Intelligent analysis system and method for data exception of power equipment based on big data

Abstract

The invention discloses an intelligent analysis system and method for data exception of power equipment based on big data. The system comprises an information acquisition module; an Internet of Things module; a preprocessing module; a remote terminal system; a data analysis module; big database information; an alarm module; a mobile terminal module; the invention discloses a big data-based intelligent analysis method for data exception of power equipment. The method comprises the following steps of: acquiring operation data of the power equipment; collected data information is subjected to communication transmission; preprocessing the data information; analyzing and processing data; remote warning maintenance is carried out; according to the invention, the operation state information of the power equipment is acquired through the information acquisition module and is transmitted through the Internet of Things module, and the remote terminal system processes the data information remotely and calculates and analyzes the data information to obtain abnormal data information; the preprocessing module is used for improving the data accuracy; the fuzzy classification judges the data information abnormity through the distance, and the abnormity type is matched and judged through the abnormity type stored in the big database.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment data anomaly analysis, and specifically to a power equipment data anomaly intelligent analysis system and method based on big data. Background Art

[0002] With the increasing global energy demand and the acceleration of energy transformation, the power equipment industry is in a stage of rapid development. As an indispensable link in the power industry chain, power equipment covers all links from power generation to power transmission and transformation, to power distribution and power quality control, and plays a key role in ensuring the stable operation of the power system and improving the efficiency of power utilization. The industry's prosperity continues to rise.

[0003] Power equipment refers to various types of equipment and devices used in power generation, transmission, transformation, distribution, and power quality control. At present, power equipment can be classified into power generation equipment, power transmission and transformation equipment, power distribution equipment, power automation equipment, etc. according to its function and purpose.

[0004] The good operating status of power equipment is the basis for the safe, economical and stable operation of the power system. Power outages caused by equipment failures will seriously affect the stable operation of the power grid and cause huge economic losses. Therefore, for equipment operating in complex working conditions and harsh environments, comprehensive, timely and accurate monitoring and analysis of the equipment operating status is the top priority to ensure the safe and stable operation of the equipment. With the continuous improvement of the intelligence level of the power system, power equipment status analysis faces challenges such as a large number of equipment types, a large number of equipment, and a variety of status types.

[0005] In the Chinese invention patent with application publication number CN116955746A, a method for identifying users with abnormal electricity consumption based on big data is disclosed. By adopting smart meter equipment to collect user electricity consumption data in real time, and performing comprehensive processing of retrieval, denoising and feature extraction on the user electricity consumption data, the user electricity consumption characteristic data based on big data is determined. According to the user electricity consumption characteristic data based on big data, the user electricity consumption standard data that meets the user electricity consumption requirements is indexed and retrieved. Based on the user electricity consumption standard data, the user electricity consumption characteristic data is compared and analyzed to determine a user electricity consumption identification analysis report based on big data. Based on data mining technology, the user electricity consumption identification analysis report based on big data is subjected to correlation and association analysis to determine a user electricity consumption abnormality control strategy that matches the user electricity consumption identification analysis report. The abnormal electricity consumption users can be effectively identified and controlled, thereby improving the electricity consumption control effect of the power system. Based on the user power consumption abnormality control strategy, power consumption control is carried out on users with abnormal power consumption, early warning operations are carried out on users with abnormal power consumption, and the reasons for the abnormal power consumption of users are remotely sent to users with abnormal power consumption, guiding them to adjust their power consumption, and early warning operations are carried out on power maintenance personnel, and power maintenance personnel are guided to perform corresponding power maintenance and adjust the power operation status.

[0006] However, the above technology mainly detects the user's electricity usage, and does not deal with the abnormal conditions of the power equipment. In addition, the abnormal conditions of the power equipment during operation can easily cause damage to the circuit. Especially when the existing power equipment is in use, the amount of data is large, the processing difficulty is high, and it is not convenient for accurate analysis and processing.

[0007] To this end, the present invention provides a system and method for intelligent analysis of power equipment data anomalies based on big data. Summary of the invention

[0008] 1. Technical issues to be resolved In view of the deficiencies in the prior art, the present invention provides an intelligent analysis system and method for power equipment data anomalies based on big data, which realizes the transmission of remotely collected power equipment data information through the Internet of Things, and preprocesses the data information to improve the accuracy of the data information and prevent the data information from being interfered with, so that the remote terminal can easily calculate and process the data information. The remote terminal fuzzily classifies the data information to determine the distance between the data information and the cluster center, and determines whether the data information contains abnormal data based on the distance to the cluster center. In order to realize the inspection and maintenance of the power equipment, the abnormal type stored in the big database is matched to realize the determination of the abnormal type of the power equipment, which is convenient for repairing the power equipment, thereby solving the technical problems recorded in the background technology.

[0009] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: The power equipment data anomaly intelligent analysis system based on big data includes: An information collection module collects the operating status information of the power equipment through the information collection module, so as to calculate and analyze the collected data information and obtain abnormal information of the operating status of the power equipment; The Internet of Things module transmits the collected data information through the Internet of Things module, which is used to transmit the collected data information remotely, so that the remote terminal system can obtain the data information and perform calculation and analysis; The preprocessing module receives the collected data information after it is transmitted through the IoT module, and preprocesses the collected data information. After the preprocessing calculation, the accuracy of the data information is improved and the validity of the data information calculation is maintained; The remote terminal system acquires the data information collected by the information collection module through the remote terminal system, and performs calculation and analysis on the data information, so as to facilitate the calculation and analysis of the abnormal situation of the power equipment data, and analyzes and processes the abnormal situation of the power equipment operation according to the calculation results; Data analysis module: The data information after calculation and processing is analyzed and processed by the data analysis module, that is, the results of data information calculation and processing, as well as the types of anomalies matching the big data query, are analyzed and processed; Big database information, which stores abnormal situations through big database information, making it easier to match abnormal situations during analysis and processing; The alarm module, after the data calculation and analysis, if the power equipment data is found to be abnormal through the calculation and analysis, the alarm module will issue an alarm; The mobile terminal module transmits the data information after calculation, analysis and processing through the Internet of Things module, which facilitates the transmission of data information to the mobile terminal module, so that the power maintenance worker can maintain the power equipment.

[0010] Furthermore, the preprocessing module includes a data information acquisition unit for receiving data information, an analog-to-digital conversion unit for converting data information, a filtering unit for filtering out noise from the data information, the filtering unit filters out noise in the data information to eliminate the influence of the noise in the data information, a gain unit for amplifying the data information, the gain unit amplifies the data information to increase the strength of the data information to prevent the data information from being too weak and being lost, and a decompression unit for decompressing the data information, the decompression unit is used to decompress the data information compressed during the transmission process of the Internet of Things module.

[0011] Furthermore, the filtering unit performs filtering processing on the data information by the following formula; , in, represents the output data set after mean filtering, m represents the size of the window, Represents the jth data information in the input data set, and the movement unit each time is 1.

[0012] Furthermore, the alarm module includes an audible and visual alarm and a remote alarm unit. The audible and visual alarm is arranged on the remote terminal system and is used to give an alarm after abnormal data of the power equipment is obtained through calculation and analysis. The remote alarm unit is used to notify the mobile terminal module after calculation and analysis show that the power equipment data is abnormal. The remote alarm unit includes SMS notification, phone notification or APP notification, and mainly uses APP notification. If the maintenance personnel does not click to accept within five minutes after the APP notification, the maintenance personnel will be contacted via SMS notification and phone notification. After the APP notification, a record is retained, and the maintenance personnel's maintenance record is also reported to the retained record.

[0013] Furthermore, the remote terminal system includes a storage module, which includes a cache memory and a hard disk memory. The cache memory is used to receive the data information transmitted by the Internet of Things module, cache the transmitted data information, and receive the data information completely; The hard disk storage is used to store the transmitted data information, store and record the results of the calculation and analysis by the data analysis module, and record the subsequent maintenance information.

[0014] Furthermore, the preprocessing module is also used to perform dimensionality reduction processing on the collected data information, mapping the passing weight of the data information to the interval [0, 1], so as to facilitate the subsequent calculation and processing of the collected data information; , Where g is the result of weight normalization calculated by Gaussian function, and the output range is between 0 and 1. is the weight calculated by the Gaussian function, is the minimum value among the weights calculated by the Gaussian function, The maximum value among the weights calculated by the Gaussian function.

[0015] The method for intelligent analysis of power equipment data anomalies based on big data includes the following steps: Collecting the operating data of the power equipment: Collecting data information on the operating status of the power equipment through the information collection module to obtain the operating status of the power equipment; The collected data information is transmitted through communication: the data information collected by the information collection module is transmitted, and the collected data information is transmitted through the Internet of Things module to realize remote transmission of the data information and upload it to the remote terminal system; Preprocessing of data information: When the IoT module transmits data information, the preprocessing module receives, converts, filters out clutter, amplifies and decompresses the data information; Data analysis and processing: After the data information is pre-processed, the remote terminal system analyzes and processes the data information through the data analysis module, obtains the abnormal data of the power equipment operation through clustering processing, and obtains the abnormal type information stored in the big database system through the Internet of Things module, matches it with the abnormal data information, and obtains the abnormal type of the power equipment; Remote warning maintenance: After the data analysis module analyzes and processes, it is determined that there is an abnormality, and after matching the abnormality type, an alarm is issued through the alarm module. At the same time, the alarm module sends the abnormality information and type to the mobile terminal module through the Internet of Things module. The maintenance worker performs on-site maintenance and uploads the maintenance report for record.

[0016] Furthermore, the remote terminal system uses the following calculation formula to perform calculation when analyzing and processing the data: Enter an assignment, and the assignment is the cluster center c j , or a sample x i For cluster center c j The membership degree u ij , that is, x i Belongs to c j probability; , Among them, m is the number of clusters, N is the number of data information, c is the number of cluster centers, and c j represents the jth cluster center, x i represents the i-th sample, u ij Represents sample x i For cluster center c j The membership degree of is an arbitrary measure of data similarity, and ij Weights are introduced in the algorithm so that when calculating and analyzing data information, the focus is on the distance to the cluster center with high weights.

[0017] Furthermore, for the membership matrix u ij and cluster center c j Calculation: , where k represents the position in the membership matrix, and Represented as data sample x i The proportion of the average data in the jth cluster is used to calculate the orientation of the data sample, that is, for a single sample x i The sum of the membership of each cluster is 1. For each sample point, the class to which its membership is the largest belongs to that class. The closer it is to 1, the higher the membership, and vice versa. , in, Represents data sample x i For each cluster membership fit coefficient, the data sample x is calculated i With the cluster center c of each group i The distance between groups is minimized, which minimizes the objective function and ensures the clustering principle of the highest similarity within the group and the lowest similarity between groups.

[0018] Furthermore, the data analysis module matches and calculates the abnormal type information and abnormal data information stored in the large database system as shown below: , in, is the posterior probability, that is, the similarity after the abnormal data information is compared, N is the feature set for comparison and judgment, i represents the detection of a feature in the feature set, is the likelihood probability of the same abnormal information, is the prior probability of the same abnormal information, is the likelihood probability that it is not the same abnormal information, is the prior probability that it is not the same abnormal information.

[0019] (III) Beneficial effects The present invention provides a system and method for intelligent analysis of power equipment data anomalies based on big data, which has the following beneficial effects: When the present invention is used, the operating status information of the power equipment is collected through the information collection module, the status information of the power equipment is obtained, and the status information is transmitted through the Internet of Things module, so as to realize remote transmission processing of the data information, so that the remote terminal system can easily realize remote processing of the data information, analyze the operating status of the collected power equipment, and calculate and analyze the abnormal data information in the collected data information; Before transmitting the data information to the remote terminal system, the IoT module pre-processes the data information through the pre-processing module, receives, converts, filters out clutter, amplifies and decompresses the data information, so that the data information can be free of noise, which is convenient for the remote terminal system to analyze and calculate, and accurately obtain abnormal information in the data information; The remote terminal fuzzily classifies the data information, determines the distance between the data information and the cluster center, and determines whether the data information contains abnormal data based on the distance from the cluster center. After the remote terminal system calculates and analyzes the data information to obtain the abnormal data information, the remote terminal system queries the big database and matches the abnormal types stored in the big database to determine the abnormal type of the power equipment, making it easier for maintenance workers to perform targeted and rapid maintenance on the power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a structural schematic diagram of the power equipment data anomaly intelligent analysis system based on big data of the present invention; Figure 2 It is a flow chart of the method for intelligent analysis of power equipment data anomalies based on big data of the present invention. DETAILED DESCRIPTION

[0021] 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. 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.

[0022] See also Figure 1 The present invention provides an intelligent analysis system for power equipment data anomaly based on big data, comprising: An information collection module collects the operating status information of the power equipment through the information collection module, so as to calculate and analyze the collected data information and obtain abnormal information of the operating status of the power equipment; The Internet of Things module transmits the collected data information through the Internet of Things module, which is used to transmit the collected data information remotely, so that the remote terminal system can obtain the data information and perform calculation and analysis; The preprocessing module receives the collected data information after it is transmitted through the IoT module, and preprocesses the collected data information. After the preprocessing calculation, the accuracy of the data information is improved and the validity of the data information calculation is maintained; The remote terminal system acquires the data information collected by the information collection module through the remote terminal system, and performs calculation and analysis on the data information, so as to facilitate the calculation and analysis of the abnormal situation of the power equipment data, and analyzes and processes the abnormal situation of the power equipment operation according to the calculation results; Data analysis module: The data information after calculation and processing is analyzed and processed by the data analysis module, that is, the results of data information calculation and processing, as well as the types of anomalies matching the big data query, are analyzed and processed; Big database information, which stores abnormal situations through big database information, making it easier to match abnormal situations during analysis and processing; The alarm module, after the data calculation and analysis, if the power equipment data is found to be abnormal through the calculation and analysis, the alarm module will issue an alarm; The mobile terminal module transmits the data information after calculation, analysis and processing through the Internet of Things module, which facilitates the transmission of data information to the mobile terminal module, so that the power maintenance worker can maintain the power equipment.

[0023] In order to preprocess the data information, improve the accuracy of the data information, eliminate the noise in the data information, and prevent the loss of the data information, in the present embodiment, preferably, the preprocessing module includes a data information acquisition unit for receiving the data information, includes an analog-to-digital conversion unit for converting the data information, includes a filtering unit for filtering out noise from the data information, the filtering unit filters out the noise in the data information, eliminates the influence of the noise in the data information, includes a gain unit for amplifying the data information, the gain unit amplifies the data information, improves the strength of the data information, prevents the data information from being too weak and lost, and includes a decompression unit for decompressing the data information, the decompression unit is used to decompress the data information compressed during the transmission process of the Internet of Things module.

[0024] In order to filter out the noise in the collected data information and improve the accuracy of the data information, in this embodiment, preferably, the filtering unit filters the data information by the following formula: , in, represents the output data set after mean filtering, m represents the size of the window, Represents the jth data information in the input data set, and the movement unit each time is 1.

[0025] In order to implement warning and notification when abnormal data information is detected and calculated, in this embodiment, preferably, the alarm module includes an audible and visual alarm and a remote alarm unit, and the audible and visual alarm is arranged on the remote terminal system, and is used to warn after abnormal data of the power equipment is obtained through calculation and analysis; The remote alarm unit is used to notify the mobile terminal module after calculation and analysis show that the power equipment data is abnormal. The remote alarm unit includes SMS notification, phone notification or APP notification, and mainly uses APP notification. If the maintenance personnel does not click to accept within five minutes after the APP notification, the maintenance personnel will be contacted via SMS notification and phone notification. After the APP notification, a record is retained, and the maintenance personnel's maintenance record is also reported to the retained record.

[0026] In order to store the collected data information and store and record the processed data, in this embodiment, preferably, the remote terminal system includes a storage module, the storage module includes a cache memory and a hard disk memory, the cache memory is used to receive the data information transmitted by the Internet of Things module, to cache the transmitted data information, and to receive the data information completely; The hard disk storage is used to store the transmitted data information, store and record the results of the calculation and analysis by the data analysis module, and record the subsequent maintenance information.

[0027] In order to realize the dimensionality reduction processing of the collected data information and prevent the data information from being too large, causing the pressure and inefficiency of calculation, in this embodiment, preferably, the preprocessing module is also used to perform dimensionality reduction processing on the collected data information, and map the passing weight of the data information between the interval [0, 1], so as to facilitate the subsequent calculation and processing of the collected data information; , Where g is the result of weight normalization calculated by Gaussian function, and the output range is between 0 and 1. is the weight calculated by the Gaussian function, is the minimum value among the weights calculated by the Gaussian function, The maximum value among the weights calculated by the Gaussian function.

[0028] refer to Figure 2 , the intelligent analysis method of power equipment data anomaly based on big data includes the following steps: Collecting the operating data of the power equipment: Collecting data information on the operating status of the power equipment through the information collection module to obtain the operating status of the power equipment; The collected data information is transmitted through communication: the data information collected by the information collection module is transmitted, and the collected data information is transmitted through the Internet of Things module to realize remote transmission of the data information and upload it to the remote terminal system; Preprocessing of data information: When the IoT module transmits data information, the preprocessing module receives, converts, filters out clutter, amplifies and decompresses the data information; Data analysis and processing: After the data information is pre-processed, the remote terminal system analyzes and processes the data information through the data analysis module, obtains the abnormal data of the power equipment operation through clustering processing, and obtains the abnormal type information stored in the big database system through the Internet of Things module, matches it with the abnormal data information, and obtains the abnormal type of the power equipment; Remote warning maintenance: After the data analysis module analyzes and processes, it is determined that there is an abnormality, and after matching the abnormality type, an alarm is issued through the alarm module. At the same time, the alarm module sends the abnormality information and type to the mobile terminal module through the Internet of Things module. The maintenance worker performs on-site maintenance and uploads the maintenance report for record.

[0029] In order to realize clustering of the collected data information and to facilitate the determination of whether it is abnormal according to the distance between the data information and the cluster center, in this embodiment, preferably, the remote terminal system uses the following calculation formula for calculation when analyzing and processing the data: Enter an assignment, and the assignment is the cluster center c j , or a sample x i For cluster center c j The membership degree u ij , that is, x i Belongs to c j probability; , Among them, m is the number of clusters, N is the number of data information, c is the number of cluster centers, and c j represents the jth cluster center, x i represents the i-th sample, u ij Represents sample x i For cluster center c j The membership degree of is an arbitrary measure of data similarity, and ij Weights are introduced in the algorithm so that when calculating and analyzing data information, the focus is on the distance to the cluster center with high weights.

[0030] In order to calculate the clustering of data and the distance between the data and the cluster center, in this embodiment, preferably, for the membership matrix u ij and cluster center c j Calculation: , where k represents the position in the membership matrix, and Represented as data sample x i The proportion of the average data in the jth cluster is used to calculate the orientation of the data sample, that is, for a single sample x iThe sum of the membership of each cluster is 1. For each sample point, the class to which its membership is the largest belongs to that class. The closer it is to 1, the higher the membership, and vice versa. , in, Represents data sample x i For each cluster membership fit coefficient, the data sample x is calculated i With the cluster center c of each group i The distance between groups is minimized, which minimizes the objective function and ensures the clustering principle of the highest similarity within the group and the lowest similarity between groups.

[0031] In order to match and determine the calculated abnormal data information with the abnormal information stored in the big database, in this embodiment, preferably, the data analysis module matches and calculates the abnormal type information stored in the big database system with the abnormal data information as shown below: , in, is the posterior probability, that is, the similarity after the abnormal data information is compared, N is the feature set for comparison and judgment, i represents the detection of a feature in the feature set, is the likelihood probability of the same abnormal information, is the prior probability of the same abnormal information, is the likelihood probability that it is not the same abnormal information, is the prior probability that it is not the same abnormal information.

[0032] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired means (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available media can be magnetic media (for example, floppy disks, hard disks, tapes), optical media (for example, DVD ), or semiconductor media. The semiconductor media may be a solid state drive.

[0033] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0034] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0035] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0036] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0037] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0038] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U Disk, mobile hard disk, read-only memory ( read - onlymemory , ROM ), Random Access Memory ( RandomAccessMemory , RAM ), magnetic disks, optical disks, and other media that can store program codes.

[0039] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0040] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. The power equipment data anomaly intelligent analysis system based on big data is characterized by: Included are: An information collection module collects the operating status information of the power equipment through the information collection module, so as to calculate and analyze the collected data information and obtain abnormal information of the operating status of the power equipment; The Internet of Things module transmits the collected data information through the Internet of Things module, which is used to transmit the collected data information remotely, so that the remote terminal system can obtain the data information and perform calculation and analysis; The preprocessing module receives the collected data information after it is transmitted through the IoT module, and preprocesses the collected data information. After the preprocessing calculation, the accuracy of the data information is improved and the validity of the data information calculation is maintained; The remote terminal system acquires the data information collected by the information collection module through the remote terminal system, and performs calculation and analysis on the data information, so as to facilitate the calculation and analysis of the abnormal situation of the power equipment data, and analyzes and processes the abnormal situation of the power equipment operation according to the calculation results; Data analysis module: The data information after calculation and processing is analyzed and processed by the data analysis module, that is, the results of data information calculation and processing, as well as the types of anomalies matching the big data query, are analyzed and processed; Big database information, which stores abnormal situations through big database information, making it easier to match abnormal situations during analysis and processing; The alarm module, after the data calculation and analysis, if the power equipment data is found to be abnormal through the calculation and analysis, the alarm module will issue an alarm; The mobile terminal module transmits the data information after calculation, analysis and processing through the Internet of Things module, which facilitates the transmission of data information to the mobile terminal module, so that the power maintenance worker can maintain the power equipment.

2. The power equipment data anomaly intelligent analysis system based on big data according to claim 1 is characterized by: The preprocessing module includes a data information acquisition unit for receiving data information, an analog-to-digital conversion unit for converting data information, a filtering unit for filtering out noise from the data information, the filtering unit filters out noise in the data information and eliminates the influence of noise in the data information, a gain unit for amplifying the data information, the gain unit amplifies the data information, improves the strength of the data information, prevents the data information from being too weak and lost, and a decompression unit for decompressing the data information, the decompression unit is used to decompress the data information compressed during the transmission process of the Internet of Things module.

3. The power equipment data anomaly intelligent analysis system based on big data according to claim 2 is characterized by: The filtering unit filters the data information using the following formula; ， in, represents the output data set after mean filtering, m represents the size of the window, Represents the jth data information in the input data set, and the movement unit each time is 1.

4. The power equipment data anomaly intelligent analysis system based on big data according to claim 2 is characterized by: The alarm module includes an audible and visual alarm and a remote alarm unit. The audible and visual alarm is set on the remote terminal system and is used to warn after the calculation and analysis show that the power equipment data is abnormal. The remote alarm unit is used to notify the mobile terminal module after calculation and analysis show that the power equipment data is abnormal. The remote alarm unit includes SMS notification, phone notification or APP notification, and mainly uses APP notification. If the maintenance personnel does not click to accept within five minutes after the APP notification, the maintenance personnel will be contacted via SMS notification and phone notification. After the APP notification, a record is retained, and the maintenance personnel's maintenance record is also reported to the retained record.

5. The power equipment data anomaly intelligent analysis system based on big data according to claim 4 is characterized by: The remote terminal system includes a storage module, which includes a cache memory and a hard disk memory. The cache memory is used to receive the data information transmitted by the Internet of Things module, realize cache processing of the transmitted data information, and realize complete reception of the data information; The hard disk storage is used to store the transmitted data information, store and record the results of the calculation and analysis by the data analysis module, and record the subsequent maintenance information.

6. The power equipment data anomaly intelligent analysis system based on big data according to claim 1 is characterized by: The preprocessing module is also used to perform dimensionality reduction processing on the collected data information, mapping the passing weight of the data information to the interval [0, 1], so as to facilitate the subsequent calculation and processing of the collected data information; ， Where g is the result of weight normalization calculated by Gaussian function, and the output range is between 0 and 1. is the weight calculated by the Gaussian function, is the minimum value among the weights calculated by the Gaussian function, The maximum value among the weights calculated by the Gaussian function.

7. An intelligent analysis method for power equipment data anomaly based on big data, characterized in that: The following steps are included: Collecting the operating data of the power equipment: Collecting data information on the operating status of the power equipment through the information collection module to obtain the operating status of the power equipment; The collected data information is transmitted through communication: the data information collected by the information collection module is transmitted, and the collected data information is transmitted through the Internet of Things module to realize remote transmission of the data information and upload it to the remote terminal system; Preprocessing of data information: When the IoT module transmits data information, the preprocessing module receives, converts, filters out clutter, amplifies and decompresses the data information; Data analysis and processing: After the data information is pre-processed, the remote terminal system analyzes and processes the data information through the data analysis module, obtains the abnormal data of the power equipment operation through clustering processing, and obtains the abnormal type information stored in the big database system through the Internet of Things module, matches it with the abnormal data information, and obtains the abnormal type of the power equipment; Remote warning maintenance: After the data analysis module analyzes and processes, it is determined that there is an abnormality, and after matching the abnormality type, an alarm is issued through the alarm module. At the same time, the alarm module sends the abnormality information and type to the mobile terminal module through the Internet of Things module. The maintenance worker performs on-site maintenance and uploads the maintenance report for record.

8. The method for intelligent analysis of power equipment data anomalies based on big data according to claim 7 is characterized in that: The remote terminal system uses the following calculation formula to calculate and process the data: Enter an assignment, and the assignment is the cluster center c j , or a sample x i For cluster center c j The membership degree u ij , that is, x i Belongs to c j probability; ， Among them, m is the number of clusters, N is the number of data information, c is the number of cluster centers, and c j represents the jth cluster center, x i represents the i-th sample, u ij Represents sample x i For cluster center c j The membership degree of is an arbitrary measure of data similarity, and ij Weights are introduced in the algorithm so that when calculating and analyzing data information, the focus is on the distance to the cluster center with high weights.

9. The method for intelligent analysis of power equipment data anomalies based on big data according to claim 8 is characterized in that: For the membership matrix u ij and cluster center c j Calculation: ， where k represents the position in the membership matrix, and Represented as data sample x i The proportion of the average data in the jth cluster is used to calculate the orientation of the data sample, that is, for a single sample x i The sum of the membership of each cluster is 1. For each sample point, the class to which its membership is the largest belongs to that class. The closer it is to 1, the higher the membership, and vice versa. ， in, Represents data sample x i For each cluster membership fit coefficient, the data sample x is calculated i With the cluster center c of each group i The distance between groups is minimized, which minimizes the objective function and ensures the clustering principle of the highest similarity within the group and the lowest similarity between groups.

10. The method for intelligent analysis of power equipment data anomalies based on big data according to claim 7, characterized in that: The data analysis module matches and calculates the abnormal type information and abnormal data information stored in the large database system as shown below: ， in, is the posterior probability, that is, the similarity after the abnormal data information is compared, N is the feature set for comparison and judgment, i represents the detection of a feature in the feature set, is the likelihood probability of the same abnormal information, is the prior probability of the same abnormal information, is the likelihood probability that it is not the same abnormal information, is the prior probability that they are not the same abnormal information.

Images