CN115712735A - Big data-based wind turbine generator fault monitoring and early warning method and system - Google Patents
Big data-based wind turbine generator fault monitoring and early warning method and system Download PDFInfo
- Publication number
- CN115712735A CN115712735A CN202211458225.2A CN202211458225A CN115712735A CN 115712735 A CN115712735 A CN 115712735A CN 202211458225 A CN202211458225 A CN 202211458225A CN 115712735 A CN115712735 A CN 115712735A
- Authority
- CN
- China
- Prior art keywords
- fault
- information
- early warning
- data
- wind turbine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a wind turbine generator fault monitoring and early warning method and system based on big data, and relates to the technical field of intelligent data processing.
Description
Technical Field
The invention relates to the technical field of intelligent data processing, in particular to a wind turbine generator fault monitoring and early warning method and system based on big data.
Background
Wind power generation is as the main energy supply mode in new forms of energy field, it is more and more extensive to use, because wind power generation's operational environment is comparatively abominable, and wind power generation operating mode is comparatively complicated changeable, along with wind turbine generator system's operation inevitable can have the unit trouble, for guaranteeing wind turbine generator system's normal steady operation, need carry out fault monitoring to it, carry out fortune dimension management to the unit based on monitoring data, now, mainly carry out traditional operating parameter through wind turbine generator system's running state and confirm, carry out the parameter evaluation and confirm that unusual operation unit founds, maintain it in order to avoid the unit to move unusually, cause the operating efficiency low and have potential safety hazard.
In the prior art, when fault detection and early warning of a wind turbine generator are performed, the processing mode of fault data is not intelligent enough, so that the completeness of a fault early warning result is not enough, and comprehensive early warning cannot be performed based on the correlation influence of each component during the operation of the wind turbine generator.
Disclosure of Invention
The application provides a wind turbine generator fault monitoring and early warning method and system based on big data, which are used for solving the technical problems that in the prior art, when fault detection and early warning of a wind turbine generator are carried out, the processing mode of fault data is not intelligent enough, so that the completeness of a fault early warning result is not enough, and comprehensive early warning cannot be carried out based on the correlation influence of each component during the operation of the wind turbine generator.
In view of the above problems, the application provides a wind turbine generator fault monitoring and early warning method and system based on big data.
In a first aspect, the application provides a wind turbine generator fault monitoring and early warning method based on big data, and the method includes:
acquiring a wind turbine database from a big data platform, wherein the wind turbine database comprises turbine monitoring data and fault recording information;
constructing a fault knowledge graph based on the fault record information;
analyzing according to the associated influence data of each fault in the fault knowledge graph to determine a fault influence factor;
according to the fault influence factor, carrying out data type identification on the big data platform, and automatically acquiring data based on the data type identification;
determining each fault early warning model according to the fault knowledge map and the unit monitoring data, and constructing a fault early warning tree;
and inputting the fault influence factor identification data acquired from the big data platform into a fault early warning tree, analyzing and early warning each fault, and outputting fault early warning information.
In a second aspect, the present application provides a wind turbine generator system fault monitoring and early warning system based on big data, the system includes:
the system comprises an information acquisition module, a fault detection module and a fault detection module, wherein the information acquisition module is used for acquiring a wind turbine database from a big data platform, and the wind turbine database comprises turbine monitoring data and fault recording information;
the map construction module is used for constructing a fault knowledge map based on the fault recording information;
the influence factor determination module is used for analyzing according to the associated influence data of each fault in the fault knowledge graph to determine a fault influence factor;
the data identification module is used for carrying out data type identification on the big data platform according to the fault influence factor and automatically acquiring data based on the data type identification;
the early warning tree construction module is used for determining each fault early warning model according to the fault knowledge map and the unit monitoring data to construct a fault early warning tree;
and the fault early warning module is used for inputting the fault influence factor identification data acquired from the big data platform into a fault early warning tree, analyzing and early warning each fault and outputting fault early warning information.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the wind turbine generator fault monitoring and early warning method based on the big data, a wind turbine generator database is obtained from a big data platform and comprises generator set monitoring data and fault recording information, a fault knowledge graph is built based on the fault recording information, relevant influence data of all faults are analyzed and determined to determine fault influence factors, then data type identification is carried out on the big data platform, data are automatically obtained based on the data type identification, according to the fault knowledge graph and the generator set monitoring data, all fault early warning model determination is carried out, a fault early warning tree is built, fault influence factor identification data obtained from the big data platform are input into the fault early warning tree, all fault analysis early warning is carried out, fault early warning information is output, the technical problems that when fault detection early warning of the wind turbine generator is carried out in the prior art, the processing mode of the fault data is not intelligent enough, the fault early warning result is not complete, and comprehensive early warning cannot be carried out based on the relevant influences of all components during operation of the wind turbine generator are solved, and the fault accident management and management of the wind turbine generators are realized by building the fault knowledge graph and the fault early warning tree.
