Abnormal state early warning method for energy storage system

Abstract

The invention relates to the technical field of energy storage system early warning, and provides an abnormal state early warning method for an energy storage system. The method comprises the following steps: connecting monitoring equipment through an embedded platform interface, and obtaining running state data; connecting a historical record library, and extracting a case set based on the state data; analyzing the case set, and determining an influence relationship; constructing an anomaly judgment model according to the influence relationship; inputting the monitoring data into the model for abnormal probability analysis, and outputting a judgment result; and generating early warning information according to the result, loading the early warning information to a historical record library, and updating the abnormal database. The technical problem that the abnormal state of the energy storage system cannot be timely and accurately found due to insufficient data analysis depth methods and low early warning model precision in existing early warning is solved, timely early warning can be performed on the abnormal state of the energy storage system through combination of the real-time monitoring data and the abnormal judgment model, and the early warning efficiency is improved. The missing report rate of early warning is effectively reduced, and the early warning accuracy and timeliness are improved.

Description

Technical Field

[0001] The present application relates to the field of energy management technology, specifically to the field of energy storage system early warning technology, and in particular to a method for early warning of abnormal state of an energy storage system. Background Art

[0002] With the rapid development and widespread application of energy storage technology, energy storage systems play an increasingly important role in power systems. However, due to the complexity and variability of the internal operating state of the energy storage system, the timely detection and handling of its abnormal state has become an urgent problem to be solved. The existing energy storage system early warning methods are often unable to detect abnormal states in a timely and accurate manner due to insufficient data analysis depth and low accuracy of the early warning model, resulting in a high rate of missed warnings, which brings potential safety hazards to the stable operation of the power system. Summary of the invention

[0003] The present application provides an abnormal state warning method for an energy storage system, aiming to solve the technical problem that the abnormal state of the energy storage system cannot be detected in a timely and accurate manner due to insufficient data analysis depth methods and low accuracy of warning models in existing warnings.

[0004] In view of the above problems, the present application provides an abnormal state early warning method for an energy storage system.

[0005] The present application provides an abnormal state early warning method for an energy storage system, the method comprising: connecting a monitoring device through an embedded platform interface to obtain operating state data, including electric quantity, charge and discharge state, temperature, voltage, and insulation resistance; connecting a historical record library, and extracting an abnormal accident case set based on the electric quantity, charge and discharge state, temperature, voltage, and insulation resistance, wherein the abnormal accident case set includes one or more abnormal operating state data of the electric quantity, charge and discharge state, temperature, voltage, and insulation resistance; analyzing each operating state data of the abnormal accident case set to determine the influence relationship of each operating state data; constructing an abnormal judgment model according to the influence relationship of each operating state data; inputting the operating state data collected by the monitoring device into the abnormal judgment model to perform abnormal probability analysis, and outputting an abnormal judgment result; generating early warning information according to the abnormal judgment result, and loading the abnormal judgment result into the historical record library, and updating the abnormal record database.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: The above-mentioned abnormal state early warning method of an energy storage system connects the monitoring device through an embedded platform interface to obtain key operating state data such as power, charge and discharge state, temperature, voltage, insulation resistance, etc. of the energy storage system in real time. Subsequently, the historical record library is connected to extract case sets related to abnormal accidents based on these operating state data, and these case sets contain data of various abnormal operating states. After that, the abnormal accident case set is deeply analyzed to determine the mutual influence relationship between each operating state data. Based on these influence relationships, an accurate abnormal judgment model is constructed. This model can receive the operating state data collected by the monitoring device in real time, perform abnormal probability analysis, and output abnormal judgment results. Once the abnormal state is judged, an early warning message will be generated immediately to notify the user in time. At the same time, these abnormal judgment results will also be loaded into the historical record library for continuous updating and improvement of the abnormal record database, and improve the accuracy and reliability of the early warning model. This method realizes timely early warning of abnormal states of the energy storage system through real-time monitoring and deep data analysis, and improves the safety and operation efficiency of the energy storage system.

[0007] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic diagram of a process of an abnormal state warning method of an energy storage system in one embodiment; Figure 2 The figure is a schematic diagram of the influence relationship of determining various operating status data in a method for early warning of abnormal status of an energy storage system in one embodiment. DETAILED DESCRIPTION

[0010] The embodiment of the present application provides an abnormal state warning method for an energy storage system to solve the technical problem that the abnormal state of the energy storage system cannot be discovered in a timely and accurate manner due to insufficient data analysis depth methods and low accuracy of warning models in existing warnings.

[0011] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0012] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0013] Embodiment 1 like Figure 1 As shown, the present application provides an abnormal state warning method for an energy storage system, the method comprising: Connect monitoring equipment through the embedded platform interface to obtain operating status data, including power, charge and discharge status, temperature, voltage, and insulation resistance; As an energy storage device, the energy storage system can balance the supply and demand of electricity and improve the stability of the power system. It is crucial for modern industrial production, power supply and other fields. The embedded platform is an important component of the energy storage system. It has a high degree of integration and real-time performance, and can realize real-time monitoring and data processing of various operating states of the energy storage system. By making full use of the advantages of the embedded platform, connecting monitoring equipment, and obtaining key operating status data of the energy storage system in real time, accurate early warning of abnormal conditions can be achieved.

[0014] In the embodiment of the present application, the system terminal successfully connected to the monitoring device through the embedded platform interface, thereby obtaining the key operating status data of the energy storage system in real time. These data cover important information such as power, charge and discharge status, temperature, voltage, and insulation resistance, providing necessary data support for subsequent abnormal status warnings. In this way, the operating status of the energy storage system can be fully understood, laying a solid foundation for subsequent analysis and warning work.

[0015] Connecting to a historical record library, extracting an abnormal accident case set based on the electric quantity, charge and discharge state, temperature, voltage, and insulation resistance, wherein the abnormal accident case set includes one or more abnormal operation state data of the electric quantity, charge and discharge state, temperature, voltage, and insulation resistance; In one embodiment, the system terminal establishes a stable connection with the historical record library by calling the interface of the embedded platform. This step ensures that the platform can smoothly access and retrieve historical data. Subsequently, the system terminal will filter the historical record library according to the current real-time monitored operating status data such as power, charge and discharge status, temperature, voltage, insulation resistance, etc. The purpose of the screening is to find historical records that are similar or related to the current status data. In the filtered historical records, the system terminal performs a cyclic search of the historical record library according to the current real-time monitored data. In each search, the system terminal compares the current real-time monitored data with the search results. If the data is roughly the same, the search is extracted until all the data in the historical record library is retrieved. These retrieved cases involve various situations such as abnormal power, abnormal charge and discharge status, abnormal temperature, voltage fluctuation, and reduced insulation resistance. Based on the extracted cases, the system terminal will further analyze and organize to build a collection of abnormal accident cases. This case collection contains various abnormal state data that occurred in the past, which helps to gain a deeper understanding of various abnormal situations that may occur in the energy storage system. By analyzing these case collections, the correlation and influence relationship between the various operating status data can be found, providing strong data support for the subsequent construction of abnormal judgment models.

[0016] Analyzing each operating status data of the abnormal accident case set to determine the influence relationship of each operating status data; In one embodiment, the analysis of each operating status data of the abnormal accident case set is limited in order to deeply explore the correlation and influence relationship between different status data. This process involves in-depth analysis of multiple key indicators such as power, charge and discharge status, temperature, voltage, insulation resistance, etc. Through accident type clustering and accident concurrent status analysis, the system terminal can establish potential connections between them. For example, when the battery temperature rises abnormally, its insulation resistance will decrease accordingly. Through such analysis, the system terminal can not only have a more comprehensive understanding of the operating status of the energy storage system, but also provide important reference for subsequent abnormal warning and troubleshooting.

[0017] Further, if Figure 2 As shown, the present application provides for analyzing each operating state data of the abnormal accident case set to determine the influence relationship of each operating state data, and the method also includes: Clustering the abnormal accident case set into accident types to obtain a multi-accident set; Performing longitudinal comparison on the operation status data of the multiple accident sets respectively to obtain a change relationship of the operation status data, and fitting an influence relationship between the operation status data and the accident type based on the change relationship of the operation status data; Preferably, the accident type clustering of the abnormal accident case set is to classify accidents with similar characteristics and causes into one category to form multiple different accident sets. Specifically, the system terminal determines the key features for clustering, such as power changes, temperature trends, voltage fluctuations, etc., based on the actual situation of the accident case and historical experience. Then extract these features for each case to form a feature vector. Subsequently, the extracted feature vector is used as input data. These feature vectors contain key information of each abnormal accident case and are used to describe the similarity between cases. After that, the system terminal randomly selects K data points as the initial cluster center points. For each data point, calculate its distance from each cluster center point and assign it to the cluster with the closest distance. Then, for each cluster, recalculate the average value of all data points within it as the new cluster center point. Repeat the above process until the cluster center point no longer changes significantly or reaches the preset number of iterations. After the clustering operation is completed, the system terminal classifies similar abnormal accident cases into one category according to the output results of the clustering algorithm to form multiple different accident sets. The cases in each accident set are similar in features and represent abnormal accidents of the same type.

[0018] After obtaining multiple accident sets, the system terminal extracts the operating status data of all corresponding abnormal accident cases for each accident set. Subsequently, the distribution of each operating status data before and after the accident is statistically analyzed, and the mean, standard deviation and other statistics before and after the accident are calculated. These statistics can help the system terminal understand the distribution and degree of change of the data. After that, the statistical changes of the same operating status data before and after the accident in different accident sets are compared, focusing on the statistics with large changes, which may have a closer relationship with the accident type. Then, based on the calculated statistics and operating status data, the Pearson correlation coefficient is used to calculate the correlation between the operating status data and between them and the accident type, and combined with the degree of change of the statistics, the operating status data that is significantly related to the accident type is identified. Further, the operating status data that is significantly related to the accident type is analyzed in time series to observe the change trend and fluctuation of the data before and after the accident. Through time series analysis, the abnormal patterns of the operating status data before the accident are identified, and these patterns indicate the occurrence of the accident. Subsequently, by comparing and analyzing the data of multiple accident sets, the change patterns of the operating status data related to specific accident types are identified. These patterns include continuous changes in a single data, combined changes between multiple data, or the occurrence of a specific sequence of events. For example, if an abnormal battery charging state (such as rapid charging or discharging) is observed, and the power also drops rapidly, this indicates that the battery has an internal fault or an abnormal external load. This combined change pattern between the charging state and the power can indicate a potential accident risk. After that, compare the cases in different accident concentrations to find out the commonalities and differences, and deeply understand the associations and differences between different accident types. Through induction and summary, a qualitative description of the impact relationship between operating status data and accident types is formed. These descriptions include thresholds of key indicators, characteristic differences between different accident types, etc. Through the above analysis process, the relationship between operating status data and accident types can be more comprehensively understood, and strong support can be provided for the subsequent establishment of the impact relationship between abnormal events and various operating status data.

[0019] Perform accident concurrent status analysis on the multiple accident sets, determine the types of concurrent accidents, construct an accident relationship tree, and determine top events and basic events; According to the influence relationship, the influence relationship of each running status data is fitted for the top event and the basic event respectively, and the influence relationship between the abnormal event and each running status data is established.

[0020] Preferably, for the analysis of multiple accident sets, the system terminal mainly performs concurrent state analysis between accidents, that is, the situation where multiple accidents occur simultaneously or successively. Specifically, the system terminal interprets the multiple accident sets in detail, including the time and location of each accident, the equipment or system involved, the consequences of the accident, etc. Then, a preliminary analysis is performed on the interpreted data to identify whether there are concurrent accidents, that is, multiple accidents occur simultaneously or successively. Subsequently, the concurrent accidents are classified according to the nature, cause and impact of the accident. For example, accidents are divided into different types such as equipment failure, operating errors, and external environmental impacts. The characteristics and laws of each type of concurrent accident are determined to provide a basis for subsequent analysis. Afterwards, each accident is used as a node, and they are connected according to the causal relationship between them to construct an accident relationship tree. In the accident relationship tree, starting from the final accident result, the top event is determined. The top event is the end point of the entire accident sequence and the main consequence of the entire accident. Then, starting from the top event, the cause event that caused the result is traced upward layer by layer to find the direct cause or precondition for the top event, that is, the basic event. These basic events are the root cause or starting point of the accident.

[0021] After determining the top events and basic events, the system terminal analyzes the impact relationship between the previously determined operating status data and the accident type, clarifies which operating status data has a significant impact on the accident type, and understands the nature and trend of these impact relationships, providing a basis for subsequent analysis of top events and basic events. Subsequently, the operating status data related to the top events are identified, which are closely related to the accident types that cause the top events in the impact relationship between the operating status data and the accident type. Then analyze the changes of these operating status data when the top events occur, including the fluctuation of values, the change of trends, etc., determine which operating status data have a direct and significant impact on the top events, and describe the specific impact relationship between them. For basic events, the same method is used to identify the operating status data related to them, and analyze the change characteristics of these operating status data when the basic events occur, to understand their contribution to the occurrence of the basic events. Then determine which operating status data has a key role in the basic events, and describe the specific impact relationship between them. After that, the impact relationship between the top events and basic events and the operating status data is comprehensively analyzed to form an overall impact relationship framework. In this framework, the causal relationship and interaction between abnormal events and various operating status data are clarified, and the specific manifestations of these influence relationships are described, so as to establish the influence relationship between abnormal events and various operating status data.

[0022] In summary, this process combines multiple steps such as accident concurrent status analysis, accident relationship tree construction, and impact relationship fitting, aiming to fully reveal the complex relationship between operating status data and accident types, and provide strong support for preventing and controlling the occurrence of accidents.

[0023] Constructing an abnormality judgment model according to the influence relationship of each operating status data; In one embodiment, the system terminal determines the influence relationship between the operating status data and different accident types through analysis. These relationships reflect the intrinsic connection between data changes and accident occurrences, and are the basis for building an abnormality judgment model. Based on these influence relationships, the system terminal analyzes the specific influence relationship between the top events and basic events and each operating status data, and constructs corresponding training data. Subsequently, the obtained training data is used to train the abnormality judgment model structure to build the required abnormality judgment model.

[0024] Furthermore, the present application provides a method for constructing an abnormality judgment model according to the influence relationship of each operating status data, and the method also includes: According to the accident relationship tree, an abnormality judgment model structure is constructed, including a basic event abnormality judgment sub-model and a top event judgment sub-model; According to the influence relationship of each running status data, basic event training data and top event training data are respectively constructed; Optionally, the system terminal uses the constructed accident relationship tree to guide the structural design of the abnormal judgment model. The accident relationship tree clearly shows the hierarchical structure and causal relationship of the accident, and provides a logical framework for the abnormal judgment of the basic event and the top event. For the basic event, the system terminal determines the operating status data directly related to the basic event according to the definition of the accident relationship tree and the basic event, and sets reasonable thresholds and judgment rules based on the influence relationship between the operating status data and the basic event. For example, when a data exceeds or falls below a specific value, the basic event abnormal judgment submodel should be judged as a basic event abnormality. Then, according to the set thresholds and rules, the structure of the basic event abnormal judgment submodel is designed. This includes conditional judgment, logical operation and other parts. For the top event, the system terminal sets the weights and priorities of different basic events according to the degree of influence of the basic events on the top event in the accident relationship tree. Then, the structure of the top event judgment submodel is initialized according to the set weights and priorities. This top event judgment submodel not only considers the data abnormalities that directly affect the top event, but also integrates the abnormal judgment results of the basic events.

[0025] In the process of building these two sub-models, the system terminal identifies the operating status data indicators that are closely related to the basic events and top events based on the influence relationship of each operating status data. Analyze the degree of influence of these key indicators on the basic events and top events, and determine their role in the event occurrence process. Subsequently, based on historical experience, a clear label is determined for each basic event to indicate whether it has occurred. Then, the label of each basic event is associated with the corresponding operating status data to form a data set containing event labels and related data. After that, based on historical experience, a clear label is determined for each top event. Because top events are often triggered by multiple basic events, the system terminal associates the relevant basic event labels and operating status data to the top event. Then, the labels of the top events, the relevant basic event labels, and the operating status data are integrated to form a comprehensive training data set, namely the top event training data.

[0026] In summary, an abnormality judgment model structure including basic event and top event judgment sub-models was constructed based on the accident relationship tree, and the corresponding training data was constructed using the influence relationship of each operating status data, laying the foundation for model training and practical application.

[0027] The basic event training data and the top event training data are used for learning respectively to obtain the basic event abnormality judgment submodel and the top event judgment submodel, and the basic event abnormality judgment submodel and the top event judgment submodel are connected according to the hierarchical relationship of the accident relationship tree to obtain the abnormality judgment model.

[0028] Optionally, the system terminal obtains two sets of training data by dividing the data, one set is the basic event training data, which contains the running status data related to the basic event and its corresponding label; the other set is the top event training data, which covers the basic event label and running status data related to the top event. Subsequently, the system terminal uses the basic event training data to train the constructed basic event abnormality judgment submodel structure. By iteratively optimizing the parameters and structure of the basic event abnormality judgment submodel, the basic event abnormality judgment submodel structure can accurately identify the abnormal state of the basic event. When the maximum number of iterations is reached, the basic event abnormality judgment submodel of the current training is output. Afterwards, the system terminal uses the top event training data to train the top event judgment submodel structure in the same way, so that the top event judgment submodel learns the complex relationship between the basic event and the top event, and can predict the occurrence of the top event according to the abnormal state of the basic event and other related features. Similarly, when the maximum number of iterations is reached, the top event judgment submodel of the current training is output. After obtaining these two submodels, the system terminal connects them according to the hierarchical relationship of the accident relationship tree. The accident relationship tree describes the causal relationship between the basic event and the top event, so the system terminal determines the connection method between the sub-models based on this relationship. The output of the basic event abnormality judgment sub-model will be used as one of the inputs of the top event judgment sub-model, so that the top event judgment sub-model can make a judgment by comprehensively considering the abnormal state of the basic event. Finally, by connecting these two sub-models, the system terminal obtains a complete abnormality judgment model. This model can monitor the operating status data in real time and predict the occurrence of basic events and top events based on the changes in the data. It not only considers the abnormal judgment of a single event, but also comprehensively considers the causal relationship between events, which improves the accuracy and reliability of the prediction. In summary, by using the basic event training data and the top event training data for learning, and connecting the sub-models according to the accident relationship tree, the abnormality judgment model was successfully constructed, providing a powerful tool for preventing and controlling accidents.

[0029] Input the operating status data collected by the monitoring device into the abnormality judgment model to perform abnormality probability analysis and output the abnormality judgment result; In one embodiment, the system terminal obtains real-time collected operating status data from the monitoring device. These data reflect the current working status of the energy storage system and are the key basis for determining whether there is an abnormality. Subsequently, these operating status data are input into the constructed abnormality judgment model. This model has learned the abnormal patterns of basic events and top events through training, and can perform fast and accurate abnormal probability analysis based on the input data. Inside the model, the data will pass through the basic event abnormality judgment submodel and the top event judgment submodel in sequence according to the hierarchical relationship of the accident relationship tree. Among them, the basic event abnormality judgment submodel will calculate the influence index of the input operating status data based on the learned knowledge and rules. The top event judgment submodel will perform weight calculations on each operating status data, as well as analyze the probability of accident occurrence, and calculate the corresponding abnormal probability. Afterwards, the abnormal judgment model will output the probability of occurrence of abnormal events calculated by the top event judgment submodel as the abnormal judgment result. This result can help the system terminal quickly understand the current state of the energy storage system, so as to take corresponding measures for risk control and prevention. In summary, by inputting the operating status data collected by the monitoring equipment into the abnormal judgment model for abnormal probability analysis, the abnormal judgment results can be quickly obtained, providing strong guarantee for the safe operation of the energy storage system.

[0030] Furthermore, the present application provides a method for obtaining the basic event abnormality judgment submodel and the top event judgment submodel, and the method further includes: A comparison matrix is ​​configured based on the influence relationship of each operating state data, wherein the comparison matrix is ​​used to characterize the importance of each state data to the occurrence of an abnormal accident; Optionally, the system terminal first converts the mutual influence relationship between each operating status data, and quantifies the mutual influence relationship between each operating status data into a specific value to facilitate the subsequent matrix construction. Subsequently, the conversion results are sorted and a comparison matrix is ​​constructed. Each row and column of this matrix represents an operating status data, and the elements in the matrix represent the relative importance of these data. These importance values ​​are determined by the conversion results. Through the comparison matrix, the system terminal can intuitively understand which status data is more important in abnormal accidents and which data has less impact. Such a matrix not only helps to deeply understand the mechanism of accident occurrence, but also provides a strong basis for subsequent abnormal detection, prediction and risk control. In summary, configuring a comparison matrix can help the system terminal comprehensively evaluate the importance of each operating status data in the occurrence of abnormal accidents, and provide strong support for improving the safety and reliability of energy storage systems.

[0031] Calculate the influence index of each running status data according to the comparison matrix, where the influence index is the sum of the matrix element values ​​of the row or column where the running status data is located; Based on the influence index and the comparison matrix, a judgment matrix is ​​established; Optionally, after constructing the comparison matrix, the system terminal calculates the influence index of each operating state data. This index is obtained by adding the matrix element values ​​of the row or column where the state data is located. The higher the influence index, the greater the importance of the state data in the overall system and the greater the contribution to the occurrence of abnormal accidents. Subsequently, the system terminal further constructs the judgment matrix based on the influence index and the comparison matrix through the judgment matrix formula. Among them, the judgment matrix formula is pre-constructed and used to calculate the judgment matrix factor and configure the judgment matrix element value. The judgment matrix is ​​constructed based on the configured judgment matrix element value, which not only contains the relative importance comparison results between the state data, but also incorporates the information of the influence index, so that the system terminal can more accurately evaluate the role and status of each state data in the occurrence of abnormal accidents. Through this process, the system terminal can not only understand the relative importance between the various operating state data, but also quantify their contribution to the occurrence of abnormal accidents. This provides a strong basis and guidance for actual safety management and risk control, helping the system terminal to more accurately identify key state data and evaluate the importance of each state data in the occurrence of abnormal accidents.

[0032] Calculate the weight of each running status data according to the judgment matrix to obtain the weight of each data factor; According to the weights and influence relationships of the data factors, the accident probability analysis is performed on the operating status data, and the probability of occurrence of abnormal events is output.

[0033] Optionally, the system terminal normalizes the judgment matrix, and then uses each element in the normalized judgment matrix to assign the weight of the corresponding operating state data. The weight reflects the relative importance of each state data in the whole. The larger the weight, the greater the influence of the state data in the occurrence of the accident. Subsequently, the system terminal combines the weights and influence relationships of each data factor to conduct an in-depth accident probability analysis on the operating state data. Specifically, for each operating state, the system terminal calculates the weighted sum of all relevant data factors. The weighted sum is obtained by multiplying the value of each factor by its corresponding weight and then adding all the products. This weighted sum reflects the potential risk of abnormal events in this state. Subsequently, the weighted sum is normalized using the maximum value and the minimum value of the weighted sum obtained in advance to obtain a normalized result between 0 and 1. Among them, the maximum value and the minimum value of the weighted sum are obtained by the system terminal through the above process in advance by iteratively calculating a large amount of historical sample data. The system terminal outputs this normalized result as the probability of abnormal events. This probability value reflects the possibility of abnormal events under the current operating state data. In summary, by calculating the weight of each operating status data and performing probabilistic analysis based on the impact relationship between them, the risk of abnormal events can be assessed more accurately, providing strong decision-making support for safety management.

[0034] Furthermore, the present application provides an influence relationship configuration comparison matrix based on the operation status data, and the method further includes: According to the influence relationship of each running status data, influence degree conversion is performed to obtain the influence degree of each running status data; Optionally, the system terminal traces back the influence relationship of each operating status data obtained, understands the mutual influence relationship between each operating status data in more detail, and determines the mutual influence strength between each operating status data. Subsequently, the system terminal assigns an influence score, i.e., influence degree, to each operating status data based on historical experience and the mutual influence strength between each operating status data. The purpose of this step is to convert the influence relationship between the original operating status data into a quantitative indicator that can reflect the degree of its influence, i.e., influence degree, so as to more accurately reflect the potential contribution of each data factor to the occurrence of abnormal events. These influence degree values ​​can serve as an important basis for the subsequent construction of the comparison matrix, helping the system terminal to better understand the operating status of the system and predict the probability of abnormal events.

[0035] Sort the relationships according to the influence of each running status data, and configure matrix element values, wherein the first element value is that the j-th element is more important than the k-th element, the second element value is that the j-th element is as important as the k-th element, and the third element value is that the j-th element is less important than the k-th element; The comparison matrix is ​​constructed based on the matrix element values.

[0036] Optionally, the system terminal compares the influence between different pairs of elements to determine which pair of elements has a more significant mutual influence. According to the comparison result, the element pairs are sorted, that is, which elements have a greater influence on other elements. Based on the sorting result of the influence, the system terminal starts to configure the element values ​​of the matrix. If the influence of the jth element on the kth element is significantly greater than the influence of the kth element on the jth element, that is, the jth element is relatively more important, the system terminal sets the corresponding matrix element to the first element value. If the influence between the jth element and the kth element is equivalent, that is, the two have similar importance, the system terminal sets the corresponding matrix element to the second element value. If the influence of the jth element on the kth element is significantly less than the influence of the kth element on the jth element, that is, the jth element is not as important as the kth element, then the system terminal sets the corresponding matrix element to the third element value. Subsequently, the system terminal constructs a complete comparison matrix based on these matrix element values ​​by judging the matrix formula. This matrix reflects the relative importance between data factors. In summary, this process is to quantify the influence of each operating status data and convert it into a matrix form so as to more intuitively represent and compare the relative importance between data factors. This is of great significance for subsequent system optimization, decision support and other aspects.

[0037] Furthermore, the present application provides a method for establishing a judgment matrix based on the influence index and the comparison matrix, and the method further includes: According to the formula: , configure the judgment matrix element values ​​and construct the judgment matrix; in, is the judgment matrix factor, To compare the minimum value of the sum of the jth row in the matrix, To compare the maximum value of the sum of the jth row in the matrix, is the influence index of the jth row, is the influence index of the kth column.

[0038] Optionally, the process of constructing a judgment matrix is ​​to calculate the element values ​​of the judgment matrix using a judgment matrix formula. This formula is based on the sum of rows and columns in the comparison matrix, and the influence index of each row and column. The formula is as follows: ; in, is the judgment matrix factor, that is, the element value of the j-th row and k-th column in the judgment matrix, indicating the importance of the j-th operating status data relative to the k-th operating status data. Compare the minimum value of the sum of the jth row in the matrix to calculate When , it is used as part of the denominator, reflecting the minimum value of the sum of the influence indexes of the elements in the jth row. The maximum value of the sum of the jth column in the comparison matrix is ​​used to calculate When , it is used as part of the denominator, reflecting the maximum value of the sum of the influence indexes of the elements in the jth column. is the sum of the influence indexes of the j-th row, that is, the sum of all elements in the j-th row in the comparison matrix, indicating the comprehensive influence of the j-th operating status data in all comparisons. is the sum of the influence index of the kth column, that is, the sum of all elements in the kth column of the comparison matrix, which represents the comprehensive influence of the kth operating status data in all comparisons. By using this formula, the system terminal can calculate multiple judgment matrix factors based on the comparison matrix. , that is, the element values ​​of the judgment matrix, so as to construct a more intuitive and easy-to-analyze judgment matrix, so as to better understand and optimize the relationship between the system operation status data.

[0039] Furthermore, the present application provides a method for calculating the weight of each operating status data according to the judgment matrix to obtain the weight of each data factor, and the method also includes: Standardizing the judgment matrix so that the sum of the elements of each row of the judgment matrix is ​​1; The standardized matrix elements are used to perform weight calculation on the operating status data to obtain the weight of each data factor.

[0040] Optionally, the system terminal performs standardization on the judgment matrix. The purpose of standardization is to make the sum of the elements in each row of the judgment matrix equal to 1, so as to ensure that each operating status data can be fairly considered when calculating the weight. The system terminal first calculates the sum of the elements in each row of the judgment matrix. Then, the element value of each row is divided by the sum of the elements of the row to achieve standardization. After completing the standardization, the system terminal uses these standardized matrix elements to match the corresponding operating status data, and then uses the value of the standardized element as the weight of the corresponding operating status data to obtain the weight of each data factor. This is because the standardization process ensures that the sum of the element values ​​in the same row is 1, so they have the property of weight distribution. By rationally using these weight values, the operating status of the energy storage system can be more accurately grasped, and the stability and efficiency of the energy storage system can be improved.

[0041] Furthermore, the present application provides inputting the operating status data collected by the monitoring device into the abnormality judgment model to perform abnormality probability analysis and output an abnormality judgment result, and the method also includes: The power, charge and discharge status, temperature, voltage, and insulation resistance impedance values ​​acquired through monitoring are input into the abnormality judgment model, and the basic event abnormality probability analysis is performed through the basic event abnormality judgment sub-model to obtain the basic abnormal events and their occurrence probabilities; Input the basic abnormal events and their occurrence probabilities into the top event judgment sub-model, perform top event occurrence probability analysis, and determine top abnormal events and their occurrence probabilities; The basic abnormal events and their occurrence probabilities, the top abnormal events and their occurrence probabilities are output as abnormality judgment results.

[0042] Optionally, the system terminal inputs the key data such as the monitored power, charge and discharge state, temperature, voltage and insulation resistance impedance value into the abnormal judgment model. This model contains the basic event abnormal judgment sub-model and the top event judgment sub-model, which will analyze these data in turn. Specifically, within the basic event abnormal judgment sub-model, the key data such as the input power, charge and discharge state, temperature, voltage and insulation resistance impedance value are subjected to matrix creation and other operations by the aforementioned method of generating the probability of occurrence of abnormal events, and the basic abnormal events and the probability of occurrence of basic abnormal events are determined. Subsequently, the basic event abnormal judgment sub-model transmits the generated basic abnormal events and the probability of occurrence of basic abnormal events to the top event judgment sub-model for further analysis; after receiving these data, the top event judgment sub-model also performs the same operation as above to determine the top abnormal events and the probability of occurrence of top abnormal events. After that, the abnormal judgment model outputs the basic abnormal events and their probability of occurrence, the top abnormal events and their probability of occurrence as the result of the entire abnormal judgment. In this way, the system terminal obtains a comprehensive and detailed abnormal analysis report, which can better understand the operating status of the energy storage system and discover potential problems in time.

[0043] Generate warning information according to the abnormality judgment result, load the abnormality judgment result into the historical record library, and update the abnormality record database.

[0044] In one embodiment, the system terminal further generates warning information based on the basic abnormal events and their occurrence probabilities in the abnormal judgment results, as well as the top abnormal events and their occurrence probabilities. These warning messages will alert users to possible abnormal events and take corresponding measures. In this way, potential energy storage system problems can be discovered and responded to in a timely manner to ensure the stable operation of the energy storage system. At the same time, the system terminal also loads these abnormal judgment results into the historical record library to update the historical data. In this way, past abnormal records can be reviewed at any time to understand the past operating status of the energy storage system. By continuously updating and improving the abnormal record database, a complete abnormal history database can be gradually formed, so that the abnormal accident case set extracted later will become more and more complete, providing strong support for the long-term stable operation of the energy storage system.

[0045] Further, the present application provides generating warning information according to the abnormal judgment result, and loading the abnormal judgment result into the historical record library, and updating the abnormal record database, and the method also includes: Obtain the warning configuration database, which includes abnormal event types, warning probability thresholds, and warning methods; The basic abnormal event, the top abnormal event and the abnormal event type are matched, and when the warning probability threshold is met, warning information is generated according to the warning method; According to the generation time of the warning information, the warning record data is generated and stored in the abnormal record database, and the abnormal record database is used to record and query the warning information.

[0046] Optionally, the system terminal establishes a connection with the early warning configuration database through the interface of the embedded platform. The early warning configuration database includes various possible abnormal event types, corresponding early warning probability thresholds, and early warning methods that should be taken when an abnormality occurs. Subsequently, the system terminal matches the basic abnormal events and top abnormal events obtained by analysis with the abnormal event types in the early warning configuration database. If the probability of occurrence of an abnormal event exceeds the preset early warning probability threshold, the system terminal will generate early warning information according to the early warning method specified in the early warning configuration database. The early warning information includes alarm sound, SMS notification, email reminder, etc., and the specific method depends on the settings in the early warning configuration. While generating the early warning information, the system terminal will also generate corresponding early warning record data according to the generation time of the early warning information, and store these data in the abnormal record database. Through this process, the system terminal can not only detect and handle abnormal events in the system in a timely manner, but also fully record the detailed information of each early warning, providing strong support for the long-term stable operation of the energy storage system.

[0047] In summary, the embodiments of the present application have at least the following technical effects: The embodiment of the present application connects the monitoring equipment through the embedded platform to obtain key operating status data such as power, charge and discharge status, temperature, voltage and insulation resistance in real time. Based on these data, a collection of abnormal accident cases is extracted from the historical record library, and the influence relationship between each operating status data is deeply analyzed. Subsequently, an abnormal judgment model is constructed using these influence relationships, which includes a basic event abnormal judgment submodel and a top event judgment submodel, which can accurately evaluate the abnormal probability of each operating status data. In the early warning process, the real-time monitoring data is input into the abnormal judgment model for abnormal probability analysis, thereby outputting the basic abnormal event and the top abnormal event and their occurrence probability. Combined with the abnormal event type, warning probability threshold and warning method in the early warning configuration database, the corresponding early warning information can be automatically generated. At the same time, the abnormal judgment result will be loaded into the historical record library for updating the abnormal record database so that the early warning information can be recorded, queried and analyzed later. In this way, the abnormal state of the energy storage system can be discovered and processed in a timely manner, and the safety and reliability of the energy storage system can be improved. These technical effects jointly solve the technical problem that the existing early warning cannot timely and accurately detect the abnormal status of the energy storage system due to insufficient depth of data analysis methods and low accuracy of the early warning model. Through the combination of real-time monitoring data and abnormal judgment models, timely early warning of abnormal status of the energy storage system can be achieved, effectively reducing the missed reporting rate of early warnings and improving the accuracy and timeliness of early warnings.

[0048] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0049] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0050] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for early warning of abnormal state of an energy storage system, characterized in that: The method is applied to an energy storage system, wherein the energy storage system comprises an embedded platform, including: Connect monitoring equipment through the embedded platform interface to obtain operating status data, including power, charge and discharge status, temperature, voltage, and insulation resistance; Connecting to a historical record library, extracting an abnormal accident case set based on the electric quantity, charge and discharge state, temperature, voltage, and insulation resistance, wherein the abnormal accident case set includes one or more abnormal operation state data of the electric quantity, charge and discharge state, temperature, voltage, and insulation resistance; Analyzing each operating status data of the abnormal accident case set to determine the influence relationship of each operating status data; Constructing an abnormality judgment model according to the influence relationship of each operating status data; Input the operating status data collected by the monitoring device into the abnormality judgment model to perform abnormality probability analysis and output the abnormality judgment result; Generate warning information according to the abnormality judgment result, load the abnormality judgment result into the historical record library, and update the abnormality record database.

2. The method according to claim 1, characterized in that Analyze each operating status data of the abnormal accident case set to determine the influence relationship of each operating status data, including: Clustering the abnormal accident case set into accident types to obtain a multi-accident set; Performing longitudinal comparison on the operation status data of the multiple accident sets respectively to obtain a change relationship of the operation status data, and fitting an influence relationship between the operation status data and the accident type based on the change relationship of the operation status data; Perform accident concurrent status analysis on the multiple accident sets, determine the types of concurrent accidents, construct an accident relationship tree, and determine top events and basic events; According to the influence relationship, the influence relationship of each running status data is fitted for the top event and the basic event respectively, and the influence relationship between the abnormal event and each running status data is established.

3. The method according to claim 2, characterized in that According to the influence relationship of each operating status data, an abnormality judgment model is constructed, including: According to the accident relationship tree, an abnormality judgment model structure is constructed, including a basic event abnormality judgment sub-model and a top event judgment sub-model; According to the influence relationship of each running status data, basic event training data and top event training data are respectively constructed; The basic event training data and the top event training data are used for learning respectively to obtain the basic event abnormality judgment submodel and the top event judgment submodel, and the basic event abnormality judgment submodel and the top event judgment submodel are connected according to the hierarchical relationship of the accident relationship tree to obtain the abnormality judgment model.

4. The method according to claim 3, characterized in that Obtaining the basic event abnormality judgment sub-model and the top event judgment sub-model includes: A comparison matrix is ​​configured based on the influence relationship of each operating state data, wherein the comparison matrix is ​​used to characterize the importance of each state data to the occurrence of an abnormal accident; Calculate the influence index of each running status data according to the comparison matrix, where the influence index is the sum of the matrix element values ​​of the row or column where the running status data is located; Based on the influence index and the comparison matrix, a judgment matrix is ​​established; Calculate the weight of each running status data according to the judgment matrix to obtain the weight of each data factor; According to the weights and influence relationships of the data factors, the accident probability analysis is performed on the operating status data, and the probability of occurrence of abnormal events is output.

5. The method according to claim 4, characterized in that The comparison matrix is ​​configured based on the influence relationship of each operation status data, including: According to the influence relationship of each running status data, influence degree conversion is performed to obtain the influence degree of each running status data; Sort the relationships according to the influence of each running status data, and configure matrix element values, wherein the first element value is that the j-th element is more important than the k-th element, the second element value is that the j-th element is as important as the k-th element, and the third element value is that the j-th element is less important than the k-th element; The comparison matrix is ​​constructed based on the matrix element values.

6. The method according to claim 5, characterized in that Based on the influence index and comparison matrix, a judgment matrix is ​​established, including: According to the formula: , configure the judgment matrix element values ​​and construct the judgment matrix; in, is the judgment matrix factor, To compare the minimum value of the sum of the jth row in the matrix, To compare the maximum value of the sum of the jth row in the matrix, is the influence index of the jth row, is the influence index of the kth column.

7. The method according to claim 4, characterized in that The weight of each operating status data is calculated according to the judgment matrix to obtain the weight of each data factor, including: Standardizing the judgment matrix so that the sum of the elements of each row of the judgment matrix is ​​1; The standardized matrix elements are used to perform weight calculation on the operating status data to obtain the weight of each data factor.

8. The method according to claim 4, characterized in that The operation status data collected by the monitoring device is input into the abnormality judgment model to perform abnormality probability analysis, and the abnormality judgment result is output, including: The power, charge and discharge status, temperature, voltage, and insulation resistance impedance values ​​acquired through monitoring are input into the abnormality judgment model, and the basic event abnormality probability analysis is performed through the basic event abnormality judgment sub-model to obtain the basic abnormal events and their occurrence probabilities; Input the basic abnormal events and their occurrence probabilities into the top event judgment sub-model, perform top event occurrence probability analysis, and determine top abnormal events and their occurrence probabilities; The basic abnormal events and their occurrence probabilities, the top abnormal events and their occurrence probabilities are output as abnormality judgment results.

9. The method according to claim 8, characterized in that Generating warning information according to the abnormality judgment result, and loading the abnormality judgment result into the historical record database, and updating the abnormality record database, including: Obtain the warning configuration database, which includes abnormal event types, warning probability thresholds, and warning methods; The basic abnormal event, the top abnormal event and the abnormal event type are matched, and when the warning probability threshold is met, warning information is generated according to the warning method; According to the generation time of the warning information, the warning record data is generated and stored in the abnormal record database, and the abnormal record database is used to record and query the warning information.

Images