Distributed energy storage power station fault diagnosis system, method and storage medium

Abstract

The present invention discloses a distributed energy storage power station fault diagnosis system, method and storage medium, which relate to the field of energy storage technology and include the following contents: acquiring historical monitoring data and real-time monitoring data of the energy storage power station; dividing related data packets through correlation analysis; digitally processing the related data packets to obtain a correlation function group; solving the intersection of the correlation functions in the correlation function group to obtain the intersection coordinate value, and calculating the distance value between the intersection and the coordinate origin based on the intersection coordinate value; determining the threshold range of the distance value based on the distance value obtained after processing the historical monitoring data, and analyzing the real-time monitoring data in the same steps to obtain the distance value to be determined; determining whether to diagnose the fault by judging whether the distance value to be determined is within the distance value threshold range, thereby avoiding fault omissions caused by non-complete regularity changes within the allowable error range of the monitoring data, and making the fault diagnosis forward-looking.

Description

Technical Field

[0001] The present invention relates to the field of energy storage technology, and in particular to a distributed energy storage power station fault diagnosis system, method and storage medium. Background Art

[0002] Distributed energy storage power stations are distributed and close to users or demand sides. They store electrical energy and release it when needed to improve the flexibility and reliability of the power system.

[0003] Existing distributed energy storage fault diagnosis systems usually use set parameter thresholds. When a parameter of the energy storage system exceeds the set parameter threshold, it is determined to be a fault;

[0004] For example, a Chinese invention patent (CN118884257A) discloses a “fault diagnosis method for energy storage grids with distributed power supply access”, which specifically discloses “preliminary diagnosis of energy storage battery packs based on electrochemical characteristic diagnosis models and electromagnetic characteristic diagnosis models to determine whether the energy storage battery packs have faults, including the following steps: setting an electrochemical characteristic diagnosis threshold and an electromagnetic characteristic diagnosis threshold based on historical status data; when the electrochemical characteristic diagnosis value is less than or equal to the electrochemical characteristic diagnosis threshold, and the electromagnetic characteristic diagnosis value is less than or equal to the electromagnetic characteristic diagnosis threshold, it is determined that the energy storage battery pack has no fault; when the electrochemical characteristic diagnosis value is less than or equal to the electrochemical characteristic diagnosis threshold, the electromagnetic characteristic diagnosis value is less than or equal to the electromagnetic characteristic diagnosis threshold, the energy storage battery pack is determined to have no fault; when the electrochemical characteristic diagnosis value is less than or equal to the electromagnetic characteristic diagnosis threshold, the energy storage battery pack is determined to have no fault. When the value is less than or equal to the electrochemical characteristic diagnosis threshold, and the electromagnetic characteristic diagnosis value is greater than the electromagnetic characteristic diagnosis threshold, it is judged that the electromagnetic field strength is abnormal and the energy storage battery pack has no fault; when the electrochemical characteristic diagnosis value is greater than the electrochemical characteristic diagnosis threshold, and the electromagnetic characteristic diagnosis value is greater than the electromagnetic characteristic diagnosis threshold, it is judged that multiple faults of charge state estimation error, internal resistance increase, temperature abnormality and electromagnetic field strength abnormality have occurred; when the electrochemical characteristic diagnosis value is greater than the electrochemical characteristic diagnosis threshold, and the electromagnetic characteristic diagnosis value is less than or equal to the electromagnetic characteristic diagnosis threshold, it is judged that multiple faults of charge state estimation error, internal resistance increase and temperature abnormality have occurred.

[0005] In the above technical solution, if the monitoring data of the energy storage system is abnormal due to a value lower than the set threshold, although it is within the threshold range, the long-term small-scale abnormality will cause the energy storage system fault to slowly expand, making it impossible to identify the fault in real time and accurately, thereby exacerbating the fault and affecting the safety of the entire energy storage power station.

[0006] Therefore, people urgently need a real-time, accurate, and forward-looking distributed energy storage power station fault diagnosis system to solve the above technical problems. Summary of the Invention

[0007] The object of the present invention is to provide a distributed energy storage power station fault diagnosis system, method and storage medium to solve the problems raised in the prior art.