Drawings
FIG. 1 is a schematic flow chart of a wind turbine generator fault monitoring and early warning method based on big data provided by the application;
FIG. 2 is a schematic diagram of a fault knowledge graph construction process in a wind turbine generator fault monitoring and early warning method based on big data provided by the application;
fig. 3 is a schematic diagram illustrating a flow of acquiring fault early warning information in a wind turbine generator fault monitoring and early warning method based on big data according to the present application;
FIG. 4 provides a schematic structural diagram of a wind turbine generator system fault monitoring and early warning system based on big data.
Description of the reference numerals: the system comprises an information acquisition module 11, a map construction module 12, an influence factor determination module 13, a data identification module 14, an early warning tree construction module 15 and a fault early warning module 16.
Detailed Description
The application provides a wind turbine generator fault monitoring and early warning method and system based on big data, a fault knowledge map is built based on fault record information, correlation influence data of all faults are analyzed to determine fault influence factors, data type identification is further carried out on a big data platform, a plurality of fault early warning models are built, a fault early warning tree is generated, each fault analysis early warning is carried out on the fault influence factor identification data, fault early warning information is output, and the method and system are used for solving the technical problems that in the prior art, when fault detection early warning of the wind turbine generator is carried out, the processing mode of fault data is not intelligent enough, the completeness of a fault early warning result is insufficient, and comprehensive early warning cannot be carried out based on correlation influence of all components during operation of the wind turbine generator.
Example one
As shown in fig. 1, the present application provides a wind turbine generator fault monitoring and early warning method based on big data, the method includes:
step S100: acquiring a wind turbine database from a big data platform, wherein the wind turbine database comprises turbine monitoring data and fault recording information;
particularly, wind power generation is as the main energy supply mode in new energy field, and the application is more and more extensive, because wind power generation's operational environment is comparatively abominable, and wind power generation operating mode is comparatively complicated changeable, along with wind power generation's operation inevitable have the unit trouble, for guaranteeing wind power generation's normal stable operation, this application provides a wind power generation group fault monitoring early warning method based on big data, through constructing the trouble knowledge map, match the fault early warning model to each node respectively, carry out the early warning of multilevel fault monitoring, at first, set for the predetermined time interval, carry out data acquisition promptly, based on the predetermined time interval, according to big data platform carries out wind power generation group operation data and calls, confirms the unit monitoring data with fault record data, wherein, unit monitoring data with fault record data one-to-one, based on time series is right unit monitoring data with fault record data carries out corresponding sign, generates wind power generation group database, wind power generation group database has covered the multiple fault data that may exist, the acquisition of wind power generation group database has provided the basis for carrying out operation fault analysis.
Step S200: constructing a fault knowledge graph based on the fault record information;
step S300: analyzing according to the associated influence data of each fault in the fault knowledge graph to determine a fault influence factor;
step S400: according to the fault influence factor, carrying out data type identification on the big data platform, and automatically acquiring data based on the data type identification;
specifically, the corresponding fault events are determined based on a plurality of fault records contained in the fault record information, the fault events are divided based on fault elements, a plurality of groups of fault events are determined, fault risk degrees are further determined for the plurality of groups of fault events, fault risk degree grades are set and correspond to different risk degree intervals respectively, the plurality of groups of fault times are layered based on the fault risk degrees, multi-level nodes are determined to serve as a graph main framework, the higher the fault risk degree is, the higher the corresponding graph level is, fault influence analysis is performed on the fault events corresponding to the multi-level nodes respectively, fault influence relations between sub-nodes corresponding to the nodes and association relations between other nodes are determined and connected, a fault event association network is generated to serve as the fault knowledge graph, and fault analysis can be performed in the fault knowledge graph through logical reasoning.
