CN117572837B - Intelligent power plant AI active operation and maintenance method and system - Google Patents
Intelligent power plant AI active operation and maintenance method and system Download PDFInfo
- Publication number
- CN117572837B CN117572837B CN202410062978.4A CN202410062978A CN117572837B CN 117572837 B CN117572837 B CN 117572837B CN 202410062978 A CN202410062978 A CN 202410062978A CN 117572837 B CN117572837 B CN 117572837B
- Authority
- CN
- China
- Prior art keywords
- abnormality
- state
- power plant
- node
- value
- 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
- 238000012423 maintenance Methods 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000005856 abnormality Effects 0.000 claims abstract description 197
- 238000004458 analytical method Methods 0.000 claims abstract description 169
- 230000002159 abnormal effect Effects 0.000 claims abstract description 116
- 238000012544 monitoring process Methods 0.000 claims abstract description 97
- 238000012795 verification Methods 0.000 claims abstract description 86
- 238000007689 inspection Methods 0.000 claims abstract description 45
- 230000003213 activating effect Effects 0.000 claims abstract description 16
- 238000010586 diagram Methods 0.000 claims description 37
- 230000000694 effects Effects 0.000 abstract description 6
- 230000000737 periodic effect Effects 0.000 abstract description 3
- 230000001419 dependent effect Effects 0.000 abstract 1
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000002547 anomalous effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/41845—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by system universality, reconfigurability, modularity
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/31—From computer integrated manufacturing till monitoring
- G05B2219/31094—Data exchange between modules, cells, devices, processors
-
- 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
Abstract
The invention discloses an intelligent power plant AI active operation and maintenance method and system, belonging to the field of power plant operation and maintenance, wherein the method comprises the following steps: loading an expected running state interval and a running parameter discrete point set of power plant equipment; constructing a first-level operation state abnormality analysis node and a second-level operation state abnormality analysis node; collecting operation state monitoring time sequence information; and activating an operation state abnormality analysis node to perform abnormality verification on the operation state monitoring time sequence information, and adding an active operation and maintenance equipment list into the power plant equipment identification active inspection tag when an abnormality verification result has an abnormality identification, and sending the power plant equipment identification active inspection tag to the power plant equipment operation and maintenance terminal. The method and the device solve the technical problems that the operation and maintenance of the existing power plant equipment are poor in pertinence and lack of initiative and accuracy due to the fact that the operation and maintenance of the power plant equipment are dependent on periodic passive inspection, and achieve the technical effects of actively inspecting and accurately operating and maintaining the power plant equipment through the abnormal analysis nodes configured by the operation states of the power plant equipment.
Description
Technical Field
The invention relates to the field of power plant operation and maintenance, in particular to an intelligent power plant AI active operation and maintenance method and system.
Background
With the rapid development of the power industry, the importance of operation and maintenance work of power plant equipment is increasingly highlighted. The state of the power plant equipment is directly related to safe and stable operation of the power grid, and the risk of equipment operation and maintenance can have a great influence on power supply. The existing operation and maintenance modes of the power plant equipment mainly adopt a periodic inspection mode, and the passive inspection mode has the problems of lack of pertinence, limited accident emergency capability and the like, so that the inspection effect is unstable, and the active and accurate operation and maintenance of the power plant equipment cannot be realized.
Disclosure of Invention
The application provides an intelligent power plant AI active operation and maintenance method and system, and aims to solve the technical problems that the operation and maintenance of the power plant equipment is poor in pertinence due to the fact that the operation and maintenance of the existing power plant equipment depends on periodic passive inspection, and the activity and the accuracy are poor.
In view of the above problems, the present application provides an intelligent power plant AI active operation and maintenance method and system.
In a first aspect of the disclosure, an intelligent power plant AI active operation and maintenance method is provided, which includes: loading an expected running state interval and a running parameter discrete point set of the first power plant equipment in a first working mode based on a preset database; constructing a first-level operation state abnormality analysis node by taking an operation state expected interval as a reference; constructing a secondary operation state anomaly analysis node by taking the operation parameter discrete point set as a reference; acquiring operation state monitoring time sequence information of first power plant equipment in a first working mode through a bottom sensing component; activating a first-stage operation state abnormality analysis node to perform abnormality verification on operation state monitoring time sequence information, and generating a first-stage abnormality verification result; when the primary abnormality verification result has an abnormality identification, adding an active operation and maintenance equipment list to the active inspection tag of the first power plant equipment identification, and sending the active inspection tag to the power plant equipment operation and maintenance terminal; when the primary abnormal verification result has a non-abnormal identifier, activating a secondary operation state abnormal analysis node to perform abnormal verification on the operation state monitoring time sequence information, and generating a secondary abnormal verification result; and when the second-level abnormality verification result has an abnormality identification, adding an active inspection tag to the first power plant equipment identification, adding the active inspection tag into an active operation and maintenance equipment list, and sending the active operation and maintenance equipment list to the power plant equipment operation and maintenance terminal.
