CN116054416B - Intelligent monitoring operation and maintenance management system based on Internet of things - Google Patents
Intelligent monitoring operation and maintenance management system based on Internet of things Download PDFInfo
- Publication number
- CN116054416B CN116054416B CN202310249294.0A CN202310249294A CN116054416B CN 116054416 B CN116054416 B CN 116054416B CN 202310249294 A CN202310249294 A CN 202310249294A CN 116054416 B CN116054416 B CN 116054416B
- Authority
- CN
- China
- Prior art keywords
- alarm
- invalid
- unit
- layer module
- analysis unit
- 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.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
Abstract
The application relates to the technical field of intelligent monitoring operation and maintenance management, in particular to an intelligent monitoring operation and maintenance management system based on the Internet of things, which comprises a display layer module, a service storage layer module, a transmission layer module and a perception layer module; the display layer module is used for outputting data related to power distribution to a user based on a system front-end power distribution network framework; the service storage layer module is used for establishing a service storage layer based on the application server, the WEB server and the database server; the transmission layer module is used for connecting software and hardware of different networks based on the gateway; the sensing layer module is used for sensing and reading data related to power distribution based on the power distribution monitoring equipment; the application updates the alarm requirement of real-time monitoring aiming at the output invalid alarm characteristics, improves the alarm accuracy, increases the accurate alarm rate of alarm events and avoids the generation of extra work of the dispatcher.
Description
Technical Field
The application relates to the technical field of intelligent monitoring operation and maintenance management, in particular to an intelligent monitoring operation and maintenance management system based on the Internet of things.
Background
The intelligent power distribution monitoring operation and maintenance system is a monitoring platform combining traditional power operation and maintenance through various technologies such as the Internet, the Internet of things and cloud computing, and can effectively realize intelligent operation and maintenance of power equipment; in the prior art, the platform can also dispatch operation and maintenance personnel in real time through a mobile phone APP, can quickly lock faults and timely process the faults, improves the supervision work efficiency, and freely designs databases, pictures and reports through configuration tools, wherein the database, the pictures and the reports comprise various visual modes such as geographic diagrams, wiring diagrams, curves, stick diagrams, cake diagrams, tables, meters, animations and the like; however, in the intelligent power distribution monitoring operation and maintenance process, a plurality of alarm events exist, and a situation that some alarm events are false alarms exists, so that extra workload is brought to operators for dispatching operation and maintenance, and the problem that how to effectively analyze the false alarms to improve the alarm accuracy is the problem that the current system needs to be optimized; meanwhile, the relevance among different alarm types is difficult to determine, and how to carry out relevance alarm on different alarm events based on monitoring data so as to improve alarm efficiency is also a problem to be solved by the intelligent power distribution monitoring operation and maintenance system.
Disclosure of Invention
The application aims to provide an intelligent monitoring operation and maintenance management system based on the Internet of things, which aims to solve the problems in the background technology.
In order to solve the technical problems, the application provides the following technical scheme: an intelligent monitoring operation and maintenance management system based on the Internet of things comprises a presentation layer module, a service storage layer module, a transmission layer module and a perception layer module;
the display layer module is used for outputting data related to power distribution to a user based on a system front-end power distribution network framework;
the service storage layer module is used for establishing a service storage layer based on the application server, the WEB server and the database server; the application server and the database server are connected and transmitted, the application server transmits signals to the WEB server, and the database server transmits signals to the WEB server;
the transmission layer module is used for connecting software and hardware of different networks based on the gateway;
the sensing layer module is used for sensing and reading data related to power distribution based on the power distribution monitoring equipment; the power distribution monitoring equipment comprises an intelligent ammeter, a calculator, a wireless metering module, a camera, a mutual inductor, microcomputer protection, an I/O module and a temperature and humidity sensor;
the perception layer module is connected with the transmission layer module, the transmission layer module is connected with the service storage layer module, the service storage layer module is connected with the display layer module, and when the display architecture in the display layer module is not unique, the service storage layer module can be respectively connected with different display architectures.
Further, the presentation layer module comprises an alarm event extraction unit and an alarm exception analysis unit;
the alarm event extraction unit is used for extracting alarm events recorded in the display layer module, wherein the alarm events comprise alarm types, alarm time and alarm information, and the alarm information refers to fault nodes corresponding to the alarm events;
the alarm event extracting unit transmits the extracted alarm event to the alarm abnormality analyzing unit;
the alarm anomaly analysis unit constructs an alarm type package by taking an alarm type as a root node, alarm time and alarm information as child nodes for an alarm event, wherein the alarm time and the alarm information are friend nodes;
the alarm anomaly analysis unit is used for carrying out set division on alarm type packages by taking the same alarm type as a unit, classifying the same alarm type packages into the same unit set and outputting the same alarm type packages into an alarm unit set; judging whether an invalid alarm packet exists in the alarm unit set, wherein the invalid alarm packet refers to a data packet recorded as a misjudgment alarm event after the alarm type packet in the alarm unit set is manually checked and verified;
when invalid alarm packets exist, the number of the invalid alarm packets is not unique and belongs to the same alarm unit set, and the alarm abnormality analysis unit outputs a first identification signal;
when invalid alarm packets exist, the number of the invalid alarm packets is not unique and the invalid alarm packets belong to different alarm unit sets, and the alarm abnormality analysis unit outputs a second identification signal.
The analysis alarm unit set is characterized in that different alarm events are recorded in the monitoring system, and execution rules of the alarm signals generated by the different alarm events are different, so that the initial data is divided by taking the alarm type as a distinguishing point, and the integration analysis of the data is facilitated.