Further, the method comprises the steps of carrying out correlation influence data analysis on each fault in the fault knowledge graph, wherein power can influence the rotating speed of a motor, the operation of a transmission structure, the temperature of a control cabinet and the like, taking the power as a fault influence factor of the fault event, wherein the same fault influence factor can cause multiple parts of faults, the same fault can correspond to multiple fault influence factors, taking the fault influence factor as identification data, carrying out data type identification on a large data platform, directly carrying out data identification and extraction through the identification data when carrying out data retrieval based on the large data platform, determining multiple groups of correlation data with faults, and avoiding data omission.
Further, as shown in fig. 2, based on the fault record information, a fault knowledge graph is constructed, and step S200 of the present application further includes:
step S210: analyzing the fault element according to the fault record information to determine the type information of the fault element;
step S220: analyzing the fault risk degree according to the fault record information based on the fault element type information, and determining the fault risk degree;
step S230: classifying the fault element type information according to the fault risk degree, and determining fault risk degree classification information;
step S240: obtaining map position grades of all faults according to the fault risk grade classification information;
step S250: analyzing and extracting influence data of each fault based on the map position grade of each fault, and determining influence information of each fault;
step S260: and connecting the associated faults in the map position levels of the faults based on the fault influence information to construct the fault knowledge map.
Specifically, the fault record information is extracted based on the fault database, fault elements of the fault record information are identified, fault element types corresponding to a plurality of pieces of fault information in the fault record information are determined, correlation correspondence is performed on the fault element types, the fault element type information is determined, fault risk degree analysis is performed according to the fault record information corresponding to each fault element type based on the fault element type information, for example, a wind turbine generator system operation fault risk level can be set, fault element risk level matching is performed based on the fault record information, and the fault risk degree is determined based on a matching result.
And taking the fault risk degrees as a division standard, dividing the fault element type information, determining multi-level fault element type information as fault risk degree classification information, namely multi-level fault events corresponding to different fault element types, and further determining the position of a fault map based on the fault risk degree classification information, wherein the higher the fault risk degree grade is, the higher the corresponding map level is, and the higher the corresponding maintenance priority is.
And further analyzing fault influence data according to the map position grades of the faults, for example, the faults of the generator may influence a transmission device to cause insufficient tension of a toothed belt and the like, a multi-level incidence relation exists, determining the fault influence information, connecting fault events in the map position grades based on the incidence influence relation, and constructing a fault knowledge map, wherein the fault knowledge map comprises a plurality of levels corresponding to different fault grades, a plurality of fault type events may exist in the same level, any fault type event corresponds to a plurality of branches, namely fault influence information, for example, the faults of the generator may correspond to generator bearing damage, winding heat dissipation abnormity, rotating speed abnormity and the like, influence relations may exist, for example, the bearing damage may influence winding heat dissipation, the transmission device may be further influenced, the fault knowledge map is connected based on the possible incidence influence relation, a fault network is generated to serve as the fault knowledge map, so as to guarantee the construction accuracy of the fault knowledge map, and when the running faults of the wind turbine generator exist, prediction analysis is performed in the fault knowledge map based on the incidence connection relation.
Further, step S260 of the present application further includes:
step S261: according to the fault record information, trend period analysis is carried out on each fault, and trend period information of each fault type is determined;
step S262: determining the risk degree of each period according to the trend period information of each fault type;
step S263: establishing a periodic risk map position based on each periodic risk degree;
step S264: embedding the periodic risk map locations into the map location hierarchy of each fault.
Specifically, any fault record is extracted based on the fault record data, a complete derivative cycle of the fault is determined, for example, the complete derivative cycle is divided into a plurality of cycle nodes of a fault initial stage, a fault middle stage and a fault later stage, fault degrees corresponding to different fault cycles are different, influence degrees on other elements of the wind turbine generator are different, trend cycle information of each fault type is determined based on a plurality of pieces of fault record information, and risk degree evaluation is further performed based on the trend cycle information of each fault type, wherein different cycle nodes correspond to different risk degrees and comprise fault element risk degrees and fault association influence risk degrees, the cycle risk positions are established based on the cycle risk degrees, corresponding fault association influence elements are under different cycle nodes and can be regarded as different fault events, so that targeted analysis is performed on the cycle nodes based on the fault, the fault prediction accuracy is improved, the cycle risk map positions are embedded into map position levels of each fault, fault location levels of each cycle node are subjected to associated fault connection, associated faults corresponding to the different cycle nodes are respectively connected, different connection modes can be set, corresponding associated network nodes are matched for different fault cycles, and the fault association map identification is completed, and the fault identification accuracy is guaranteed.
