A refined management method and system for single-cluster batteries
By monitoring and predicting the power supply data of the battery cells in the battery cluster in real time, the problem of unbalanced output when the battery cells in the electric locomotive battery cluster is solved, and the balanced output and stable operation of the battery cluster are achieved.
Patent Information
- Application Number
- CN202411117194.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-15
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-08-15
AI Technical Summary
When the battery cells are operated uniformly, the existing large-capacity battery clusters of electric locomotives lack analysis of the health status and output stability of the single battery cells, which makes it difficult to maintain the balanced output of the battery clusters when any one or more battery cells fail.
By collecting and monitoring the power supply data of each battery cell in the battery cluster in real time, we predict whether each battery cell can supply power normally in the next power supply period, and shield the faulty battery cell when it is predicted and adjust the output power of other battery cells. To achieve the equalization output of the battery cluster.
The balanced output of the battery cluster is realized, the attenuation and consistency requirements are reduced, and the faulty battery cells are quickly shielded to ensure the stable operation of the battery cluster.
Smart Images

Figure CN118636748B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of locomotives, and in particular to a refined management method and system for a single-cluster battery. Background Art
[0002] Locomotives are divided into steam locomotives, diesel locomotives, gas turbine locomotives, etc. These locomotives carry fuel and water, are self-powered locomotives, and can travel independently. These locomotives all have the problem of polluting the environment. Later, electric locomotives came into being, but existing electric locomotives have large-capacity batteries, and large-capacity batteries are usually composed of multiple battery clusters, each of which is composed of multiple single cells in parallel. The existing BMS system lacks analysis of the health status of each single cell in the battery cluster. When managing the output of the battery cell, there is a lack of stability analysis of the output of the battery cell. When all batteries in the battery cluster are operating uniformly and working at the same time, how to maintain the balanced output of the entire battery cluster when any one or more cells fail. Summary of the invention
[0003] The present invention provides a refined management method and system for a single battery cluster to solve the technical problem of how to maintain balanced output of the entire battery cluster when any one or more cells fail during the period when all batteries in the battery cluster are operating uniformly and working simultaneously.
[0004] The embodiment of the present invention provides a refined management method for a single battery cluster, comprising:
[0005] Real-time collection and monitoring of the cell power supply data of each cell in the battery cluster currently supplying power, the cell power supply data including at least multiple power supply time periods and the voltage, current, SOC, output power and temperature corresponding to each power supply time period;
[0006] Using the battery power supply data of each battery cell in the battery cluster, predicting whether each battery cell can supply power normally in the next power supply time period;
[0007] If it is predicted that any one or more cells cannot supply power normally in the next power supply time period, the cells that cannot supply power normally are shielded before the next power supply time period, and the output power of the cells that can supply power normally in the next power supply time period is adjusted to achieve balanced output of the battery cluster.
[0008] Preferably, it also includes:
[0009] Obtain historical battery power supply data and corresponding health status of multiple battery cells at different output powers;
[0010] A predicted cell health model is established, and the predicted cell health model is trained using the historical cell power supply data to obtain a trained predicted cell health model.
[0011] Preferably, using the cell power supply data of each cell in the battery cluster to predict whether each cell can supply power normally in the next power supply time period includes:
[0012] If the power supply data of any battery cell in the battery cluster corresponding to the power supply data of the battery cell during the current power supply time period jumps, it is predicted that the battery cell cannot supply power normally in the next power supply time period;
[0013] If the cell power supply data corresponding to the cell power supply data of any cell in the battery cluster during the current power supply time period does not change, the trained predicted cell health model is further used to predict whether the cell can supply power normally in the next power supply time period.
[0014] Preferably, using the trained predicted cell health model to predict whether the cell can supply power normally in the next power supply time period includes:
[0015] The health of each battery cell in the battery cluster is obtained by inputting the battery cell power supply data of each battery cell in the battery cluster into the trained predicted battery cell health model;
[0016] If the health of any battery cell in the next power supply time period is not lower than the health threshold, it is predicted that the battery cell can supply power normally in the next power supply time period;
[0017] If the health of any battery cell in the next power supply time period is lower than the health threshold, it is predicted that the battery cell cannot supply power normally in the next power supply time period.
[0018] Preferably, it also includes:
[0019] Collect and monitor the cell charging data of each cell in the battery cluster in real time, where the cell charging data includes at least multiple charging time points and the voltage, current, SOC, output power and temperature corresponding to each charging time point;
[0020] Using the battery cell charging data of each battery cell in the battery cluster, determining whether each battery cell can supply power normally;
[0021] If it is determined that any cell in the battery cluster cannot supply power normally, the power supply of the cell is shielded before the battery cluster supplies power, and the output power of other cells is adjusted to achieve balanced output of the battery cluster.
[0022] Preferably, using the battery cell charging data of each battery cell in the battery cluster to determine whether each battery cell can supply power normally includes:
[0023] If the charging data of any cell in the battery cluster changes, it is determined that the cell cannot supply power normally, and the fault type is determined according to the charging data of the cell that changes, and a corresponding fault alarm is issued based on the fault type.
[0024] Preferably, adjusting the output power of the battery cell capable of normal power supply in the next power supply time period includes:
[0025] According to the total output power of the battery cluster and the number of cells that can normally supply power in the next power supply time period, the second output power of each cell that can normally supply power is calculated, and the second output power is used as the output power of each cell that can normally supply power in the next power supply time period.
[0026] Preferably, the second output powers of each battery cell capable of supplying power normally are equal or unequal, and the difference between the second output power values is not greater than a preset difference threshold.
[0027] The embodiment of the present invention further provides a refined management system for a single battery cluster, including:
[0028] A monitoring module is used to collect and monitor the power supply data of each battery cell in the battery cluster currently supplying power in real time, where the power supply data of the battery cell includes at least multiple power supply time periods and the voltage, current, SOC, output power and temperature corresponding to each power supply time period;
[0029] A prediction module, used to use the cell power supply data of each cell in the battery cluster to predict whether each cell can supply power normally in the next power supply time period;
[0030] The balancing management module is used to shield the cells that cannot supply power normally before the next power supply period if it is predicted that any one or more cells cannot supply power normally in the next power supply period, and adjust the output power of the cells that can supply power normally in the next power supply period to achieve balanced output of the battery cluster.
[0031] Preferably, the prediction module is also used to obtain historical battery cell power supply data of multiple battery cells at different output powers and their corresponding health levels; establish a predicted battery cell health model, and use the historical battery cell power supply data to train the predicted battery cell health model to obtain a trained predicted battery cell health model.
[0032] The beneficial effect of the present invention is that the power supply data of each battery cell in the battery cluster currently supplying power is collected and monitored in real time, and whether each battery cell can supply power normally in the next power supply time period is predicted; if it is predicted that any one or more battery cells cannot supply power normally in the next power supply time period, the battery cells that cannot supply power normally are shielded before the next power supply time period, and the output power of the battery cells that can supply power normally in the next power supply time period is adjusted to achieve balanced output of the battery cluster, thereby reducing consistency requirements, reducing attenuation, quickly shielding faulty battery cells, and achieving balanced output of the entire battery cluster by adjusting the output power of normal battery cells. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 It is a flow chart of a refined management method of a single-cluster battery provided by an embodiment of the present invention;
[0034] Figure 2 This is a schematic diagram of the appearance of a single 4.5MWh container battery system provided by an embodiment of the present invention;
[0035] Figure 3 This is a schematic diagram of the internal layout of a single 4.5MWh container battery system provided by an embodiment of the present invention;
[0036] Figure 4 This is a schematic diagram of the architecture of a single 4.5MWh container battery system provided by an embodiment of the present invention;
[0037] Figure 5 1 is a front view schematic diagram of a battery cluster in a single 4.5MWh container battery system provided by an embodiment of the present invention;
[0038] Figure 6 is a schematic diagram of the layout of a thermal management system provided by an embodiment of the present invention;
[0039] Figure 7 It is a schematic diagram of the functional relationship between the abnormal evaluation value of the power-on and power-off control environment and the battery abnormal interference index provided by an embodiment of the present invention;
[0040] Figure 8 is a bottom view schematic diagram of a partial structure of an energy storage system in an electric locomotive provided by an embodiment of the present invention;
[0041] Fig. 9 It is a structural schematic diagram of a hoisting matching mechanism provided on a bottom frame of an energy storage system in an electric locomotive provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0042] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. In the subsequent description, the use of suffixes such as "module", "component" or "unit" used to represent elements is only to facilitate the description of the present invention and has no specific meaning in itself. Therefore, "module", "component" or "unit" can be used in a mixed manner.
[0043] Figure 1 is a flow chart of a refined management method for a single battery cluster provided by an embodiment of the present invention, such as Figure 1 As shown, including:
[0044] Step S101: collecting and monitoring the cell power supply data of each cell in the battery cluster currently supplying power in real time, where the cell power supply data at least includes multiple power supply time periods and the voltage, current, SOC, output power and temperature corresponding to each power supply time period;
[0045] Step S102: using the power supply data of each battery cell in the battery cluster, predicting whether each battery cell can supply power normally in the next power supply time period;
[0046] Step S103: If it is predicted that any one or more cells cannot supply power normally in the next power supply time period, the cells that cannot supply power normally are shielded before the next power supply time period, and the output power of the cells that can supply power normally in the next power supply time period is adjusted to achieve balanced output of the battery cluster.
[0047] In an embodiment of the present invention, it also includes: obtaining historical battery cell power supply data of multiple battery cells at different output powers and their corresponding health levels; establishing a predictive battery cell health model, and using the historical battery cell power supply data to train the predictive battery cell health model to obtain a trained predictive battery cell health model.
[0048] Furthermore, using the cell power supply data of each cell in the battery cluster, predicting whether each cell can supply power normally in the next power supply time period includes: if the cell power supply data corresponding to the current power supply time period in the cell power supply data of any cell in the battery cluster changes, then predicting that the cell cannot supply power normally in the next power supply time period; if the cell power supply data corresponding to the current power supply time period in the cell power supply data of any cell in the battery cluster does not change, then further using the trained predictive cell health model to predict whether the cell can supply power normally in the next power supply time period.
[0049] Specifically, using the trained predicted cell health model to predict whether the cell can supply power normally in the next power supply time period includes: inputting the cell power supply data of each cell in the battery cluster into the trained predicted cell health model to obtain the health of each cell in the next power supply time period; if the health of any cell in the next power supply time period is not lower than the health threshold, it is predicted that the cell can supply power normally in the next power supply time period; if the health of any cell in the next power supply time period is lower than the health threshold, it is predicted that the cell cannot supply power normally in the next power supply time period.
[0050] In an embodiment of the present invention, it also includes: real-time collection and monitoring of battery cell charging data of each battery cell in the battery cluster, the battery cell charging data at least including multiple charging time points and the voltage, current, SOC, output power and temperature corresponding to each charging time point; using the battery cell charging data of each battery cell in the battery cluster to determine whether each battery cell can supply power normally; if it is determined that any battery cell in the battery cluster cannot supply power normally, shielding the power supply of the battery cell before the battery cluster supplies power, and adjusting the output power of other battery cells to achieve balanced output of the battery cluster.
[0051] Furthermore, using the battery cell charging data of each battery cell in the battery cluster to determine whether each battery cell can supply power normally includes: if the battery cell charging data of any battery cell in the battery cluster changes, then determining that the battery cell cannot supply power normally, and determining the fault type according to the charging data of the battery cell that changes, and issuing a corresponding fault alarm based on the fault type.
[0052] Specifically, adjusting the output power of the battery cells that can supply power normally in the next power supply time period includes: calculating the second output power of each battery cell that can supply power normally according to the total output power of the battery cluster and the number of battery cells that can supply power normally in the next power supply time period, and using the second output power as the output power of each battery cell that can supply power normally in the next power supply time period. Among them, the second output power of each battery cell that can supply power normally is equal or unequal, and the difference between the second output power values is not greater than the preset difference threshold. For example, if the battery cluster is powered by 4 battery cells at the same time, and the total output power of the battery cluster is 1000W, and the output power of each battery cell is 250W, if it is predicted that a certain battery cell cannot supply power normally in the next power supply time period, the battery cell is shielded from supplying power in the next power supply time period, and the output power of the other three battery cells is adjusted to (1000 / 3)W or the output power of the other three battery cells is adjusted as needed. Alternatively, if the output power of a cell in the current power supply period is much smaller or greater than the output power of the other three cells, and it is predicted that a cell cannot supply power normally in the next power supply period, the cell will be blocked from supplying power in the next power supply period, and the output power of the other three cells will be adjusted. It should be noted that during the power supply period of each cell in the battery cluster, the output power of each cell can be the same or different, and can be adjusted according to the load power supply demand.
[0053] The refined management method of a single-cluster battery provided by the present invention collects and monitors the cell power supply data of each cell in the currently powered battery cluster in real time, and predicts whether each cell can supply power normally in the next power supply time period; if it is predicted that any one or more cells cannot supply power normally in the next power supply time period, the cells that cannot supply power normally are shielded before the next power supply time period, and the output power of the cells that can supply power normally in the next power supply time period is adjusted to achieve balanced output of the battery cluster, so that after predicting that any one or more cells cannot supply power normally, the cells that cannot supply power normally are quickly shielded, and balanced output of the entire battery cluster is achieved by adjusting the output power of the normal cells.
[0054] The embodiment of the present invention also provides a refined management system for a single-cluster battery, including: a monitoring module, used to collect and monitor in real time the cell power supply data of each cell in the battery cluster currently supplying power, the cell power supply data including at least multiple power supply time periods and the voltage, current, SOC, output power and temperature corresponding to each power supply time period; a prediction module, used to use the cell power supply data of each cell in the battery cluster to predict whether each cell can supply power normally in the next power supply time period; a balancing management module, used to shield the cells that cannot supply power normally before the next power supply time period if it is predicted that any one or more cells cannot supply power normally in the next power supply time period, and adjust the output power of the cells that can supply power normally in the next power supply time period to achieve balanced output of the battery cluster.
[0055] Furthermore, the prediction module is also used to obtain historical battery cell power supply data of multiple battery cells at different output powers and their corresponding health levels; establish a predicted battery cell health model, and use the historical battery cell power supply data to train the predicted battery cell health model to obtain a trained predicted battery cell health model.
[0056] In the embodiment of the present invention, the container battery system includes a battery cluster, a DC / DC converter, a convergence module, and a power distribution module; the electric energy inside the container battery system can be stored and released according to the vehicle control system. The input and output ports of the container battery system have high-voltage direct current and low-voltage communication.
[0057] During the period of realizing balanced output of the entire battery cluster, the present invention also provides a control method based on a power-swap locomotive, including: acquiring power-on and power-off control environment data and high-voltage system status data through a sensor network, comprehensively analyzing to obtain a battery abnormal interference index of the power-swap locomotive, and processing to obtain a battery cluster abnormality assessment threshold based on the battery abnormal interference index of the power-swap locomotive; monitoring the abnormal status data of each battery cell of the power-swap locomotive, comprehensively analyzing to obtain a battery cluster abnormality assessment value of the power-swap locomotive; comparing the battery cluster abnormality assessment value of the power-swap locomotive with the battery cluster abnormality assessment threshold, and if the battery cluster abnormality assessment value of the power-swap locomotive is greater than the battery cluster abnormality assessment threshold, power-off control is performed on the power-swap locomotive.
[0058] Specifically, a comprehensive analysis is conducted to obtain the abnormal battery interference index of the battery swapping locomotive. The specific analysis process is as follows: deploy several environmental monitoring points, collect the ambient temperature, ambient humidity and ambient air pressure at each environmental monitoring point, and obtain the reference suitable ambient temperature, reference suitable ambient humidity and reference suitable ambient air pressure from the battery swapping locomotive database, and obtain the abnormal assessment value of the up and down power control environment after processing.
[0059] In a specific embodiment, the environmental anomaly assessment influencing factors corresponding to the set ambient temperature, ambient humidity and ambient pressure are obtained from the electric-swap locomotive database, and the allowable deviation ambient temperature, allowable deviation ambient humidity and allowable deviation ambient pressure are extracted from the electric-swap locomotive database, and the up and down power control environment anomaly assessment value is obtained by comprehensive analysis. The specific numerical expression is:
[0060]
[0061] In the formula, Indicates the abnormal evaluation value of the power-on and power-off control environment. represents the ambient temperature of the jth environmental monitoring point, represents the ambient humidity at the jth environmental monitoring point, represents the ambient air pressure at the jth environmental monitoring point, Indicates the reference to the appropriate ambient temperature. Indicates reference to suitable ambient humidity. Indicates reference to suitable ambient air pressure. Indicates the allowable deviation ambient temperature, Indicates the allowable deviation of ambient humidity, Indicates the allowable deviation of ambient pressure, Indicates the environmental anomaly assessment impact factor corresponding to the set ambient temperature. Indicates the environmental anomaly assessment impact factor corresponding to the set environmental humidity. It represents the environmental anomaly assessment impact factor corresponding to the set ambient air pressure, j represents the number of each environmental monitoring point, j=1,2,3,...,m, and m represents the total number of environmental monitoring points.
[0062] It should be understood that in this embodiment, the value range of the environmental anomaly assessment impact factor corresponding to the ambient temperature, ambient humidity and ambient pressure is between 0 and 1. A mapping set of ambient temperature, ambient humidity and ambient pressure and the corresponding environmental anomaly assessment impact factors can be established through historical environmental data. According to the ambient temperature, ambient humidity and ambient pressure obtained by real-time monitoring, the environmental anomaly assessment impact factors corresponding to the ambient temperature, ambient humidity and ambient pressure are obtained through the mapping set.
[0063] In a specific embodiment, the abnormal evaluation value of the power-on / off control environment is used to quantitatively evaluate the abnormal degree of the power-on / off control environment, and provide a data basis for power-on / off control. The abnormal evaluation value of the power-on / off control environment is related to the ambient temperature, ambient humidity, and ambient air pressure. The more the ambient temperature, ambient humidity, and ambient air pressure deviate from the corresponding reference suitable index, the larger the abnormal evaluation value of the power-on / off control environment is, indicating that the power-on / off control environment is more abnormal.
[0064] It should be understood that in this embodiment, the environmental monitoring points are deployed to monitor the power-on and power-off control environmental data. Power-on and power-off control refers to the process management of opening (powering on) and closing (powering off) the high-voltage electrical system of the electric swapping locomotive. This process involves the orderly power-on and power-off of multiple high-voltage components of the vehicle to ensure the safety and efficiency of the operation.
[0065] The power-on process refers to starting the entire electrical system and ensuring that each subsystem is activated in a predetermined order to prepare for vehicle operation, including waking up the BMS (Battery Management System) to monitor the battery status, activating the MCU (Microcontroller Unit) to control the motor, and safely closing the high-voltage contactor through the pre-charging circuit so that the high-voltage battery can supply power to the vehicle's high-voltage system.
[0066] The power-off process refers to the control process of system shutdown, including gradually shutting down high-voltage loads, disconnecting high-voltage power supplies, performing necessary safety checks and energy release, and ultimately allowing the entire high-voltage system to safely enter a non-working state.
[0067] In this embodiment, the power-on and power-off control environment data will have a direct impact on the power-on and power-off control. By monitoring the power-on and power-off control environment data, it is helpful to comprehensively improve the safety and efficiency of the system, ensure that all operations are performed under appropriate environmental conditions, and prevent safety hazards caused by extreme environments. In addition, environmental monitoring data can also optimize battery management strategies, adjust the charging and discharging process according to the real-time environment, and avoid excessive charging and discharging of batteries in extreme environments. It can not only improve charging and discharging efficiency and reduce energy consumption, but also help maintain battery health and extend battery life. The power-on and power-off control environment data can be used as part of predictive maintenance. By analyzing the relationship between environmental conditions and battery performance degradation, potential problems can be identified in advance, maintenance intervention can be carried out in a timely manner, and failures can be reduced.
[0068] Deploy several time monitoring points to collect the actual voltage and current of the high-voltage system at each time monitoring point, obtain the reference standard current of the high-voltage system from the battery-changing locomotive database, and obtain the abnormal status assessment value of the high-voltage system after processing.
[0069] In a specific embodiment, the abnormal influence factor of the high-voltage system state corresponding to the set voltage and current is obtained from the electric-swap locomotive database, and the allowable deviation current of the high-voltage system is extracted from the electric-swap locomotive database. The abnormal evaluation value of the high-voltage system state is obtained by comprehensive analysis. The specific numerical expression is:
[0070]
[0071] In the formula, Indicates the abnormal evaluation value of the high-voltage system status. represents the actual voltage at the i-th time monitoring point, represents the actual current at the i-th time monitoring point, Indicates the reference standard current of the high voltage system. Indicates the allowable deviation current of the high voltage system. Indicates the abnormal impact factor of the high voltage system state corresponding to the set voltage, It represents the abnormal impact factor of the high voltage system state corresponding to the set current, i represents the number of each time monitoring point, i=1,2,3,...,n, and n represents the total number of time monitoring points.
[0072] It should be understood that in this embodiment, the value range of the high-voltage system state abnormality influencing factors corresponding to the voltage and current is between 0 and 1. A mapping set of voltage and current and corresponding high-voltage system state abnormality influencing factors can be established through historical high-voltage system state data. According to the voltage and current of the high-voltage system obtained by monitoring, the high-voltage system state abnormality influencing factors corresponding to the voltage and current are obtained through the mapping set.
[0073] Table 1 Example of abnormal evaluation value data of high-voltage system status
[0074]
[0075] As shown in Table 1, in a specific embodiment, =200A, =5A, =0.6, =0.4. To simplify the calculation, it is assumed that five groups of time monitoring point data are collected, and the values of each group of data are the same. =1003V.
[0076] It should be understood that the abnormal evaluation value of the high-voltage system state in this embodiment is used to quantitatively evaluate the abnormality of the high-voltage system state of the power-swap locomotive. The abnormal evaluation value of the high-voltage system state is related to the actual voltage and actual current of the high-voltage system. When the fluctuation level of the actual voltage is greater and the actual current deviates from the reference standard value, the corresponding abnormal evaluation value of the high-voltage system state is greater, indicating that the state of the high-voltage system of the power-swap locomotive is more abnormal.
[0077] The formula of this embodiment combines two important parameters, voltage and current, and realizes a comprehensive evaluation of the state of the high-voltage system by calculating the difference between the actual value and the standard value or average value at each time monitoring point, as well as the weight of these differences in the overall evaluation. By introducing the weight factor, the relative importance of voltage and current in the evaluation can be adjusted according to the actual situation, so that the evaluation results are more in line with actual needs. The square root and summation operations in the formula help to highlight the impact of outliers, so that when large deviations occur in the system, the evaluation value can be quickly reflected, thereby achieving the purpose of anomaly detection.
[0078] It should be understood that the high-voltage system of the battery-swap locomotive in this embodiment refers to the overall system consisting of electrical components in the vehicle involving high voltage (usually more than 60 volts, commonly hundreds of volts to thousands of volts) and their interconnections. These components work together to achieve the storage, conversion and transmission of electrical energy, thereby driving the motor to operate the vehicle. In the power-on and power-off control of the battery-swap locomotive, analyzing the abnormal state of the high-voltage system plays a vital role. By real-time monitoring and analyzing the working state of the high-voltage system, faults can be predicted and diagnosed in advance, reducing the shutdown of the battery-swap locomotive due to faults. Accurately judging the abnormality of the high-voltage system can help implement preventive maintenance and extend the service life of the battery-swap locomotive and high-voltage system components.
[0079] According to the abnormal evaluation values of the upper and lower power control environment and the abnormal evaluation values of the high-voltage system status, the battery abnormal interference index of the battery swapping locomotive is obtained through comprehensive analysis.
[0080] In a specific embodiment, the battery abnormal interference degree influencing factor corresponding to the set upper and lower power control environment abnormal evaluation value and the high-voltage system state abnormal evaluation value is obtained from the battery swap locomotive database, and the battery abnormal interference degree index of the battery swap locomotive is obtained by comprehensive analysis. The specific numerical expression is:
[0081]
[0082] In the formula, represents the battery abnormal interference index of electric locomotive, e represents the natural constant, Indicates the abnormal evaluation value of the power-on and power-off control environment. Indicates the abnormal evaluation value of the high-voltage system status. Indicates the battery abnormal interference degree impact factor corresponding to the set power-on and power-off control environment abnormal evaluation value. Indicates the battery abnormal interference degree impact factor corresponding to the set high-voltage system state abnormal evaluation value.
[0083] It should be understood that in this embodiment, the value range of the battery abnormal interference degree influence factor corresponding to the upper and lower power control environment abnormal evaluation values and the high-voltage system state abnormal evaluation values is between 0 and 1. A mapping set of the upper and lower power control environment abnormal evaluation values and the high-voltage system state abnormal evaluation values and the corresponding battery abnormal interference degree influence factors can be established through the battery abnormal interference degree historical data, and the battery abnormal interference degree influence factors corresponding to the upper and lower power control environment abnormal evaluation values and the high-voltage system state abnormal evaluation values obtained through data processing can be obtained through the mapping set.
[0084] The battery abnormality interference index of the battery swapping locomotive is used to quantify the degree of interference of the power-on and power-off control environment data and the high-voltage system status data on the battery cluster abnormality assessment. Figure 7 As shown, in this embodiment, =0.5, = 0.5, when =0.042, the functional relationship between the abnormal evaluation value of the power-on and power-off control environment and the abnormal interference index of the battery is shown in curve a; when =0.284, the functional relationship between the abnormal evaluation value of the power-on and power-off control environment and the abnormal interference index of the battery is shown in curve a; when =0.404, the functional relationship between the upper and lower power control environment abnormality assessment value and the battery abnormality interference index is shown in curve a. The battery abnormality interference index of the electric swapping locomotive is jointly determined by the upper and lower power control environment abnormality assessment value and the high-voltage system state abnormality assessment value. The larger the upper and lower power control environment abnormality assessment value and the high-voltage system state abnormality assessment value, the larger the corresponding battery abnormality interference index of the electric swapping locomotive, indicating that the upper and lower power control environment data and the high-voltage system state data have a greater degree of interference with the battery cluster abnormality assessment.
[0085] The formula in this embodiment uses the Sigmoid function expression, which can map the input value to an output value between 0 and 1, can help smooth data fluctuations, and is conducive to mutual comparison between different types of data.
[0086] It should be understood that in this embodiment, a comprehensive analysis of the up and down power control environment and the high-voltage system status is performed. A reasonable up and down power control environment can ensure that the high-voltage system operates under safe conditions, reduce the occurrence of faults and abnormalities, help reduce the interference of the high-voltage system on the battery, and improve the performance and safety of the battery. By optimizing the up and down power control environment and the high-voltage system status, the coordinated optimization of the two can be achieved. For example, by adjusting the charging and discharging strategy, optimizing the thermal management system and other measures, the battery's charging and discharging performance and the operating status of the high-voltage system can be improved at the same time, thereby reducing the degree of interference to the battery.
[0087] Specifically, the battery cluster abnormality level assessment threshold is obtained by processing, and the specific process is: comparing the battery abnormality interference index of the battery swapping locomotive with the battery cluster abnormality level assessment threshold compensation parameters corresponding to each battery abnormality interference index interval stored in the battery swapping locomotive database, to obtain the battery cluster abnormality level assessment threshold compensation parameters of the battery swapping locomotive.
[0088] It should be understood that the battery cluster abnormality assessment threshold compensation parameter in this embodiment is used to correct the battery cluster abnormality assessment threshold to improve the accuracy of subsequent fault threshold comparisons. The set reference battery cluster abnormality assessment threshold is obtained from the battery swapping locomotive database, and the battery cluster abnormality assessment threshold compensation parameter of the battery swapping locomotive is summed with the reference battery cluster abnormality assessment threshold to obtain the battery cluster abnormality assessment threshold.
[0089] Specifically, a comprehensive analysis is performed to obtain an abnormality evaluation value of the battery cluster of the battery swapping locomotive. The specific analysis process is: the voltage of each battery cell in the battery cluster of the battery swapping locomotive is monitored, and a voltage variation curve of each battery cell over time is obtained after processing, which is marked as a voltage time series curve of each battery cell.
[0090] It should be understood that the process of connecting the voltage data points into a curve in this embodiment is a visualization processing of the voltage time series data analysis. Specifically, the voltage data is sorted in chronological order, and then adjacent data points are connected with line segments through graphics software or data analysis tools to form a curve graph of voltage changes over time. The curve graph uses time as the horizontal axis and voltage as the vertical axis, which can describe the fluctuation trend of the voltage of each battery cell in the time series.
[0091] The length of the voltage time series curve of each battery cell is obtained, and the voltage time series curves of each battery cell are overlapped and compared with each other, the overlap length between the voltage time series curves of each battery cell is extracted, and the overlap length matrix D of the voltage change curve over time is constructed. The mathematical expression of the matrix D is:
[0092]
[0093] In the formula, represents the overlap length between the rth battery cell voltage time series curve and the tth battery cell voltage time series curve, r represents the row number in the matrix, t represents the column number in the matrix, r=1,2,3,...,s, t=1,2,3,...,s, s represents the total number of battery cells.
[0094] The temperature of each battery unit is collected and comprehensively analyzed to obtain the abnormality evaluation value of the battery cluster of the electric locomotive.
[0095] It should be understood that the overlap between the battery cell voltage time series curves in this embodiment is disordered, so the matrix D is an unordered matrix. , and when r=t, the curve overlap length is equal to the length of the curve itself. To avoid repeated calculations, the upper triangular elements of matrix D that do not contain diagonal elements can be extracted to participate in subsequent calculations.
[0096] In a specific embodiment, the battery cluster abnormality evaluation influencing factors corresponding to the set voltage and temperature are obtained from the electric locomotive database, and the battery cluster abnormality evaluation value of the electric locomotive is obtained through comprehensive analysis. The specific numerical expression is:
[0097]
[0098] In the formula, , is the average value of the upper triangular elements of matrix D, represents the length of the p-th battery cell voltage time series curve, represents the overlap length between the voltage time series curve of the rth battery cell and the voltage time series curve of the r+kth battery cell, p represents the number of each battery cell, p=1,2,3,...,s, s represents the total number of battery cells, r+k represents the column number of the upper triangular element of the matrix D, where k=1,2,3,...,sr, Indicates the abnormality evaluation value of the battery cluster of the electric locomotive, It is a quantitative indicator of the dispersion of battery cell temperature and is used to quantitatively evaluate the temperature deviation of each battery cell in the battery cluster of an electric locomotive.
[0099]
[0100] represents the temperature of the pth battery cell, Indicates the impact factor of battery cluster abnormality assessment corresponding to the set voltage, Indicates the impact factor of battery cluster abnormality evaluation corresponding to the set temperature.
[0101] It should be understood that in this embodiment, the value range of the battery cluster abnormality assessment influence factor corresponding to the voltage and temperature is between 0 and 1, and a mapping set of the voltage and temperature and the corresponding battery cluster abnormality assessment influence factor can be constructed through the battery cluster historical data. According to the collected voltage and temperature of the battery cell, the battery cluster abnormality assessment influence factor corresponding to the voltage and temperature is obtained through the mapping set.
[0102] It should be understood that in this embodiment, the value range of the battery cluster abnormality assessment influence factor corresponding to the voltage and temperature is between 0 and 1, and a mapping set of the voltage and temperature and the corresponding battery cluster abnormality assessment influence factor can be constructed through the battery cluster historical data. According to the collected voltage and temperature of the battery cell, the battery cluster abnormality assessment influence factor corresponding to the voltage and temperature is obtained through the mapping set.
[0103] It should be understood that the abnormality evaluation value of the battery cluster of the electric swapping locomotive in this embodiment is used to quantitatively evaluate the abnormality of the battery cluster of the electric swapping locomotive. By analyzing the voltage time series curve and temperature of each battery cell in the battery cluster, the voltage balance state and temperature balance state of the battery cluster of the electric swapping locomotive are evaluated. By monitoring the voltage balance, the overcharge or undercharge problem of a single battery cell can be discovered and solved in time, which helps to avoid the gradual increase in the capacity difference between the battery cells and reduce the overall decay rate of the battery pack, thereby extending the battery life. Unbalanced voltage may cause some battery cells to overheat, increasing the risk of battery failure or even thermal runaway. By monitoring the temperature, overheating can be prevented, cooling measures can be taken in time, and safety accidents can be avoided. Balanced voltage and temperature states help the battery management system to estimate the battery state more accurately, thereby optimizing the charging and discharging strategy and improving energy utilization efficiency.
[0104] like Figure 2 As shown, the 9MWh battery system provided by the present invention is mainly composed of two sets of 4.5MWh container battery system units connected in parallel. A single set of 4.5MWh container system units is arranged in a 45-foot container. The container is carried on a battery-specific flatbed truck. The container and the flatbed truck are connected by corner fittings. Wiring sockets are designed on the left and right end faces of the container. The two sets of container systems can be electrically connected through the inter-box connecting harness to form a complete 9MWh battery system. During the use of the system, the user can select any unconnected terminal of the container as the main output port of the 9MWh battery system according to actual needs, and electrically connect the 9MWh battery system to the locomotive through the connecting harness between the locomotive and the container.
[0105] The 9MWh battery system consists of two 4.5MWh container battery system units, which have the same internal and external dimensions, layout, and functions. When describing the internal layout of the unit, any one of the units will be used as the description object. The internal layout of a single 4.5MWh container battery system is as follows: Figure 3 As shown in the figure, it can be seen that its interior is mainly composed of 4 sets of battery cluster stacks, 4 DC / DC cabinets, 1 electrical cabinet and other units. The container is installed on a battery-specific flatbed truck, and the container and the flatbed truck are fixed by 14 standard corner pieces; the container battery system consists of 4 battery cluster stack systems, each battery cluster consists of 4 battery clusters, and each battery cluster consists of 8 battery packs (also known as battery cells). The core components of the container battery system are divided into battery clusters, electrical cabinets, DC / DC converters and other units.
[0106] like Figure 4As shown, there are 16 battery clusters in the container battery system, with 4 batteries forming a cluster stack, which are respectively connected to the electrical cabinet after passing through 1 DCDC. The electrical cabinet includes power distribution and confluence functions: the power distribution part includes BMS three-level master control, display screen, fire display control, switch, micro-breaker, liquid cooler power supply DCDC, disconnector, fuse, surge protection, cooling fan and other equipment; the confluence function is composed of disconnector and fuse, and the disconnector can be controlled by BMS three-level master control; the fire protection of the container battery system is distributed, with 1 independent fire protection unit per cluster, the PACK contains fire detectors, and fire suppression devices are set in the cluster. Every 8 clusters are connected to the fire display control on the electrical cabinet; the container is equipped with 8 liquid cooling units, each liquid cooler corresponds to 2 battery clusters, which are controlled by the BMS secondary master control; the units of the container battery system are connected by high-voltage cables.
[0107] The battery cluster stack is mainly composed of 4 battery clusters and 1 auxiliary electrical rack. A single battery cluster is designed with 8 sets of battery boxes, which are connected in series. The middle auxiliary electrical rack is designed with 6 layers, of which the top 2 layers are used to arrange the thermal management unit, and the bottom 4 layers are used to arrange the high-voltage box and the fire host. The pipelines and wiring harness units in the entire cluster are arranged as follows: Figure 5 As shown, it can be seen from the figure that two battery cluster units share one thermal management unit, the water pipes of the battery boxes on the same layer are in series, and the water pipes between layers are in parallel; the high-voltage box and the fire host have a one-to-one correspondence with the battery cluster units, and the battery boxes in each battery cluster are connected in series and then output through the corresponding high-voltage box, and the fire host is connected to the battery box nozzles in each battery cluster through the fire pipeline.
[0108] Furthermore, the thermal management system in the battery cluster is composed of a thermal management unit, a liquid cooling pipeline, an expansion kettle and other units, such as Figure 6 As shown, it is mainly used to adjust the temperature of the internal units of the battery box. It contains cooling and heating units. These functional units can be controlled by the thermal management control unit, and then the external liquid cooling pipeline is used for diversion and heat exchange, so that the entire battery cluster is in a heating or cooling state, thereby achieving the temperature control effect of the battery cells in the battery pack.
[0109] In the embodiment of the present invention, the three-level master control is a battery management system level control module (also called the three-level module of BMS), which can analyze and process the real-time battery data collected by the second-level BCMU module and the first-level BMU module, monitor the real-time status of the battery system, and execute control, optimization and protection strategies according to the established plan. The module can also support data interaction with the locomotive-side PLC, ground charging system, system thermal management unit, fire protection unit and other systems. In addition, in order to facilitate users to understand the battery information in real time, a display screen is configured on the door of the battery distribution cabinet. The display screen communicates with the three-level master control in real time, and users can check the battery system status through the data on the display screen.
[0110] The 9MWh battery system placed in the container provided by the present invention is not easy to transport due to its large size. The present invention also provides an energy storage system that is easy to hoist. Figure 8 and Fig. 9 As shown, it includes: a container 211 and a lifting and matching mechanism 219. The container 211 has a cavity, in which a battery pack, a high-voltage box, a DC-DC converter and a junction box are arranged. The battery pack is electrically connected to the high-voltage box, the high-voltage box is electrically connected to the DC-DC converter, and the junction box is electrically connected to the DC-DC converter. The lifting and matching mechanism 219 includes a fixed part 2191 and a movable part 2192. The fixed part 2191 is fixedly arranged on the container 211, and the movable part 2192 can be movably connected to the fixed part 2191. The lifting and matching mechanism 219 has a storage state and a use state. In the use state, the movable part 2192 extends out of the fixed part 2191, and the movable part 2192 is used to connect the lifting equipment. In the storage state, the movable part 2192 retracts into the fixed part 2191 to avoid interference between the movable part 2192 and the external structure.
[0111] The energy storage system convenient for lifting of the present invention is provided with a lifting matching mechanism 219, which can be connected and matched with the lifting equipment, facilitating the overall disassembly and assembly of the container 211 and improving the assembly efficiency. The lifting equipment can have a collar, which is sleeved on the extended movable part 2192.
[0112] In some possible implementations, the container 211 includes a top frame and a bottom frame 2111 , a cavity is formed between the top frame and the bottom frame 2111 , and the fixing portion 2191 of the lifting and fitting mechanism 219 is disposed on the bottom frame 2111 .
[0113] The hoisting cooperation mechanism 219 is arranged on the bottom frame 2111, and the hoisting equipment is directly connected to the hoisting cooperation mechanism 219 on the bottom frame 2111, which improves the stability and safety of the hoisting operation.
[0114] In some possible implementation schemes, the movable direction of the movable portion 2192 is parallel to the width direction of the bottom frame 2111. In the use state, the movable portion 2192 extends out of the bottom frame 2111 along the width direction of the bottom frame 2111. In the storage state, the movable portion 2192 retracts to one side of the bottom frame 2111. The movable portion 2192 extends along the width direction of the bottom frame 2111, which can be conveniently connected to the corresponding structure on the lifting equipment. A plurality of lifting matching mechanisms 219 can be provided on the bottom frame 2111, and each lifting matching mechanism 219 is respectively provided on both sides of the bottom frame 2111 along the width direction, and each lifting matching mechanism 219 on the same side of the bottom frame 2111 is sequentially provided along the length direction of the bottom frame 2111. By setting up a plurality of lifting cooperation mechanisms 219, the connection parts between the bottom frame 2111 and the lifting equipment can be increased, thereby improving the stability of the connection structure between the lifting equipment and the bottom frame 2111. The setting of a plurality of lifting cooperation mechanisms 219 is beneficial to uniform force on the container 211, and the posture of the container 211 remains stable and is not easy to tilt.
[0115] In some possible embodiments, the bottom frame 2111 includes a plurality of structural beams 21111, each structural beam 21111 is sequentially arranged along the length direction of the bottom frame 2111, each structural beam 21111 extends along the width direction of the frame, and the fixing portion 2191 is located between each structural beam 21111 and fixedly connected to the structural beam 21111.
[0116] Each hoisting and matching mechanism 219 is respectively arranged in the space formed between two adjacent structural beams 21111, and does not occupy additional space of the bottom frame 2111. The embodiment of the present invention makes full use of the bottom frame 2111, and the assembly structure of the hoisting and matching mechanism 219 is adaptively designed according to the structural characteristics of the bottom frame 2111. The structural beam 21111 has high structural strength, and the fixing portion 2191 is directly connected to the structural beam 21111, so the structural strength is high, and the hoisting and matching mechanism 219 has a long service life.
[0117] In some possible implementations, the bottom frame 2111 includes a plurality of connectors 21112, the connectors 21112 are located between two adjacent structural beams 21111, and the connectors 21112 are respectively welded to the two structural beams 21111 and the fixing portion 2191 located between the two structural beams 21111. The connectors 21112 may be metal structures, such as metal plates or metal blocks, and the connectors 21112 are respectively welded to the structural beams 21111 on both sides and the fixing portion 2191 in the middle, connecting the three into an integrated structure.
[0118] When the fixing portion 2191 is cylindrical, the connecting piece 21112 may be provided with a circular avoidance hole, the avoidance hole may be sleeved on the fixing portion 2191 , and the inner end surface of the avoidance hole may be fitted and welded to the surface of the fixing portion 2191 .
[0119] In some possible implementations, the bottom frame 2111 may include two side main beams 21113, the two side main beams 21113 are arranged at intervals, each structural beam 21111 is located between the two side main beams 21113, and the two ends of the structural beam 21111 are respectively connected to the two side main beams 21113, the side main beams 21113 have a through hole extending along the width direction of the bottom frame 2111, and the fixing portion 2191 is penetrated through the through hole. The fixing portion 2191 can be a cylindrical body, and the fixing portion 2191 has a slide groove, which extends in a direction perpendicular to the side main beams 21113, and the slide groove defines the movable direction of the movable portion 2192.
[0120] In some possible implementations, the fixed portion 2191 has a through slide groove, the movable portion 2192 is arranged through the slide groove, and flange portions 21921 are respectively arranged at both ends of the movable portion 2192, and the outer diameter of the flange portion 21921 is larger than the inner diameter of the slide groove. The flange portions 21921 are arranged at both ends of the movable portion 2192, thereby limiting the sliding range of the movable portion 2192 and preventing the movable portion 2192 from sliding off the fixed portion 2191 as a whole.
[0121] In some possible implementations, the movable portion 2192 is provided with a connection hole on the flange portion 21921 located outside the bottom frame 2111, and one end of the stopper can pass through the connection hole to be connected to the fixed portion 2191 or the bottom frame 2111 of the container 211, and the other end is limited to the flange portion 21921. The stopper may include a cap body and a screw rod, the screw rod passes through the connection hole and is threadedly connected to a thread groove provided on the fixed portion 2191 or the container 211, and the cap body is limited to the flange portion 21921, thereby fixing the position of the movable portion 2192 to prevent the movable portion 2192 from accidentally sliding out and colliding with the external structure.
[0122] In summary, the refined management method and system of a single-cluster battery provided by the present invention collects and monitors the power supply data of each battery cell in the currently powered battery cluster in real time, and predicts whether each battery cell can supply power normally in the next power supply time period; if it is predicted that any one or more battery cells cannot supply power normally in the next power supply time period, the battery cells that cannot supply power normally are shielded before the next power supply time period, and the output power of the battery cells that can supply power normally in the next power supply time period is adjusted to achieve balanced output of the battery cluster, thereby effectively ensuring the stability of the operating output of the battery cluster, while maintaining the balanced output of the battery cluster to prevent over-discharge of the battery cluster. This method effectively ensures the rational management planning of the output power of each single battery cell in the battery cluster, and timely shields the battery cells that cannot supply power normally, thereby meeting the high-efficiency and stable operation requirements of the battery cluster.
[0123] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the present invention is not limited thereby. Any modification, equivalent substitution and improvement made by those skilled in the art without departing from the scope and essence of the present invention shall be within the scope of the present invention.
Claims
1. A refined management method for a single cluster battery, It is characterized in that include: Real-time collection and monitoring of the cell power supply data of each cell in the battery cluster currently supplying power, the cell power supply data including at least multiple power supply time periods and the voltage, current, SOC, output power and temperature corresponding to each power supply time period; Using the battery power supply data of each battery cell in the battery cluster, predicting whether each battery cell can supply power normally in the next power supply time period; If it is predicted that any one or more battery cells cannot supply power normally in the next power supply time period, the battery cells that cannot supply power normally are shielded before the next power supply time period, and the output power of the battery cells that can supply power normally in the next power supply time period is adjusted to achieve balanced output of the battery cluster; During the period of achieving balanced output of the entire battery cluster, the power-on and power-off control environment data and the high-voltage system status data are obtained through the sensor network, and the battery abnormal interference index of the power-swap locomotive is obtained by comprehensive analysis. According to the battery abnormal interference index of the power-swap locomotive, the battery cluster abnormality assessment threshold is processed; the abnormal status data of each battery unit of the power-swap locomotive is monitored, and the battery cluster abnormality assessment value of the power-swap locomotive is obtained by comprehensive analysis; the battery cluster abnormality assessment value of the power-swap locomotive is compared with the battery cluster abnormality assessment threshold. If the battery cluster abnormality assessment value of the power-swap locomotive is greater than the battery cluster abnormality assessment threshold, the power-off control of the power-swap locomotive is performed.
2. The method according to claim 1, It is characterized in that Also includes: Obtain historical battery power supply data and corresponding health status of multiple battery cells at different output powers; A predicted cell health model is established, and the predicted cell health model is trained using the historical cell power supply data to obtain a trained predicted cell health model.
3. The method according to claim 2, It is characterized in that Using the cell power supply data of each cell in the battery cluster, predicting whether each cell can supply power normally in the next power supply time period includes: If the power supply data of any battery cell in the battery cluster corresponding to the power supply data of the battery cell during the current power supply time period jumps, it is predicted that the battery cell cannot supply power normally in the next power supply time period; If the cell power supply data corresponding to the cell power supply data of any cell in the battery cluster during the current power supply time period does not change, the trained predicted cell health model is further used to predict whether the cell can supply power normally in the next power supply time period.
4. The method according to claim 3, It is characterized in that Predicting whether the battery cell can supply power normally in the next power supply time period by using the trained predicted battery cell health model includes: The health of each battery cell in the battery cluster is obtained by inputting the battery cell power supply data of each battery cell in the battery cluster into the trained predicted battery cell health model; If the health of any battery cell in the next power supply time period is not lower than the health threshold, it is predicted that the battery cell can supply power normally in the next power supply time period; If the health of any battery cell in the next power supply time period is lower than the health threshold, it is predicted that the battery cell cannot supply power normally in the next power supply time period.
5. The method according to claim 1, It is characterized in that Also includes: Collect and monitor the cell charging data of each cell in the battery cluster in real time, where the cell charging data includes at least multiple charging time points and the voltage, current, SOC, output power and temperature corresponding to each charging time point; Using the battery cell charging data of each battery cell in the battery cluster, determining whether each battery cell can supply power normally; If it is determined that any cell in the battery cluster cannot supply power normally, the power supply of the cell is shielded before the battery cluster supplies power, and the output power of other cells is adjusted to achieve balanced output of the battery cluster.
6. The method according to claim 5, It is characterized in that Using the battery cell charging data of each battery cell in the battery cluster to determine whether each battery cell can supply power normally includes: If the charging data of any cell in the battery cluster changes, it is determined that the cell cannot supply power normally, and the fault type is determined according to the charging data of the cell that changes, and a corresponding fault alarm is issued based on the fault type.
7. The method according to claim 1, It is characterized in that Adjusting the output power of the battery cell that can normally supply power in the next power supply time period includes: According to the total output power of the battery cluster and the number of cells that can normally supply power in the next power supply time period, the second output power of each cell that can normally supply power is calculated, and the second output power is used as the output power of each cell that can normally supply power in the next power supply time period.
8. The method according to claim 7, It is characterized in that The second output powers of each battery cell that can supply power normally are equal or unequal, and the difference between the second output power values is not greater than a preset difference threshold.
9. A refined management system for single-cluster batteries, It is characterized in that include: A monitoring module is used to collect and monitor the power supply data of each battery cell in the battery cluster currently supplying power in real time, where the power supply data of the battery cell includes at least multiple power supply time periods and the voltage, current, SOC, output power and temperature corresponding to each power supply time period; A prediction module, used to use the cell power supply data of each cell in the battery cluster to predict whether each cell can supply power normally in the next power supply time period; A balancing management module, for shielding the cells that cannot supply power normally before the next power supply period if it is predicted that any one or more cells cannot supply power normally in the next power supply period, and adjusting the output power of the cells that can supply power normally in the next power supply period, so as to achieve balanced output of the battery cluster; Among them, the balancing management module is also used to obtain the power-on and power-off control environment data and the high-voltage system status data through the sensor network during the period of realizing the balanced output of the entire battery cluster, comprehensively analyze and obtain the battery abnormal interference index of the power-swap locomotive, and according to the battery abnormal interference index of the power-swap locomotive, process and obtain the battery cluster abnormality assessment threshold; monitor the abnormal status data of each battery unit of the power-swap locomotive, and comprehensively analyze and obtain the battery cluster abnormality assessment value of the power-swap locomotive; compare the battery cluster abnormality assessment value of the power-swap locomotive with the battery cluster abnormality assessment threshold; if the battery cluster abnormality assessment value of the power-swap locomotive is greater than the battery cluster abnormality assessment threshold, the power-off control of the power-swap locomotive is performed.
10. The system according to claim 9, It is characterized in that The prediction module is also used to obtain historical battery cell power supply data of multiple battery cells at different output powers and their corresponding health levels; establish a predicted battery cell health model, and use the historical battery cell power supply data to train the predicted battery cell health model to obtain a trained predicted battery cell health model.