Further, the service storage layer module comprises a signal identification unit and a feature analysis unit;
the signal identification unit is used for identifying the identification signal output by the alarm abnormality analysis unit, and transmitting the identification signal to the feature analysis unit after the identification is successful;
the feature analysis unit is used for extracting data from the alarm unit set corresponding to the first identification signal, sequencing alarm type packets in the alarm unit set according to the sequence of alarm time, and calculating an average alarm time interval T, T= (1/n-1) sigma (T) i+1 -t i ) Wherein t is i Alarm time, t, representing the ith alarm event i+1 The alarm time of the (i+1) th alarm event is represented, and n represents the total number of alarm events existing in the alarm unit set; i is more than or equal to 1 and less than or equal to n-1;
the method comprises the steps of marking the sequence positions of invalid alarm packages, extracting a feature set of the invalid alarm packages, wherein the feature set refers to image data acquired by a perception layer module and power distribution related data, and the power distribution related data comprises a switch state, a voltage current value, a temperature value and a transformer parameter value.
Further, the feature analysis unit comprises a similarity analysis unit, a feature attribution value calculation unit, a comparison condition analysis unit and a target feature output unit;
the similarity analysis unit obtains the kth attribute characteristic U of the jth invalid alarm package jk And outputs the feature similarity S of the corresponding features between the invalid alarm packets Uk ，S Uk Representing the similarity of the kth attribute characteristics corresponding to any two invalid alarm packets;
calculating average similarity S containing all features between any two invalid alarm packets 0 Extracting m (m-1)/2 average similarity S formed by m invalid alarm packets 0 J is less than or equal to m; obtaining invalid warning packet logarithm Q meeting average similarity greater than or equal to average similarity threshold 1 Transmitting the signal to a feature attribution value calculating unit, using the formula:
R＝Q 1 /[m*(m-1)/2]
calculating a characteristic attribution value R; calculating a characteristic attribution value to analyze whether attribute characteristics among invalid alarm packets have characteristic rules or not; setting a characteristic attribution value threshold R 0 And obtaining the average similarity E of other alarm type packages except invalid alarm packages in the alarm unit set 0 Average similarity refers to the alarm type between packagesA similarity average value of the corresponding attribute features;
the comparison condition analysis unit is set when R is more than or equal to R 0 ，
And S is 0 -E 0 Is greater than the first difference threshold value,
and when the event interval corresponding to any adjacent non-invalid alarm event of the alarm event corresponding to the invalid alarm packet is greater than or equal to the average alarm time interval T; the target feature output unit outputs an attribute feature with feature similarity greater than or equal to a similarity threshold value between the invalid alarm packets as an invalid target feature;
otherwise, the comparison condition analysis unit judges that any unsatisfied condition exists, and the transmission signal display layer module is returned to continue monitoring.
Further, the service storage layer module further comprises an event analysis unit;
the event analysis unit is used for starting the analysis unit when the signal recognition unit recognizes the second recognition signal;
the event analysis unit extracts the occurrence frequency X of the invalid alarm packet in the p-th alarm unit set p1 And the occurrence frequency X of the alarm type packet of the invalid alarm packet is removed from the p-th alarm unit set by the invalid alarm packet p2 The method comprises the steps of carrying out a first treatment on the surface of the Using the formula:
Z p ＝a 1 *(X p1 /X p2 )+a 2 *(m p1 /m)
calculating burst index Z corresponding to invalid alarm packet in p-th alarm unit set p Wherein m is p1 Representing the corresponding number when the similarity is greater than or equal to a similarity threshold value after the similarity of the invalid alarm package of the p-th alarm unit set and any invalid alarm package is compared, and m represents the total number of the invalid alarm packages; a, a 1 、a 2 Representing a first reference coefficient and a second reference coefficient, 0<a 1 、a 2 <1，a 1 +a 1 ＝1；
The burst index is analyzed to judge the contingency of the alarm type of the invalid alarm packet in the system monitoring process, and if the difference of the alarm types corresponding to the invalid alarm packet is larger and the existence frequency is lower, the contingency of the alarm event corresponding to the invalid alarm packet can be deduced to be larger;
setting a burst index threshold Z 0 ，
When Z is p <Z 0 When the transmission signal is transmitted, the transmission signal display layer module is returned to monitor continuously;
when Z is p ≥Z 0 When in use, then locate Z p ≥Z 0 And the corresponding alarm unit sets and transmits signals to the characteristic analysis unit to analyze and output invalid target characteristics. When the analyzed event does not meet the condition of contingency, a signal can be transmitted to a feature analysis unit which singly performs feature analysis to output, so that whether the invalid target feature with regularity exists is further accurately judged.
Further, the service storage layer module further comprises an alarm requirement updating unit;
extracting an invalid alarm packet to which the invalid target feature corresponds, and outputting the invalid alarm packet to be recorded in a first critical value of the display layer module, wherein the data critical value refers to the minimum value of recorded data in the invalid alarm packet;
extracting the minimum value of the corresponding record data of the alarm type package in the alarm unit set to which the invalid alarm package belongs as a second critical value;
if the first critical value is smaller than the second critical value, outputting an alarm requirement of the alarm unit set corresponding to the invalid target feature as the second critical value;
if the first critical value is larger than the second critical value, outputting an alarm requirement of the alarm unit set corresponding to the invalid target feature as the first critical value;
and if the first critical value is equal to the second critical value, comparing the invalid target characteristics in real time, and outputting the alarm requirement of the set of alarm units corresponding to the invalid target characteristics as the first critical value when the invalid target characteristics exist in real time, otherwise outputting the alarm requirement of the set of alarm units corresponding to the invalid target characteristics as the second critical value.
The method is characterized in that a new alarm requirement is output after invalid target characteristics are analyzed, when a first critical value is smaller than a second critical value, data corresponding to an event which does not actually need to be alarmed is included in alarm requirements initially set by a system, so that a corresponding interval of alarm data is reduced, and the alarm is more accurate.
Further, the intelligent monitoring operation and maintenance management system also comprises a multi-source early warning analysis module;
the multisource early warning analysis module is used for carrying out association analysis on different alarm events recorded by the monitoring operation and maintenance management system and determining the association between the different alarm events;
the multi-source early warning analysis module performs association analysis and comprises extracting set target characteristics in different warning type packages, wherein the set target characteristics comprise invalid target characteristics and conventional target characteristics, and the conventional target characteristics are attribute characteristics corresponding to warning type packages except invalid warning packages in the warning unit set;
drawing a radar chart corresponding to the f-th alarm type package by using the set target characteristics in the alarm type package, and marking an image interval V of the radar chart corresponding to the f-th alarm type package f Image interval V corresponding to d alarm type packages f Overlapping every two by the center of the radar chart, and comparing the overlapping area C, C= { V of the image interval 1 ∩V 2 ,V 1 ∩V 3 ,V 2 ∩V 3 ,......,V f-1 ∩V f F is less than or equal to d, d represents the number of types of alarm type packages;
and outputting two alarm type packages corresponding to the overlapping area threshold value which is larger than or equal to the overlapping area C as associated alarm packages with association.
Further, the multi-source early warning analysis module comprises a real-time early warning analysis unit;
the real-time early warning analysis unit is used for monitoring the alarm type of the transmission signal extraction alarm event when the intelligent monitoring operation and maintenance management system records the alarm event in real time;
when the alarm type does not exist in the associated alarm package, continuing monitoring;
and when the alarm type exists in the associated alarm package, transmitting a real-time early warning signal of another alarm type package in the associated alarm package. The relevance between the analysis alarm type packages can make early warning pre-judgment for the real-time monitoring system, so that the analysis efficiency of the system is improved, the relevance analysis of the distribution monitoring data by the system is more convenient, and the safety, the wide range and the multisource of the overall monitoring are improved.
Compared with the prior art, the application has the following beneficial effects: the application analyzes the alarm events recorded in the distribution monitoring system, takes the alarm type difference as a starting point to divide and extract the invalid alarm events, determines the alarm characteristics of the invalid alarm events by the uniqueness of the alarm events, and carries out secondary confirmation when the invalid alarm events are not unique, thereby improving the accuracy and the effectiveness of the alarm event analysis; the application updates the alarm requirement of real-time monitoring aiming at the output invalid alarm characteristics, improves the alarm accuracy, increases the accurate alarm rate of alarm events, avoids the generation of extra work of scheduling personnel, simultaneously analyzes the relevance among alarm type packages to make early warning pre-judgment for a real-time monitoring system, improves the analysis efficiency of the system, ensures that the relevance analysis of the system to distribution monitoring data is more convenient, and improves the safety, the wide range and the multisource of the whole monitoring.
Drawings
The accompanying drawings are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, serve to explain the application. In the drawings:
FIG. 1 is a schematic diagram of an intelligent monitoring operation management system based on the Internet of things;
FIG. 2 is a schematic diagram of a module unit of the intelligent monitoring operation and maintenance management system based on the Internet of things;
fig. 3 is a radar graphic illustration of an intelligent monitoring operation and maintenance management system based on the internet of things.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1-3, the present application provides the following technical solutions: an intelligent monitoring operation and maintenance management system based on the Internet of things comprises a presentation layer module, a service storage layer module, a transmission layer module and a perception layer module;
the display layer module is used for outputting data related to power distribution to a user based on a system front-end power distribution network framework;
the service storage layer module is used for establishing a service storage layer based on the application server, the WEB server and the database server; the application server and the database server are connected and transmitted, the application server transmits signals to the WEB server, and the database server transmits signals to the WEB server;
the transmission layer module is used for connecting software and hardware of different networks based on the gateway;
the sensing layer module is used for sensing and reading data related to power distribution based on the power distribution monitoring equipment; the power distribution monitoring equipment comprises an intelligent ammeter, a calculator, a wireless metering module, a camera, a mutual inductor, microcomputer protection, an I/O module and a temperature and humidity sensor;
the perception layer module is connected with the transmission layer module, the transmission layer module is connected with the service storage layer module, the service storage layer module is connected with the display layer module, and when the display architecture in the display layer module is not unique, the service storage layer module can be respectively connected with different display architectures. In practical application, the display architecture of the display layer is a carrier for supporting data, such as a computer end, a mobile phone end and a panel end.
The display layer module comprises an alarm event extraction unit and an alarm abnormality analysis unit;
the alarm event extraction unit is used for extracting alarm events recorded in the display layer module, wherein the alarm events comprise alarm types, alarm time and alarm information, and the alarm information refers to fault nodes corresponding to the alarm events;
the alarm event extracting unit transmits the extracted alarm event to the alarm abnormality analyzing unit;
the alarm anomaly analysis unit constructs an alarm type package by taking an alarm type as a root node, alarm time and alarm information as child nodes for an alarm event, wherein the alarm time and the alarm information are friend nodes;
the alarm anomaly analysis unit is used for carrying out set division on alarm type packages by taking the same alarm type as a unit, classifying the same alarm type packages into the same unit set and outputting the same alarm type packages into an alarm unit set; judging whether an invalid alarm packet exists in the alarm unit set, wherein the invalid alarm packet refers to a data packet recorded as a misjudgment alarm event after the alarm type packet in the alarm unit set is manually checked and verified;
when invalid alarm packets exist, the number of the invalid alarm packets is not unique and belongs to the same alarm unit set, and the alarm abnormality analysis unit outputs a first identification signal;
when invalid alarm packets exist, the number of the invalid alarm packets is not unique and the invalid alarm packets belong to different alarm unit sets, and the alarm abnormality analysis unit outputs a second identification signal.
The analysis alarm unit set is characterized in that different alarm events are recorded in the monitoring system, and execution rules of the alarm signals generated by the different alarm events are different, so that the initial data is divided by taking the alarm type as a distinguishing point, and the integration analysis of the data is facilitated.
The first identification signal is used for analyzing the condition of an invalid alarm packet in the same alarm unit set, and shows that certain characteristic rules exist in the alarm event, so that the accuracy rate is reduced on the original alarm rules set by the system monitoring, so that the alarm range is further reduced, and the accuracy rate is improved; the second identification signal is used for determining the meaning in different alarm unit sets, only needs to judge whether the alarm unit sets are accidental or inevitable, and if a rule exists, the analysis of the data of the single unit set can be performed like the first identification signal to obtain the characteristics.
The service storage layer module comprises a signal identification unit and a feature analysis unit;
the signal identification unit is used for identifying the identification signal output by the alarm abnormality analysis unit, and transmitting the identification signal to the feature analysis unit after the identification is successful;
the feature analysis unit is used for extracting data from the alarm unit set corresponding to the first identification signal, sequencing alarm type packets in the alarm unit set according to the sequence of alarm time, and calculating an average alarm time interval T, T= (1/n-1) sigma (T) i+1 -t i ) Wherein t is i Alarm time, t, representing the ith alarm event i+1 The alarm time of the (i+1) th alarm event is represented, and n represents the total number of alarm events existing in the alarm unit set; i is more than or equal to 1 and less than or equal to n-1;
the method comprises the steps of marking the sequence positions of invalid alarm packages, extracting a feature set of the invalid alarm packages, wherein the feature set refers to image data acquired by a perception layer module and power distribution related data, and the power distribution related data comprises a switch state, a voltage current value, a temperature value and a transformer parameter value.
The feature analysis unit comprises a similarity analysis unit, a feature attribution value calculation unit, a comparison condition analysis unit and a target feature output unit;
the similarity analysis unit obtains the kth attribute characteristic U of the jth invalid alarm package jk And outputs the feature similarity S of the corresponding features between the invalid alarm packets Uk ，S Uk Representing the similarity of the kth attribute characteristics corresponding to any two invalid alarm packets; when the characteristic is image data, comparing the similarity between the images, when the characteristic is a numerical value, the characteristic similarity is the ratio of the comparison numerical value difference value to the threshold value difference value, when the characteristic is a switching state, the characteristic similarity is 0 or 1, when the characteristics are the same, the output is 1, and when the characteristics are different, the output is 0; and carrying out normalization calculation on the similarity of different types;
calculating average similarity S containing all features between any two invalid alarm packets 0 Extracting m invalid noticesM-1/2 average similarity S formed by police packet 0 J is less than or equal to m; obtaining invalid warning packet logarithm Q meeting average similarity greater than or equal to average similarity threshold 1 Transmitting the signal to a feature attribution value calculating unit, using the formula:
R＝Q 1 /[m*(m-1)/2]
calculating a characteristic attribution value R; calculating a characteristic attribution value to analyze whether attribute characteristics among invalid alarm packets have characteristic rules or not; setting a characteristic attribution value threshold R 0 And obtaining the average similarity E of other alarm type packages except invalid alarm packages in the alarm unit set 0 The average similarity refers to the average value of the similarity of the corresponding attribute features among the alarm type packages;
the comparison condition analysis unit is set when R is more than or equal to R 0 ，
And S is 0 -E 0 Is greater than the first difference threshold value,
and when the event interval corresponding to any adjacent non-invalid alarm event of the alarm event corresponding to the invalid alarm packet is greater than or equal to the average alarm time interval T; the target feature output unit outputs an attribute feature with feature similarity greater than or equal to a similarity threshold value between the invalid alarm packets as an invalid target feature;
otherwise, the comparison condition analysis unit judges that any unsatisfied condition exists, and the transmission signal display layer module is returned to continue monitoring. At this time, the alarm event corresponding to the invalid alarm packet is described as an accidental emergency event, and the condition that the alarm requirement is redefined by the same type of difference features is not provided, so that the original alarm requirement is still maintained for alarming.
The service storage layer module also comprises an event analysis unit;
the event analysis unit is used for starting the analysis unit when the signal recognition unit recognizes the second recognition signal;
the event analysis unit extracts the occurrence frequency X of the invalid alarm packet in the p-th alarm unit set p1 And the occurrence frequency X of the alarm type packet of the invalid alarm packet is removed from the p-th alarm unit set by the invalid alarm packet p2 The method comprises the steps of carrying out a first treatment on the surface of the Using the formula:
Z p ＝a 1 *(X p1 /X p2 )+a 2 *(m p1 /m)
calculating burst index Z corresponding to invalid alarm packet in p-th alarm unit set p Wherein m is p1 Representing the corresponding number when the similarity is greater than or equal to a similarity threshold value after the similarity of the invalid alarm package of the p-th alarm unit set and any invalid alarm package is compared, and m represents the total number of the invalid alarm packages; a, a 1 、a 2 Representing a first reference coefficient and a second reference coefficient, 0<a 1 、a 2 <1，a 1 +a 1 ＝1；
The burst index is analyzed to judge the contingency of the alarm type of the invalid alarm packet in the system monitoring process, and if the difference of the alarm types corresponding to the invalid alarm packet is larger and the existence frequency is lower, the contingency of the alarm event corresponding to the invalid alarm packet can be deduced to be larger;
setting a burst index threshold Z 0 ，
When Z is p <Z 0 When the transmission signal is transmitted, the transmission signal display layer module is returned to monitor continuously;
when Z is p ≥Z 0 When in use, then locate Z p ≥Z 0 And the corresponding alarm unit sets and transmits signals to the characteristic analysis unit to analyze and output invalid target characteristics. When the analyzed event does not meet the condition of contingency, a signal can be transmitted to a feature analysis unit which singly performs feature analysis to output, so that whether the invalid target feature with regularity exists is further accurately judged.
The service storage layer module also comprises an alarm requirement updating unit;
extracting an invalid alarm packet to which the invalid target feature corresponds, and outputting the invalid alarm packet to be recorded in a first critical value of the display layer module, wherein the data critical value refers to the minimum value of recorded data in the invalid alarm packet;
extracting the minimum value of the corresponding record data of the alarm type package in the alarm unit set to which the invalid alarm package belongs as a second critical value;
if the first critical value is smaller than the second critical value, outputting an alarm requirement of the alarm unit set corresponding to the invalid target feature as the second critical value;
if the first critical value is larger than the second critical value, outputting an alarm requirement of the alarm unit set corresponding to the invalid target feature as the first critical value;
and if the first critical value is equal to the second critical value, comparing the invalid target characteristics in real time, and outputting the alarm requirement of the set of alarm units corresponding to the invalid target characteristics as the first critical value when the invalid target characteristics exist in real time, otherwise outputting the alarm requirement of the set of alarm units corresponding to the invalid target characteristics as the second critical value.
The method is characterized in that a new alarm requirement is output after invalid target characteristics are analyzed, when a first critical value is smaller than a second critical value, data corresponding to an event which does not actually need to be alarmed is included in alarm requirements initially set by a system, so that a corresponding interval of alarm data is reduced, and the alarm is more accurate.
The intelligent monitoring operation and maintenance management system also comprises a multi-source early warning analysis module;
the multisource early warning analysis module is used for carrying out association analysis on different alarm events recorded by the monitoring operation and maintenance management system and determining the association between the different alarm events;
the multi-source early warning analysis module performs association analysis and comprises extracting set target characteristics in different warning type packages, wherein the set target characteristics comprise invalid target characteristics and conventional target characteristics, and the conventional target characteristics are attribute characteristics corresponding to warning type packages except invalid warning packages in the warning unit set;
drawing a radar chart corresponding to the f-th alarm type package by using the set target characteristics in the alarm type package, and marking an image interval V of the radar chart corresponding to the f-th alarm type package f Image areas corresponding to d alarm type packagesV of the room f The radar chart is overlapped in pairs by the center of the radar chart, as shown in fig. 3, each fixed point of the polygon represents one data related to power distribution, the point where the vertexes converge is the center of the polygon, the shaded part represents an image interval formed by corresponding specific values of the data related to power distribution, and the overlapping areas C, C= { V of the image interval are compared 1 ∩V 2 ,V 1 ∩V 3 ,V 2 ∩V 3 ,......,V f-1 ∩V f F is less than or equal to d, d represents the number of types of alarm type packages;
and outputting two alarm type packages corresponding to the overlapping area threshold value which is larger than or equal to the overlapping area C as associated alarm packages with association.
The multi-source early warning analysis module comprises a real-time early warning analysis unit;
the real-time early warning analysis unit is used for monitoring the alarm type of the transmission signal extraction alarm event when the intelligent monitoring operation and maintenance management system records the alarm event in real time;
when the alarm type does not exist in the associated alarm package, continuing monitoring;
and when the alarm type exists in the associated alarm package, transmitting a real-time early warning signal of another alarm type package in the associated alarm package. The relevance between the analysis alarm type packages can make early warning pre-judgment for the real-time monitoring system, so that the analysis efficiency of the system is improved, the relevance analysis of the distribution monitoring data by the system is more convenient, and the safety, the wide range and the multisource of the overall monitoring are improved.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the above is only a preferred embodiment of the present application, and the present application is not limited thereto, but it is to be understood that the present application is described in detail with reference to the foregoing embodiments, and modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (4)
1. The intelligent monitoring operation and maintenance management system based on the Internet of things is characterized by comprising a display layer module, a service storage layer module, a transmission layer module and a perception layer module;
the display layer module is used for outputting data related to power distribution to a user based on a system front-end power distribution network framework;
the display layer module comprises an alarm event extraction unit and an alarm exception analysis unit;
the alarm event extraction unit is used for extracting alarm events recorded in the display layer module, wherein the alarm events comprise alarm types, alarm time and alarm information, and the alarm information refers to fault nodes corresponding to the alarm events;
the alarm event extracting unit transmits the extracted alarm event to the alarm abnormality analyzing unit;
the alarm anomaly analysis unit constructs an alarm type package for the alarm event by taking the alarm type as a root node, alarm time and alarm information as child nodes, wherein the alarm time and the alarm information are friend nodes;
the alarm anomaly analysis unit is used for carrying out set division by taking the same alarm type as a unit on the alarm type package, classifying the same alarm type package into the same unit set and outputting the same alarm type package into an alarm unit set; judging whether an invalid alarm packet exists in the alarm unit set, wherein the invalid alarm packet refers to a data packet recorded as a misjudgment alarm event after the alarm type packet in the alarm unit set is manually checked and verified;
when invalid alarm packets exist, the number of the invalid alarm packets is not unique and the invalid alarm packets belong to the same alarm unit set, and the alarm abnormality analysis unit outputs a first identification signal;
when invalid alarm packets exist, the number of the invalid alarm packets is not unique and the alarm packets belong to different alarm unit sets, and the alarm abnormality analysis unit outputs a second identification signal;
the service storage layer module is used for establishing a service storage layer based on an application server, a WEB server and a database server; the application server and the database server are connected and transmitted, the application server transmits signals to the WEB server, and the database server transmits signals to the WEB server;
the service storage layer module comprises a signal identification unit and a feature analysis unit;
the signal identification unit is used for identifying the identification signal output by the alarm abnormality analysis unit, and transmitting the identification signal to the feature analysis unit after successful identification;
the feature analysis unit is used for extracting data from the alarm unit set corresponding to the first identification signal, sequencing alarm type packages in the alarm unit set according to the sequence of alarm time, and calculating an average alarm time interval T, T= (1/n-1) sigma (T) i+1 -t i ) Wherein t is i Alarm time, t, representing the ith alarm event i+1 The alarm time of the (i+1) th alarm event is represented, and n represents the total number of alarm events existing in the alarm unit set; i is more than or equal to 1 and less than or equal to n-1;
marking the sequence positions of the invalid alarm packets, and extracting a feature set of the invalid alarm packets, wherein the feature set refers to image data acquired by the perception layer module and power distribution related data, and the power distribution related data comprises a switch state, a voltage current value, a temperature value and a transformer parameter value;
the feature analysis unit comprises a similarity analysis unit, a feature attribution value calculation unit, a comparison condition analysis unit and a target feature output unit;
the similarity analysis unit obtains the kth attribute characteristic U of the jth invalid alarm package jk And outputs the feature similarity S of the corresponding features between the invalid alarm packets Uk ，S Uk Representing the similarity of the kth attribute characteristics corresponding to any two invalid alarm packets;
calculating average similarity S containing all features between any two invalid alarm packets 0 Extracting m (m-1)/2 average similarity S formed by m invalid alarm packets 0 J is less than or equal to m; obtaining invalid warning packet logarithm Q meeting average similarity greater than or equal to average similarity threshold 1 Transmitting a signal to the characteristic attribution value calculating unit, using the formula:
R=Q 1 /[m*(m-1)/2]
calculating a characteristic attribution value R; setting a characteristic attribution value threshold R 0 And obtaining the average similarity E of other alarm type packages except invalid alarm packages in the alarm unit set 0 The average similarity refers to a similarity average value of corresponding attribute characteristics among alarm type packages;
the comparison condition analysis unit is set when R is more than or equal to R 0 ，
And S is 0 -E 0 Is greater than the first difference threshold value,
and when the event interval corresponding to any adjacent non-invalid alarm event of the alarm event corresponding to the invalid alarm packet is greater than or equal to the average alarm time interval T; the target feature output unit outputs an attribute feature with feature similarity greater than or equal to a similarity threshold value between the invalid alarm packets as an invalid target feature;
otherwise, the comparison condition analysis unit returns to the transmission signal display layer module to continue monitoring when judging that any unsatisfied condition exists;
the service storage layer module further comprises an event analysis unit;
the event analysis unit is used for starting the analysis unit when the signal identification unit identifies the second identification signal;
the event analysis unit extracts the occurrence frequency of the invalid alarm packet in the p-th alarm unit setX p1 And the occurrence frequency X of the alarm type packet of the invalid alarm packet is removed from the p-th alarm unit set by the invalid alarm packet p2 The method comprises the steps of carrying out a first treatment on the surface of the Using the formula:
Z p =a 1 *(X p1 /X p2 )+a 2 *(m p1 /m)
calculating burst index Z corresponding to invalid alarm packet in p-th alarm unit set p Wherein m is p1 Representing the corresponding number when the similarity is greater than or equal to a similarity threshold value after the similarity of the invalid alarm package of the p-th alarm unit set and any invalid alarm package is compared, and m represents the total number of the invalid alarm packages; a, a 1 、a 2 Representing a first reference coefficient and a second reference coefficient, 0<a 1 、a 2 <1，a 1 +a 1 =1；
Setting a burst index threshold Z 0 ，
When Z is p <Z 0 When the transmission signal is transmitted, the transmission signal display layer module is returned to monitor continuously;
when Z is p ≥Z 0 When in use, then locate Z p ≥Z 0 The corresponding alarm unit sets and transmits signals to the characteristic analysis unit to analyze and output invalid target characteristics;
the transmission layer module is used for connecting software and hardware of different networks based on the gateway;
the sensing layer module is used for sensing and reading data related to power distribution based on power distribution monitoring equipment; the power distribution monitoring equipment comprises an intelligent ammeter, a calculator, a wireless metering module, a camera, a transformer, microcomputer protection, an I/O module and a temperature and humidity sensor;
the perception layer module is connected with the transmission layer module, the transmission layer module is connected with the service storage layer module, the service storage layer module is connected with the display layer module, and when the display architecture in the display layer module is not unique, the service storage layer module can be respectively connected with different display architectures.
2. The intelligent monitoring operation and maintenance management system based on the internet of things according to claim 1, wherein: the service storage layer module further comprises an alarm requirement updating unit;
extracting an invalid alarm packet to which the invalid target feature corresponds, and outputting an invalid alarm packet to be recorded in a first critical value of the presentation layer module, wherein the data critical value refers to the minimum value of recorded data in the invalid alarm packet;
extracting the minimum value of the corresponding record data of the alarm type package in the alarm unit set to which the invalid alarm package belongs as a second critical value;
if the first critical value is smaller than the second critical value, outputting an alarm requirement of the alarm unit set corresponding to the invalid target feature as the second critical value;
if the first critical value is larger than the second critical value, outputting an alarm requirement of the alarm unit set corresponding to the invalid target feature as the first critical value;
and if the first critical value is equal to the second critical value, comparing the invalid target characteristics in real time, and outputting the alarm requirement of the set of alarm units corresponding to the invalid target characteristics as the first critical value when the invalid target characteristics exist in real time, otherwise outputting the alarm requirement of the set of alarm units corresponding to the invalid target characteristics as the second critical value.
3. The intelligent monitoring operation and maintenance management system based on the internet of things according to claim 2, wherein: the intelligent monitoring operation and maintenance management system also comprises a multi-source early warning analysis module;
the multi-source early warning analysis module is used for carrying out association analysis on different alarm events recorded by the monitoring operation and maintenance management system and determining the association between the different alarm events;
the multi-source early warning analysis module performs association analysis and comprises extracting set target characteristics in different warning type packages, wherein the set target characteristics comprise invalid target characteristics and conventional target characteristics, and the conventional target characteristics are attribute characteristics corresponding to warning type packages except the invalid warning packages in the warning unit set;
drawing the f-th alarm by the set target characteristics in the alarm type packageThe radar map corresponding to the type package marks the image interval V of the radar map corresponding to the f-th alarm type package f Image interval V corresponding to d alarm type packages f Overlapping every two by the center of the radar chart, and comparing the overlapping area C, C= { V of the image interval 1 ∩V 2 ,V 1 ∩V 3 ,V 2 ∩V 3 ,......,V f-1 ∩V f F is less than or equal to d, d represents the number of types of alarm type packages;
and outputting two alarm type packages corresponding to the overlapping area threshold value which is larger than or equal to the overlapping area C as associated alarm packages with association.
4. The intelligent monitoring operation and maintenance management system based on the internet of things according to claim 3, wherein: the multi-source early warning analysis module comprises a real-time early warning analysis unit;
the real-time early warning analysis unit is used for monitoring the alarm type of the alarm event extracted by the transmission signal when the intelligent monitoring operation and maintenance management system records the alarm event in real time;
when the alarm type does not exist in the associated alarm package, continuing monitoring;
and when the alarm type exists in the associated alarm package, transmitting a real-time early warning signal of another alarm type package in the associated alarm package.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310249294.0A CN116054416B (en) | 2023-03-15 | 2023-03-15 | Intelligent monitoring operation and maintenance management system based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310249294.0A CN116054416B (en) | 2023-03-15 | 2023-03-15 | Intelligent monitoring operation and maintenance management system based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116054416A CN116054416A (en) | 2023-05-02 |
| CN116054416B true CN116054416B (en) | 2023-09-22 |
Family
ID=86118461
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310249294.0A Active CN116054416B (en) | 2023-03-15 | 2023-03-15 | Intelligent monitoring operation and maintenance management system based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116054416B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094563B (en) * | 2023-10-16 | 2024-02-06 | 南京六季光电技术研究院有限公司 | Intelligent liquid waste leakage monitoring system and method based on big data |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015043441A1 (en) * | 2013-09-24 | 2015-04-02 | 许继集团有限公司 | Smart alarm inference method based on multi-scenario analysis |
| WO2016029570A1 (en) * | 2014-08-28 | 2016-03-03 | 北京科东电力控制系统有限责任公司 | Intelligent alert analysis method for power grid scheduling |
| CN106375339A (en) * | 2016-10-08 | 2017-02-01 | 电子科技大学 | Attack mode detection method based on event slide window |
| CN108847968A (en) * | 2018-06-04 | 2018-11-20 | 国网浙江省电力有限公司 | Monitoring accident, anomalous event identification and multidimensional analysis method |
| CN109450098A (en) * | 2018-12-14 | 2019-03-08 | 朱明增 | Power regulation integral system warning information optimization method |
| CN109871305A (en) * | 2019-01-18 | 2019-06-11 | 深圳壹账通智能科技有限公司 | Processing method, device, computer equipment and the storage medium of warning information |
| CN110688892A (en) * | 2019-08-20 | 2020-01-14 | 武汉烽火众智数字技术有限责任公司 | Portrait identification alarm method and system based on data fusion technology |
| CN111506478A (en) * | 2020-04-17 | 2020-08-07 | 上海浩方信息技术有限公司 | Method for realizing alarm management control based on artificial intelligence |
| CN111898647A (en) * | 2020-07-07 | 2020-11-06 | 贵州电网有限责任公司 | Clustering analysis-based low-voltage distribution equipment false alarm identification method |
| WO2021082697A1 (en) * | 2019-11-01 | 2021-05-06 | 平安科技（深圳）有限公司 | Batch alarm event-based positioning method and apparatus, electronic device, and medium |
| WO2021114977A1 (en) * | 2019-12-12 | 2021-06-17 | 深圳前海微众银行股份有限公司 | Method and device for positioning fundamental cause of abnormal event |
| WO2021223665A1 (en) * | 2020-05-08 | 2021-11-11 | 华为技术有限公司 | Method and device for reducing invalid warnings |
| CN114357762A (en) * | 2021-12-31 | 2022-04-15 | 郑州力通水务有限公司 | Wisdom power equipment high in clouds control automatic system |
| CN114721912A (en) * | 2021-01-04 | 2022-07-08 | 腾讯科技（深圳）有限公司 | Data analysis method, device, equipment and medium |
| CN114866396A (en) * | 2022-07-07 | 2022-08-05 | 浩鲸云计算科技股份有限公司 | Method for realizing network fault location under inaccurate resources based on text similarity |
| CN115001753A (en) * | 2022-05-11 | 2022-09-02 | 绿盟科技集团股份有限公司 | Method and device for analyzing associated alarm, electronic equipment and storage medium |
| WO2022193617A1 (en) * | 2021-03-16 | 2022-09-22 | 通号通信信息集团有限公司 | Fault location method, fault location system, and video management system |
-
2023
- 2023-03-15 CN CN202310249294.0A patent/CN116054416B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015043441A1 (en) * | 2013-09-24 | 2015-04-02 | 许继集团有限公司 | Smart alarm inference method based on multi-scenario analysis |
| WO2016029570A1 (en) * | 2014-08-28 | 2016-03-03 | 北京科东电力控制系统有限责任公司 | Intelligent alert analysis method for power grid scheduling |
| CN106375339A (en) * | 2016-10-08 | 2017-02-01 | 电子科技大学 | Attack mode detection method based on event slide window |
| CN108847968A (en) * | 2018-06-04 | 2018-11-20 | 国网浙江省电力有限公司 | Monitoring accident, anomalous event identification and multidimensional analysis method |
| CN109450098A (en) * | 2018-12-14 | 2019-03-08 | 朱明增 | Power regulation integral system warning information optimization method |
| CN109871305A (en) * | 2019-01-18 | 2019-06-11 | 深圳壹账通智能科技有限公司 | Processing method, device, computer equipment and the storage medium of warning information |
| CN110688892A (en) * | 2019-08-20 | 2020-01-14 | 武汉烽火众智数字技术有限责任公司 | Portrait identification alarm method and system based on data fusion technology |
| WO2021082697A1 (en) * | 2019-11-01 | 2021-05-06 | 平安科技（深圳）有限公司 | Batch alarm event-based positioning method and apparatus, electronic device, and medium |
| WO2021114977A1 (en) * | 2019-12-12 | 2021-06-17 | 深圳前海微众银行股份有限公司 | Method and device for positioning fundamental cause of abnormal event |
| CN111506478A (en) * | 2020-04-17 | 2020-08-07 | 上海浩方信息技术有限公司 | Method for realizing alarm management control based on artificial intelligence |
| WO2021223665A1 (en) * | 2020-05-08 | 2021-11-11 | 华为技术有限公司 | Method and device for reducing invalid warnings |
| CN111898647A (en) * | 2020-07-07 | 2020-11-06 | 贵州电网有限责任公司 | Clustering analysis-based low-voltage distribution equipment false alarm identification method |
| CN114721912A (en) * | 2021-01-04 | 2022-07-08 | 腾讯科技（深圳）有限公司 | Data analysis method, device, equipment and medium |
| WO2022193617A1 (en) * | 2021-03-16 | 2022-09-22 | 通号通信信息集团有限公司 | Fault location method, fault location system, and video management system |
| CN114357762A (en) * | 2021-12-31 | 2022-04-15 | 郑州力通水务有限公司 | Wisdom power equipment high in clouds control automatic system |
| CN115001753A (en) * | 2022-05-11 | 2022-09-02 | 绿盟科技集团股份有限公司 | Method and device for analyzing associated alarm, electronic equipment and storage medium |
| CN114866396A (en) * | 2022-07-07 | 2022-08-05 | 浩鲸云计算科技股份有限公司 | Method for realizing network fault location under inaccurate resources based on text similarity |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116054416A (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220137612A1 (en) | Transformer fault diagnosis and positioning system based on digital twin | |
| CN103001328B (en) | Fault diagnosis and assessment method of intelligent substation | |
| CN107146018A (en) | Data Management Analysis method and system based on electric network state monitoring system | |
| CN112910089A (en) | Transformer substation secondary equipment fault logic visualization method and system | |
| CN112817280A (en) | Implementation method for intelligent monitoring alarm system of thermal power plant | |
| CN107492952A (en) | A kind of regulation and control center alarm signal analysis method and the intelligent warning system based on it | |
| CN116054416B (en) | Intelligent monitoring operation and maintenance management system based on Internet of things | |
| CN114021971A (en) | Comprehensive evaluation system, method and storage medium for expressway operation and maintenance management | |
| CN109491339B (en) | Big data-based substation equipment running state early warning system | |
| CN113053063A (en) | Mobile terminal-based disaster online disposal flow implementation method | |
| CN106646110A (en) | Low-voltage distribution network fault positioning system based on GIS and Petri technologies | |
| CN112134871A (en) | Abnormal flow detection device and method for energy internet information support network | |
| CN111476979A (en) | Intelligent security and stability maintenance method and system based on multi-model analysis | |
| CN115811138A (en) | Distribution automation main website equipment anomaly monitoring system | |
| CN110930644A (en) | Cable production safety early warning system | |
| CN112326583A (en) | Intelligent toxic gas detection system and method based on Internet of things | |
| CN116317171B (en) | Electric quantity and non-electric quantity internet of things monitoring device | |
| CN108808850A (en) | Intelligent substation based on IEC61850 alerts intelligent analysis method | |
| CN115664006B (en) | Intelligent management and control integrated platform for incremental power distribution network | |
| CN111667391A (en) | Environment-friendly big data monitoring system | |
| CN116185757A (en) | Intelligent monitoring system for energy consumption of machine room | |
| CN115658772A (en) | Unmanned aerial vehicle photovoltaic inspection data asset management method and system | |
| CN114646735A (en) | Carbon dioxide concentration monitoring system in air | |
| CN104301330B (en) | The Honey net detection method measured with member's cohesion is monitored based on abnormal behaviour | |
| CN114167837A (en) | Intelligent fault diagnosis method and system for railway signal 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |