CN-121356124-B - Dynamic safety boundary adjustment method and system based on energy storage system

CN121356124BCN 121356124 BCN121356124 BCN 121356124BCN-121356124-B

Abstract

The invention discloses a dynamic safety boundary adjustment method and system based on an energy storage system, which comprises the steps of obtaining historical fault data of the energy storage system and corresponding parameter data of the historical fault data at the same time, carrying out feature analysis according to the historical fault data and the corresponding parameter data, calculating relevance values of each type of fault data and the corresponding parameter data, calculating comprehensive risk score predicted values of each type of fault according to the relevance values of the corresponding parameters of the calculated fault types, obtaining static safety boundary values of parameter data values, constructing corresponding dynamic safety boundary functions according to the parameter data of different fault types, calculating dynamic safety boundary values according to the comprehensive risk score predicted values and the static safety boundary values, reconfiguring response rules of the energy storage system under the current time sequence according to the dynamic safety boundary of the parameter data values of the corresponding fault types, and reconfiguring the corresponding response rules according to the new dynamic safety boundary under the next time sequence.

Inventors

LUO KANGWEI
SONG WEI
CHEN XIAOHUI
ZHANG GUOHONG

Assignees

浙江简捷物联科技有限公司

Dates

Publication Date: 20260512
Application Date: 20251217

Claims (8)

1. A method for dynamic safety boundary adjustment based on an energy storage system, the method comprising: Acquiring historical fault data of an energy storage system and corresponding parameter data of the historical fault data at the same time, performing feature analysis according to the historical fault data and the corresponding parameter data, and calculating a relevance value of each type of fault data and the corresponding parameter data; calculating a comprehensive risk score predicted value of each fault type according to the calculated relevance value of the corresponding parameter of the fault type; acquiring static safety boundary values of parameter data values of different fault types, constructing corresponding dynamic safety boundary functions according to the parameter data of the different fault types, and calculating the dynamic safety boundary values of the parameter data values of the corresponding fault types according to the comprehensive risk score predicted values and the static safety boundary values; reconfiguring a response rule of the energy storage system under the current time sequence according to a dynamic safety boundary of a parameter data value of a corresponding fault type, and reconfiguring a corresponding response rule according to a new dynamic safety boundary under the next time sequence; The calculation method of the relevance value of each type of fault data and the corresponding parameter data comprises the steps of obtaining each parameter data value X m of each type of fault Y n in a continuous time sequence in historical data, wherein n represents a fault type identifier, and m represents a parameter type identifier; constructing a relation model of corresponding type fault binary variables and corresponding parameter continuous variables by using the type fault Y n and the parameter data value X m and adopting a point two-column correlation coefficient algorithm, wherein the corresponding type fault binary variables comprise a variable value of 1 when corresponding type faults exist and a variable value of 0 when no corresponding type faults exist, and calculating a relevance value of each type parameter relative to the corresponding type faults according to the relation model of the corresponding type fault binary variables and the corresponding parameter continuous variables; after the relevance value of the corresponding fault type is obtained through calculation of a point two-column relevance coefficient algorithm, the relevance parameters meeting the corresponding fault type are screened out through setting a relevance threshold value, and risk value calculation of the corresponding relevance parameters is carried out according to the following formula: ; Wherein i may refer to any parameter type that is selected by screening, A risk value representing an associated parameter type i, which may be a specific value or a gradient value, Representing the gradient value of the corresponding parameter type when the risk value is 0.5, e is a natural constant, And (3) representing the curve steepness parameter, further calculating a weight value of the associated parameter corresponding to the fault type according to the association value of the screened associated parameter, and obtaining a comprehensive risk score predicted value of the corresponding fault type by carrying out weighted summation on the risk value and the weight value of the associated parameter.
2. The method of claim 1, wherein the calculating the correlation value between each type of fault data and the corresponding parameter data includes calculating corresponding parameter data values X j , s e n, j e m, s for all corresponding types of faults Y s , j for a particular type of fault, j for a particular type of parameter data, and calculating an average value of all similar parameter data values for corresponding types of faults Y s satisfying the binary variable Wherein the average value of the homogeneous parameter data values Comprising two parts, each being an average of the values of the same-class parameter data in the presence of a variable value of 1 for a corresponding type of fault Y s And average value of the same-class parameter data value in the absence of the variable value of the corresponding type fault Y s being 0 And calculating the standard deviation of the corresponding parameter data value X j of the corresponding type fault Y s in the same parameter type j sample, and calculating the relevance value of the corresponding type parameter relative to the corresponding type fault by combining the corresponding type fault proportion value.
3. The method for adjusting a dynamic safety boundary based on an energy storage system according to claim 2, wherein the formula of the correlation value of the corresponding type parameter with respect to the corresponding type fault is: wherein The value of the correlation is represented by a value of the correlation, And the standard deviation of the corresponding type parameter data j in the same fault type s is represented, p represents the proportion value of the quantity of 1 binary variable value of the corresponding type fault Y s in the same sample, q represents the ratio of the quantity of 0 binary variable value of the corresponding type fault Y s in the same sample, and the binary variable value of the corresponding type fault Y s is automatically calculated through the corresponding fault label, and is obtained through the original static safety boundary of the energy storage system and the fault label output after the energy storage system is actually operated.
4. The method for adjusting dynamic safety boundary based on energy storage system according to claim 3, wherein the method for calculating comprehensive risk score predicted value further comprises the steps of carrying out normalization processing on the correlation value after calculating the correlation value of all types of parameters of corresponding types of faults, carrying out weighted summation calculation on the correlation value after normalization processing and an average value of corresponding types of parameter data to obtain a comprehensive risk score predicted value of corresponding fault types under corresponding types of parameters, and calculating updated dynamic safety boundary according to the comprehensive risk score predicted value and a dynamic safety boundary function.
5. The method for adjusting dynamic safety boundary based on energy storage system according to claim 4, wherein each corresponding type parameter of the corresponding fault type is normalized according to sample data to obtain dimensionless data in a 0-1 interval, an average value of the corresponding type parameter is calculated for each dimensionless parameter, the average value of the dimensionless corresponding type parameter is used as a characteristic parameter of the comprehensive risk score predicted value, the correlation value of the corresponding type parameter and the characteristic parameter of the corresponding parameter type are combined and weighted and summed to obtain the comprehensive risk score predicted value of the corresponding fault type, and grading processing is performed according to the calculated comprehensive risk score predicted value.
6. The method for adjusting dynamic safety boundary based on energy storage system according to claim 1, wherein after obtaining the predicted value of comprehensive risk score, obtaining a static safety boundary value of a corresponding type parameter, automatically matching an adjustment coefficient according to the classified result of the predicted value of comprehensive risk score, and constructing a linear constraint function of the corresponding type parameter of each fault type as the dynamic safety boundary function according to the predicted value of comprehensive risk score and the adjustment coefficient, wherein the static safety boundary of the corresponding type parameter of each fault type is defined as V max and V min respectively, V max represents an upper limit boundary of the static safety boundary, V min represents a lower limit boundary of the static safety boundary, and calculating the dynamic safety boundary by the following function formula: , Wherein D max and D min represent upper and lower dynamic security boundaries, respectively, c represents a corresponding comprehensive risk score predictor, and λ represents an adjustment coefficient at a corresponding risk level.
7. A dynamic safety boundary adjustment system based on an energy storage system, wherein the system performs a dynamic safety boundary adjustment method based on an energy storage system according to any one of claims 1-6.
8. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program, which is executed by a processor to implement a dynamic safety boundary adjustment method based on an energy storage system according to any one of claims 1-6.

Description

Dynamic safety boundary adjustment method and system based on energy storage system Technical Field The invention relates to the technical field of energy storage, in particular to a dynamic safety boundary adjustment method and system based on an energy storage system. Background In the prior art, the safety boundary of an energy storage system generally refers to the limit range of parameters such as charge-discharge current, voltage, temperature and the like. Traditional EMS adopts static safety boundary setting more, namely traditional safety boundary is fixed relative to the fixed, and traditional safety boundary is based on equipment design parameters and experience values, and lack of dynamic response capability to real-time running state and environment change may lead to over conservation, limit energy storage system performance and life utilization rate, or safety boundary setting is insufficient, and potential safety hazards exist. Therefore, how to design a method for dynamically adjusting the safety boundary can intelligently adjust the safety operation range of the energy storage system according to real-time data and prediction information, so that the safety is ensured, and the efficiency and the service life of the system are technical problems which are needed to be solved at present. Disclosure of Invention One of the purposes of the invention is to provide a method and a system for adjusting dynamic safety boundaries based on an energy storage system, which are used for collecting historical data of the energy storage system, counting fault types and parameter characteristics in each historical data, analyzing the relevance of the parameter characteristics and the fault characteristics, constructing comprehensive risk prediction values of different fault types according to the relevance, and dynamically adjusting static safety boundaries of various parameters by utilizing the comprehensive risk prediction values, so that the energy storage system can better adapt to operation changes and environmental changes, and the system performance and the service efficiency and the service life of the system are improved under specific conditions. The invention further aims to provide a dynamic safety boundary adjustment method and system based on an energy storage system, wherein the method and system are used for carrying out high, medium and low three-level risk statistical analysis on various types of energy storage risks, and respectively calculating corresponding parameter safety boundaries for fault types corresponding to the three risk levels. The invention further aims to provide a dynamic safety boundary adjustment method and system based on an energy storage system, wherein after historical data of the energy storage system are acquired, the method and system calculate relevance values of all parameter features of each fault type by using Point-to-Biserial Correlation Coefficient, take each parameter feature relevance value of the corresponding fault type as feature weight of the parameter feature under the corresponding fault type, calculate a corresponding fault type safety risk value according to the feature weight, and perform dynamic boundary adjustment according to parameters meeting a certain relevance threshold according to the corresponding fault type safety risk value, so that the energy storage system can take the safety and efficiency of the system into consideration. The invention further aims to provide a dynamic safety boundary adjusting method and system based on the energy storage system, wherein the method and system construct a dynamic safety boundary function by utilizing a safety risk value of a corresponding fault type, and the parameter boundary of each energy storage device of the energy storage system is recalculated by utilizing the dynamic safety boundary function, so that the energy storage system reconfigures strategies including alarming, current limiting, voltage limiting, power scheduling and the like according to the newly calculated parameter boundaries, and the safety and performance cooperation of the whole cooperative operation of the energy storage system are ensured. In order to achieve at least one of the above objects, the present invention further provides a dynamic safety boundary adjustment method based on an energy storage system, the method comprising: Acquiring historical fault data of an energy storage system and corresponding parameter data of the historical fault data at the same time, performing feature analysis according to the historical fault data and the corresponding parameter data, and calculating a relevance value of each type of fault data and the corresponding parameter data; Calculating the comprehensive risk score predicted value of each fault type according to the relevance value of the corresponding parameter of the calculated fault type and the parameter data value, Acquiring static safety boundary values of parameter data