CN113537415A - Convertor station inspection method and device based on multi-information fusion and computer equipment - Google Patents
Convertor station inspection method and device based on multi-information fusion and computer equipment Download PDFInfo
- Publication number
- CN113537415A CN113537415A CN202111089906.1A CN202111089906A CN113537415A CN 113537415 A CN113537415 A CN 113537415A CN 202111089906 A CN202111089906 A CN 202111089906A CN 113537415 A CN113537415 A CN 113537415A
- Authority
- CN
- China
- Prior art keywords
- data
- fusion
- information
- running state
- state
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The application relates to a convertor station inspection method and device based on multi-information fusion and computer equipment. The method comprises the following steps: acquiring running state data of a monitored object in a converter station; performing data fusion processing on the running state data to obtain fusion data; carrying out data mining processing on the fusion data to obtain target influence data influencing the running state of the monitored object; carrying out regression analysis on the target influence data to obtain a real-time predicted value of the running state of the monitored object; and when the real-time predicted value exceeds the numerical range of the normal running state of the monitored object stored in the running state database, early warning is carried out. The method can effectively solve the problems of the inspection of the convertor station equipment, realize the automatic inspection of the machine and the automatic data acquisition, reduce the workload of operation and maintenance personnel, improve the inspection quality of the convertor station equipment, improve the inspection automation degree of the convertor station equipment, and realize the unmanned and the less-humanized effects of all stations.
Description
Technical Field
The application relates to the technical field of electric power, in particular to a convertor station inspection method and device based on multi-information fusion, computer equipment and a storage medium.
Background
At present, the monitoring of the equipment state of the converter station plays a very critical role in the prevention of power grid accidents, the mode of 'manual inspection + machine inspection' is often adopted for carrying out inspection of the converter station, but in the application process, a monitoring system only plays a role in real-time uploading of running state signals of related system equipment, functions such as equipment running data analysis in the station, equipment running risk assessment and intelligent early warning of the running state of the equipment cannot be realized, an effective auxiliary effect cannot be achieved, the pertinence of operation and maintenance personnel in operation is reduced, and the error rate of judgment according to manual experience is increased.
Disclosure of Invention
Therefore, it is necessary to provide a converter station inspection method and device, a computer device and a storage medium based on multi-information fusion aiming at the technical problems that the monitoring system cannot play an effective auxiliary role, the operation pertinence of operation and maintenance maintainers is reduced, and the error rate of judgment according to manual experience is increased.
A convertor station inspection method based on multi-information fusion comprises the following steps:
acquiring running state data of a monitored object in a converter station;
performing data fusion processing on the running state data to obtain fusion data;
performing data mining processing on the fusion data to obtain target influence data influencing the running state of the monitored object;
carrying out regression analysis processing on the target influence data to obtain a real-time predicted value of the running state of the monitored object;
and when the real-time predicted value exceeds the numerical range of the normal running state of the monitored object stored in the running state database, early warning is carried out on the monitored object in the converter station.
In one embodiment, the performing data fusion processing on the operating state data to obtain fused data includes:
performing information fusion processing on the original data of the running state data to obtain data layer fusion data;
or, performing feature extraction processing on data from a target information source in the running state data to obtain feature data of the target information source, and performing information fusion processing on the feature data to obtain feature layer fusion data;
or, performing information fusion processing on the data layer fusion data and the feature layer fusion data to obtain decision layer fusion data.
In one embodiment, the performing data mining on the fusion data to obtain target influence data influencing the running state of the monitored object includes:
and carrying out data mining processing on any fused data in the data layer fused data, the feature layer fused data and the decision layer fused data based on a hierarchical clustering algorithm to obtain the target influence data.
In one embodiment, after obtaining the target influence data influencing the operation state of the monitoring object, the method further includes:
acquiring pre-experiment information, historical information and running state information of the monitored object;
and inputting the pre-experiment information, the historical information, the running state information and the target influence data into a trained multi-information fusion converter station monitoring object state evaluation model to obtain the running state of the monitoring object.
In one embodiment, the state evaluation model of the multi-information-fused converter station monitoring object is obtained by training in the following way, including:
acquiring sample pre-experiment information, sample historical information, sample online monitoring information and sample running state information of the monitored object as sample information data;
and training a state evaluation model to be trained through the sample information data to obtain the multi-information fusion converter station monitoring object state evaluation model.
In one embodiment, after obtaining the operation state of the monitoring object, the method further includes:
when the running state is a fault state, determining the fault state grade of the monitored object;
acquiring maintenance content corresponding to the fault state grade in a preset knowledge base according to the fault state grade; the knowledge base stores a plurality of fault cases and corresponding overhaul contents;
and generating an operation report of the monitored object based on the overhaul content, and sending the operation report to a user terminal.
In one embodiment, the method further comprises:
when a new fault case is obtained, judging the new fault case to obtain an evaluation result;
and when the evaluation result passes the verification, storing the new fault case into the knowledge base to obtain an updated knowledge base.
A convertor station inspection device based on multi-information fusion, the device comprises:
the acquisition module is used for acquiring the running state data of the monitored object in the converter station;
the fusion module is used for carrying out data fusion processing on the running state data to obtain fusion data;
the mining module is used for carrying out data mining processing on the fusion data to obtain target influence data influencing the running state of the monitored object;
the prediction module is used for carrying out regression analysis processing on the target influence data to obtain a real-time prediction value of the running state of the monitored object;
and the early warning module is used for early warning the monitoring object in the converter station when the real-time predicted value exceeds a numerical range of the monitoring object stored in the running state database and in a normal running state.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring running state data of a monitored object in a converter station;
performing data fusion processing on the running state data to obtain fusion data;
carrying out data mining processing on the fusion data to obtain target influence data influencing the running state of the monitored object;
carrying out regression analysis processing on the target influence data to obtain a real-time predicted value of the running state of the monitored object;
and when the real-time predicted value exceeds the numerical range of the normal running state of the monitored object stored in the running state database, early warning is carried out on the monitored object in the converter station.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring running state data of a monitored object in a converter station;
performing data fusion processing on the running state data to obtain fusion data;
carrying out data mining processing on the fusion data to obtain target influence data influencing the running state of the monitored object;
carrying out regression analysis processing on the target influence data to obtain a real-time predicted value of the running state of the monitored object;
and when the real-time predicted value exceeds the numerical range of the normal running state of the monitored object stored in the running state database, early warning is carried out on the monitored object in the converter station.
According to the convertor station inspection method, the convertor station inspection device, the computer equipment and the storage medium based on multi-information fusion, after the running state data of the monitored object in the convertor station is obtained, the running state data is subjected to data fusion and data mining to obtain target influence data influencing the running state of the monitored object, regression analysis is performed on the target influence data to obtain a real-time predicted value of the running state of the monitored object, the real-time predicted value is matched with a numerical range of the monitored object stored in a running state database and in a normal running state, and early warning is performed according to a matching result. The method focuses on changing the existing manual inspection and recording mode, can effectively solve the problems existing in the inspection of the convertor station equipment, realizes automatic inspection of a machine and automatic data acquisition, reduces the work burden of operation and maintenance personnel, improves the inspection quality of the convertor station equipment, improves the inspection automation degree of the convertor station equipment, and realizes unmanned and unmanned of each station; the functions of analyzing the operation data of the equipment in the station, evaluating the operation risk of the equipment, intelligently early warning the operation state of the equipment and the like are realized by deeply mining and applying the monitoring data of the equipment, data support and scientific criteria are provided for the subsequent state maintenance, and the safe and stable operation of the equipment of the converter station is ensured.
Drawings
FIG. 1 is a diagram of the overall architecture of a converter station training system based on multi-information fusion in one embodiment;
FIG. 2 is a schematic flow chart of a convertor station inspection method based on multi-information fusion in one embodiment;
FIG. 3 is a diagram illustrating data layer information fusion, feature layer information fusion, and decision layer information fusion, in accordance with an embodiment;
FIG. 4 is a schematic flow chart of a convertor station inspection method based on multi-information fusion in another embodiment;
FIG. 5 is a schematic flow chart diagram illustrating the operation of data analysis in one embodiment;
FIG. 6 is a functional block diagram of a system of a convertor station inspection system based on multi-information fusion in one embodiment;
FIG. 7 is a flow chart of the operation of the inspection system for the converter station based on multi-information fusion in one embodiment;
FIG. 8 is a block diagram of a converter station inspection device based on multi-information fusion in one embodiment;
FIG. 9 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The application provides a numerical intelligence convertor station inspection method based on multi-information fusion, which is mainly developed from three dimensions of data acquisition intellectualization, data transmission synergy and data fusion depth, and is designed and transformed intelligently aiming at the problems in the data acquisition, data processing and data utilization processes.
Referring to fig. 1, in order to implement the overall architecture diagram of the multi-information fusion-based converter station training system of the present application, a front-end acquisition system is composed of intelligent equipment arranged on a converter station site, and is used for acquiring environmental data, equipment operation data, equipment status data, and the like of a converter station line field, so as to achieve intelligent sensing acquisition of converter station inspection data, and transmit the data to a server end through an HTTPS protocol; the server side is composed of a background management system, is an application carrier of data, realizes analysis and decision of the data, synchronously pushes the data to a client side of a user workstation and a mobile terminal application APP, and simultaneously receives data update participated by the client side and the APP; the client and the APP can receive the server push synchronization information, check the inspection defects and the fault processing progress of the converter station equipment, and synchronously upload the data processing operation request behaviors of the user and the related data records to the server.
In one embodiment, as shown in fig. 2, a converter station inspection method based on multi-information fusion is provided, which is described by taking the method as an example applied to the server side in fig. 1, and includes the following steps:
step S202, obtaining the operation state data of the monitoring object in the converter station.
The monitoring objects can be converter transformers, converter valves, circuit breakers, direct current equipment, valve coolers, valve halls, isolating switches, motors, terminal boxes, control cubicles and other auxiliary equipment.
In specific implementation, intelligent equipment can be arranged on the site of the converter station to form a front-end acquisition system, intelligent sensing and acquisition of converter station monitoring data are realized, the monitoring data are connected and communicated with a server end in modes of optical fiber/4G/Bluetooth and the like, and are transmitted through protocols such as HTTPS and the like. Meanwhile, the server end accesses the monitoring data of the existing monitoring system, and obtains the running state data of the monitored object according to the monitoring data acquired by the front-end acquisition system and the monitoring data of the existing monitoring system. Wherein, intelligent equipment contains unmanned aerial vehicle, removes and patrols and examines robot, high definition digtal camera, infrared and visible light camera, partial discharge on-line monitoring, optic fibre winding temperature measurement, arrester on-line monitoring, SF6 gas pressure on-line monitoring, humiture on-line monitoring etc..
On the basis of acquiring a plurality of equipment state information, organizing application operation support data according to four processes of data access, data cleaning, data fusion and data mining, wherein the data source of a front-end acquisition system is various and has different monitoring data characteristics such as equipment vibration, equipment real-time temperature, equipment noise and the like, and the acquired data format also comprises structured data and unstructured data, so that the data access of a server end needs to fuse multi-source heterogeneous data types such as files, pictures, audio, video and the like, an acquisition standard specification and a uniform data communication protocol are established for the structured data (table data, databases and the like) and the unstructured data (files, pictures, audio and video and the like), the service is called according to a service calling interface specification, the associative data access is carried out, and various data information islands among station domains are communicated, therefore, the intelligent equipment such as the on-station online monitoring device, the camera and the infrared temperature measurement can be effectively linked, data circulation is realized, scenes such as inspection, supervision, operation, accident handling and safety operation of the converter station equipment are effectively supported, and the defects that a barrier exists between various monitoring data and data communication cannot be realized are overcome. For the service integration access of the existing monitoring system, the service access is carried out according to the specific technical architecture of the system and the existing system service integration access specification.
And step S204, performing data fusion processing on the running state data to obtain fusion data.
In specific implementation, the data fusion of the operation state data includes three types of fusion, namely data layer data fusion, feature layer data fusion and decision layer data fusion. More specifically, when the original data in the running state data is subjected to information fusion processing, data layer fusion data are obtained; when the data from the target information source in the running state data is subjected to feature extraction processing to obtain feature data of the target information source, and when the feature data is subjected to information fusion processing, feature layer fusion data is obtained; and when the data layer fusion data and the feature layer fusion data are subjected to information fusion processing, the decision layer fusion data are obtained.
And step S206, performing data mining processing on the fusion data to obtain target influence data influencing the running state of the monitored object.
In specific implementation, empirical knowledge and an intelligent analysis algorithm can be fused, state information and knowledge which are hidden in the fused data and have potential useful important effects on safe operation of the converter station equipment are extracted from the fused data, and the state information and the knowledge are used as target influence data influencing the operation state of a monitoring object.
And step S208, carrying out regression analysis processing on the target influence data to obtain a real-time predicted value of the running state of the monitored object.
In specific implementation, a regression prediction model may be trained in advance, specifically, a regression analysis prediction model may be established by taking target influence data obtained by real-time online monitoring as an independent variable and taking an operation state of a monitored object as a dependent variable, and performing calculation according to historical statistical data of the independent variable and the dependent variable, wherein a certain relationship exists between the dependent variable and the independent variable (for example, the operation state of equipment is abnormal because real-time monitoring data has a difference change compared with normal monitoring data). When the regression prediction model passes various tests and the prediction error is smaller than the threshold value, the calculation value prediction can be carried out through the regression prediction model, namely after target influence data are obtained, a prediction value set is obtained on the basis of the target influence data and the regression prediction model, each prediction value is represented in a coordinate system, a scattering point corresponding to each prediction value represents the approximate trend that a dependent variable changes along with an independent variable, a regression equation is adopted to fit a straight line capable of covering the data to a large extent to represent the prediction value, and finally, data which do not meet requirements are removed through comprehensive analysis to obtain a final prediction value.
And step S210, when the real-time predicted value exceeds the numerical range of the normal running state of the monitored object stored in the running state database, early warning is carried out on the monitored object.
In specific implementation, the operation state database can be obtained by performing data mining on historical information monitored by the converter station equipment through an improved hierarchical clustering algorithm, and the operation state database contains a numerical range of a monitored object in a normal operation state. After the real-time predicted value of the operation state of the monitored object is obtained, the real-time predicted value can be matched with the numerical range of the monitored object in the normal operation state stored in the operation state database, when the real-time predicted value exceeds the corresponding numerical range, the monitored object is judged to possibly have a fault, and pre-warning is carried out by utilizing a preset warning rule.
According to the convertor station inspection method based on multi-information fusion, after the running state data of the monitored object in the convertor station is obtained, the running state data is subjected to data fusion and data mining to obtain target influence data influencing the running state of the monitored object, regression analysis is carried out on the target influence data to obtain a real-time predicted value of the running state of the monitored object, the real-time predicted value is matched with a numerical range of the monitored object stored in a running state database and in a normal running state, and early warning is carried out according to a matching result. The method focuses on changing the existing manual inspection and recording mode, can effectively solve the problems existing in the inspection of the convertor station equipment, realizes automatic inspection of a machine and automatic data acquisition, reduces the work burden of operation and maintenance personnel, improves the inspection quality of the convertor station equipment, improves the inspection automation degree of the convertor station equipment, and realizes unmanned and unmanned of each station; the functions of analyzing the operation data of the equipment in the station, evaluating the operation risk of the equipment, intelligently early warning the operation state of the equipment and the like are realized by deeply mining and applying the monitoring data of the equipment, data support and scientific criteria are provided for the subsequent state maintenance, and the safe and stable operation of the equipment of the converter station is ensured.
In one embodiment, step S204 specifically includes: performing information fusion processing on data from different information sources in the running state data to obtain data layer fusion data; or, performing feature extraction processing on data from a target information source in the running state data to obtain feature data of the target information source, and performing information fusion processing on the feature data to obtain feature layer fusion data; or, performing information fusion processing on the data layer fusion data and the feature layer fusion data to obtain decision layer fusion data.
In a specific implementation, referring to fig. 3, schematic diagrams of data layer information fusion, feature layer information fusion, and decision layer information fusion are respectively shown, where the data layer information fusion represents fusion performed on an acquired original data layer, and data synthesis and analysis are performed before original measured reports of various sensors are not preprocessed; the feature layer information fusion represents that the original information from the sensor is subjected to feature extraction (the features can be the edge, the direction, the speed, the vibration, the temperature, the noise and the like of a target), and then the feature information is subjected to comprehensive analysis and processing; decision layer information fusion means that the same target is observed by different types of sensors, and each sensor locally performs basic processing including preprocessing, feature extraction, recognition or judgment to establish a preliminary conclusion on the observed target.
In the embodiment, different types of data fusion are performed, so that the required fusion data can be selected according to requirements during data mining.
In an exemplary embodiment, before step S204, a data cleaning process is further performed on the operation state data, and a data fusion process is performed on the operation state data after the data cleaning. Specifically, the accessed massive running state data can be subjected to missing value cleaning, format content cleaning, logic error cleaning, non-required data cleaning and relevance verification according to the characteristics of the data source of the massive running state data; secondly, calling a rule for data formatting in the rule base, and formatting and standardizing the data set needing to be cleaned, such as replacing abbreviations, replacing illegal characters and the like. And then, cleaning error data, similar repeated data, incomplete data, calling a cleaning algorithm of the expansion module and the like according to the sequence. Finally, manual processing is performed for situations that cannot be automatically processed. Meanwhile, the correctness of data cleaning can be checked by checking the data cleaning log, and the cleaning error can be corrected manually. The original monitoring data and the operation data are converted into state quantities which can be identified by operation management, analysis and evaluation, evaluation and diagnosis algorithm and early warning mechanism, and basic data support is provided for follow-up intelligent decision analysis.
In an embodiment, the step S206 specifically includes: and carrying out data mining processing on any fused data in the data layer fused data, the feature layer fused data and the decision layer fused data based on a hierarchical clustering algorithm to obtain target influence data.
Hierarchical Clustering (Hierarchical Clustering) is one of Clustering algorithms, and a Hierarchical nested cluster tree is created by calculating similarities between data points of different classes. In a cluster tree, the original data points of different classes are the lowest level of the tree, and the top level of the tree is the root node of a cluster.
In specific implementation, based on consideration of time complexity, an improved hierarchical clustering algorithm can be adopted to perform data mining processing on any fused data of the data layer fused data, the feature layer fused data and the decision layer fused data, so as to obtain target influence data influencing safe operation of converter station equipment.
In the embodiment, data mining is performed through an improved hierarchical clustering algorithm, so that time complexity can be reduced, and accuracy of data mining results is improved.
In one embodiment, after obtaining the target influence data influencing the operation state of the monitored object, the method further comprises: acquiring pre-experiment information, historical information and running state information of a monitored object; inputting the pre-experiment information, the historical information, the running state information and the target influence data into a trained multi-information fusion convertor station monitoring object state evaluation model to obtain the running state of the monitoring object.
The operation state comprises a normal state and a fault state, and the fault state comprises an attention state, an abnormal state and a serious state.
The pre-experiment information is used for representing various characteristics of the monitoring object and is state information indispensable for fault diagnosis and state evaluation of the monitoring object.
The historical information is used for representing the basic state of the monitoring object before operation.
The online monitoring information is the concrete representation of the current state of the monitored object.
The operation state information is a record of the operation state of the monitoring object, and is related to the service life and the aging state of the monitoring object.
For example, taking a transformer as an example, the result of the preliminary test can basically reflect various characteristics of the transformer, and the information data corresponding to the preliminary test mainly comprises winding direct-current resistance, chromatographic analysis of gas dissolved in oil, an insulating oil test, a loss factor of a winding medium, iron core insulation resistance and the like; the historical information comprises technical performance parameters of the transformer, factory inspection data, handover acceptance inspection data, maintenance records, fault records and the like, and the data information forms a basic state of the transformer before operation; the on-line monitoring information is the concrete representation of the current state of the transformer and mainly comprises data of gas chromatography analysis, partial discharge, winding deformation monitoring, iron core grounding current monitoring and the like; the running state information comprises load of the transformer, oil temperature data, sealing and leakage, abnormal noise of the transformer in running, bad working conditions and the like, and is a record of the running state of the transformer, and the running state is directly related to the service life and the aging state of the transformer.
In the embodiment, the running state of the monitored object is determined together with the target influence data through the pre-experiment information, the historical information and the running state information of the monitored object, so that the accuracy of the obtained running state result is greatly improved.
In one embodiment, the state evaluation model of the monitoring object of the multi-information fusion converter station is obtained by training in the following way: acquiring sample pre-experiment information, sample historical information, sample online monitoring information and a sample running state of a monitored object as sample data; and training the state evaluation model to be trained through the sample data to obtain the multi-information fusion converter station monitoring object state evaluation model.
In specific implementation, an RBF (Radial Basis Function) neural network can be pre-constructed as a state evaluation model to be trained, according to division of state information of converter station equipment, four types of sub-information such as pre-test information, history information, online monitoring information, running state information and the like of a monitoring object are used as information input spaces, each sub-information space is input, and a corresponding state subset can be obtained through training of the RBF neural network, wherein the equipment state subset can be divided into four conditions: normal state, attentive state, abnormal state, severe state. Finally, testing the trained network to determine the performance of each sub-network (including the recognition rate, the misjudgment rate and the rejection rate of the network); and then, constructing an evidence body by using the output results of each sub-network, and obtaining a final evaluation conclusion, namely the running state of the monitored object of the evaluated converter station, by adopting an improved synthesis rule through evidence fusion reasoning analysis. It is understood that the RBF neural network may be replaced by a support vector machine, a decision tree, a fault tree, etc., and the present application is not limited thereto.
For example, taking a transformer as an example, the normal state: the transformer state quantity is stable and within the warning value and the attention value (standard limit) specified by the regulation, and the transformer can normally operate. Note the state: the trend of the single (or multiple) state quantity changes towards the direction close to the standard limit value, but the state quantity does not exceed the standard limit value, the operation can be continued, and the monitoring in the operation is enhanced. Abnormal state: the single important state quantity has larger change and exceeds or slightly exceeds the standard limit value, the operation is monitored, and the power failure maintenance is carried out at the right time. Severe state: the single important state quantity seriously exceeds the standard limit value, and the power failure maintenance needs to be arranged as soon as possible.
In this embodiment, the state evaluation model to be trained is trained through the sample information data to obtain the multi-information-fused converter station monitoring object state evaluation model, so as to further obtain a more accurate diagnosis result (such as a normal state, an attention state, an abnormal state, and a severe state) of the running state of the monitoring object according to the multi-information-fused converter station monitoring object state evaluation model.
In one embodiment, after obtaining the operation state of the monitoring object, the method further includes: when the running state is a fault state, determining the fault state grade of the detection object; acquiring maintenance content corresponding to the fault state grade in a preset knowledge base according to the fault state grade; the knowledge base stores a plurality of fault cases and corresponding overhaul contents; and generating an operation report of the monitored object based on the overhaul content, and sending the operation report to the user terminal.
The fault status levels may include three levels, an attention status, an abnormal status, and a severity status.
In the concrete implementation, after the fault state grade of the monitoring object of the converter station is obtained, relevant maintenance regulations and maintenance manuals in the knowledge base can be automatically matched according to the fault state grade, for example: the intelligent infrared inspection monitoring system for the field valve hall and the valve cooling of the converter station has the conditions of inaccurate temperature measurement, incapability of focusing, infrared power-on fault and the like, the system searches in a knowledge base according to fault characteristics, automatically matches converter valve maintenance files, and draws a conclusion according to the maintenance files: the problems of inaccurate temperature measurement and incapability of focusing are solved by manually presetting focusing, hardware problems of infrared power-on faults, incapability of focusing of partial cameras and the like are solved by replacing fault cameras, the operation report and the operation suggestion of a monitored object are synchronously pushed to the user terminal, and operation and maintenance personnel of the user terminal can overhaul according to the operation suggestion.
In the embodiment, the fault state grade of the monitored object is determined, the corresponding overhaul content is obtained, the operation report is generated and sent to the user terminal, operation and maintenance personnel of the user terminal can overhaul the monitored object according to the operation suggestion, and the equipment operation and maintenance efficiency and the decision-making assisting capability are improved.
In one embodiment, further comprising: when a new fault case is obtained, judging the new fault case to obtain an evaluation result; and when the evaluation result passes the verification, storing the new fault case into the knowledge base so as to update the knowledge base.
In the specific implementation, the knowledge base can represent an expert knowledge base, the expert knowledge base contains a large amount of expert knowledge in the power field, for example, the state evaluation of the transformer can be realized in the mode of case matching and the like during the state evaluation of the transformer, in addition, the expert knowledge base also has a self-learning function, a state evaluation standard is formed through the existing expert experience, and when a new case is input, self judgment can be carried out to obtain an evaluation result. After the transformer equipment evaluation result is verified, the expert knowledge base can store the new fault case, and the updating and iteration of the fault case base are realized.
In the embodiment, the matching rate of the fault case base and the fault of the monitored object can be improved by updating the fault case base, and the condition that the fault case base and the monitored object are not matched is reduced.
In one embodiment, as shown in fig. 4, another method for inspecting a converter station based on multi-information fusion is provided, and in this embodiment, the method includes the following steps:
step S402, acquiring running state data of a monitoring object in the converter station, and performing data fusion processing on the running state data to obtain fusion data;
step S404, performing data mining processing on the fusion data to obtain target influence data influencing the running state of the monitored object;
step S406, acquiring pre-experiment information, historical information and running state information of the monitored object;
step S408, inputting pre-experimental information, historical information, running state information and target influence data into a trained multi-information-fused converter station monitoring object state evaluation model to obtain the running state of a monitoring object;
step S410, when the running state is the fault state, determining the fault state grade of the monitored object;
step S412, acquiring maintenance content corresponding to the fault state grade in a preset knowledge base according to the fault state grade; the knowledge base stores a plurality of fault cases and corresponding overhaul contents;
and step S414, generating an operation report of the monitored object based on the overhaul content, and sending the operation report to the user terminal.
The method for the intelligent inspection of the converter station is characterized in that a set of complete intelligent converter station inspection method based on multi-information fusion is provided, intelligent equipment such as an inspection robot, an unmanned aerial vehicle and a high-definition camera and various sensors such as force, light, sound, heat and electricity are comprehensively applied, and an intelligent monitoring data acquisition technology is researched; establishing a unified data acquisition standard specification and a data communication protocol to realize the access of data with different structure types; original monitoring and operation data are converted into state quantities which can be identified by operation management, analysis evaluation, evaluation and diagnosis algorithm and early warning mechanism through the processes of data cleaning, data conversion, data screening, data verification and the like; the method is characterized in that system data fusion technologies such as converter station equipment monitoring, online monitoring, video, security, fire protection, environment monitoring and the like are researched, information collected by various sensors is comprehensively analyzed and processed, robot routing inspection data, discrete monitoring data and the like are subjected to information fusion, and intelligent comprehensive sensing of converter station number routing inspection is achieved; the method comprises the steps of establishing a convertor station equipment operation key index evaluation model, judging the equipment operation state and trend, combining with the dynamic historical fault case library and the historical fault risk library to automatically alarm, realizing integrated, digital and intelligent routing inspection, providing data support and scientific criteria for subsequent state maintenance, effectively improving the efficiency and accuracy of convertor station equipment routing inspection, reducing the routing inspection workload of routing inspection personnel, and improving the intelligent routing inspection level of convertor station equipment.
In one embodiment, to facilitate understanding of the embodiments of the present application by those skilled in the art, the method of the present application will be described below with reference to the accompanying drawings. Referring to fig. 5, a schematic flow chart of data analysis work according to the present application is shown, where based on obtaining state information of a plurality of monitoring objects, organization of application operation support data is implemented according to four processes of data access, data cleaning, data fusion, and data mining.
Wherein, the data access: according to different monitoring data characteristics such as equipment vibration, equipment real-time temperature, equipment noise and the like, and different structure type data such as table data, a database, files, pictures, audio, video and the like, a unified data acquisition standard specification and a data communication protocol are established, and service calling is carried out according to a service calling interface specification.
Data cleaning: firstly, carrying out missing value cleaning, format content cleaning, logic error cleaning, non-demand data cleaning and relevance verification on the accessed massive monitoring data according to the characteristics of a data source of the massive monitoring data; secondly, calling a rule for data formatting in the rule base, and formatting and standardizing the data set needing to be cleaned, such as replacing abbreviations, replacing illegal characters and the like. And then, cleaning error data, similar repeated data, incomplete data, calling a cleaning algorithm of the expansion module and the like according to the sequence. Finally, manual processing is performed for situations that cannot be automatically processed.
Data fusion: the data collected by different knowledge sources or sensors are combined according to established rules to form a more comprehensive, reliable and complete description of the equipment object. The hierarchical result of the fusion information can have three basic fusion types, namely data layer information fusion, feature layer information fusion and decision layer information fusion.
Data mining: and empirical knowledge and an intelligent analysis algorithm are fused, and latent and useful equipment state information and knowledge are extracted from the fused data, so that fault diagnosis, analysis and evaluation and intelligent early warning of the monitored object are realized.
Referring to fig. 6, which is a functional block diagram of the system of the present application, the platform according to this embodiment includes eight functional blocks, namely, device management, routing inspection management, defect management, knowledge management, alarm management, trend analysis, report management, and log management. Referring to fig. 7, as a system service flow chart of the present application, in the embodiment, the platform accesses data acquired by the front-end acquisition system and data of an existing monitoring system, the system makes a periodic inspection task (periodic task) according to an operation and maintenance measure table of each station of the converter station, and may dynamically adjust an inspection period of an operation and maintenance policy according to equipment inspection data and equipment state trend sensing (normal, attention, abnormality, and severity), increase inspection frequency according to actual conditions, and increase equipment operation inspection strength. After the task allocation and the task issuing are completed, the task information is synchronously updated to the server and synchronously pushed to the client and the APP. The field operation personnel visit the intelligence converter station system of patrolling and examining through the browser (or through mobile terminal (cell-phone, Pad etc.) APP), look over operations such as task, download task, executive task, patrol and examine the process through the APP terminal in the executive task process and record, save the record after patrolling and examining the completion, click the task information synchronization that data synchronization can be with the APP terminal to the server side. The behavior operations such as query, download, execution, export and the like performed by field operators at the browser client and the APP end have corresponding data records, and are synchronously uploaded to the server end for updating and backup.
The periodic inspection task (periodic task) is formulated according to an operation and maintenance measure table of each station of the converter station, and the inspection content of the converter transformer equipment comprises casing inspection, body inspection, voltage regulation tap switch inspection, cooling device inspection, an online monitoring device, a non-electric quantity protection device (which can be observed by a video monitoring system), a control box, a mechanism box moisture-proof seal and secondary element inspection, oil temperature checking, temperature winding, on-load tap switch gear site and background indication consistency and the like.
If the converter transformer body is inspected, the following contents need to be inspected:
1. checking whether the oil temperature, the winding temperature, the oil level of the body oil conservator and the oil level of the on-load tap changer are abnormal or not, wherein the high alarm value of the oil temperature of the body is 75 ℃, and the high alarm value of the linear temperature of the body is 110 ℃; the temperature indication controller has good appearance, the dial plate has good sealing without condensation, and the temperature display pointer is not higher than the highest temperature pointer; when the oil level is suspected to be abnormal, the actual oil level of the oil conservator is checked by means of an infrared imager and the like.
2. Checking the oil leakage condition and judging the severity. The following parts were examined for oil leakage (video monitoring, etc. if necessary): each valve, meter, tap switch, flange connection and welding seam in the visible range of the body. The cooler valve, the radiating pipe, the oil pump and the like are well connected; the oil level indicator has complete appearance and indicates normal; the oil tank, the lifting seat, the tank wall of the body and the like have no sign of oil leakage.
Determining the inspection category of the converter transformer body inspection as daily inspection according to the contents of a +/-500 kV inspection operation instruction book of the converter transformer from the western converter station, wherein the inspection period is 1 time/8 days, the frequency is 3.75 times per month, and the specially-inspected planned times are 90 (Taiji/times); according to a polling operation instruction book of +/-500 kV secondary terminal boxes and DC blocking devices of the converter transformer of the western converter station, the control box, the mechanism box and the secondary element inspection are determined to belong to daily polling, the polling period is 1 time/half month, the frequency is 2 times per month, and the polling time is 48 (benches and times). The inspection contents of different equipment need to be determined according to corresponding operation instruction books, and the determined contents comprise inspection types, inspection periods, inspection frequency and the like, wherein the inspection periods and the inspection frequency can also be dynamically adjusted according to the running states (normal state, attention state, abnormal state and serious state) of the equipment, and if the equipment with serious faults increases the inspection frequency according to the actual condition, the key equipment is focused, the inspection force is increased, and the problem finding is facilitated.
After the system formulates the inspection task, field operating personnel download the inspection task to the terminal in a WIFI/4G/5G mode through a mobile terminal APP access system, operations such as task checking and execution are carried out, and finally the task information of the APP end is synchronized to the server end. The method comprises the steps of intelligently analyzing the trend of the existence of defect hidden danger or fault risk in the state of the sensing equipment through background information fusion, automatically linking intelligent equipment such as a high-definition camera, an inspection robot and the like which are arranged on the site by an inspection system to verify the condition, dynamically adjusting the inspection period, the important attention equipment, the close attention parameter and the like of an operation and maintenance strategy according to the inspection data of the equipment and the trend sensing of the state of the equipment, automatically creating an inspection task according to the level of the state of the risk of the equipment, and informing field operation personnel to go out of the fault equipment to perform secondary inspection and inspection.
By the method provided by the application, the following beneficial effects can be realized: (1) the comprehensive application patrols intelligent equipment such as a patrolling robot, an unmanned aerial vehicle and a high-definition camera and various sensors such as optoacoustic thermoelectric devices, and realizes the analysis and extraction of key parameters of equipment facilities of the convertor station in a mode with highest efficiency and lowest cost. Such as: the inspection robot is adopted to carry out repetitive work to replace manual accurate judgment of the in-place operation condition; the online monitoring equipment is matched with the image recognition technology, real-time monitoring of the equipment condition is achieved, alarming and reminding are conducted on abnormal conditions, all-weather, all-around and all-autonomous intelligent inspection of the convertor station equipment is achieved, and meanwhile inspection efficiency of the convertor station is greatly improved. (2) According to the method, by fusing multi-source heterogeneous data types such as files, pictures, audios and videos, structured and unstructured association access, deep mining, comprehensive analysis and data storage are performed, meanwhile, an expert knowledge base is dynamically constructed, deep fusion and application of intelligent monitoring data are achieved, and necessary data are provided for later-stage equipment operation state analysis. (3) According to the method and the device, the intelligent study and judgment of the running state and the trend of the equipment are carried out by establishing a converter station equipment running key index evaluation model, the automatic alarm of a historical fault case library and a historical fault risk library is combined, the message reminding of key attention objects is realized, the functions of routing inspection task making, routing inspection route planning, risk defect processing strategy pushing and the like are realized, and finally the integrated, digital and intelligent routing inspection is realized. (4) According to the application, the high-definition camera device is combined with an image recognition technology and a video stream analysis technology, on-site smoke and fire recognition is achieved, abnormal conditions such as safety helmets, smoking, fire and the like are not worn according to regulations or illegal behavior alarm reminding is achieved, the accident rate of an operation site can be reduced, the operation safety of personnel is guaranteed, the on-site safe operation control coverage range is strengthened, and the all-dimensional three-dimensional inspection monitoring disc is achieved.
It should be understood that although the steps in the flowcharts of fig. 2 and 4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2 and 4 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.
In one embodiment, as shown in fig. 8, there is provided a converter station inspection device based on multi-information fusion, including: an obtaining module 802, a fusing module 804, a mining module 806, a prediction module 808, and an early warning module 810, wherein:
an obtaining module 802, configured to obtain operation state data of a monitored object in a converter station;
the fusion module 804 is used for performing data fusion processing on the running state data to obtain fusion data;
the mining module 806 is configured to perform data mining on the fusion data to obtain target influence data that influences the operation state of the monitored object;
the prediction module 808 is configured to perform regression analysis on the target influence data to obtain a real-time prediction value of the operation state of the monitored object;
and the early warning module 810 is configured to perform early warning on the monitoring object in the flow switching station when the real-time predicted value exceeds a value range of the monitoring object stored in the operation state database in a normal operation state.
In an embodiment, the fusion module 804 is specifically configured to perform information fusion processing on the original data of the running state data to obtain data layer fusion data; or, performing feature extraction processing on data from a target information source in the running state data to obtain feature data of the target information source, and performing information fusion processing on the feature data to obtain feature layer fusion data; or, performing information fusion processing on the data layer fusion data and the feature layer fusion data to obtain decision layer fusion data.
In an embodiment, the mining module 806 is specifically configured to perform data mining on any one of the data layer fusion data, the feature layer fusion data, and the decision layer fusion data based on a hierarchical clustering algorithm to obtain target influence data.
In one embodiment, the device further comprises a state determination module, configured to obtain pre-experiment information, historical information, and operating state information of the monitored object; inputting the pre-experiment information, the historical information, the running state information and the target influence data into a trained multi-information fusion convertor station monitoring object state evaluation model to obtain the running state of the monitoring object.
In one embodiment, the device further comprises a model training module, configured to obtain sample pre-experiment information, sample history information, sample online monitoring information, and sample running state information of the monitored object, as sample information data; and training the state evaluation model to be trained through the sample information data to obtain the multi-information fusion converter station monitoring object state evaluation model.
In one embodiment, the apparatus further includes a report generation module, configured to determine a fault status level of the monitored object when the operation status is a fault status; acquiring maintenance content corresponding to the fault state grade in a preset knowledge base according to the fault state grade; the knowledge base stores a plurality of fault cases and corresponding overhaul contents; and generating an operation report of the monitored object based on the overhaul content, and sending the operation report to the user terminal.
In one embodiment, the apparatus further includes an updating module, configured to determine a new fault case when the new fault case is obtained, so as to obtain an evaluation result; and when the evaluation result passes the verification, storing the new fault case into the knowledge base to obtain an updated knowledge base.
It should be noted that the converter station inspection device based on multi-information fusion of the present application corresponds to the converter station inspection method based on multi-information fusion of the present application one to one, and the technical features and the beneficial effects thereof described in the above embodiments of the converter station inspection method based on multi-information fusion are all applicable to the embodiments of the converter station inspection device based on multi-information fusion, and specific contents may refer to the descriptions in the embodiments of the method of the present application, and are not repeated herein, and thus, the present application claims.
In addition, all or part of the modules in the convertor station inspection device based on multi-information fusion can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing data in the inspection process of the converter station based on multi-information fusion. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to realize a convertor station inspection method based on multi-information fusion.
Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A convertor station inspection method based on multi-information fusion is characterized by comprising the following steps:
acquiring running state data of a monitored object in a converter station;
performing data fusion processing on the running state data to obtain fusion data;
performing data mining processing on the fusion data to obtain target influence data influencing the running state of the monitored object;
carrying out regression analysis processing on the target influence data to obtain a real-time predicted value of the running state of the monitored object;
and when the real-time predicted value exceeds the numerical range of the normal running state of the monitored object stored in the running state database, early warning is carried out on the monitored object in the converter station.
2. The method according to claim 1, wherein the performing data fusion processing on the operating state data to obtain fused data comprises:
performing information fusion processing on the original data of the running state data to obtain data layer fusion data;
or the like, or, alternatively,
performing feature extraction processing on data from a target information source in the running state data to obtain feature data of the target information source, and performing information fusion processing on the feature data to obtain feature layer fusion data;
or the like, or, alternatively,
and carrying out information fusion processing on the data layer fusion data and the feature layer fusion data to obtain decision layer fusion data.
3. The method according to claim 2, wherein the performing data mining on the fusion data to obtain target influence data influencing the operation state of the monitored object comprises:
and carrying out data mining processing on any fused data in the data layer fused data, the feature layer fused data and the decision layer fused data based on a hierarchical clustering algorithm to obtain the target influence data.
4. The method of claim 1, after obtaining target impact data that impacts the operational state of the monitored object, further comprising:
acquiring pre-experiment information, historical information and running state information of the monitored object;
and inputting the pre-experiment information, the historical information, the running state information and the target influence data into a trained multi-information fusion converter station monitoring object state evaluation model to obtain the running state of the monitoring object.
5. The method according to claim 4, wherein the multi-information-fused converter station monitoring object state estimation model is trained by the following method comprising:
acquiring sample pre-experiment information, sample historical information, sample online monitoring information and sample running state information of the monitored object as sample information data;
and training a state evaluation model to be trained through the sample information data to obtain the multi-information fusion converter station monitoring object state evaluation model.
6. The method of claim 4, further comprising, after obtaining the operational status of the monitored object:
when the running state is a fault state, determining the fault state grade of the monitored object;
acquiring maintenance content corresponding to the fault state grade in a preset knowledge base according to the fault state grade; the knowledge base stores a plurality of fault cases and corresponding overhaul contents;
and generating an operation report of the monitored object based on the overhaul content, and sending the operation report to a user terminal.
7. The method of claim 6, further comprising:
when a new fault case is obtained, judging the new fault case to obtain an evaluation result;
and when the evaluation result passes the verification, storing the new fault case into the knowledge base to obtain an updated knowledge base.
8. The utility model provides a converter station inspection device based on multi-information fusion which characterized in that, the device includes:
the acquisition module is used for acquiring the running state data of the monitored object in the converter station;
the fusion module is used for carrying out data fusion processing on the running state data to obtain fusion data;
the mining module is used for carrying out data mining processing on the fusion data to obtain target influence data influencing the running state of the monitored object;
the prediction module is used for carrying out regression analysis processing on the target influence data to obtain a real-time prediction value of the running state of the monitored object;
and the early warning module is used for early warning the monitoring object in the converter station when the real-time predicted value exceeds a numerical range of the monitoring object stored in the running state database and in a normal running state.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111089906.1A CN113537415A (en) | 2021-09-17 | 2021-09-17 | Convertor station inspection method and device based on multi-information fusion and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111089906.1A CN113537415A (en) | 2021-09-17 | 2021-09-17 | Convertor station inspection method and device based on multi-information fusion and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113537415A true CN113537415A (en) | 2021-10-22 |
Family
ID=78093293
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111089906.1A Pending CN113537415A (en) | 2021-09-17 | 2021-09-17 | Convertor station inspection method and device based on multi-information fusion and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113537415A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114093145A (en) * | 2021-11-12 | 2022-02-25 | 许继集团有限公司 | Visual-auditory cooperative power equipment inspection system and method |
| CN114513401A (en) * | 2022-01-28 | 2022-05-17 | 上海云轴信息科技有限公司 | Automatic operation and maintenance repair method and device for private cloud and computer readable medium |
| CN117010601A (en) * | 2023-09-28 | 2023-11-07 | 武汉吧哒科技股份有限公司 | Data processing method, device, computer equipment and computer readable storage medium |
| WO2023223448A1 (en) * | 2022-05-18 | 2023-11-23 | 日本電気株式会社 | Information processing device, information processing method, and program |
| WO2024012109A1 (en) * | 2022-07-11 | 2024-01-18 | 中兴通讯股份有限公司 | Inspection method, alarm method, inspection system, and computer-readable storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107274115A (en) * | 2017-08-11 | 2017-10-20 | 国网江苏省电力公司电力科学研究院 | Active distribution network Situation Awareness System and method based on distributed monitoring and Multi-source Information Fusion |
| CN107506832A (en) * | 2017-07-10 | 2017-12-22 | 国网浙江省电力公司温州供电公司 | The hidden danger method for digging aided in is maked an inspection tour to monitoring |
| CN107578066A (en) * | 2017-09-07 | 2018-01-12 | 南京莱斯信息技术股份有限公司 | Civil defence comprehensive situation based on Multi-source Information Fusion shows system and method |
| CN108037415A (en) * | 2017-12-15 | 2018-05-15 | 国网江苏省电力有限公司南京供电分公司 | Distribution network failure information excavating and diagnostic method based on multi-source heterogeneous data |
| CN108564254A (en) * | 2018-03-15 | 2018-09-21 | 国网四川省电力公司绵阳供电公司 | Controller switching equipment status visualization platform based on big data |
| CN110716103A (en) * | 2019-09-27 | 2020-01-21 | 国网山西省电力公司太原供电公司 | Early warning method for distribution network fault |
| CN112529036A (en) * | 2020-11-06 | 2021-03-19 | 上海发电设备成套设计研究院有限责任公司 | Fault early warning method, device, equipment and storage medium |
| CN112557445A (en) * | 2020-11-17 | 2021-03-26 | 华中科技大学 | Defect online detection method, device and system based on additive manufacturing |
| CN112686402A (en) * | 2020-12-28 | 2021-04-20 | 无锡市工业设备安装有限公司 | Method for combining daily inspection and intelligent operation and maintenance management platform |
-
2021
- 2021-09-17 CN CN202111089906.1A patent/CN113537415A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107506832A (en) * | 2017-07-10 | 2017-12-22 | 国网浙江省电力公司温州供电公司 | The hidden danger method for digging aided in is maked an inspection tour to monitoring |
| CN107274115A (en) * | 2017-08-11 | 2017-10-20 | 国网江苏省电力公司电力科学研究院 | Active distribution network Situation Awareness System and method based on distributed monitoring and Multi-source Information Fusion |
| CN107578066A (en) * | 2017-09-07 | 2018-01-12 | 南京莱斯信息技术股份有限公司 | Civil defence comprehensive situation based on Multi-source Information Fusion shows system and method |
| CN108037415A (en) * | 2017-12-15 | 2018-05-15 | 国网江苏省电力有限公司南京供电分公司 | Distribution network failure information excavating and diagnostic method based on multi-source heterogeneous data |
| CN108564254A (en) * | 2018-03-15 | 2018-09-21 | 国网四川省电力公司绵阳供电公司 | Controller switching equipment status visualization platform based on big data |
| CN110716103A (en) * | 2019-09-27 | 2020-01-21 | 国网山西省电力公司太原供电公司 | Early warning method for distribution network fault |
| CN112529036A (en) * | 2020-11-06 | 2021-03-19 | 上海发电设备成套设计研究院有限责任公司 | Fault early warning method, device, equipment and storage medium |
| CN112557445A (en) * | 2020-11-17 | 2021-03-26 | 华中科技大学 | Defect online detection method, device and system based on additive manufacturing |
| CN112686402A (en) * | 2020-12-28 | 2021-04-20 | 无锡市工业设备安装有限公司 | Method for combining daily inspection and intelligent operation and maintenance management platform |
Non-Patent Citations (4)
| Title |
|---|
| 姚伟义主编: "《实用金融预测方法》", 31 March 1992 * |
| 朱玉生: "基于物联网的输变电设备故障诊断", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 * |
| 沈燚 等: "换流站阀厅智能巡检机器人系统设计及应用", 《电力安全技术》 * |
| 袁路路: "基于电力物联网的智能配电房状态监测与故障预警研究", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114093145A (en) * | 2021-11-12 | 2022-02-25 | 许继集团有限公司 | Visual-auditory cooperative power equipment inspection system and method |
| CN114513401A (en) * | 2022-01-28 | 2022-05-17 | 上海云轴信息科技有限公司 | Automatic operation and maintenance repair method and device for private cloud and computer readable medium |
| WO2023223448A1 (en) * | 2022-05-18 | 2023-11-23 | 日本電気株式会社 | Information processing device, information processing method, and program |
| WO2024012109A1 (en) * | 2022-07-11 | 2024-01-18 | 中兴通讯股份有限公司 | Inspection method, alarm method, inspection system, and computer-readable storage medium |
| CN117010601A (en) * | 2023-09-28 | 2023-11-07 | 武汉吧哒科技股份有限公司 | Data processing method, device, computer equipment and computer readable storage medium |
| CN117010601B (en) * | 2023-09-28 | 2024-01-19 | 武汉吧哒科技股份有限公司 | Data processing method, device, computer equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113537415A (en) | Convertor station inspection method and device based on multi-information fusion and computer equipment | |
| CN110401262B (en) | GIS equipment state intelligent monitoring system and method based on edge computing technology | |
| CN109146093B (en) | Power equipment field investigation method based on learning | |
| US11289944B2 (en) | Distribution network risk identification system and method and computer storage medium | |
| CN105353702B (en) | Intelligent monitoring system for high-voltage equipment | |
| US10310453B2 (en) | Dynamic assessment system for high-voltage electrical components | |
| CN108073551B (en) | High-voltage switch cabinet online fault diagnosis method based on multi-Agent cooperation | |
| CN112036610A (en) | Intelligent cable early warning platform and early warning method based on big data analysis | |
| CN108398934B (en) | equipment fault monitoring system for rail transit | |
| CN112926257A (en) | Reciprocating natural gas compressor fault diagnosis system and diagnosis method | |
| US20160292802A1 (en) | Asset Management Support System | |
| CN110729813A (en) | Intelligent operation and maintenance and full life cycle management method for transformer substation and cloud management platform | |
| CN113904443A (en) | Multidimensional space visual field transformer equipment monitoring and early warning system | |
| CN115657617A (en) | Implementation method of intelligent monitoring alarm system for thermal power plant | |
| CN111143447B (en) | Dynamic monitoring early warning decision system and method for weak links of power grid | |
| KR20110048771A (en) | The engineering platform system of the electric power- telemetrics and its using method | |
| CN110907064A (en) | GIS disconnecting switch contact temperature prediction method and device and readable storage medium | |
| CN113204919B (en) | Method and device for predicting state of main transformer conservator based on digital twinning and electronic equipment | |
| CN117251810A (en) | Substation equipment state evaluation early warning system and method based on digital twin platform | |
| Wang et al. | Power equipment fault information acquisition system based on Internet of things | |
| CN115618303A (en) | Dispatching automation monitoring and fault positioning system based on information fusion technology | |
| CN114066163A (en) | Power equipment state analysis method and device based on three-layer architecture mode | |
| CN113869589A (en) | Power transmission line accident prediction method based on knowledge graph and inspection system | |
| CN104751281A (en) | Automatic working condition evaluation method for zinc oxide arrester equipment | |
| CN112104073B (en) | Real-time information calibration method for power system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211022 |
|
| RJ01 | Rejection of invention patent application after publication |