Electric power operation and maintenance power distribution station intelligent monitoring platform based on artificial intelligence

Abstract

The invention relates to the technical field of power operation and maintenance data processing, in particular to a power operation and maintenance power distribution station intelligent monitoring platform based on artificial intelligence. The platform comprises a data acquisition unit used for acquiring current monitoring data of the power distribution station; the sample space construction unit is used for obtaining a data curve of each dimension and calculating a fluctuation state characteristic value of each dimension, and establishing a sample space based on the fluctuation state characteristic value; the data point suspected anomaly degree calculation unit is used for calculating the spatial distribution anomaly degree and the multi-dimensional similarity relevance of the data points, and the sum of the spatial distribution anomaly degree and the multi-dimensional similarity relevance of the data points is the suspected anomaly degree; the abnormal data point detection unit is used for correcting the initial neighbor quantity parameter of the data point by using the suspected abnormal degree; and detecting abnormal data points in the current monitoring data in the sample space by using the neighbor quantity parameters after data point correction. According to the invention, the power distribution station can be accurately monitored and abnormal data can be acquired.

Description

Technical Field

[0001] The present invention relates to the technical field of power operation and maintenance data processing, and in particular to an intelligent monitoring platform for power operation and maintenance distribution stations based on artificial intelligence. Background Art

[0002] The intelligent operation and maintenance service of power distribution is centered on the intelligent operation and maintenance platform. By installing online monitoring devices on the distribution room, high and low voltage distribution cabinets, the operating status is transmitted to the intelligent operation and maintenance platform in real time, and remote operation and maintenance are carried out. It provides customers with power operation and maintenance solutions in the big data era, better ensures the safety and reliability of power supply, and at the same time achieves the purpose of reducing losses and energy, reducing manpower expenses, and improving economic benefits.

[0003] For the intelligent monitoring of the distribution room, the existing technology can usually collect multiple types of data in the monitoring room and use the LOF outlier detection algorithm to obtain abnormal data during the monitoring process. However, when using the LOF outlier detection algorithm to detect anomalies in the distribution station monitoring data, it is difficult to determine the value of the neighbor number parameter because it needs to combine multi-dimensional data. If the neighbor number parameter k is too small, it may cause the algorithm to be too sensitive to local outliers during detection. If the neighbor number parameter k is too large, it may cause the algorithm to be unable to effectively capture local anomalies during detection. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide an intelligent monitoring platform for power operation and maintenance distribution stations based on artificial intelligence. The technical solutions adopted are as follows: An embodiment of the present invention provides an intelligent monitoring platform for power distribution station operation and maintenance based on artificial intelligence, which includes a data acquisition unit, a sample space construction unit, a data point suspected abnormality degree calculation unit and an abnormal data point detection unit. Specifically: A data acquisition unit, used to collect current monitoring data of the power distribution station using sensors, wherein the monitoring data is multi-dimensional data; A sample space construction unit is used to obtain a data curve of each dimension based on the data of each dimension in the historical monitoring data; calculate the fluctuation state characteristic value of each dimension using the maximum longitudinal distance from each peak to its corresponding trough point in the data curve; and establish a sample space based on the fluctuation state characteristic value; The suspected abnormality degree calculation unit of the data point is used to calculate the abnormality degree of the spatial distribution of the data point according to the clustering result of the current monitoring data in the sample space; the multidimensional similarity correlation of the data point is calculated using the value of the data point in each dimension in the sample space; the sum of the abnormality degree of the spatial distribution of the data point and the multidimensional similarity correlation is the suspected abnormality degree; The abnormal data point detection unit is used to modify the initial neighbor quantity parameter of the data point using the suspected abnormality degree of the data point; and detect abnormal data points in the current monitoring data in the sample space using the modified neighbor quantity parameter of the data point.

[0005] Preferably, the maximum longitudinal distance from each peak to its corresponding trough point in the data curve is used to calculate the characteristic value of the fluctuation state in each dimension, including: Obtain the variance of the maximum longitudinal distance from each peak to its corresponding trough point in a data curve of one dimension, recorded as the longitudinal variance; obtain the sum of the distances from the horizontal coordinates of each peak to the horizontal coordinates of the corresponding trough points on the left and right sides, recorded as the span of the peak; obtain the variance of the span of each peak, recorded as the transverse variance; add the longitudinal variance and the transverse variance, compare the maximum longitudinal distance from each peak to its corresponding trough point with the summed result and sum them up to obtain the characteristic value of the fluctuation state of this dimension.

[0006] Preferably, establishing a sample space based on the fluctuation state characteristic value includes: The preset number of dimensions with the largest eigenvalues ​​of the fluctuation state are obtained as the main dimensions to establish the sample space.

[0007] Preferably, calculating the degree of abnormality of spatial distribution of data points according to the clustering result of the current monitoring data in the sample space includes: Obtain the volume of the minimum bounding sphere of each point cluster in the clustering result; obtain the volume of the minimum bounding sphere of the point cluster where the data point is located in the current monitoring data after clustering; obtain the connecting line between the centroid of the point cluster where the data point is located and the centroid of other point clusters, obtain the number of data points within two unit lengths of the vertical distance connecting line, and remove the data points of the point clusters belonging to the two connecting lines. The number of remaining data points is the number of free data points corresponding to the connecting line; the degree of abnormality of the spatial distribution of the data point is obtained according to the volume of the minimum bounding sphere of the point cluster where the data point is located and the number of free data points corresponding to the connecting line between the centroid of the point cluster where the data point is located and the centroid of other point clusters.

[0008] Preferably, the calculation formula for the degree of spatial distribution anomaly is specifically: , in, Indicates the degree of abnormality of the spatial distribution of the pth data point; Represents the volume of the minimum circumscribed sphere of the point cluster where the pth data point is located; Represents the number of all point clusters; It represents the number of free data points corresponding to the line connecting the centroid of the point cluster where the p-th data point is located and the midline of the i-th point cluster outside the point cluster where the p-th data point is located.

[0009] Preferably, the calculation formula of the multi-dimensional similarity correlation of data points is specifically: , in, Represents the multidimensional similarity correlation of the p-th data point; Represents the value of the p-th data point in the t-th dimension; Represents the mean value of the data points in the tth dimension; and They represent the maximum and minimum values ​​of the data points in the t-th dimension respectively; σ[ ] represents the variance function; t represents the t-th dimension.

[0010] Preferably, the initial neighbor number parameter of the data point is corrected using the suspected abnormality degree of the data point, including: The ratio of the initial number of neighbors of a data point to the suspected abnormality degree of the data point is the corrected number of neighbors of the data point.

[0011] Preferably, detecting abnormal data points in the current monitoring data in the sample space using the neighbor quantity parameter after the correction of the data point includes: In the sample space, the LOF outlier detection algorithm is used to calculate the data points in the sample space based on the corrected neighbor number parameter of each data point to obtain the LOF value of each data point; the absolute value of the difference between the LOF value of each data point and the mean LOF value of all data points is calculated and normalized to obtain the monitoring abnormality degree of each data point; an abnormal threshold is set, and when the monitoring abnormality degree of a data point is greater than or equal to the abnormal threshold, the data point is an abnormal data point.

[0012] The embodiments of the present invention have at least the following beneficial effects: the present invention uses historical monitoring data for analysis to obtain the fluctuation state characteristic values ​​of each dimension and obtain the main dimensions, and then constructs a new sample space, avoiding the problem that the LOF algorithm performs poorly on high-dimensional data sets, making subsequent anomaly detection more accurate; further, the spatial distribution anomaly degree and multi-dimensional similarity correlation of the data points are calculated, and the suspected anomaly degree of each data point is obtained by comprehensive analysis, and the initial neighbor number parameter of each data point is corrected based on this. Compared with the prior art, directly using a fixed empirical neighbor number parameter k for LOF outlier detection will lead to inaccurate detection results of outlier abnormal data. In the present invention, the corrected neighbor number parameter is used for LOF outlier detection. For data with higher abnormal risk, correcting its neighbor number parameter can make it easier to be detected as an outlier. Conversely, for data with lower abnormal risk, correcting its neighbor number parameter can make it less likely to be detected as abnormal outlier data, thereby obtaining more accurate distribution room monitoring data anomaly detection results and improving the accuracy of anomaly detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0014] Figure 1 A platform block diagram of an artificial intelligence-based smart monitoring platform for power operation and maintenance distribution stations provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0015] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, characteristics and effects of an intelligent monitoring platform for power operation and maintenance distribution stations based on artificial intelligence proposed by the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures, or characteristics in one or more embodiments may be combined in any suitable form.

[0016] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0017] The following is a detailed description of a specific solution of an intelligent monitoring platform for power operation and maintenance distribution stations based on artificial intelligence provided by the present invention in conjunction with the accompanying drawings.

[0018] Example: The main application scenarios of the present invention are: When using the LOF outlier detection algorithm to detect anomalies in the monitoring data of various equipment sensors in the distribution room, it is difficult to determine the value of the neighbor number parameter for each data point due to the need to combine multi-dimensional data, and the use of fixed empirical parameters is likely to lead to inaccurate anomaly detection results and inaccurate power operation and maintenance feedback information in the distribution room. In response to the above problems, this solution obtains the suspected abnormality degree of the data point through the distribution characteristics in the data space composed of various monitoring data, and performs weighted correction on the neighbor number parameter k value of the data point to obtain a more appropriate neighbor number parameter value, and then uses the LOF outlier detection algorithm for anomaly detection.

[0019] See also Figure 1 , which shows a platform block diagram of an artificial intelligence-based smart monitoring platform for power operation and maintenance distribution stations provided in an embodiment of the present invention, the platform includes a data acquisition unit, a sample space construction unit, a data point suspected abnormality degree calculation unit and an abnormal data point detection unit.

[0020] The data acquisition unit is used to collect current monitoring data of the power distribution station using sensors, wherein the monitoring data is multi-dimensional data.

[0021] During the operation of the distribution station, it is necessary to collect a variety of data to monitor the operation of the distribution station. In the present invention, six different types of data are collected, namely voltage, current, temperature, humidity, noise and dust content. When performing specific collection, the corresponding sensor equipment is used to collect multi-dimensional related monitoring data of the distribution station. The collection frequency of multiple sensors is set uniformly, which is once per second. The collection cycle is 24 hours, that is, 24 hours is a cycle for detection. It should be noted that the data obtained by each sensor is stored separately in the corresponding sequence, and the newly collected data is added at the end of the corresponding sequence, so that the monitoring data of the distribution station can be obtained, where the monitoring data is multi-dimensional data, and the current monitoring data can be obtained.

[0022] The sample space construction unit is used to obtain the data curve of each dimension based on the data of each dimension in the historical monitoring data; calculate the fluctuation state characteristic value of each dimension using the maximum longitudinal distance from each peak to its corresponding trough point in the data curve; and establish the sample space based on the fluctuation state characteristic value.

[0023] The monitoring data of multiple dimensions collected at each moment can form a multidimensional data point. The data points at multiple moments are placed in a multidimensional space to form a discrete multidimensional point set. The LOF outlier detection algorithm is used in the multidimensional point set to obtain outliers. However, since LOF performs poorly on high-dimensional data sets, in high-dimensional space, the distances between sample points tend to be consistent, and the local density is difficult to distinguish abnormal points, making outlier detection in high-dimensional data unreliable. Therefore, it is necessary to reduce the dimension to construct the sample space of LOF outlier detection as the basis for subsequent LOF outlier detection to improve the accuracy of subsequent detection.

[0024] The present invention obtains the main dimension by evaluating the fluctuation state of the dimensional data. The more frequent the data fluctuation in the dimension and the greater the degree of fluctuation, the more sensitive it is to the anomaly and the more timely it can reflect the anomaly. On the other hand, the higher the similarity of normal fluctuations and the higher the repetition frequency, the more the abnormal fluctuations can be highlighted and the stronger the effect of capturing abnormal data fluctuations.

[0025] Furthermore, historical monitoring data is obtained. Specifically, relative to the current cycle, if there is no abnormal data point in the previous cycle, the monitoring data in the previous acquisition cycle is used as the historical monitoring data. If the monitoring data in the previous cycle is abnormal, the monitoring data in the previous cycle of the previous cycle is used as the historical monitoring data, and so on. The historical monitoring data is obtained by performing a fluctuation state evaluation on the data of each dimension in the historical monitoring data to obtain the fluctuation state characteristic value of the dimension.

[0026] Specifically, the data of each dimension in the historical monitoring data is projected into a two-dimensional plane coordinate system, with the horizontal axis being the time series and the vertical axis being the dimension value, to obtain the data curve of each dimension. The AMPD peak search algorithm is used on the data curve to obtain the peak on the data curve of each dimension, where each peak has two corresponding trough points on the left and right sides.

[0027] Obtain the variance of the maximum longitudinal distance from each peak to its corresponding trough point in the data curve, recorded as the longitudinal variance; obtain the sum of the distances from the abscissa of each peak to the abscissa of the corresponding trough points on the left and right sides, recorded as the lateral span of the peak; obtain the variance of the lateral span of each peak, recorded as the lateral variance; add the longitudinal variance and the lateral variance, compare the maximum longitudinal distance from each peak to its corresponding trough point with the summed result and sum them to obtain the fluctuation state characteristic value of the data curve, that is, the fluctuation state characteristic value of the dimension corresponding to the data curve. The specific calculation formula is: , in, Represents the fluctuation state characteristic value of the qth dimension in the historical monitoring data; Indicates the number of peaks in the data curve corresponding to the qth dimension; It represents the maximum longitudinal distance between the ith wave crest and its corresponding wave valley point, that is, one wave crest has two corresponding wave valley points, and the longitudinal distances between the wave crest and its two corresponding wave valley points are obtained in the vertical direction respectively, and the largest of the two distances is the maximum longitudinal distance; It represents the variance of the maximum longitudinal distance from each peak to its corresponding trough point in the data curve, which is also called the longitudinal variance. It represents the variance of the sum of the distances from the horizontal coordinates of each peak to the horizontal coordinates of the corresponding trough points on the left and right sides, which is also called the horizontal variance. In the above formula, It means that the maximum longitudinal distance of each peak is used as the weight, and the sum of the number of peaks. The larger the weighted sum is, the more frequent the data fluctuations in the qth dimension are, the greater the degree of fluctuation is, the larger the characteristic value of the fluctuation state of the qth dimension is, and the more suitable it is as the main dimension; and The smaller it is, the higher the similarity between the fluctuations and the higher the repetition frequency. When abnormal data fluctuations occur, the abnormal detection effect is more obvious. The larger it is, the larger the eigenvalue of the fluctuation state of the qth dimension is, and the more suitable it is as the main dimension.

[0028] Thus, the fluctuation state characteristic values ​​of each dimension are obtained, and the preset number of dimensions with the largest fluctuation state characteristic values ​​are selected as the main dimensions to construct the sample space for LOF outlier detection. Preferably, in the embodiment of the present invention, the value of the preset number is 3, and the three coordinate axes of the space represent the values ​​of the three dimensions. The data after dimensionality reduction improves the accuracy of LOF outlier detection and is the basis for subsequent analysis of data distribution characteristics.

[0029] The data point suspected abnormality degree calculation unit is used to calculate the spatial distribution abnormality degree of the data point according to the clustering result of the current monitoring data in the sample space; the multidimensional similarity correlation of the data point is calculated using the value of the data point in each dimension in the sample space; the sum of the spatial distribution abnormality degree and the multidimensional similarity correlation of the data point is the suspected abnormality degree.

[0030] In the sample space, the neighborhood spatial distribution characteristics of the data points are analyzed. In the distribution room, common anomalies are caused by grid instability or local load fluctuations. The corresponding voltage and current changes are sudden numerical jumps. At the same time, changes in other sensor monitoring data such as temperature and noise will also cause temperature and sound mutations due to changes in load equipment. Therefore, in addition to the point set where normal data is clustered in the sample space, it is easy to form a small cluster point set, and this cluster will be identified as a local cluster in the LOF anomaly detection, resulting in inaccurate anomaly detection results. This type of cluster is relatively small in size, and because it is a cluster of mutation data, the number of discrete data points between the normal data point set is relatively small. Therefore, the data point is located in this type of point cluster, and the possibility that the data point is a suspected anomaly point is high.

[0031] In the sample space, kmeans is used to cluster the current monitoring data. The k value is obtained through the elbow method to obtain the clustering result. The data in the sample space is divided into multiple point clusters. The minimum bounding sphere of each point cluster is obtained using the random increment algorithm. The bounding sphere represents the volume range of the point cluster. The volume of the minimum bounding sphere of the point cluster where the data point in the current monitoring data is located after clustering is obtained; the connecting line between the centroid of the point cluster where the data point is located and the centroid of other point clusters is obtained, and the number of data points within two unit lengths of the vertical distance connecting line is obtained. The data points belonging to the point clusters of the two connecting lines are removed, and the number of remaining data points is the number of free data points corresponding to the connecting line; The degree of abnormality of spatial distribution of data points is obtained according to the volume of the minimum bounding sphere of the point cluster where the data point is located and the number of free data points corresponding to the line between the centroid of the point cluster where the data point is located and the centroid of other point clusters. The calculation formula of the degree of abnormality of spatial distribution is as follows: , in, Indicates the degree of abnormality of the spatial distribution of the pth data point; Represents the volume of the minimum circumscribed sphere of the point cluster where the pth data point is located; Indicates the number of clusters other than the cluster where the pth data point is located. Represents the number of all point clusters; Indicates the number of free data points corresponding to the line connecting the centroid of the cluster where the p-th data point is located and the midline of the i-th cluster outside the cluster where the p-th data point is located; The volume of the minimum enclosing sphere of the point cluster where the pth data point is located. The smaller the volume, the more the pth cluster conforms to the characteristics of a small point set. It may be a point cluster composed of mutation data. The more abnormal the cluster where the pth data point is located is; the smaller the number of free data points, the fewer the number of discrete data points between the point clusters. The cumulative sum of the number of data points around the line connecting the point cluster where the p-th data point is located and other point clusters. The smaller the cumulative sum, the more isolated the point cluster where the p-th data point is located, the fewer discrete data between it and the normal point cluster, and the more it conforms to the point cluster characteristics formed by the aggregation of mutation data point characteristics, and the greater the degree of abnormality of the spatial distribution of the corresponding p-th data point.

[0032] In this way, the degree of abnormality of the spatial distribution of all data points is obtained. However, relying solely on spatial distribution characteristics has limitations. Here, we further combine multidimensional data association characteristics to improve the accuracy of obtaining suspected abnormal data points.

[0033] The distribution station is a relatively closed environment. Therefore, when an abnormality occurs inside, various monitoring data will have interrelated changes. The abnormal changes of various monitoring data are all caused by the same abnormality and will be disturbed to the same extent. Therefore, the data points in the three-dimensional space are disassembled into one-dimensional data. When the data points have similar outlier levels in each dimension, it means that the data point is likely to be an outlier data point caused by the abnormality in the distribution station. If the degree of outliers in each dimension is different, it means that the data point may be a normal change in the current dimension data, such as the change of current and voltage under the call of the power grid. Here, by obtaining the degree of outliers of the data points in each dimension, the similarity correlation between the data points in multiple dimensions is obtained.

[0034] Thus, the value of the data point in each dimension in the sample space is obtained, and then the multi-dimensional similarity correlation of the data point is calculated. The specific calculation formula of the multi-dimensional similarity correlation of the data point is: , in, Represents the multidimensional similarity correlation of the p-th data point; Represents the value of the p-th data point in the t-th dimension; Represents the mean value of the data points in the tth dimension; and They represent the maximum and minimum values ​​of the data points in the tth dimension respectively; σ[ ] represents the variance function; It is the difference between the value of the p-th data point in the t-th dimension and the mean of the values ​​of the data points in the t-th dimension, indicating the degree of outlier of the p-th data point in the t-th dimension. The larger the difference, the more outlier the p-th data point is in the t-th dimension. Represents the normalization of the outlier degree to unify the magnitude of the outlier degree in different dimensions. It represents the variance of the outlier degree of the pth data point in three dimensions. The smaller the variance is, the stronger the similarity correlation between the corresponding multiple dimensions is, so an inverse proportional form is adopted.

[0035] Here, the degree of suspected abnormality of the data point is obtained by combining the degree of spatial distribution abnormality with the multidimensional similarity correlation: , is the suspected abnormality degree of the pth data point in the sample space; Represents the multidimensional similarity correlation of the pth data point in the sample space; Indicates the degree of abnormality of the spatial distribution of the pth data point in the sample space. The stronger the degree of abnormality of the spatial distribution of the pth data point, the stronger the multidimensional similarity correlation, and the stronger the suspected abnormality of the corresponding point.

[0036] From this, we can conclude that the more suspected anomalies each data point has, the stronger the degree of abnormality.

[0037] The abnormal data point detection unit is used to modify the initial neighbor quantity parameter of the data point using the suspected abnormality degree of the data point; and detect abnormal data points in the current monitoring data in the sample space using the modified neighbor quantity parameter of the data point.

[0038] After obtaining the suspected abnormality degree in the sample space, it is necessary to use the suspected abnormality degree to correct the initial neighbor number parameter of each data point to obtain the corrected neighbor number parameter; the ratio of the initial neighbor number parameter of the data point to the suspected abnormality degree of the data point is the corrected neighbor number parameter of the data point. The specific calculation formula is: , in, Represents the corrected neighbor number parameter of the pth data point in the sample space; Represents the parameter of the initial number of neighbors of the pth data point in the sample space; Indicates the suspected abnormality degree of the pth data point in the sample space; The stronger the suspected abnormality of the p-th point, the smaller the corresponding number of neighbors k, which can improve the sensitivity to outlier data points and effectively capture local anomalies; the weaker the suspected abnormality of the p-th point, the more the data is biased towards normal, the larger the number of neighbors k, and it is not easy to identify normal outliers as abnormalities. It should also be noted that after optimizing the initial neighbor number parameter, the corrected neighbor number parameter obtained may not be an integer, so it needs to be verified. In the present invention, rounding is used for integer rounding.

[0039] Furthermore, in the sample space, the LOF outlier detection algorithm is used to calculate the data points in the sample space based on the corrected neighbor number parameter of each data point to obtain the LOF value of each data point. If the LOF value is larger, it means that it is more abnormal, and vice versa, if it is smaller, it means that it is more normal. Furthermore, the absolute value of the difference between the LOF value of each data point and the mean LOF value of all data points is calculated and normalized to obtain the monitoring abnormality degree of each data point. The specific calculation formula is: , in, Indicates the monitoring abnormality degree of the pth data point; represents the LOF value of the pth data point; It represents the mean of the LOF values ​​of all data points in the current monitoring data; norm represents the normalization operation; It shows the difference between the LOF value of the pth data point and the mean LOF value. Since the cardinality of the LOF value of a smaller value is larger, the larger the difference is, the stronger the abnormality of the pth data point is. Here, norm is used for linear normalization.

[0040] Finally, the abnormal threshold Y is set. Preferably, the value of the abnormal threshold in the embodiment of the present invention is 0.6. The implementer can adjust the abnormal threshold Y according to the actual scenario or obtain it based on statistical analysis. When the monitoring abnormality degree of a data point is greater than or equal to the abnormal threshold, the data point is an abnormal data point. These abnormal data points are recorded and a warning is transmitted to the monitoring platform to remind the staff.

[0041] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The above is a description of a specific embodiment of this specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0042] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0043] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An artificial intelligence-based intelligent monitoring platform for power distribution station operation and maintenance, characterized in that: The platform includes: A data acquisition unit, used to collect current monitoring data of the power distribution station using sensors, wherein the monitoring data is multi-dimensional data; A sample space construction unit is used to obtain a data curve of each dimension based on the data of each dimension in the historical monitoring data; calculate the fluctuation state characteristic value of each dimension using the maximum longitudinal distance from each peak to its corresponding trough point in the data curve; and establish a sample space based on the fluctuation state characteristic value; The suspected abnormality degree calculation unit of the data point is used to calculate the abnormality degree of the spatial distribution of the data point according to the clustering result of the current monitoring data in the sample space; the multidimensional similarity correlation of the data point is calculated using the value of the data point in each dimension in the sample space; the sum of the abnormality degree of the spatial distribution of the data point and the multidimensional similarity correlation is the suspected abnormality degree; The abnormal data point detection unit is used to modify the initial neighbor quantity parameter of the data point using the suspected abnormality degree of the data point; and detect abnormal data points in the current monitoring data in the sample space using the modified neighbor quantity parameter of the data point.

2. According to claim 1, an artificial intelligence-based intelligent monitoring platform for power distribution station operation and maintenance, characterized in that: The method of calculating the fluctuation state characteristic value of each dimension by using the maximum longitudinal distance from each peak to its corresponding trough point in the data curve includes: Obtain the variance of the maximum longitudinal distance from each peak to its corresponding trough point in a data curve of one dimension, recorded as the longitudinal variance; obtain the sum of the distances from the horizontal coordinates of each peak to the horizontal coordinates of the corresponding trough points on the left and right sides, recorded as the span of the peak; obtain the variance of the span of each peak, recorded as the transverse variance; add the longitudinal variance and the transverse variance, compare the maximum longitudinal distance from each peak to its corresponding trough point with the summed result and sum them up to obtain the characteristic value of the fluctuation state of this dimension.

3. According to the artificial intelligence-based intelligent monitoring platform for power distribution station operation and maintenance according to claim 1, it is characterized in that: The establishing of a sample space based on the fluctuation state characteristic value comprises: The preset number of dimensions with the largest eigenvalues ​​of the fluctuation state are obtained to establish the sample space as the main dimensions.

4. According to the artificial intelligence-based intelligent monitoring platform for power distribution station operation and maintenance according to claim 1, it is characterized in that: The calculation of the degree of abnormality of spatial distribution of data points according to the clustering result of the current monitoring data in the sample space includes: Obtain the volume of the minimum bounding sphere of each point cluster in the clustering result; obtain the volume of the minimum bounding sphere of the point cluster where the data point is located in the current monitoring data after clustering; obtain the connecting line between the centroid of the point cluster where the data point is located and the centroid of other point clusters, obtain the number of data points within two unit lengths of the vertical distance connecting line, and remove the data points of the point clusters belonging to the two connecting lines. The number of remaining data points is the number of free data points corresponding to the connecting line; the degree of abnormality of the spatial distribution of the data point is obtained according to the volume of the minimum bounding sphere of the point cluster where the data point is located and the number of free data points corresponding to the connecting line between the centroid of the point cluster where the data point is located and the centroid of other point clusters.

5. The intelligent monitoring platform for power distribution station operation and maintenance based on artificial intelligence according to claim 4 is characterized in that: The calculation formula of the spatial distribution anomaly degree is specifically: ， in, Indicates the degree of abnormality of the spatial distribution of the pth data point; Represents the volume of the minimum circumscribed sphere of the point cluster where the pth data point is located; Represents the number of all point clusters; It represents the number of free data points corresponding to the line connecting the centroid of the point cluster where the p-th data point is located and the midline of the i-th point cluster outside the point cluster where the p-th data point is located.

6. The power distribution station intelligent monitoring platform based on artificial intelligence according to claim 1 is characterized in that: The calculation formula of the multi-dimensional similarity correlation of the data points is specifically: ， in, Represents the multidimensional similarity correlation of the p-th data point; Represents the value of the p-th data point in the t-th dimension; Represents the mean value of the data points in the tth dimension; and They represent the maximum and minimum values ​​of the data points in the t-th dimension respectively; σ[ ] represents the variance function; t represents the t-th dimension.

7. The intelligent monitoring platform for power distribution station operation and maintenance based on artificial intelligence according to claim 1 is characterized in that: The method of modifying the initial neighbor quantity parameter of the data point by using the suspected abnormality degree of the data point includes: The ratio of the initial number of neighbors of a data point to the suspected abnormality degree of the data point is the corrected number of neighbors of the data point.

8. The intelligent monitoring platform for power distribution station operation and maintenance based on artificial intelligence according to claim 1 is characterized in that: The method of detecting abnormal data points in the current monitoring data in the sample space by using the neighbor quantity parameter after the data point correction includes: In the sample space, the LOF outlier detection algorithm is used to calculate the data points in the sample space based on the corrected neighbor number parameter of each data point to obtain the LOF value of each data point; the absolute value of the difference between the LOF value of each data point and the mean LOF value of all data points is calculated and normalized to obtain the monitoring abnormality degree of each data point; an abnormal threshold is set, and when the monitoring abnormality degree of a data point is greater than or equal to the abnormal threshold, the data point is an abnormal data point.

Images