In another aspect of the disclosure, an intelligent power plant AI active operation and maintenance system is provided, the system comprising: the operation data loading module is used for loading an operation state expected interval and an operation parameter discrete point set in a first working mode of the first power plant equipment based on a preset database; the first-level analysis node module is used for constructing a first-level operation state abnormality analysis node by taking an operation state expected interval as a reference; the secondary analysis node module is used for constructing a secondary operation state abnormality analysis node by taking the operation parameter discrete point set as a reference; the monitoring data acquisition module is used for acquiring the operation state monitoring time sequence information of the first power plant equipment in the first working mode through the bottom sensing assembly; the primary node verification module is used for activating a primary operation state abnormality analysis node to perform abnormality verification on the operation state monitoring time sequence information, and generating a primary abnormality verification result; the primary result abnormality module is used for adding an active operation and maintenance equipment list to the active inspection tag of the first power plant equipment identifier when the primary abnormality verification result has an abnormality identifier, and sending the active inspection tag to the power plant equipment operation and maintenance terminal; the secondary node verification module is used for activating a secondary operation state abnormality analysis node to perform abnormality verification on the operation state monitoring time sequence information when the primary abnormality verification result has a non-abnormality mark, so as to generate a secondary abnormality verification result; and the secondary node abnormality module is used for adding an active operation and maintenance equipment list to the active inspection tag of the first power plant equipment identifier when the secondary abnormality verification result has an abnormality identifier, and sending the active inspection tag to the power plant equipment operation and maintenance terminal.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
because the method adopts the method based on the preset database, the expected interval of the running state and the discrete point set of the running parameters in the first working mode of the first power plant equipment are loaded so as to acquire the reference data and construct the basis of abnormality judgment; constructing a first-level operation state abnormality analysis node by taking an operation state expected interval as a reference, and establishing a first level of a judgment model to judge in a normal interval; constructing a second-level operation state anomaly analysis node by taking an operation parameter discrete point set as a reference, establishing a second level of a judgment model, and calculating anomaly probability judgment by discrete points; acquiring running state monitoring time sequence information of first power plant equipment through a bottom sensing component, and acquiring real-time state parameter data of the equipment; activating a first-level abnormality analysis node to perform abnormality verification on the operation state monitoring time sequence information, generating a first-level abnormality verification result, and judging whether the equipment state is abnormal or not by a first level; when the primary abnormality checking result has an abnormality mark, marking an active inspection tag, adding the active inspection tag into an active operation and maintenance equipment list, and determining equipment to be actively inspected; when the primary checking result is non-abnormal, activating a secondary abnormal analysis node to continue judging, generating a secondary abnormal checking result, and if the first level is not found, continuing judging the secondary level; the technical scheme that the two-stage abnormality checking result is abnormal, the active inspection tag is marked and added into an active operation and maintenance equipment list, and the equipment to be actively checked is determined when the two-stage level abnormality is abnormal, so that the technical problems that the operation and maintenance of the existing power plant equipment is poor in initiative and accuracy due to poor pertinence due to the fact that the operation and maintenance of the power plant equipment are periodically and passively inspected are solved, the technical effects of configuring an abnormality analysis node through the operation state of the power plant equipment and realizing the active inspection and accurate operation and maintenance of the power plant equipment are achieved.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
FIG. 1 is a schematic flow chart of an AI active operation and maintenance method for an intelligent power plant according to an embodiment of the present application;
fig. 2 is a schematic flow chart of constructing a secondary operation state anomaly analysis node in an AI active operation and maintenance method of an intelligent power plant according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an intelligent power plant AI active operation system according to an embodiment of the present application.
Reference numerals illustrate: the system comprises an operation data loading module 11, a primary analysis node module 12, a primary analysis node module 13, a monitoring data acquisition module 14, a primary node verification module 15, a primary result exception module 16, a secondary node verification module 17 and a secondary node exception module 18.
Detailed Description
The technical scheme provided by the application has the following overall thought:
the embodiment of the application provides an intelligent power plant AI active operation and maintenance method and system, which are used for realizing active monitoring and intelligent judgment of power plant operation parameters by constructing a power plant equipment multi-level operation state anomaly analysis model, and accurately identifying power plant equipment needing special inspection, so as to guide active accurate operation and maintenance of the equipment.
Firstly, loading an expected running state interval and a running parameter discrete point set of power plant equipment in a normal working mode based on running data of the equipment, and constructing a primary running state abnormality analysis node and a secondary running state abnormality analysis node according to the expected running state interval and the running parameter discrete point set. And then, acquiring multidimensional operation parameters such as temperature, current, voltage and the like of the power plant equipment in real time through the bottom monitoring component, and acquiring operation state monitoring time sequence information of the equipment. And then, judging the operation state monitoring time sequence information through the primary operation state abnormality analysis node and the secondary operation state abnormality analysis node, and identifying abnormal equipment. And then, automatically identifying an active inspection tag for the judged abnormal equipment, updating an active operation and maintenance equipment list in real time, and providing an inspection object for active and accurate operation and maintenance.
By means of digital monitoring of the running state of the power plant equipment and application of multi-level intelligent technical analysis, the technical problems that the existing power plant equipment is low in inspection efficiency and insufficient in accident hidden trouble investigation are effectively solved, accurate and active power plant equipment health management is achieved, and safe and stable running of power grid equipment is ensured.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an embodiment of the present application provides an intelligent power plant AI active operation and maintenance method, which includes:
loading an expected running state interval and a running parameter discrete point set of the first power plant equipment in a first working mode based on a preset database;
further, the method comprises the following steps:
positive sample collection is carried out on the first working mode of the first power plant equipment, and an operation state record transaction set is generated;
extracting a running state record value set of a first running state attribute according to the running state record transaction set;
constructing an operation state record value box diagram according to the operation state record value set;
extracting box body concentrated data and box line discrete data based on the running state record value box line graph;
constructing a first running state attribute expected interval according to the box body concentrated data, and adding the first running state attribute expected interval into the running state expected interval;
setting the box line discrete data as a first running state attribute discrete point set, and adding the first running state attribute discrete point set into the running parameter discrete point set;
and storing the expected operating state interval and the operating parameter discrete point set simultaneously with the first operating mode of the first power plant.
Further, the method further comprises the following steps:
obtaining a first quartile record value and a second quartile record value according to the running state record value box diagram, wherein the second quartile record value is larger than or equal to the first quartile record value;
extracting the box body concentrated data which is larger than or equal to the first quartile record and smaller than or equal to the second quartile record value from the running state record value set;
obtaining a box line upper limit value and a box line lower limit value according to the running state record value box line diagram;
extracting first bin line discrete data which is larger than the second quartile record value and smaller than or equal to the bin line upper limit value from the running state record value set;
extracting second bin line discrete data which is smaller than the first quarter bit recorded value and larger than or equal to the bin line lower limit value from the running state recorded value set;
the first bin line discrete data and the second bin line discrete data are added to the bin line discrete data.
In a preferred embodiment, the predetermined database is a database for storing operating state data of the first power plant; the first power plant equipment is any one of electric equipment in the power plant; the first operating mode is any of the different operating conditions for the power plant. Firstly, configuring data acquisition equipment in a preset database, accessing first power plant equipment, setting acquisition operation parameters, and determining parameters such as acquisition time sequence, acquisition frequency and the like of the acquisition equipment. And secondly, controlling the first power plant equipment to start according to a first working mode, starting the data acquisition equipment after the equipment operates to be stable, and acquiring operation parameters according to configured frequency and time sequence to generate an original data sample. Then, multiple sets of raw data samples are collected, forming a running state record transaction set, wherein each set of raw data samples forms a transaction. And then analyzing the operation state record transaction sets, wherein each transaction comprises a plurality of groups of operation state attribute monitoring data, extracting monitoring data values related to the first operation state attribute from the monitoring data of all transactions to form an original set of operation state record values of the first operation state attribute, and performing redundancy record value de-duplication processing on the original set of operation state record values of the first operation state attribute to obtain an operation state record value set of the first operation state attribute. And then, sorting the running state record value set to enable the record values to be orderly arranged from small to large, calculating the number of the record values in the set, determining data of one quarter and three quarters of the data, namely 25% and 75% of the total number, and setting the record values at the two positions as a first quarter bit record value and a second quarter bit record value respectively. Then, the difference between the second quartile recorded value and the first quartile recorded value is calculated as the quartile range, minus 1.5 of the quartile range is taken as the lower limit of the box line, and the first quartile recorded value and the second quartile recorded value are taken as the upper limit and the lower limit of the box body, so that the running state recorded value box line diagram is constructed.
Then, according to the constructed running state record value box diagram, reading the lower limit value of the box body in the diagram, namely, the first quartile record value; and reading the upper limit value of the box body in the diagram, namely a second quartile recorded value, wherein the second quartile recorded value is larger than or equal to the first quartile recorded value according to the structural characteristics of the box diagram. Then, traversing the running state record value set, judging each record value one by one, and judging whether each record value meets the following conditions: and the record values which are larger than or equal to the first quartile record value and smaller than or equal to the second quartile record value are extracted, and the record values meeting the conditions are collected to form the box body concentrated data. Then, in the constructed running state record value box diagram, two values constituting the upper edge line and the lower edge line of the box line are identified, and the upper limit value and the lower limit value of the box line are obtained. Then, traversing the running state record value set, judging each record value one by one, and judging whether each record value meets the following conditions: and the record values which are larger than the second quartile record value and smaller than or equal to the box line upper limit value are extracted, and the record values meeting the conditions are collected to form first box line discrete data. Meanwhile, traversing the running state record value set, judging each record value one by one, and judging whether each record value meets the following conditions: and the record values which are smaller than the first quartile record value and larger than or equal to the box line lower limit value are extracted, and the record values meeting the conditions are collected to form second box line discrete data. And then, merging the first box line discrete data and the second box line discrete data, uniformly adding the first box line discrete data and the second box line discrete data into the box line discrete data to obtain integrated box line discrete data, and providing support for accurately judging the abnormal operation state.
And then, acquiring box centralized data, namely a data set in a box section, determining the minimum value and the maximum value of the box centralized data as a lower limit expected value and an upper limit expected value of a first running state attribute respectively, constructing an expected section of the state attribute according to the determined lower limit expected value and upper limit expected value, and adding the constructed expected section of the first running state attribute into the running state expected section to lay a foundation for subsequent abnormal analysis. Meanwhile, the obtained box line discrete data, namely the data set belonging to the abnormal section, is used as a first running state attribute discrete point set and is added into an running parameter discrete point set. And finally, creating a data structure of the first working mode of the power plant equipment, wherein static information such as working mode information, an equipment identifier and the like is contained in the data structure, and the constructed expected running state interval and the running parameter discrete point set are associated and bound with the data structure, so that simultaneous storage is realized, efficient management of the power plant equipment in different working states under the specified working mode is realized, and data support is provided for subsequent state monitoring and abnormality identification.
Constructing a first-level operation state abnormality analysis node by taking the operation state expected interval as a reference;
Further, the method comprises the following steps:
constructing a first operation state anomaly analysis function:
，
wherein,a first operating condition anomaly coefficient characterizing operating condition monitoring data,the frequency at which the ith attribute of the characterization operational state monitoring data deviates from the ith attribute expected interval,a monitoring status value characterizing the ith attribute at the jth moment,/->And->Representing the lower limit and the upper limit of the expected interval of the ith attribute, Q representing the total time sequence, N representing the total attribute, <>Representing preset weights of the ith attribute;
constructing a second operation state anomaly analysis function:
，
，
wherein,characterizing a second operating state anomaly coefficient, +.>Characterizing the deviation distance of the monitoring value of the ith attribute at the jth moment;
and configuring a first operation state abnormal coefficient threshold and a second operation state abnormal coefficient threshold, setting an operation state abnormal analysis rule by combining the first operation state abnormal analysis function and the second operation state abnormal analysis function, and constructing the first-stage operation state abnormal analysis node.
Further, the operation state anomaly analysis rule includes:
triggering condition A1: when the output value of the first running state abnormality analysis function is greater than or equal to the first running state abnormality coefficient threshold value, generating an abnormality identification and adding the abnormality identification into the primary abnormality verification result;
Triggering condition A2: when the first running state abnormality analysis function is smaller than the first running state abnormality coefficient threshold value and the output value of the second running state abnormality analysis function is larger than or equal to the second running state abnormality coefficient threshold value, generating an abnormality mark and adding the abnormality mark into the primary abnormality verification result;
triggering condition A3: and when the first running state abnormality analysis function is smaller than the first running state abnormality coefficient threshold and the output value of the second running state abnormality analysis function is smaller than the second running state abnormality coefficient threshold, generating a non-abnormality mark and adding the non-abnormality mark into the primary abnormality verification result.
In a preferred embodiment, a first operating state anomaly analysis function is first constructed:
，
wherein,a first operating state anomaly coefficient representing operating state monitoring data for quantifying an anomaly degree representing the operating state monitoring data; />Frequency of deviation of ith attribute from ith attribute expected interval, indicative of running state monitoring data, +.>A monitoring status value characterizing the ith attribute at the jth moment,/->And->Representing the lower limit and the upper limit of the expected interval of the ith attribute, Q representing the total time sequence, N representing the total attribute, < >The preset weight of the ith attribute is characterized. The first running state abnormality analysis function can obtain abnormal distribution and contribution of all running state attributes in a specified time window, reflect the overall running abnormality degree of the equipment and provide basis for abnormality processing.
Meanwhile, a second operation state anomaly analysis function is constructed:
，
，
wherein,characterizing a second operating condition anomaly coefficient for quantitatively representing operating condition monitoring dataDegree of abnormality of->And characterizing the deviation distance of the monitoring value of the ith attribute at the jth moment. And the maximum abnormal degree in the running state of the equipment is reflected by solving the average value of the maximum deviation distances of all the attributes, so that a basis is provided for subsequent abnormal processing.
Then, determining a first operation state abnormality coefficient threshold according to response requirements to the abnormality, wherein the first operation state abnormality coefficient threshold is used for judging whether the output of the first operation state abnormality analysis function is abnormal or not; and determining a second operating state anomaly coefficient threshold value for determining whether the second operating state anomaly analysis function output is anomalous. And then, judging whether the first power plant equipment is in an abnormal state or not through an operation state abnormality analysis rule by combining the output values of the first operation state abnormality analysis function and the second operation state abnormality analysis function according to the configured first operation state abnormality coefficient threshold and the second operation state abnormality coefficient threshold. The operation state exception analysis rule comprises three trigger conditions: firstly, when the output value of the first running state abnormality analysis function is greater than or equal to a first running state abnormality coefficient threshold value, generating an abnormality identification and adding the abnormality identification into a primary abnormality verification result; secondly, when the first running state abnormality analysis function is smaller than the first running state abnormality coefficient threshold value and the output value of the second running state abnormality analysis function is larger than or equal to the second running state abnormality coefficient threshold value, generating an abnormality mark and adding the abnormality mark into a primary abnormality verification result; thirdly, when the output values of the first running state abnormality analysis function and the second running state abnormality analysis function are lower than the corresponding threshold values, generating a non-abnormality identification and adding the non-abnormality identification into a primary abnormality verification result.
Constructing a secondary operation state anomaly analysis node by taking the operation parameter discrete point set as a reference;
further, as shown in fig. 2, the embodiment of the present application further includes:
obtaining a first state attribute discrete point set of the operation parameter discrete point set;
constructing a first abnormal analysis continuous node diagram based on the first state attribute discrete point set, wherein any node deploys record values with the same size of the first state attribute discrete point set, and the number of the record values of any node is at least equal to 2;
adding the first anomaly analysis continuous node map into a plurality of anomaly analysis continuous node maps, wherein the plurality of anomaly analysis continuous node maps are in one-to-one correspondence with state attributes;
and configuring an anomaly analysis rule, and constructing the secondary operation state anomaly analysis node by combining the plurality of anomaly analysis continuous node diagrams.
Further, the anomaly analysis rule includes:
when a kth node of the first abnormal analysis continuous node diagram receives a first attribute monitoring state value, judging whether the first attribute monitoring state value is equal to a kth node record value;
if not, entering a k+1st node for comparison;
if the first attribute monitoring state value is equal to the first attribute monitoring state value, carrying out non-abnormal identification on the first attribute monitoring state value;
If not, and the kth node is a tail node, carrying out abnormal identification on the first attribute monitoring state value;
when any one of all the attribute monitoring state values has an abnormal identifier, generating an abnormal identifier, and adding the abnormal identifier into the secondary abnormal verification result;
and when the number of the abnormal identifiers of all the attribute monitoring state values is equal to 0, generating a non-abnormal identifier, and adding the non-abnormal identifier into the secondary abnormal verification result.
In a preferred embodiment, first, a corresponding first state attribute discrete point set is obtained from the operating parameter discrete point set by searching and matching according to the first operating state attribute. And then, according to the number of abnormal points in the first state attribute discrete point set, calculating and determining the number of continuous nodes, configuring a storage space for each node, and ensuring that the state attribute abnormal record values with the same number can be stored. And then, reading the abnormal recorded values from the first state attribute discrete point set, and uniformly distributing the abnormal recorded values to each abnormal analysis node, wherein if the recorded value number of a certain node is less than 2, the recorded values need to be borrowed from adjacent nodes, so that the recorded value number of each node is ensured to be not less than 2, and a first abnormal analysis continuous node diagram is obtained. And then initializing a storage unit of the abnormal analysis node diagram, which is used for storing the abnormal analysis node diagrams of a plurality of state attributes, and realizing the corresponding relation binding of the state attributes and the node diagrams. And then, a first abnormal analysis continuous node diagram corresponding to the first state attribute is taken, the first abnormal analysis continuous node diagram and the state attribute are correspondingly bound and uniformly stored in a storage unit of the abnormal analysis node diagram, so that a plurality of abnormal analysis node diagrams are obtained, the corresponding abnormal analysis node diagram can be conveniently and rapidly searched and acquired according to the attribute, and support is provided for abnormal value transmission judgment.
And then, configuring an anomaly analysis rule, and constructing a secondary operation state anomaly analysis node by combining a plurality of anomaly analysis continuous node diagrams. Wherein, the anomaly analysis rule is: when a kth node of the first abnormal analysis continuous node diagram receives the first attribute monitoring state value, judging whether the first attribute monitoring state value is equal to a kth node record value; if the first attribute monitoring state value is not equal to the k node record value, comparing the first attribute monitoring state value with the k+1th node; and so on, comparing the first attribute monitoring status value to each node in the first anomaly analysis continuous node graph prior to comparison to the tail node in the first anomaly analysis continuous node graph; if the first attribute monitoring state value is equal to a certain node record value in the sequential comparison process, carrying out non-abnormal identification on the first attribute monitoring state value; if the node record values equal to the first attribute monitoring state value are not present in the tail node, carrying out abnormal identification on the first attribute monitoring state value; if any one of all the attribute monitoring state values has an abnormal identifier, generating an abnormal identifier, and adding a secondary abnormal verification result; and if the number of the abnormal identifiers of all the attribute monitoring state values is equal to 0, generating a non-abnormal identifier, and adding a secondary abnormal verification result. The method for judging whether the state value is abnormal or not by traversing the node comparison realizes detailed abnormality detection and provides support for equipment operation and maintenance.
Acquiring operation state monitoring time sequence information of first power plant equipment in a first working mode through a bottom sensing component;
in the embodiment of the application, the bottom sensing component is a hardware system module for collecting equipment running state data and consists of a sensor component and a data collecting unit, wherein the sensor component comprises physical sensing equipment of parameters such as temperature, current, voltage, vibration and the like, and the sensors are connected with target monitored equipment to collect equipment running parameters in real time; the data acquisition unit is responsible for centralizing the data acquired by various sensors and converting the data into digital signals. First, a target device is locked, and the target device is determined to be a first power plant device; then, inquiring and determining the current working mode of the first power plant equipment to obtain a first working mode; and then, accessing and configuring a bottom sensing component on the first power plant equipment to acquire equipment state data and obtain operation state monitoring time sequence information.
Activating the first-stage operation state abnormality analysis node to perform abnormality verification on the operation state monitoring time sequence information, and generating a first-stage abnormality verification result;
in the embodiment of the application, the first-stage operation state abnormality analysis node is activated while the operation state monitoring time sequence information of the first power plant equipment in the first working mode is acquired, and the operation state monitoring time sequence information is input into the node in real time. And then, the first-stage operation state abnormality analysis node analyzes and judges the operation state monitoring time sequence information according to the operation state abnormality analysis function and the operation state abnormality analysis rule which are configured by the first-stage operation state abnormality analysis node, so that a first-stage abnormality verification result is generated and is used for carrying out preliminary abnormality detection on the state monitoring information.
When the primary abnormality verification result has an abnormality identification, adding an active operation and maintenance equipment list to the active inspection tag of the first power plant equipment identification, and sending the active inspection tag to a power plant equipment operation and maintenance terminal;
in the embodiment of the application, first, a primary abnormality verification result is analyzed, and whether an abnormality identifier is specific to the first power plant equipment in the primary abnormality verification result is judged. If an abnormal identifier exists on the first power plant equipment in the primary abnormal verification result, an active inspection tag of the first power plant equipment is generated, the active inspection tag is added to an active operation and maintenance equipment list, the active operation and maintenance equipment list is updated, and the updated active operation and maintenance equipment list is sent to the power plant equipment operation and maintenance terminal for display, so that operation and maintenance personnel are reminded of carrying out important active maintenance, and the healthy operation level of the power plant equipment is improved.
When the primary abnormal verification result has a non-abnormal mark, activating the secondary operation state abnormal analysis node to perform abnormal verification on the operation state monitoring time sequence information, and generating a secondary abnormal verification result;
in the embodiment of the application, when the first-stage abnormality verification result does not have the abnormality identification for the first power plant equipment, the equipment is explained to preliminarily judge that the state is normal. At this time, the constructed secondary operation state anomaly analysis node is activated, the collected operation state monitoring time sequence information is sent, the secondary operation state anomaly analysis node receives the information, detailed transmission judgment is carried out according to the integrated multiple anomaly analysis continuous node diagrams, and a secondary anomaly verification result is generated.
And when the secondary abnormality verification result has an abnormality identification, adding an active operation and maintenance equipment list to the active inspection tag of the first power plant equipment identification, and sending the active inspection tag to the power plant equipment operation and maintenance terminal.
In the embodiment of the application, after the secondary abnormal verification result is obtained, the secondary abnormal verification result is analyzed, and whether the abnormal identifier aiming at the first power plant equipment exists is judged. When the second-level abnormality verification result includes an abnormality identification of the first power plant equipment, an active inspection tag of the first power plant equipment is generated and added into an active operation and maintenance equipment name list, and the updated active operation and maintenance equipment list is sent to an operation and maintenance terminal of the power plant equipment to be displayed so as to perform accurate active operation and maintenance on the first power plant equipment.
Through two-stage anomaly analysis and labeling, the identification capability of potential hidden trouble of equipment is improved, and active inspection and accurate operation and maintenance of power plant equipment are realized.
In summary, the intelligent power plant AI active operation and maintenance method provided by the embodiment of the application has the following technical effects:
based on a preset database, loading an expected running state interval and a running parameter discrete point set of the first power plant equipment in a first working mode, and providing a data basis for realizing accurate and intelligent judgment. And constructing a first-stage operation state abnormality analysis node by taking an operation state expected interval as a reference, judging whether the data is abnormal or not according to a normal interval, and realizing simple and rapid judgment. Constructing a secondary operation state anomaly analysis node by taking the operation parameter discrete point set as a reference; when the first-level operation state abnormality analysis node is insufficient in judgment, depth judgment is realized according to the outlier. And acquiring operation state monitoring time sequence information of the first power plant equipment in the first working mode through the bottom sensing component, and providing necessary input data for abnormality judgment. And activating a first-stage operation state abnormality analysis node to perform abnormality verification on the operation state monitoring time sequence information, generating a first-stage abnormality verification result, and judging whether the data is abnormal or not. And when the primary abnormality verification result has an abnormality identification, adding an active inspection tag to the first power plant equipment identification, adding the active inspection tag into an active operation and maintenance equipment list, and sending the active operation and maintenance equipment list to the power plant equipment operation and maintenance terminal. And when the primary abnormal verification result has a non-abnormal identifier, activating a secondary operation state abnormal analysis node to perform abnormal verification on the operation state monitoring time sequence information, generating a secondary abnormal verification result, and realizing the deep judgment of the power plant equipment. When the second-level abnormality verification result has an abnormality identification, the first power plant equipment identification is added into an active operation and maintenance equipment list and sent to a power plant equipment operation and maintenance terminal, so that the power plant equipment is actively inspected and accurately operated and maintained.
Example two
Based on the same inventive concept as the method for active operation and maintenance of an intelligent power plant AI in the foregoing embodiments, as shown in fig. 3, an embodiment of the present application provides an active operation and maintenance system of an intelligent power plant AI, which includes:
the operation data loading module 11 is used for loading an operation state expected interval and an operation parameter discrete point set in a first operation mode of the first power plant equipment based on a preset database;
the first-stage analysis node module 12 is configured to construct a first-stage operation state anomaly analysis node based on the operation state expected interval;
the secondary analysis node module 13 is used for constructing a secondary operation state abnormality analysis node by taking the operation parameter discrete point set as a reference;
the monitoring data acquisition module 14 is configured to acquire, through the bottom sensing component, operation state monitoring timing information in a first operation mode of the first power plant equipment;
the primary node verification module 15 is used for activating the primary operation state anomaly analysis node to perform anomaly verification on the operation state monitoring time sequence information, and generating a primary anomaly verification result;
the primary result exception module 16 is configured to add an active operation and maintenance equipment list to the first power plant equipment identifier active inspection tag when the primary exception verification result has an exception identifier, and send the active operation and maintenance equipment list to a power plant equipment operation and maintenance terminal;
The second-level node checking module 17 is configured to activate the second-level operation state anomaly analysis node to perform anomaly checking on the operation state monitoring time sequence information when the first-level anomaly checking result has a non-anomaly identifier, so as to generate a second-level anomaly checking result;
and the secondary node anomaly module 18 is used for adding the active inspection tag to the first power plant equipment identifier, adding the active inspection tag to an active operation and maintenance equipment list and sending the active inspection tag to the power plant equipment operation and maintenance terminal when the secondary anomaly verification result has an anomaly identifier.
Further, the operation data loading module 11 includes the following steps:
positive sample collection is carried out on the first working mode of the first power plant equipment, and an operation state record transaction set is generated;
extracting a running state record value set of a first running state attribute according to the running state record transaction set;
constructing an operation state record value box diagram according to the operation state record value set;
extracting box body concentrated data and box line discrete data based on the running state record value box line graph;
constructing a first running state attribute expected interval according to the box body concentrated data, and adding the first running state attribute expected interval into the running state expected interval;
Setting the box line discrete data as a first running state attribute discrete point set, and adding the first running state attribute discrete point set into the running parameter discrete point set;
and storing the expected operating state interval and the operating parameter discrete point set simultaneously with the first operating mode of the first power plant.
Further, the operation data loading module 11 further includes the following execution steps:
obtaining a first quartile record value and a second quartile record value according to the running state record value box diagram, wherein the second quartile record value is larger than or equal to the first quartile record value;
extracting the box body concentrated data which is larger than or equal to the first quartile record and smaller than or equal to the second quartile record value from the running state record value set;
obtaining a box line upper limit value and a box line lower limit value according to the running state record value box line diagram;
extracting first bin line discrete data which is larger than the second quartile record value and smaller than or equal to the bin line upper limit value from the running state record value set;
extracting second bin line discrete data which is smaller than the first quarter bit recorded value and larger than or equal to the bin line lower limit value from the running state recorded value set;
The first bin line discrete data and the second bin line discrete data are added to the bin line discrete data.
Further, the primary analysis node module 12 includes the following steps:
constructing a first operation state anomaly analysis function:
，
wherein,a first operating condition anomaly coefficient characterizing operating condition monitoring data,the frequency at which the ith attribute of the characterization operational state monitoring data deviates from the ith attribute expected interval,a monitoring status value characterizing the ith attribute at the jth moment,/->And->Representing the lower limit and the upper limit of the expected interval of the ith attribute, Q representing the total time sequence, N representing the total attribute, <>Representing preset weights of the ith attribute;
constructing a second operation state anomaly analysis function:
，
，
wherein,characterizing a second operating state anomaly coefficient, +.>Characterizing the deviation distance of the monitoring value of the ith attribute at the jth moment;
and configuring a first operation state abnormal coefficient threshold and a second operation state abnormal coefficient threshold, setting an operation state abnormal analysis rule by combining the first operation state abnormal analysis function and the second operation state abnormal analysis function, and constructing the first-stage operation state abnormal analysis node.
Further, the primary analysis node module 12 further comprises the following steps:
The operation state anomaly analysis rule includes:
triggering condition A1: when the output value of the first running state abnormality analysis function is greater than or equal to the first running state abnormality coefficient threshold value, generating an abnormality identification and adding the abnormality identification into the primary abnormality verification result;
triggering condition A2: when the first running state abnormality analysis function is smaller than the first running state abnormality coefficient threshold value and the output value of the second running state abnormality analysis function is larger than or equal to the second running state abnormality coefficient threshold value, generating an abnormality mark and adding the abnormality mark into the primary abnormality verification result;
triggering condition A3: and when the first running state abnormality analysis function is smaller than the first running state abnormality coefficient threshold and the output value of the second running state abnormality analysis function is smaller than the second running state abnormality coefficient threshold, generating a non-abnormality mark and adding the non-abnormality mark into the primary abnormality verification result.
Further, the secondary analysis node module 13 comprises the following execution steps:
obtaining a first state attribute discrete point set of the operation parameter discrete point set;
constructing a first abnormal analysis continuous node diagram based on the first state attribute discrete point set, wherein any node deploys record values with the same size of the first state attribute discrete point set, and the number of the record values of any node is at least equal to 2;
Adding the first anomaly analysis continuous node map into a plurality of anomaly analysis continuous node maps, wherein the plurality of anomaly analysis continuous node maps are in one-to-one correspondence with state attributes;
and configuring an anomaly analysis rule, and constructing the secondary operation state anomaly analysis node by combining the plurality of anomaly analysis continuous node diagrams.
Further, the secondary analysis node module 13 further comprises the following execution steps:
the anomaly analysis rule is as follows:
when a kth node of the first abnormal analysis continuous node diagram receives a first attribute monitoring state value, judging whether the first attribute monitoring state value is equal to a kth node record value;
if not, entering a k+1st node for comparison;
if the first attribute monitoring state value is equal to the first attribute monitoring state value, carrying out non-abnormal identification on the first attribute monitoring state value;
if not, and the kth node is a tail node, carrying out abnormal identification on the first attribute monitoring state value;
when any one of all the attribute monitoring state values has an abnormal identifier, generating an abnormal identifier, and adding the abnormal identifier into the secondary abnormal verification result;
and when the number of the abnormal identifiers of all the attribute monitoring state values is equal to 0, generating a non-abnormal identifier, and adding the non-abnormal identifier into the secondary abnormal verification result.
Any of the steps of the methods described above may be stored as computer instructions or programs in a non-limiting computer memory and may be called by a non-limiting computer processor to identify any of the methods to implement embodiments of the present application, without unnecessary limitations.
Further, the first or second element may not only represent a sequential relationship, but may also represent a particular concept, and/or may be selected individually or in whole among a plurality of elements. It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (5)
1. An intelligent power plant AI active operation and maintenance method is characterized by comprising the following steps:
loading an expected running state interval and a running parameter discrete point set of the first power plant equipment in a first working mode based on a preset database;
constructing a first-level operation state abnormality analysis node by taking the operation state expected interval as a reference;
constructing a secondary operation state anomaly analysis node by taking the operation parameter discrete point set as a reference;
Acquiring operation state monitoring time sequence information of first power plant equipment in a first working mode through a bottom sensing component;
activating the first-stage operation state abnormality analysis node to perform abnormality verification on the operation state monitoring time sequence information, and generating a first-stage abnormality verification result;
when the primary abnormality verification result has an abnormality identification, adding an active operation and maintenance equipment list to the active inspection tag of the first power plant equipment identification, and sending the active inspection tag to a power plant equipment operation and maintenance terminal;
when the primary abnormal verification result has a non-abnormal mark, activating the secondary operation state abnormal analysis node to perform abnormal verification on the operation state monitoring time sequence information, and generating a secondary abnormal verification result;
when the secondary abnormality verification result has an abnormality identification, adding an active operation and maintenance equipment list to the active inspection tag of the first power plant equipment identification, and sending the active inspection tag to a power plant equipment operation and maintenance terminal;
the method for constructing the first-stage operation state abnormality analysis node by taking the operation state expected interval as a reference comprises the following steps:
constructing a first operation state anomaly analysis function:
，
wherein,first operating state abnormality coefficient characterizing operating state monitoring data,/- >Frequency of deviation of ith attribute from ith attribute expected interval, indicative of running state monitoring data, +.>A monitoring status value characterizing the ith attribute at the jth moment,/->And->Representing the lower limit and the upper limit of the expected interval of the ith attribute, Q representing the total time sequence, N representing the total attribute, <>Representing preset weights of the ith attribute;
constructing a second operation state anomaly analysis function:
，
，
wherein,characterizing a second operating state anomaly coefficient, +.>Characterizing the deviation distance of the monitoring value of the ith attribute at the jth moment;
configuring a first operation state abnormality coefficient threshold and a second operation state abnormality coefficient threshold, setting an operation state abnormality analysis rule by combining the first operation state abnormality analysis function and the second operation state abnormality analysis function, and constructing the first-stage operation state abnormality analysis node;
configuring a first operating state anomaly coefficient threshold and a second operating state anomaly coefficient threshold, setting an operating state anomaly analysis rule by combining the first operating state anomaly analysis function and the second operating state anomaly analysis function, and constructing the first-stage operating state anomaly analysis node, wherein the method comprises the following steps:
the operation state anomaly analysis rule includes:
triggering condition A1: when the output value of the first running state abnormality analysis function is greater than or equal to the first running state abnormality coefficient threshold value, generating an abnormality identification and adding the abnormality identification into the primary abnormality verification result;
Triggering condition A2: when the first running state abnormality analysis function is smaller than the first running state abnormality coefficient threshold value and the output value of the second running state abnormality analysis function is larger than or equal to the second running state abnormality coefficient threshold value, generating an abnormality mark and adding the abnormality mark into the primary abnormality verification result;
triggering condition A3: when the first running state abnormality analysis function is smaller than the first running state abnormality coefficient threshold value and the output value of the second running state abnormality analysis function is smaller than the second running state abnormality coefficient threshold value, generating a non-abnormality mark and adding the non-abnormality mark into the primary abnormality verification result;
constructing a secondary operation state anomaly analysis node by taking the operation parameter discrete point set as a reference, wherein the method comprises the following steps of:
obtaining a first state attribute discrete point set of the operation parameter discrete point set;
constructing a first abnormal analysis continuous node diagram based on the first state attribute discrete point set, wherein any node deploys record values with the same size of the first state attribute discrete point set, and the number of the record values of any node is at least equal to 2;
adding the first anomaly analysis continuous node map into a plurality of anomaly analysis continuous node maps, wherein the plurality of anomaly analysis continuous node maps are in one-to-one correspondence with state attributes;
And configuring an anomaly analysis rule, and constructing the secondary operation state anomaly analysis node by combining the plurality of anomaly analysis continuous node diagrams.
2. The method of claim 1, wherein loading the operating state expected interval and the set of operating parameter discrete points in the first operating mode of the first power plant comprises:
positive sample collection is carried out on the first working mode of the first power plant equipment, and an operation state record transaction set is generated;
extracting a running state record value set of a first running state attribute according to the running state record transaction set;
constructing an operation state record value box diagram according to the operation state record value set;
extracting box body concentrated data and box line discrete data based on the running state record value box line graph;
constructing a first running state attribute expected interval according to the box body concentrated data, and adding the first running state attribute expected interval into the running state expected interval;
setting the box line discrete data as a first running state attribute discrete point set, and adding the first running state attribute discrete point set into the running parameter discrete point set;
and storing the expected operating state interval and the operating parameter discrete point set simultaneously with the first operating mode of the first power plant.
3. The method of claim 2, wherein extracting bin set data and bin line discrete data based on the operational state record value bin line graph comprises:
obtaining a first quartile record value and a second quartile record value according to the running state record value box diagram, wherein the second quartile record value is larger than or equal to the first quartile record value;
extracting the box body concentrated data which is larger than or equal to the first quartile record and smaller than or equal to the second quartile record value from the running state record value set;
obtaining a box line upper limit value and a box line lower limit value according to the running state record value box line diagram;
extracting first bin line discrete data which is larger than the second quartile record value and smaller than or equal to the bin line upper limit value from the running state record value set;
extracting second bin line discrete data which is smaller than the first quarter bit recorded value and larger than or equal to the bin line lower limit value from the running state recorded value set;
the first bin line discrete data and the second bin line discrete data are added to the bin line discrete data.
4. The method of claim 1, wherein configuring exception analysis rules in conjunction with the plurality of exception analysis successive node graphs to construct the secondary operational state exception analysis node comprises:
the anomaly analysis rule is as follows:
when a kth node of the first abnormal analysis continuous node diagram receives a first attribute monitoring state value, judging whether the first attribute monitoring state value is equal to a kth node record value;
if not, entering a k+1st node for comparison;
if the first attribute monitoring state value is equal to the first attribute monitoring state value, carrying out non-abnormal identification on the first attribute monitoring state value;
if not, and the kth node is a tail node, carrying out abnormal identification on the first attribute monitoring state value;
when any one of all the attribute monitoring state values has an abnormal identifier, generating an abnormal identifier, and adding the abnormal identifier into the secondary abnormal verification result;
and when the number of the abnormal identifiers of all the attribute monitoring state values is equal to 0, generating a non-abnormal identifier, and adding the non-abnormal identifier into the secondary abnormal verification result.
5. An intelligent power plant AI active operation and maintenance system, for implementing the intelligent power plant AI active operation and maintenance method as claimed in any one of claims 1-4, comprising:
the operation data loading module is used for loading an operation state expected interval and an operation parameter discrete point set in a first working mode of the first power plant equipment based on a preset database;
The first-level analysis node module is used for constructing a first-level operation state abnormality analysis node by taking the operation state expected interval as a reference;
the first-stage analysis node module is used for constructing a first-stage operation state anomaly analysis node by taking the operation parameter discrete point set as a reference;
the monitoring data acquisition module is used for acquiring the operation state monitoring time sequence information of the first power plant equipment in the first working mode through the bottom sensing assembly;
the primary node verification module is used for activating the primary operation state abnormality analysis node to carry out abnormality verification on the operation state monitoring time sequence information, and generating a primary abnormality verification result;
the primary result abnormality module is used for adding an active operation and maintenance equipment list to the first power plant equipment identification active inspection tag when the primary abnormality verification result has an abnormality identification, and sending the first power plant equipment identification active inspection tag to a power plant equipment operation and maintenance terminal;
the secondary node verification module is used for activating the secondary operation state abnormality analysis node to carry out abnormality verification on the operation state monitoring time sequence information when the primary abnormality verification result has a non-abnormality mark, and generating a secondary abnormality verification result;
And the secondary node abnormality module is used for adding an active operation and maintenance equipment list to the active inspection tag of the first power plant equipment identifier when the secondary abnormality verification result has an abnormality identifier, and sending the active inspection tag to the power plant equipment operation and maintenance terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410062978.4A CN117572837B (en) | 2024-01-17 | 2024-01-17 | Intelligent power plant AI active operation and maintenance method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410062978.4A CN117572837B (en) | 2024-01-17 | 2024-01-17 | Intelligent power plant AI active operation and maintenance method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117572837A CN117572837A (en) | 2024-02-20 |
| CN117572837B true CN117572837B (en) | 2024-04-16 |
Family
ID=89862902
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410062978.4A Active CN117572837B (en) | 2024-01-17 | 2024-01-17 | Intelligent power plant AI active operation and maintenance method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117572837B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20040038124A (en) * | 2002-10-31 | 2004-05-08 | 한국전력공사 | A On-line Real-time Operation Performance Monitoring and Diagnostic System for Combined-cycle Power Plant |
| WO2019233047A1 (en) * | 2018-06-07 | 2019-12-12 | 国电南瑞科技股份有限公司 | Power grid dispatching-based operation and maintenance method |
| CN113657622A (en) * | 2021-07-13 | 2021-11-16 | 国网河北省电力有限公司电力科学研究院 | Method, device, terminal and storage medium for fusing multidimensional state data of electrical equipment |
| CN114048874A (en) * | 2021-11-16 | 2022-02-15 | 西安热工研究院有限公司 | A wisdom prison dish that is arranged in wisdom power plant to always operate |
| CN117236934A (en) * | 2023-11-01 | 2023-12-15 | 山东经纬信息集团有限公司 | Industrial Internet remote monitoring operation and maintenance management system and working method thereof |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| BR112019017301A2 (en) * | 2017-10-09 | 2020-04-22 | Bl Technologies, Inc. | intelligent methods and systems for health diagnosis of a water treatment plant, anomaly detection and control |
-
2024
- 2024-01-17 CN CN202410062978.4A patent/CN117572837B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20040038124A (en) * | 2002-10-31 | 2004-05-08 | 한국전력공사 | A On-line Real-time Operation Performance Monitoring and Diagnostic System for Combined-cycle Power Plant |
| WO2019233047A1 (en) * | 2018-06-07 | 2019-12-12 | 国电南瑞科技股份有限公司 | Power grid dispatching-based operation and maintenance method |
| CN113657622A (en) * | 2021-07-13 | 2021-11-16 | 国网河北省电力有限公司电力科学研究院 | Method, device, terminal and storage medium for fusing multidimensional state data of electrical equipment |
| CN114048874A (en) * | 2021-11-16 | 2022-02-15 | 西安热工研究院有限公司 | A wisdom prison dish that is arranged in wisdom power plant to always operate |
| CN117236934A (en) * | 2023-11-01 | 2023-12-15 | 山东经纬信息集团有限公司 | Industrial Internet remote monitoring operation and maintenance management system and working method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 工控运维中基于语义分析的智能电网控制攻击防御;麻建中;胡凯波;於立峰;;中国电力(第09期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117572837A (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108802535B (en) | Screening method, main interference source identification method and device, server and storage medium | |
| CN111143438A (en) | Workshop field data real-time monitoring and anomaly detection method based on stream processing | |
| CN112668870B (en) | Nuclear power plant equipment state online intelligent monitoring method and computer terminal | |
| CN110580492A (en) | Track circuit fault precursor discovery method based on small fluctuation detection | |
| CN115204536A (en) | Building equipment fault prediction method, device, equipment and storage medium | |
| CN113657747A (en) | Enterprise safety production standardization level intelligent evaluation system | |
| CN117572837B (en) | Intelligent power plant AI active operation and maintenance method and system | |
| CN117131364A (en) | Rolling bearing process detection integration method and system | |
| CN113360555A (en) | Fault diagnosis and analysis method and system based on big data of power grid secondary equipment | |
| CN115469585B (en) | Hydropower unit state monitoring method and system based on big data | |
| CN115128345B (en) | Power grid safety early warning method and system based on harmonic monitoring | |
| CN116738261A (en) | Numerical characteristic discretization attribution analysis method and device based on clustering and binning | |
| CN114518988B (en) | Resource capacity system, control method thereof, and computer-readable storage medium | |
| CN115422821A (en) | Data processing method and device for rock mass parameter prediction | |
| CN115598459A (en) | Power failure prediction method for 10kV feeder line fault of power distribution network | |
| CN113268552A (en) | Generator equipment hidden danger early warning method based on locality sensitive hashing | |
| CN112270203A (en) | Fan characteristic optimization method based on entropy weight method | |
| CN114492636B (en) | Transformer winding state signal acquisition system | |
| CN117436846B (en) | Equipment predictive maintenance method and system based on neural network | |
| CN117368651B (en) | Comprehensive analysis system and method for faults of power distribution network | |
| CN116502070B (en) | Intelligent monitoring system for state of miniature wind turbine generator | |
| CN116643170B (en) | Motor shafting vibration testing method and device and computer equipment | |
| Lei et al. | Application of distributed machine learning model in fault diagnosis of air preheater | |
| CN117723917B (en) | Monitoring application method based on optical fiber extrinsic Fabry-Perot type ultrasonic sensor | |
| CN112648715A (en) | Air conditioner control system and device based on intelligent substation |
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 |