Distribution network holographic data intelligent identification processing system

Abstract

The invention relates to the technical field of power grid automation, in particular to a distribution network holographic data intelligent identification processing system which comprises an inertial data analysis module, a real-time monitoring module, a distribution network data analysis module, a label setting module and a data identification module. The method comprises the following steps: retrieving an equipment fault position existing in a power distribution network through an inertial data analysis module, analyzing fault characteristics of the equipment fault position to obtain a fault characteristic curve of the equipment fault position, and then collecting and processing holographic data of the power distribution network in real time to obtain a data fluctuation set; the method comprises the following steps: calculating a similarity value of a unit interval and a data fluctuation set, setting a data label for a target monitoring position based on the similarity value, calculating a priority value based on a priority identifier in the data label, and finally performing priority processing on real-time operation data of the target monitoring position according to the size of the priority value, thereby facilitating optimal allocation of resources and improving the accuracy of the real-time operation data. And the abnormal data can be quickly responded and processed.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid automation, and in particular to a distribution network holographic data intelligent recognition and processing system. Background Art

[0002] Distribution network holographic data refers to the deployment of intelligent terminal sensing devices and edge computing devices on distribution network equipment, which uses high-precision three-dimensional digital technology and real-time data collection to perform one-to-one three-dimensional restoration and digital panoramic presentation of distribution network equipment and operating status.

[0003] Prior art CN115730410A discloses a method for constructing a grid topology of a power distribution network based on a holographic data model of power distribution and utilization, comprising: obtaining graphic data of a plurality of power grid devices in a power grid PMS system, converting the graphic data into topology data, and writing the topology data into a graph database; based on the graph database, identifying a substation node in a plurality of power grid devices and a plurality of pole tower nodes having a connection relationship therewith; determining sag-related parameters based on the distance between each two adjacent pole towers in the plurality of pole tower nodes, and constructing a sag line segment function based on the sag-related parameters; drawing an overhead line curve between each two adjacent pole towers based on the sag line segment function to obtain a grid topology diagram of a power distribution network;

[0004] However, the amount of data collected and processed by the distribution network holographic data center is large, which not only requires strong computing power support, but also takes a long time to analyze and process, resulting in poor real-time performance of the data and difficulty in responding to the data in real time. Delayed data response will lead to delayed warning of abnormal data failures in the distribution network, posing a threat to the safety of the distribution network. Summary of the invention

[0005] The purpose of the present invention is to solve the problems in the background technology and to propose a distribution network holographic data intelligent recognition and processing system.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A distribution network holographic data intelligent recognition and processing system, comprising:

[0008] The inertial data analysis module identifies the individual accessories in the distribution network based on the equipment operation information of the distribution network, matches the corresponding equipment fault location according to the accessory information of the individual accessories, and then marks the fault cause of the equipment fault location as the target fault, and obtains the abnormal data packet of the target fault, which includes the fault data of the target fault and the monitoring data before the fault, and then determines the fault characteristic curve of the target fault based on the abnormal data packet;

[0009] The real-time monitoring unit is used to monitor and collect the distribution network holographic data in real time to obtain the real-time operation data of the distribution network;

[0010] The distribution network data analysis module is used to correspond the real-time operation data with the collection location, set the target monitoring location at the same time, mark the real-time operation data of the target monitoring location as the target data, and perform data processing on the target data to obtain the data fluctuation set of the target monitoring location, then set the unit interval on the fault characteristic curve of the target monitoring location, and then calculate the similarity value between the elements in the data fluctuation set and the unit interval, and determine the real-time operation status of the target monitoring location according to the similarity value, wherein the real-time operation status includes the normal operation status and the abnormal operation status;

[0011] A label setting module is used to set a data label for the target monitoring position according to the real-time operating status of the target detection position, wherein the data label includes a time mark and a priority mark. When the data label is a priority mark, the priority value of the target detection position is calculated based on the similarity value and the endpoint value of the unit interval;

[0012] The data identification module is used to identify the data tag and give priority to the target data of the target monitoring location according to the priority identification and priority value in the data tag.

