CN117149498A - Power plant fault diagnosis method and system - Google Patents
Power plant fault diagnosis method and system Download PDFInfo
- Publication number
- CN117149498A CN117149498A CN202311403606.5A CN202311403606A CN117149498A CN 117149498 A CN117149498 A CN 117149498A CN 202311403606 A CN202311403606 A CN 202311403606A CN 117149498 A CN117149498 A CN 117149498A
- Authority
- CN
- China
- Prior art keywords
- equipment
- parameter
- virtual
- abnormal
- power plant
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000003745 diagnosis Methods 0.000 title claims abstract description 27
- 230000005540 biological transmission Effects 0.000 claims abstract description 77
- 238000013507 mapping Methods 0.000 claims abstract description 71
- 238000004458 analytical method Methods 0.000 claims abstract description 21
- 230000002159 abnormal effect Effects 0.000 claims description 64
- 238000012549 training Methods 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 19
- 238000004519 manufacturing process Methods 0.000 claims description 13
- 230000001960 triggered effect Effects 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000012512 characterization method Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 239000007789 gas Substances 0.000 description 13
- 239000000446 fuel Substances 0.000 description 9
- 239000000463 material Substances 0.000 description 3
- 238000002485 combustion reaction Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 239000002817 coal dust Substances 0.000 description 1
- 239000002826 coolant Substances 0.000 description 1
- 239000000498 cooling water Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- -1 feedwater Substances 0.000 description 1
- 239000002737 fuel gas Substances 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000746 purification Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/079—Root cause analysis, i.e. error or fault diagnosis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/0751—Error or fault detection not based on redundancy
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application discloses a power plant fault diagnosis method and a system, which relate to the technical field of power plant management, wherein equipment of a power plant is set as virtual equipment blocks, an equipment application map is constructed and generated based on respective position nodes, parameter transmission channels are constructed among different virtual equipment blocks, monitoring analysis is carried out on the parameter transmission channels, first equipment faults of the equipment are determined, equipment hidden danger characteristics of different equipment are determined based on a relation influence model among parameter mapping nodes, and the equipment hidden danger characteristics are displayed on the equipment application map based on the determined first equipment faults and the equipment hidden danger characteristics, so that analysis and display of the equipment faults and hidden troubles of the power plant are realized, and the time for workers to take countermeasures is effectively reduced.
Description
Technical Field
The application relates to the technical field of power plant management, in particular to a power plant fault diagnosis method and system.
Background
The power plant fault diagnosis method and system are one of key technologies designed for ensuring safe and stable operation of the power plant. Along with the continuous increase of the scale and complexity of the power system, it becomes an important task to accurately diagnose the power plant faults and take effective measures in time.
In an electrical power system, a power plant is a core facility for generating electricity and is typically composed of a plurality of generators, boilers, turbines, and a control system. However, since various potential faults and abnormal conditions exist in equipment and systems of the power plant, such as equipment aging, overload, electrical faults and the like, and the faults may cause shutdown, damage to the equipment and reduction of energy efficiency or even safety accidents, in order to solve the problems, a conventional fault diagnosis method comprises monitoring operation parameters of different equipment of the power plant by using various sensors or other acquisition devices, and determining whether equipment faults exist or not through analysis of the operation parameters, wherein although the abnormality of the equipment can be determined to a certain extent, the fault state and hidden trouble state of each equipment cannot be displayed, and corresponding countermeasures cannot be made by staff more quickly.
Disclosure of Invention
The application aims to provide a fault diagnosis method and system capable of displaying fault states and hidden danger states of various devices.
The application discloses a power plant fault diagnosis method, which comprises the following steps:
establishing an equipment application map aiming at equipment of a power plant, and mapping and calibrating a plurality of virtual equipment blocks on the equipment application map based on position nodes of the equipment;
analyzing the equipment process logic, constructing parameter transmission channels among the virtual equipment blocks based on an analysis result, and constructing a transmission channel set aiming at all the parameter transmission channels connected to one virtual equipment block;
based on the operation logic of the equipment, constructing a plurality of equipment operation state trees, wherein the equipment operation state trees comprise a plurality of parameter mapping nodes, each parameter mapping node is associated with a specific preset equipment fault, and based on the influence relation among the equipment faults, a relation influence model is established among different parameter mapping nodes;
comparing and analyzing real-time operation parameters transmitted in each parameter transmission channel in the virtual equipment block transmission channel set, and determining whether the virtual equipment block is abnormal;
substituting the real-time operation parameters corresponding to the abnormal virtual equipment blocks into corresponding equipment operation state trees, determining a first equipment fault existing in equipment according to the parameter mapping nodes to which the real-time operation parameters belong, and determining equipment hidden danger characteristics of the equipment based on a relation influence model among the parameter mapping nodes;
and mapping the virtual equipment block on the equipment application map for characterization based on the determined first equipment fault and equipment hidden trouble characteristics of the equipment.
In some embodiments of the present application, a method for mapping and calibrating a virtual device block on a device application map based on a location node of a device includes:
acquiring an equipment directory of an application, and finding out an equipment icon of each application in a preset equipment icon set aiming at the equipment directory;
acquiring a power plant map, establishing a first reference coordinate system based on the power plant map, and calibrating vector coordinates of each device under the first reference coordinate system;
scaling the vector coordinates of different devices in equal proportion to determine the relative relation between the position nodes of different devices;
mapping the position nodes on the equipment application map based on the relative relation between the position nodes of different equipment, and calibrating the equipment on the equipment application map in the form of equipment icons to generate a plurality of virtual equipment blocks.
In some embodiments of the present application, the method for mapping the calibrated virtual device block on the device application map further comprises:
setting the shortest limiting distance for the distance between the device icons;
determining the map positions of different equipment icons relative to the equipment application maps, and calculating and analyzing the relative distances between the different equipment icons;
maintaining the relative distance between the different device icons to be greater than or equal to the shortest limiting distance, and if the device icons break through the boundary of the device application map boundary, pulling the device icons breaking through the device application map boundary to the device application map boundary;
if the overlapped equipment icons exist, determining the pulling distance between the overlapped equipment icons based on the scaling of vector coordinates of different equipment, and pulling the overlapped equipment icons longitudinally or transversely according to the determined pulling distance;
the expression for calculating the distance between the overlapped equipment icons is as follows:
；
wherein,for the pull-off distance between the ith device icon and the (i+1) th device icon,/for the (i) th device icon>Is the scaling of the vector coordinates of the different devices, k is the pull-apart distance conversion coefficient, +.>The constant is adjusted for scaling.
In some embodiments of the present application, a method of building a number of device operational state trees based on the operational logic of a device includes:
analyzing the operation logic of the equipment, and determining a plurality of functions of the equipment and a plurality of participation modules corresponding to each function;
constructing an equipment running state tree aiming at each function division of equipment, wherein the equipment running state tree sets a corresponding function as a root node, and sets a plurality of preset function anomalies corresponding to each function as secondary nodes;
and a plurality of parameter mapping nodes are downwards extended aiming at the secondary node, each parameter mapping node is associated with a plurality of abnormal operation parameter intervals of the participating modules, and each parameter mapping node is associated with a specific preset equipment fault.
In some embodiments of the present application, a method of building a relationship influence model includes:
acquiring a past operation log of equipment, analyzing the past operation log of the equipment, screening out faults of the past equipment and fault operation parameters of the equipment, and screening out fault-free operation parameters of the past equipment;
triggering judgment of parameter mapping nodes is carried out on fault operation parameters corresponding to past equipment faults according to classification rules of an equipment operation state tree, the triggered parameter mapping nodes under the same time node are determined, the fault operation parameters at the moment are used as a first training input parameter set, and all the parameter mapping nodes triggered at the moment are used as a training output label set;
taking the screened non-fault operation parameters as a second training input parameter set, and taking the non-triggering parameter mapping nodes as training output pseudo-label sets;
and performing semi-supervised learning training based on the first training input parameter set and the training output label set and the second training input parameter set and the training output label set to generate a relationship influence model.
In some embodiments of the present application, a method for constructing a parameter transmission channel between virtual device blocks includes:
analyzing the equipment process logic, and determining the production association sequence and production contact characteristics among the equipment;
and determining the connection sequence between different virtual equipment blocks based on the production association sequence between the equipment, and determining the type of the parameter transmission channel established between the different virtual equipment blocks based on the production association characteristics.
In some embodiments of the present application, a method for comparing and analyzing real-time operation parameters transmitted in each parameter transmission channel in a set of virtual device block transmission channels to determine whether a virtual device block is abnormal includes:
setting a plurality of levels of warning thresholds for the real-time operation parameters transmitted in each parameter transmission channel, and determining a first abnormal value of the real-time operation parameters according to the warning threshold of the highest level triggered by the real-time operation parameters;
determining a second abnormal value of the parameter transmission channel according to the first abnormal values of all real-time operation parameters of the same parameter transmission channel;
and determining a third abnormal value of the virtual equipment block according to the second abnormal values of all the parameter transmission channels of the virtual equipment block, and determining the abnormal condition of the virtual equipment block according to the third abnormal value.
In some embodiments of the present application, a method of determining a third outlier of a virtual device block includes:
configuring warning reference evaluation values aiming at warning threshold values of different levels of each real-time operation parameter, and recognizing the triggered warning reference evaluation values as first abnormal reference values;
counting the first abnormal reference values corresponding to all the real-time operation parameters of the same parameter transmission channel, and determining the second abnormal reference value of the parameter transmission channel based on the first abnormal reference values corresponding to all the real-time operation parameters;
constructing an influence weight coefficient operator aiming at all parameter transmission channels corresponding to the virtual equipment block, and determining a third abnormal value of the virtual equipment block by combining a second abnormal reference value;
the expression for calculating the third outlier of the virtual device block is:
；
wherein,for the third abnormal reference value, +.>In order to influence the weight coefficient operator, r is the weight conversion coefficient, t is the number of real-time operation parameters with abnormality of the virtual equipment module, and +.>Adjusting constant for number, +.>Conversion coefficient for the outlier of the nth parameter transmission channel,>is the sum of the first abnormal reference values of all real-time operating parameters in the nth parameter transmission channel,/>The constant is adjusted for the outlier reference.
In some embodiments of the application, a power plant fault diagnosis system is also disclosed, comprising:
the equipment application map management module is used for establishing equipment application maps for equipment of a power plant, calibrating a plurality of virtual equipment blocks on the basis of the position nodes of the equipment, analyzing equipment process logic, constructing parameter transmission channels among the virtual equipment blocks on the basis of analysis results, and constructing a transmission channel set for all the parameter transmission channels connected to one virtual equipment block;
the relation analysis module is used for constructing a plurality of equipment operation state trees based on the operation logic of the equipment, wherein the equipment operation state trees comprise a plurality of parameter mapping nodes, each parameter mapping node is associated with a specific preset equipment fault, and a relation influence model is established among different parameter mapping nodes based on the influence relation among the equipment faults;
the fault analysis module is used for comparing and analyzing the real-time operation parameters transmitted in each parameter transmission channel in the virtual equipment block transmission channel set, determining whether the virtual equipment block is abnormal, substituting the real-time operation parameters corresponding to the abnormal virtual equipment block into the corresponding equipment operation state tree, determining the first equipment fault of the equipment according to the parameter mapping node to which the real-time operation parameters belong, and determining the hidden equipment characteristics of the equipment based on the relation influence model among the parameter mapping nodes.
In some embodiments of the application, the power plant fault diagnosis system further comprises:
and the display module is used for mapping the virtual equipment block on the equipment application map for characterization based on the determined first equipment fault and equipment hidden trouble characteristics of the equipment.
The application discloses a power plant fault diagnosis method and a system, which relate to the technical field of power plant management, wherein equipment of a power plant is set as virtual equipment blocks, an equipment application map is constructed and generated based on respective position nodes, parameter transmission channels are constructed among different virtual equipment blocks, monitoring analysis is carried out on the parameter transmission channels, first equipment faults of the equipment are determined, equipment hidden danger characteristics of different equipment are determined based on a relation influence model among parameter mapping nodes, and the equipment hidden danger characteristics are displayed on the equipment application map based on the determined first equipment faults and the equipment hidden danger characteristics, so that analysis and display of the equipment faults and hidden troubles of the power plant are realized, and the time for workers to take countermeasures is effectively reduced.
The technical scheme of the application is further described in detail through the drawings and the embodiments.
Drawings
Fig. 1 is a method step diagram of a power plant fault diagnosis method disclosed in an embodiment of the application.
Detailed Description
The technical scheme of the application is further described below through the attached drawings and the embodiments.
The technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings and specific embodiments, it being understood that the preferred embodiments described herein are for illustrating and explaining the present application only and are not to be construed as limiting the scope of the present application, and that some insubstantial modifications and adaptations can be made by those skilled in the art in light of the following disclosure.
Examples:
the application aims to provide a fault diagnosis method and system capable of displaying fault states and hidden danger states of various devices.
The application discloses a power plant fault diagnosis method, referring to fig. 1, comprising the following steps:
step S100, an equipment application map is established for equipment of a power plant, and a plurality of virtual equipment blocks are calibrated on the basis of the position nodes of the equipment.
It should be understood that the generation of the device application spectrum may utilize conventional graphic modeling software, and first design based on a preset size, construct a coordinate system for the generated device application spectrum, and determine, in combination with the location nodes of the device, the location of the corresponding virtual device block in the coordinate system.
Step S200, analyzing the device process logic, constructing parameter transmission channels between the virtual device blocks based on the analysis result, and constructing a transmission channel set for all the parameter transmission channels connected to one virtual device block.
It should be understood that the device process logic may include the processing sequence of the input materials by the device, or may require inter-device coordination logic for the function to be finally implemented, for example:
step a, fuel supply and treatment: depending on the type of fuel employed by the power plant, the fuel supply system delivers fuel from the storage area to the boiler or gas turbine. The fuel supply system may pre-treat the fuel, such as coal breakage, drying, coal dust production, and the like. Meanwhile, for liquid fuel and gas fuel, it is necessary to perform pressure regulation, purification, preheating, and the like.
Step b, boiler or gas turbine operation control: the operation of the boiler or gas turbine is regulated by a control system. The control system controls the supply of fuel and adjusts the temperature and pressure in the combustion process according to the power grid demand and the equipment load demand so as to maintain the stable operation of the boiler or the gas turbine.
Step c, energy conversion of steam or fuel gas: the high-temperature and high-pressure steam or gas generated by the boiler is conveyed to a steam turbine or a gas turbine through a pipeline. In a steam turbine, high temperature, high pressure steam enters a rotor formed of blades, which pushes the rotor to rotate. In the gas turbine, the gas is combusted by a combustion chamber to generate high-temperature and high-pressure gas, and the rotor composed of blades is pushed to rotate.
Step d, generator operation control: the generator is responsible for converting the mechanical energy output by the steam turbine or gas turbine into electrical energy. The operation control system of the generator monitors and adjusts the output voltage, frequency and power factor of the generator to meet the requirements of the power grid and maintain the balance of the electric energy in the power plant.
Step e, auxiliary system: the power plant also includes various auxiliary systems such as cooling water systems, water supply systems, ventilation systems, and exhaust gas treatment systems. These systems provide the necessary cooling medium, feedwater, air and treatment exhaust gas support facilities to ensure proper operation and safety of the power plant equipment.
Step S300, based on the operation logic of the equipment, constructing a plurality of equipment operation state trees, wherein the equipment operation state trees comprise a plurality of parameter mapping nodes, each parameter mapping node is associated with a specific preset equipment fault, and based on the influence relation among the equipment faults, a relation influence model is established among different parameter mapping nodes.
Step S400, comparing and analyzing the real-time operation parameters transmitted in each parameter transmission channel in the virtual equipment block transmission channel set to determine whether the virtual equipment block is abnormal.
It should be understood that the meaning of a parameter transmission channel is understood to mean that some physical medium or material is required to be transmitted from one device to another, such as steam, i.e. the parameter transmission channel is the collection and guiding path of output parameters about the physical medium or material collected from the previous device.
Step S500, substituting the real-time operation parameters corresponding to the determined abnormal virtual equipment blocks into the corresponding equipment operation state tree, determining the first equipment faults existing in the equipment according to the parameter mapping nodes to which the real-time operation parameters belong, and determining the hidden equipment characteristics of the equipment based on the relation influence model among the parameter mapping nodes.
Step S600, mapping the virtual device block on the device application map for characterization based on the determined first device failure and device hidden trouble feature of the device.
In some embodiments of the present application, a method for mapping and calibrating a virtual device block on a device application map based on a location node of a device includes:
the method comprises the steps of firstly, obtaining equipment names of applications, and finding out equipment icons of each application in a preset equipment icon set aiming at the equipment names.
And secondly, acquiring a power plant map, establishing a first reference coordinate system based on the power plant map, and calibrating vector coordinates of each device under the first reference coordinate system.
And thirdly, carrying out equal-proportion scaling on vector coordinates of different devices, and determining the relative relation between the position nodes of the different devices.
And fourthly, mapping the position nodes on the equipment application map based on the relative relation among the position nodes of different equipment, and calibrating the equipment on the equipment application map in the form of equipment labels to generate a plurality of virtual equipment blocks.
In some embodiments of the present application, the method for mapping the calibrated virtual device block on the device application map further comprises:
in the first step, a shortest limiting distance is set for the spacing between device icons.
And secondly, determining the positions of the different equipment icons relative to the application icons of the equipment, and calculating and analyzing the relative distances between the different equipment icons.
And thirdly, keeping the relative distance between the different device icons to be larger than or equal to the shortest limiting distance, and if the device icons break through the boundary of the device application map boundary, pulling the device icons breaking through the device application map boundary to the device application map boundary.
And step four, if the overlapped equipment icons exist, determining the pulling distance between the overlapped equipment icons based on the scaling of vector coordinates of different equipment, and pulling the overlapped equipment icons longitudinally or transversely according to the determined pulling distance.
The expression for calculating the distance between the overlapped equipment icons is as follows:
。
wherein,for the pull-off distance between the ith device icon and the (i+1) th device icon,/for the (i) th device icon>Is the scaling of the vector coordinates of the different devices, k is the pull-apart distance conversion coefficient, +.>The constant is adjusted for scaling.
In some embodiments of the present application, a method of building a number of device operational state trees based on the operational logic of a device includes:
the first step, the operation logic of the equipment is analyzed, and a plurality of functions of the equipment and a plurality of participation modules corresponding to each function are determined.
And secondly, constructing an equipment operation state tree aiming at each function division of the equipment, wherein the equipment operation state tree sets the corresponding function as a root node, and sets a plurality of preset function anomalies corresponding to each function as secondary nodes.
Thirdly, a plurality of parameter mapping nodes are downwards extended aiming at the secondary node, each parameter mapping node is associated with a plurality of abnormal operation parameter intervals of the participating modules, and each parameter mapping node is associated with a specific preset equipment fault.
In some embodiments of the present application, a method of building a relationship influence model includes:
the method comprises the steps of firstly, obtaining a device past operation log, analyzing the device past operation log, screening out past device faults and fault operation parameters of the device, and screening out fault-free operation parameters of the past device.
And secondly, triggering and judging the parameter mapping nodes according to the fault operation parameters corresponding to the past equipment faults and the classification rules of the equipment operation state tree, determining the parameter mapping nodes triggered at the same time, taking the fault operation parameters at the moment as a first training input parameter set, and taking all the parameter mapping nodes triggered at the moment as a training output label set.
And thirdly, taking the screened non-fault operation parameters as a second training input parameter set, and taking the non-triggering parameter mapping nodes as training output pseudo-label sets.
And fourthly, performing semi-supervised learning training based on the first training input parameter set and the training output label set, and the second training input parameter set and the training output label set to generate a relation influence model.
It should be appreciated that Semi-supervised learning (Semi-Supervised Learning) is a machine learning method that combines the learning process of labeled data and unlabeled data. In semi-supervised learning, a large amount of unlabeled or unlabeled data is utilized in addition to having a portion of the labeled training data to assist in the model training and learning process.
Semi-supervised learning aims to improve the performance and generalization ability of models by utilizing information of unlabeled data, compared to supervised learning using only labeled data and unsupervised learning using only unlabeled data. By combining tagged data and untagged data, semi-supervised learning can overcome the limitations of limited tagged data, provide more data information, and utilize the structure and distribution of untagged data for better modeling and classification.
In some embodiments of the present application, a method for constructing a parameter transmission channel between virtual device blocks includes:
first, the equipment process logic is analyzed to determine the production association sequence and the production association characteristics between the equipment.
And a second step of determining connection sequences among different virtual equipment blocks based on production association sequences among the equipment, and determining the types of parameter transmission channels established among the different virtual equipment blocks based on production association characteristics.
In some embodiments of the present application, a method for comparing and analyzing real-time operation parameters transmitted in each parameter transmission channel in a set of virtual device block transmission channels to determine whether a virtual device block is abnormal includes:
the first step, a plurality of levels of warning thresholds are set for the real-time operation parameters transmitted in each parameter transmission channel, and a first abnormal value of the real-time operation parameters is determined according to the warning threshold of the highest level triggered by the real-time operation parameters.
And a second step of determining a second abnormal value of the parameter transmission channel according to the first abnormal values of all the real-time operation parameters of the same parameter transmission channel.
And thirdly, determining a third abnormal value of the virtual equipment block for the second abnormal values of all the parameter transmission channels of the virtual equipment block, and determining the abnormal condition of the virtual equipment block according to the third abnormal value.
In some embodiments of the present application, a method of determining a third outlier of a virtual device block includes:
first, an alert reference evaluation value is configured for alert thresholds of different levels for each real-time operation parameter, and the triggered alert reference evaluation value is recognized as a first abnormal reference value.
And secondly, counting first abnormal reference values corresponding to all real-time operation parameters of the same parameter transmission channel, and determining second abnormal reference values of the parameter transmission channel based on the first abnormal reference values corresponding to all real-time operation parameters.
Thirdly, constructing an influence weight coefficient operator aiming at all parameter transmission channels corresponding to the virtual equipment block, and determining a third abnormal value of the virtual equipment block by combining the second abnormal reference value.
The expression for calculating the third outlier of the virtual device block is:
。
wherein,for the third abnormal reference value, +.>In order to influence the weight coefficient operator, r is the weight conversion coefficient, t is the number of real-time operation parameters with abnormality of the virtual equipment module, and +.>Adjusting constant for number, +.>Conversion coefficient for the outlier of the nth parameter transmission channel,>is the sum of the first abnormal reference values of all real-time operating parameters in the nth parameter transmission channel,/>The constant is adjusted for the outlier reference.
In some embodiments of the application, a power plant fault diagnosis system is also disclosed, comprising: the system comprises an equipment application map management module, a relation analysis module and a fault analysis module.
The equipment application map management module is used for establishing equipment application maps for equipment of a power plant, calibrating a plurality of virtual equipment blocks on the basis of the position nodes of the equipment, analyzing equipment process logic, constructing parameter transmission channels among the virtual equipment blocks on the basis of analysis results, and constructing a transmission channel set for all the parameter transmission channels connected to one virtual equipment block;
the relation analysis module is used for constructing a plurality of equipment operation state trees based on the operation logic of the equipment, wherein the equipment operation state trees comprise a plurality of parameter mapping nodes, each parameter mapping node is associated with a specific preset equipment fault, and a relation influence model is established among different parameter mapping nodes based on the influence relation among the equipment faults;
the fault analysis module is used for comparing and analyzing the real-time operation parameters transmitted in each parameter transmission channel in the virtual equipment block transmission channel set, determining whether the virtual equipment block is abnormal, substituting the real-time operation parameters corresponding to the abnormal virtual equipment block into the corresponding equipment operation state tree, determining the first equipment fault of the equipment according to the parameter mapping node to which the real-time operation parameters belong, and determining the hidden equipment characteristics of the equipment based on the relation influence model among the parameter mapping nodes.
In some embodiments of the application, the power plant fault diagnosis system further comprises: and the display module is used for mapping the virtual equipment block on the equipment application map for characterization based on the determined first equipment fault and equipment hidden trouble characteristics of the equipment.
The application discloses a power plant fault diagnosis method and a system, which relate to the technical field of power plant management, wherein equipment of a power plant is set as virtual equipment blocks, an equipment application map is constructed and generated based on respective position nodes, parameter transmission channels are constructed among different virtual equipment blocks, monitoring analysis is carried out on the parameter transmission channels, first equipment faults of the equipment are determined, equipment hidden danger characteristics of different equipment are determined based on a relation influence model among parameter mapping nodes, and the equipment hidden danger characteristics are displayed on the equipment application map based on the determined first equipment faults and the equipment hidden danger characteristics, so that analysis and display of the equipment faults and hidden troubles of the power plant are realized, and the time for workers to take countermeasures is effectively reduced.
From the above description of the embodiments, it will be clear to those skilled in the art that the present application may be implemented in hardware, or may be implemented by means of software plus necessary general hardware platforms. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.), and includes several instructions for causing a computer device (may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective implementation scenario of the present application.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application and not for limiting it, and although the present application has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that: the technical scheme of the application can be modified or replaced by the same, and the modified technical scheme cannot deviate from the spirit and scope of the technical scheme of the application.
Claims (10)
1. A power plant fault diagnosis method, comprising:
establishing an equipment application map aiming at equipment of a power plant, and mapping and calibrating a plurality of virtual equipment blocks on the equipment application map based on position nodes of the equipment;
analyzing the equipment process logic, constructing parameter transmission channels among the virtual equipment blocks based on an analysis result, and constructing a transmission channel set aiming at all the parameter transmission channels connected to one virtual equipment block;
based on the operation logic of the equipment, constructing a plurality of equipment operation state trees, wherein the equipment operation state trees comprise a plurality of parameter mapping nodes, each parameter mapping node is associated with a specific preset equipment fault, and based on the influence relation among the equipment faults, a relation influence model is established among different parameter mapping nodes;
comparing and analyzing real-time operation parameters transmitted in each parameter transmission channel in the virtual equipment block transmission channel set, and determining whether the virtual equipment block is abnormal;
substituting the real-time operation parameters corresponding to the abnormal virtual equipment blocks into corresponding equipment operation state trees, determining a first equipment fault existing in equipment according to the parameter mapping nodes to which the real-time operation parameters belong, and determining equipment hidden danger characteristics of the equipment based on a relation influence model among the parameter mapping nodes;
and mapping the virtual equipment block on the equipment application map for characterization based on the determined first equipment fault and equipment hidden trouble characteristics of the equipment.
2. The power plant fault diagnosis method according to claim 1, wherein the method for mapping and calibrating the virtual equipment blocks on the equipment application map based on the location nodes of the equipment comprises the following steps:
acquiring an equipment directory of an application, and finding out an equipment icon of each application in a preset equipment icon set aiming at the equipment directory;
acquiring a power plant map, establishing a first reference coordinate system based on the power plant map, and calibrating vector coordinates of each device under the first reference coordinate system;
scaling the vector coordinates of different devices in equal proportion to determine the relative relation between the position nodes of different devices;
mapping the position nodes on the equipment application map based on the relative relation between the position nodes of different equipment, and calibrating the equipment on the equipment application map in the form of equipment icons to generate a plurality of virtual equipment blocks.
3. The power plant fault diagnosis method according to claim 2, wherein the method for mapping and calibrating the virtual equipment blocks on the equipment application map further comprises:
setting the shortest limiting distance for the distance between the device icons;
determining the map positions of different equipment icons relative to the equipment application maps, and calculating and analyzing the relative distances between the different equipment icons;
maintaining the relative distance between the different device icons to be greater than or equal to the shortest limiting distance, and if the device icons break through the boundary of the device application map boundary, pulling the device icons breaking through the device application map boundary to the device application map boundary;
if the overlapped equipment icons exist, determining the pulling distance between the overlapped equipment icons based on the scaling of vector coordinates of different equipment, and pulling the overlapped equipment icons longitudinally or transversely according to the determined pulling distance;
the expression for calculating the distance between the overlapped equipment icons is as follows:
；
wherein,for the pull-off distance between the ith device icon and the (i+1) th device icon,/for the (i) th device icon>Is the scaling of the vector coordinates of the different devices, k is the pull-apart distance conversion coefficient, +.>The constant is adjusted for scaling.
4. The power plant fault diagnosis method according to claim 1, wherein the method of constructing a plurality of plant operation status trees based on the operation logic of the plant comprises:
analyzing the operation logic of the equipment, and determining a plurality of functions of the equipment and a plurality of participation modules corresponding to each function;
constructing an equipment running state tree aiming at each function division of equipment, wherein the equipment running state tree sets a corresponding function as a root node, and sets a plurality of preset function anomalies corresponding to each function as secondary nodes;
and a plurality of parameter mapping nodes are downwards extended aiming at the secondary node, each parameter mapping node is associated with a plurality of abnormal operation parameter intervals of the participating modules, and each parameter mapping node is associated with a specific preset equipment fault.
5. The power plant fault diagnosis method as claimed in claim 4, wherein the method for establishing the relationship influence model comprises:
acquiring a past operation log of equipment, analyzing the past operation log of the equipment, screening out faults of the past equipment and fault operation parameters of the equipment, and screening out fault-free operation parameters of the past equipment;
triggering judgment of parameter mapping nodes is carried out on fault operation parameters corresponding to past equipment faults according to classification rules of an equipment operation state tree, the triggered parameter mapping nodes under the same time node are determined, the fault operation parameters at the moment are used as a first training input parameter set, and all the parameter mapping nodes triggered at the moment are used as a training output label set;
taking the screened non-fault operation parameters as a second training input parameter set, and taking the non-triggering parameter mapping nodes as training output pseudo-label sets;
and performing semi-supervised learning training based on the first training input parameter set and the training output label set and the second training input parameter set and the training output label set to generate a relationship influence model.
6. The power plant fault diagnosis method according to claim 1, wherein the method of constructing the parameter transmission channel between the virtual equipment blocks comprises:
analyzing the equipment process logic, and determining the production association sequence and production contact characteristics among the equipment;
and determining the connection sequence between different virtual equipment blocks based on the production association sequence between the equipment, and determining the type of the parameter transmission channel established between the different virtual equipment blocks based on the production association characteristics.
7. The power plant fault diagnosis method according to claim 1, wherein the method for comparing and analyzing the real-time operation parameters transmitted in each parameter transmission channel in the set of virtual equipment block transmission channels to determine whether the virtual equipment block is abnormal comprises:
setting a plurality of levels of warning thresholds for the real-time operation parameters transmitted in each parameter transmission channel, and determining a first abnormal value of the real-time operation parameters according to the warning threshold of the highest level triggered by the real-time operation parameters;
determining a second abnormal value of the parameter transmission channel according to the first abnormal values of all real-time operation parameters of the same parameter transmission channel;
and determining a third abnormal value of the virtual equipment block according to the second abnormal values of all the parameter transmission channels of the virtual equipment block, and determining the abnormal condition of the virtual equipment block according to the third abnormal value.
8. The power plant fault diagnosis method according to claim 7, wherein the method of determining the third outlier of the virtual equipment block comprises:
configuring warning reference evaluation values aiming at warning threshold values of different levels of each real-time operation parameter, and recognizing the triggered warning reference evaluation values as first abnormal reference values;
counting the first abnormal reference values corresponding to all the real-time operation parameters of the same parameter transmission channel, and determining the second abnormal reference value of the parameter transmission channel based on the first abnormal reference values corresponding to all the real-time operation parameters;
constructing an influence weight coefficient operator aiming at all parameter transmission channels corresponding to the virtual equipment block, and determining a third abnormal value of the virtual equipment block by combining a second abnormal reference value;
the expression for calculating the third outlier of the virtual device block is:
；
wherein,for the third abnormal reference value, +.>In order to influence the weight coefficient operator, r is the weight conversion coefficient, t is the number of real-time operation parameters with abnormality of the virtual equipment module, and +.>Adjusting constant for number, +.>Conversion coefficient for the outlier of the nth parameter transmission channel,>is the sum of the first abnormal reference values of all real-time operating parameters in the nth parameter transmission channel,/>The constant is adjusted for the outlier reference.
9. A power plant fault diagnosis system, comprising:
the equipment application map management module is used for establishing equipment application maps for equipment of a power plant, calibrating a plurality of virtual equipment blocks on the basis of the position nodes of the equipment, analyzing equipment process logic, constructing parameter transmission channels among the virtual equipment blocks on the basis of analysis results, and constructing a transmission channel set for all the parameter transmission channels connected to one virtual equipment block;
the relation analysis module is used for constructing a plurality of equipment operation state trees based on the operation logic of the equipment, wherein the equipment operation state trees comprise a plurality of parameter mapping nodes, each parameter mapping node is associated with a specific preset equipment fault, and a relation influence model is established among different parameter mapping nodes based on the influence relation among the equipment faults;
the fault analysis module is used for comparing and analyzing the real-time operation parameters transmitted in each parameter transmission channel in the virtual equipment block transmission channel set, determining whether the virtual equipment block is abnormal, substituting the real-time operation parameters corresponding to the abnormal virtual equipment block into the corresponding equipment operation state tree, determining the first equipment fault of the equipment according to the parameter mapping node to which the real-time operation parameters belong, and determining the hidden equipment characteristics of the equipment based on the relation influence model among the parameter mapping nodes.
10. The power plant fault diagnosis system according to claim 9, further comprising:
and the display module is used for mapping the virtual equipment block on the equipment application map for characterization based on the determined first equipment fault and equipment hidden trouble characteristics of the equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311403606.5A CN117149498B (en) | 2023-10-27 | 2023-10-27 | Power plant fault diagnosis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311403606.5A CN117149498B (en) | 2023-10-27 | 2023-10-27 | Power plant fault diagnosis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117149498A true CN117149498A (en) | 2023-12-01 |
| CN117149498B CN117149498B (en) | 2024-03-01 |
Family
ID=88904596
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311403606.5A Active CN117149498B (en) | 2023-10-27 | 2023-10-27 | Power plant fault diagnosis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117149498B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117421567A (en) * | 2023-12-19 | 2024-01-19 | 华能济南黄台发电有限公司 | Power plant energy management method and system applied to city |
| CN117934248A (en) * | 2024-03-25 | 2024-04-26 | 山东汇通创软信息技术有限公司 | Power plant safety management and control platform data analysis method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537484A (en) * | 2014-12-22 | 2015-04-22 | 国家电网公司 | Power grid load loss risk assessment method based on PSASP model and emergency power supply automatic throw-in strategy |
| CN112307218A (en) * | 2020-10-21 | 2021-02-02 | 浙江大学 | Intelligent power plant typical equipment fault diagnosis knowledge base construction method based on knowledge graph |
| CN113741368A (en) * | 2021-09-06 | 2021-12-03 | 华能信息技术有限公司 | Power enterprise safety production management method based on management and control of Internet of things |
| WO2021259002A1 (en) * | 2020-06-23 | 2021-12-30 | 平安科技（深圳）有限公司 | Decision tree-based method and apparatus for outputting abnormal data sources, and computer device |
| CN114137915A (en) * | 2021-11-18 | 2022-03-04 | 成都航天科工大数据研究院有限公司 | Fault diagnosis method for industrial equipment |
| CN115562143A (en) * | 2022-10-19 | 2023-01-03 | 北京好利阀业集团有限公司 | Valve remote fault monitoring method and system based on Internet of things |
| CN115638875A (en) * | 2022-11-14 | 2023-01-24 | 国家电投集团河南电力有限公司技术信息中心 | Power plant equipment fault diagnosis method and system based on map analysis |
| CN116756909A (en) * | 2023-04-18 | 2023-09-15 | 西安西热控制技术有限公司 | Early warning diagnosis system of thermal power plant based on data model and mechanism model |
-
2023
- 2023-10-27 CN CN202311403606.5A patent/CN117149498B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537484A (en) * | 2014-12-22 | 2015-04-22 | 国家电网公司 | Power grid load loss risk assessment method based on PSASP model and emergency power supply automatic throw-in strategy |
| WO2021259002A1 (en) * | 2020-06-23 | 2021-12-30 | 平安科技（深圳）有限公司 | Decision tree-based method and apparatus for outputting abnormal data sources, and computer device |
| CN112307218A (en) * | 2020-10-21 | 2021-02-02 | 浙江大学 | Intelligent power plant typical equipment fault diagnosis knowledge base construction method based on knowledge graph |
| CN113741368A (en) * | 2021-09-06 | 2021-12-03 | 华能信息技术有限公司 | Power enterprise safety production management method based on management and control of Internet of things |
| CN114137915A (en) * | 2021-11-18 | 2022-03-04 | 成都航天科工大数据研究院有限公司 | Fault diagnosis method for industrial equipment |
| CN115562143A (en) * | 2022-10-19 | 2023-01-03 | 北京好利阀业集团有限公司 | Valve remote fault monitoring method and system based on Internet of things |
| CN115638875A (en) * | 2022-11-14 | 2023-01-24 | 国家电投集团河南电力有限公司技术信息中心 | Power plant equipment fault diagnosis method and system based on map analysis |
| CN116756909A (en) * | 2023-04-18 | 2023-09-15 | 西安西热控制技术有限公司 | Early warning diagnosis system of thermal power plant based on data model and mechanism model |
Non-Patent Citations (4)
| Title |
|---|
| ZHANG SHILING ETC.: "Time Series Prediction and Pattern Recognition of Fault Decomposition Gas for High Voltage Composite Electrical Appliances Based on Grey System OBGM (1, N) Model", 2019 IEEE 5TH INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATIONS (ICCC) * |
| 任岩;闫素英;万元;胡边;龚传利;: "基于3D虚拟现实技术的风电场全数字化巡检及监测平台", 可再生能源, no. 10 * |
| 卿子龙 等: "海上风电场换流站智慧型监控管理***", 分布式能源, vol. 8, no. 3 * |
| 赵倩;: "数控设备故障知识图谱的构建与应用", 航空制造技术, no. 03 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117421567A (en) * | 2023-12-19 | 2024-01-19 | 华能济南黄台发电有限公司 | Power plant energy management method and system applied to city |
| CN117421567B (en) * | 2023-12-19 | 2024-03-08 | 华能济南黄台发电有限公司 | Power plant energy management method and system applied to city |
| CN117934248A (en) * | 2024-03-25 | 2024-04-26 | 山东汇通创软信息技术有限公司 | Power plant safety management and control platform data analysis method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117149498B (en) | 2024-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117149498B (en) | Power plant fault diagnosis method and system | |
| Zaher et al. | Online wind turbine fault detection through automated SCADA data analysis | |
| Park et al. | Development of a novel power curve monitoring method for wind turbines and its field tests | |
| CN103400302B (en) | A kind of wind power base cascading failure risk perceptions method for early warning | |
| Teng et al. | DNN‐based approach for fault detection in a direct drive wind turbine<? show [AQ ID= Q1]?> | |
| CN105134510A (en) | State monitoring and failure diagnosis method for wind generating set variable pitch system | |
| JP6173946B2 (en) | Power system monitoring apparatus, power system control apparatus, and power system monitoring method | |
| CN108072524B (en) | Wind turbine generator gearbox bearing fault early warning method | |
| Hu et al. | Using domain knowledge features for wind turbine diagnostics | |
| CN116660672B (en) | Power grid equipment fault diagnosis method and system based on big data | |
| CN104005917A (en) | Method and system for predicting wind machine state based on Bayesian reasoning mode | |
| EP4038462A1 (en) | System and method for fusing multiple analytics of a wind turbine for improved efficiency | |
| Du et al. | A SCADA data based anomaly detection method for wind turbines | |
| CN106950926B (en) | System and method for controlling and monitoring a power generation facility | |
| CN116624341A (en) | Wind turbine generator power abnormality diagnosis method, system and equipment | |
| Zhang et al. | Wind turbine condition monitoring based on bagging ensemble strategy and KNN algorithm | |
| CN108074045B (en) | Wind turbine generator complete machine vulnerability analysis and fault sequencing method and electronic terminal | |
| Kumar et al. | Performance evaluation of a coal-fired power plant | |
| JP6554162B2 (en) | Power plant performance evaluation method and power plant performance evaluation program | |
| CN116011332A (en) | Wind turbine generator system state monitoring method based on GAN-QP feature migration model | |
| Pandit et al. | Comparison of binned and Gaussian Process based wind turbine power curves for condition monitoring purposes | |
| Wei et al. | Wind turbine pitch system condition monitoring based on performance curves in multiple states | |
| McKinnon et al. | Investigation of anomaly detection technique for wind turbine pitch systems | |
| Mary | Fault Diagnosis and Control Techniques for Wind Energy Conversion System: A Systematic Review | |
| Sompura et al. | A practical approach to improve alarm system performance: Application to power plant |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |