A method and system for monitoring the state of an energy storage battery

Abstract

The application discloses a state monitoring method and system of an energy storage battery, and the method comprises the following steps: acquiring a plurality of operation parameters of an energy storage battery to be monitored in real time; determining actual parameter correlation, actual parameter deviation rate, standard parameter correlation and standard parameter deviation rate of the energy storage battery to be monitored according to the plurality of operation parameters, time stamps of the operation parameters and configuration parameters of the energy storage battery to be monitored; constructing an actual feature vector and a standard feature vector of the energy storage battery to be monitored, and calculating the similarity between the actual feature vector and the standard feature vector; predicting a plurality of fault elements in the actual feature vector based on actual vector element values in the actual feature vector and standard vector element values in the standard feature vector, and determining a fault type to obtain a state monitoring result of the energy storage battery to be monitored, so that the comprehensiveness of the state monitoring of the energy storage battery and the accuracy of the monitoring result can be improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of energy storage batteries, and particularly relates to a state monitoring method and system for an energy storage battery. BACKGROUND

[0002] With the rapid development of smart grids, energy storage batteries have been widely applied as core equipment for power storage and dispatch. The operation state of an energy storage battery is directly related to the safety, stability and economy of a system. Precise and real-time state monitoring of an energy storage battery by measuring electrical variables of the energy storage battery, and timely identification of safety hazards and fault types of the energy storage battery, have become key requirements in the field of energy storage batteries.

[0003] The existing state monitoring method for an energy storage battery mainly measures single electrical variable parameters such as voltage, current and internal resistance during the charging and discharging process of the energy storage battery, compares the measurement results of the electrical variable parameters with preset electrical variable parameter thresholds, and determines whether the battery is in a safe operation state. However, the existing technology relies on comparison of single electrical variable parameters, and can only alarm when a fault has occurred, which has the problems of incomplete state monitoring of the energy storage battery and inaccurate monitoring results. SUMMARY

[0004] The purpose of the embodiments of the present application is to provide a state monitoring method and system for an energy storage battery, which solves the problems of incomplete state monitoring of the energy storage battery and inaccurate monitoring results in the prior art. The actual feature vector and the standard feature vector of the energy storage battery to be monitored are constructed by determining the parameter correlation and the parameter deviation rate of the energy storage battery to be monitored. In the case that the similarity of the feature vectors is less than a preset battery state safety similarity threshold, the fault type of the battery is determined based on the actual vector element value and the standard vector element value, and the state monitoring result of the energy storage battery to be monitored is obtained. The purpose of state monitoring and fault screening of the monitored energy storage battery based on multi-dimensional electrical variable parameters is achieved, and the comprehensiveness of state monitoring of the energy storage battery and the accuracy of the monitoring results are improved.

[0005] In a first aspect, the embodiments of the present application provide a state monitoring method for an energy storage battery, which comprises:

[0006] real-time acquisition of a plurality of operating parameters of an energy storage battery to be monitored, determination of actual parameter correlation, actual parameter deviation rate, standard parameter correlation and standard parameter deviation rate of the energy storage battery to be monitored according to the plurality of operating parameters, time stamps of the operating parameters and configuration parameters of the energy storage battery to be monitored;

[0007] The actual feature vector of the to-be-monitored energy storage battery is constructed based on actual parameter correlation and actual parameter deviation rate, and the standard feature vector of the to-be-monitored energy storage battery is constructed based on standard parameter correlation and standard parameter deviation rate, and the similarity between the actual feature vector and the standard feature vector is calculated;

[0008] In a case where the similarity is less than a preset battery state safety similarity threshold, a plurality of fault elements in the actual feature vector are predicted based on actual vector element values in the actual feature vector and standard vector element values in the standard feature vector, and a fault type corresponding to the plurality of fault elements is determined, to obtain a state monitoring result of the to-be-monitored energy storage battery.

[0009] Further, the operating parameters include basic operating parameters, cumulative charging times and cumulative discharging time lengths;

[0010] The standard parameter correlation and the standard parameter deviation rate of the to-be-monitored energy storage battery are determined according to the plurality of operating parameters, the time stamps of the operating parameters and the configuration parameters of the to-be-monitored energy storage battery, including:

[0011] The plurality of operating parameters are grouped according to the time stamps of the operating parameters to obtain a current stage operating parameter group and a historical stage operating parameter group;

[0012] The historical parameter correlation of the to-be-monitored energy storage battery is determined according to a plurality of historical basic operating parameters in the historical stage operating parameter group, and the historical parameter deviation rate of the to-be-monitored energy storage battery is determined according to the plurality of historical basic operating parameters and the configuration parameters of the to-be-monitored energy storage battery;

[0013] The standard parameter correlation and the standard parameter deviation rate of the to-be-monitored energy storage battery are obtained by aging correction of the historical parameter correlation and the historical parameter deviation rate based on the cumulative charging times and the cumulative discharging time lengths.

[0014] Further, the historical basic operating parameters include historical current values, historical voltage values and historical temperature values, the configuration parameters include resistance values, battery heat capacities and open-circuit voltage values of the to-be-monitored energy storage battery, the historical parameter correlation includes historical current-voltage correlation and historical temperature-power correlation, and the historical parameter deviation rate includes historical temperature growth deviation rate and historical voltage deviation rate;

[0015] The historical parameter correlation of the to-be-monitored energy storage battery is determined according to a plurality of historical basic operating parameters in the historical stage operating parameter group, and the historical parameter deviation rate of the to-be-monitored energy storage battery is determined according to the plurality of historical basic operating parameters and the configuration parameters of the to-be-monitored energy storage battery;

[0016] determine a historical current-voltage correlation degree of the to-be-monitored energy storage battery according to the plurality of historical current values and the plurality of historical voltage values, and determine a historical temperature-power correlation degree of the to-be-monitored energy storage battery according to the plurality of historical current values, the plurality of historical voltage values and the plurality of historical temperature values;

[0017] determine a historical temperature growth deviation rate of the to-be-monitored energy storage battery according to the plurality of historical temperature values, the resistance value, the plurality of historical current values and the battery heat capacity, and determine a historical voltage deviation rate of the to-be-monitored energy storage battery according to the open-circuit voltage value, the resistance value, the plurality of historical current values and the plurality of historical voltage values.

[0018] Further, the determination of the historical temperature growth deviation rate of the to-be-monitored energy storage battery according to the plurality of historical temperature values, the resistance value, the plurality of historical current values and the battery heat capacity comprises:

[0019] determine a historical end-point temperature value, a historical current average value and a historical current statistical duration corresponding to the historical stage operation parameter group according to the plurality of historical temperature values and time stamps respectively corresponding to the historical temperature values;

[0020] determine a historical actual temperature growth value of the to-be-monitored energy storage battery according to the historical end-point temperature value, and determine a historical theoretical temperature growth value of the to-be-monitored energy storage battery according to the historical end-point temperature value, the historical current average value, the historical current statistical duration, the resistance value and the battery heat capacity;

[0021] determine a historical temperature growth deviation rate of the to-be-monitored energy storage battery according to the historical actual temperature growth value and the historical theoretical temperature growth value.

[0022] Further, the aging correction of the historical parameter correlation degree and the historical parameter deviation rate based on the cumulative charging times and the cumulative discharging duration respectively comprises:

[0023] determine an aging coefficient of the to-be-monitored energy storage battery based on the cumulative charging times and the cumulative discharging duration, and determine a first aging correction coefficient sign corresponding to the historical parameter correlation degree and a second aging correction coefficient sign corresponding to the historical parameter deviation rate;

[0024] perform first aging correction on the historical parameter correlation degree according to the aging coefficient and the first aging correction coefficient sign, and perform second aging correction on the historical parameter deviation rate according to the aging coefficient and the second aging correction coefficient sign.

[0025] Further, the prediction of the plurality of fault elements in the actual feature vector based on the actual vector element values in the actual feature vector and the standard vector element values in the standard feature vector comprises:

[0026] calculate a deviation degree of each actual vector element value in the actual feature vector from a corresponding standard vector element value in the standard feature vector;

[0027] determine a floating scale corresponding to each standard vector element value in the standard feature vector, and sort the plurality of actual vector elements in the actual feature vector according to the fault degree in the size relationship of the deviation degrees in a case where each deviation degree is less than the corresponding floating scale;

[0028] determine a plurality of fault element prediction results in the actual feature vector based on the preset fault element quantity and the fault degree sorting result.

[0029] Further, determine the fault type corresponding to the plurality of fault elements, comprising:

[0030] randomly combine the plurality of fault elements, and match the random combination result with a preset fault type mapping library, and determine the fault type corresponding to the fault element screening result according to the matching result.

[0031] In a second aspect, an embodiment of the present application provides a state monitoring system of an energy storage battery, the system comprising:

[0032] a parameter deviation rate determination module, configured to acquire a plurality of operating parameters of a to-be-monitored energy storage battery in real time, and determine an actual parameter correlation degree, an actual parameter deviation rate, a standard parameter correlation degree and a standard parameter deviation rate of the to-be-monitored energy storage battery according to the plurality of operating parameters, time stamps of the operating parameters and configuration parameters of the to-be-monitored energy storage battery;

[0033] a vector similarity calculation module, configured to construct an actual feature vector of the to-be-monitored energy storage battery based on the actual parameter correlation degree and the actual parameter deviation rate, and construct a standard feature vector of the to-be-monitored energy storage battery based on the standard parameter correlation degree and the standard parameter deviation rate, and calculate a similarity between the actual feature vector and the standard feature vector;

[0034] a state monitoring module, configured to predict a plurality of fault elements in the actual feature vector based on actual vector element values in the actual feature vector and standard vector element values in the standard feature vector in a case where the similarity is less than a preset battery state safety similarity threshold, and determine a fault type corresponding to the plurality of fault elements, to obtain a state monitoring result of the to-be-monitored energy storage battery.

[0035] In a third aspect, an embodiment of the present application provides an electronic device, which comprises a processor, a memory, and a program or instruction stored on the memory and executable on the processor, and the program or instruction is executed by the processor to implement the steps of the method of the first aspect.

[0036] In a fourth aspect, an embodiment of the present application provides a readable storage medium, which stores a program or instruction, and the program or instruction is executed by a processor to implement the steps of the method of the first aspect.

[0037] Fifthly, embodiments of this application also provide a computer program product comprising a computer program stored in a computer-readable storage medium, wherein at least one processor of the device reads from the computer-readable storage medium and executes the computer program, causing the device to perform the method described in the first aspect.

[0038] In this embodiment, multiple operating parameters of the energy storage battery to be monitored are acquired in real time. Based on the multiple operating parameters, the timestamps of each operating parameter, and the configuration parameters of the energy storage battery to be monitored, the actual parameter correlation, actual parameter deviation rate, standard parameter correlation, and standard parameter deviation rate of the energy storage battery to be monitored are determined. Based on the actual parameter correlation and actual parameter deviation rate, an actual feature vector of the energy storage battery to be monitored is constructed, and based on the standard parameter correlation and standard parameter deviation rate, a standard feature vector of the energy storage battery to be monitored is constructed, and the similarity between the actual feature vector and the standard feature vector is calculated. If the similarity is less than a preset battery state safety similarity threshold, multiple fault elements in the actual feature vector are predicted based on the actual vector element values ​​in the actual feature vector and the standard vector element values ​​in the standard feature vector, and the fault types corresponding to the multiple fault elements are determined, thus obtaining the state monitoring results of the energy storage battery to be monitored. The aforementioned energy storage battery state monitoring method solves the problems of incomplete and inaccurate state monitoring results in existing technologies. By determining the parameter correlation and parameter deviation rate of the energy storage battery to be monitored, the actual feature vector and standard feature vector of the energy storage battery to be monitored are constructed respectively. When the similarity of the feature vectors is less than the preset battery state safety similarity threshold, the fault type of the battery is determined based on the actual vector element values ​​and the standard vector element values, thus obtaining the state monitoring results of the energy storage battery to be monitored. This method can achieve the purpose of state monitoring and fault screening of the monitored energy storage battery based on multi-dimensional electrical variable parameters, improving the comprehensiveness of energy storage battery state monitoring and the accuracy of monitoring results. Attached Figure Description

[0039] Figure 1 This is a flowchart of a state monitoring method for an energy storage battery provided in an embodiment of this application;

[0040] Figure 2 This is a flowchart of determining the deviation rate of standard parameters provided in the embodiments of this application;

[0041] Figure 3 This is a graph showing the relationship between current and voltage as a function of the aging coefficient, provided in an embodiment of this application.

[0042] Figure 4 This is a flowchart for determining the historical parameter deviation rate provided in an embodiment of this application;

[0043] Figure 5This is a structural block diagram of a state monitoring system for an energy storage battery provided in an embodiment of this application;

[0044] Figure 6 This is a structural block diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this application clearer, specific embodiments of this application are described in detail below with reference to the accompanying drawings. It is understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. Furthermore, it should be noted that, for ease of description, only the parts relevant to this application are shown in the drawings, not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0046] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0047] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0048] Firstly, this solution can be used for monitoring the state of energy storage batteries, particularly for accurately and in real-time monitoring based on the battery's electrical variables, enabling timely identification of safety hazards and fault types. By determining the parameter correlation and parameter deviation rate of the battery to be monitored, actual and standard feature vectors are constructed. When the similarity of the feature vectors is less than a preset battery state safety similarity threshold, the fault type of the battery is determined based on the actual and standard vector element values, yielding the state monitoring results. This achieves the goal of monitoring the state and screening faults of the monitored energy storage battery based on multi-dimensional electrical variable parameters, improving the comprehensiveness and accuracy of the monitoring results. Based on the above application scenario, it is understood that the execution entity for each step in this solution can be a computer device. This computer device refers to any electronic device with data computing, processing, and storage capabilities, such as mobile phones, PCs (Personal Computers), tablets, and other terminal devices, or servers, etc. This application embodiment does not limit this.

[0049] The following description, in conjunction with the accompanying drawings, details a method and system for monitoring the state of an energy storage battery provided in this application, through specific embodiments and application scenarios.

[0050] Figure 1 This is a flowchart of a state monitoring method for an energy storage battery provided in an embodiment of this application. Figure 1 As shown, the specific steps include the following:

[0051] S101 acquires multiple operating parameters of the energy storage battery to be monitored in real time, and determines the actual parameter correlation, actual parameter deviation rate, standard parameter correlation, and standard parameter deviation rate of the energy storage battery to be monitored based on the multiple operating parameters, the timestamp of each operating parameter, and the configuration parameters of the energy storage battery to be monitored.

[0052] The operating parameters can be parameters describing the charge and discharge state of the monitored energy storage battery. Examples include current, voltage, and temperature values. The timestamps for each operating parameter can mark the time when that parameter was generated. Based on the timestamps, the operating parameters acquired in real-time from the initial stage of battery use to the current moment can be divided into operating parameters for the early stage of battery use and operating parameters for the later aging stage, or into historical stage operating parameters and current stage operating parameters, etc. The configuration parameters of the monitored energy storage battery can be parameters representing the battery's own hardware characteristics and rated operating parameters. Examples include resistance, open-circuit voltage, and short-circuit current values.

[0053] Actual parameter correlation can represent the degree of association between multiple actual operating parameters at the same moment or within the same time series. Examples include the correlation between voltage and current, and temperature and power. Under normal battery conditions, the correlation between operating parameters typically stabilizes within a certain range. Actual parameter correlation can be calculated using multiple actual operating parameters of the monitored energy storage battery at the current stage and the Pearson correlation coefficient formula. Actual parameter deviation rate can represent the degree to which the actual change of a single operating parameter deviates from its theoretical change under normal conditions. Actual parameter deviation rate can be expressed as the degree of deviation between the actual change of a single operating parameter and its theoretical change over a period of time. The theoretical change of a parameter can be calculated using other operating parameters affecting that parameter and the configuration parameters of the energy storage battery according to battery parameter calculation formulas. Standard parameter correlation can represent the theoretical correlation between multiple operating parameters at the same moment or within the same time series when the monitored energy storage battery is under normal conditions. Standard parameter correlation can be calculated using multiple historical operating parameters of the monitored energy storage battery from historical periods and the parameter correlation calculation formula. The standard parameter deviation rate can be the maximum allowable deviation rate threshold for a single parameter of the monitored energy storage battery. This refers to the upper limit of the acceptable deviation range of a parameter under normal conditions. The standard parameter deviation rate can be represented by the degree of deviation between the historical parameter change of a single operating parameter over a period of time and the theoretical parameter change of that parameter. By calculating the standard parameter deviation rate, the inherent error between the actual operating parameters and theoretical parameters of the monitored energy storage battery is quantified, thereby improving the accuracy of subsequent assessments of the actual parameter deviation rate at the current stage.

[0054] In one embodiment, multiple operating parameters can be divided into historical stage operating parameters and current stage operating parameters based on their timestamps. The correlation coefficient between each pair of parameters at the same timestamp in the current stage is calculated using the Pearson correlation coefficient to obtain the actual parameter correlation of the energy storage battery under monitoring. Other parameters associated with each operating parameter are determined based on the battery operation physics calculation formula. The theoretical parameter change for that operating parameter in the current stage is determined based on the configuration parameters and the associated other parameters. The actual parameter change for that operating parameter is calculated based on the initial and final parameter values ​​at the corresponding endpoint timestamp in the current stage. The actual parameter deviation rate of the energy storage battery under monitoring is determined based on the theoretical and actual parameter changes. To avoid inaccurate calculations of theoretical parameter changes due to increased internal resistance caused by battery aging, the resistance value of the energy storage battery under monitoring can be obtained in real time through the BMS battery management system. The average resistance value for the corresponding time period in the current stage is calculated. The theoretical parameter change for the current stage is calculated based on the average resistance value, the battery's fixed configuration parameters, and the real-time operating parameters. Similarly, the standard parameter correlation and standard parameter deviation rate of the energy storage battery under monitoring are determined based on the historical stage operating parameters. Since the battery under monitoring has a high level of safety during the initial use stage, the processing results of the historical operating parameters can be used as a reference standard for whether the battery under monitoring is currently in a safe state. In addition, the aging degree of the battery is low during the initial use stage, and the internal resistance hardly changes. At this time, the resistance value in the configuration parameters of the battery under monitoring can be directly used to calculate the changes in the relevant theoretical parameters during the historical stage.

[0055] S102, construct the actual feature vector of the energy storage battery to be monitored based on the correlation of actual parameters and the deviation rate of actual parameters, and construct the standard feature vector of the energy storage battery to be monitored based on the correlation of standard parameters and the deviation rate of standard parameters, and calculate the similarity between the actual feature vector and the standard feature vector.

[0056] The actual feature vector can be a vector describing the actual operating characteristics of the monitored energy storage battery at the current stage. The standard feature vector can be a vector describing the standard operating characteristics of the monitored energy storage battery when it is in a safe operating state at the current stage. The similarity between the actual feature vector and the standard feature vector can be due to data describing the safety level of the monitored energy storage battery.

[0057] In one embodiment, there are multiple parameter correlations and multiple parameter deviation rates. Multiple actual parameter correlations and multiple actual parameter deviation rates can be integrated to construct the actual feature vector of the energy storage battery to be monitored. Multiple standard parameter correlations and multiple standard parameter deviation rates can be integrated to construct the standard feature vector of the energy storage battery to be monitored. The similarity between the actual feature vector and the standard feature vector is calculated by using a cosine similarity algorithm.

[0058] S103, when the similarity is less than the preset battery state safety similarity threshold, predict multiple fault elements in the actual feature vector based on the actual vector element values ​​in the actual feature vector and the standard vector element values ​​in the standard feature vector, and determine the fault type corresponding to the multiple fault elements to obtain the state monitoring result of the energy storage battery to be monitored.

[0059] The preset battery state safety similarity threshold can be the minimum similarity pre-set when the battery is in a safe operating state. Fault elements can be actual vector elements whose values ​​are significantly greater than their corresponding standard vector elements in the standard feature vector. Fault types can describe specific abnormal states or fault modes that the monitored energy storage battery may exhibit during its current operating phase. The fault type is determined based on the element types corresponding to multiple fault elements. The state monitoring results of the monitored energy storage battery can describe whether the monitored energy storage battery is in a safety risk state and the types of faults causing the safety risk.

[0060] In one embodiment, when the similarity is less than a preset battery state safety similarity threshold, multiple fault elements in the actual feature vector are predicted based on the actual vector element values ​​in the actual feature vector and the standard vector element values ​​in the standard feature vector, and the fault type corresponding to the multiple fault elements is determined to obtain the state monitoring result of the energy storage battery to be monitored.

[0061] The similarity between the actual feature vector and the standard feature vector can be compared with a preset safety threshold. If the similarity is less than the preset safety threshold, the difference between corresponding element values ​​in the two sets of vectors is calculated and compared with the corresponding difference threshold to identify elements whose actual values ​​significantly deviate from the standard values, thus obtaining the fault element prediction result. The intersection of the fault types corresponding to multiple fault elements is used to determine the fault type associated with each fault element, and the state monitoring result of the energy storage battery to be monitored is then used to identify the fault type. One fault element can correspond to one or more fault types. For example, a temperature fault can correspond to a battery short circuit fault or an abnormal battery state of charge.

[0062] In one embodiment, predicting multiple fault elements in an actual feature vector based on actual vector element values ​​in an actual feature vector and standard vector element values ​​in a standard feature vector includes: calculating the deviation between each actual vector element value in the actual feature vector and the corresponding standard vector element value in the standard feature vector; determining the floating scale corresponding to each standard vector element value in the standard feature vector; and, if all deviations are less than the corresponding floating scale, ranking the multiple actual vector elements in the actual feature vector according to the magnitude of the deviations; and determining the prediction result of the multiple fault elements in the actual feature vector based on the preset number of fault elements and the ranking result of the fault degree.

[0063] The floating scale can be the maximum value that each standard vector element can float upwards or downwards from its current value when the monitored battery is in a safe operating state. The floating scale can be obtained by calculating the difference between the maximum or minimum value that each standard vector element can reach under safe operating conditions and the standard vector element value. The fault severity ranking can be a ranking that describes the severity of the fault. The preset number of fault elements can be a pre-set number of fault elements that must exist if the monitored energy storage battery has a safety risk.

[0064] In one embodiment, the difference between each actual vector element value in the actual feature vector and the corresponding standard vector element value in the standard feature vector can be calculated, and the ratio of the difference to the corresponding standard vector element value can be calculated to obtain the deviation of the vector element value. The floating scale corresponding to each standard vector element value in the standard feature vector can also be read. If the deviation of multiple element values ​​is greater than the corresponding floating scale, the actual feature vector element with a deviation greater than the corresponding floating scale can be directly regarded as a fault element. If all deviations are less than the corresponding floating scale, it indicates that a single actual feature vector element poses a risk of causing the monitored battery to malfunction, but the superposition of multiple actual feature vector elements causes a risk to the monitored battery's safe operation. That is, if the superposition of multiple actual feature vector elements results in a similarity less than a preset battery state safety similarity threshold, then to filter out fault elements, the multiple actual vector elements in the actual feature vector can be sorted by fault degree from largest to smallest according to the deviation degree, and the multiple actual vector elements with a preset number of fault elements from largest to smallest in the fault degree sorting result can be selected as the prediction result of multiple fault elements in the actual feature vector.

[0065] This scheme calculates the deviation between the actual vector element values ​​in the actual feature vector and the corresponding standard vector element values ​​in the standard feature vector. When each deviation is less than the corresponding floating scale, the prediction results of multiple fault elements in the actual feature vector are determined according to the magnitude of the deviation and the preset number of fault elements. This can achieve the purpose of predicting fault elements that have an indirect impact on the safe operation of the battery, and improve the comprehensiveness and accuracy of the prediction results of fault elements.

[0066] In one embodiment, determining the fault type corresponding to multiple fault elements includes: randomly combining the multiple fault elements, matching the random combination result with a preset fault type mapping library, and determining the fault type corresponding to the fault element filtering result based on the matching result.

[0067] The preset fault type mapping library can be a pre-set reference database that maps a single fault element or a combination of multiple fault elements to a fault type.

[0068] In one embodiment, multiple fault elements can be randomly combined, and the random combination result can be compared with the preset fault element combinations in the preset fault type mapping library. The fault type corresponding to the same fault element combination is taken as the fault type corresponding to the fault element filtering result.

[0069] This solution determines the fault type corresponding to the fault element screening results by randomly combining multiple fault elements and matching them with a preset fault type mapping library. This can improve the efficiency of fault type determination and is beneficial for real-time status monitoring of energy storage batteries.

[0070] The technical solution provided in this application acquires multiple operating parameters of the energy storage battery under monitoring in real time. Based on the multiple operating parameters, the timestamps of each operating parameter, and the configuration parameters of the energy storage battery under monitoring, the actual parameter correlation, actual parameter deviation rate, standard parameter correlation, and standard parameter deviation rate of the energy storage battery under monitoring are determined. Based on the actual parameter correlation and actual parameter deviation rate, an actual feature vector of the energy storage battery under monitoring is constructed, and based on the standard parameter correlation and standard parameter deviation rate, a standard feature vector of the energy storage battery under monitoring is constructed, and the similarity between the actual feature vector and the standard feature vector is calculated. If the similarity is less than a preset battery state safety similarity threshold, multiple fault elements in the actual feature vector are predicted based on the actual vector element values ​​in the actual feature vector and the standard vector element values ​​in the standard feature vector, and the fault types corresponding to the multiple fault elements are determined, thus obtaining the state monitoring results of the energy storage battery under monitoring. The aforementioned energy storage battery state monitoring method solves the problems of incomplete and inaccurate state monitoring results in existing technologies. By determining the parameter correlation and parameter deviation rate of the energy storage battery to be monitored, the actual feature vector and standard feature vector of the energy storage battery to be monitored are constructed respectively. When the similarity of the feature vectors is less than the preset battery state safety similarity threshold, the fault type of the battery is determined based on the actual vector element values ​​and the standard vector element values, thus obtaining the state monitoring results of the energy storage battery to be monitored. This method can achieve the purpose of state monitoring and fault screening of the monitored energy storage battery based on multi-dimensional electrical variable parameters, improving the comprehensiveness of energy storage battery state monitoring and the accuracy of monitoring results.

[0071] Figure 2 This is a flowchart illustrating the determination of the standard parameter deviation rate provided in an embodiment of this application. For example... Figure 2 As shown, the operating parameters include basic operating parameters, cumulative charging times, and cumulative discharging duration, specifically including the following steps:

[0072] S201, based on the timestamp of each operating parameter, group multiple operating parameters to obtain the current stage operating parameter group and the historical stage operating parameter group.

[0073] The basic operating parameters can be parameters used to describe the input and output states of the monitored energy storage battery. The cumulative number of charges can be the total number of charges from the start of use of the monitored energy storage battery to the current time. The cumulative discharge duration can be the total discharge duration from the start of use of the monitored energy storage battery to the current time. The current stage operating parameter group can be a parameter group that includes the operating parameters of the monitored energy storage battery at the current time and within a preset time period prior to the current time. The historical stage operating parameter group can be a parameter group that includes the operating parameters of the monitored energy storage battery at the initial use time and within a preset time period after the initial use time.

[0074] In one embodiment, multiple operating parameters belonging to the current stage can be divided according to the timestamps of each operating parameter and the timestamp range corresponding to the current stage operating parameter group, thus obtaining the current stage operating parameter group. The timestamps of the operating parameters at the initial use of the battery to be monitored are identified, and multiple operating parameters belonging to the historical stage are divided according to the time length corresponding to the current stage operating parameter group and the timestamps of the operating parameters at the initial use of the battery to be monitored. That is, the historical stage operating parameter group has the same time length as the current stage operating parameter group. Furthermore, to ensure that the historical stage operating parameters are the historical operating parameters of the energy storage battery under safe conditions, the historical operating parameters in a safe state obtained from the above-divided historical stage operating parameters can be filtered according to a preset cumulative charging number or the difference between the historical operating parameters and the rated operating parameters, thus obtaining the historical stage operating parameter group.

[0075] S202, determine the correlation of historical parameters of the energy storage battery to be monitored based on multiple historical basic operating parameters in the historical stage operating parameter group, and determine the deviation rate of historical parameters of the energy storage battery to be monitored based on multiple historical basic operating parameters and the configuration parameters of the energy storage battery to be monitored.

[0076] In one embodiment, the correlation between historical parameters of each pair of historical basic operating parameters in the monitored energy storage battery can be determined based on multiple historical basic operating parameters representing the input and output states of the monitored energy storage battery in the historical stage operating parameter group and the correlation calculation formula. The actual parameter deviation and theoretical parameter deviation of each historical basic operating parameter can be determined based on multiple historical basic operating parameters and the configuration parameters of the monitored energy storage battery. The historical parameter deviation rate of the monitored energy storage battery can be calculated based on the actual parameter deviation and theoretical parameter deviation.

[0077] S203, based on the cumulative number of charging cycles and the cumulative discharge duration, aging corrections are performed on the correlation of historical parameters and the deviation rate of historical parameters to obtain the correlation of standard parameters and the deviation rate of standard parameters of the energy storage battery to be monitored.

[0078] Among them, aging correction can be an operation that corrects the correlation and deviation rate of historical parameters according to the change pattern of the operating parameters of the energy storage battery under monitoring over the duration of use, so as to determine the standard parameter correlation and standard parameter deviation rate that the energy storage battery under monitoring needs to achieve at the current moment.

[0079] In one embodiment, the correlation of historical parameters and the deviation rate of historical parameters are aged based on the cumulative number of charging cycles and the cumulative discharge duration, respectively, to obtain the standard parameter correlation and standard parameter deviation rate of the energy storage battery to be monitored.

[0080] In one embodiment, aging correction is performed on the correlation of historical parameters and the deviation rate of historical parameters based on the cumulative number of charging cycles and the cumulative discharge duration, respectively. This includes: determining the aging coefficient of the energy storage battery to be monitored based on the cumulative number of charging cycles and the cumulative discharge duration, and determining the sign of the first aging correction coefficient corresponding to the correlation of historical parameters and the sign of the second aging correction coefficient corresponding to the deviation rate of historical parameters; performing a first aging correction on the correlation of historical parameters according to the aging coefficient and the sign of the first aging correction coefficient, and performing a second aging correction on the deviation rate of historical parameters according to the aging coefficient and the sign of the second aging correction coefficient.

[0081] The aging coefficient can represent the degree of aging of the monitored energy storage battery and its impact on various operating parameters. The first aging correction coefficient can be a negative sign used to reduce the original correlation. The second aging correction coefficient can be a positive sign used to increase the original initial deviation rate.

[0082] In one embodiment, the aging coefficient of the energy storage battery under monitoring can be obtained by calculating the weighted sum of the cumulative number of charging cycles and the cumulative discharge duration. Since the cumulative number of charging cycles and the cumulative discharge duration have different effects on the parameter correlation and parameter deviation rate, the sign of the first aging correction coefficient corresponding to the parameter correlation can be determined according to the change law or curve of the parameter correlation with the aging coefficient, and the sign of the second aging correction coefficient corresponding to the parameter deviation rate can be determined according to the change law or curve of the parameter deviation rate with the aging coefficient.

[0083] Figure 3 This is a graph showing the correlation between current and voltage as a function of the aging coefficient, provided in an embodiment of this application. Figure 3As shown, the horizontal axis represents the aging coefficient of the monitored energy storage battery as the cumulative number of charge cycles and cumulative discharge duration increases, while the vertical axis represents the correlation between current and voltage. In the low aging stage (aging coefficient 0-0.2), the correlation between current and voltage is high and stable. At this stage, the internal structure, electrode materials, electrolyte, and separator of the monitored energy storage battery are intact, the electrochemical characteristics are stable, the battery's internal resistance and polarization resistance change very little, and the correlation coefficient between current and voltage values ​​is large with a small fluctuation range. In the moderate aging stage (aging coefficient 0.2-0.6), the correlation between current and voltage slowly decreases. As aging deepens, the electrode materials gradually pulverize, active materials detach, and the internal resistance, especially the polarization resistance, begins to slowly increase, and the stability of the internal resistance decreases. As the aging process progresses, the relationship between current and voltage begins to deviate from the ideal linear law, and the correlation coefficient gradually decreases. In the high aging stage, where the aging coefficient is between 0.6 and 1, the correlation decays rapidly. Internal aging of the battery intensifies, electrolyte decomposes, separator ages and breaks down, and dendrites grow. Internal resistance increases sharply and becomes unstable, even posing a risk of local short circuits. Simultaneously, capacity decays severely, charging and discharging efficiency drops significantly, and the correlation between current and voltage is severely disrupted. Voltage response to current changes is delayed, and even phenomena such as constant current but voltage jumps occur, causing the correlation coefficient to drop rapidly. Based on the curve's variation pattern in the figure, the first aging correction coefficient corresponding to the current-voltage correlation is negative.

[0084] The correlation to be adjusted is determined based on the aging coefficient and the correlation of historical parameters. The correlation of historical parameters is then corrected by the first aging correction coefficient and the correlation to be adjusted. The deviation rate to be adjusted is determined directly based on the aging coefficient and the deviation rate of historical parameters. The deviation rate of historical parameters is then corrected by the second aging correction coefficient and the deviation rate to be adjusted.

[0085] This scheme determines the aging coefficient of the energy storage battery to be monitored based on the cumulative number of charging cycles and cumulative discharge duration. It then performs aging correction on the correlation and deviation rate of historical parameters according to the aging coefficient and aging correction coefficient. This allows for the adjustment of the parameter benchmark under the historical normal state by quantifying the degree of battery aging, and adapting it to the standard parameter correlation and standard parameter deviation rate under the current aging state. This is beneficial to improving the accuracy of subsequent state assessment of the energy storage battery to be monitored.

[0086] The technical solution provided in this application groupes multiple operating parameters according to their timestamps, determines the correlation of historical parameters based on multiple basic operating parameters in the historical group, and determines the deviation rate of historical parameters based on multiple basic operating parameters and the configuration parameters of the energy storage battery to be monitored. Based on the cumulative number of charging times and the cumulative discharge time, the correlation of historical parameters and the deviation rate of historical parameters are aged and corrected respectively, so as to obtain the standard parameter correlation and standard parameter deviation rate of the energy storage battery to be monitored. This can achieve the purpose of aging and correcting the historical characteristics of the energy storage battery to be monitored, and improve the accuracy of the standard parameter correlation and standard parameter deviation rate.

[0087] Figure 4 This is a flowchart illustrating the determination of historical parameter deviation rate provided in an embodiment of this application. For example... Figure 4 As shown, the historical basic operating parameters include historical current values, historical voltage values, and historical temperature values. The configuration parameters include the resistance value, battery thermal capacity, and open-circuit voltage value of the energy storage battery to be monitored. The historical parameter correlations include the correlation between historical current and voltage and the correlation between historical temperature and power. The historical parameter deviation rates include the historical temperature growth deviation rate and the historical voltage deviation rate. The specific steps are as follows:

[0088] S401 determines the correlation between historical current and voltage of the energy storage battery to be monitored based on multiple historical current values ​​and multiple historical voltage values, and determines the correlation between historical temperature and power of the energy storage battery to be monitored based on multiple historical current values, multiple historical voltage values, and multiple historical temperature values.

[0089] The historical current-voltage correlation describes the degree of correlation between current and voltage values ​​over a historical period. The historical temperature-power correlation describes the degree of correlation between the surface temperature and operating power of the monitored energy storage battery over a historical period. The operating power value can be calculated from the current and voltage values. The historical temperature growth deviation rate describes the degree of deviation between the actual and theoretical temperature variables over a historical period. The historical voltage deviation rate describes the degree of deviation between the actual and theoretical voltage variables over a historical period.

[0090] In one embodiment, the historical current-voltage correlation of the energy storage battery to be monitored can be determined based on multiple historical current values, multiple historical voltage values, and a correlation calculation formula, and the historical temperature-power correlation of the energy storage battery to be monitored can be determined based on multiple historical current values, multiple historical voltage values, multiple historical temperature values, and a correlation calculation formula.

[0091] S402 determines the historical temperature growth deviation rate of the energy storage battery to be monitored based on multiple historical temperature values, resistance values, multiple historical current values ​​and battery thermal capacity, and determines the historical voltage deviation rate of the energy storage battery to be monitored based on open circuit voltage values, resistance values, multiple historical current values ​​and multiple historical voltage values.

[0092] In one embodiment, the historical actual temperature change of the monitored energy storage battery can be determined based on multiple historical temperature values, and the historical theoretical temperature change can be determined based on the resistance value, multiple historical current values, and battery thermal capacity. The historical temperature growth deviation rate of the monitored energy storage battery can then be determined based on both the historical actual temperature change and the historical theoretical temperature change. Since the temperature of the monitored energy storage battery is the result of accumulation over time, the multiple historical temperature values ​​and multiple historical current values ​​used in this scheme to calculate the historical temperature growth deviation rate are all corresponding parameter values ​​under continuous timestamps in the historical period. Similarly, the historical actual voltage change of the monitored energy storage battery can be determined based on multiple historical voltage values, and the historical theoretical voltage change can be determined based on the open-circuit voltage value, resistance value, and multiple historical current values. The historical temperature growth deviation rate of the monitored energy storage battery can then be determined based on both the historical actual voltage change and the historical theoretical voltage change.

[0093] In one embodiment, determining the historical temperature growth deviation rate of the monitored energy storage battery based on multiple historical temperature values, resistance values, multiple historical current values, and battery thermal capacity includes: determining the historical endpoint temperature value, historical average current value, and historical current statistical duration corresponding to the historical stage operating parameter group based on multiple historical temperature values ​​and the timestamp of each historical temperature value; determining the historical actual temperature growth value of the monitored energy storage battery based on the historical endpoint temperature value; determining the historical theoretical temperature growth value of the monitored energy storage battery based on the historical endpoint temperature value, historical average current value, historical current statistical duration, resistance value, and battery thermal capacity; and determining the historical temperature growth deviation rate of the monitored energy storage battery based on the historical actual temperature growth value and the historical theoretical temperature growth value.

[0094] The historical endpoint temperature values ​​can include the temperature values ​​corresponding to the start and end timestamps of a historical period. The historical actual temperature increase value can be the difference between the historical endpoint temperature values. The historical theoretical temperature increase value can be the theoretical temperature change of the monitored energy storage battery during a historical period, calculated according to the input and output operating parameters and temperature calculation formula of the monitored energy storage battery.

[0095] In one embodiment, the historical temperature value corresponding to the earliest timestamp and the historical temperature value corresponding to the latest timestamp can be determined based on multiple historical temperature values ​​and their corresponding timestamps. This yields the historical endpoint temperature value corresponding to the historical stage's operating parameter group and the total duration of the historical stage. The total duration of the historical stage is used as the historical current statistical duration, and the historical current average value is calculated based on the historical current statistical duration and the current value of the historical stage. The historical actual temperature increase value of the monitored energy storage battery is determined based on the historical endpoint temperature value. The historical theoretical heat generated by the monitored energy storage battery in the historical stage is determined based on the historical current average value, the historical current statistical duration, and the resistance value. The historical theoretical temperature increase value of the monitored energy storage battery is determined based on the historical theoretical heat and the battery's thermal capacity. The difference between the historical actual temperature increase value and the historical theoretical temperature increase value is calculated, and the ratio of this difference to the historical theoretical temperature increase value is calculated to obtain the historical temperature increase deviation rate of the monitored energy storage battery.

[0096] This scheme determines the historical endpoint temperature value, historical current average value, and historical current statistical duration based on multiple historical temperature values ​​and the timestamps of each historical temperature value. It also calculates the historical temperature growth deviation rate of the monitored energy storage battery by calculating the historical actual temperature growth value and the historical theoretical temperature growth value. This can improve the comprehensiveness of the historical temperature growth deviation rate calculation and the accuracy of the calculation results.

[0097] The technical solution provided in this application can improve the comprehensiveness of the standard feature vector construction of the energy storage battery under monitoring by determining the historical current-voltage correlation, historical temperature-power correlation, historical temperature growth deviation rate, and historical voltage deviation rate of the energy storage battery under monitoring, thereby improving the accuracy of the state monitoring of the energy storage battery under monitoring.

[0098] Figure 5 This is a structural block diagram of a state monitoring system for an energy storage battery provided in an embodiment of this application. Figure 5 As shown, it specifically includes the following:

[0099] The parameter deviation rate determination module 501 is used to acquire multiple operating parameters of the energy storage battery to be monitored in real time, and determine the actual parameter correlation, actual parameter deviation rate, standard parameter correlation and standard parameter deviation rate of the energy storage battery to be monitored based on the multiple operating parameters, the timestamp of each operating parameter and the configuration parameters of the energy storage battery to be monitored.

[0100] The vector similarity calculation module 502 is used to construct the actual feature vector of the energy storage battery to be monitored based on the correlation of actual parameters and the deviation rate of actual parameters, and to construct the standard feature vector of the energy storage battery to be monitored based on the correlation of standard parameters and the deviation rate of standard parameters, and to calculate the similarity between the actual feature vector and the standard feature vector.

[0101] The state monitoring module 503 is used to predict multiple fault elements in the actual feature vector based on the actual vector element values ​​in the actual feature vector and the standard vector element values ​​in the standard feature vector when the similarity is less than the preset battery state safety similarity threshold, and to determine the fault type corresponding to the multiple fault elements, so as to obtain the state monitoring result of the energy storage battery to be monitored.

[0102] Furthermore, the operating parameters include basic operating parameters, cumulative number of charging cycles, and cumulative discharge duration;

[0103] The parameter deviation rate determination module 501 is specifically used for:

[0104] Based on the timestamp of each operating parameter, multiple operating parameters are grouped to obtain the current stage operating parameter group and the historical stage operating parameter group;

[0105] The correlation of historical parameters of the energy storage battery to be monitored is determined based on multiple historical basic operating parameters in the historical stage operating parameter group, and the deviation rate of historical parameters of the energy storage battery to be monitored is determined based on multiple historical basic operating parameters and the configuration parameters of the energy storage battery to be monitored.

[0106] Based on the cumulative number of charging cycles and cumulative discharge duration, aging corrections are performed on the correlation and deviation rates of historical parameters to obtain the correlation and deviation rates of standard parameters for the energy storage battery under monitoring.

[0107] Furthermore, the historical basic operating parameters include historical current values, historical voltage values, and historical temperature values; the configuration parameters include the resistance value, battery thermal capacity, and open-circuit voltage value of the energy storage battery to be monitored; the historical parameter correlation includes the correlation between historical current and voltage and the correlation between historical temperature and power; and the historical parameter deviation rate includes the historical temperature growth deviation rate and the historical voltage deviation rate.

[0108] The parameter deviation rate determination module 501 is specifically used for:

[0109] The correlation between historical current and voltage of the energy storage battery under monitoring is determined based on multiple historical current values ​​and multiple historical voltage values, and the correlation between historical temperature and power of the energy storage battery under monitoring is determined based on multiple historical current values, multiple historical voltage values, and multiple historical temperature values.

[0110] The historical temperature growth deviation rate of the monitored energy storage battery is determined based on multiple historical temperature values, resistance values, multiple historical current values, and battery thermal capacity. The historical voltage deviation rate of the monitored energy storage battery is determined based on open-circuit voltage values, resistance values, multiple historical current values, and multiple historical voltage values.

[0111] Furthermore, the parameter deviation rate determination module 501 is specifically used for:

[0112] Based on multiple historical temperature values ​​and the timestamps of each historical temperature value, the historical endpoint temperature value, the historical average current value, and the historical current statistical duration corresponding to the historical stage operating parameter group are determined respectively.

[0113] The historical actual temperature growth value of the energy storage battery to be monitored is determined based on the historical endpoint temperature value, and the historical theoretical temperature growth value of the energy storage battery to be monitored is determined based on the historical endpoint temperature value, the historical average current value, the historical current statistical duration, the resistance value, and the battery thermal capacity.

[0114] The historical temperature growth deviation rate of the energy storage battery to be monitored is determined based on the historical actual temperature growth value and the historical theoretical temperature growth value.

[0115] Furthermore, the parameter deviation rate determination module 501 is specifically used for:

[0116] The aging coefficient of the energy storage battery to be monitored is determined based on the cumulative number of charging times and the cumulative discharge duration. The sign of the first aging correction coefficient corresponding to the correlation with historical parameters and the sign of the second aging correction coefficient corresponding to the deviation rate of historical parameters are also determined.

[0117] The correlation of historical parameters is corrected by the first aging factor and the first aging correction factor, and the deviation rate of historical parameters is corrected by the second aging factor and the first aging correction factor.

[0118] Furthermore, the status monitoring module 503 is specifically used for:

[0119] Calculate the deviation between the actual vector element values ​​in the actual feature vector and the corresponding standard vector element values ​​in the standard feature vector;

[0120] Determine the floating scale corresponding to each standard vector element value in the standard feature vector. If each deviation is less than the corresponding floating scale, sort the multiple actual vector elements in the actual feature vector according to the magnitude of the deviation.

[0121] The prediction results of multiple fault elements in the actual feature vector are determined based on the preset number of fault elements and the ranking results of fault severity.

[0122] Furthermore, the status monitoring module 503 is specifically used for:

[0123] Multiple fault elements are randomly combined, and the random combination result is matched with a preset fault type mapping library. Based on the matching result, the fault type corresponding to the fault element filtering result is determined.

[0124] The technical solution provided in this application includes a parameter deviation rate determination module, which acquires multiple operating parameters of the energy storage battery to be monitored in real time, and determines the actual parameter correlation, actual parameter deviation rate, standard parameter correlation, and standard parameter deviation rate of the energy storage battery to be monitored based on the multiple operating parameters, the timestamp of each operating parameter, and the configuration parameters of the energy storage battery to be monitored; a vector similarity calculation module, which constructs the actual feature vector of the energy storage battery to be monitored based on the actual parameter correlation and actual parameter deviation rate, and constructs the standard feature vector of the energy storage battery to be monitored based on the standard parameter correlation and standard parameter deviation rate, and calculates the similarity between the actual feature vector and the standard feature vector; and a state monitoring module, which predicts multiple fault elements in the actual feature vector based on the actual vector element values ​​in the actual feature vector and the standard vector element values ​​in the standard feature vector when the similarity is less than a preset battery state safety similarity threshold, and determines the fault type corresponding to the multiple fault elements, thereby obtaining the state monitoring result of the energy storage battery to be monitored. The aforementioned energy storage battery state monitoring system solves the problems of incomplete and inaccurate state monitoring results in existing technologies. By determining the parameter correlation and parameter deviation rate of the energy storage battery to be monitored, the system constructs the actual feature vector and standard feature vector of the battery. When the similarity of the feature vectors is less than a preset battery state safety similarity threshold, the system determines the battery fault type based on the actual vector element values ​​and the standard vector element values, thus obtaining the state monitoring results of the energy storage battery. This system achieves the purpose of state monitoring and fault screening of the monitored energy storage battery based on multi-dimensional electrical variable parameters, improving the comprehensiveness of energy storage battery state monitoring and the accuracy of monitoring results.

[0125] The energy storage battery state monitoring system in this application embodiment can be configured in a device, or in a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network-attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This application embodiment does not impose specific limitations.

[0126] The state monitoring system for an energy storage battery in this application embodiment can be an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0127] The energy storage battery state monitoring system provided in this application embodiment can realize the various processes implemented in the above method embodiments, and will not be repeated here to avoid repetition.

[0128] like Figure 6 As shown, this application embodiment also provides an electronic device 600, including a processor 601, a memory 602, and a program or instructions stored in the memory 602 and executable on the processor 601. When the program or instructions are executed by the processor 601, they implement the various processes of the above-described embodiment of the energy storage battery state monitoring method and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0129] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0130] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described embodiment of the energy storage battery state monitoring method and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0131] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0132] This application also provides a program product including program code. When the program product is run on a computer device, the program code causes the computer device to perform the steps of the methods described above according to various exemplary embodiments of this application. For example, the computer device can execute a state monitoring method for an energy storage battery as described in an embodiment of this application. The program product can be implemented using any combination of one or more readable media.

[0133] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element. Furthermore, it should be noted that the scope of the methods and systems in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0134] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0135] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

[0136] The above description is merely a preferred embodiment and the technical principles employed in this application. This application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that can be made by those skilled in the art will not depart from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the claims.

Claims

1. A method for monitoring the state of an energy storage battery, characterized in that, The method includes: Multiple operating parameters of the energy storage battery to be monitored are acquired in real time. Based on the multiple operating parameters, the timestamp of each operating parameter, and the configuration parameters of the energy storage battery to be monitored, the actual parameter correlation, actual parameter deviation rate, standard parameter correlation, and standard parameter deviation rate of the energy storage battery to be monitored are determined. The actual feature vector of the energy storage battery to be monitored is constructed based on the actual parameter correlation and the actual parameter deviation rate, and the standard feature vector of the energy storage battery to be monitored is constructed based on the standard parameter correlation and the standard parameter deviation rate. The similarity between the actual feature vector and the standard feature vector is then calculated. If the similarity is less than a preset battery state safety similarity threshold, multiple fault elements in the actual feature vector are predicted based on the actual vector element values ​​in the actual feature vector and the standard vector element values ​​in the standard feature vector, and the fault type corresponding to the multiple fault elements is determined to obtain the state monitoring result of the energy storage battery to be monitored.

2. The state monitoring method for energy storage batteries according to claim 1, characterized in that, The operating parameters include basic operating parameters, cumulative number of charging cycles, and cumulative discharge duration; The standard parameter correlation and standard parameter deviation rate of the energy storage battery under monitoring are determined based on the multiple operating parameters, the timestamps of each operating parameter, and the configuration parameters of the energy storage battery under monitoring, including: Based on the timestamps of each of the aforementioned operating parameters, the multiple operating parameters are grouped to obtain the current stage operating parameter group and the historical stage operating parameter group; The correlation of historical parameters of the energy storage battery to be monitored is determined based on multiple historical basic operating parameters in the historical stage operating parameter group, and the deviation rate of historical parameters of the energy storage battery to be monitored is determined based on the multiple historical basic operating parameters and the configuration parameters of the energy storage battery to be monitored. Based on the cumulative number of charging cycles and the cumulative discharge duration, the correlation of the historical parameters and the deviation rate of the historical parameters are aged and corrected to obtain the standard parameter correlation and standard parameter deviation rate of the energy storage battery to be monitored.

3. The state monitoring method for energy storage batteries according to claim 2, characterized in that, The historical basic operating parameters include historical current values, historical voltage values, and historical temperature values. The configuration parameters include the resistance value, battery thermal capacity, and open-circuit voltage value of the energy storage battery to be monitored. The historical parameter correlation includes the correlation between historical current and voltage and the correlation between historical temperature and power. The historical parameter deviation rate includes the historical temperature growth deviation rate and the historical voltage deviation rate. The step of determining the historical parameter correlation of the energy storage battery under monitoring based on multiple historical basic operating parameters in the historical stage operating parameter group, and determining the historical parameter deviation rate of the energy storage battery under monitoring based on the multiple historical basic operating parameters and the configuration parameters of the energy storage battery under monitoring, includes: The historical current-voltage correlation of the energy storage battery under monitoring is determined based on multiple historical current values ​​and multiple historical voltage values, and the historical temperature-power correlation of the energy storage battery under monitoring is determined based on the multiple historical current values, the multiple historical voltage values, and multiple historical temperature values. The historical temperature growth deviation rate of the energy storage battery under monitoring is determined based on the plurality of historical temperature values, the resistance value, the plurality of historical current values ​​and the battery thermal capacity, and the historical voltage deviation rate of the energy storage battery under monitoring is determined based on the open circuit voltage value, the resistance value, the plurality of historical current values ​​and the plurality of historical voltage values.

4. The state monitoring method for energy storage batteries according to claim 3, characterized in that, The step of determining the historical temperature growth deviation rate of the monitored energy storage battery based on the plurality of historical temperature values, the resistance value, the plurality of historical current values, and the battery thermal capacity includes: Based on the multiple historical temperature values ​​and the timestamps of each historical temperature value, the historical endpoint temperature value, the historical average current value, and the historical current statistical duration corresponding to the historical stage operating parameter group are determined respectively. The historical actual temperature growth value of the energy storage battery to be monitored is determined based on the historical endpoint temperature value, and the historical theoretical temperature growth value of the energy storage battery to be monitored is determined based on the historical endpoint temperature value, the historical average current value, the historical current statistical duration, the resistance value, and the battery thermal capacity. The historical temperature growth deviation rate of the monitored energy storage battery is determined based on the historical actual temperature growth value and the historical theoretical temperature growth value.

5. The state monitoring method for energy storage batteries according to claim 2, characterized in that, The aging correction of the correlation of historical parameters and the deviation rate of historical parameters based on the cumulative number of charging times and the cumulative discharge duration includes: The aging coefficient of the energy storage battery to be monitored is determined based on the cumulative number of charging times and the cumulative discharge duration, and the sign of the first aging correction coefficient corresponding to the correlation with the historical parameters and the sign of the second aging correction coefficient corresponding to the deviation rate of the historical parameters are determined. The historical parameter correlation is first aging corrected according to the aging coefficient and the sign of the first aging correction coefficient, and the historical parameter deviation rate is second aging corrected according to the aging coefficient and the sign of the second aging correction coefficient.

6. The state monitoring method for energy storage batteries according to claim 1, characterized in that, The prediction of multiple fault elements in the actual feature vector based on the actual vector element values ​​in the actual feature vector and the standard vector element values ​​in the standard feature vector includes: Calculate the deviation between the actual vector element value in the actual feature vector and the corresponding standard vector element value in the standard feature vector; Determine the floating scale corresponding to each standard vector element value in the standard feature vector; when each deviation is less than the corresponding floating scale, sort the multiple actual vector elements in the actual feature vector according to the magnitude of the deviation. The prediction results of multiple fault elements in the actual feature vector are determined based on the preset number of fault elements and the ranking results of fault severity.

7. The state monitoring method for energy storage batteries according to claim 1, characterized in that, Determining the fault type corresponding to the plurality of fault elements includes: The multiple fault elements are randomly combined, and the random combination result is matched with a preset fault type mapping library. The fault type corresponding to the multiple fault elements is determined based on the matching result.

8. A state monitoring system for an energy storage battery, characterized in that, The system includes: The parameter deviation rate determination module is used to acquire multiple operating parameters of the energy storage battery to be monitored in real time, and determine the actual parameter correlation, actual parameter deviation rate, standard parameter correlation and standard parameter deviation rate of the energy storage battery to be monitored based on the multiple operating parameters, the timestamp of each operating parameter and the configuration parameters of the energy storage battery to be monitored. The vector similarity calculation module is used to construct the actual feature vector of the energy storage battery to be monitored based on the actual parameter correlation and the actual parameter deviation rate, and to construct the standard feature vector of the energy storage battery to be monitored based on the standard parameter correlation and the standard parameter deviation rate, and to calculate the similarity between the actual feature vector and the standard feature vector. The status monitoring module is used to predict multiple fault elements in the actual feature vector based on the actual vector element values ​​in the actual feature vector and the standard vector element values ​​in the standard feature vector when the similarity is less than a preset battery status safety similarity threshold, and to determine the fault type corresponding to the multiple fault elements, thereby obtaining the status monitoring result of the energy storage battery to be monitored.

9. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and running on the processor, wherein when the program or instructions are executed by the processor, they implement the steps of the state monitoring method for an energy storage battery as described in any one of claims 1-7.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the energy storage battery state monitoring method as described in any one of claims 1-7.

Images