[0013] As a further solution of the present invention, a method for determining a device fault location includes:

[0014] Based on the visual structure of the target distribution network, the existing components in the target distribution network are identified and marked as single components, where the target distribution network refers to the distribution system that uses holographic three-dimensional sensing technology for data collection and monitoring, and the visual structure refers to the three-dimensional space model of the target distribution network;

[0015] The accessory information of a single accessory is used as a search keyword, and a search is performed on the Internet information terminal to obtain the operating failures that have occurred in the historical operation of the single accessory. Then, according to the location of the operating failure in the single accessory, the corresponding location is marked as the equipment failure location. The accessory information refers to the accessory name, model and function of the single accessory.

[0016] As a further solution of the present invention, a method for calculating a fault characteristic curve of a target fault includes:

[0017] Randomly select a device fault location as the fault object, and mark the fault cause corresponding to the device fault location as the target fault, and obtain n fault data and front-end data of the target fault. The fault data refers to the monitoring data displayed in the single device after the target fault has occurred in the single accessory. The front-end data refers to the monitoring data collected from the single device within a period of time before the target fault occurs in the single device. n is the threshold;

[0018] Bind a fault data and its corresponding front-end data and mark them as abnormal data packets;

[0019] With time as the horizontal axis and monitoring data as the vertical axis, a two-dimensional coordinate system is set, and then an abnormal data packet is used as a unit, and the data in the abnormal data packet is linearly fitted in the two-dimensional coordinate system to obtain the abnormal linear function y=F(x);

[0020] Perform a derivative operation on the abnormal linear function y=F(x), and mark the result of the operation as the trend function f, further f=F'(x);

[0021] According to the above processing method, the trend function fi of all abnormal data packets of the target fault is calculated, i∈[1,n], indicating that there are n trend functions in total;

[0022] Then, the polyfit function in MATLAB is used to fit the n trend functions fi into a curve and mark it as the fault characteristic curve of the target fault.

[0023] As a further solution of the present invention, a method for calculating similarity values ​​between elements in a data fluctuation set and a unit interval includes:

[0024] The real-time operation data is classified according to the data collection location, and then a data collection location is arbitrarily selected as the target monitoring location. At the same time, the real-time operation data continuously collected by the target monitoring location in the previous unit time is obtained with the current time as the node, and marked as the target data CM j , j∈[1, J], indicating that j sets of data are collected at the target monitoring location within a unit time;

[0025] Arrange the target data in the order of the time of collection, calculate the instantaneous change value Bb of the target data, and use the instantaneous change value as an element to obtain the data fluctuation set Db of the target monitoring position, where Db = {Bb}, Bb = CM j -CM j-1 , where j starts at 2 and b = j-1;

[0026] Extract the fault characteristic curve corresponding to the target monitoring location, and set data nodes in the fault characteristic curve according to the equipment collection interval time;

[0027] According to the data length in the data fluctuation set Db, several unit intervals are set in the fault characteristic curve, wherein the number of data nodes in each unit interval is the same as the number of elements in the data fluctuation set;

[0028] Afterwards based on The similarity coefficient r between the data fluctuation set and the unit interval is obtained, where Ba is the mean of the elements in the data fluctuation set Db, Tb is the data node in the unit interval, and Ta is the mean of the data node in the unit interval.

[0029] As a further solution of the present invention, a method for determining the real-time operating status of a target monitoring position includes:

[0030] Compare the similarity coefficients r of all unit intervals in the fault characteristic curve and take the maximum value rmax of the similarity coefficient;

[0031] Compare rmax with the similarity threshold XS. If rmax<XS, the real-time operating state of the target monitoring location is marked as a normal operating state. If rmax≥XS, the real-time operating state of the target monitoring location is marked as an abnormal operating state.

[0032] As a further solution of the present invention, the processing method of the label setting module includes:

[0033] Identify the real-time operating status of the target monitoring location, and if the real-time operating status is a normal operating status, set the data tag to a time mark;

[0034] If the real-time operating status of the target monitoring position is an abnormal operating status, the corresponding data label is set as the priority mark, and the unit interval corresponding to the similarity coefficient rmax is marked as the control interval, the endpoint values ​​of the control interval are identified, and the endpoint values ​​are marked as QR and QL respectively, QL is the leftmost data node of the control interval, and QR is the rightmost data node of the control interval;

[0035] Then based on the formula The priority value YX corresponding to the target monitoring position is obtained, where ZL is the leftmost data node in the fault characteristic curve, ZR is the rightmost data node in the fault characteristic curve, α1 and α2 are both proportional coefficients, and rmax is the maximum value of the similarity coefficient.

