A method and system for adjusting dynamic security boundaries based on energy storage systems

Abstract

The application discloses a kind of based on energy storage system dynamic security boundary adjustment method and system, comprising: obtaining the historical failure data of energy storage system and the corresponding parameter data of the historical failure data simultaneously, according to historical failure data and corresponding parameter data are carried out feature analysis, the correlation value of each type failure data and corresponding parameter data is calculated;According to the correlation value of the calculated failure type corresponding parameter, the comprehensive risk score prediction value of each fault type is calculated, the static security boundary value of parameter data value is obtained, and the corresponding dynamic security boundary function is constructed according to the parameter data of different fault types, and the dynamic security boundary value is calculated according to the comprehensive risk score prediction value and static security boundary value;According to the dynamic security boundary of the parameter data value of corresponding fault type, the response rule under the current time sequence of the energy storage system is reconfigured, and the corresponding response rule is reconfigured according to the new dynamic security boundary under the next time sequence.

Description

Technical Field

[0001] This invention relates to the field of energy storage technology, and in particular to a method and system for adjusting the dynamic safety boundary of an energy storage system. Background Technology

[0002] In existing technologies, the safety boundary of an energy storage system typically refers to the limited range of parameters such as charging and discharging current, voltage, and temperature. Traditional EMS systems often employ static safety boundary settings, meaning that traditional safety boundaries are relatively fixed and based on equipment design parameters and empirical values. These traditional safety boundaries lack the ability to dynamically respond to real-time operating conditions and environmental changes, potentially leading to overly conservative settings that limit the performance and lifespan of the energy storage system, or insufficient safety boundaries that pose safety hazards. Therefore, designing a method for dynamically adjusting the safety boundary, capable of intelligently adjusting the safe operating range of the energy storage system based on real-time data and predictive information, while ensuring safety and improving system efficiency and lifespan, is a pressing technical problem that needs to be solved. Summary of the Invention

[0003] One objective of this invention is to provide a method and system for adjusting the dynamic safety boundary of an energy storage system. The method and system collect historical data from the energy storage system, statistically analyze the fault types and parameter characteristics in each historical data set, and analyze the correlation between these parameter characteristics and fault characteristics. Based on this correlation, a comprehensive risk prediction value for different fault types is constructed. This comprehensive risk prediction value is then used to dynamically adjust the static safety boundaries of various parameters, thereby enabling the energy storage system to better adapt to operational and environmental changes, improving system performance and efficiency under specific conditions, and extending the system's lifespan.

[0004] Another objective of this invention is to provide a method and system for adjusting the dynamic safety boundary of an energy storage system. The method and system perform statistical analysis of high, medium and low risks for various types of energy storage risks, and calculate the corresponding parameter safety boundary for the fault type corresponding to the above three risk levels. Therefore, this invention can adjust the safety boundary of the corresponding parameter under different risk levels, so that the energy storage system described in this invention can meet both multi-level safety and multi-level performance output, and can give full play to the performance effect of the energy storage system.

[0005] Another objective of this invention is to provide a method and system for dynamic safety boundary adjustment of an energy storage system. After acquiring historical data of the energy storage system, the method and system use point-biserial correlation coefficient to calculate the correlation value of all parameter features for each fault type. The correlation value of each parameter feature for the corresponding fault type is used as the feature weight of the parameter feature under the corresponding fault type. The safety risk value of the corresponding fault type is calculated based on the feature weight. Based on the safety risk value of the corresponding fault type, the parameters that meet a certain correlation threshold are dynamically adjusted, thereby enabling the energy storage system to balance system safety and efficiency.

[0006] Another objective of this invention is to provide a method and system for adjusting the dynamic safety boundary of an energy storage system. The method and system construct a dynamically changing safety boundary function using the safety risk value of the corresponding fault type, and recalculate the parameter boundary of each energy storage device in the energy storage system using the dynamically changing safety boundary function. Therefore, the energy storage system will reconfigure strategies including alarms, current limiting, voltage limiting, and power scheduling according to the newly calculated parameter boundary, thereby ensuring the safety and performance coordination of the overall collaborative operation of the energy storage system.

[0007] To achieve at least one of the above-mentioned objectives, the present invention further provides a method for adjusting the dynamic safety boundary of an energy storage system, the method comprising:

[0008] Acquire historical fault data of the energy storage system and corresponding parameter data simultaneously with the historical fault data; perform feature analysis based on the historical fault data and corresponding parameter data; and calculate the correlation value between each type of fault data and corresponding parameter data.

[0009] Calculate the comprehensive risk score prediction value for each fault type based on the correlation values ​​of the parameters corresponding to the fault type and the parameter data values.

[0010] Obtain static safety boundary values ​​of parameter data for different fault types, construct corresponding dynamic safety boundary functions based on parameter data for different fault types, and calculate dynamic safety boundary values ​​of parameter data for corresponding fault types based on the comprehensive risk score prediction value and static safety boundary values.

[0011] The response rules of the energy storage system under the current time series are reconfigured based on the dynamic safety boundary of the parameter data value corresponding to the fault type, and the corresponding response rules are reconfigured based on the new dynamic safety boundary in the next time series.

[0012] According to a preferred embodiment of the present invention, the method for calculating the correlation value between each type of fault data and the corresponding parameter data includes: obtaining each type of fault Y in a continuous time series from historical data. n Each parameter data value X m Where n represents the fault type identifier and m represents the parameter type identifier; using the fault type Y n and parameter data value X m A point-binary correlation coefficient algorithm is used to construct a relationship model between binary variables of corresponding fault types and continuous variables of corresponding parameters. The binary variables of corresponding fault types include variables with a value of 1 when the corresponding fault type exists and variables with a value of 0 when the corresponding fault type does not exist. The correlation value of each type parameter relative to the corresponding fault type is calculated based on the relationship model of the binary variables of corresponding fault types and continuous variables of corresponding parameters.

[0013] According to another preferred embodiment of the present invention, the method for calculating the correlation value of each type of fault data and corresponding parameter data includes: calculating all corresponding type fault Y s The corresponding parameter data value X j Let s∈n, j∈m, where s represents a specific type of fault, j represents a specific type of parameter data, and calculate the corresponding type of fault Y. s The average value of all similar parameter data values ​​of the binary variable. The average value of the same type of parameter data. It consists of two parts, namely, the existence of a corresponding type of fault Y. s The average value of similar parameter data when the variable value is 1 And there is no corresponding type of fault Y s The average value of similar parameter data when the variable value is 0. And calculate the corresponding type of fault Y s The corresponding parameter data value X j The correlation value between the corresponding type parameter and the corresponding type of fault is calculated by combining the standard deviation of the sample of the same parameter type j with the corresponding type of fault proportion value.

[0014] According to another preferred embodiment of the present invention, the formula for the correlation value of the corresponding type parameter relative to the corresponding type of fault is:

[0015] ,in This represents the correlation value. p represents the standard deviation of parameter j of the same type in the same fault type s, and p represents the corresponding type of fault Y. s The proportion of binary variables with a value of 1 in the same sample; where q represents the corresponding type of fault Y. sThe percentage of binary variable values ​​of 0 in the same sample, where the corresponding type of fault Y is... s The binary variable values ​​are automatically calculated through the corresponding fault labels, specifically obtained from the original static safety boundary of the energy storage system and the fault labels output after the actual operation of the energy storage system.

[0016] According to a preferred embodiment of the present invention, after calculating the correlation value of the corresponding fault type using the point-binary correlation coefficient algorithm, correlation parameters that meet the corresponding fault type are filtered out by setting a correlation threshold, and the risk value of the corresponding correlation parameter is calculated according to the following formula:

[0017] ;

[0018] Here, 'i' can refer to any parameter type selected through the filtering process. This represents the risk value of parameter type i corresponding to the fault type. The parameter type can be a specific value or a gradient value. c This represents the specific value or gradient value of the corresponding parameter type when the risk value is 0.5, where e is a natural constant. Furthermore, the weight value of the corresponding fault type's associated parameter is calculated based on the correlation value of the selected associated parameters. The comprehensive risk score prediction value of the corresponding fault type is obtained by weighted summing of the risk value and weight value of the associated parameters.

[0019] According to another preferred embodiment of the present invention, after calculating the correlation values ​​of all type parameters of the corresponding type of fault, the correlation values ​​are further normalized, and the normalized correlation values ​​and the average value of the corresponding type parameter data are weighted and summed to obtain the comprehensive risk score prediction value of the corresponding fault type under the corresponding type parameters. The updated dynamic safety boundary is then calculated based on the comprehensive risk score prediction value and the dynamic safety boundary function.

[0020] According to another preferred embodiment of the present invention, each corresponding type parameter of the corresponding fault type is normalized according to the sample data to obtain dimensionless data in the range of 0-1. The average value of the corresponding type parameter is calculated for each dimensionless parameter, and the average value of the corresponding type parameter is used as the feature parameter of the comprehensive risk score prediction value. The comprehensive risk score prediction value of the corresponding fault type is obtained by weighted summation of the correlation value of the corresponding type parameter and the feature parameter of the corresponding parameter type. The comprehensive risk score prediction value is then graded according to its magnitude.

[0021] According to another preferred embodiment of the present invention, after obtaining the comprehensive risk score prediction value, the static safety boundary value of the corresponding type parameter is obtained, and an adjustment coefficient is automatically matched according to the classification result of the comprehensive risk score prediction value. A linear constraint function of the corresponding type parameter for each fault type is constructed based on the comprehensive risk score prediction value and the adjustment coefficient as the dynamic safety boundary function. Specifically, the method includes: defining the static safety boundary values ​​of the corresponding type parameters for the corresponding fault type as V... max and V min , where V max V represents the upper bound of the static safety boundary. min The lower bound of the static safety boundary is represented by the following function formula, and the dynamic safety boundary is calculated using this formula: , D max and D min λ represents the upper and lower dynamic safety boundaries, respectively; c represents the predicted value of the corresponding comprehensive risk score; and λ represents the adjustment coefficient under the corresponding risk level.

[0022] To achieve at least one of the above-mentioned objectives, the present invention further provides a dynamic safety boundary adjustment system based on an energy storage system, wherein the system executes the above-mentioned dynamic safety boundary adjustment method based on an energy storage system.

[0023] The present invention further provides a computer-readable storage medium storing a computer program, which is executed by a processor to implement the above-described method for adjusting the dynamic safety boundary of an energy storage system. Attached Figure Description

[0024] Figure 1 The diagram shown is a flowchart of a method for adjusting the dynamic safety boundary of an energy storage system according to the present invention. Detailed Implementation

[0025] The following description is intended to disclose the present invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art. The basic principles of the invention defined in the following description can be applied to other embodiments, modifications, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the invention.

[0026] It is understood that the term "a" should be understood as "at least one" or "one or more," that is, in one embodiment, the number of an element can be one, while in another embodiment, the number of the element can be multiple, and the term "a" should not be understood as a limitation on the number.

[0027] Combination Figure 1This invention discloses a method and system for adjusting the dynamic safety boundary of an energy storage system. The method specifically includes:

[0028] S01. Obtain historical fault data of the energy storage system and corresponding parameter data at the same time as the historical fault data; perform feature analysis based on the historical fault data and corresponding parameter data; and calculate the correlation value between each type of fault data and corresponding parameter data.

[0029] S02. Calculate the comprehensive risk score prediction value for each fault type based on the correlation values ​​of the parameters corresponding to the fault type and the parameter data values.

[0030] S03. Obtain the static safety boundary value of the parameter data value for different fault types, and construct the corresponding dynamic safety boundary function based on the parameter data of different fault types. Calculate the dynamic safety boundary value of the parameter data value for the corresponding fault type based on the comprehensive risk score prediction value and the static safety boundary value.

[0031] S04. Reconfigure the response rules of the energy storage system under the current time series according to the dynamic safety boundary of the parameter data value corresponding to the fault type, and reconfigure the corresponding response rules under the new dynamic safety boundary in the next time series.

[0032] Specifically, the method for calculating the correlation value between each type of fault data and the corresponding parameter data in this invention includes: obtaining the fault Y of each type under continuous time series in historical data. n Each parameter data value X m Where n represents the fault type identifier and m represents the parameter type identifier, the fault types include, but are not limited to, cell body faults, battery management system faults, power conversion faults, thermal management faults, and insulation faults, etc., where the above fault types are general types, and the art can classify each of the above fault types into sub-types; using the type fault Y n and parameter data value X m A point-binary correlation coefficient algorithm is used to construct a relationship model between a binary variable representing a corresponding type of fault and a continuous variable representing a corresponding parameter. The binary variable representing the corresponding type of fault includes variables with a value of 1 if the corresponding type of fault exists and a value of 0 if the corresponding type of fault does not exist. Based on this relationship model, the correlation value of each type parameter relative to the corresponding type of fault is calculated. It should be noted that the corresponding type of fault Y in this invention... n and parameter data value X m This is a time-series mapping relationship group, that is, when the energy storage device has a corresponding type of fault Y n For a time series t with fault 1 present or fault 0 absent, multiple types of parameter data for the corresponding energy storage devices with the same time series are sampled.

[0033] Furthermore, this invention requires calculating the correlation between each type of fault data and its corresponding parameter data. Those skilled in the art will understand that different fault types in energy storage devices exhibit different parameter value fluctuations, and these fluctuations have varying impacts on the fault type. Therefore, this invention requires calculating the correlation between each type of fault data and its corresponding parameter data. The method for calculating the correlation value between each type of fault data and its corresponding parameter data includes: calculating all corresponding fault types Y... s The corresponding parameter data value X j Let s∈n, j∈m, where s represents a specific type of fault, j represents a specific type of parameter data, and calculate the corresponding type of fault Y. s The average value of all similar parameter data values ​​of the binary variable. The average value of the same type of parameter data. It consists of two parts, namely, the existence of a corresponding type of fault Y. s The average value of similar parameter data when the variable value is 1 And there is no corresponding type of fault Y s The average value of similar parameter data when the variable value is 0. And calculate the corresponding type of fault Y s The corresponding parameter data value X j The standard deviation of the parameter j in the same parameter type samples is used to calculate the correlation value of the corresponding type parameter relative to the corresponding type of fault, combined with the proportion of the corresponding type of fault. It should be noted that in this invention, in the binary mapping of corresponding type faults and non-faults, if the average value of the corresponding type parameter data values ​​is... Significantly greater than the average value of the same type of parameter data. This indicates that the current type parameter j has a significant influence and correlation with the fault type s, and this influence is positive; that is, the larger the value of the current type parameter j, the higher the probability of the corresponding fault type s occurring; the smaller the value of the current type parameter j, the lower the probability of the corresponding fault type s occurring. Conversely, when the average value of the corresponding type parameter data is lower... Less than the average value of the same type of parameter data If the value of the corresponding parameter type j is greater, it means that the corresponding fault type s also has a significant influence and correlation on the occurrence of the fault type s, but this influence is negative. That is, the larger the value of the current type parameter j, the smaller the probability of the corresponding fault type s occurring.

[0034] In one preferred embodiment of the present invention, the formula for the correlation value of the corresponding type parameter relative to the corresponding type of fault is:

[0035] ,in This represents the correlation value. p represents the standard deviation of parameter j of the same type in the same fault type s, and p represents the corresponding type of fault Y. s The proportion of binary variables with a value of 1 in the same sample; where q represents the corresponding type of fault Y. s The percentage of binary variable values ​​of 0 in the same sample, corresponding to the fault type Y. s The binary variable values ​​are automatically calculated using the corresponding fault labels, specifically obtained from the original static safety boundary of the energy storage system and the fault labels output after the actual operation of the energy storage system. Further, after calculating the correlation values ​​of all type parameters for the corresponding fault type, this invention further normalizes these correlation values. The normalization algorithm in this invention can be implemented using, but is not limited to, the Z-score algorithm. Any existing normalization algorithm can be referenced, and this invention will not elaborate further. The normalized correlation values ​​and the average value of the corresponding type parameter data are then weighted and summed to obtain the comprehensive risk score prediction value for the corresponding fault type under the corresponding type parameters. The updated dynamic safety boundary is then calculated based on the comprehensive risk score prediction value and the dynamic safety boundary function.

[0036] It is worth mentioning that, in this invention, each corresponding type parameter of the corresponding fault type is normalized according to the sample data to obtain dimensionless data in the 0-1 interval. The average value of the corresponding type parameter is calculated for each dimensionless parameter, and this average value is used as a feature parameter of the predicted comprehensive risk score. The predicted comprehensive risk score for the corresponding fault type is obtained by weighted summation of the correlation value of the corresponding type parameter and the feature parameter of the corresponding parameter type. The predicted comprehensive risk score is then graded based on its magnitude. After obtaining the predicted comprehensive risk score, the static safety boundary value of the corresponding type parameter is acquired. An adjustment coefficient is automatically matched based on the grading result of the predicted comprehensive risk score. A linear constraint function for the corresponding type parameter of each fault type is constructed based on the predicted comprehensive risk score and the adjustment coefficient, serving as the dynamic safety boundary function. Specifically, the method includes defining the static safety boundary of the corresponding type parameter for the corresponding fault type as V... max and V min , where V max V represents the upper bound of the static safety boundary. min The lower bound of the static safety boundary is represented by the following function formula, and the dynamic safety boundary is calculated using this formula: , D max and D mindenoted as upper and lower dynamic safety boundaries, respectively; c represents the corresponding risk score prediction value; and λ represents the adjustment coefficient under the corresponding risk level.

[0037] For example, the present invention can dynamically set, including but not limited to: voltage safety boundary, current safety boundary, power safety boundary, temperature safety boundary, temperature difference safety boundary, and battery SOC safety boundary, etc., and the above-mentioned different types of safety boundaries are based on the dynamic safety boundary function. , Therefore, the specific parameter calculations will not be described in detail in this invention. When the above-mentioned different types of safety boundaries are reset, the corresponding energy storage system's response information is also reset. For example, overheat warnings and excessive current warnings are all executed according to the dynamically set new safety boundaries.

[0038] Furthermore, in another preferred embodiment of the present invention, after calculating the correlation value of the corresponding type parameter relative to the corresponding type of fault using the above-described point-binary correlation coefficient algorithm, multiple corresponding type parameters that meet the correlation requirements of the corresponding fault type are further screened out using a correlation threshold method, and the risk value is calculated using the following formula:

[0039] Taking battery failure types in energy storage systems as an example, the relevant parameters selected include temperature gradient. In energy storage systems, the temperature gradient should be kept within a relatively reasonable range. When the temperature gradient rises to a certain critical point, the probability of the corresponding failure type risk in the energy storage system will increase significantly. High temperature gradients may lead to internal battery failures in the energy storage system. Therefore, this invention uses the following formula to calculate the temperature gradient risk value for the aforementioned battery failure types:

[0040] ;

[0041] in, The temperature gradient is represented as The risk value at that time, wherein the value of the temperature gradient risk value ranges from [0-1]. This indicates the current temperature gradient, measured in °C / minute. This represents the critical temperature gradient, which is set as the temperature gradient when the risk value is 0.5. It should be noted that different types of energy storage batteries have different critical temperature gradients; this invention is merely illustrative. This parameter represents the steepness of the curve, controlling the rate at which the risk value changes from low to high. A higher value indicates a faster increase in risk. It should be noted that the steepness parameter... It can be dynamically adjusted, where e is the natural constant. In actual simulation calculations, if the device experiences multiple battery fault types and a large temperature gradient, but the corresponding temperature gradient is... When the risk value is low, the curve steepness parameter can be dynamically increased. This makes the temperature gradient risk value more sensitive to the battery fault type. The above curve steepness parameter... It can be dynamically adjusted based on statistical analysis of historical data within a certain period of time.

[0042] Furthermore, the parameter types that need to be statistically analyzed for the battery fault types also include voltage gradient, and the risk value of the corresponding voltage gradient is calculated using the same formula:

[0043] ;

[0044] in The voltage gradient is represented as The risk value at that time, wherein the voltage gradient risk value ranges from [0-1], and This indicates the current measured voltage gradient, in volts per minute. This represents the critical voltage gradient, where the critical voltage gradient is set as the voltage gradient when the risk value is 0.5. This represents the curve steepness parameter, which, like the temperature gradient mentioned above, can be used as a dynamically adjustable parameter to match the voltage gradient risk value with the sensitivity of battery fault types.

[0045] It should be noted that the same formula described above can be used to calculate the risk values ​​of all other relevant parameters selected through screening, resulting in the following general formula:

[0046] ;

[0047] Where 'i' can refer to any type of parameter selected, and the parameter type can be a specific value or a gradient value. c This indicates the specific value or gradient value of the corresponding parameter type when the risk value is 0.5.

[0048] Further, a weight value is calculated based on the relevance of each relevant parameter to the fault type. This weight value can be obtained by using, but is not limited to, the proportion of the total relevance value of the relevant parameters selected for the fault type corresponding to the relevance value of each relevant parameter itself. For example, if the relevant parameters selected for the corresponding battery fault include voltage gradient, current gradient, and temperature gradient, then the total relevance value of all voltage gradient, current gradient, and temperature gradients needs to be calculated. Based on this total relevance value, the independent proportions of each voltage gradient, current gradient, and temperature gradient are then calculated as the weight values ​​for the relevant parameters. .

[0049] After obtaining the relevant parameter weight values ​​for the corresponding fault type, the comprehensive risk value for the corresponding fault type is further calculated using the following formula: Where i represents the relevant parameter type for the corresponding fault type obtained by the above point-binary correlation coefficient algorithm, and R i This represents the risk value of the relevant parameter type corresponding to the fault type. It is further combined with the comprehensive risk value Q for the corresponding fault type. s Adjust the safety boundaries of the relevant parameters as described above.

[0050] The processes described in the flowcharts above, as disclosed in the embodiments of this invention, can be implemented as computer software programs. Embodiments of this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), the methods of this application are not limited to the aforementioned functions. It should be noted that the computer-readable medium described above can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wire segments, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless segments, wire segments, optical fibers, RF, etc., or any suitable combination thereof.

[0051] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0052] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are merely examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functions and structural principles of the present invention have been shown and explained in the embodiments. Without departing from the stated principles, the implementation of the present invention may have any variations or modifications.

Claims

1. A method for adjusting the dynamic safety boundary of an energy storage system, characterized in that, The method includes: Acquire historical fault data of the energy storage system and corresponding parameter data simultaneously with the historical fault data; perform feature analysis based on the historical fault data and corresponding parameter data; and calculate the correlation value between each type of fault data and corresponding parameter data. Calculate the comprehensive risk score prediction value for each fault type based on the correlation values ​​of the parameters corresponding to the fault types. Obtain static safety boundary values ​​of parameter data for different fault types, construct corresponding dynamic safety boundary functions based on parameter data for different fault types, and calculate dynamic safety boundary values ​​of parameter data for corresponding fault types based on the comprehensive risk score prediction value and static safety boundary values. The response rules of the energy storage system under the current time sequence are reconfigured according to the dynamic safety boundary of the parameter data value corresponding to the fault type, and the corresponding response rules are reconfigured according to the new dynamic safety boundary in the next time sequence. The method for calculating the correlation value between each type of fault data and its corresponding parameter data includes: obtaining the fault Y of each type in the continuous time series of historical data. n Each parameter data value X m Where n represents the fault type identifier and m represents the parameter type identifier; using the fault type Y n and parameter data value X m A point-binary correlation coefficient algorithm is used to construct a relationship model between binary variables of corresponding fault types and continuous variables of corresponding parameters. The binary variables of corresponding fault types include variables with a value of 1 when the corresponding fault type exists and variables with a value of 0 when the corresponding fault type does not exist. The correlation value of each type parameter relative to the corresponding fault type is calculated based on the relationship model of the binary variables of corresponding fault types and continuous variables of corresponding parameters. After calculating the correlation value of the corresponding fault type using the point-binary correlation coefficient algorithm, correlation parameters that meet the corresponding fault type are filtered out by setting a correlation threshold, and the risk value of the corresponding correlation parameter is calculated according to the following formula: ； Here, 'i' can refer to any parameter type selected through the filtering process. This represents the risk value of the associated parameter type i corresponding to the fault type. The parameter type can be a specific value or a gradient value. This represents the gradient value of the parameter type when the risk value is 0.5, where e is the natural constant. The curve steepness parameter is represented, and the weight value of the corresponding fault type correlation parameter is calculated based on the correlation value of the selected correlation parameters. The comprehensive risk score prediction value of the corresponding fault type is obtained by weighted summation of the risk value and weight value of the correlation parameters.

2. The method for adjusting the dynamic safety boundary of an energy storage system according to claim 1, characterized in that, The method for calculating the correlation value between each type of fault data and its corresponding parameter data includes: calculating the correlation value of all corresponding type fault Y. s The corresponding parameter data value X j Let s∈n, j∈m, where s represents a specific type of fault, j represents a specific type of parameter data, and calculate the corresponding type of fault Y. s The average value of all similar parameter data values ​​of the binary variable. The average value of the same type of parameter data. It consists of two parts, namely, the existence of a corresponding type of fault Y. s The average value of similar parameter data when the variable value is 1 And there is no corresponding type of fault Y s The average value of similar parameter data when the variable value is 0 And calculate the corresponding type of fault Y s The corresponding parameter data value X j The correlation value between the corresponding type parameter and the corresponding type of fault is calculated by combining the standard deviation of the sample of the same parameter type j with the corresponding type of fault proportion value.

3. The method for adjusting the dynamic safety boundary of an energy storage system according to claim 2, characterized in that, The formula for the correlation value between the corresponding type parameter and the corresponding type of fault is: ,in This represents the correlation value. p represents the standard deviation of parameter j of the same type in the same fault type s, and p represents the corresponding type of fault Y. s The proportion of binary variables with a value of 1 in the same sample; where q represents the corresponding type of fault Y. s The percentage of binary variable values ​​of 0 in the same sample, where the corresponding type of fault Y is... s The binary variable values ​​are automatically calculated through the corresponding fault labels, specifically obtained from the original static safety boundary of the energy storage system and the fault labels output after the actual operation of the energy storage system.

4. The method for adjusting the dynamic safety boundary of an energy storage system according to claim 3, characterized in that, The method for calculating the comprehensive risk score prediction value further includes: after calculating the correlation values ​​of all type parameters of the corresponding type of fault, normalizing the correlation values, and weighting and summing the normalized correlation values ​​and the average value of the corresponding type parameter data to obtain the comprehensive risk score prediction value of the corresponding fault type under the corresponding type parameters, and calculating the updated dynamic safety boundary based on the comprehensive risk score prediction value and the dynamic safety boundary function.

5. The method for adjusting the dynamic safety boundary of an energy storage system according to claim 4, characterized in that, For each corresponding type parameter of the corresponding fault type, normalize the sample data to obtain dimensionless data in the 0-1 interval. Calculate the average value of the corresponding type parameter for each dimensionless parameter and use the average value of the corresponding type parameter as the feature parameter of the comprehensive risk score prediction value. Combine the correlation value of the corresponding type parameter with the feature parameter of the corresponding parameter type and perform a weighted summation to obtain the comprehensive risk score prediction value of the corresponding fault type. Then, classify the calculated comprehensive risk score prediction value according to its magnitude.

6. The method for adjusting the dynamic safety boundary of an energy storage system according to claim 1, characterized in that, After obtaining the comprehensive risk score prediction value, the static safety boundary value of the corresponding type parameter is obtained, and an adjustment coefficient is automatically matched according to the classification result of the comprehensive risk score prediction value. A linear constraint function for the corresponding type parameter of each fault type is constructed based on the comprehensive risk score prediction value and the adjustment coefficient, serving as the dynamic safety boundary function. (Specific method follows.) This includes defining the corresponding type parameters and static safety boundaries for each fault type, namely V. max and V min , where V max V represents the upper bound of the static safety boundary. min The lower bound of the static safety boundary is represented by the following function formula, and the dynamic safety boundary is calculated using this formula: , D max and D min λ represents the upper and lower dynamic safety boundaries, respectively; c represents the predicted value of the corresponding comprehensive risk score; and λ represents the adjustment coefficient under the corresponding risk level.

7. A dynamic safety boundary adjustment system based on an energy storage system, characterized in that, The system executes a method for adjusting the dynamic safety boundary of an energy storage system as described in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement a method for adjusting the dynamic safety boundary of an energy storage system as described in any one of claims 1-6.

Images