CN113556369A - Power grid equipment management and control method and system based on power internet of things - Google Patents
Power grid equipment management and control method and system based on power internet of things Download PDFInfo
- Publication number
- CN113556369A CN113556369A CN202010332863.4A CN202010332863A CN113556369A CN 113556369 A CN113556369 A CN 113556369A CN 202010332863 A CN202010332863 A CN 202010332863A CN 113556369 A CN113556369 A CN 113556369A
- Authority
- CN
- China
- Prior art keywords
- data
- power grid
- fault diagnosis
- grid equipment
- condition
- 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
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000003745 diagnosis Methods 0.000 claims abstract description 94
- 238000004891 communication Methods 0.000 claims abstract description 37
- 230000008447 perception Effects 0.000 claims abstract description 16
- 230000006870 function Effects 0.000 claims abstract description 15
- 238000007781 pre-processing Methods 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims abstract description 5
- 230000008569 process Effects 0.000 claims abstract description 4
- 238000007726 management method Methods 0.000 claims description 39
- 230000005540 biological transmission Effects 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 19
- 238000005065 mining Methods 0.000 claims description 17
- 230000006855 networking Effects 0.000 claims description 8
- 239000002131 composite material Substances 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 7
- 230000003287 optical effect Effects 0.000 claims description 7
- 238000011160 research Methods 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 5
- 238000013499 data model Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 206010063385 Intellectualisation Diseases 0.000 abstract description 2
- 238000012800 visualization Methods 0.000 abstract description 2
- 238000011161 development Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000004128 high performance liquid chromatography Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/03—Cooperating elements; Interaction or communication between different cooperating elements or between cooperating elements and receivers
- G01S19/10—Cooperating elements; Interaction or communication between different cooperating elements or between cooperating elements and receivers providing dedicated supplementary positioning signals
- G01S19/12—Cooperating elements; Interaction or communication between different cooperating elements or between cooperating elements and receivers providing dedicated supplementary positioning signals wherein the cooperating elements are telecommunication base stations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Abstract
The invention discloses a power grid equipment management and control method and system based on an electric power internet of things. The method comprises the steps that a sensing layer collects data in real time and carries out preprocessing, the probability of equipment failure is judged, and a feature library for failure diagnosis is formed; the network layer transmits the data of the power grid equipment of the sensing layer and the preprocessed data, and accurately positions the power grid equipment; the platform layer carries out comprehensive analysis and judgment on the data transmitted by the network layer, and carries out fault diagnosis; and the application layer provides the fault information and the positioning of the equipment for the electric power overhaul department. The management and control system comprises a sensing unit, a network unit, a platform unit and an application unit. The invention fully utilizes the function of realizing multi-parameter integrated acquisition and preprocessing of a perception link by a perception layer, shares data and communication equipment of a network layer, and efficiently processes data of a platform layer to realize visualization, intellectualization and real-time performance on power grid equipment. Fault information and accurate positioning of the application layer.
Description
Technical Field
The invention belongs to the technical field of monitoring of the safety state of power grid equipment and risk assessment, and particularly relates to a power grid equipment management and control method and a management and control system based on the power internet of things.
Background
With the rapid development of social economy and the progress of science and technology, the scale of a power grid becomes larger and larger, the requirement of the whole society on the power supply reliability is higher and higher, and therefore the safety maintenance and risk assessment of power grid equipment become more and more important. The quantity of the relevant information of the states of various power grid equipment with different functions and the basic data are large, the information is different, the functions of the relevant information and the basic data are scattered, the service systems are mutually independent, the data formats of different systems are inconsistent, the data are difficult to share and compatible, the data and the information of different systems are even contradictory, the accuracy and the consistency of the data are difficult to ensure, the multi-dimensional deep analysis and the mining of various information and data are not facilitated, and the quick sharing of the information is not facilitated.
The internet of things refers to interaction between different people and different objects and information network links between different objects. The electric power internet of things is an intelligent service system which fully applies modern information technologies such as mobile interconnection, artificial intelligence and the like and advanced communication technologies around each link of an electric power system, realizes the mutual object interconnection and man-machine interaction of each link of the electric power system, and has the characteristics of comprehensive state perception, efficient information processing and convenient and flexible application. The service collaboration and data communication are basically realized, unified internet of things management is preliminarily realized, and all levels of intelligent energy comprehensive service platforms have basic functions and support the development of power grid services and emerging services.
At present, with the rapid development of the scale of a power grid, the requirement of the whole society on the reliability of power supply is higher and higher, and power grid equipment with good state and stable operation is the basis of the power internet of things. Therefore, a safe, intelligent and stably-operating power grid equipment management and control method based on the power internet of things is urgently needed at present.
Disclosure of Invention
The purpose of the invention is as follows:
the invention aims to provide a power grid equipment management and control method and a management and control system based on the power internet of things; the perception layer relies on the intelligent perception terminal to carry out unified access and unified management on different types of data of different power grid equipment, and the network layer carries out comprehensive, quick, accurate transmission to perception layer mass data, carries out accurate positioning to power grid equipment, and the platform layer carries out high-efficient processing to information, calls, accurately judges the running state of power grid equipment, detects in real time. The application layer supports the business application requirements of each unit and each department.
The technical scheme is as follows:
a power grid equipment management and control method based on the power Internet of things comprises the following steps:
step 1, a perception layer collects historical/quasi-real-time and power grid space data of power grid equipment in real time; preprocessing the data, judging the probability of equipment failure, and forming a feature library for failure diagnosis based on the data;
step 2, the network layer transmits mass data and preprocessing data of the power grid equipment of the sensing layer, and accurately positions the power grid equipment;
step 3, the platform layer carries out comprehensive analysis and judgment on data transmitted by the network layer, extracts equipment characteristic values from a fault diagnosis characteristic library, carries out discretization processing, generates a strong association rule between the broken line fault diagnosis condition characteristics and result characteristics, and carries out fault diagnosis;
and 4, the application layer provides the fault information and accurate positioning of the equipment for the electric power overhaul department.
Further, the data acquisition and processing by the sensing layer specifically includes: the intelligent management terminal collects historical/quasi-real-time data of the power grid equipment, preprocesses the data and judges the probability of equipment failure based on weather conditions; and establishing a uniform power grid equipment accident probability model and forming a fault diagnosis feature library.
Further, the power grid equipment accident probability model specifically includes: lambda [ alpha ]a、λb、λcAre respectively in the normal stateThe annual failure rate of equipment elements in weather, severe weather and extreme weather is calculated according to the following formula:
λa＝λavg(1-Fn)/pa (1)
λb＝λavg(1-Fm)/pb (2)
λc＝λavg(1-Fm)/pc (3)
in the formula: lambda [ alpha ]avgIs the average annual failure rate of the component, p, based on historical data statisticsa、pb、pcRespectively based on the steady-state probabilities of normal weather, severe weather and extreme weather occurring in historical statistical data; fnIs the proportion of the failure occurring in bad weather and extreme conditions; fmProportion of extreme weather in bad weather conditions;
when the element under consideration is operating in only the "normal" or "shut down" 2 operating conditions, the number of times the element is exposed to weather during the predicted time period Δ t under consideration is approximately subject to a poisson distribution, so that t0The element in normal operation at the moment, at t0The probability of a outage occurring at time + Δ t may be expressed approximately as:
in the formula: lambda [ alpha ]1Is the element annual failure rate obtained by short-term weather forecast and equations (1), (2) and (3); the delta t can be selected according to the updating time interval or the actual requirement of the actual data on site;
at t0The probability of an expected accident occurring at time + Δ t is calculated by:
in the formula: a is the system state under the expected accident; D. and U is a failure element set and a normal element set in the system state respectively.
Further, the accurate positioning of the power grid equipment in the step 2 is performed through a network layer communication transmission network; the communication transmission network builds an integrated communication network by developing the research and application of mixed networking technologies such as a high-capacity backbone optical transmission network, a medium-low voltage high-speed power line carrier, a power wireless private network, a low-power wide area network, a photoelectric composite cable, a 5G network slice, a Beidou communication satellite and the like.
Further, the step 3 specifically includes: performing mRMR algorithm-based main feature selection on the basis of a fault diagnosis feature library established on the basis of the sensing layer, and further mining association rules between fault diagnosis main condition features and result features through an FP-Growth algorithm, so as to establish a fault diagnosis rule library and perform fault diagnosis;
(1) the mRMR algorithm;
the mRMR algorithm measures the correlation between features using mutual information; if two features X and Y, p (X), p (Y) and p (Y) are probability density functions of the feature X and the feature Y, respectively, and p (X, Y) is a joint probability of the two features, a mutual information definition I (X, Y) between the two features is:
the objective of the mrMR algorithm is to find a vector containing m { x }iA feature subset S of the features such that the correlation between the fault diagnosis condition features and the result features is maximized and the redundancy between the condition features is minimized, i.e.
In the formula: x is the number ofiIs the ith conditional feature, xjIs the jth condition characteristic; c is a result characteristic; s is a feature subset; | S | is the feature subset dimension; d (S, c) is the correlation between S and c; r (S) is the redundancy among the conditional features;
taking the maximum correlation and the minimum redundancy as the standard of feature selection in a comprehensive mode;
maxφ(D，R)，φ＝D-R (9)
on the basis of the feature selection standard, searching for approximate optimal features in an incremental search mode; assume an existing feature set Sm-1From the remaining features X-Sm-1Finding out the mth characteristic, and meeting the following conditions to enable phi to be maximum;
(2) FP-Growth algorithm;
the algorithm organizes data by a frequent pattern tree and a compact structure, extracts frequent item sets from the data, and performs association rule mining on the data sets, and the basic steps are as follows:
1) constructing FP-Tree;
scanning a fault data set for the first time, wherein each transaction in the data set represents a power grid historical operation record, and the record consists of fault diagnosis main characteristics and corresponding result characteristics; counting the occurrence frequency of all single elements, and removing the elements with the occurrence frequency less than the set minimum support degree to form a 1-frequent item set;
scanning the data set for the second time, arranging the elements of each transaction in the data set according to the descending order of the support degree, and starting to construct an FP-Tree; the FP-Tree root node is empty; each transaction, all elements of which form a path from the root node to a leaf node; the first n nodes are shared by a plurality of transactions with the same first n elements after the transactions are arranged according to the descending order of the support degree; counting the number of each node in the FP-Tree as the number of transactions passing through the node;
2) excavating FP-Growth;
excavating the FP-Tree in a bottom-up iteration mode; for each frequent item, taking the condition mode base of the frequent item as a new data set, removing the item which does not meet the minimum support degree, and forming a new condition FP-Tree by the rest items; continuously circulating and mining a frequent mode to obtain all K-frequent item sets;
the fault diagnosis only needs to obtain the association rules between the condition characteristics and the result characteristics, the association rules between the condition characteristics are useless information for fault diagnosis, according to the condition, after each condition mode base is obtained, judgment is firstly carried out, if the condition mode base contains the result characteristics, the condition FP-Tree is continuously generated, if the condition mode base only contains the condition characteristics, the condition FP-Tree is not generated, and the next frequent mode base is excavated;
3) diagnosing faults;
on the basis of obtaining a frequent item set by the FP-Growth algorithm mining, a strong association rule between the fault diagnosis condition characteristic and the result characteristic is obtained; in the building and mining processes of the FP-Tree, the minimum support degree is considered, and the strong association rule is considered when the minimum confidence degree requirement is met; further screening the excavated strong association rules, only keeping the strong association rules taking the fault type as a back item, and removing redundant rules to obtain a fault diagnosis rule base;
when fault diagnosis is carried out, matching the condition characteristics to be diagnosed with the condition characteristics of each rule in the rule base, if no matched rule exists, judging that no fault occurs, if a certain rule in the rule base is matched, finding out the result characteristics corresponding to the certain rule to obtain a fault diagnosis result, wherein the confidence coefficient of the rule is the confidence coefficient of the diagnosis result;
4) fault location;
the excavated strong association rule can be further used for fault positioning besides fault diagnosis, and the fault position is deduced according to the rule content; if the fault is diagnosed, the fault occurrence place is deduced according to the condition characteristics in the matched association rule, and the fault area is intelligently determined.
The power grid equipment management and control system based on the power Internet of things comprises a sensing unit, a network unit, a platform unit and an application unit;
the sensing unit is used for acquiring historical/quasi-real-time and power grid space data of the power grid equipment in real time; preprocessing the data, judging the probability of equipment failure, and forming a failure diagnosis feature library based on the data;
the network unit is used for transmitting the mass data and the preprocessing data of the power grid equipment of the sensing unit and accurately positioning the power grid equipment;
the platform unit is used for comprehensively analyzing and judging the data transmitted by the network unit, extracting a device characteristic value from a fault diagnosis characteristic library, carrying out discretization processing, generating a strong association rule between the broken line fault diagnosis condition characteristic and the result characteristic, and carrying out fault diagnosis;
and the application unit is used for providing fault information and accurate positioning of equipment for the electric power overhaul department.
Further, the data acquisition and processing of the sensing unit specifically includes: the intelligent management terminal collects historical/quasi-real-time data of the power grid equipment, preprocesses the data and judges the probability of equipment failure based on weather conditions; and establishing a uniform power grid equipment accident probability data model and forming a fault diagnosis feature library.
Furthermore, the accurate positioning of the power grid equipment is realized through a communication transmission network of the network unit; the communication transmission network builds an integrated communication network by developing the technical research and application of a high-capacity backbone optical transmission network, a medium-low voltage high-speed power line carrier, a power wireless private network, a low-power wide area network, a photoelectric composite cable, a 5G network slice and a Beidou communication satellite hybrid networking.
Further, the platform unit is based on a fault diagnosis feature library established by the sensing unit, performs main feature selection based on an mRMR algorithm, and further excavates association rules between fault diagnosis main condition features and result features through an FP-Growth algorithm, so as to establish a rule library for fault diagnosis and perform fault diagnosis.
The advantages and effects are as follows:
the invention has the following advantages and beneficial effects:
based on under the condition of the electric power internet of things, the sensing layer carries out comprehensive real-time sensing, data information efficient processing and storage on the condition of the power grid equipment, and the communication network through the network layer 5G and the Beidou communication satellite is quick and accurate to be transmitted to the platform layer. The platform layer checks two-dimensional/three-dimensional images of the power grid equipment in the jurisdiction range in real time, browses the running condition of the equipment, comprehensively knows the relevant information and the environmental condition of the power grid equipment, evaluates and accurately predicts the real-time state of the power grid equipment, and realizes visual, intelligent and real-time management and control. The application layer provides value-added services for power consumers, power industries and governments. The purpose of the application layer is to establish an intelligent comprehensive energy internet on the basis of ensuring the safe and stable operation of a power grid.
The invention fully utilizes the functions of multi-parameter integrated acquisition and preprocessing of a perception link of the intelligent terminal of the perception layer, the functions of quick transmission and accurate positioning of the network layer 5G and the Beidou communication satellite, and the high-efficiency processing of platform layer data to realize visualization, intellectualization and real-time performance on the power grid equipment.
Drawings
FIG. 1 is a power Internet of things framework diagram;
FIG. 2 is a diagram of a smart sensor terminal design;
fig. 3 is a flow chart of a fault diagnosis algorithm.
Detailed Description
The invention is further described below with reference to the drawings and specific preferred embodiments of the description, without thereby limiting the scope of protection of the invention.
The perception layer relies on the intelligent perception terminal to carry out unified access and unified management on different types of data of different power grid equipment, and the network layer carries out comprehensive, quick, accurate transmission to perception layer mass data, carries out accurate positioning to power grid equipment, and the platform layer carries out high-efficient processing to information, calls, accurately judges the running state of power grid equipment, detects in real time. The application layer supports the business application requirements of each unit and each department. The power internet of things framework diagram is shown in fig. 1.
As shown in fig. 1, the sensing layer collects historical/quasi-real-time and power grid spatial data such as monitoring state, production management, operation scheduling, environmental weather, early warning information, geographic information and the like of the power grid equipment in real time, and preprocesses and stores the data. The network layer meets the access requirements of traditional electric services and emerging services by developing the research and application of mixed networking technologies such as a high-capacity backbone optical transmission network, a medium-low voltage high-speed power line carrier, an electric wireless private network, a low-power wide area network, an optical-electric composite cable, a 5G network slice, a Beidou communication satellite and the like, builds an integrated communication network with high bandwidth, low time delay, wide coverage and large connection, comprehensively, quickly and accurately transmits the mass data of the power grid equipment, accurately positions the power grid equipment and realizes the sharing function of the data and the communication equipment. The platform layer carries out high-efficiency processing on the preprocessing data of the power grid equipment, carries out comprehensive analysis and judgment and realizes unique source end and global sharing of the equipment data.
A power grid equipment management and control method based on the power Internet of things comprises the following steps:
step 1, a perception layer collects historical/quasi-real-time and power grid space data of power grid equipment in real time; preprocessing the data, judging the probability of equipment failure, and forming a feature library for failure diagnosis based on the data.
The historical/quasi-real-time data of the power grid equipment comprises historical/quasi-real-time data of monitoring states, production management, operation scheduling, environmental weather, early warning information, geographic information and the like of the power grid equipment.
Step 2, the network layer comprehensively, quickly and accurately transmits mass data and preprocessed data of the power grid equipment of the sensing layer, and accurately positions the power grid equipment; and data and communication equipment sharing functions are realized.
And 3, comprehensively analyzing and judging the data transmitted by the network layer by the platform layer, extracting the equipment characteristic value from the fault diagnosis characteristic library, carrying out discretization processing, generating a strong association rule between the broken line fault diagnosis condition characteristic and the result characteristic, and carrying out fault diagnosis.
Step 4, the application layer provides fault information and accurate positioning of equipment for the electric power overhaul department, so that rapid fault processing is facilitated; and supporting the business application requirements of each unit and each department.
The acquisition and processing data of the perception layer specifically comprises the following steps:
the intelligent management terminal collects historical/quasi-real-time data of the power grid equipment, preprocesses the data and judges the probability of equipment failure based on weather conditions; and establishing a uniform power grid equipment accident probability model and forming a fault diagnosis feature library.
The power grid equipment accident probability model specifically comprises the following steps:
λa、λb、λcthe annual failure rate of the equipment element in normal weather, severe weather and extreme weather is calculated according to the following formula:
λa＝λavg(1-Fn)/pa (1)
λb＝λavg(1-Fm)/pb (2)
λc＝λavg(1-Fm)/pc (3)
in the formula: lambda [ alpha ]avgIs the average annual failure rate of the component, p, based on historical data statisticsa、pb、pcRespectively based on the steady-state probabilities of normal weather, severe weather and extreme weather occurring in historical statistical data; fnIs the proportion of the failure occurring in bad weather and extreme conditions; fmProportion of extreme weather in bad weather conditions;
when the element under consideration is operating in only the "normal" or "shut down" 2 operating conditions, the number of times the element is exposed to weather during the predicted time period Δ t under consideration is approximately subject to a poisson distribution, so that t0The element in normal operation at the moment, at t0The probability of a outage occurring at time + Δ t may be approximated by table as:
in the formula: lambda [ alpha ]1Is the element annual failure rate obtained by short-term weather forecast and equations (1), (2) and (3); the delta t can be selected according to the updating time interval of the actual data on site or actual needs,such as 10min, 15min or 1 h.
Thus, at t0The probability of an expected accident occurring at time + Δ t is calculated by:
in the formula: a is the system state under the expected accident; D. and U is a failure element set and a normal element set in the system state respectively.
The intelligent sensing terminal design is shown in fig. 2. The intelligent management terminal follows the design concept of the SG-CIM4.0 model, establishes a unified data model, realizes the standardization of the access data of the sensing layer, realizes the multi-mode network access, and realizes the unified access of the sensing object and the unified management of the data. The intelligent management terminal is composed of a plurality of modules and units, and data are transmitted among the modules and the units through a high-speed bus, so that the effectiveness of data transmission is guaranteed. The metering core module undertakes metering related work, realizes data acquisition and processing and can store a large amount of data; the management core module is responsible for various management functions, including display, Bluetooth interaction, control and other functions, and uploads data; the uplink communication module is responsible for interacting with the multifunctional sensing terminal and can support HPLC or dual-mode (HPLC + micropower wireless) communication. The intelligent management terminal has a liquid crystal display, realizes a display function, and can facilitate operation and maintenance personnel to inquire equipment data and real-time images. The development requirement of human-computer interaction in the power Internet of things is met.
In the step 2, the accurate positioning of the power grid equipment is carried out through a network layer communication transmission network;
the communication transmission network meets the access requirements of the traditional electric service and the emerging service by developing the research and application of the mixed networking technologies of a high-capacity backbone optical transmission network, a medium-low voltage high-speed power line carrier, an electric wireless private network, a low-power wide area network, an optical-electric composite cable, a 5G network slice, a Beidou communication satellite and the like, builds an integrated communication network with high bandwidth, low time delay, wide coverage and large connection, transmits mass data of power grid equipment comprehensively, quickly and accurately, positions the power grid equipment accurately, and realizes the sharing function of the data and the communication equipment.
The platform layer in the step 3 specifically comprises the following steps:
performing mRMR algorithm-based main feature selection on the basis of a fault diagnosis feature library established on the basis of the sensing layer, and further mining association rules between fault diagnosis main condition features and result features through an FP-Growth algorithm, so as to establish a fault diagnosis rule library and perform fault diagnosis;
(1) the mRMR algorithm;
the core idea of the mRMR algorithm is to maximize the correlation between the condition features and the result features while minimizing the correlation between the condition features. The method has higher operation speed and meets the requirement of fault diagnosis on diagnosis speed.
The mRMR algorithm measures the correlation between features using mutual information; if two features X and Y, p (X), p (Y) and p (Y) are probability density functions of the feature X and the feature Y, respectively, and p (X, Y) is a joint probability of the two features, a mutual information definition I (X, Y) between the two features is:
the objective of the mrMR algorithm is to find a vector containing m { x }iA feature subset S of the features such that the correlation between the fault diagnosis condition features and the result features is maximized and the redundancy between the condition features is minimized, i.e.
In the formula: x is the number ofiIs the ith condition characteristic; x is the number ofjIs the jth condition characteristic; c is a result characteristic; s is a feature subset; | S | is the feature subset dimension; d (S, c) is the correlation between S and c; r (S) is the redundancy between conditional features.
And taking the maximum correlation and the minimum redundancy as the standard of feature selection in a comprehensive mode.
maxφ(D，R)，φ＝D-R (9)
On the basis of the feature selection standard, searching for approximate optimal features in an incremental search mode; assume an existing feature set Sm-1From the remaining features X-Sm-1Finding out the mth characteristic, and meeting the following conditions to enable phi to be maximum;
(2) FP-Growth algorithm;
the algorithm organizes data by a frequent pattern tree and a compact structure, extracts frequent item sets from the data, and performs association rule mining on the data sets, and the basic steps are as follows:
1) constructing FP-Tree;
scanning a fault data set for the first time, wherein each transaction in the data set represents a power grid historical operation record, and the record consists of fault diagnosis main characteristics and corresponding result characteristics; and counting the occurrence frequency of all single elements, and removing the elements with the occurrence frequency less than the set minimum support degree to form a 1-frequent item set.
Scanning the data set for the second time, arranging the elements of each transaction in the data set according to the descending order of the support degree, and starting to construct an FP-Tree; the FP-Tree root node is empty; each transaction, all elements of which form a path from the root node to a leaf node; the first n nodes are shared by a plurality of transactions with the same first n elements after the transactions are arranged according to the descending order of the support degree; the count of each node in the FP-Tree is the number of transactions passing through the node.
2) Excavating FP-Growth;
excavating the FP-Tree in a bottom-up iteration mode; for each frequent item, taking the condition mode base of the frequent item as a new data set, removing the item which does not meet the minimum support degree, and forming a new condition FP-Tree by the rest items; continuously circulating and mining a frequent mode to obtain all K-frequent item sets;
the fault diagnosis only needs to obtain the association rules between the condition characteristics and the result characteristics, the association rules between the condition characteristics are useless information for fault diagnosis, according to the condition, after each condition mode base is obtained, judgment is firstly carried out, if the condition mode base contains the result characteristics, the condition FP-Tree is continuously generated, if the condition mode base only contains the condition characteristics, the condition FP-Tree is not generated, and the next frequent mode base is excavated; therefore, useless rules can be filtered out in advance, unnecessary scanning times are reduced, and the algorithm efficiency is further improved.
3) Diagnosing faults;
on the basis of obtaining a frequent item set by the FP-Growth algorithm mining, a strong association rule between the fault diagnosis condition characteristic and the result characteristic is obtained; in the building and mining process of the FP-Tree, the minimum support degree is considered, and the strong association rule can be considered when the minimum confidence requirement is met. And further screening the excavated strong association rules, only keeping the strong association rules taking the fault type as a later item, and removing redundant rules to obtain a fault diagnosis rule base.
When fault diagnosis is carried out, the condition features to be diagnosed are matched with the condition features of each rule in the rule base, if no matched rule exists, no fault is judged to occur, if a certain rule in the rule base is matched, the result feature corresponding to the certain rule is found out to obtain a fault diagnosis result, and the confidence coefficient of the rule is the confidence coefficient of the diagnosis result.
4) Fault location;
the excavated strong association rule can be further used for fault positioning besides fault diagnosis, and the fault position is deduced according to the rule content; if the fault is diagnosed, deducing the fault occurrence place according to the condition characteristics in the matched association rule, and intelligently determining a fault area; the specific algorithm flow is shown in fig. 3.
As shown in fig. 3, firstly, an equipment fault diagnosis main feature library is established, association rules between fault diagnosis main condition features and result features are further mined, a fault diagnosis rule is established to improve the fault diagnosis speed, data are organized in a frequent pattern tree structure, a frequent item set is extracted through two times of data set scanning, and the association rule mining efficiency is improved. Besides being used for fault diagnosis, the mined strong association rule can also be further used for fault location, and the fault location is deduced according to the rule content. If the fault is diagnosed, the fault occurrence place is deduced according to the condition characteristics in the matched association rule, and the fault area is intelligently determined.
The power grid equipment management and control system based on the power Internet of things comprises a sensing unit, a network unit, a platform unit and an application unit;
the sensing unit is used for acquiring historical/quasi-real-time and power grid space data of the power grid equipment in real time; preprocessing the data, judging the probability of equipment failure, and forming a failure diagnosis feature library based on the data;
the network unit is used for transmitting the mass data and the preprocessing data of the power grid equipment of the sensing unit and accurately positioning the power grid equipment;
the platform unit is used for comprehensively analyzing and judging the data transmitted by the network unit, extracting a device characteristic value from a fault diagnosis characteristic library, carrying out discretization processing, generating a strong association rule between the broken line fault diagnosis condition characteristic and the result characteristic, and carrying out fault diagnosis;
and the application unit is used for providing fault information and accurate positioning of equipment for the electric power overhaul department.
The data acquisition and processing of the sensing unit specifically comprises:
the intelligent management terminal collects historical/quasi-real-time data of the power grid equipment, preprocesses the data and judges the probability of equipment failure based on weather conditions; and establishing a uniform power grid equipment accident probability data model and forming a fault diagnosis feature library.
The accurate positioning of the power grid equipment is carried out through a communication transmission network of the network unit;
the communication transmission network builds an integrated communication network by developing the technical research and application of a high-capacity backbone optical transmission network, a medium-low voltage high-speed power line carrier, a power wireless private network, a low-power wide area network, a photoelectric composite cable, a 5G network slice and a Beidou communication satellite hybrid networking.
The platform unit is based on the fault diagnosis feature library established by the sensing unit, carries out main feature selection based on an mRMR algorithm, and further excavates association rules between the fault diagnosis main condition features and result features through an FP-Growth algorithm, thereby establishing a rule library for fault diagnosis and carrying out fault diagnosis.
And the platform layer judges the failure probability of the equipment according to the detected ambient environment of the equipment and the working characteristics of the equipment, so that an equipment management department can manage the equipment. If the power grid equipment fails, the platform layer judges which area is possibly failed according to the specific failure, the equipment which is possibly failed is checked through the rapid propagation and the accurate positioning of the network layer, the location and the equipment where the failure occurs are finally checked, and the failure is quickly and accurately solved by a maintenance department conveniently.
The foregoing is considered as illustrative of the preferred embodiments of the invention and is not to be construed as limiting the invention in any way. Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical spirit of the present invention should fall within the protection scope of the technical scheme of the present invention, unless the technical spirit of the present invention departs from the content of the technical scheme of the present invention.
Claims (9)
1. A power grid equipment management and control method based on the Internet of things of electric power is characterized in that: the method comprises the following steps:
step 1, a perception layer collects historical/quasi-real-time and power grid space data of power grid equipment in real time; preprocessing the data, judging the probability of equipment failure, and forming a feature library for failure diagnosis based on the data;
step 2, the network layer transmits mass data and preprocessing data of the power grid equipment of the sensing layer, and accurately positions the power grid equipment;
step 3, the platform layer carries out comprehensive analysis and judgment on data transmitted by the network layer, extracts equipment characteristic values from a fault diagnosis characteristic library, carries out discretization processing, generates a strong association rule between the broken line fault diagnosis condition characteristics and result characteristics, and carries out fault diagnosis;
and 4, the application layer provides the fault information and accurate positioning of the equipment for the electric power overhaul department.
2. The power grid equipment management and control method based on the power internet of things according to claim 1, characterized in that: the acquisition and processing data of the perception layer specifically comprises the following steps:
the intelligent management terminal collects historical/quasi-real-time data of the power grid equipment, preprocesses the data and judges the probability of equipment failure based on weather conditions; and establishing a uniform power grid equipment accident probability model and forming a fault diagnosis feature library.
3. The power grid equipment management and control method based on the power internet of things as claimed in claim 2, wherein: the power grid equipment accident probability model specifically comprises the following steps:
λa、λb、λcthe annual failure rate of the equipment element in normal weather, severe weather and extreme weather is calculated according to the following formula:
λa＝λavg(1-Fn)/pa (1)
λb＝λavg(1-Fm)/pb (2)
λc＝λavg(1-Fm)/pc (3)
in the formula: lambda [ alpha ]avgIs based on historical numbersStatistical annual mean failure rate of components, pa、pb、pcRespectively based on the steady-state probabilities of normal weather, severe weather and extreme weather occurring in historical statistical data; fnIs the proportion of the failure occurring in bad weather and extreme conditions; fmProportion of extreme weather in bad weather conditions;
when the element under consideration is operating in only the "normal" or "shut down" 2 operating conditions, the number of times the element is exposed to weather during the predicted time period Δ t under consideration is approximately subject to a poisson distribution, so that an element that is operating normally at time t0, at t0The probability of a outage occurring at time + Δ t may be approximated by table as:
in the formula: lambda [ alpha ]iIs the element annual failure rate obtained by short-term weather forecast and equations (1), (2) and (3); the delta t can be selected according to the updating time interval or the actual requirement of the actual data on site;
at t0The probability of an expected accident occurring at time + Δ t is calculated by:
in the formula: a is the system state under the expected accident; D. and U is a failure element set and a normal element set in the system state respectively.
4. The power grid equipment management and control method based on the power internet of things according to claim 1, characterized in that: in the step 2, the accurate positioning of the power grid equipment is carried out through a network layer communication transmission network;
the communication transmission network builds an integrated communication network by developing the research and application of mixed networking technologies such as a high-capacity backbone optical transmission network, a medium-low voltage high-speed power line carrier, a power wireless private network, a low-power wide area network, a photoelectric composite cable, a 5G network slice, a Beidou communication satellite and the like.
5. The power grid equipment management and control method based on the power internet of things according to claim 1, characterized in that: the platform layer in the step 3 specifically comprises the following steps:
performing mRMR algorithm-based main feature selection on the basis of a fault diagnosis feature library established on the basis of the sensing layer, and further mining association rules between fault diagnosis main condition features and result features through an FP-Growth algorithm, so as to establish a fault diagnosis rule library and perform fault diagnosis;
(1) the mRMR algorithm;
the mRMR algorithm measures the correlation between features using mutual information; if two features X and Y, p (X), p (Y) and p (Y) are probability density functions of the feature X and the feature Y, respectively, and p (X, Y) is a joint probability of the two features, a mutual information definition I (X, Y) between the two features is:
the objective of the mrMR algorithm is to find a vector containing m { x }iA feature subset S of the features such that the correlation between the fault diagnosis condition features and the result features is maximized and the redundancy between the condition features is minimized, i.e.
In the formula: x is the number ofiIs the ith conditional feature, xjIs the jth condition characteristic; c is a result characteristic; s is a feature subset; | S | is the feature subset dimension; d (S, c) is the correlation between S and c; r (S) is the redundancy among the conditional features;
taking the maximum correlation and the minimum redundancy as the standard of feature selection in a comprehensive mode;
maxφ(D,R),φ＝D-R (9)
on the basis of the feature selection standard, searching for approximate optimal features in an incremental search mode; assume an existing feature set Sm-1From the remaining features X-Sm-1Finding out the mth characteristic, and meeting the following conditions to enable phi to be maximum;
(2) FP-Growth algorithm;
the algorithm organizes data by a frequent pattern tree and a compact structure, extracts frequent item sets from the data, and performs association rule mining on the data sets, and the basic steps are as follows:
1) constructing FP-Tree;
scanning a fault data set for the first time, wherein each transaction in the data set represents a power grid historical operation record, and the record consists of fault diagnosis main characteristics and corresponding result characteristics; counting the occurrence frequency of all single elements, and removing the elements with the occurrence frequency less than the set minimum support degree to form a 1-frequent item set;
scanning the data set for the second time, arranging the elements of each transaction in the data set according to the descending order of the support degree, and starting to construct an FP-Tree; the FP-Tree root node is empty; each transaction, all elements of which form a path from the root node to a leaf node; the first n nodes are shared by a plurality of transactions with the same first n elements after the transactions are arranged according to the descending order of the support degree; counting the number of each node in the FP-Tree as the number of transactions passing through the node;
2) excavating FP-Growth;
excavating the FP-Tree in a bottom-up iteration mode; for each frequent item, taking the condition mode base of the frequent item as a new data set, removing the item which does not meet the minimum support degree, and forming a new condition FP-Tree by the rest items; continuously circulating and mining a frequent mode to obtain all K-frequent item sets;
the fault diagnosis only needs to obtain the association rules between the condition characteristics and the result characteristics, the association rules between the condition characteristics are useless information for fault diagnosis, according to the condition, after each condition mode base is obtained, judgment is firstly carried out, if the condition mode base contains the result characteristics, the condition FP-Tree is continuously generated, if the condition mode base only contains the condition characteristics, the condition FP-Tree is not generated, and the next frequent mode base is excavated;
3) diagnosing faults;
on the basis of obtaining a frequent item set by the FP-Growth algorithm mining, a strong association rule between the fault diagnosis condition characteristic and the result characteristic is obtained; in the building and mining processes of the FP-Tree, the minimum support degree is considered, and the strong association rule is considered when the minimum confidence degree requirement is met; further screening the excavated strong association rules, only keeping the strong association rules taking the fault type as a back item, and removing redundant rules to obtain a fault diagnosis rule base;
when fault diagnosis is carried out, matching the condition characteristics to be diagnosed with the condition characteristics of each rule in the rule base, if no matched rule exists, judging that no fault occurs, if a certain rule in the rule base is matched, finding out the result characteristics corresponding to the certain rule to obtain a fault diagnosis result, wherein the confidence coefficient of the rule is the confidence coefficient of the diagnosis result;
4) fault location;
the excavated strong association rule can be further used for fault positioning besides fault diagnosis, and the fault position is deduced according to the rule content; if the fault is diagnosed, the fault occurrence place is deduced according to the condition characteristics in the matched association rule, and the fault area is intelligently determined.
6. Power grid equipment management and control system based on electric power thing networking, its characterized in that:
the power grid equipment management and control system comprises a sensing unit, a network unit, a platform unit and an application unit;
the sensing unit is used for acquiring historical/quasi-real-time and power grid space data of the power grid equipment in real time; preprocessing the data, judging the probability of equipment failure, and forming a failure diagnosis feature library based on the data;
the network unit is used for transmitting the mass data and the preprocessing data of the power grid equipment of the sensing unit and accurately positioning the power grid equipment;
the platform unit is used for comprehensively analyzing and judging the data transmitted by the network unit, extracting a device characteristic value from a fault diagnosis characteristic library, carrying out discretization processing, generating a strong association rule between the broken line fault diagnosis condition characteristic and the result characteristic, and carrying out fault diagnosis;
and the application unit is used for providing fault information and accurate positioning of equipment for the electric power overhaul department.
7. The power grid equipment management and control system based on the power internet of things according to claim 6, characterized in that: the data acquisition and processing of the sensing unit specifically comprises:
the intelligent management terminal collects historical/quasi-real-time data of the power grid equipment, preprocesses the data and judges the probability of equipment failure based on weather conditions; and establishing a uniform power grid equipment accident probability data model and forming a fault diagnosis feature library.
8. The power grid equipment management and control system based on the power internet of things according to claim 6, characterized in that: the accurate positioning of the power grid equipment is carried out through a communication transmission network of the network unit;
the communication transmission network builds an integrated communication network by developing the technical research and application of a high-capacity backbone optical transmission network, a medium-low voltage high-speed power line carrier, a power wireless private network, a low-power wide area network, a photoelectric composite cable, a 5G network slice and a Beidou communication satellite hybrid networking.
9. The power grid equipment management and control system based on the power internet of things according to claim 6, characterized in that: the platform unit is based on the fault diagnosis feature library established by the sensing unit, carries out main feature selection based on an mRMR algorithm, and further excavates association rules between the fault diagnosis main condition features and result features through an FP-Growth algorithm, thereby establishing a rule library for fault diagnosis and carrying out fault diagnosis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010332863.4A CN113556369A (en) | 2020-04-24 | 2020-04-24 | Power grid equipment management and control method and system based on power internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010332863.4A CN113556369A (en) | 2020-04-24 | 2020-04-24 | Power grid equipment management and control method and system based on power internet of things |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113556369A true CN113556369A (en) | 2021-10-26 |
Family
ID=78101270
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010332863.4A Pending CN113556369A (en) | 2020-04-24 | 2020-04-24 | Power grid equipment management and control method and system based on power internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113556369A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115497267A (en) * | 2022-09-06 | 2022-12-20 | 江西小手软件技术有限公司 | Equipment early warning platform based on time sequence association rule |
| CN115580635A (en) * | 2022-09-26 | 2023-01-06 | 广州健新科技有限责任公司 | Intelligent fault diagnosis method and system for terminal of Internet of things |
| CN116170283A (en) * | 2023-04-23 | 2023-05-26 | 湖南开放大学(湖南网络工程职业学院、湖南省干部教育培训网络学院) | Processing method based on network communication fault system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103871003A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Power distribution network fault diagnosis method utilizing historical fault data |
| WO2015176565A1 (en) * | 2014-05-22 | 2015-11-26 | 袁志贤 | Method for predicting faults in electrical equipment based on multi-dimension time series |
| US20170006135A1 (en) * | 2015-01-23 | 2017-01-05 | C3, Inc. | Systems, methods, and devices for an enterprise internet-of-things application development platform |
| US20180107695A1 (en) * | 2016-10-19 | 2018-04-19 | Futurewei Technologies, Inc. | Distributed fp-growth with node table for large-scale association rule mining |
-
2020
- 2020-04-24 CN CN202010332863.4A patent/CN113556369A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103871003A (en) * | 2014-03-31 | 2014-06-18 | 国家电网公司 | Power distribution network fault diagnosis method utilizing historical fault data |
| WO2015176565A1 (en) * | 2014-05-22 | 2015-11-26 | 袁志贤 | Method for predicting faults in electrical equipment based on multi-dimension time series |
| US20170006135A1 (en) * | 2015-01-23 | 2017-01-05 | C3, Inc. | Systems, methods, and devices for an enterprise internet-of-things application development platform |
| US20180107695A1 (en) * | 2016-10-19 | 2018-04-19 | Futurewei Technologies, Inc. | Distributed fp-growth with node table for large-scale association rule mining |
Non-Patent Citations (9)
| Title |
|---|
| 刘建明;赵子岩;季翔;: "物联网技术在电力输配电系统中的研究与应用", 物联网学报, no. 01 * |
| 刘思怡: "基于 FP-Growth 算法的 10kV 配电网分支线断线故障诊断与定位方法", 《电网技术》, pages 2 - 2 * |
| 刘柱;华威;陈睿;冯雷;刘平;朱林;: "电网运行风险评估的综述", 机电工程技术, no. 12 * |
| 徐鑫;武晋龙;张瑾;闫磊;: "基于物联网的智能电网应用方案研究", 中国新通信, no. 01 * |
| 李西明;赵斌;杨一帆;李?;: "基于泛在电力物联网技术的配电网故障诊断方法优化", 内蒙古电力技术, no. 01 * |
| 杨成月;: "基于物联网与空间信息技术的电网应急指挥系统", 电网技术, no. 06 * |
| 胡畔: "泛在电力物联网发展建议及关键技术展望", 《湖北电力》, pages 1 - 3 * |
| 邓彬;郭创新;王越;黄太贵;汤伟;: "基于well-being分析的电网设备重要度评估与排序方法", 电网技术, no. 12, pages 1 * |
| 陈天超;: "物联网技术在智能电网中的应用", 湖北广播电视大学学报, no. 04 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115497267A (en) * | 2022-09-06 | 2022-12-20 | 江西小手软件技术有限公司 | Equipment early warning platform based on time sequence association rule |
| CN115580635A (en) * | 2022-09-26 | 2023-01-06 | 广州健新科技有限责任公司 | Intelligent fault diagnosis method and system for terminal of Internet of things |
| CN116170283A (en) * | 2023-04-23 | 2023-05-26 | 湖南开放大学(湖南网络工程职业学院、湖南省干部教育培训网络学院) | Processing method based on network communication fault system |
| CN116170283B (en) * | 2023-04-23 | 2023-07-14 | 湖南开放大学(湖南网络工程职业学院、湖南省干部教育培训网络学院) | Processing method based on network communication fault system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113556369A (en) | Power grid equipment management and control method and system based on power internet of things | |
| CN105515184B (en) | Multisensor many reference amounts distribution synergic monitoring system based on wireless sensor network | |
| CN104777813A (en) | Comprehensive meteorological observation operation monitoring system and monitoring method thereof | |
| CN112803592B (en) | Intelligent fault early warning method and system suitable for distributed power station | |
| CN106161620A (en) | A kind of cloud computing resources Internet of Things supervision and service platform | |
| CN109522380A (en) | A kind of power grid disaster comprehensive monitoring warning data system and method towards mobile application | |
| CN101308384A (en) | Lake eutrophication monitoring system platform based on wireless sensing network | |
| CN107705054A (en) | Meet the new energy grid-connected power remote measuring and diagnosing platform and method of complex data | |
| CN111428895A (en) | Intelligent ammeter fault diagnosis support center | |
| CN112488502A (en) | Standard water resource management integrated management and control platform | |
| CN103617447A (en) | Evaluation system and method for intelligent substation | |
| CN112463892A (en) | Early warning method and system based on risk situation | |
| CN112613790A (en) | Cooperative data processing method, device and medium applied to multi-station fusion environment | |
| CN114709923A (en) | Intelligent fault judgment method for power Internet of things | |
| CN110545321A (en) | Offshore platform integrated information integration system based on distributed technology | |
| CN114090667A (en) | Distributed intelligent integrated management platform for cross-basin hydropower station group | |
| CN112488873A (en) | Intelligent mining construction method for health codes and state tracks of power supply and utilization equipment | |
| CN117291317B (en) | AEM-based intelligent power monitoring and optimizing system | |
| Gu et al. | Optimal design of intelligent analysis and control system for power grid operation and maintenance | |
| CN113269435B (en) | New energy station running state coupling monitoring and evaluating system | |
| Qin | Data Monitoring Platform for Submarine Cable Tunnel Operation Based on Data Mining | |
| CN219304859U (en) | Cloud-edge combined battery management system and energy storage system | |
| CN116150257B (en) | Visual analysis method, system and storage medium for electric power communication optical cable resources | |
| CN113659716A (en) | Monitoring system for power network emergency | |
| CN111857015B (en) | Power transmission and transformation cloud intelligent controller |
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 |