battery cabinet and the maintenance time of the multi-cluster DC battery cabinet in the battery cluster charge state after completing the calibration process.

[0034] Optionally, the first calibration module is specifically used to:

[0035] Obtaining full battery data of a multi-cluster DC battery cabinet at all times, and judging whether the multi-cluster DC battery cabinet meets a charge state calibration condition based on the current full battery data;

[0036] When the multi-cluster DC battery cabinet meets the charge state calibration condition, based on the current battery full quantity data, the current charge state of the multi-cluster DC battery cabinet is calculated by a charge state identification model;

[0037] The current state of charge is sent to a local state calibration unit via the cloud, and based on the current state of charge, the state of charge calibration process is performed on the multi-cluster DC battery cabinet via the local state calibration unit.

[0038] Optionally, the first calibration module is specifically used to:

[0039] Based on the battery full quantity data, identifying the battery voltage value of the multi-cluster DC battery cabinet, the battery current value of the multi-cluster DC battery cabinet, and the battery temperature value of the multi-cluster DC battery cabinet;

[0040] Based on the battery voltage value, the battery current value, and the battery temperature value, an initial state of charge recognition model is trained, and when the number of training times of the initial state of charge recognition model is less than a preset number of training times, returning to execute the step of obtaining current full battery data of the multi-cluster DC battery cabinet;

[0041] When the training times of the initial state of charge recognition model is not less than the preset training times, the initial state of charge recognition model obtained by the last iteration is used as the target state of charge recognition model, and it is determined that the multi-cluster DC battery cabinet meets the state of charge calibration condition.

[0042] Optionally, the second calibration module is specifically used to:

[0043] In a multi-cluster DC battery cabinet, randomly selecting a target single cluster of batteries and isolating a battery scheduling response mode of the target single cluster of batteries;

[0044] Controlling the target battery cluster to perform power-on processing through a power-on control unit, and when the highest cell voltage of the target battery cluster reaches a full charge calibration voltage threshold, replacing the current state of charge of the target battery cluster based on a preset state of charge calibration value to obtain a new state of charge of the target battery cluster;

[0045] Based on the new state of charge, the state of charge calibration process is performed on the target single cluster battery, and the battery scheduling response mode of the target single cluster battery is restored;

[0046] In the multi-cluster DC battery cabinet, the target single cluster batteries that have not been screened as target single cluster batteries are rescreened, and the battery scheduling response method step of isolating the target single cluster batteries is returned to execute until all single cluster batteries have completed the state of charge calibration processing, and it is determined that the multi-cluster DC battery cabinet has completed the state of charge calibration processing.

[0047] Optionally, the device further comprises:

[0048] a power-on module, configured to identify a minimum continuous charging value of the target single-cluster battery based on the battery specification information of the target single-cluster battery, and perform continuous charging processing on the target single-cluster battery through the power-on control unit based on the minimum continuous charging value;

[0049] The detection module is used to detect the current battery voltage value of the target single-cluster battery, and when the current battery voltage value is lower than the full calibration voltage threshold, return to the step of detecting the current battery voltage value of the target single-cluster battery, until the current battery voltage value is equal to the full calibration voltage threshold, and determine that the highest single cell voltage of the target single-cluster battery reaches the full calibration voltage threshold.

[0050] Optionally, the update module is specifically used to:

[0051] Identifying a current state of charge of the multi-cluster DC battery cabinet, and replacing the battery cluster state of charge of the multi-cluster DC battery cabinet with the current state of charge;

[0052] The maintenance time is reset to zero, completing the task of updating the maintenance time of the multi-cluster DC battery cabinet in the battery cluster charge state.

[0053] In a third aspect, the present application provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0054] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0055] In a fifth aspect, the present application provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0056] The battery state of charge calibration method, device and computer equipment described above obtain the battery cluster state of charge of a multi-cluster DC battery cabinet, the duration of the multi-cluster DC battery cabinet being in the battery cluster state of charge, and the current calibration time of the multi-cluster DC battery cabinet; when the current calibration time of the multi-cluster DC battery cabinet is lower than a preset time threshold, the battery cluster state of charge is a preset state of charge, and the duration of the multi-cluster DC battery cabinet being in the battery cluster state of charge is longer than the preset time, the multi-cluster DC battery cabinet is calibrated using a cloud-based passive state of charge calibration strategy. The battery cabinet performs charge state calibration processing; when the current calibration time of the multi-cluster DC battery cabinet is higher than the preset time threshold, the battery cluster charge state is the preset charge state, and the maintenance time of the multi-cluster DC battery cabinet in the battery cluster charge state is longer than the preset time, the multi-cluster DC battery cabinet performs charge state calibration processing on the multi-cluster DC battery cabinet through an active charge state calibration strategy; after completing the calibration processing, the battery cluster charge state of the multi-cluster DC battery cabinet and the maintenance time of the multi-cluster DC battery cabinet in the battery cluster charge state are updated. This solution uses active calibration and cloud-based passive state-of-charge calibration strategies to perform state-of-charge calibration at different states of charge of the battery cluster and at different maintenance times, thereby ensuring that the state of charge of the battery cluster can be calibrated under any conditions. In addition, this solution designs different battery state calculation methods for different states of the battery cluster, thereby greatly reducing the SOC calculation error under the condition of multiple battery clusters in parallel and improving the SOC calibration accuracy under the condition of multiple battery clusters in parallel. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 FIG. 1 is an application environment diagram of a method for calibrating a battery state of charge in one embodiment;

[0059] Figure 2 A schematic diagram of a flow chart of a method for calibrating a battery state of charge in one embodiment;

[0060] Figure 3 A schematic diagram of a flow chart of an example of calibration of a battery state of charge in one embodiment;

[0061] Figure 4 is a structural block diagram of a device for calibrating a battery state of charge in one embodiment;

[0062] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application 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 application and are not used to limit the present application.

[0064] The battery state of charge calibration method provided in the embodiment of the present application can be applied to Figure 1 In the application environment of multiple battery clusters in parallel, the application environment includes a host battery cabinet and multiple slave battery cabinets, each battery cabinet is connected in parallel, and all battery cabinets are calibrated by a control center including EMS (Energy Management System), SCU (on-site monitoring system, three-level BMS (Battery Monitoring and Management System), switch, PCS (Power Conversion System, energy storage converter), and cloud. Among them, SCU is responsible for the summary and statistics of multi-cluster battery information, power management, and external northbound communication; EMS is responsible for charge and discharge scheduling management, coordinated control of PCS and SCU, to ensure power safety and power quality of the power system; PCS charge and discharge execution unit; GRU (gated recurrent unit network, i.e., recurrent neural network). Among them, the control center can be a terminal, a server, or a system obtained by combining a terminal and a server. Among them, the terminal can be but not limited to a computer, a personal computer, a laptop, etc., and the server can be implemented by an independent server or a server cluster composed of multiple servers. Among them, when the control center is a terminal, the terminal uses an active calibration method and a cloud-based passive state of charge calibration strategy to perform state of charge calibration under different charge states of the battery cluster and under different maintenance time conditions, thereby ensuring that the battery cluster can be calibrated under any state conditions. In addition, this solution designs different battery state calculation methods for different states of the battery cluster, thereby greatly reducing the SOC calculation error under the condition of multiple battery clusters in parallel, and improving the SOC calibration accuracy under the condition of multiple battery clusters in parallel.

[0065] In an exemplary embodiment, Figure 2 As shown, a method for calibrating the state of charge of a battery is provided. Figure 1The control center is described as a terminal as an example, including the following steps S201 to S204. Among them:

[0066] Step S201 , obtaining the battery cluster charge state of the multi-cluster DC battery cabinet, the duration of the multi-cluster DC battery cabinet being in the battery cluster charge state, and the current calibration time of the multi-cluster DC battery cabinet.

[0067] In this embodiment, the terminal obtains the state of charge of each battery cabinet of the multi-cluster DC battery cabinet through the SCU to obtain the state of charge of the battery cluster. Then, the terminal detects in real time through the timing module the duration of the multi-cluster DC battery cabinet being in the state of charge of the battery cluster and the current calibration time of the multi-cluster DC battery cabinet.

[0068] Step S202, when the current calibration time of the multi-cluster DC battery cabinet is lower than the preset time threshold, the battery cluster charge state is the preset charge state, and the maintenance time of the multi-cluster DC battery cabinet in the battery cluster charge state is greater than the preset time, the multi-cluster DC battery cabinet is calibrated for the charge state through the cloud-based passive charge state calibration strategy.

[0069] In this embodiment, when the current calibration time of the multi-cluster DC battery cabinet is lower than the preset time threshold, the battery cluster charge state is the preset charge state, and the multi-cluster DC battery cabinet is in the battery cluster charge state for a duration greater than the preset duration, the terminal performs charge state calibration processing on the multi-cluster DC battery cabinet through the cloud passive charge state calibration strategy. Specifically, the preset time threshold, preset charge state, and preset duration are, for example, after the multi-cluster DC battery cabinet completes the last calibration, the summary sheet updates the calibration time, the calibration time is reset to zero, and then it is determined whether the current swing time is less than 14*24 hours (that is, the current calibration time of the multi-cluster DC battery cabinet is lower than the preset time threshold), the SOC is less than 30% (the battery cluster charge state is the preset charge state), and the stationary state exceeds 1 hour (the multi-cluster DC battery cabinet is in the battery cluster charge state for a duration greater than the preset duration), the terminal performs charge state calibration processing on the multi-cluster DC battery cabinet through the cloud passive charge state calibration strategy. Specifically, the calibration process of the cloud-based passive state of charge calibration strategy will be described in detail later.

[0070] Step S203, when the current calibration time of the multi-cluster DC battery cabinet is higher than the preset time threshold, the battery cluster charge state is the preset charge state, and the maintenance time of the multi-cluster DC battery cabinet in the battery cluster charge state is longer than the preset time, the multi-cluster DC battery cabinet is calibrated by the active charge state calibration strategy.

[0071] In this embodiment, when the current calibration time of the multi-cluster DC battery cabinet is higher than the preset time threshold, the battery cluster charge state is the preset charge state, and the multi-cluster DC battery cabinet is in the battery cluster charge state for a duration longer than the preset duration (i.e., a condition completely opposite to the judgment condition of the cloud-based passive charge state calibration strategy), the terminal performs charge state calibration on the multi-cluster DC battery cabinet using the active charge state calibration strategy. Specifically, the calibration process of the active charge state calibration strategy will be described in detail later.

[0072] Step S204: after the calibration process is completed, the battery cluster charge states of the multi-cluster DC battery cabinet and the duration for which the multi-cluster DC battery cabinet is in the battery cluster charge state are updated.

[0073] In this embodiment, after completing the calibration process, the terminal updates the battery cluster charge state of the multi-cluster DC battery cabinet and the duration of the multi-cluster DC battery cabinet being in the battery cluster charge state. The updating of the battery group charge state is the process of recalibrating the charge state of each battery cabinet, and the updating of the duration of the multi-cluster DC battery cabinet being in the battery cluster charge state is the process of recalculating the duration of the battery cabinet being in the charge state after returning the duration of each battery cabinet being in the charge state to zero.

[0074] Based on the above scheme, through active calibration and cloud-based passive state of charge calibration strategy, the state of charge calibration is performed separately under different states of charge of the battery cluster and under different maintenance time conditions, thereby ensuring that the battery cluster can be calibrated under any state conditions. In addition, this scheme designs different battery state calculation methods for different states of the battery cluster, thereby greatly reducing the SOC calculation error under the condition of multiple clusters of batteries in parallel, and improving the SOC calibration accuracy under the condition of multiple clusters of batteries in parallel.

[0075] Optionally, a cloud-based passive state of charge calibration strategy is used to perform state of charge calibration on multi-cluster DC battery cabinets, including: obtaining full battery data of the multi-cluster DC battery cabinets at all times, and judging whether the multi-cluster DC battery cabinets meet state of charge calibration conditions based on the current full battery data; when the multi-cluster DC battery cabinets meet the state of charge calibration conditions, based on the current full battery data, using a state of charge identification model, calculating the current state of charge of the multi-cluster DC battery cabinets; sending the current state of charge to a local state calibration unit via the cloud, and based on the current state of charge, performing state of charge calibration on the multi-cluster DC battery cabinets through the local state calibration unit.

[0076] In this embodiment, the terminal obtains the full battery data of the multi-cluster DC battery cabinets at all times, and based on the current full battery data, determines whether the multi-cluster DC battery cabinets meet the state of charge calibration conditions. Among them, the full battery data of the entire period includes the full battery data collected from the white battery at each collection time point. Among them, the full battery data includes but is not limited to the battery voltage value, battery current value, and battery temperature value of each battery cabinet, specifically, including but not limited to the maximum voltage, maximum battery cell temperature, minimum battery cell temperature, number of contactor closure clusters, and minimum cluster continuous charging current. The specific judgment process will be described in detail later.

[0077] Then, when the multi-cluster DC battery cabinet meets the state of charge calibration conditions, the terminal calculates the current state of charge of the multi-cluster DC battery cabinet based on the current full battery data through the state of charge recognition model. Among them, the state of charge recognition model is a time series prediction model obtained by training a large amount of sample data based on the established GRU network structure.

[0078] Then, the terminal sends the current state of charge to the local state calibration unit through the cloud, and based on the current state of charge, the local state calibration unit calibrates the state of charge of multiple clusters of DC battery cabinets.

[0079] Based on the above solution, the cloud-based passive calibration method enables the battery state of charge to be accurately calculated under low battery state of charge, thereby ensuring the calibration accuracy of multi-cluster parallel battery cabinets under low battery state of charge.

[0080] Optionally, based on the current full battery data, determine whether the multi-cluster DC battery cabinet meets the state of charge calibration conditions, including: based on the full battery data, identify the battery voltage value of the multi-cluster DC battery cabinet, the battery current value of the multi-cluster DC battery cabinet, and the battery temperature value of the multi-cluster DC battery cabinet; based on the battery voltage value, the battery current value, and the battery temperature value, train an initial state of charge recognition model, and when the number of training times of the initial state of charge recognition model is less than a preset number of training times, return to execute the step of obtaining the current full battery data of the multi-cluster DC battery cabinet; when the number of training times of the initial state of charge recognition model is not less than a preset number of training times, use the initial state of charge recognition model obtained by the last iteration as the target state of charge recognition model, and determine that the multi-cluster DC battery cabinet meets the state of charge calibration conditions.

[0081] In this embodiment, the terminal identifies the battery voltage value, battery current value, and battery temperature value of the multi-cluster DC battery cabinet based on the full battery data. Then, the terminal trains the initial state of charge recognition model based on the battery voltage value, battery current value, and battery temperature value, and returns to execute the step of obtaining the current full battery data of the multi-cluster DC battery cabinet when the number of training times of the initial state of charge recognition model is lower than the preset number of training times. Wherein, when training the model, after the terminal obtains the full battery data, it is also necessary to obtain the battery state of charge of the multi-cluster DC battery cabinet calibrated each time the full battery data is collected. Then, the model is trained based on the battery state of charge and the full battery data. Wherein, the preset number of training times is the number of training times preset by the staff at the terminal. Wherein, due to the time series prediction model trained by the full battery data of each battery of the multi-cluster DC battery cabinet collected during the whole period, the state of charge of the multi-cluster DC battery cabinet can be effectively identified.

[0082] When the training times of the initial state of charge recognition model is not less than the preset training times, the terminal uses the initial state of charge recognition model obtained by the last iteration as the target state of charge recognition model, and determines whether the multi-cluster DC battery cabinet meets the state of charge calibration condition, where the state of charge calibration condition is the preset training times.