Step S500: determining each fault early warning model according to the fault knowledge map and the unit monitoring data, and constructing a fault early warning tree;
step S600: and inputting the fault influence factor identification data acquired from the big data platform into a fault early warning tree, analyzing and early warning each fault, and outputting fault early warning information.
Specifically, a plurality of early warning nodes are determined based on the fault knowledge graph, the fault early warning model is established based on the incidence relation between graph nodes and the unit monitoring data, the early warning nodes respectively correspond to a fault early warning model, the fault early warning models are connected based on the connection relation between the nodes to form the fault early warning tree, the fault early warning tree corresponds to the fault knowledge graph and is used for fault accident early warning and warning of each node in the fault knowledge graph, further, fault influence factor identification data is extracted based on the big data platform and is input into the fault early warning tree, the fault influence factor identification data is subjected to influence node identification based on the incidence relation between a fault factor and a top event, the corresponding fault early warning model is started based on an identification result, the fault early warning information is generated for model output by performing single-node fault analysis and multi-incidence node comprehensive analysis, and the operation and maintenance management of the wind turbine generator is performed based on the fault and mechanism information.
Further, according to the fault knowledge map and the unit monitoring data, determining each fault early warning model, wherein step S500 of the present application further includes:
step S510: extracting fault information of a preset risk degree according to the fault knowledge map, wherein the fault information of the preset risk degree comprises faults of a plurality of wind turbine generators;
step S520: sequentially taking the faults of the wind turbine generators as top events, and analyzing fault factors;
step S530: performing accident minimum segmentation on the corresponding type of the fault based on the fault factor and the unit monitoring data, and determining a minimum segmentation set;
step S540: and determining a fault early warning result according to the incidence relation between the minimum segmentation set and the fault of the wind turbine generator.
Specifically, the preset risk is obtained, that is, a risk critical value for extracting a risk accident is obtained, the fault knowledge graph includes multiple possible fault events of the operation of the wind turbine generator, fault information is extracted according to the preset risk based on the fault knowledge graph, multiple fault events including multiple wind turbine generator faults are obtained, the multiple wind turbine generator faults are sequentially used as the top events and can be divided into three types of top events including a serious fault accident, a major fault accident and a general fault accident, all cause events related to the wind turbine generator faults are analyzed for various factors, such as the generator fault and the pitch system fault, wherein the pitch system fault may be a problem occurring in a pitch motor, a control cabinet, a toothed belt and the like, and is used as an accident factor of the top events.
And further performing accident minimum segmentation on the type corresponding to the fault based on the fault factor and the unit monitoring data. The method comprises the steps of performing multi-level segmentation until a minimum fault accident is determined, using the minimum segmentation as the most aggressive segmentation set, performing association analysis on the minimum segmentation set and the wind turbine generator faults, determining the wind turbine generator faults possibly caused by the minimum segmentation accident, including influence faults generated along with fermentation of the minimum segmentation accident, using the influence faults as fault early warning results, performing reverse fault association analysis layer by layer according to a fault knowledge graph based on the minimum segmentation accident by performing accident minimum segmentation, and early warning by using possible faults with association relations as analysis results, so as to guarantee completeness of fault query.
Further, in the step S540 of constructing the fault early warning tree, the method further includes:
step S541: determining map positions of faults of the wind turbine generators according to the fault knowledge maps;
step S542: and based on the map positions, performing relational connection on the fault early warning models of the faults of the wind generation sets to construct the fault early warning tree.
Specifically, the fault knowledge graph has multi-level nodes, the fault knowledge graph respectively corresponds to faults of the wind generation sets, graph positions corresponding to the faults of the wind generation sets are determined, a fault early warning model is built based on a machine learning algorithm, the fault early warning model is a multi-level network layer and comprises an association recognition layer, a level analysis layer and an early warning output layer, the fault early warning model can perform multi-level early warning, the faults of the wind generation sets corresponding to the graph positions are respectively linked with one fault early warning model, the fault early warning model is of the same type, the fault early warning models are connected based on the connection relation of the fault knowledge graph, the fault early warning tree is generated, the corresponding models perform fault analysis and early warning when the fault nodes exist, meanwhile, the connection analysis is performed based on the association recognition layer, the early warning model is started when the connection relation exists, the fault analysis is performed based on the fault period and the association degree, the corresponding fault levels are determined when the fault influence exists, then the early warning information is generated based on the early warning output layer, and the automatic early warning analysis of the fault accident is realized.