[0008] To achieve the above-mentioned object, the present invention provides the following technical solutions: a method for diagnosing faults in a distributed energy storage power station, which obtains historical monitoring data of the energy storage power station and receives real-time monitoring data;

[0009] According to the monitoring data attributes, the historical monitoring data is divided into related data packets DP, and the real-time monitoring data is divided into related data packets. The purpose is to facilitate the comparison and analysis of real-time monitoring data with historical monitoring data with the same attributes to ensure the reliability of fault diagnosis;

[0010] A plane rectangular coordinate system is established, and the historical monitoring data and real-time monitoring data in the same correlation data package are digitally processed to obtain the correlation function group R and the correlation function group R respectively. ’ ;

[0011] The historical monitoring data of a correlation data packet is processed digitally to obtain a set of correlation function groups R, and the real-time monitoring data of a correlation data packet is processed digitally to obtain a set of correlation function groups R ’ ;

[0012] Solve the same correlation function r of any two adjacent time stamps in the correlation function group R to obtain the intersection coordinate value CP;

[0013] If the same correlation function r of any two adjacent timestamps exists completely parallel in the plane rectangular coordinate system, then there is no intersection coordinate value. In this case, the historical monitoring data corresponding to the correlation function r of the latter timestamp is discarded;

[0014] Because in the actual analysis process, if the above situation exists, the historical monitoring data will not be able to serve as the comparison basis for the real-time monitoring data analysis because there is no abnormal situation;

[0015] Calculate the distance value L between the intersection coordinate value CP and the coordinate origin, because the intersection coordinate value of the same correlation function r of two adjacent time stamps reflects the non-complete regularity change of the historical monitoring data of the two adjacent time stamps, that is, the error change within the allowable range, and solve the distance value L between the intersection coordinate value and the coordinate origin, which can intuitively reflect whether this non-complete regularity change is within the allowable error range, and based on the maximum distance L of the same correlation function r in the historical monitoring data max and the minimum distance L min Determine the distance range of the correlation function r [L min , L max ], in the historical monitoring data, no faults were found in the energy storage power station. This means that all irregular changes in the historical monitoring data are within the allowable error range, that is, the threshold range can be set based on the analysis results of the historical monitoring data;

[0016] The correlation function r and the correlation function r of the adjacent time stamps of the real-time monitoring data are ’ Solve between them and get the intersection coordinate value CP ’ , and calculate the intersection coordinate value CP ’ The distance L from the origin of the coordinate system ’ ;

[0017] Determine the distance value L ’ Is it within the distance range [L min , L max ] If it is within the distance range, continue to analyze the received real-time monitoring data; if it is not within the distance range, diagnose the fault and issue an early warning. When it is not within the distance range, it indicates that the real-time monitoring data may still be within the allowable error range, but it has deviated from the corresponding historical monitoring data trajectory. If this continues for a long time, it will cause a fault to occur. Therefore, it is necessary to diagnose it as a fault and issue an early warning to facilitate early maintenance.

[0018] According to the above technical solution, the number of historical monitoring data with the same timestamp in the associated data packet DP is n. A regular n-gon is established based on the number n of historical monitoring data. After the real-time monitoring data is divided into its associated data packets, the associated data packets corresponding to the historical monitoring data with the same attributes and quantity are found through comparison and analysis. The purpose is to ensure that when visually positioning the historical monitoring data or the real-time monitoring data, it is carried out under a unified standard. If the attributes or quantities are different, the probability of abnormalities in the analysis and comparison of the historical monitoring data and the real-time monitoring data will increase, which will also lead to abnormal fault diagnosis.

[0019] According to the above technical solution, when digitally processing the historical monitoring data and the real-time monitoring data in the same associated data packet, the following steps are included:

[0020] Step 1. Establish a plane rectangular coordinate system with the center of the regular n-gon as the coordinate origin;

[0021] Step 2: Establish an extension line from the coordinate origin to any vertex of the regular n-gon as the attribute line of the monitoring data;

[0022] Step 3: Position the historical monitoring data and real-time monitoring data on the corresponding attribute lines according to the monitoring data attributes and monitoring data values;

[0023] Step 4. Connect two monitoring data with different attributes of any set of monitoring data to obtain a function segment. Extend the two ends of the function segment infinitely to obtain a correlation function. Then a set of monitoring data will obtain n*(n-1) / 2 correlation functions to form a correlation function group, and obtain a set of correlation function group R of historical monitoring data and a set of correlation function group R of real-time monitoring data.’ .

[0024] According to the above technical solution, in the analysis of historical monitoring data, the same correlation function of any two adjacent timestamps is expressed as r (x)-T and r (x)-T+t , where T represents the timestamp of historical monitoring data collection, and t represents the time interval for collecting historical monitoring data;

[0025] Correlation function r (x)-T and the correlation function r (x)-T+t Solve and get the intersection coordinate value CP=(x j ,y j );

[0026] Calculate the intersection coordinates CP=(x j ,y j ) and the coordinate origin (0,0) is the distance L. The distance L is calculated using the formula [(x i -0) 2 +(y i -0) 2 ] 1 / 2 Calculate and obtain the same correlation function distance value set L of any two adjacent time stamps in the historical monitoring data 集 , extract L 集 The maximum value L in max and the minimum value L min , [L min ,L max ] as the distance value range threshold of the correlation function.

[0027] According to the above technical solution, determine the associated data packet DP of the real-time monitoring data that needs to be analyzed k , where k indicates that the real-time monitoring data belongs to the kth associated data packet, from the associated data packet DP k Extracting historical monitoring data adjacent to the timestamp of the real-time monitoring data to be analyzed;

[0028] Determine the correlation function group of the historical monitoring data as R k , determine the correlation function group of real-time monitoring data to be analyzed as R k ’ ;

[0029] Among them, the correlation function group R k ={r k1 ,r k2 ,r k3 ,…,r kn}, associated function group R k ’ ={rk1 ’ ,r k2 ’ ,r k3 ’ ,…,r kn ’}, where n represents n correlation functions; for example, if n=10, it means that the real-time monitoring data contains 5 monitoring data with different attributes;

[0030] For the correlation function group R k and the associated function group R k ’ Solve the same correlation function in ;

[0031] Get the coordinates of the intersection point of any same correlation function (x k-a ,y k-a ), where a represents the correlation function group R k and the associated function group R k ’ The a-th correlation function in ;

[0032] The intersection coordinates (x k-a ,y k-a ) and the origin of coordinates (0,0) to calculate the distance value. The distance value L is calculated using the formula [(x k-a -0) 2 +(y k-a -0) 2 ] 1 / 2 Calculate and get the distance value L k-a , and finally form the associated data packet DP k The set L of distance values 集 ={L k-a ,L k-b ,L k-c ,…,L k-m}, where m represents the final calculated m distance values;

[0033] L 集 Perform range analysis on the distance value in and determine L 集 Does the distance value in [L min ,L max ], if L 集 If the distance value in the range is not within the distance range, a fault is diagnosed and an early warning is issued.

[0034] Through the above technical solution, it can be found that the present application does not directly determine whether there is a fault in the energy storage power station by setting a threshold value of the monitoring data, but analyzes the monitoring data step by step through digital processing after performing correlation analysis. Through the solution of the present application, it is possible to diagnose the fault when the monitoring data has non-complete regularity anomalies, that is, the monitoring data is within the allowable error range, but long-term non-complete regularity anomalies will eventually lead to a fault. Therefore, the above technical solution of the present application is more forward-looking and avoids safety accidents in the energy storage power station caused by a fault.

[0035] A distributed energy storage power station fault diagnosis system, comprising a data acquisition module, a data preprocessing module, a data analysis module, and a fault diagnosis module;

[0036] The data acquisition module is used to acquire historical monitoring data of the energy storage power station and receive real-time monitoring data; the data preprocessing module is used to associate historical monitoring data and real-time monitoring data and perform data preprocessing to obtain several association function groups; the data analysis module is used to calculate and analyze the data processed by the data preprocessing module as a basis for fault diagnosis; and the fault diagnosis module is used to diagnose faults of the energy storage power station based on the analysis results of the data analysis module.

[0037] According to the above technical solution, the data acquisition module includes a historical monitoring data acquisition unit and a real-time monitoring data receiving unit;

[0038] The historical monitoring data acquisition unit is used to acquire historical monitoring data from the database; the real-time monitoring data receiving unit is used to receive real-time monitoring data of the energy storage power station, and after the fault diagnosis is completed, store the received real-time monitoring data into the database as historical monitoring data.

[0039] According to the above technical solution, the data preprocessing module includes a data association unit, a visualization processing unit, a coordinate system establishment unit and a function generation unit;

[0040] The data association unit associates and binds the historical monitoring data and the real-time monitoring data based on the monitoring data attributes to obtain an associated data packet; the visualization processing unit is used to visualize the historical monitoring data and the real-time monitoring data in the associated data packet, and establish a polygon based on the number of data attributes in the associated data packet; the coordinate system establishment unit is used to establish a plane rectangular coordinate system on the polygon processed by the visualization processing unit; the function generation unit is used to connect different attribute data of the same timestamp in the historical monitoring data or the real-time monitoring data in the plane rectangular coordinate system to obtain a line segment function, and infinitely extend the two ends of the line segment function to obtain an associated function. The associated functions of the same timestamp constitute an associated function group.

[0041] According to the above technical solution, the data analysis module includes a function solving unit, a distance value calculation unit and a range threshold determination unit;

[0042] The function solving unit is used to solve the same correlation function of different time stamps generated by the historical monitoring data in the correlation data packet to obtain the intersection coordinate value CP, and is also used to solve the same correlation function of adjacent time stamps generated by the historical monitoring data and the real-time monitoring data in the same correlation data packet to obtain the intersection coordinate value CP ’ The distance value calculation unit obtains the intersection coordinate values ​​CP and CP ’ The distance value between the coordinate origin is calculated to obtain the distance value L and the distance value L'; the range threshold determination unit is based on the maximum distance L of the same correlation function in the historical monitoring data. max and the minimum distance L min Determine the distance range of the correlation function r [L min , L max ];

[0043] The fault diagnosis module is used to determine the distance value L ’ Is it within the distance range [L min , L max ] If it is, there is no fault; if not, the energy storage power station fault is diagnosed and an early warning is issued.

[0044] A readable storage medium stores a computer program, which, when executed on a processor, implements a method for diagnosing faults in a distributed energy storage power station.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] The present invention abandons the traditional method of directly setting thresholds and comparing monitoring data with set thresholds to determine whether the energy storage power station is faulty. Instead, it adopts digital and visual analysis of the monitoring data. Therefore, even if the monitoring data is within the threshold range, if non-completely regular changes occur, it can be diagnosed as a fault. Moreover, in the actual data monitoring process of the energy storage power station, the long-term existence of such non-completely regular changes will lead to the occurrence of faults. Therefore, the above-mentioned fault diagnosis method of the present invention has a certain degree of foresight and can perform fault diagnosis and maintenance before the fault occurs and when there are safety hazards, thereby avoiding the occurrence of faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 Schematic diagram of the logic flow of the distributed energy storage power station fault diagnosis method of the present invention.

[0048] Figure 2This is a diagram of a visualized correlation function of the second embodiment of the distributed energy storage power station fault diagnosis method of the present invention. DETAILED DESCRIPTION

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0050] Example 1:

[0051] like Figure 1 As shown, the present invention provides a distributed energy storage power station fault diagnosis method, comprising the following steps:

[0052] S1. Obtain historical monitoring data of the energy storage power station and receive real-time monitoring data;

[0053] S2. Relevance-based grouping of historical monitoring data based on monitoring data attributes to obtain associated data packets DP. For example, the current data, voltage data, temperature data, charging efficiency, and discharge efficiency of energy storage batteries in an energy storage power station are related to each other. Therefore, these five data can be grouped into the same associated data packet. Real-time monitoring data is also grouped into associated data packets. This facilitates comparison and analysis of real-time monitoring data with historical monitoring data of the same attributes, ensuring the reliability of fault diagnosis.

[0054] Specifically, the number of historical monitoring data with the same timestamp in the associated data packet DP is n, and a regular n-gon is established based on the number of historical monitoring data n. For example, if the number of historical monitoring data in the third associated data packet DP3 is 5, a regular pentagon is established. It is emphasized here that the number of historical monitoring data must be the same timestamp, because only at the same timestamp can it be compared and analyzed with the real-time monitoring data. If the combination of historical monitoring data with different timestamps is compared with the real-time monitoring data, the comparison value of this application will be lost. After the real-time monitoring data is divided into its associated data packets, the associated data packets corresponding to the historical monitoring data with the same attributes and quantity are found through comparison and analysis. The purpose is to ensure that when visually positioning the historical monitoring data or the real-time monitoring data, it is carried out under a unified standard. If the attributes or quantities are different, the probability of abnormal analysis and comparison of the historical monitoring data and the real-time monitoring data will increase, which will also lead to abnormal fault diagnosis.

[0055] S3. Establish a plane rectangular coordinate system and digitally process the historical monitoring data and real-time monitoring data in the same correlation data package to obtain the correlation function group R and the correlation function group R respectively.’ ;

[0056] The historical monitoring data of a correlation data packet is processed digitally to obtain a set of correlation function groups R, and the real-time monitoring data of a correlation data packet is processed digitally to obtain a set of correlation function groups R ’ ;

[0057] Specifically, when digitally processing the historical monitoring data and the real-time monitoring data in the same associated data packet, the following steps are included:

[0058] Step 1. Establish a plane rectangular coordinate system with the center of the regular n-gon as the coordinate origin;

[0059] Step 2: Establish an extension line from the coordinate origin to any vertex of the regular n-gon as the attribute line of the monitoring data;

[0060] Step 3: Position the historical monitoring data and real-time monitoring data on the corresponding attribute lines according to the monitoring data attributes and monitoring data values;

[0061] Step 4. Connect two monitoring data with different attributes of any set of monitoring data to obtain a function segment. Extend the two ends of the function segment infinitely to obtain a correlation function. Then a set of monitoring data will obtain n*(n-1) / 2 correlation functions to form a correlation function group, and obtain a set of correlation function group R of historical monitoring data and a set of correlation function group R of real-time monitoring data. ’ .

[0062] In this embodiment, the number of monitoring data of the third group of historical monitoring data and real-time monitoring data is 5, so the correlation function group R and the correlation function group R ’ They are composed of 10 correlation functions, namely R={r1,r2,r3,…,r 10}, R ’ ={r1 ’ ,r2 ’ ,r3 ’ ,…,r 10 ’}, the correlation functions in the correlation function group R and the correlation function group R' are all correlation functions generated at the same timestamp.

[0063] S4. Solve the same correlation function r of any two adjacent time stamps in the correlation function group R to obtain the intersection coordinate value CP;

[0064] Specifically, in the analysis of historical monitoring data, the same correlation function of any two adjacent timestamps is expressed as r (x)-T and r (x)-T+t , where T represents the timestamp of historical monitoring data collection, and t represents the time interval for collecting historical monitoring data;

[0065] For example: (x)-T represents the correlation function generated by the current-temperature data collected at time 12:10:10, r (x)-T+t represents the correlation function generated by the current-temperature data collected at time 12:10:12, where t = 2s;

[0066] Correlation function r (x)-T and the correlation function r (x)-T+t Solve and get the intersection coordinate value CP=(x j ,y j );

[0067] If the same correlation function r of any two adjacent timestamps exists completely parallel in the plane rectangular coordinate system, then there is no intersection coordinate value. In this case, the historical monitoring data corresponding to the correlation function r of the latter timestamp is discarded;

[0068] Because in the actual analysis process, if the above situation exists, the historical monitoring data will not be able to serve as the comparison basis for the real-time monitoring data analysis because there is no abnormal situation;

[0069] S5. Calculate the distance value L between the intersection coordinate value CP and the coordinate origin, because the intersection coordinate value of the same correlation function r of two adjacent time stamps reflects the non-complete regularity change of the historical monitoring data of the two adjacent time stamps. Non-complete regularity change means that the change of historical monitoring data is irregular, not gradually rising or falling, but sudden, and this sudden change is within the normal threshold range, that is, the error change within the allowable range. Solving the distance value L between the intersection coordinate value and the coordinate origin can intuitively reflect whether this non-complete regularity change is within the allowable error range, and based on the maximum distance L of the same correlation function r in the historical monitoring data max and the minimum distance L min Determine the distance range of the correlation function r [L min , L max ], in the historical monitoring data, no fault was determined in the energy storage power station. This indicates that all irregular changes in the historical monitoring data are within the allowable error range. In other words, the threshold range can be set based on the analysis results of the historical monitoring data. However, in the traditional abnormality judgment process, when the abnormal change does not exceed the set threshold, no warning will be generated. However, long-term or repeated abnormal changes can also lead to faults. Therefore, it is particularly important to consider this situation.

[0070] Specifically, calculate the intersection coordinate value CP=(x j ,y j) and the coordinate origin (0,0) is the distance L. The distance L is calculated using the formula [(x i -0) 2 +(y i -0) 2 ] 1 / 2 Calculate and obtain the same correlation function distance value set L of any two adjacent time stamps in the historical monitoring data 集 , extract L 集 The maximum value L in max and the minimum value L min , [L min ,L max ] as the distance value range threshold of the correlation function.

[0071] S6, the correlation function r and the correlation function r adjacent to the real-time monitoring data ’ Solve between them and get the intersection coordinate value CP ’ For example, if the current-temperature monitoring data is collected from the energy storage power station every 2 seconds, and the timestamp of the current-temperature real-time monitoring data is 12:02:02, then the correlation function r corresponding to the current-temperature historical monitoring data with a timestamp of 12:02:00 in the historical monitoring data is used as the correlation function r corresponding to the current-temperature real-time monitoring data with a timestamp of 12:02:02. ’ The solution object and calculate the intersection coordinate value CP ’ The distance L from the origin of the coordinate system ’ ;

[0072] Specifically, determine the associated data packet DP of the real-time monitoring data that needs to be analyzed k , where k indicates that the real-time monitoring data belongs to the kth associated data packet, from the associated data packet DP k Extracting historical monitoring data adjacent to the timestamp of the real-time monitoring data to be analyzed;

[0073] For example: Associated Data Packet DP k The timestamp of the real-time monitoring data in the data packet is 12:25:32, and the collection interval of the monitoring data is 2s. k The timestamp of the historical monitoring data extracted is 12:25:30;

[0074] Determine the correlation function group of the historical monitoring data as R k , determine the correlation function group of real-time monitoring data to be analyzed as R k ’ ;

[0075] Among them, the correlation function group R k ={rk1 ,r k2 ,r k3 ,…,r kn}, associated function group R k ’ ={r k1 ’ ,r k2 ’ ,r k3 ’ ,…,r kn ’}, where n represents n correlation functions; for example, if n=10, it means that the real-time monitoring data contains 5 monitoring data with different attributes;

[0076] For the correlation function group R k and the associated function group R k ’ Solve the same correlation function in ;

[0077] Get the coordinates of the intersection point of any same correlation function (x k-a ,y k-a ), where a represents the correlation function group R k and the associated function group R k ’ The a-th correlation function in ;

[0078] The intersection coordinates (x k-a ,y k-a ) and the origin of coordinates (0,0) to calculate the distance value. The distance value L is calculated using the formula [(x k-a -0) 2 +(y k-a -0) 2 ] 1 / 2 Calculate and get the distance value L k-a , and finally form the associated data packet DP k The set L of distance values 集 ={L k-a ,L k-b ,L k-c ,…,L k-m}, where m represents the final calculated m distance values;

[0079] S7. Determine distance value L ’ Is it within the distance range [L min , L max] If it is within the distance range, continue to analyze the received real-time monitoring data; if it is not within the distance range, diagnose the fault and issue an early warning. When it is not within the distance range, it indicates that the real-time monitoring data may still be within the allowable error range, but it has deviated from the corresponding historical monitoring data trajectory. If this continues for a long time, it will cause a fault to occur. Therefore, it is necessary to diagnose it as a fault and issue an early warning to facilitate early maintenance.

[0080] This application judges abnormal situations by the distance value between the intersection coordinate value and the origin. The reason is that: when the change in a set of adjacent monitoring data falls within the threshold range, no warning will be generated. However, during the digital processing process, this application converts the monitoring data into the form of an extension function. On an extension line, if the monitoring data shows non-completely regular changes, that is, mutation, then there must be an intersection between the extension functions corresponding to the correlation function. When the mutation change is greater, the extension function of the correlation function will inevitably have a larger offset, and then the distance value between it and the coordinate origin will inevitably increase.

[0081] Specifically, L 集 Perform range analysis on the distance value in and determine L 集 Does the distance value in [L min ,L max ], if L 集 If the distance value in the range is not within the distance range, a fault is diagnosed and an early warning is issued.

[0082] Through the above technical solution, it can be found that the present application does not directly determine whether there is a fault in the energy storage power station by setting a threshold value of the monitoring data, but analyzes the monitoring data step by step through digital processing after performing correlation analysis. Through the solution of the present application, it is possible to diagnose the fault when the monitoring data has non-complete regularity anomalies, that is, the monitoring data is within the allowable error range, but long-term non-complete regularity anomalies will eventually lead to a fault. Therefore, the above technical solution of the present application is more forward-looking and avoids safety accidents in the energy storage power station caused by a fault.

[0083] Example 2:

[0084] like Figure 2 As shown, the data attributes in the associated data packet are: current, voltage, temperature, charging efficiency and discharging efficiency;

[0085] Through the analysis of historical monitoring data, we know that the distance range value is [2.16,8.52];

[0086] The timestamp of the historical monitoring data is 12:32:18, and the generated correlation function group is R={r1,r2,r3,…,r 10};

[0087] The timestamp of the real-time monitoring data is 12:32:20, and the generated correlation function group is R ’ ={r1 ’ ,r2 ’ ,r3 ’ ,…,r 10 ’};

[0088] Solve the intersection coordinates of the same correlation function in the correlation function group R and the correlation function group R' to obtain the set of intersection coordinates CP 集 ’ ={cp1 ’ ,cp2 ’ ,cp3 ’ ,…,cp 10 ’};

[0089] The intersection coordinate value set CP 集 ’ Calculate the distance values ​​between each coordinate origin and obtain a set of distance values:

[0090] L 集 ’ ={3.25,5.58,5.83,2.58,4.32,7.65,10.02,5.65,6.11,4.69};

[0091] L 集 ’ By comparing the distance value in with the distance range value [2.16,8.52], it can be found that the distance value 10.02 does not belong to the distance range value, so a fault is diagnosed and an early warning is issued.

[0092] Example 3:

[0093] A readable storage medium stores a computer program, which, when executed on a processor, implements a method for diagnosing faults in a distributed energy storage power station.

[0094] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A method for diagnosing faults in a distributed energy storage power station, characterized by: Obtain historical monitoring data of energy storage power plants and receive real-time monitoring data; According to the monitoring data attributes, the historical monitoring data is divided into related data packets DP, and the real-time monitoring data is divided into related data packets; A plane rectangular coordinate system is established, and the historical monitoring data and real-time monitoring data in the same correlation data package are digitally processed to obtain the correlation function group R and the correlation function group R respectively. ’ ; Solve the same correlation function r of any two adjacent time stamps in the correlation function group R to obtain the intersection coordinate value CP; Calculate the distance L between the intersection coordinate value CP and the coordinate origin, and use the maximum distance L of the same correlation function r in the historical monitoring data max and the minimum distance L min Determine the distance range of the correlation function r [L min , L max ]; The correlation function r and the correlation function r of the adjacent time stamps of the real-time monitoring data are ’ Solve between them and get the intersection coordinate value CP ’ , and calculate the intersection coordinate value CP ’ The distance L from the origin of the coordinate system ’ ; Determine the distance value L ’ Is it within the distance range [L min , L max If it is within the distance range, continue to analyze the received real-time monitoring data; if it is not within the distance range, diagnose the fault and issue an early warning; The number of historical monitoring data with the same timestamp in the associated data packet DP is n. A regular n-gon is established based on the number n of historical monitoring data. After the real-time monitoring data is divided into associated data packets, the associated data packets corresponding to the historical monitoring data with the same attributes and quantity are found through comparison and analysis. When digitally processing the historical monitoring data and the real-time monitoring data in the same associated data packet, the following steps are included: Step 1. Establish a plane rectangular coordinate system with the center of the regular n-gon as the coordinate origin; Step 2: Establish an extension line from the coordinate origin to any vertex of the regular n-gon as the attribute line of the monitoring data; Step 3: Position the historical monitoring data and real-time monitoring data on the corresponding attribute lines according to the monitoring data attributes and monitoring data values; Step 4. Connect two monitoring data with different attributes of any set of monitoring data to obtain a function segment. Extend the two ends of the function segment infinitely to obtain a correlation function. Then a set of monitoring data will obtain n*(n-1) / 2 correlation functions to form a correlation function group, and obtain a set of correlation function group R of historical monitoring data and a set of correlation function group R of real-time monitoring data. ’ ; Determine the associated data packets DP of the real-time monitoring data that need to be analyzed k , where k indicates that the real-time monitoring data belongs to the kth associated data packet, from the associated data packet DP k Extracting historical monitoring data adjacent to the timestamp of the real-time monitoring data to be analyzed; Determine the correlation function group of the historical monitoring data as R k , determine the correlation function group of real-time monitoring data to be analyzed as R k ’ ; For the correlation function group R k and the associated function group R k ’ Solve the same correlation function in ; Get the coordinates of the intersection point of any same correlation function (x k-a ,y k-a ), where a represents the correlation function group R k and the associated function group R k ’ The a-th correlation function in ; The intersection coordinates (x k-a ,y k-a ) and the coordinate origin (0,0) to calculate the distance value and obtain the distance value L k-a , and finally form the associated data packet DP k The set L of distance values 集 ={L k-a ,L k-b ,L k-c ,…,L k-m }, where m represents the final calculated m distance values; L 集 Perform range analysis on the distance value in and determine L 集 Does the distance value in [L min ,L max ], if L 集 If the distance value in the range is not within the distance range, a fault is diagnosed and an early warning is issued.

2. The distributed energy storage power station fault diagnosis method according to claim 1, characterized in that: In the analysis of historical monitoring data, the same correlation function of any two adjacent timestamps is expressed as r (x)-T and r (x)-T+t , where T represents the timestamp of historical monitoring data collection, and t represents the time interval for collecting historical monitoring data; Correlation function r (x)-T and the correlation function r (x)-T+t Solve and get the intersection coordinate value CP=(x j ,y j ); Calculate the intersection coordinates CP=(x j ,y j ) and the coordinate origin (0,0), and obtain the same correlation function distance value set L of any two adjacent timestamps in the historical monitoring data 集 , extract L 集 The maximum value L in max and the minimum value L min , [L min ,L max ] as the distance value range threshold of the correlation function.

3. A distributed energy storage power station fault diagnosis system for executing the distributed energy storage power station fault diagnosis method according to any one of claims 1 to 2, characterized in that: The diagnostic system includes a data acquisition module, a data preprocessing module, a data analysis module and a fault diagnosis module; The data acquisition module is used to acquire historical monitoring data of the energy storage power station and receive real-time monitoring data; the data preprocessing module is used to associate historical monitoring data and real-time monitoring data and perform data preprocessing to obtain several association function groups; the data analysis module is used to calculate and analyze the data processed by the data preprocessing module as a basis for fault diagnosis; and the fault diagnosis module is used to diagnose faults of the energy storage power station based on the analysis results of the data analysis module.

4. The distributed energy storage power station fault diagnosis system according to claim 3, characterized in that: The data acquisition module includes a historical monitoring data acquisition unit and a real-time monitoring data receiving unit; The historical monitoring data acquisition unit is used to acquire historical monitoring data from the database; the real-time monitoring data receiving unit is used to receive real-time monitoring data of the energy storage power station, and after the fault diagnosis is completed, store the received real-time monitoring data into the database as historical monitoring data.

5. The distributed energy storage power station fault diagnosis system according to claim 4, characterized in that: The data preprocessing module includes a data association unit, a visualization processing unit, a coordinate system establishment unit and a function generation unit; The data association unit associates and binds the historical monitoring data and the real-time monitoring data based on the monitoring data attributes to obtain an associated data packet; the visualization processing unit is used to visualize the historical monitoring data and the real-time monitoring data in the associated data packet, and establish a polygon based on the number of data attributes in the associated data packet; the coordinate system establishment unit is used to establish a plane rectangular coordinate system on the polygon processed by the visualization processing unit; the function generation unit is used to connect different attribute data of the same timestamp in the historical monitoring data or the real-time monitoring data in the plane rectangular coordinate system to obtain a line segment function, and infinitely extend the two ends of the line segment function to obtain an associated function. The associated functions of the same timestamp constitute an associated function group.

6. The distributed energy storage power station fault diagnosis system according to claim 4, characterized in that: The data analysis module includes a function solving unit, a distance value calculating unit and a range threshold determining unit; The function solving unit is used to solve the same correlation function of different time stamps generated by the historical monitoring data in the correlation data packet to obtain the intersection coordinate value CP, and is also used to solve the same correlation function of adjacent time stamps generated by the historical monitoring data and the real-time monitoring data in the same correlation data packet to obtain the intersection coordinate value CP ’ The distance value calculation unit obtains the intersection coordinate values ​​CP and CP ’ The distance value between the coordinate origin is calculated to obtain the distance value L and the distance value L'; the range threshold determination unit is based on the maximum distance L of the same correlation function in the historical monitoring data. max and the minimum distance L min Determine the distance range of the correlation function r [L min , L max ]; The fault diagnosis module is used to determine the distance value L ’ Is it within the distance range [L min , L max ] If it is, there is no fault; if not, the energy storage power station fault is diagnosed and an early warning is issued.

7. A readable storage medium, characterized in that: It stores a computer program, which, when executed on a processor, implements the distributed energy storage power station fault diagnosis method according to any one of claims 1 to 2.

Images