[0036] As a further solution of the present invention, the identification method of the data identification module specifically includes:

[0037] If the data tag is a time tag, the corresponding real-time operation data will be processed in the order of the collected time. If the data tag is a priority tag, the target data of the target monitoring position with the largest priority value will be processed first according to the priority value of the priority tag.

[0038] As a further solution of the present invention, the inertial data analysis module includes a position determination unit and a feature analysis unit;

[0039] The location determination unit is used to identify the equipment fault location in the distribution network, the feature analysis unit is used to determine the fault characteristics of the equipment fault location and determine the fault characteristic curve, and the location determination unit and the feature analysis unit are respectively connected to the distribution network data analysis module for unidirectional communication.

[0040] As a further solution of the present invention, it also includes a cloud data storage module for storing equipment operation information of the distribution network, the equipment operation information includes distribution network abnormal time records, power grid monitoring data and power grid fault data, and at the same time, there is a one-way communication connection between the cloud data storage module and the inertial data analysis module.

[0041] Compared with the prior art, the advantages of the present invention are:

[0042] The present invention retrieves the equipment fault position existing in the distribution network through an inertial data analysis module, analyzes the fault characteristics of the equipment fault position, obtains the fault characteristic curve of the equipment fault position, and then collects and processes the distribution network holographic data in the distribution network in real time to obtain a data fluctuation set, obtains the fault characteristic curve of this position according to the collected position, divides the fault characteristic curve into multiple unit intervals according to the data length of the collected data fluctuation set, and calculates the similarity value between the unit interval and the data fluctuation set, and then sets a data label for the target monitoring position based on the similarity value, and calculates the priority value based on the priority identifier in the data label according to the similarity value, and finally prioritizes the real-time operation data of the target monitoring position according to the size of the priority value, which is helpful for optimizing the allocation of resources and ensuring that abnormal data is quickly responded to and processed. At the same time, the real-time operation data of the target monitoring position with the largest priority value is prioritized, which is helpful for timely discovery and response to potential safety issues. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0044] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0045] Reference Figure 1 , a distribution network holographic data intelligent identification and processing system, including a cloud data storage module, an inertial data analysis module, a real-time monitoring module, a distribution network data analysis module, a label setting module and a data identification module;

[0046] The cloud data storage module is used to store the equipment operation information of the distribution network. At the same time, there is a one-way communication connection between the cloud data storage module and the inertial data analysis module. The equipment operation information includes the abnormal time record of the distribution network, the power grid monitoring data and the power grid fault data;

[0047] The inertial data analysis module is used to perform inertial analysis on the equipment operation information of the distribution network, and determine the equipment fault location and fault characteristics of the distribution network according to the analysis results;

[0048] Specifically, the inertial data analysis module includes a position determination unit and a feature analysis unit, wherein the position determination unit is used to identify the equipment fault location in the distribution network, and the feature analysis unit is used to determine the fault characteristics of the equipment fault location, and the position determination unit and the feature analysis unit are respectively connected to the distribution network data analysis module in a unidirectional communication manner;

[0049] The location determination unit and the feature analysis unit are in a one-way communication connection, and the method for determining the location of the equipment fault by the location determination unit includes:

[0050] Based on the visual structure of the target distribution network, the existing components in the target distribution network are identified and marked as single components, where the target distribution network refers to the distribution system that uses holographic three-dimensional sensing technology for data collection and monitoring, and the visual structure refers to the three-dimensional space model of the target distribution network;

[0051] The accessory information of a single accessory is used as a search keyword, and a search is performed on the Internet information terminal to obtain the operating faults that have occurred in the historical operation of the single accessory. Then, according to the position of the operating fault in the single accessory, the corresponding position is marked as the equipment fault position. The accessory information refers to the name, model, function and other parameters of the single accessory;

[0052] It should be further explained that there may be only one device failure location in a single accessory, or there may be multiple device failure locations;

[0053] The method for the feature analysis unit to determine the fault feature includes:

[0054] Arbitrarily select a device fault location as the fault object, and mark the fault cause corresponding to the device fault location as the target fault, and obtain n fault data and front-end data of the target fault, wherein the fault data refers to the monitoring data displayed in the single device after the target fault has occurred in the single accessory, and the front-end data refers to the monitoring data collected from the single device within a period of time before the target fault occurs in the single device, and n is a threshold value, and in this embodiment, n is 100;

[0055] It should be further explained that there is a one-to-one correspondence between the fault data of the target fault and the front-end data;

[0056] Bind a fault data and its corresponding front-end data, and mark them as abnormal data packets. Set the time as the horizontal coordinate and the monitoring data as the vertical coordinate, and set a two-dimensional coordinate system. Take an abnormal data packet as a unit, and perform linear fitting on the data in the abnormal data packet in the two-dimensional coordinate system to obtain the abnormal linear function y=F(x).

[0057] It should be further explained that the linear fitting method in this embodiment is selected as the gradient descent method. By continuously adjusting the parameters, the loss function value is made to decrease along the gradient direction until the minimum value is found, thereby completing the linear fitting process. The specific operation process of the gradient descent method is a prior art and will not be described in detail here.

[0058] Then, the derivative operation is performed on the abnormal linear function y=F(x), and the result after the operation is marked as the trend function f, and further f=F'(x);

[0059] According to the above processing method, the trend function fi of all abnormal data packets of the target fault is calculated, i∈[1,n], indicating that there are n trend functions in total;

[0060] Then, mathematical tools are used to fit the n trend functions fi into a curve, which is marked as the fault characteristic curve of the target fault;

[0061] In this embodiment, the mathematical tool uses the polyfit function in MATLAB. According to the trend function, the data points of multiple curves are generated, and the polyfit function is used to obtain the fitting polynomial coefficients. Then, the fitting accuracy is controlled by adjusting the polynomial degree. The specific fitting process is a prior art and will not be described in detail here.

[0062] The equipment fault locations in all single accessories are taken as fault objects in turn, and the fault causes corresponding to the fault locations are taken as target faults, and the fault characteristic curves of all equipment fault locations are calculated according to the above method;

[0063] The real-time monitoring module is used to monitor and collect the distribution network holographic data in real time to obtain the real-time operation data of the distribution network. The real-time monitoring module then transmits the real-time operation data to the distribution network data analysis module. The distribution network holographic data refers to the one-to-one three-dimensional restoration and digital panoramic presentation of the distribution network equipment and operation status through high-precision three-dimensional digital technology and real-time data collection;

[0064] The distribution network data analysis module determines the real-time operation status of the distribution network based on the real-time operation data. The specific method for determining the real-time operation status includes:

[0065] First, the real-time operation data is classified according to the data collection location, and then a data collection location is arbitrarily selected as the target monitoring location. At the same time, the real-time operation data continuously collected by the target monitoring location in the previous unit time is obtained with the current time as the node, and marked as the target data CM j , j∈[1, J], indicating that j sets of data are collected at the target monitoring position in a unit time, wherein the specific value of the unit time is determined by technicians in this field according to actual equipment parameters;

[0066] Arrange the target data in the order of the time of collection, then calculate the instantaneous change value Bb of the target data, and use the instantaneous change value as an element to obtain the data fluctuation set Db of the target monitoring position. Further, Db={Bb}, Bb=CM j -CM j-1 , where j starts at 2 and b = j-1;

[0067] Extract the fault characteristic curve corresponding to the target monitoring location, and set data nodes in the fault characteristic curve according to the equipment collection interval time;

[0068] According to the data length in the data fluctuation set Db, several unit intervals are set in the fault characteristic curve, wherein the number of data nodes in each unit interval is the same as the number of elements in the data fluctuation set;

[0069] Afterwards based on The similarity coefficient r between the data fluctuation set and the unit interval is obtained, where Ba is the mean of the elements in the data fluctuation set Db, Tb is the data node in the unit interval, and Ta is the mean of the data node in the unit interval;

[0070] Compare the similarity coefficients r of all unit intervals in the fault characteristic curve, take the maximum value rmax of the similarity coefficient, and then compare rmax with the similarity threshold XS. If rmax<XS, the real-time operating state of the target monitoring position is marked as a normal operating state. If rmax≥XS, the real-time operating state of the target detection position is marked as an abnormal operating state. The similarity threshold XS is obtained by technicians in this field based on big data calculations.

[0071] The distribution network data analysis module and the tag setting module are connected in a one-way communication;

[0072] The label setting module is used to set data labels for the real-time operation data collected at the target monitoring location according to the real-time operation status. The specific data label setting method includes:

[0073] First, the real-time operating status of the target monitoring location is identified. If the real-time operating status is a normal operating status, the data tag is set to a time tag, that is, the real-time operating data of the target monitoring location is processed according to the time sequence of the collection;

[0074] If the real-time operating status of the target monitoring position is an abnormal operating status, the corresponding data label is set as the priority mark, and the unit interval corresponding to the similarity coefficient rmax is marked as the control interval, the endpoint values ​​of the control interval are identified, and the endpoint values ​​are marked as QR and QL respectively, QL is the leftmost data node of the control interval, and QR is the rightmost data node of the control interval;

[0075] Then based on the formula The priority value YX corresponding to the target monitoring position is obtained, wherein ZL is the leftmost data node in the fault characteristic curve, ZR is the rightmost data node in the fault characteristic curve, α1 and α2 are both proportional coefficients, and the specific values ​​of α1 and α2 are obtained by technicians in this field after big data calculation;

[0076] After that, there is a one-way communication connection between the tag setting module and the data identification module;

[0077] The data identification module is used to identify the data tags of real-time operation data. If the data tag is a time tag, the corresponding real-time operation data will be processed in the order of the collection time. If the data tag is a priority tag, the target data of the target monitoring location with the largest priority value will be prioritized according to the priority value of the priority tag, which helps to timely discover and respond to potential safety issues.

[0078] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A distribution network holographic data intelligent recognition and processing system, characterized in that: include: The inertial data analysis module identifies the individual accessories in the distribution network based on the equipment operation information of the distribution network, matches the corresponding equipment fault location according to the accessory information of the individual accessories, and then marks the fault cause of the equipment fault location as the target fault, and obtains the abnormal data packet of the target fault, which includes the fault data of the target fault and the monitoring data before the fault, and then determines the fault characteristic curve of the target fault based on the abnormal data packet; The real-time monitoring unit is used to monitor and collect the distribution network holographic data in real time to obtain the real-time operation data of the distribution network; The distribution network data analysis module is used to correspond the real-time operation data with the collection location, set the target monitoring location at the same time, mark the real-time operation data of the target monitoring location as the target data, and perform data processing on the target data to obtain the data fluctuation set of the target monitoring location, then set the unit interval on the fault characteristic curve of the target monitoring location, and then calculate the similarity value between the elements in the data fluctuation set and the unit interval, and determine the real-time operation status of the target monitoring location according to the similarity value, wherein the real-time operation status includes the normal operation status and the abnormal operation status; A label setting module is used to set a data label for the target monitoring position according to the real-time operating status of the target detection position, wherein the data label includes a time mark and a priority mark. When the data label is a priority mark, the priority value of the target detection position is calculated based on the similarity value and the endpoint value of the unit interval; The data identification module is used to identify the data tag and give priority to the target data of the target monitoring location according to the priority identification and priority value in the data tag.

2. A distribution network holographic data intelligent recognition and processing system according to claim 1, characterized in that: Methods for determining the location of equipment failure include: Based on the visual structure of the target distribution network, the existing components in the target distribution network are identified and marked as single components, where the target distribution network refers to the distribution system that uses holographic three-dimensional sensing technology for data collection and monitoring, and the visual structure refers to the three-dimensional space model of the target distribution network; The accessory information of a single accessory is used as a search keyword, and a search is performed on the Internet information terminal to obtain the operating failures that have occurred in the historical operation of the single accessory. Then, according to the location of the operating failure in the single accessory, the corresponding location is marked as the equipment failure location. The accessory information refers to the accessory name, model and function of the single accessory.

3. A distribution network holographic data intelligent recognition and processing system according to claim 1, characterized in that: The calculation method of the fault characteristic curve of the target fault includes: Randomly select a device fault location as the fault object, and mark the fault cause corresponding to the device fault location as the target fault, and obtain n fault data and front-end data of the target fault. The fault data refers to the monitoring data displayed in the single device after the target fault has occurred in the single accessory. The front-end data refers to the monitoring data collected from the single device within a period of time before the target fault occurs in the single device. n is the threshold; Bind a fault data and its corresponding front-end data and mark them as abnormal data packets; With time as the horizontal axis and monitoring data as the vertical axis, a two-dimensional coordinate system is set, and then an abnormal data packet is used as a unit, and the data in the abnormal data packet is linearly fitted in the two-dimensional coordinate system to obtain the abnormal linear function y=F(x); Perform a derivative operation on the abnormal linear function y=F(x), and mark the result of the operation as the trend function f, further f=F'(x); According to the above processing method, the trend function fi of all abnormal data packets of the target fault is calculated, i∈[1,n], indicating that there are n trend functions in total; Then, the polyfit function in MATLAB is used to fit the n trend functions fi into a curve and mark it as the fault characteristic curve of the target fault.

4. A distribution network holographic data intelligent recognition and processing system according to claim 1, characterized in that: The calculation method of the similarity value between the elements in the data fluctuation set and the unit interval includes: The real-time operation data is classified according to the data collection location, and then a data collection location is arbitrarily selected as the target monitoring location. At the same time, the real-time operation data continuously collected by the target monitoring location in the previous unit time is obtained with the current time as the node, and marked as the target data CM j , j∈[1, J], indicating that j sets of data are collected at the target monitoring location in unit time; Arrange the target data in the order of the time of collection, calculate the instantaneous change value Bb of the target data, and use the instantaneous change value as an element to obtain the data fluctuation set Db of the target monitoring position, where Db = {Bb}, Bb = CM j -CM j-1 , where j starts at 2 and b = j-1; Extract the fault characteristic curve corresponding to the target monitoring location, and set data nodes in the fault characteristic curve according to the equipment collection interval time; According to the data length in the data fluctuation set Db, several unit intervals are set in the fault characteristic curve, wherein the number of data nodes in each unit interval is the same as the number of elements in the data fluctuation set; Afterwards based on The similarity coefficient r between the data fluctuation set and the unit interval is obtained, where Ba is the mean of the elements in the data fluctuation set Db, Tb is the data node in the unit interval, and Ta is the mean of the data node in the unit interval.

5. A distribution network holographic data intelligent recognition and processing system according to claim 4, characterized in that: The method for determining the real-time operating status of the target monitoring location includes: Compare the similarity coefficients r of all unit intervals in the fault characteristic curve and take the maximum value rmax of the similarity coefficient; Compare rmax with the similarity threshold XS. If rmax<XS, the real-time operating state of the target monitoring location is marked as a normal operating state. If rmax≥XS, the real-time operating state of the target monitoring location is marked as an abnormal operating state.

6. A distribution network holographic data intelligent recognition and processing system according to claim 1, characterized in that: The processing methods of the label setting module include: Identify the real-time operating status of the target monitoring location, and if the real-time operating status is a normal operating status, set the data tag to a time mark; If the real-time operating status of the target monitoring position is an abnormal operating status, the corresponding data label is set as the priority mark, and the unit interval corresponding to the similarity coefficient rmax is marked as the control interval, the endpoint values ​​of the control interval are identified, and the endpoint values ​​are marked as QR and QL respectively, QL is the leftmost data node of the control interval, and QR is the rightmost data node of the control interval; Then based on the formula The priority value YX corresponding to the target monitoring position is obtained, where ZL is the leftmost data node in the fault characteristic curve, ZR is the rightmost data node in the fault characteristic curve, α1 and α2 are both proportional coefficients, and rmax is the maximum value of the similarity coefficient.

7. A distribution network holographic data intelligent recognition and processing system according to claim 1, characterized in that: The identification method of the data identification module specifically includes: If the data tag is a time tag, the corresponding real-time operation data will be processed in the order of the collected time. If the data tag is a priority tag, the target data of the target monitoring position with the largest priority value will be processed first according to the priority value of the priority tag.

8. The distribution network holographic data intelligent recognition and processing system according to claim 1 is characterized in that: The inertial data analysis module includes a position determination unit and a feature analysis unit; The location determination unit is used to identify the equipment fault location in the distribution network, the feature analysis unit is used to determine the fault characteristics of the equipment fault location and determine the fault characteristic curve, and the location determination unit and the feature analysis unit are respectively connected to the distribution network data analysis module for unidirectional communication.

9. The distribution network holographic data intelligent recognition and processing system according to claim 1 is characterized in that: It also includes a cloud data storage module for storing equipment operation information of the distribution network. The equipment operation information includes distribution network abnormal time records, power grid monitoring data and power grid fault data. At the same time, there is a one-way communication connection between the cloud data storage module and the inertial data analysis module.

Images