Further, as shown in fig. 3, the fault influence factor identification data obtained from the big data platform is input into a fault early warning tree, each fault is analyzed and early warned, and fault early warning information is output, where step S600 in the present application further includes:
step S610: inputting fault influence factor identification data into the fault early warning tree, and early warning each fault to obtain early warning information of each map node;
step S620: judging whether the early warning information of each map node meets preset requirements or not;
step S630: when the condition is met, sending fault early warning information;
step S640: when the fault risk is not met, determining the fault risk weight according to the risk degree of the fault of each node in the fault knowledge graph;
step S650: and calculating based on the fault incidence relation and the fault risk weight in the fault knowledge graph to obtain comprehensive early warning information, and determining the fault early warning information according to the comprehensive early warning information.
Specifically, the fault influence factor identification data is called based on the big data platform, and is input into the fault early warning tree, a position having an association relation with the fault influence factor is determined, a corresponding fault early warning model is started, early warning information of each map node is obtained through model analysis so as to perform early warning, whether the early warning information of each map node meets the preset requirement is further judged, the preset requirement is a critical value of node fault occurrence, when the preset requirement is met, the fault influence factor causes the fault occurrence, the fault early warning information is sent to perform early warning, so that fault correction is performed in time, when the preset requirement is not met, a fault accident corresponding to the current node is not occurred but has a certain fault hidden danger, a risk weight of each node is determined based on the risk degree of each node fault in the fault knowledge graph, wherein the fault risk weight is in direct proportion to the fault risk degree, an associated node corresponding to the node to be analyzed is determined based on the fault association relation in the fault knowledge graph, the risk weight calculation of the associated node is used as the risk level of the node, the comprehensive fault risk information is generated based on the fault risk level, and early warning information is output and early warning management is performed based on the fault early warning information.
Further, the present application further includes step S700, including:
step S710: acquiring minimum segmentation fault information and fault area positioning information;
step S720: performing area range work order matching based on the minimum segmentation fault information and the fault area positioning information, and determining matched work order information;
step S730: acquiring work order processing plan information according to the matched work order information;
step S740: judging whether the work order processing plan information meets processing requirements, wherein the processing requirements comprise influence degree information and timeliness information;
step S750: and generating processing work order information when the influence degree information and the aging information are both satisfied.
Specifically, fault information of a minimum segmentation accident is determined, fault positioning is further performed, a wind turbine generator is positioned, fault area positioning information is obtained, an operation and maintenance management area of the wind turbine generator is used as the area range, work order matching is performed based on the minimum segmentation fault information and the fault area positioning information, an optimal operation and maintenance group is determined, matching work order information is generated, fault correction information extraction is performed based on the matching work order information, work order processing plan information is generated, influence information and aging information are set, the aging information is a fault processing event interval, failure grade promotion possibly caused by exceeding of the aging information is generated, the influence information is a related influence range of a current fault and is used as the processing requirement whether the related fault is caused or not, whether the work order processing plan information meets the processing requirement or not is judged, when the influence information and the aging information meet both, the work order processing plan information can finish fault correction, the processing work order information is generated and is transferred to a corresponding operation group, and normal operation of the fault maintenance and guarantee unit is performed in time.
Example two
Based on the same inventive concept as the wind turbine generator fault monitoring and early warning method based on big data in the foregoing embodiment, as shown in fig. 4, the present application provides a wind turbine generator fault monitoring and early warning system based on big data, the system includes:
the system comprises an information acquisition module 11, wherein the information acquisition module 11 is used for acquiring a wind turbine database from a big data platform, and the wind turbine database comprises turbine monitoring data and fault recording information;
the map building module 12, the map building module 12 is used for building a fault knowledge map based on the fault record information;
the influence factor determination module 13 is configured to analyze the associated influence data of each fault in the fault knowledge graph to determine a fault influence factor;
the data identification module 14 is used for identifying the data type of the big data platform according to the fault influence factor and automatically acquiring data based on the data type identification;
the early warning tree construction module 15 is used for determining each fault early warning model according to the fault knowledge map and the unit monitoring data to construct a fault early warning tree;
and the fault early warning module 16 is used for inputting the fault influence factor identification data acquired from the big data platform into a fault early warning tree, analyzing and early warning each fault, and outputting fault early warning information.
Further, the system further comprises:
the information determining module is used for analyzing the fault element according to the fault record information and determining the type information of the fault element;
the risk analysis module is used for analyzing the fault risk degree according to the fault record information based on the fault element type information to determine the fault risk degree;
the information classification module is used for classifying the fault element type information according to the fault risk degree and determining fault risk degree classification information;
the grade acquisition module is used for acquiring the map position grade of each fault according to the fault risk grade classification information;
the influence information determining module is used for analyzing and extracting influence data of each fault based on the map position grade of each fault and determining influence information of each fault;
and the knowledge graph construction module is used for connecting the associated faults in the graph position levels of the faults based on the fault influence information to construct the fault knowledge graph.
Further, the system further comprises:
the period analysis module is used for carrying out trend period analysis on each fault according to the fault record information and determining trend period information of each fault type;
the risk degree determining module is used for determining the risk degree of each period according to the trend period information of each fault type;
the map position establishing module is used for establishing periodic risk map positions based on the periodic risk degrees;
a location embedding module to embed the periodic risk map locations into the map location classes of each fault.
Further, the system further comprises:
the fault information extraction module is used for extracting fault information of a preset risk degree according to the fault knowledge map, and the fault information of the preset risk degree comprises faults of a plurality of wind turbine generators;
the fault factor analysis module is used for sequentially taking faults of the wind turbine generators as top events and analyzing fault factors;
the accident segmentation module is used for performing accident minimum segmentation on the corresponding type of the fault based on the fault factor and the unit monitoring data to determine a minimum segmentation set;
and the early warning result determining module is used for determining a fault early warning result according to the incidence relation between the minimum segmentation set and the fault of the wind turbine generator.
Further, the system further comprises:
the position determining module is used for determining map positions of faults of the wind turbine generators according to the fault knowledge maps;
and the fault early warning tree construction module is used for carrying out relational connection on fault early warning models of faults of the wind turbine generators based on map positions to construct the fault early warning tree.
Further, the system further comprises:
the node early warning information acquisition module is used for inputting fault influence factor identification data into the fault early warning tree, early warning each fault and acquiring early warning information of each map node;
the information judgment module is used for judging whether the early warning information of each map node meets preset requirements or not;
the early warning information sending module is used for sending fault early warning information when the fault early warning information is met;
the weight determining module is used for determining the fault risk weight according to the risk degree of each node fault in the fault knowledge graph when the fault risk weight is not met;
and the fault early warning information determining module is used for calculating based on the fault incidence relation and the fault risk weight in the fault knowledge graph to obtain comprehensive early warning information, and determining the fault early warning information according to the comprehensive early warning information.
Further, the system further comprises:
the fault information acquisition module is used for acquiring minimum segmentation fault information and fault area positioning information;
the work order matching module is used for matching the work orders within the area range based on the minimum segmentation fault information and the fault area positioning information and determining matched work order information;
the plan acquisition module is used for acquiring work order processing plan information according to the matched work order information;
the plan judgment module is used for judging whether the work order processing plan information meets the processing requirements, and the processing requirements comprise influence degree information and aging information;
and the work order information generation module is used for generating and processing the work order information when the influence degree information and the aging information are both satisfied.
In the present specification, through the foregoing detailed description of the wind turbine generator fault monitoring and early warning method based on big data, those skilled in the art can clearly know that the wind turbine generator fault monitoring and early warning method and system based on big data in the present embodiment.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A wind turbine generator fault monitoring and early warning method based on big data is characterized by comprising the following steps:
acquiring a wind turbine database from a big data platform, wherein the wind turbine database comprises turbine monitoring data and fault recording information;
constructing a fault knowledge graph based on the fault recording information;
analyzing according to the association influence data of each fault in the fault knowledge graph to determine a fault influence factor;
according to the fault influence factor, carrying out data type identification on the big data platform, and automatically acquiring data based on the data type identification;
determining each fault early warning model according to the fault knowledge map and the unit monitoring data, and constructing a fault early warning tree;
and inputting the fault influence factor identification data acquired from the big data platform into a fault early warning tree, analyzing and early warning each fault, and outputting fault early warning information.
2. The method of claim 1, wherein constructing a fault knowledge graph based on the fault record information comprises:
analyzing the fault element according to the fault record information to determine the type information of the fault element;
analyzing the fault risk degree according to the fault record information based on the fault element type information, and determining the fault risk degree;
classifying the fault element type information according to the fault risk degree, and determining fault risk degree classification information;
obtaining map position grades of all faults according to the fault risk grade classification information;
analyzing and extracting influence data of each fault based on the map position grade of each fault, and determining influence information of each fault;
and connecting the associated faults in the map position levels of the faults based on the fault influence information to construct the fault knowledge map.
3. The method of claim 2, wherein the method further comprises:
trend period analysis is carried out on each fault according to the fault record information, and trend period information of each fault type is determined;
determining the risk degree of each period according to the trend period information of each fault type;
establishing a periodic risk map position based on each periodic risk degree;
embedding the periodic risk map locations into the map location hierarchy of each fault.
4. The method of claim 1, wherein determining each fault early warning model based on the fault knowledge graph and the unit monitoring data comprises:
extracting fault information of a preset risk degree according to the fault knowledge map, wherein the fault information of the preset risk degree comprises faults of a plurality of wind turbine generators;
sequentially taking the faults of the wind turbine generators as top events, and analyzing fault factors;
performing accident minimum segmentation on the corresponding type of the fault based on the fault factor and the unit monitoring data, and determining a minimum segmentation set;
and determining a fault early warning result according to the incidence relation between the minimum segmentation set and the fault of the wind turbine generator.
5. The method of claim 4, wherein the constructing the fault warning tree comprises:
determining map positions of faults of the wind turbine generators according to the fault knowledge maps;
and based on the map positions, performing relational connection on the fault early warning models of the faults of the wind generation sets to construct the fault early warning tree.
6. The method of claim 1, wherein inputting the fault influence factor identification data obtained from the big data platform into a fault early warning tree, performing each fault analysis early warning, and outputting fault early warning information, comprises:
inputting fault influence factor identification data into the fault early warning tree, and early warning each fault to obtain early warning information of each map node;
judging whether the early warning information of each map node meets preset requirements or not;
when the condition is met, sending fault early warning information;
when the fault risk is not met, determining the fault risk weight according to the risk degree of the fault of each node in the fault knowledge graph;
and calculating based on the fault incidence relation and the fault risk weight in the fault knowledge graph to obtain comprehensive early warning information, and determining the fault early warning information according to the comprehensive early warning information.
7. The method of claim 4, wherein the method further comprises:
acquiring minimum segmentation fault information and fault area positioning information;
performing area range work order matching based on the minimum segmentation fault information and the fault area positioning information, and determining matched work order information;
acquiring work order processing plan information according to the matched work order information;
judging whether the work order processing plan information meets processing requirements, wherein the processing requirements comprise influence degree information and timeliness information;
and generating processing work order information when the influence degree information and the aging information are both satisfied.
8. The utility model provides a wind turbine generator system fault monitoring early warning system based on big data which characterized in that, the system includes:
the system comprises an information acquisition module, a fault detection module and a fault analysis module, wherein the information acquisition module is used for acquiring a wind turbine database from a big data platform, and the wind turbine database comprises turbine monitoring data and fault recording information;
the map construction module is used for constructing a fault knowledge map based on the fault recording information;
the influence factor determination module is used for analyzing according to the associated influence data of each fault in the fault knowledge graph to determine a fault influence factor;
the data identification module is used for carrying out data type identification on the big data platform according to the fault influence factor and automatically acquiring data based on the data type identification;
the early warning tree construction module is used for determining each fault early warning model according to the fault knowledge map and the unit monitoring data to construct a fault early warning tree;
and the fault early warning module is used for inputting the fault influence factor identification data acquired from the big data platform into a fault early warning tree, analyzing and early warning each fault and outputting fault early warning information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211458225.2A CN115712735A (en) | 2022-11-21 | 2022-11-21 | Big data-based wind turbine generator fault monitoring and early warning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211458225.2A CN115712735A (en) | 2022-11-21 | 2022-11-21 | Big data-based wind turbine generator fault monitoring and early warning method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115712735A true CN115712735A (en) | 2023-02-24 |
Family
ID=85234357
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211458225.2A Pending CN115712735A (en) | 2022-11-21 | 2022-11-21 | Big data-based wind turbine generator fault monitoring and early warning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115712735A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116701731A (en) * | 2023-06-08 | 2023-09-05 | 费莱(浙江)科技有限公司 | Dynamic monitoring and early warning method for operation stability in life cycle of motor |
| CN116880395A (en) * | 2023-07-19 | 2023-10-13 | 天津市易控科技发展有限公司 | Monitoring method, device, equipment and medium based on DCS system |
| CN117040137A (en) * | 2023-10-09 | 2023-11-10 | 国网山东省电力公司聊城供电公司 | Ring main unit temperature rise early warning method, system, terminal and medium based on multi-source data |
| CN117808456A (en) * | 2023-12-30 | 2024-04-02 | 龙坤(无锡)智慧科技有限公司 | Equipment fault early warning method and device based on intelligent operation management |
-
2022
- 2022-11-21 CN CN202211458225.2A patent/CN115712735A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116701731A (en) * | 2023-06-08 | 2023-09-05 | 费莱(浙江)科技有限公司 | Dynamic monitoring and early warning method for operation stability in life cycle of motor |
| CN116701731B (en) * | 2023-06-08 | 2024-04-05 | 费莱(浙江)科技有限公司 | Dynamic monitoring and early warning method for operation stability in life cycle of motor |
| CN116880395A (en) * | 2023-07-19 | 2023-10-13 | 天津市易控科技发展有限公司 | Monitoring method, device, equipment and medium based on DCS system |
| CN116880395B (en) * | 2023-07-19 | 2024-06-07 | 天津市易控科技发展有限公司 | Monitoring method, device, equipment and medium based on DCS system |
| CN117040137A (en) * | 2023-10-09 | 2023-11-10 | 国网山东省电力公司聊城供电公司 | Ring main unit temperature rise early warning method, system, terminal and medium based on multi-source data |
| CN117040137B (en) * | 2023-10-09 | 2024-05-07 | 国网山东省电力公司聊城供电公司 | Ring main unit temperature rise early warning method, system, terminal and medium based on multi-source data |
| CN117808456A (en) * | 2023-12-30 | 2024-04-02 | 龙坤(无锡)智慧科技有限公司 | Equipment fault early warning method and device based on intelligent operation management |
| CN117808456B (en) * | 2023-12-30 | 2024-06-11 | 龙坤(无锡)智慧科技有限公司 | Equipment fault early warning method and device based on intelligent operation management |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115712735A (en) | Big data-based wind turbine generator fault monitoring and early warning method and system | |
| Hsu et al. | Wind turbine fault diagnosis and predictive maintenance through statistical process control and machine learning | |
| He et al. | A spatio-temporal multiscale neural network approach for wind turbine fault diagnosis with imbalanced SCADA data | |
| CN107220469B (en) | Method and system for estimating state of fan | |
| CN110362045B (en) | Marine doubly-fed wind turbine generator fault discrimination method considering marine meteorological factors | |
| CN113339204B (en) | Wind driven generator fault identification method based on hybrid neural network | |
| CN111878320B (en) | Monitoring method and system of wind generating set and computer readable storage medium | |
| CN114856941A (en) | Offshore wind power plant and unit fault diagnosis operation and maintenance system and diagnosis operation and maintenance method thereof | |
| CN115822887A (en) | Performance evaluation and energy efficiency diagnosis method and system of wind turbine generator | |
| CN114487705A (en) | Power grid equipment fault positioning detection method | |
| CN114463143A (en) | Method for enhancing SCADA fault data of offshore doubly-fed wind generator | |
| CN117521498A (en) | Charging pile guide type fault diagnosis prediction method and system | |
| CN115469585B (en) | Hydropower unit state monitoring method and system based on big data | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN114837902B (en) | Health degree evaluation method, system, equipment and medium for wind turbine generator | |
| CN113902222B (en) | New forms of energy wisdom fortune dimension system | |
| CN115598459A (en) | Power failure prediction method for 10kV feeder line fault of power distribution network | |
| CN113762536A (en) | Fault early warning system of generator set equipment | |
| CN117200449B (en) | Multi-dimensional algorithm analysis-based power grid monitoring management method and system | |
| CN117951633B (en) | Photovoltaic power generation equipment fault diagnosis method and system | |
| Liu et al. | Wind turbine spindle operating state recognition and early warning driven by SCADA data | |
| Siddhartha et al. | Artificial Intelligent Approach to Prediction Analysis of Engineering Fault Detection and Segregation Based on RNN | |
| CN118008727A (en) | Wind power system-based fault early warning device and system | |
| Shuai et al. | Deep Fault Diagnosis of Marine Diesel Generator Sets Based on Multi-Level Decision Fusion Model | |
| CN117869213A (en) | Wind turbine generator abnormality detection method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |