Intelligent fault analysis and management system and method based on big data

Abstract

The invention provides an intelligent fault analysis and management system and method based on big data, and the method comprises the steps: carrying out the architecture development through employing a Spring Cloud technology stack, generating a multi-dimensional fault management platform corresponding to each service station, carrying out the editing and creation of a manual library of the service station through employing the multi-dimensional fault management platform, and carrying out the analysis and management of the manual library. Generating a fault identification list corresponding to each service station, determining fault features of the corresponding service station according to the real-time data corresponding to each service station, identifying the corresponding fault features in the fault identification list, determining fault information corresponding to each service station, and performing deep mining on the fault information in the multi-dimensional fault management platform. And determining and displaying the compensation mode corresponding to each service station, thereby effectively solving the problems in the aspects of fault processing, drawing management, data analysis, operation and maintenance efficiency and the like in the prior art, and providing powerful support for intelligent operation and maintenance transformation.

Description

Technical Field

[0001] The present invention relates to the technical field of fault analysis management, and in particular to an intelligent fault analysis and management system and method based on big data. Background Art

[0002] In the current management system, facing the increasingly large and complex power equipment network, the traditional fault handling methods show obvious limitations. These methods often rely on the experience judgment and manual records of operation and maintenance personnel, which is not only inefficient, but also difficult to ensure the timeliness and accuracy of fault handling. The management of manuals and drawings is usually scattered, and there is a lack of a unified online platform, which causes operation and maintenance personnel to spend a lot of time looking for relevant information during the fault handling process. In addition, the statistical analysis of equipment failure data also mostly relies on manual collation, which makes it difficult to achieve deep mining and intelligent analysis of data, and cannot provide strong support for operation and maintenance decisions. In addition, the traditional query based on paper fault manuals or query based on electronic documents can no longer meet the rapid processing of equipment failures. At the same time, paper fault manuals have problems such as bulky and inconvenient query, while electronic documents have problems such as inconvenient query and poor interactive experience, and low query efficiency, which increases the difficulty of operation and maintenance for new employees and reduces the efficiency of maintenance.

[0003] Therefore, the present invention provides an intelligent fault analysis and management system and method based on big data. Summary of the invention

[0004] The present invention provides an intelligent fault analysis and management system and method based on big data, which effectively solves the problems existing in the prior art in fault handling, drawing management, data analysis and operation and maintenance efficiency, and provides strong support for the transformation to intelligent operation and maintenance.

[0005] The present invention provides an intelligent fault analysis and management system based on big data, comprising:

[0006] The multi-dimensional management module is used to develop the architecture using the Spring Cloud technology stack and generate a multi-dimensional fault management platform corresponding to each service station;

[0007] A data management module, used to edit and create a manual library of the service station using the multi-dimensional fault management platform, and generate a fault identification list corresponding to each service station;

[0008] An analysis implementation module, used to determine the fault characteristics of the corresponding service station according to the real-time data corresponding to each of the service stations, identify the corresponding fault characteristics in the fault identification list, and determine the fault information corresponding to each of the service stations;

[0009] The fault management module is used to perform in-depth mining of the fault information in the multi-dimensional fault management platform, determine the corresponding compensation method for each service station and display it.

[0010] In one practicable manner,

[0011] The multi-dimensional fault management platform includes:

[0012] A manual management sub-platform, for classifying the corresponding manual library according to a specified document structure by using semantic analysis, and generating a manual document for each of the service stations;

[0013] The command response sub-platform is used to search for the corresponding target manual in the manual document and display it based on the search command issued by the operation and maintenance personnel;

[0014] The offline buffering sub-platform is used to buffer the manual document offline.

[0015] In one practicable manner,

[0016] The multi-dimensional management module comprises:

[0017] A microservice architecture unit, used to respectively obtain site location information and work attribute information corresponding to each service station, create an initial analysis management platform using the site location information and work attribute information, and divide the initial analysis management platform into a plurality of microservices using the Spring Cloud technology stack;

[0018] A functional analysis unit is used to trace the source of each microservice, determine the service object corresponding to each microservice, collect the functional attribute information corresponding to each service object, analyze the topological relationship between different functional attribute information according to the distribution of the microservices in the initial analysis management platform, and generate a functional topology network;

[0019] A function deployment unit, configured to generate a function annotation of a corresponding service object based on the node data corresponding to each topological node in the functional topological network, determine a docking function corresponding to each of the service objects in combination with the network logic of the functional topological network, and perform function deployment on the corresponding microservices using the docking function to obtain available microservices corresponding to each of the service stations;

[0020] The platform construction unit is used to identify the high-frequency faults corresponding to each of the service stations based on the site location information and work attribute information corresponding to each of the service stations, use the high-frequency faults to enhance the functions of the available microservices, and establish a multi-dimensional fault management platform corresponding to each of the service stations in combination with the preset platform construction technology.

[0021] In one practicable manner,

[0022] The platform construction unit comprises:

[0023] A fault identification subunit is used to draw a service station function structure diagram based on the initial analysis management platform, determine the dynamic working information and static working information of the corresponding service station according to the site location information and working attribute information corresponding to each of the service stations, and sequentially delete each of the dynamic working information and static working information in the service station function structure diagram to obtain a dynamic fault threshold and a static fault threshold corresponding to each of the service stations;

[0024] A fault mining subunit is used to generate a number of dynamic faults and static faults corresponding to each of the service stations by using each of the available microservices in combination with the corresponding dynamic fault threshold and static fault threshold, retrieve historical faults of similar service stations in the big data center based on the working attribute information of the service station, and determine a number of high-frequency faults of each of the service stations based on a first similarity between each of the dynamic faults and the historical faults and a second similarity between each of the static faults and the historical faults;

[0025] A service enhancement subunit is used to obtain the fault level and fault performance corresponding to each of the high-frequency faults, establish mirror service information using the fault level and the fault performance, and enhance the functions of the corresponding available microservices using the mirror service information to obtain the preferred microservice corresponding to each of the service stations;

[0026] The platform building sub-unit is used to build a platform structure based on the front-end framework, back-end technology and the interaction mode between the databases corresponding to the initial analysis management platform, input each of the preferred microservices into the platform structure to generate a preferred management platform, search for the sub-platform corresponding to each of the service stations in the preferred management platform and perform functional repairs to obtain a multi-dimensional fault management platform corresponding to each of the service stations.

[0027] In one practicable manner,

[0028] The data management module comprises:

[0029] A data collection unit is used to search for operation and maintenance data corresponding to each service station of the same type in the big data center, establish a plurality of operation and maintenance data information corresponding to the service station according to the operation and maintenance data, and determine data description features corresponding to each operation and maintenance data information based on semantic analysis technology;

[0030] A data screening unit is used to locate contradictory operation and maintenance data information with opposite data description characteristics, upload the contradictory operation and maintenance data information to the big data service center for information search, obtain the objective support amount corresponding to each contradictory operation and maintenance data information, eliminate unqualified operation and maintenance data information according to the objective support amount, obtain a number of qualified operation and maintenance data information corresponding to each service station, and respectively build a manual library corresponding to each service station;

[0031] A fault identification unit is used to generate a number of fault descriptions corresponding to the service station in the multi-dimensional fault management platform, search for a number of corresponding matching information in the manual library according to the keywords corresponding to each of the fault descriptions, and determine the response information of the corresponding service station to each of the fault descriptions and the fault identification list according to the matching information.

[0032] In one practicable manner,

[0033] The analysis implementation module comprises:

[0034] A data processing unit, used for collecting the real-time data generated by each of the service stations, respectively obtaining a data period corresponding to each of the real-time data, determining a cutoff distance corresponding to each of the real-time data according to the data period, cutting the corresponding real-time data into a plurality of single data segments using the cutoff distance, and respectively performing data sampling in each of the single data segments corresponding to the same real-time data segment to obtain a plurality of sampled data;

[0035] A feature generation unit, used to obtain data similarity between different sampled data, determine association features between different single data segments, perform clustering processing on sub-data contained in each single data segment, obtain an abnormal value corresponding to each single data segment, analyze an associated abnormal value corresponding to each abnormal value based on the association features, and establish a fault feature of the corresponding service station based on distribution information of the associated abnormal value in the real-time data;

[0036] A fault identification unit is used to search for matching information corresponding to each fault feature in the fault identification list, establish a fault knowledge graph for each service station according to the matching information corresponding to each service station, and generate a plurality of fault information existing in the service station based on the fault level corresponding to each fault feature and the fault knowledge graph.

[0037] In one practicable manner,

[0038] The fault management module comprises:

[0039] A fault decomposition unit is used to initially identify each of the fault information in the multi-dimensional fault management platform, obtain dimension coverage information corresponding to each of the fault information, and perform multi-scale coarse-graining processing on each of the fault information based on the dimension coverage information to obtain a plurality of single-dimensional fault information corresponding to each of the service stations;

[0040] A fault mining unit is used to establish a fault damage model corresponding to the service station according to the fault dimension corresponding to each single-dimensional fault information, input the single-dimensional fault information corresponding to the same service station into the fault damage model for deep training, and obtain explicit faults and hidden faults corresponding to each service station;

[0041] A fault compensation unit is used to trace the fault source of each explicit fault in the fault damage model, obtain the first fault component corresponding to each explicit fault, enhance each implicit fault, run the fault damage model to determine the second fault component corresponding to each enhanced implicit fault, obtain the manual information corresponding to each first fault component and the second fault component in the manual library, establish a compensation method corresponding to each fault information and display it.

[0042] In one practicable manner,

[0043] The fault compensation unit comprises:

[0044] A first fault tracing subunit is used to run the fault damage model to obtain a first fault device corresponding to each of the explicit faults, respectively obtain a fault level classification corresponding to each of the implicit faults, determine a maximum fault level classification corresponding to each of the implicit faults, enhance the implicit fault to the corresponding maximum fault level classification, and obtain an enhanced implicit fault;

[0045] A second fault tracing subunit is used to regard the enhanced hidden fault as a model operation result, adjust the model operation data in the fault damage model using the model operation result, and determine a second fault device corresponding to the hidden fault according to the adjustment direction corresponding to the model operation data;

[0046] The fault compensation execution subunit is used to count a number of first fault components and second fault components corresponding to each of the service stations, filter the manual information corresponding to each of the first fault components and the second fault components in the corresponding manual library, determine the maintenance method corresponding to each fault component based on the manual information, merge the maintenance methods, obtain the compensation method corresponding to each of the service stations and display it.

[0047] In one practicable manner,

[0048] Also includes:

[0049] a fusion execution subunit, configured to match a priority weight for each of the first faulty components respectively, and to match a non-priority weight for each of the second faulty components respectively;

[0050] A fusion threshold corresponding to the maintenance method is determined based on the priority weight and the non-priority weight, and the maintenance method is fused based on the fusion threshold to generate a compensation method.

[0051] The present invention provides an intelligent fault analysis and management method based on big data, comprising:

[0052] Step 1: Use the Spring Cloud technology stack to develop the architecture and generate a multi-dimensional fault management platform for each service station;

[0053] Step 2: Using the multi-dimensional fault management platform to edit and create the manual library of the service station, and generate a fault identification list corresponding to each service station;

[0054] Step 3: determining the fault characteristics of the corresponding service station according to the real-time data corresponding to each of the service stations, identifying the corresponding fault characteristics in the fault identification list, and determining the fault information corresponding to each of the service stations;

[0055] Step 4: In the multi-dimensional fault management platform, the fault information is deeply mined, and the corresponding compensation method for each service station is determined and displayed.

[0056] The achievable beneficial effects of the above technical solution are as follows: in order to improve the efficiency of fault analysis and management, the easy integration feature of the Spring Cloud technology stack is used for architecture development, a multi-dimensional fault management platform is established for each service station, and then the manual is edited and created in the multi-dimensional fault management platform to establish a fault identification list for each service station. During the operation of the service station, the real-time data generated by each service station is collected, and the real-time data is used to construct the fault characteristics of each service station, and then the corresponding faults are identified in the fault identification list, and the fault information corresponding to each service station is determined. The fault information is further deeply mined in the multi-dimensional fault management platform, and finally a fault compensation method for each service station is established. Through such technical means, funny guidance and management of power operation and maintenance faults can be carried out, and problems in fault handling, drawing management, data analysis and operation and maintenance efficiency can be effectively resolved, providing strong support for the intelligent operation and maintenance transformation, and can also intuitively and conveniently display the trends of various dimensions of faults to maintenance management personnel, which can accurately guide maintenance operations, prepare for a rainy day, and improve the availability of service stations.

[0057] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0058] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0060] Figure 1 A schematic diagram of the composition of an intelligent fault analysis and management system based on big data in an embodiment of the present invention;

[0061] Figure 2 The figure is a schematic diagram of the workflow of an intelligent fault analysis and management method based on big data in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0063] Example 1

[0064] This embodiment provides an intelligent fault analysis and management system based on big data, such as Figure 1 As shown, including:

[0065] The multi-dimensional management module is used to develop the architecture using the Spring Cloud technology stack and generate a multi-dimensional fault management platform corresponding to each service station;

[0066] A data management module, used to edit and create a manual library of the service station using the multi-dimensional fault management platform, and generate a fault identification list corresponding to each service station;

[0067] An analysis implementation module, used to determine the fault characteristics of the corresponding service station according to the real-time data corresponding to each of the service stations, identify the corresponding fault characteristics in the fault identification list, and determine the fault information corresponding to each of the service stations;

[0068] The fault management module is used to perform in-depth mining of the fault information in the multi-dimensional fault management platform, determine the corresponding compensation method for each service station and display it.

[0069] In this example, the Spring Cloud technology stack is a tool for building microservices;

[0070] In this example, the service station represents an independent wind power station;

[0071] In this example, the manual library represents a database storing files of various equipment and devices in a service station, and a service station is equipped with a manual library;

[0072] In this example, the fault identification list contains all possible faults that may occur in a service station;

[0073] In this example, real-time data refers to data generated by a service station during operation;

[0074] In this example, the editing and creation process is the process of organizing the manual library;

[0075] In this example, the multi-dimensional fault management platform refers to a platform used to analyze and manage service stations. One service station is equipped with one multi-dimensional fault management platform, and the multi-dimensional fault management platform supports application access on the web and mobile terminals, ensuring that operation and maintenance personnel can perform fault troubleshooting and processing work anytime and anywhere;

[0076] In this example, the fault characteristics represent the characteristics presented by the corresponding fault location when a fault occurs in the service station;

[0077] In this example, the fault information indicates the description information about the fault contained in the service station;

[0078] In this example, deep mining refers to the process of locating the location of faults that have occurred in the service station and mining potential faults;

[0079] In this example, the multi-dimensional fault management platform can be used to display the compensation method of each service station.

[0080] The working principle and beneficial effects of the above technical solution: In order to improve the efficiency of fault analysis and management, the easy integration feature of the Spring Cloud technology stack is used for architecture development, and a multi-dimensional fault management platform is established for each service station. Then, the manual is edited and created in the multi-dimensional fault management platform to establish a fault identification list for each service station. During the operation of the service station, the real-time data generated by each service station is collected, and the real-time data is used to build the fault characteristics of each service station. Then, the corresponding faults are identified in the fault identification list, and the fault information corresponding to each service station is determined. The fault information is further deeply mined in the multi-dimensional fault management platform, and finally, a fault compensation method for each service station is established. Through such technical means, funny guidance and management of power operation and maintenance faults can be carried out, and problems in fault handling, drawing management, data analysis and operation and maintenance efficiency can be effectively resolved, providing strong support for the intelligent operation and maintenance transformation. It can also intuitively and conveniently display the trends of various dimensions of faults to maintenance management personnel, which can accurately guide maintenance operations, prepare for a rainy day, and improve the availability of service stations.

[0081] Example 2

[0082] On the basis of Example 1, the intelligent fault analysis and management system based on big data, the multi-dimensional fault management platform, includes:

[0083] A manual management sub-platform, for classifying the corresponding manual library according to a specified document structure by using semantic analysis, and generating a manual document for each of the service stations;

[0084] The command response sub-platform is used to search for the corresponding target manual in the manual document and display it based on the search command issued by the operation and maintenance personnel;

[0085] The offline buffering sub-platform is used to buffer the manual document offline.

[0086] In this example, fault handling manuals are managed by grade and classification based on factors such as manufacturer, machine model, and equipment fault type, forming a structured manual library;

[0087] In this example, in order to solve the problem of unstable network in offshore wind farms, the system adds a file cache function, and the operation and maintenance personnel can cache the fault handling manual and drawing library to the mobile terminal as needed for offline viewing. In addition, the system also adds a batch import function for standard templates of fault handling manuals to save input time and improve user experience;

[0088] In this example, operation and maintenance personnel can quickly find the required documents through tags or keywords and perform approval operations.

[0089] The working principle and beneficial effects of the above technical solution: In order to improve the standardization and efficiency of document management and solve some problems in actual use, the manual library is sorted out. When operation and maintenance personnel look for manuals, they can respond quickly, thereby improving the work efficiency of operation and maintenance personnel, making the system not only suitable for ordinary power plants, but also can be used in power plants in various complex environments.

[0090] Example 3

[0091] On the basis of Example 1, the intelligent fault analysis and management system based on big data, the multi-dimensional management module includes:

[0092] A microservice architecture unit, used to respectively obtain site location information and work attribute information corresponding to each service station, create an initial analysis management platform using the site location information and work attribute information, and divide the initial analysis management platform into a plurality of microservices using the Spring Cloud technology stack;

[0093] A functional analysis unit is used to trace the source of each microservice, determine the service object corresponding to each microservice, collect the functional attribute information corresponding to each service object, analyze the topological relationship between different functional attribute information according to the distribution of the microservices in the initial analysis management platform, and generate a functional topology network;

[0094] A function deployment unit, configured to generate a function annotation of a corresponding service object based on the node data corresponding to each topological node in the functional topological network, determine a docking function corresponding to each of the service objects in combination with the network logic of the functional topological network, and perform function deployment on the corresponding microservices using the docking function to obtain available microservices corresponding to each of the service stations;

[0095] The platform construction unit is used to identify the high-frequency faults corresponding to each of the service stations based on the site location information and work attribute information corresponding to each of the service stations, use the high-frequency faults to enhance the functions of the available microservices, and establish a multi-dimensional fault management platform corresponding to each of the service stations in combination with the preset platform construction technology.

[0096] In this example, a microservice represents an independent service system, and one service station corresponds to one microservice;

[0097] In this example, the service object represents the object of the microservice, that is, the device or equipment served by the microservice in the service station;

[0098] In this example, the function attribute information indicates the executable function corresponding to the service and its basic attributes;

[0099] In this example, the functional topology network represents a functional cross network composed of the associations between various functional attribute information;

[0100] In this example, a topological node corresponds to a service object, and the topological node represents a node in the functional topological network. The topological node contains the corresponding functional attribute information and the association between functions;

[0101] In this example, the functional annotation means a method of explaining the corresponding function of the service using concise language;

[0102] In this example, the docking function means that a service object can be docked with other service objects;

[0103] In this example, available microservices represent microservices that can perform corresponding analysis on the functionality of the service station;

[0104] In this example, high-frequency faults represent faults that frequently occur in the service station;

[0105] In this example, the preset platform building technology can be a platform orchestration technology process;

[0106] In this example, the purpose of strengthening the available microservices is to enhance the functions of the available microservices so that the available microservices can better adapt to high-frequency failures.

[0107] The working principle and beneficial effects of the above technical solution are as follows: in order to enable each service station to perform self-management, firstly, an initial analysis management platform for all service stations is established according to the site location and work attribute information of each service station, and then the technology stack is used to divide it into several microservices. In this way, each service station is assigned a microservice, and then the microservice is traced to determine its service object, and then a functional topology network is constructed according to the functional attribute information of each service object, and then the functional topology network is further analyzed and functionally deployed to obtain the available microservices of each service station, and finally the high-frequency faults of each service station are identified, and the functions of the available microservices are enhanced by using high-frequency faults. Finally, a multi-dimensional fault management platform for each service station is established in combination with platform building technology. In this way, not only can a multi-dimensional fault management platform for self-management be set up for each service station, but also each multi-dimensional fault management platform can be guaranteed to accurately manage the service station, reduce redundant functions in the multi-dimensional fault management platform, and improve the work efficiency and work quality of the multi-dimensional fault management platform.

[0108] Example 4

[0109] On the basis of Example 3, the intelligent fault analysis and management system based on big data, the platform construction unit includes:

[0110] A fault identification subunit is used to draw a service station function structure diagram based on the initial analysis management platform, determine the dynamic working information and static working information of the corresponding service station according to the site location information and working attribute information corresponding to each of the service stations, and sequentially delete each of the dynamic working information and static working information in the service station function structure diagram to obtain a dynamic fault threshold and a static fault threshold corresponding to each of the service stations;

[0111] A fault mining subunit is used to generate a number of dynamic faults and static faults corresponding to each of the service stations by using each of the available microservices in combination with the corresponding dynamic fault threshold and static fault threshold, retrieve historical faults of similar service stations in the big data center based on the working attribute information of the service station, and determine a number of high-frequency faults of each of the service stations based on a first similarity between each of the dynamic faults and the historical faults and a second similarity between each of the static faults and the historical faults;

[0112] A service enhancement subunit is used to obtain the fault level and fault performance corresponding to each of the high-frequency faults, establish mirror service information using the fault level and the fault performance, and enhance the functions of the corresponding available microservices using the mirror service information to obtain the preferred microservice corresponding to each of the service stations;

[0113] The platform building sub-unit is used to build a platform structure based on the front-end framework, back-end technology and the interaction mode between the databases corresponding to the initial analysis management platform, input each of the preferred microservices into the platform structure to generate a preferred management platform, search for the sub-platform corresponding to each of the service stations in the preferred management platform and perform functional repairs to obtain a multi-dimensional fault management platform corresponding to each of the service stations.

[0114] In this example, the service station function structure diagram represents the result of arranging all the functions designed for the service station according to their structure;

[0115] In this example, the dynamic work information refers to information generated when the dynamic work is performed in the service station, for example, information generated when the motor rotates;

[0116] In this example, the static work information refers to the information generated when the static work is performed in the service station, such as: information of the place of production when the display screen is used;

[0117] In this example, the dynamic fault threshold value represents a threshold value presented when a dynamic fault occurs in the service station;

[0118] In this example, the static fault threshold value represents a threshold value presented when a static fault occurs in the service station;

[0119] In this example, the same type of service station refers to other service stations corresponding to the service station type;

[0120] In this example, historical faults represent faults presented by similar service stations;

[0121] In this example, the first similarity represents the similarity between the dynamic fault of the service station and the historical fault, and the second similarity represents the similarity between the static fault of the service station and the historical fault;

[0122] In this example, high-frequency faults represent dynamic faults / static faults with a similarity greater than 45%;

[0123] In this example, the fault level indicates the number of levels that high-frequency faults can be classified into;

[0124] In this example, the fault performance indicates the performance of the service station under the influence of the fault when a high-frequency fault occurs;

[0125] In this example, the mirror service information refers to the information obtained by mirroring the fault level and the fault performance. The essence of the mirror service information is the information that is completely opposite to the high-frequency fault.

[0126] In this example, the preferred microservice represents a microservice that can better manage the service station;

[0127] In this example, the front-end framework, back-end technology, and database are all part of the preset platform building technology. The front-end framework can be React or Vue, the back-end technology can be Node.js or Django, and the database can be MySQL or MongoDB.

[0128] In this example, the platform structure means designing the system architecture, including the front-end, back-end, database, and how they interact with each other;

[0129] In this instance, the purpose of functional repair is to: improve the functionality of each sub-platform;

[0130] In this example, one service station corresponds to one sub-platform.

[0131] The working principle and beneficial effects of the above technical solution are as follows: first, the service station function structure diagram is drawn using the initial analysis management platform to determine the dynamic working information and static working information of each service station. The dynamic fault threshold and static fault threshold of each service station are determined by deleting the simulation. Then, the dynamic faults and static faults of the service station are analyzed based on the available microservices. Then, the high-frequency faults of each service station are determined by comparing with the historical faults of similar service stations retrieved from the big data center. The available microservices are functionally enhanced by establishing mirror service information for each high-frequency fault, and the preferred microservices for each service station are generated. Finally, the platform building technology is used to perform functional repairs on the sub-platform corresponding to each service station, and finally a multi-dimensional fault management platform is obtained for each service station. In this way, each service station can be functionally analyzed and troubleshooted, and its high-frequency faults can be analyzed and processed in detail. A multi-dimensional fault management platform is built for each service station to improve the self-management efficiency of each service station.

[0132] Example 5

[0133] On the basis of Example 1, the intelligent fault analysis and management system based on big data, the data management module includes:

[0134] A data collection unit is used to search for operation and maintenance data corresponding to each service station of the same type in the big data center, establish a plurality of operation and maintenance data information corresponding to the service station according to the operation and maintenance data, and determine data description features corresponding to each operation and maintenance data information based on semantic analysis technology;

[0135] A data screening unit is used to locate contradictory operation and maintenance data information with opposite data description characteristics, upload the contradictory operation and maintenance data information to the big data service center for information search, obtain the objective support amount corresponding to each contradictory operation and maintenance data information, eliminate unqualified operation and maintenance data information according to the objective support amount, obtain a number of qualified operation and maintenance data information corresponding to each service station, and respectively build a manual library corresponding to each service station;

[0136] A fault identification unit is used to generate a number of fault descriptions corresponding to the service station in the multi-dimensional fault management platform, search for a number of corresponding matching information in the manual library according to the keywords corresponding to each of the fault descriptions, and determine the response information of the corresponding service station to each of the fault descriptions and the fault identification list according to the matching information.

[0137] In this example, the data period refers to the period of repetition of the relevant data presented in the real-time data;

[0138] In this example, the truncation distance is consistent with the length of the data cycle. The truncation distance indicates the standard for truncating the real-time data into a number of single data segments. The length of each single data segment is consistent with the truncation distance. Since the data cycle may be different, the truncation distance corresponding to each real-time data may also be different.

[0139] In this example, the sampling method is: random sampling is performed in each single data segment, and the sampling quantity is 1;

[0140] In this example, clustering refers to the process of grouping sub-data with the same characteristics into one category;

[0141] In this example, the outlier represents the data value corresponding to the sub-data that cannot be classified into the same category as other sub-data;

[0142] In this example, the fault knowledge graph represents a graph used to describe the associations between various faults presented by the service station;

[0143] In this example, the fault information refers to information presented when a service station fails.

[0144] The working principle and beneficial effects of the above technical solution are as follows: in order to perform corresponding fault analysis on each service station, the real-time data generated by the service station is collected during its operation, and then the truncation distance is determined according to the data period corresponding to each real-time data, so as to truncate the real-time data and divide the real-time data into several single data segments, and further perform data sampling work, and determine the associated features between the single data segments according to the data similarity between different sampled data, and then perform clustering processing on the sub-data in the single data segment, screen the abnormal values ​​of each single data segment, so as to determine the associated abnormal values ​​of each service station, and determine the fault characteristics of each service station in combination with the distribution of the associated abnormal values ​​in the real-time data, and then establish the fault knowledge graph of the service station by searching for the matching information of each fault feature, and generate the fault information of the service station in combination with the corresponding fault features and fault levels. In this way, the service station can be analyzed in real time, and the fault features presented at different times can be determined, and its fault information can be determined, which can lay the foundation for subsequent fault management, and also allow operation and maintenance personnel to discover faults in time, handle faults in time, and reduce the impact of faults.

[0145] Example 7

[0146] On the basis of Example 1, the intelligent fault analysis and management system based on big data, the fault management module includes:

[0147] A fault decomposition unit is used to initially identify each of the fault information in the multi-dimensional fault management platform, obtain dimension coverage information corresponding to each of the fault information, and perform multi-scale coarse-graining processing on each of the fault information based on the dimension coverage information to obtain a plurality of single-dimensional fault information corresponding to each of the service stations;

[0148] A fault mining unit is used to establish a fault damage model corresponding to the service station according to the fault dimension corresponding to each single-dimensional fault information, input the single-dimensional fault information corresponding to the same service station into the fault damage model for deep training, and obtain explicit faults and hidden faults corresponding to each service station;

[0149] A fault compensation unit is used to trace the fault source of each explicit fault in the fault damage model, obtain the first fault component corresponding to each explicit fault, enhance each implicit fault, run the fault damage model to determine the second fault component corresponding to each enhanced implicit fault, obtain the manual information corresponding to each first fault component and the second fault component in the manual library, establish a compensation method corresponding to each fault information and display it.

[0150] In this instance, the dimension coverage information indicates the dimensions involved in a fault information;

[0151] In this example, the processing scale of the multi-scale coarse-graining process is the same as the coverage of the dimension-covered information;

[0152] In this example, the fault damage model represents a model of damage caused to a service station by various faults presented by a service station;

[0153] In this example, the explicit fault indicates the fault currently present in the service station, and the implicit fault indicates the potential fault of the service station, that is, when the explicit fault does not exist, the implicit fault may disappear;

[0154] In this example, the first faulty device refers to a device that is currently faulty, and the second faulty device refers to a device that is not currently faulty but has a potential fault.

[0155] The working principle and beneficial effects of the above technical solution: In order to facilitate the operation and maintenance personnel to handle the faults of the service station in a timely manner, each fault information is initially identified in the multi-dimensional fault management platform to determine the corresponding dimension coverage information, and then the fault information is subjected to multi-scale coarsening processing, and several single-dimensional fault information in the service station is determined. Further, the fault damage model of the service station is established based on the different fault dimensions corresponding to a service station. Through deep training, the explicit and hidden faults of the service station are determined, and the faulty devices are determined by tracing the source, and then the corresponding manual information is searched in the manual library. Finally, the compensation method is established based on the queried manual information. In this way, multiple faults can be compensated at the same time, which improves the efficiency of the operation and maintenance personnel in solving problems, ensures the quality of problem solving, and reduces losses.

[0156] Example 8

[0157] On the basis of Example 7, the intelligent fault analysis and management system based on big data, the fault compensation unit includes:

[0158] A first fault tracing subunit is used to run the fault damage model to obtain a first fault device corresponding to each of the explicit faults, respectively obtain a fault level classification corresponding to each of the implicit faults, determine a maximum fault level classification corresponding to each of the implicit faults, enhance the implicit fault to the corresponding maximum fault level classification, and obtain an enhanced implicit fault;

[0159] A second fault tracing subunit is used to regard the enhanced hidden fault as a model operation result, adjust the model operation data in the fault damage model using the model operation result, and determine a second fault device corresponding to the hidden fault according to the adjustment direction corresponding to the model operation data;

[0160] The fault compensation execution subunit is used to count a number of first fault components and second fault components corresponding to each of the service stations, filter the manual information corresponding to each of the first fault components and the second fault components in the corresponding manual library, determine the maintenance method corresponding to each fault component based on the manual information, merge the maintenance methods, obtain the compensation method corresponding to each of the service stations and display it.

[0161] In this example, the maximum fault level classification indicates the maximum level of hidden faults;

[0162] In this example, the purpose of generating enhanced impact faults is to facilitate better device tracing.

[0163] The working principle and beneficial effects of the above technical solution are as follows: when forming a compensation method, first determine the first fault device and the latent fault corresponding to the explicit fault according to the fault damage model, and at the same time improve the traceability quality by strengthening the latent fault, determine the second fault device corresponding to the latent fault, and then search in the manual library to construct a compensation method for the service station. In this way, multiple maintenance methods can be integrated, multiple faults can be handled at one time, and unnecessary processing steps can be reduced.

[0164] Example 9

[0165] On the basis of Example 8, the intelligent fault analysis and management system based on big data further includes:

[0166] a fusion execution subunit, configured to match a priority weight for each of the first faulty components respectively, and to match a non-priority weight for each of the second faulty components respectively;

[0167] A fusion threshold corresponding to the maintenance method is determined based on the priority weight and the non-priority weight, and the maintenance method is fused based on the fusion threshold to generate a compensation method.

[0168] In this example, during the fusion process, the maintenance methods with non-priority weights are adjusted first, and then the maintenance methods with priority weights are adjusted, so as to ensure that the quality of the maintenance methods with priority weights is reduced.

[0169] The working principle and beneficial effects of the above technical solution: when re-integration is performed, the maintenance method of the first faulty component is fine-tuned, and the maintenance method of the second faulty component is multi-adjusted to ensure the processing quality of the dominant fault.

[0170] Example 10

[0171] This example provides an intelligent fault analysis and management method based on big data, including:

[0172] Step 1: Use the Spring Cloud technology stack to develop the architecture and generate a multi-dimensional fault management platform for each service station;

[0173] Step 2: Using the multi-dimensional fault management platform to edit and create the manual library of the service station, and generate a fault identification list corresponding to each service station;

[0174] Step 3: determining the fault characteristics of the corresponding service station according to the real-time data corresponding to each of the service stations, identifying the corresponding fault characteristics in the fault identification list, and determining the fault information corresponding to each of the service stations;

[0175] Step 4: In the multi-dimensional fault management platform, the fault information is deeply mined, and the corresponding compensation method for each service station is determined and displayed.

[0176] In the example, the Spring Cloud technology stack is a tool for building microservices;

[0177] In this example, the service station represents an independent wind power station;

[0178] In this example, the manual library represents a database storing files of various equipment and devices in a service station, and a service station is equipped with a manual library;

[0179] In this example, the fault identification list contains all possible faults that may occur in a service station;

[0180] In this example, real-time data refers to data generated by a service station during operation;

[0181] In this example, the editing and creation process is the process of organizing the manual library;

[0182] In this example, the multi-dimensional fault management platform refers to a platform used to analyze and manage service stations. One service station is equipped with one multi-dimensional fault management platform, and the multi-dimensional fault management platform supports application access on the web and mobile terminals, ensuring that operation and maintenance personnel can perform fault troubleshooting and processing work anytime and anywhere;

[0183] In this example, the fault characteristics represent the characteristics presented by the corresponding fault location when a fault occurs in the service station;

[0184] In this example, the fault information indicates the description information about the fault contained in the service station;

[0185] In this example, deep mining refers to the process of locating the location of faults that have occurred in the service station and mining potential faults;

[0186] In this example, the multi-dimensional fault management platform can be used to display the compensation method of each service station.

[0187] The working principle and beneficial effects of the above technical solution: In order to improve the efficiency of fault analysis and management, the easy integration feature of the Spring Cloud technology stack is used for architecture development, and a multi-dimensional fault management platform is established for each service station. Then, the manual is edited and created in the multi-dimensional fault management platform to establish a fault identification list for each service station. During the operation of the service station, the real-time data generated by each service station is collected, and the real-time data is used to build the fault characteristics of each service station. Then, the corresponding faults are identified in the fault identification list, and the fault information corresponding to each service station is determined. The fault information is further deeply mined in the multi-dimensional fault management platform, and finally, a fault compensation method for each service station is established. Through such technical means, funny guidance and management of power operation and maintenance faults can be carried out, and problems in fault handling, drawing management, data analysis and operation and maintenance efficiency can be effectively resolved, providing strong support for the intelligent operation and maintenance transformation. It can also intuitively and conveniently display the trends of various dimensions of faults to maintenance management personnel, which can accurately guide maintenance operations, prepare for a rainy day, and improve the availability of service stations.

[0188] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent fault analysis and management system based on big data, characterized in that: include: The multi-dimensional management module is used to develop the architecture using the Spring Cloud technology stack and generate a multi-dimensional fault management platform corresponding to each service station; A data management module, used to edit and create a manual library of the service station using the multi-dimensional fault management platform, and generate a fault identification list corresponding to each service station; An analysis implementation module, used to determine the fault characteristics of the corresponding service station according to the real-time data corresponding to each of the service stations, identify the corresponding fault characteristics in the fault identification list, and determine the fault information corresponding to each of the service stations; The fault management module is used to perform in-depth mining of the fault information in the multi-dimensional fault management platform, determine the corresponding compensation method for each service station and display it.

2. The intelligent fault analysis and management system based on big data according to claim 1, characterized in that: The multi-dimensional fault management platform includes: A manual management sub-platform, for classifying the corresponding manual library according to a specified document structure by using semantic analysis, and generating a manual document for each of the service stations; The command response sub-platform is used to search for the corresponding target manual in the manual document and display it based on the search command issued by the operation and maintenance personnel; The offline buffering sub-platform is used to buffer the manual document offline.

3. The intelligent fault analysis and management system based on big data according to claim 1, characterized in that: The multi-dimensional management module comprises: A microservice architecture unit, used to respectively obtain site location information and work attribute information corresponding to each service station, create an initial analysis management platform using the site location information and work attribute information, and divide the initial analysis management platform into a plurality of microservices using the Spring Cloud technology stack; A functional analysis unit is used to trace the source of each microservice, determine the service object corresponding to each microservice, collect the functional attribute information corresponding to each service object, analyze the topological relationship between different functional attribute information according to the distribution of the microservices in the initial analysis management platform, and generate a functional topology network; A function deployment unit, configured to generate a function annotation of a corresponding service object based on the node data corresponding to each topological node in the functional topological network, determine a docking function corresponding to each of the service objects in combination with the network logic of the functional topological network, and perform function deployment on the corresponding microservices using the docking function to obtain available microservices corresponding to each of the service stations; The platform construction unit is used to identify the high-frequency faults corresponding to each of the service stations based on the site location information and work attribute information corresponding to each of the service stations, use the high-frequency faults to enhance the functions of the available microservices, and establish a multi-dimensional fault management platform corresponding to each of the service stations in combination with the preset platform construction technology.

4. The intelligent fault analysis and management system based on big data as claimed in claim 3, characterized in that: The platform construction unit comprises: A fault identification subunit is used to draw a service station function structure diagram based on the initial analysis management platform, determine the dynamic working information and static working information of the corresponding service station according to the site location information and working attribute information corresponding to each of the service stations, and sequentially delete each of the dynamic working information and static working information in the service station function structure diagram to obtain a dynamic fault threshold and a static fault threshold corresponding to each of the service stations; A fault mining subunit is used to generate a number of dynamic faults and static faults corresponding to each of the service stations by using each of the available microservices in combination with the corresponding dynamic fault threshold and static fault threshold, retrieve historical faults of similar service stations in the big data center based on the working attribute information of the service station, and determine a number of high-frequency faults of each of the service stations based on a first similarity between each of the dynamic faults and the historical faults and a second similarity between each of the static faults and the historical faults; A service enhancement subunit is used to obtain the fault level and fault performance corresponding to each of the high-frequency faults, establish mirror service information using the fault level and the fault performance, and enhance the functions of the corresponding available microservices using the mirror service information to obtain the preferred microservice corresponding to each of the service stations; The platform building sub-unit is used to build a platform structure based on the front-end framework, back-end technology and the interaction mode between the databases corresponding to the initial analysis management platform, input each of the preferred microservices into the platform structure to generate a preferred management platform, search for the sub-platform corresponding to each of the service stations in the preferred management platform and perform functional repairs to obtain a multi-dimensional fault management platform corresponding to each of the service stations.

5. The intelligent fault analysis and management system based on big data according to claim 1, characterized in that: The data management module comprises: A data collection unit is used to search for operation and maintenance data corresponding to each service station of the same type in the big data center, establish a plurality of operation and maintenance data information corresponding to the service station according to the operation and maintenance data, and determine data description features corresponding to each operation and maintenance data information based on semantic analysis technology; A data screening unit is used to locate contradictory operation and maintenance data information with opposite data description characteristics, upload the contradictory operation and maintenance data information to the big data service center for information search, obtain the objective support amount corresponding to each contradictory operation and maintenance data information, eliminate unqualified operation and maintenance data information according to the objective support amount, obtain a number of qualified operation and maintenance data information corresponding to each service station, and respectively build a manual library corresponding to each service station; A fault identification unit is used to generate a number of fault descriptions corresponding to the service station in the multi-dimensional fault management platform, search for a number of corresponding matching information in the manual library according to the keywords corresponding to each of the fault descriptions, and determine the response information of the corresponding service station to each of the fault descriptions and the fault identification list according to the matching information.

6. The intelligent fault analysis and management system based on big data according to claim 1, characterized in that: The analysis implementation module comprises: A data processing unit, used for collecting the real-time data generated by each of the service stations, respectively obtaining a data period corresponding to each of the real-time data, determining a cutoff distance corresponding to each of the real-time data according to the data period, cutting the corresponding real-time data into a plurality of single data segments using the cutoff distance, and respectively performing data sampling in each of the single data segments corresponding to the same real-time data segment to obtain a plurality of sampled data; A feature generation unit, used to obtain data similarity between different sampled data, determine association features between different single data segments, perform clustering processing on sub-data contained in each single data segment, obtain an abnormal value corresponding to each single data segment, analyze an associated abnormal value corresponding to each abnormal value based on the association features, and establish a fault feature of the corresponding service station based on distribution information of the associated abnormal value in the real-time data; A fault identification unit is used to search for matching information corresponding to each fault feature in the fault identification list, establish a fault knowledge graph for each service station according to the matching information corresponding to each service station, and generate a plurality of fault information existing in the service station based on the fault level corresponding to each fault feature and the fault knowledge graph.

7. The intelligent fault analysis and management system based on big data according to claim 1, characterized in that: The fault management module comprises: A fault decomposition unit is used to initially identify each of the fault information in the multi-dimensional fault management platform, obtain dimension coverage information corresponding to each of the fault information, and perform multi-scale coarse-graining processing on each of the fault information based on the dimension coverage information to obtain a plurality of single-dimensional fault information corresponding to each of the service stations; A fault mining unit is used to establish a fault damage model corresponding to the service station according to the fault dimension corresponding to each single-dimensional fault information, input the single-dimensional fault information corresponding to the same service station into the fault damage model for deep training, and obtain explicit faults and hidden faults corresponding to each service station; A fault compensation unit is used to trace the fault source of each explicit fault in the fault damage model, obtain the first fault component corresponding to each explicit fault, enhance each implicit fault, run the fault damage model to determine the second fault component corresponding to each enhanced implicit fault, obtain the manual information corresponding to each first fault component and the second fault component in the manual library, establish a compensation method corresponding to each fault information and display it.

8. The intelligent fault analysis and management system based on big data according to claim 7, characterized in that: The fault compensation unit comprises: A first fault tracing subunit is used to run the fault damage model to obtain a first fault device corresponding to each of the explicit faults, respectively obtain a fault level classification corresponding to each of the implicit faults, determine a maximum fault level classification corresponding to each of the implicit faults, enhance the implicit fault to the corresponding maximum fault level classification, and obtain an enhanced implicit fault; A second fault tracing subunit is used to regard the enhanced hidden fault as a model operation result, adjust the model operation data in the fault damage model using the model operation result, and determine a second fault device corresponding to the hidden fault according to the adjustment direction corresponding to the model operation data; The fault compensation execution subunit is used to count a number of first fault components and second fault components corresponding to each of the service stations, filter the manual information corresponding to each of the first fault components and the second fault components in the corresponding manual library, determine the maintenance method corresponding to each fault component based on the manual information, merge the maintenance methods, obtain the compensation method corresponding to each of the service stations and display it.

9. The intelligent fault analysis and management system based on big data according to claim 8, characterized in that: Also includes: a fusion execution subunit, configured to match a priority weight for each of the first faulty components respectively, and to match a non-priority weight for each of the second faulty components respectively; A fusion threshold corresponding to the maintenance method is determined based on the priority weight and the non-priority weight, and the maintenance method is fused based on the fusion threshold to generate a compensation method.

10. An intelligent fault analysis and management method based on big data, characterized in that: include: Step 1: Use the Spring Cloud technology stack to develop the architecture and generate a multi-dimensional fault management platform for each service station; Step 2: Using the multi-dimensional fault management platform to edit and create the manual library of the service station, and generate a fault identification list corresponding to each service station; Step 3: determining the fault characteristics of the corresponding service station according to the real-time data corresponding to each of the service stations, identifying the corresponding fault characteristics in the fault identification list, and determining the fault information corresponding to each of the service stations; Step 4: In the multi-dimensional fault management platform, the fault information is deeply mined, and the corresponding compensation method for each service station is determined and displayed.

Images