[0083] Based on the above solution, the recognition accuracy and comprehensiveness of the target state of charge recognition model are optimized in real time by collecting and training simultaneously.

[0084] Optionally, an active state of charge calibration strategy is used to perform state of charge calibration processing on a multi-cluster DC battery cabinet, including: in the multi-cluster DC battery cabinet, randomly screening a target single cluster battery, and isolating the battery scheduling response mode of the target single cluster battery; controlling the target single cluster battery to perform power-on processing through a power-on control unit, and when the highest single cell voltage of the target single cluster battery reaches the full calibration voltage threshold, replacing the current state of charge of the target single cluster battery based on a preset state of charge calibration value to obtain a new state of charge of the target single cluster battery; based on the new state of charge, performing state of charge calibration processing on the target single cluster battery, and restoring the battery scheduling response mode of the target single cluster battery; in the multi-cluster DC battery cabinet, re-screening the target single cluster battery that has not been screened as the target single cluster battery, and returning to execute the step of isolating the battery scheduling response mode of the target single cluster battery, until all single cluster batteries have completed the state of charge calibration processing, determining that the multi-cluster DC battery cabinet has completed the state of charge calibration processing.

[0085] In this embodiment, the terminal randomly selects a target single cluster battery in a multi-cluster DC battery cabinet and cuts off the battery scheduling response mode of the target single cluster battery. The purpose of cutting off the battery scheduling response mode of the target single cluster battery is to perform offline battery state of charge calibration on the target single cluster battery, avoiding the problem of low accuracy of battery state of charge calibration due to battery scheduling response. The accuracy of battery state of charge calibration of the target single cluster battery is improved.

[0086] Then, the terminal controls the target battery cluster to power on through the power-on control unit, and when the highest cell voltage of the target battery cluster reaches the full charge calibration voltage threshold, the current state of charge of the target battery cluster is replaced based on the preset state of charge calibration value to obtain the new state of charge of the target battery cluster. The specific power-on process will be described in detail later, and the full charge calibration voltage threshold is the voltage threshold preset by the staff in the terminal. It is used to determine the end time of battery charging.

[0087] Afterwards, the terminal performs a state of charge calibration process on the target single-cluster battery based on the new state of charge, and restores the battery scheduling response mode of the target single-cluster battery. Among them, the battery scheduling response mode is to restore the normal operation process of the target single-cluster battery, so that the calibrated single-cluster battery can still operate normally. Afterwards, the terminal re-screens the target single-cluster battery that has not been screened as the target single-cluster battery in the multi-cluster DC battery cabinet, and returns to execute the battery scheduling response mode step of isolating the target single-cluster battery until all single-cluster batteries have completed the state of charge calibration process, and determines that the multi-cluster DC battery cabinet has completed the state of charge calibration process. The above method is to perform battery calibration on each single-cluster battery separately. In addition, the battery calibration is performed by powering on the battery, so that each battery has an SOC value of 100% after calibration. Thereby, the calibration accuracy of the multi-cluster battery is ensured, and the battery can also be charged at the same time to avoid the problem of low battery state of charge affecting the normal operation of the battery.

[0088] Based on the above solution, through the battery calibration process after power-on, the calibration accuracy of the multi-cluster battery cabinet is ensured, while the battery life and the progress of maintaining the normal operating status are improved.

[0089] Optionally, before replacing the current state of charge of the target single cluster battery based on a preset state of charge calibration value and obtaining a new state of charge of the target single cluster battery, it also includes: identifying the minimum continuous charging value of the target single cluster battery based on the battery specification information of the target single cluster battery, and based on the minimum continuous charging value, performing continuous charging processing on the target single cluster battery through a power-on control unit; detecting the current battery voltage value of the target single cluster battery, and when the current battery voltage value is lower than the full calibration voltage threshold, returning to execute the step of detecting the current battery voltage value of the target single cluster battery, until the current battery voltage value is equal to the full calibration voltage threshold, determining that the highest single cell voltage of the target single cluster battery reaches the full calibration voltage threshold.

[0090] In this embodiment, the terminal identifies the minimum continuous charging value of the target single-cluster battery based on the battery specification information of the target single-cluster battery, and performs continuous charging processing on the target single-cluster battery through the power-on control unit based on the minimum continuous charging value. Before charging starts, the terminal checks the continuous charging current table based on the battery cells of two conditions, namely, the maximum voltage and the maximum battery cell temperature, and the maximum voltage and the minimum battery cell temperature. Output the currently available continuous charging current value, and take the minimum value of the two. The stack continuous charging current value output by the SCU = the number of contactor closure clusters * the minimum value of the cluster continuous charging current; since the PCS power control is set by the EMS, the stack continuous charging current value output by the SCU needs to be uploaded to the EMS via Ethernet communication. The EMS sets the PCS charging power according to the battery cell SOP and starts charging, which effectively guarantees the service life of the battery.

[0091] After the charging process starts, the Ah integral and full charge voltage calibration strategy are combined, and the Ah integral is calculated as follows:

[0092] After power-on, the terminal reads the current cumulative charging capacity InitChrgCapAh and cumulative discharge capacity InitDchaCapAh; then, the terminal calculates the capacity change DeltaCap during the charging and discharging process (charging is negative and discharging is positive), where the calculation formula is as follows:

[0093]

[0094] Among them, calculate △SOC:

[0095]

[0096] The terminal iteratively calculates the SOC of all cells based on the Ah integral according to the following formula:

[0097]

[0098] When the highest single cell voltage reaches the full charge calibration threshold, the terminal calibrates the SOC of the target single cluster battery to 100%.

[0099] Then, the terminal detects the current battery voltage value of the target battery cluster, and when the current battery voltage value is lower than the full calibration voltage threshold, returns to the step of detecting the current battery voltage value of the target battery cluster, until the current battery voltage value is equal to the full calibration voltage threshold, and determines that the highest single cell voltage of the target battery cluster reaches the full calibration voltage threshold. Specifically, when the SOC of the target battery cluster is charged to 100%, the SCU sets the stack request charging current = 0, and updates and uploads it to the EMS, and the EMS controls the PCS to switch to standby, and the SCU sends a power-off command to the cluster with an SOC of 100%, completing the full charge calibration and exiting the charging state.

[0100] Based on the above solution, the accuracy of the full charge calibration of the target single cluster battery is identified by calculating the capacity change during the charge and discharge process.

[0101] Optionally, the battery cluster charge state of a multi-cluster DC battery cabinet and the maintenance time of the multi-cluster DC battery cabinet in the battery cluster charge state are updated, including: identifying the current charge state of the multi-cluster DC battery cabinet and replacing the battery cluster charge state of the multi-cluster DC battery cabinet with the current charge state; resetting the maintenance time to zero, completing the task of updating the maintenance time of the multi-cluster DC battery cabinet in the battery cluster charge state.

[0102] In this embodiment, the terminal identifies the current state of charge of the multi-cluster DC battery cabinet and replaces the battery cluster state of charge of the multi-cluster DC battery cabinet with the current state of charge. Then, the terminal resets the maintenance time to zero, completing the task of updating the maintenance time of the multi-cluster DC battery cabinet in the battery cluster state of charge.

[0103] Based on the above solution, by updating the battery cluster charge state and maintenance time, the real-time analysis efficiency of the battery cluster charge state of multiple DC battery cabinets is improved, and the recognition accuracy of the battery cluster charge state is ensured in the subsequent recognition.

[0104] This application also provides a battery state of charge calibration example, such as Figure 3 As shown, the specific processing process includes the following steps:

[0105] Step S301 , obtaining the battery cluster charge state of the multi-cluster DC battery cabinet, the duration of the multi-cluster DC battery cabinet being in the battery cluster charge state, and the current calibration time of the multi-cluster DC battery cabinet.

[0106] Step S302, obtaining full battery data of multiple clusters of DC battery cabinets at all times.

[0107] Step S303 , based on the battery full quantity data, identifying the battery voltage values ​​of the multiple-cluster DC battery cabinets, the battery current values ​​of the multiple-cluster DC battery cabinets, and the battery temperature values ​​of the multiple-cluster DC battery cabinets.

[0108] Step S304, based on the battery voltage value, the battery current value, and the battery temperature value, the initial state of charge recognition model is trained, and when the number of training times of the initial state of charge recognition model is less than the preset number of training times, the step of obtaining the current full battery data of the multi-cluster DC battery cabinet is returned to.

[0109] Step S305, when the training times of the initial state of charge recognition model is not less than the preset training times, the initial state of charge recognition model obtained by the last iteration is used as the target state of charge recognition model, and it is determined that the multi-cluster DC battery cabinet meets the state of charge calibration condition.

[0110] Step S306, when the multi-cluster DC battery cabinet meets the charge state calibration condition, the current charge state of the multi-cluster DC battery cabinet is calculated based on the current battery full quantity data through the charge state recognition model.

[0111] Step S307, the current state of charge is sent to the local state calibration unit through the cloud, and based on the current state of charge, the local state calibration unit performs charge state calibration processing on the multiple clusters of DC battery cabinets.

[0112] Step S308: randomly select a target single cluster of batteries in the multi-cluster DC battery cabinet, and isolate the battery scheduling response mode of the target single cluster of batteries.

[0113] Step S309: Control the target battery cluster to perform power-on processing through the power-on control unit.

[0114] Step S310 , based on the battery specification information of the target battery cluster, identifying the minimum continuous charging value of the target battery cluster, and performing continuous charging processing on the target battery cluster through the power-on control unit based on the minimum continuous charging value.

[0115] Step S311, detecting the current battery voltage value of the target single-cluster battery, and when the current battery voltage value is lower than the full calibration voltage threshold, returning to the step of detecting the current battery voltage value of the target single-cluster battery, until the current battery voltage value is equal to the full calibration voltage threshold, determining that the highest single cell voltage of the target single-cluster battery reaches the full calibration voltage threshold.

[0116] Step S312 , when the highest cell voltage of the target battery cluster reaches the full charge calibration voltage threshold, the current state of charge of the target battery cluster is replaced based on the preset state of charge calibration value to obtain a new state of charge of the target battery cluster.

[0117] Step S313: Based on the new state of charge, the state of charge calibration process is performed on the target single cluster battery, and the battery scheduling response mode of the target single cluster battery is restored.

[0118] Step S314, in the multi-cluster DC battery cabinet, re-screen the target single cluster batteries that have not been screened as target single cluster batteries, and return to execute the battery scheduling response method step of isolating the target single cluster batteries, until all single cluster batteries have completed the charge state calibration processing, and determine that the multi-cluster DC battery cabinet has completed the charge state calibration processing.

[0119] Step S315 , identifying the current state of charge of the multi-cluster DC battery cabinet, and replacing the battery cluster state of charge of the multi-cluster DC battery cabinet with the current state of charge.

[0120] Step S316, the maintenance time is reset to zero, completing the task of updating the maintenance time of the multi-cluster DC battery cabinet in the battery cluster charged state.

[0121] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0122] Based on the same inventive concept, the embodiment of the present application also provides a battery state of charge calibration device for implementing the battery state of charge calibration method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more battery state of charge calibration devices provided below can refer to the limitations of the battery state of charge calibration method above, and will not be repeated here.

[0123] In an exemplary embodiment, Figure 4 As shown, a battery state of charge calibration device is provided, including: an acquisition module 410, a first calibration module 420, a second calibration module 430 and an update module 440, wherein:

[0124] An acquisition module 410 is used to acquire a battery cluster charge state of a multi-cluster DC battery cabinet, a maintenance time of the multi-cluster DC battery cabinet in the battery cluster charge state, and a current calibration time of the multi-cluster DC battery cabinet;

[0125] The first calibration module 420 is used to perform a state of charge calibration process on the multi-cluster DC battery cabinet through a cloud-based passive state of charge calibration strategy when the current calibration time of the multi-cluster DC battery cabinet is lower than a preset time threshold, the state of charge of the battery cluster is a preset state of charge, and the maintenance time of the multi-cluster DC battery cabinet in the battery cluster state of charge is longer than a preset time.

[0126] The first calibration module 430 is used to perform a state of charge calibration process on the multi-cluster DC battery cabinet through an active state of charge calibration strategy when the current calibration time of the multi-cluster DC battery cabinet is higher than the preset time threshold, the state of charge of the battery cluster is the preset state of charge, and the maintenance time of the multi-cluster DC battery cabinet in the battery cluster state of charge is longer than the preset time;

[0127] The updating module 440 is used to update the battery cluster charge state of the multi-cluster DC battery cabinet and the maintenance time of the multi-cluster DC battery cabinet in the battery cluster charge state after completing the calibration process.

[0128] Optionally, the first calibration module 420 is specifically configured to:

[0129] Obtaining full battery data of a multi-cluster DC battery cabinet at all times, and judging whether the multi-cluster DC battery cabinet meets a charge state calibration condition based on the current full battery data;

[0130] When the multi-cluster DC battery cabinet meets the charge state calibration condition, based on the current battery full quantity data, the current charge state of the multi-cluster DC battery cabinet is calculated by a charge state identification model;

[0131] The current state of charge is sent to a local state calibration unit via the cloud, and based on the current state of charge, the state of charge calibration process is performed on the multi-cluster DC battery cabinet via the local state calibration unit.

[0132] Optionally, the first calibration module 420 is specifically configured to:

[0133] Based on the battery full quantity data, identifying the battery voltage value of the multi-cluster DC battery cabinet, the battery current value of the multi-cluster DC battery cabinet, and the battery temperature value of the multi-cluster DC battery cabinet;

[0134] Based on the battery voltage value, the battery current value, and the battery temperature value, an initial state of charge recognition model is trained, and when the number of training times of the initial state of charge recognition model is less than a preset number of training times, returning to execute the step of obtaining current full battery data of the multi-cluster DC battery cabinet;

[0135] When the training times of the initial state of charge recognition model is not less than the preset training times, the initial state of charge recognition model obtained by the last iteration is used as the target state of charge recognition model, and it is determined that the multi-cluster DC battery cabinet meets the state of charge calibration condition.

[0136] Optionally, the second calibration module 430 is specifically configured to:

[0137] In a multi-cluster DC battery cabinet, randomly selecting a target single cluster of batteries and isolating a battery scheduling response mode of the target single cluster of batteries;

[0138] Controlling the target battery cluster to perform power-on processing through a power-on control unit, and when the highest cell voltage of the target battery cluster reaches a full charge calibration voltage threshold, replacing the current state of charge of the target battery cluster based on a preset state of charge calibration value to obtain a new state of charge of the target battery cluster;

[0139] Based on the new state of charge, the state of charge calibration process is performed on the target single cluster battery, and the battery scheduling response mode of the target single cluster battery is restored;

[0140] In the multi-cluster DC battery cabinet, the target single cluster batteries that have not been screened as target single cluster batteries are rescreened, and the battery scheduling response method step of isolating the target single cluster batteries is returned to execute until all single cluster batteries have completed the state of charge calibration processing, and it is determined that the multi-cluster DC battery cabinet has completed the state of charge calibration processing.

[0141] Optionally, the device further comprises:

[0142] a power-on module, configured to identify a minimum continuous charging value of the target single-cluster battery based on the battery specification information of the target single-cluster battery, and perform continuous charging processing on the target single-cluster battery through the power-on control unit based on the minimum continuous charging value;

[0143] The detection module is used to detect the current battery voltage value of the target single-cluster battery, and when the current battery voltage value is lower than the full calibration voltage threshold, return to the step of detecting the current battery voltage value of the target single-cluster battery, until the current battery voltage value is equal to the full calibration voltage threshold, and determine that the highest single cell voltage of the target single-cluster battery reaches the full calibration voltage threshold.

[0144] Optionally, the updating module 440 is specifically configured to:

[0145] Identifying a current state of charge of the multi-cluster DC battery cabinet, and replacing the battery cluster state of charge of the multi-cluster DC battery cabinet with the current state of charge;

[0146] The maintenance time is reset to zero, completing the task of updating the maintenance time of the multi-cluster DC battery cabinet in the battery cluster charge state.

[0147] Each module in the above-mentioned battery state of charge calibration device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0148] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for calibrating the state of charge of a battery is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0149] Those skilled in the art will understand that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0150] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0151] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0152] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0153] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0154] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0155] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0156] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for calibrating a battery state of charge, characterized in that: The method comprises: Acquire the battery cluster charge state of a multi-cluster DC battery cabinet, the duration for which the multi-cluster DC battery cabinet is in the battery cluster charge state, and the current calibration time of the multi-cluster DC battery cabinet; When the current calibration time of the multi-cluster DC battery cabinet is lower than the preset time threshold, the state of charge of the battery cluster is lower than 30% of the state of charge, and the maintenance time of the multi-cluster DC battery cabinet in the state of charge of the battery cluster is longer than the preset time, obtain the full battery data of the multi-cluster DC battery cabinet in the whole period, and identify the battery voltage value of the multi-cluster DC battery cabinet, the battery current value of the multi-cluster DC battery cabinet, and the battery temperature value of the multi-cluster DC battery cabinet based on the full battery data; Based on the battery voltage value, the battery current value, and the battery temperature value, an initial state of charge recognition model is trained, and when the number of training times of the initial state of charge recognition model is less than a preset number of training times, returning to execute the step of obtaining current full battery data of the multi-cluster DC battery cabinet; When the training times of the initial state of charge recognition model is not less than the preset training times, the initial state of charge recognition model obtained by the last iteration is used as the target state of charge recognition model, and it is determined that the multi-cluster DC battery cabinet meets the state of charge calibration condition; When the multi-cluster DC battery cabinet meets the charge state calibration condition, based on the current battery full quantity data, the current charge state of the multi-cluster DC battery cabinet is calculated by a charge state identification model; The current state of charge is sent to a local state calibration unit via the cloud, and based on the current state of charge, the state of charge calibration process is performed on the multi-cluster DC battery cabinet via the local state calibration unit; When the current calibration time of the multi-cluster DC battery cabinet is higher than the preset time threshold, the battery cluster state of charge is not less than 30% of the state of charge, and the multi-cluster DC battery cabinet is in the battery cluster state of charge for a duration longer than the preset duration, in the multi-cluster DC battery cabinet, a target single cluster battery is randomly selected, and the battery scheduling response mode of the target single cluster battery is cut off; The target single cluster battery is controlled to be powered on by a power-on control unit, and based on the battery specification information of the target single cluster battery, the minimum continuous charging value of the target single cluster battery is identified by a minimum continuous current algorithm, and based on the minimum continuous charging value, the target single cluster battery is continuously charged by the power-on control unit; the calculation formula of the minimum continuous current algorithm is as follows: The continuous charging current value of the stack = the number of contactor closing clusters * the minimum continuous charging current value of the cluster; In the above formula, the minimum continuous charging current of the cluster is the minimum continuous charging value; The current battery voltage value of the target single-cluster battery is detected, and when the current battery voltage value is lower than the full calibration voltage threshold, the step of detecting the current battery voltage value of the target single-cluster battery is returned to execute until the current battery voltage value is equal to the full calibration voltage threshold, and it is determined that the highest single cell voltage of the target single-cluster battery reaches the full calibration voltage threshold; the current battery voltage value of the target single-cluster battery is detected and calculated by a charge and discharge detection algorithm, and the calculation formula of the charge and discharge detection algorithm is as follows: ； In the above formula, InitChrgCapAh k is the cumulative charging capacity at the current moment, InitDchaCapAh is the cumulative discharge capacity at the current moment, DeltaCap k is the capacity change value during the charge and discharge process, k is the virtual number of the target cluster battery; The calculation formula for calculating the change value of the battery state of charge is: ； In the above formula, △SOC k DeltaCap is the current change in battery state of charge. k is the capacity change during the charge and discharge process, SOHAry.Cap rated is the preset corresponding ratio value; The calculation formula for iteratively calculating the battery state of charge of all cells based on the change value of the battery state of charge is: ； In the above formula, SOC k is the current state of charge value of the target single cluster battery, InitSOC is the preset target battery state of charge value, △SOC k is the current change value of the battery state of charge; Based on a preset state of charge calibration value, replacing the current state of charge of the target single cluster battery to obtain a new state of charge of the target single cluster battery; Based on the new state of charge, the state of charge calibration process is performed on the target single cluster battery, and the battery scheduling response mode of the target single cluster battery is restored; In the multi-cluster DC battery cabinet, the target single-cluster batteries that have not been selected as the target single-cluster batteries are re-screened, and the battery scheduling response mode step of isolating the target single-cluster batteries is returned to be executed until all the single-cluster batteries have completed the state of charge calibration process, and it is determined that the multi-cluster DC battery cabinet has completed the state of charge calibration process; After the calibration process is completed, the battery cluster charge states of the multi-cluster DC battery cabinet and the duration for which the multi-cluster DC battery cabinet is in the battery cluster charge state are updated.

2. The method according to claim 1, characterized in that: The updating of the battery cluster charge state of the multi-cluster DC battery cabinet and the duration for which the multi-cluster DC battery cabinet is in the battery cluster charge state includes: Identifying a current state of charge of the multi-cluster DC battery cabinet, and replacing the battery cluster state of charge of the multi-cluster DC battery cabinet with the current state of charge; The maintenance time is reset to zero, completing the task of updating the maintenance time of the multi-cluster DC battery cabinet in the battery cluster charge state.

3. A battery state of charge calibration device, characterized in that: The device comprises: An acquisition module, used to acquire the battery cluster charge state of a multi-cluster DC battery cabinet, the duration for which the multi-cluster DC battery cabinet is in the battery cluster charge state, and the current calibration time of the multi-cluster DC battery cabinet; The first calibration module is used to obtain the full battery data of the multi-cluster DC battery cabinet in the whole period when the current calibration time of the multi-cluster DC battery cabinet is lower than the preset time threshold, the state of charge of the battery cluster is lower than 30%, and the maintenance time of the multi-cluster DC battery cabinet in the state of charge of the battery cluster is longer than the preset time, and based on the full battery data, identify the battery voltage value of the multi-cluster DC battery cabinet, the battery current value of the multi-cluster DC battery cabinet, and the battery temperature value of the multi-cluster DC battery cabinet; based on the battery voltage value, the battery current value, and the battery temperature value, train an initial state of charge recognition model, and when the number of training times of the initial state of charge recognition model is lower than the preset number of training times, return to execute The steps of obtaining the current full battery data of the multi-cluster DC battery cabinet are performed; when the training times of the initial state of charge recognition model are not less than the preset training times, the initial state of charge recognition model obtained by the last iteration is used as the target state of charge recognition model, and it is determined that the multi-cluster DC battery cabinet meets the state of charge calibration condition; when the multi-cluster DC battery cabinet meets the state of charge calibration condition, based on the current full battery data, the current state of charge of the multi-cluster DC battery cabinet is calculated through the state of charge recognition model; the current state of charge is sent to the local state calibration unit through the cloud, and based on the current state of charge, the state of charge calibration processing of the multi-cluster DC battery cabinet is performed through the local state calibration unit; The first calibration module is used to randomly select a target single cluster battery in the multi-cluster DC battery cabinet and cut off the battery scheduling response mode of the target single cluster battery when the current calibration time of the multi-cluster DC battery cabinet is higher than the preset time threshold, the charge state of the battery cluster is not less than 30%, and the maintenance time of the multi-cluster DC battery cabinet in the charge state of the battery cluster is longer than the preset time; control the target single cluster battery to perform power-on processing through the power-on control unit, and identify the minimum continuous charging value of the target single cluster battery through the minimum continuous current algorithm based on the battery specification information of the target single cluster battery, and perform continuous charging processing on the target single cluster battery through the power-on control unit based on the minimum continuous charging value. The calculation formula of the minimum continuous current algorithm is as follows: stack continuous charging current value = number of contactor closed clusters * minimum cluster continuous charging current value; in the above formula, the minimum cluster continuous charging current value is the minimum continuous charging value; the current battery voltage value of the target single cluster battery is detected, and when the current battery voltage value is lower than the full calibration voltage threshold, the step of detecting the current battery voltage value of the target single cluster battery is returned to execute until the current battery voltage value is equal to the full calibration voltage threshold, and the highest single cell voltage of the target single cluster battery is determined to reach the full calibration voltage threshold; the current battery voltage value of the target single cluster battery is detected and calculated by the charge and discharge detection algorithm, and the calculation formula of the charge and discharge detection algorithm is as follows: ; In the above formula, InitChrgCapAh k is the cumulative charging capacity at the current moment, InitDchaCapAh is the cumulative discharge capacity at the current moment, DeltaCap k is the capacity change value during the charge and discharge process, and k is the virtual number of the target cluster battery; wherein the calculation formula for calculating the change value of the battery state of charge is: ; In the above formula, △SOC k DeltaCap is the current change in battery state of charge. k is the capacity change during the charge and discharge process, SOHAry.Cap rated is a preset corresponding ratio value; wherein, based on the change value of the battery state of charge, the calculation formula for iteratively calculating the battery state of charge of all cells is: ; In the above formula, SOC k is the current state of charge value of the target single cluster battery, InitSOC is the preset target battery state of charge value, △SOC k is the current change value of the battery state of charge; based on the preset state of charge calibration value, the current state of charge of the target single cluster battery is replaced to obtain the new state of charge of the target single cluster battery; based on the new state of charge, the state of charge calibration process is performed on the target single cluster battery, and the battery scheduling response mode of the target single cluster battery is restored; in the multi-cluster DC battery cabinet, the target single cluster battery that has not been screened as the target single cluster battery is re-screened, and the battery scheduling response mode step of isolating the target single cluster battery is returned to execute until all single cluster batteries have completed the state of charge calibration process, and it is determined that the multi-cluster DC battery cabinet has completed the state of charge calibration process; The updating module is used to update the battery cluster charge state of the multi-cluster DC battery cabinet and the maintenance time of the multi-cluster DC battery cabinet in the battery cluster charge state after completing the calibration process.

4. 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, the steps of the method according to any one of claims 1 to 2 are implemented.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 2 are implemented.

6. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 2 are implemented.

Images