A new energy vehicle charging station abnormality monitoring method and system

Abstract

The present invention discloses a method and system for monitoring abnormalities in a new energy vehicle charging station. The method includes: collecting voltage data of each charging pile measurement point of the new energy vehicle charging station, obtaining voltage fluctuation state characteristic values ​​of each charging pile measurement point and each charging pile clustering area, calculating local voltage fluctuation characteristic values ​​of each charging pile clustering area, determining voltage fluctuation similarity areas of each charging pile clustering area, obtaining regional voltage fluctuation synthesis vectors of each charging pile clustering area, calculating charging abnormality factors of each charging pile clustering area, determining each charging abnormality area, obtaining abnormality scores of each charging pile measurement point in each charging abnormality area, so as to evaluate the abnormality degree of each charging pile measurement point. The method and system for monitoring abnormalities in a new energy vehicle charging station provided by the embodiment of the present invention improve the efficiency of abnormal monitoring of new energy vehicle charging stations.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy vehicle charging monitoring, and in particular to a new energy vehicle charging station abnormality monitoring method and system. Background Art

[0002] New energy vehicle charging stations are facilities that provide charging services for new energy vehicles such as electric vehicles and plug-in hybrid vehicles. With the continuous advancement of new energy vehicle technology and the increasing popularity of new energy vehicle technology, the number and distribution of new energy vehicle charging stations will continue to increase and improve, providing new energy vehicle users with more convenient, efficient and reliable charging services.

[0003] As the infrastructure for charging electric vehicles, the safety of new energy vehicle charging stations is directly related to the safety of users' lives and property. By conducting abnormal monitoring of new energy vehicle charging stations, potential electrical hazards such as leakage, short circuit, overload and other problems can be discovered and dealt with in a timely manner, effectively preventing the occurrence of safety accidents.

[0004] However, since the voltage data collected at the charging pile measurement point has not only temporal variability but also spatial differences, the existing technology has a relatively simple processing process for voltage data and does not take into account the complex temporal and spatial characteristics of voltage data, resulting in low efficiency in abnormal monitoring of new energy vehicle charging stations.

[0005] It can be seen that how to improve the efficiency of abnormal monitoring of new energy vehicle charging stations has become a technical problem that technical personnel in this field need to solve urgently. Summary of the invention

[0006] The present invention provides a new energy vehicle charging station abnormality monitoring method and system to solve the technical problem that the voltage data collected from multiple charging pile measurement points presents complex temporal and spatial characteristics, resulting in low efficiency in abnormality monitoring of new energy vehicle charging stations.

[0007] In order to solve the above technical problems, an embodiment of the present invention provides a method for monitoring abnormalities in a new energy vehicle charging station.

[0008] Collect voltage data of each charging pile measurement point of the new energy vehicle charging station, analyze the fluctuation characteristics of all the voltage data, and obtain the voltage fluctuation state characteristic value of each charging pile measurement point;

[0009] Performing cluster analysis on the geographical location information of all the charging pile measurement points to obtain each charging pile clustering area; calculating the local voltage fluctuation characteristic value of each charging pile clustering area based on all the voltage fluctuation state characteristic values; determining the voltage fluctuation similar area of ​​each charging pile clustering area based on the similarity characteristics between the local voltage fluctuation characteristic value of each charging pile clustering area and all other local voltage fluctuation characteristic values;

[0010] Aligning the voltage data of all the charging pile measurement points in each charging pile clustering area to obtain voltage alignment data of each charging pile measurement point; performing deviation merging processing on all the voltage alignment data in each charging pile clustering area to obtain a regional voltage fluctuation synthesis vector of each charging pile clustering area;

[0011] Calculating a charging abnormality factor for each charging pile clustering region according to the difference characteristics between the regional voltage fluctuation synthesis vector of each charging pile clustering region and the regional voltage fluctuation synthesis vectors of all corresponding regions with similar voltage fluctuations;

[0012] The charging anomaly factors of all the charging pile clustering areas are processed to obtain various charging anomaly areas; an anomaly detection algorithm is used to perform anomaly detection on the voltage data of all the charging pile measurement points in each charging anomaly area to obtain an anomaly score of each charging pile measurement point in each charging anomaly area to evaluate the degree of anomaly of each charging pile measurement point.

[0013] As one of the preferred solutions, the deviation merging process is performed on all the voltage alignment data in each charging pile clustering area to obtain the regional voltage fluctuation synthesis vector of each charging pile clustering area, including:

[0014] Obtaining a charging pile reference point for each charging pile clustering area based on a comparison result of the voltage alignment data of all charging pile measurement points in each charging pile clustering area;

[0015] Obtaining a voltage alignment deviation vector of each charging pile measurement point according to the difference characteristics of the voltage alignment data of each charging pile measurement point and the voltage alignment data of the corresponding charging pile reference point;

[0016] A regional voltage fluctuation synthesis vector of each charging pile clustering area is obtained based on a merging result of all the voltage alignment deviation vectors in each charging pile clustering area.

[0017] As one of the preferred solutions, the fluctuation characteristics of all the voltage data are analyzed to obtain the voltage fluctuation state characteristic value of each charging pile measurement point, including:

[0018] Performing spectrum analysis on all the voltage data at each charging pile measurement point to obtain voltage fluctuation frequency parameters, phase angle parameters and amplitude parameters at each charging pile measurement point;

[0019] Compare and analyze each of the voltage data with the nominal voltage value to obtain corresponding voltage deviation data, use the least squares method to perform curve fitting on all the voltage deviation data at each charging pile measurement point to obtain the voltage fluctuation curve equation at each charging pile measurement point, and extract the fluctuation period parameter of the voltage fluctuation curve equation;

[0020] The normalized result of the voltage fluctuation frequency parameter, the normalized result of the phase angle parameter, the normalized result of the amplitude parameter and the normalized result of the fluctuation period parameter are weighted averaged to obtain the voltage fluctuation state characteristic value of each charging pile measurement point.

[0021] As one of the preferred solutions, the calculating of the local voltage fluctuation characteristic value of each charging pile clustering area based on all the voltage fluctuation state characteristic values ​​includes:

[0022] Divide each of the charging pile clustering areas into a plurality of grids, and perform interpolation processing on all of the grids in each of the charging pile clustering areas according to all of the voltage fluctuation state characteristic values ​​in each of the charging pile clustering areas by using an inverse distance weighted interpolation operation to obtain a voltage fluctuation state characteristic value of each of the grids;

[0023] Taking the average value of all the voltage fluctuation state characteristic values ​​in each charging pile clustering area as the voltage fluctuation area characteristic value of each charging pile clustering area, and calculating the area parameter and measurement point density parameter of each charging pile clustering area;

[0024] A weighted summation process is performed on the normalized result of the voltage fluctuation region characteristic value, the normalized result of the area parameter, and the normalized result of the measurement point density parameter to obtain a local voltage fluctuation characteristic value of each charging pile clustering region.

[0025] As one of the preferred solutions, the method of determining the voltage fluctuation similarity region of each charging pile clustering region based on the similarity characteristics between the local voltage fluctuation characteristic value of each charging pile clustering region and all other local voltage fluctuation characteristic values ​​includes:

[0026] Taking the absolute value of the difference between the local voltage fluctuation characteristic values ​​of the two charging pile clustering areas as the local voltage fluctuation difference index between the two charging pile clustering areas;

[0027] The local voltage fluctuation difference index between each of the charging pile clustering areas and all other charging pile clustering areas is subjected to a first sorting process, and based on the result of the first sorting process, a voltage fluctuation similarity area of ​​each of the charging pile clustering areas is obtained.

[0028] As one of the preferred solutions, the comparison result of the voltage alignment data of all charging pile measurement points in each charging pile clustering area is used to obtain the charging pile reference point of each charging pile clustering area, including:

[0029] The sum of the voltage alignment data of each charging pile measurement point at all acquisition times is taken as the voltage fluctuation amplitude of each charging pile measurement point;

[0030] The voltage fluctuation amplitudes of all the charging pile measurement points in each of the charging pile clustering areas are subjected to a second sorting process, and the charging pile reference points of each of the charging pile clustering areas are obtained based on the result of the second sorting process.

[0031] As one of the preferred solutions, the voltage alignment deviation vector of each charging pile measurement point is obtained according to the difference characteristics of the voltage alignment data of each charging pile measurement point and the voltage alignment data of the corresponding charging pile reference point, including:

[0032] The difference between the voltage alignment data of each charging pile measurement point and the voltage alignment data of the corresponding charging pile reference point is used as the voltage alignment deviation data of each charging pile measurement point;

[0033] All the voltage alignment deviation data of each charging pile measurement point are arranged in ascending order according to the time sequence of acquisition, as the voltage alignment deviation vector of each charging pile measurement point.

[0034] As one of the preferred solutions, the charging abnormality factor of each charging pile clustering area is calculated according to the difference characteristics between the regional voltage fluctuation synthesis vector of each charging pile clustering area and the regional voltage fluctuation synthesis vectors of all corresponding voltage fluctuation similar areas, including:

[0035] All the charging pile clustering areas are combined in pairs, and the cosine similarity between the regional voltage fluctuation synthesis vectors of the two charging pile clustering areas in each combination is used as the voltage fluctuation similarity factor of each combination, and the maximum value of all the voltage fluctuation similarity factors is used as the voltage fluctuation reference similarity factor;

[0036] The average value of the cosine similarity between the regional voltage fluctuation synthesis vector of each charging pile clustering area and the regional voltage fluctuation synthesis vectors of all corresponding voltage fluctuation similar areas is used as the voltage fluctuation average similarity factor of each charging pile clustering area;

[0037] The difference between the voltage fluctuation reference similarity factor and the voltage fluctuation average similarity factor of each charging pile clustering area is divided by the voltage fluctuation reference similarity factor as the charging abnormality factor of each charging pile clustering area.

[0038] As one of the preferred solutions, cluster analysis is performed on the geographical location information of all the charging pile measurement points to obtain cluster areas of each charging pile, including:

[0039] Performing Gaussian projection parameter conversion on the geographic longitude and latitude coordinates of each charging pile measurement point to obtain corresponding plane rectangular coordinates, calculating the Euclidean distance between any two plane rectangular coordinates, constructing a measurement point distance matrix based on all the Euclidean distances, and clustering all the charging pile measurement points according to the measurement point distance matrix to obtain each charging pile cluster;

[0040] The Thiessen polygon partitioning method is used to process each of the charging pile clusters to obtain a corresponding charging pile cluster area.

[0041] Another embodiment of the present invention provides a new energy vehicle charging station abnormality monitoring system, the system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the new energy vehicle charging station abnormality monitoring method as described above.

[0042] Compared with the prior art, the embodiments of the present invention have the following advantages:

[0043] (1) The voltage data of each charging pile measurement point of the new energy vehicle charging station is collected, and the fluctuation characteristics of all voltage data are analyzed to obtain the voltage fluctuation state characteristic value of each charging pile measurement point. Since the charging pile measurement points are distributed in different geographical locations, it is difficult to directly compare and analyze them. The geographical location information of all charging pile measurement points is clustered and analyzed to obtain the clustering areas of each charging pile. The charging pile clustering areas are then analyzed as a whole, which improves the real-time performance of abnormal monitoring of new energy vehicle charging stations.

[0044] (2) First, based on all voltage fluctuation state characteristic values, the local voltage fluctuation characteristic value of each charging pile clustering area is obtained to evaluate the voltage fluctuation characteristics of each charging pile clustering area, and then the similarity characteristics between the local voltage fluctuation characteristic value of each charging pile clustering area and all other local voltage fluctuation characteristic values ​​are analyzed to determine the voltage fluctuation similar area of ​​each charging pile clustering area;

[0045] (3) Then, the voltage data of all charging pile measurement points in each charging pile clustering area are aligned to obtain the voltage alignment data of each charging pile measurement point. By aligning the voltage data of all charging pile measurement points in each charging pile clustering area, the data differences caused by different measurement time points are eliminated, so that the voltage data of different charging piles at the same time point are comparable. Deviation merging processing is performed on all voltage alignment data in each charging pile clustering area to obtain the regional voltage fluctuation synthesis vector of each charging pile clustering area. The voltage data of multiple charging pile measurement points are effectively integrated to form a comprehensive regional voltage fluctuation synthesis vector, which comprehensively considers the voltage fluctuations of different charging piles in the same time period, thereby improving the accuracy of the voltage fluctuation feature analysis of each charging pile clustering area;

[0046] (4) The charging anomaly factor of each charging pile clustering area is calculated based on the difference characteristics between the regional voltage fluctuation synthetic vector of each charging pile clustering area and the regional voltage fluctuation synthetic vectors of all corresponding voltage fluctuation similar areas. The charging anomaly factors of all the charging pile clustering areas are processed to obtain each charging anomaly area. The difference between the regional voltage fluctuation synthetic vector and the similar area is comprehensively considered to reduce the false alarm caused by a single factor or accidental factors. At the same time, by comparing the voltage fluctuations in similar areas, the real abnormal area can be identified more accurately and the underreporting phenomenon can be reduced. The voltage data of all charging pile measurement points in each charging anomaly area are detected by an anomaly detection algorithm to obtain the anomaly score of each charging pile measurement point in each charging anomaly area to evaluate the degree of anomaly of each charging pile measurement point. Each charging pile measurement point is compared with the charging pile measurement points in the same charging pile clustering area to eliminate the differences caused by different spatial positions, thereby improving the reliability of abnormal monitoring of new energy vehicle charging stations and further improving the efficiency of abnormal monitoring of new energy vehicle charging stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] FIG1 is a flow chart of a method for monitoring abnormality of a new energy vehicle charging station in one embodiment of the present invention;

[0048] FIG. 2 is a schematic diagram of obtaining a charging abnormality factor in one embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0051] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0052] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0053] An embodiment of the present invention provides a method for monitoring abnormalities in a new energy vehicle charging station. Specifically, please refer to Figures 1 and 2. Figure 1 is a flow chart of a method for monitoring abnormalities in a new energy vehicle charging station in one embodiment of the present invention, and Figure 2 is a schematic diagram for obtaining a charging abnormality factor in one embodiment of the present invention.

[0054] A flowchart of a new energy vehicle charging station abnormality monitoring method in one embodiment of the present invention includes the following steps S1 to S5, which are specifically as follows:

[0055] Step S1: Collect voltage data from each charging pile measurement point of a new energy vehicle charging station, analyze the fluctuation characteristics of all voltage data, obtain the voltage fluctuation state characteristic value of each charging pile measurement point, perform cluster analysis on the geographical location information of all charging pile measurement points, and obtain the clustering areas of each charging pile.

[0056] Specifically, several charging pile measurement points are arranged in the new energy vehicle charging station, the sampling interval is set to 10 seconds, the voltage data of each charging pile measurement point is collected, and the spectrum analysis is performed on all voltage data of each charging pile measurement point to obtain the voltage fluctuation frequency parameters, phase angle parameters and amplitude parameters of each charging pile measurement point.

[0057] It should be noted that the voltage fluctuation frequency parameter can be used to determine the oscillation source, the phase angle parameter can be used to determine the propagation direction, and the amplitude parameter can be used to quantify the degree of influence. When the voltage fluctuates due to changes in the charging pile load, the recorded voltage value shows a periodic change characteristic.

[0058] Furthermore, each voltage data is compared and analyzed with the nominal voltage value to obtain the corresponding voltage deviation data, and the least squares method is used to perform curve fitting on all voltage deviation data of each charging pile measurement point to obtain the voltage fluctuation curve equation of each charging pile measurement point, and the fluctuation period parameters of the voltage fluctuation curve equation are extracted.

[0059] The normalized results of the voltage fluctuation frequency parameter, the phase angle parameter, the amplitude parameter and the fluctuation period parameter are weighted averaged to obtain the voltage fluctuation state characteristic value of each charging pile measurement point.

[0060] It should be noted that since the charging pile measurement points are distributed in different geographical locations, it is difficult to directly compare and analyze them. Therefore, before comparing and analyzing the charging pile measurement points, it is necessary to cluster the charging pile measurement points.

[0061] Specifically, the geographic longitude and latitude coordinates of each charging pile measurement point are transformed by Gauss projection parameters to obtain the corresponding plane rectangular coordinates. The Euclidean distance between any two plane rectangular coordinates is calculated, and a measurement point distance matrix is ​​constructed based on all Euclidean distances. All charging pile measurement points are clustered according to the measurement point distance matrix to obtain each charging pile cluster.

[0062] It should be noted that the use of the Gaussian projection formula can convert the geodetic coordinates into plane rectangular coordinates. Clustering is a well-known technology, which will not be described in detail in this application. The result of clustering directly reflects the spatial distribution characteristics of the charging pile measurement points.

[0063] As an embodiment of the present application, the minimum clustering distance for clustering processing is 200 meters.

[0064] Furthermore, the Thiessen polygon partitioning method is used to process each charging pile cluster to obtain the corresponding charging pile cluster area.

[0065] Step S2: obtaining the local voltage fluctuation characteristic value of each charging pile clustering area based on all voltage fluctuation state characteristic values, and determining the voltage fluctuation similar area of ​​each charging pile clustering area based on the similarity characteristics between the local voltage fluctuation characteristic value of each charging pile clustering area and all other local voltage fluctuation characteristic values.

[0066] Specifically, the Thiessen polygon partitioning method is used to process each charging pile cluster to obtain the corresponding charging pile cluster area, and each charging pile cluster area is divided into a number of grids. According to all voltage fluctuation state characteristic values ​​in each charging pile cluster area, the inverse distance weighted interpolation operation is used to interpolate all grids in each charging pile cluster area to obtain the voltage fluctuation state characteristic value of each grid.

[0067] As an embodiment of the present application, the interval between grids is 20 meters.

[0068] Furthermore, the average value of all voltage fluctuation state characteristic values ​​in each charging pile clustering area is taken as the voltage fluctuation area characteristic value of each charging pile clustering area, and the area parameter and measurement point density parameter of each charging pile clustering area are calculated.

[0069] The normalized results of the voltage fluctuation area characteristic value, the normalized results of the area parameter and the normalized results of the measurement point density parameter are weighted summed to obtain the local voltage fluctuation characteristic value of each charging pile clustering area.

[0070] As an embodiment of the present application, the weights of the voltage fluctuation region characteristic value, area parameter and measurement point density parameter are 0.4, 0.3 and 0.3 respectively.

[0071] It should be noted that the measurement point density parameter reflects the degree of spatial aggregation of the charging pile measurement points. The local voltage fluctuation characteristic values ​​between different regions can be quantitatively compared to evaluate the similarity of voltage fluctuations between regions.

[0072] Furthermore, the absolute value of the difference between the local voltage fluctuation characteristic values ​​of two charging pile clustering areas is taken as the local voltage fluctuation difference index between the two charging pile clustering areas, and the local voltage fluctuation difference index between each charging pile clustering area and all other charging pile clustering areas is subjected to a first sorting processing, and the voltage fluctuation similarity area of ​​each charging pile clustering area is obtained based on the result of the first sorting processing.

[0073] As an embodiment of the present application, the local voltage fluctuation difference index between each charging pile clustering area and all other charging pile clustering areas are arranged in ascending order, and the charging pile clustering areas whose local voltage fluctuation difference index is less than a preset difference threshold are taken as the voltage fluctuation similarity areas of each charging pile clustering area.

[0074] Step S3: aligning the voltage data of all charging pile measurement points in each charging pile clustering area to obtain the voltage alignment data of each charging pile measurement point, performing deviation merging processing on all voltage alignment data in each charging pile clustering area to obtain the regional voltage fluctuation synthesis vector of each charging pile clustering area.

[0075] It should be noted that since the charging pile measurement points are distributed in different geographical locations, the relationships between these vectors are complex and difficult to directly compare and analyze. It is necessary to consider how to merge the voltage fluctuation vectors of multiple charging pile measurement points to form a comprehensive regional voltage fluctuation synthetic vector.

[0076] Specifically, a dynamic time warping algorithm is used to align the voltage data of all charging pile measurement points in each charging pile clustering area to obtain voltage alignment data of each charging pile measurement point.

[0077] The sum of the voltage alignment data of each charging pile measurement point at all collection moments is taken as the voltage fluctuation amplitude of each charging pile measurement point, the voltage fluctuation amplitudes of all charging pile measurement points in each charging pile clustering area are subjected to a second sorting process, and the charging pile reference point of each charging pile clustering area is obtained based on the result of the second sorting process.

[0078] As an embodiment of the present application, the voltage fluctuation amplitudes of all charging pile measurement points in each charging pile clustering area are arranged in descending order, and the charging pile measurement point corresponding to the largest voltage fluctuation amplitude in each charging pile clustering area is used as the charging pile reference point of each charging pile clustering area.

[0079] The difference between the voltage alignment data of each charging pile measurement point and the voltage alignment data of the corresponding charging pile reference point is used as the voltage alignment deviation data of each charging pile measurement point, and all the voltage alignment deviation data of each charging pile measurement point are arranged in ascending order according to the time sequence of acquisition as the voltage alignment deviation vector of each charging pile measurement point.

[0080] Based on the merging result of all voltage alignment deviation vectors in each charging pile clustering area, the regional voltage fluctuation synthetic vector of each charging pile clustering area is obtained.

[0081] As an embodiment of the present application, vector addition is used to perform vector addition processing on the voltage alignment deviation vectors of all charging pile measurement points in each charging pile clustering area to obtain a regional voltage fluctuation synthetic vector of each charging pile clustering area.

[0082] Step S4: Calculate the charging anomaly factor of each charging pile clustering area according to the difference characteristics between the regional voltage fluctuation synthesis vector of each charging pile clustering area and the regional voltage fluctuation synthesis vectors of all corresponding areas with similar voltage fluctuations.

[0083] All charging pile clustering areas are combined in pairs, and the cosine similarity between the regional voltage fluctuation synthetic vectors of the two charging pile clustering areas in each combination is used as the voltage fluctuation similarity factor of each combination, and the maximum value of all voltage fluctuation similarity factors is used as the voltage fluctuation reference similarity factor.

[0084] The average value of the cosine similarity between the regional voltage fluctuation synthesis vector of each charging pile clustering area and the regional voltage fluctuation synthesis vectors of all corresponding voltage fluctuation similar areas is taken as the average similarity factor of the voltage fluctuation of each charging pile clustering area.

[0085] The difference between the voltage fluctuation reference similarity factor and the average voltage fluctuation similarity factor of each charging pile clustering area is divided by the voltage fluctuation reference similarity factor as the charging abnormality factor of each charging pile clustering area.

[0086] Step S5: Process the charging anomaly factors of all charging pile clustering areas to obtain various charging anomaly areas, perform anomaly detection on the voltage data of all charging pile measurement points in each charging anomaly area, and obtain the anomaly score of each charging pile measurement point in each charging anomaly area.

[0087] When the charging abnormality factor is greater than the preset abnormality threshold, it is determined that the corresponding charging pile clustering area has charging and discharging abnormalities, otherwise, it is determined that the corresponding charging pile clustering area has no charging and discharging abnormalities.

[0088] Anomaly detection algorithm is used to perform anomaly detection on the voltage data of all charging pile measurement points in each charging abnormality area to obtain the anomaly score of each charging pile measurement point to evaluate the degree of abnormality of each charging pile measurement point.

[0089] It should be noted that the anomaly detection algorithm is a well-known technology and will not be described in detail in this application.

[0090] Another embodiment of the present invention provides a new energy vehicle charging station abnormality monitoring system, the system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the new energy vehicle charging station abnormality monitoring method as described above.

[0091] Compared with the prior art, the method and system for monitoring abnormality of a new energy vehicle charging station provided by the embodiment of the present invention have the following beneficial effects:

[0092] (1) The voltage data of each charging pile measurement point of the new energy vehicle charging station is collected, and the fluctuation characteristics of all voltage data are analyzed to obtain the voltage fluctuation state characteristic value of each charging pile measurement point. Since the charging pile measurement points are distributed in different geographical locations, it is difficult to directly compare and analyze them. The geographical location information of all charging pile measurement points is clustered and analyzed to obtain the clustering areas of each charging pile. The charging pile clustering areas are then analyzed as a whole, which improves the real-time performance of abnormal monitoring of new energy vehicle charging stations.

[0093] (2) First, based on all voltage fluctuation state characteristic values, the local voltage fluctuation characteristic value of each charging pile clustering area is obtained to evaluate the voltage fluctuation characteristics of each charging pile clustering area, and then the similarity characteristics between the local voltage fluctuation characteristic value of each charging pile clustering area and all other local voltage fluctuation characteristic values ​​are analyzed to determine the voltage fluctuation similar area of ​​each charging pile clustering area;

[0094] (3) Then, the voltage data of all charging pile measurement points in each charging pile clustering area are aligned to obtain the voltage alignment data of each charging pile measurement point. By aligning the voltage data of all charging pile measurement points in each charging pile clustering area, the data differences caused by different measurement time points are eliminated, so that the voltage data of different charging piles at the same time point are comparable. Deviation merging processing is performed on all voltage alignment data in each charging pile clustering area to obtain the regional voltage fluctuation synthesis vector of each charging pile clustering area. The voltage data of multiple charging pile measurement points are effectively integrated to form a comprehensive regional voltage fluctuation synthesis vector, which comprehensively considers the voltage fluctuations of different charging piles in the same time period, thereby improving the accuracy of the voltage fluctuation feature analysis of each charging pile clustering area;

[0095] (4) The charging anomaly factor of each charging pile clustering area is calculated based on the difference characteristics between the regional voltage fluctuation synthetic vector of each charging pile clustering area and the regional voltage fluctuation synthetic vectors of all corresponding voltage fluctuation similar areas. The charging anomaly factors of all the charging pile clustering areas are processed to obtain each charging anomaly area. The difference between the regional voltage fluctuation synthetic vector and the similar area is comprehensively considered to reduce the false alarm caused by a single factor or accidental factors. At the same time, by comparing the voltage fluctuations in similar areas, the real abnormal area can be identified more accurately and the underreporting phenomenon can be reduced. The voltage data of all charging pile measurement points in each charging anomaly area are detected by an anomaly detection algorithm to obtain the anomaly score of each charging pile measurement point in each charging anomaly area to evaluate the degree of anomaly of each charging pile measurement point. Each charging pile measurement point is compared with the charging pile measurement points in the same charging pile clustering area to eliminate the differences caused by different spatial positions, thereby improving the reliability of abnormal monitoring of new energy vehicle charging stations and further improving the efficiency of abnormal monitoring of new energy vehicle charging stations.

[0096] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for monitoring abnormalities in a new energy vehicle charging station, characterized in that: The method comprises: Collect voltage data of each charging pile measurement point of the new energy vehicle charging station, analyze the fluctuation characteristics of all the voltage data, and obtain the voltage fluctuation state characteristic value of each charging pile measurement point; Performing cluster analysis on the geographical location information of all the charging pile measurement points to obtain each charging pile clustering area; calculating the local voltage fluctuation characteristic value of each charging pile clustering area based on all the voltage fluctuation state characteristic values; determining the voltage fluctuation similar area of ​​each charging pile clustering area based on the similarity characteristics between the local voltage fluctuation characteristic value of each charging pile clustering area and all other local voltage fluctuation characteristic values; Aligning the voltage data of all the charging pile measurement points in each charging pile clustering area to obtain voltage alignment data of each charging pile measurement point; performing deviation merging processing on all the voltage alignment data in each charging pile clustering area to obtain a regional voltage fluctuation synthesis vector of each charging pile clustering area; Calculating a charging abnormality factor for each charging pile clustering region according to the difference characteristics between the regional voltage fluctuation synthesis vector of each charging pile clustering region and the regional voltage fluctuation synthesis vectors of all corresponding regions with similar voltage fluctuations; The charging anomaly factors of all the charging pile clustering areas are processed to obtain various charging anomaly areas; an anomaly detection algorithm is used to perform anomaly detection on the voltage data of all the charging pile measurement points in each charging anomaly area to obtain an anomaly score of each charging pile measurement point in each charging anomaly area to evaluate the degree of anomaly of each charging pile measurement point.

2. A method for monitoring abnormality of a new energy vehicle charging station according to claim 1, characterized in that: The performing deviation merging processing on all the voltage alignment data in each charging pile clustering area to obtain a regional voltage fluctuation synthesis vector of each charging pile clustering area includes: Obtaining a charging pile reference point for each charging pile clustering area based on a comparison result of the voltage alignment data of all charging pile measurement points in each charging pile clustering area; Obtaining a voltage alignment deviation vector of each charging pile measurement point according to the difference characteristics of the voltage alignment data of each charging pile measurement point and the voltage alignment data of the corresponding charging pile reference point; A regional voltage fluctuation synthesis vector of each charging pile clustering area is obtained based on a merging result of all the voltage alignment deviation vectors in each charging pile clustering area.

3. The method for monitoring abnormality of a new energy vehicle charging station according to claim 1, characterized in that: The analyzing the fluctuation characteristics of all the voltage data to obtain the voltage fluctuation state characteristic value of each charging pile measurement point includes: Performing spectrum analysis on all the voltage data at each charging pile measurement point to obtain voltage fluctuation frequency parameters, phase angle parameters and amplitude parameters at each charging pile measurement point; Compare and analyze each of the voltage data with the nominal voltage value to obtain corresponding voltage deviation data, use the least squares method to perform curve fitting on all the voltage deviation data at each charging pile measurement point to obtain the voltage fluctuation curve equation at each charging pile measurement point, and extract the fluctuation period parameter of the voltage fluctuation curve equation; The normalized result of the voltage fluctuation frequency parameter, the normalized result of the phase angle parameter, the normalized result of the amplitude parameter and the normalized result of the fluctuation period parameter are weighted averaged to obtain the voltage fluctuation state characteristic value of each charging pile measurement point.

4. The method for monitoring abnormality of a new energy vehicle charging station according to claim 1, characterized in that: The calculating the local voltage fluctuation characteristic value of each charging pile clustering area based on all the voltage fluctuation state characteristic values ​​includes: Divide each of the charging pile clustering areas into a plurality of grids, and perform interpolation processing on all of the grids in each of the charging pile clustering areas according to all of the voltage fluctuation state characteristic values ​​in each of the charging pile clustering areas by using an inverse distance weighted interpolation operation to obtain a voltage fluctuation state characteristic value of each of the grids; Taking the average value of all the voltage fluctuation state characteristic values ​​in each charging pile clustering area as the voltage fluctuation area characteristic value of each charging pile clustering area, and calculating the area parameter and measurement point density parameter of each charging pile clustering area; A weighted summation process is performed on the normalized result of the voltage fluctuation region characteristic value, the normalized result of the area parameter, and the normalized result of the measurement point density parameter to obtain a local voltage fluctuation characteristic value of each charging pile clustering region.

5. The method for monitoring abnormality of a new energy vehicle charging station according to claim 1, characterized in that: The determining of the voltage fluctuation similarity region of each charging pile clustering region based on the similarity feature between the local voltage fluctuation characteristic value of each charging pile clustering region and all other local voltage fluctuation characteristic values ​​comprises: Taking the absolute value of the difference between the local voltage fluctuation characteristic values ​​of the two charging pile clustering areas as the local voltage fluctuation difference index between the two charging pile clustering areas; The local voltage fluctuation difference index between each of the charging pile clustering areas and all other charging pile clustering areas is subjected to a first sorting process, and based on the result of the first sorting process, a voltage fluctuation similarity area of ​​each of the charging pile clustering areas is obtained.

6. A method for monitoring abnormality of a new energy vehicle charging station according to claim 2, characterized in that: The obtaining of the charging pile reference point of each charging pile clustering area based on the comparison result of the voltage alignment data of all charging pile measurement points in each charging pile clustering area includes: The sum of the voltage alignment data of each charging pile measurement point at all acquisition times is taken as the voltage fluctuation amplitude of each charging pile measurement point; The voltage fluctuation amplitudes of all the charging pile measurement points in each of the charging pile clustering areas are subjected to a second sorting process, and the charging pile reference points of each of the charging pile clustering areas are obtained based on the result of the second sorting process.

7. A method for monitoring abnormality of a new energy vehicle charging station according to claim 2, characterized in that: The step of obtaining the voltage alignment deviation vector of each charging pile measurement point according to the difference characteristics between the voltage alignment data of each charging pile measurement point and the voltage alignment data of the corresponding charging pile reference point includes: The difference between the voltage alignment data of each charging pile measurement point and the voltage alignment data of the corresponding charging pile reference point is used as the voltage alignment deviation data of each charging pile measurement point; All the voltage alignment deviation data of each charging pile measurement point are arranged in ascending order according to the time sequence of acquisition, as the voltage alignment deviation vector of each charging pile measurement point.

8. The method for monitoring abnormality of a new energy vehicle charging station according to claim 1, characterized in that: The calculating the charging abnormality factor of each charging pile clustering area according to the difference characteristics between the regional voltage fluctuation synthesis vector of each charging pile clustering area and the regional voltage fluctuation synthesis vectors of all corresponding voltage fluctuation similar areas includes: All the charging pile clustering areas are combined in pairs, and the cosine similarity between the regional voltage fluctuation synthesis vectors of the two charging pile clustering areas in each combination is used as the voltage fluctuation similarity factor of each combination, and the maximum value of all the voltage fluctuation similarity factors is used as the voltage fluctuation reference similarity factor; The average value of the cosine similarity between the regional voltage fluctuation synthesis vector of each charging pile clustering area and the regional voltage fluctuation synthesis vectors of all corresponding voltage fluctuation similar areas is used as the voltage fluctuation average similarity factor of each charging pile clustering area; The difference between the voltage fluctuation reference similarity factor and the voltage fluctuation average similarity factor of each charging pile clustering area is divided by the voltage fluctuation reference similarity factor as the charging abnormality factor of each charging pile clustering area.

9. The method for monitoring abnormality of a new energy vehicle charging station according to claim 1, characterized in that: The cluster analysis is performed on the geographical location information of all the charging pile measurement points to obtain each charging pile cluster area, including: Performing Gaussian projection parameter conversion on the geographic longitude and latitude coordinates of each charging pile measurement point to obtain corresponding plane rectangular coordinates, calculating the Euclidean distance between any two plane rectangular coordinates, constructing a measurement point distance matrix based on all the Euclidean distances, and clustering all the charging pile measurement points according to the measurement point distance matrix to obtain each charging pile cluster; The Thiessen polygon partitioning method is used to process each of the charging pile clusters to obtain a corresponding charging pile cluster area.

10. A new energy vehicle charging station abnormality monitoring system, characterized in that: The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, a new energy vehicle charging station abnormality monitoring method as described in any one of claims 1 to 9 is implemented.

Images