CN117010191A - Abnormal state identification method and system for hydroelectric generating set - Google Patents
Abnormal state identification method and system for hydroelectric generating set Download PDFInfo
- Publication number
- CN117010191A CN117010191A CN202310978913.XA CN202310978913A CN117010191A CN 117010191 A CN117010191 A CN 117010191A CN 202310978913 A CN202310978913 A CN 202310978913A CN 117010191 A CN117010191 A CN 117010191A
- Authority
- CN
- China
- Prior art keywords
- state
- index
- abnormal
- representation
- parameter set
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 209
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012544 monitoring process Methods 0.000 claims abstract description 117
- 238000012545 processing Methods 0.000 claims abstract description 33
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 31
- 230000001105 regulatory effect Effects 0.000 claims abstract description 6
- 238000012512 characterization method Methods 0.000 claims description 55
- 230000005856 abnormality Effects 0.000 claims description 30
- 238000007781 pre-processing Methods 0.000 claims description 22
- 238000004458 analytical method Methods 0.000 claims description 20
- 230000009467 reduction Effects 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 11
- 238000005452 bending Methods 0.000 claims description 10
- 238000013064 process characterization Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 5
- 230000010349 pulsation Effects 0.000 claims description 5
- 238000007621 cluster analysis Methods 0.000 claims description 4
- 230000001276 controlling effect Effects 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 4
- 238000009877 rendering Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 7
- 230000000694 effects Effects 0.000 abstract description 5
- 230000000007 visual effect Effects 0.000 description 6
- 238000001914 filtration Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 229910052799 carbon Inorganic materials 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/20—Hydro energy
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Probability & Statistics with Applications (AREA)
- Control Of Water Turbines (AREA)
Abstract
The invention provides a method and a system for identifying abnormal states of a hydroelectric generating set, and relates to the technical field of data processing, wherein the method comprises the following steps: obtaining a predetermined monitoring category; obtaining a target real-time operation parameter set; randomly extracting a first parameter set; obtaining a first state index; if the first state index does not accord with a first preset index threshold value, analyzing and identifying the first parameter set to obtain a first abnormal prediction result; the method is characterized in that the target water turbine generator set is regulated and controlled, so that the technical problems of the prior art that the monitoring index is set more singly, the monitoring index is not scientific and is not enough in pertinence, and the monitoring positioning accuracy and the refinement of abnormal faults are further caused are solved, the abnormal identification of different parts of the target water turbine generator set is realized, the unit part can be subjected to pertinence overhaul and maintenance, the accuracy and the pertinence of the abnormal identification are improved, and the technical effect of the abnormal identification efficiency is further improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a system for identifying abnormal states of a hydroelectric generating set.
Background
Along with popularization of low-carbon environment-friendly concepts, hydroelectric power generation becomes an important component in a power generation system, and a hydroelectric generating set is an important device for carrying out hydroelectric power generation.
In summary, in the prior art, the monitoring index is set more singly, and the monitoring index is set scientifically and pertinently not enough, so that the technical problems of insufficient monitoring and positioning accuracy and refinement of abnormal faults are caused.
Disclosure of Invention
The invention provides a method and a system for identifying abnormal states of a hydroelectric generating set, which are used for solving the technical problems that in the prior art, the setting of monitoring indexes is single, the setting of the monitoring indexes is not scientific and the pertinence is insufficient, and further, the monitoring and positioning accuracy and the refinement of abnormal faults are insufficient.
According to a first aspect of the present invention, there is provided a method for identifying an abnormal state of a hydro-generator set, including: analyzing the historical abnormal state records of the similar units of the target hydroelectric generating set to obtain an abnormal state representation category set, and taking the abnormal state representation category set as a preset monitoring category; performing real-time state monitoring on the target hydroelectric generating set based on the preset monitoring category to obtain a target real-time operation parameter set; randomly extracting any one operation parameter set in the target real-time operation parameter set, and recording the operation parameter set as a first parameter set, wherein the first parameter set is provided with an identifier of a first monitoring category; analyzing the first parameter set through a first estimation channel in the state estimator to obtain a first state index; if the first state index does not accord with a first preset index threshold value, starting an abnormality identification unit to analyze and identify the first parameter set to obtain a first abnormality prediction result; and regulating and controlling the target hydroelectric generating set according to the first abnormal prediction result.
According to a second aspect of the present invention, there is provided an abnormal state identification system of a hydro-generator set, comprising: the system comprises a preset monitoring category determining module, a target hydroelectric generating set, a monitoring category determining module and a monitoring category determining module, wherein the preset monitoring category determining module is used for analyzing historical abnormal state records of similar units of the target hydroelectric generating set to obtain an abnormal state representation category set, and the abnormal state representation category set is used as a preset monitoring category; the real-time state monitoring module is used for monitoring the real-time state of the target water turbine generator set based on the preset monitoring category to obtain a target real-time operation parameter set; the operation parameter extraction module is used for randomly extracting any one operation parameter set in the target real-time operation parameter set and recording the operation parameter set as a first parameter set, wherein the first parameter set is provided with an identifier of a first monitoring category; the state analysis module is used for analyzing the first parameter set through a first estimation channel in the state estimator to obtain a first state index; the abnormality prediction module is used for starting an abnormality identification unit to analyze and identify the first parameter set if the first state index does not accord with a first preset index threshold value, so as to obtain a first abnormality prediction result; and the regulation and control processing module is used for carrying out regulation and control processing on the target hydroelectric generating set according to the first abnormal prediction result.
According to one or more technical schemes provided by the invention, the following technical effects can be achieved:
1. the method comprises the steps of analyzing historical abnormal state records of similar units of a target hydroelectric generating set to obtain an abnormal state representation category set, taking the abnormal state representation category set as a preset monitoring category, carrying out real-time state monitoring on the target hydroelectric generating set based on the preset monitoring category to obtain a target real-time operation parameter set, randomly extracting any one operation parameter set in the target real-time operation parameter set, and recording the operation parameter set as a first parameter set, wherein the first parameter set is provided with a first monitoring category identification, analyzing the first parameter set through a first estimation channel in a state estimator to obtain a first state index, starting an abnormal recognition unit to carry out analysis and recognition on the first parameter set to obtain a first abnormal prediction result, carrying out regulation and control treatment on the target hydroelectric generating set according to the first abnormal prediction result, carrying out targeted overhaul and maintenance on different parts of the target hydroelectric generating set, and further improving the accuracy and pertinence of the abnormal recognition efficiency.
2. Extracting a first historical record in the historical abnormal state records, wherein the first historical record comprises first abnormal fault representation information of a first abnormal fault, a historical abnormal fault representation information set is built based on the first abnormal fault representation information, clustering analysis is carried out on the historical abnormal fault representation information set based on a preset clustering scheme to obtain a clustering result, the clustering result comprises a plurality of clustering clusters with representation type identifiers, the abnormal state representation type set is built according to the clustering result, the purpose of conveniently carrying out state monitoring analysis on a target water turbine generator set according to a preset monitoring type in a targeted mode is achieved, irrelevant data is prevented from being monitored, waste of monitoring resources is avoided, and then the accuracy and the recognition efficiency of abnormal state recognition are improved.
3. A digital twin model of the target hydroelectric generating set is constructed, if the first state index accords with a first preset index threshold value, a first monitoring category is marked, if the first state index does not accord with the first preset index threshold value, a second monitoring category is marked, wherein the first mark is a finger-like normal mark, the state normal mark is provided with an identification of the first state index, the second mark is a finger-like abnormal mark, the state abnormal mark is provided with an identification of the first state index, the first mark or the second mark is rendered to the digital twin model, the digital twin model is used for carrying out visual display on the states of all parts of the target hydroelectric generating set, visual display on the abnormal states is achieved, and the technical effects that staff can clearly know the abnormal parts and the state index of the target hydroelectric generating set conveniently are achieved, so that overhaul and maintenance are timely carried out are achieved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following brief description will be given of the drawings used in the description of the embodiments or the prior art, it being obvious that the drawings in the description below are only exemplary and that other drawings can be obtained from the drawings provided without the inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for identifying abnormal states of a water turbine generator set according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of constructing an abnormal state characterization category set in an abnormal state identification method of a water turbine generator set according to the present invention;
fig. 3 is a schematic flow chart of visually displaying states of each component of a target hydroelectric generating set in the abnormal state identification method of a hydroelectric generating set according to the present invention;
fig. 4 is a schematic structural diagram of an abnormal state identification system of a water turbine generator set according to an embodiment of the present invention.
Reference numerals illustrate: the system comprises a scheduled monitoring category determining module 11, a real-time state monitoring module 12, an operation parameter extracting module 13, a state analyzing module 14, an abnormality predicting module 15 and a regulating and controlling processing module 16.
Detailed Description
Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Example 1
Fig. 1 is a diagram of an abnormal state identification method of a water turbine generator set according to an embodiment of the present invention, where the method is applied to an abnormal state identification system of a water turbine generator set, and the system is communicatively connected to a state estimator, and the method includes:
step S100: analyzing the historical abnormal state records of the similar units of the target hydroelectric generating set to obtain an abnormal state representation category set, and taking the abnormal state representation category set as a preset monitoring category;
As shown in fig. 2, step S100 of the embodiment of the present invention further includes:
step S110: extracting a first history record in the history abnormal state records, wherein the first history record comprises first abnormal fault characterization information of a first abnormal fault;
step S120: constructing a historical abnormal fault characterization information set based on the first abnormal fault characterization information;
step S130: performing cluster analysis on the historical abnormal fault representation information set based on a preset cluster scheme to obtain a cluster result, wherein the cluster result comprises a plurality of cluster clusters with representation type destination identifiers;
step S140: and constructing the abnormal state representation category set according to the clustering result.
Specifically, the abnormal state identification method of the hydroelectric generating set provided by the embodiment of the invention is applied to an abnormal state identification system of the hydroelectric generating set, wherein the abnormal state identification system is a system platform for executing the abnormal state identification method of the hydroelectric generating set, the system is in communication connection with a state estimator, and the state estimator is a model for analyzing the running state of the hydroelectric generating set.
The method comprises the steps of analyzing historical abnormal state records of similar units of a target hydroelectric generating set to obtain an abnormal state representation category set, wherein the target hydroelectric generating set is any hydroelectric generating set to be subjected to abnormal state identification, the historical abnormal state records refer to abnormal record data when the same type unit of the target hydroelectric generating set is subjected to abnormal monitoring in a past period of time, the abnormal record data can be directly acquired through a power plant where the target hydroelectric generating set is located, the abnormal state representation category set comprises abnormal types of different parts of the target hydroelectric generating set, and the specific analysis process is as follows:
extracting a first history record in the history abnormal state records, wherein the first history record generally refers to any record in the history abnormal state records, the first history record comprises first abnormal fault representation information of a first abnormal fault, such as when a hydro-generator set has cavitation faults, the pressure of each point of an overcurrent part is larger than a preset pressure range, the cavitation faults are first abnormal faults, the pressure of each point of the overcurrent part is larger than the preset pressure range, the first abnormal fault representation information is the first abnormal fault representation information, the first abnormal fault represents the abnormal fault type, and the first abnormal fault representation information represents abnormal operation parameters in the target hydro-generator set when the first abnormal fault occurs. And combining the falling historical abnormal fault representation information set according to the first abnormal fault representation information in the plurality of historical records. And further carrying out cluster analysis on the historical abnormal fault representation information set based on a preset cluster scheme to obtain a cluster result, wherein the cluster result comprises a plurality of cluster clusters with representation category identifiers, the preset cluster scheme is to cluster according to the abnormal representation components of the historical abnormal fault representation information, for example, the historical abnormal fault representation information of the abnormal overcurrent component is aggregated together to be used as a cluster, the historical abnormal fault representation information of the abnormal frame state is aggregated together, and the like, the cluster clusters are marked according to the representation category (namely the abnormal representation component) during the clustering, the cluster result is used as a cluster result, the abnormal state representation category set is further constructed according to the cluster result, and the abnormal state representation category set comprises a plurality of abnormal representation positions, namely, the representation category marking result of the cluster clusters. The abnormal state representation category set comprises a frame state, a frame shafting, hydraulic energy, an overcurrent component state, a working condition process and a unit temperature, and the frame is a component for installing a generator bearing. The abnormal state characterization category set is used as a preset monitoring category, so that the historical abnormal state record is analyzed to obtain the preset monitoring category, the state monitoring analysis of the target hydroelectric generating set can be conveniently and pertinently carried out according to the preset monitoring category, the irrelevant data is prevented from being monitored, the waste of monitoring resources is avoided, and the accuracy and the recognition efficiency of abnormal state recognition are improved.
Step S200: performing real-time state monitoring on the target hydroelectric generating set based on the preset monitoring category to obtain a target real-time operation parameter set;
the step S200 of the embodiment of the present invention further includes:
step S210: analyzing and determining a frame state representation index of the frame state, wherein the frame state representation index refers to frame vibration signal characteristics;
step S220: analyzing and constructing a frame shafting characterization index set of the frame shafting, wherein the frame shafting characterization index set comprises a large-shaft swing degree, a dynamic bending amount of a unit axis and a bending azimuth angle;
step S230: analyzing and constructing a hydraulic energy representation index set of the hydraulic energy, wherein the hydraulic energy representation index set comprises unit relative efficiency, machine-passing flow and water consumption rate;
step S240: analyzing and constructing an overcurrent component state characterization index set of the overcurrent component state, wherein the overcurrent component state characterization index set comprises a measuring point pressure and a measuring point pressure pulsation value;
step S250: analyzing and constructing a working condition process characterization index set of the working condition process, wherein the working condition process characterization index set comprises rotor current, voltage, unit rotating speed, power, guide vane opening, water head and generator outlet switch state;
Step S260: analyzing and constructing a unit temperature representation index set of the unit temperature, wherein the unit temperature representation index set comprises thrust bearing temperature, cooler temperature, guide bearing bush temperature, stator temperature and oil temperature;
step S270: and taking the frame state representation index, the frame shafting representation index set, the hydraulic energy representation index set, the overcurrent part state representation index set, the working condition process representation index set and the unit temperature representation index set as preset monitoring index sets of the preset monitoring category.
Specifically, the real-time state monitoring is performed on the target water turbine generator set based on the predetermined monitoring category, so as to obtain a target real-time operation parameter set, the predetermined monitoring category includes a unit part to be detected, such as a frame state, a frame shafting, hydraulic energy, an overcurrent part state, a working condition process, and a unit temperature, before the real-time state monitoring is performed, specific monitoring indexes, that is, monitoring indexes, such as temperature, vibration frequency, and the like, need to be determined, as predetermined monitoring indexes, the operation data of the target water turbine generator set is acquired through the predetermined monitoring indexes, and the acquired monitoring index parameters form the target real-time operation parameter set, so as to be used for representing the operation state of the target water turbine generator set, and the specific process is as follows:
The frame state representation index of the frame state is analyzed and determined, wherein the frame state representation index refers to frame vibration signal characteristics, specifically, by analyzing historical abnormal fault representation information contained in a cluster corresponding to the frame state, it can be obtained that when the vibration frequency of the frame is abnormal, the frame state is abnormal, so that the frame vibration signal characteristics are used as frame state representation indexes, and the frame state can be analyzed by subsequently acquiring the vibration signals of the frame. Similarly, when the frame shafting has abnormal faults, the large-axis swing degree, the dynamic bending amount of the unit axis and the bending azimuth angle deviate from normal values, so that the frame shafting characterization index set comprises the large-axis swing degree, the dynamic bending amount of the unit axis and the bending azimuth angle; the abnormality of the hydraulic energy can be characterized according to the relative efficiency, the machine-passing flow and the water consumption rate of the machine set, so that the hydraulic energy characterization index set comprises the relative efficiency, the machine-passing flow and the water consumption rate of the machine set; the running state of the overcurrent component can be represented by the measuring point pressure and the measuring point pressure pulsation value, so that the state representation index set of the overcurrent component comprises the measuring point pressure and the measuring point pressure pulsation value; determining a working condition process state by analyzing rotor current, voltage, unit rotating speed, power, guide vane opening, water head and generator outlet switch state, so that the working condition process characterization index set comprises rotor current, voltage, unit rotating speed, power, guide vane opening, water head and generator outlet switch state; the unit temperature comprises the temperatures of different parts of the unit, so that the unit temperature representation index set comprises the thrust bearing temperature, the cooler temperature, the guide bearing bush temperature, the stator temperature and the oil temperature.
The frame state characterization index, the frame shafting characterization index set, the hydraulic energy characterization index set, the overcurrent component state characterization index set, the working condition process characterization index set and the unit temperature characterization index set are used as preset monitoring index sets of preset monitoring categories, further, a temperature sensor, a vibration sensor, a pressure sensor, a water flow sensor, a current and voltage sensor and the like can be arranged at corresponding positions of a target hydroelectric generating set according to the preset monitoring index sets, the acquisition result is a target real-time operation parameter set, the target real-time operation parameter set comprises a plurality of operation parameter sets, each operation parameter set represents acquisition data of the characterization index set, for example, the monitoring index parameter acquired according to the frame state characterization index is used as one operation parameter set, the data acquired according to the frame shafting characterization index set is used as another operation parameter set, and accordingly, the frame state characterization index, the frame characterization index set, the hydraulic energy characterization index set, the overcurrent component state characterization index set, the temperature characterization index set and the hydraulic energy characterization index set are acquired at corresponding positions of the target hydroelectric generating set, the corresponding operation parameter sets are respectively, and the real-time analysis is realized.
Step S300: randomly extracting any one operation parameter set in the target real-time operation parameter set, and recording the operation parameter set as a first parameter set, wherein the first parameter set is provided with an identifier of a first monitoring category;
the step S300 of the embodiment of the present invention further includes:
step S310: if the first parameter set is the vibration signal characteristic information of the frame vibration signal characteristic, calling a preset processing scheme;
step S320: and carrying out noise reduction processing on the vibration signal characteristic information according to the preset processing scheme to obtain an information noise reduction result, and taking the information noise reduction result as the first parameter set.
Specifically, any one of the target real-time operation parameter sets is randomly extracted and is recorded as a first parameter set, wherein the first parameter set is provided with an identifier of a first monitoring category, that is, a predetermined monitoring category is marked to the first parameter set according to the monitoring category to which the extracted operation parameter set belongs, for example, if the operation parameter set corresponding to the state characterization index set of the overcurrent element is extracted, the overcurrent element is marked to the first parameter set.
It should be noted that, if the extracted first parameter set is an operation parameter set corresponding to the frame shafting characterization index set, the hydraulic energy characterization index set, the overcurrent component state characterization index set, the working condition process characterization index set and the unit temperature characterization index set, the first parameter set may be used as the first parameter set as long as the first monitoring category is identified according to the predetermined monitoring category. However, if the first parameter set is an operation parameter set corresponding to the frame state representation index, that is, the first parameter is vibration signal feature information of the frame vibration signal feature, a predetermined processing scheme needs to be called, noise reduction processing is performed on the vibration signal feature information according to the predetermined processing scheme to obtain an information noise reduction result, in short, the vibration signal can be interfered by environmental electromagnetic, unit strong noise and the like, the collected vibration signal feature information contains multiple kinds of interference, therefore, noise reduction processing is performed on the vibration signal feature information to eliminate or weaken interference of other noise, specifically, the noise reduction processing can be performed through the existing filtering methods such as median filtering and mean filtering, and the like, and the noise reduction method in the predetermined processing scheme can be determined by a person skilled in the art according to actual conditions by taking the noise reduction method as the predetermined processing scheme, the noise reduction result of the processed vibration signal feature information is the information noise reduction result, and the information noise reduction result is taken as the first parameter set, so that the collection accuracy of monitoring data is ensured, and the unit abnormal recognition accuracy is further improved.
Step S400: analyzing the first parameter set through a first estimation channel in the state estimator to obtain a first state index;
the step S400 of the embodiment of the present invention further includes:
step S410: extracting a first numerical parameter in the first parameter set, and performing decimal scaling normalization processing on the first numerical parameter to obtain a first preprocessing parameter;
step S420: extracting a first classification parameter in the first parameter set, and carrying out coding treatment on the first classification parameter to obtain a second preprocessing parameter;
step S430: the first pretreatment parameters and the second pretreatment parameters form a first pretreatment parameter set;
step S440: and carrying out weighted calculation on a plurality of preprocessing parameters in the first preprocessing parameter group to obtain the first state index.
Specifically, the first parameter set is analyzed through a first estimation channel in the state estimator, the state estimator comprises six estimation channels, and the six estimation channels respectively correspond to six characterization components in a preset monitoring category, namely, the six estimation channels are respectively used for carrying out state analysis on the state of the machine frame, the machine frame shafting, the hydraulic energy, the state of the overcurrent component, the working condition process and the temperature of the machine set, so that a first state index is obtained, and the first state index generally refers to the running state of any one of the characterization components in the state of the machine frame, the machine frame shafting, the hydraulic energy, the state of the overcurrent component, the working condition process and the temperature of the machine set.
Specifically, a first numerical parameter in the first parameter set is extracted, the first numerical parameter generally refers to any numerical monitoring parameter in the first parameter set, for example, the monitoring parameter collected according to the working condition process characterization index set includes rotor current, voltage, unit rotation speed, power, guide vane opening, water head and generator outlet switch state, wherein the rotor current, voltage, unit rotation speed, power and guide vane opening are parameters which can be directly represented by numerical values, the parameters are used as the first numerical parameter, the first numerical parameter is subjected to decimal scaling normalization processing, the decimal scaling normalization processing is to divide the original data by a certain fixed value, so that the absolute value of the data is smaller than 1, and the maximum absolute value of the divided data is generally selected between [ -1,1], for example, the range of the first numerical parameter is 20 to 100, the parameters in the first numerical parameter are divided by 100, and the obtained result is the first preprocessing parameter. And further extracting a first classification parameter in the first parameter set, wherein the first classification parameter is a parameter which cannot be directly represented by a numerical value, such as a generator outlet switch state, and carrying out coding processing on the first classification parameter, namely using different numbers to represent different classification states, such as a generator outlet switch state comprising an on state and an off state, using 0 to represent the off state, using 1 to represent the on state, realizing coding processing, facilitating the identification of the parameter by a computer system, and using a coding processing result as a second preprocessing parameter.
The first preprocessing parameters and the second preprocessing parameters form a first preprocessing parameter set, the weighting calculation is carried out on a plurality of preprocessing parameters in the first preprocessing parameter set, specifically, the weight distribution results of the plurality of preprocessing parameters can be determined through the existing weight analysis method, the weight distribution results of the plurality of preprocessing parameters can be determined through analysis by a variation coefficient method, the weight analysis method is a common technical means for a person skilled in the art, therefore, the first preprocessing parameter set is not unfolded, the weighted calculation results are used as the first state index, the operation state analysis of different characterization parts of the target hydro-generator set is realized, the anomaly identification is conveniently carried out on different parts in a targeted mode, and the identification efficiency and the identification accuracy are improved.
Step S500: if the first state index does not accord with a first preset index threshold value, starting an abnormality identification unit to analyze and identify the first parameter set to obtain a first abnormality prediction result;
the step S500 of the embodiment of the present invention further includes:
step S510: constructing a first training data set based on the first abnormal fault and the first abnormal fault characterization information;
Step S520: performing supervised learning and inspection on the first training data set to obtain the anomaly identification unit;
step S530: analyzing the first parameter set through the abnormality identification unit to obtain a second abnormal fault represented by the first parameter set;
step S540: and taking the second abnormal fault as the first abnormal prediction result.
Specifically, the first predetermined index threshold is set by a person skilled in the art according to the actual situation, and in particular, may be set by combining with historical experience, where the first predetermined index threshold is a normal state index range determined by the method for obtaining the first state index provided by the embodiment when the characterization component corresponding to each predetermined monitoring category of the target hydro-generator set is operating normally, and it is to be noted that the first predetermined index thresholds corresponding to different predetermined monitoring categories are different. And matching a corresponding first preset index threshold according to a first monitoring category to which the first parameter group belongs, comparing the first state index with the first preset index threshold, and starting an abnormality identification unit to analyze and identify the first parameter group to obtain a first abnormality prediction result if the first state index does not accord with the first preset index threshold.
Specifically, the starting abnormality identification unit analyzes and identifies the first parameter set, and the process of obtaining the first abnormality prediction result is as follows:
and based on the first abnormal faults and the first abnormal fault representation information, a first training data set is built, the first training data set is subjected to supervised learning and inspection to obtain the abnormal recognition unit, the abnormal recognition unit is a neural network model in machine learning, the input of the abnormal recognition unit is the first abnormal fault representation information, the output of the abnormal recognition unit is the first abnormal faults, the first abnormal fault representation information is input into the abnormal recognition unit, the first abnormal faults are utilized to supervise and regulate the output of the abnormal recognition unit, the first abnormal faults and the first abnormal fault representation information generally refer to multiple groups of training data, and the abnormal recognition unit with the accuracy meeting the requirement can be obtained by training the multiple groups of training data and testing the accuracy of the trained abnormal recognition unit. And further analyzing the first parameter set through the anomaly identification unit, namely outputting and obtaining a second anomaly fault represented by the first parameter set, and taking the second anomaly fault as the first anomaly prediction result, thereby realizing anomaly identification of different representation components of the target hydroelectric generating set.
Step S600: and regulating and controlling the target hydroelectric generating set according to the first abnormal prediction result.
Specifically, the target hydroelectric generating set is regulated and controlled according to the first abnormality prediction result, in short, the abnormal component, such as a frame, an overcurrent component and the like, is positioned according to the first abnormality fault corresponding to the first abnormality prediction result, and the abnormal component is subjected to targeted maintenance according to the first parameter set corresponding to the abnormal component, so that the first parameter set is restored to a normal value, thereby realizing the abnormality identification of the target hydroelectric generating set, further carrying out maintenance of the corresponding set part, and improving the accuracy and pertinence of the abnormality identification.
As shown in fig. 3, the embodiment of the present invention further includes:
step S710: constructing a digital twin model of the target hydroelectric generating set;
step S720: if the first state index meets the first preset index threshold value, first marking the first monitoring category, and if the first state index does not meet the first preset index threshold value, second marking the first monitoring category;
step S730: the first mark is a finger state normal mark, the state normal mark is provided with the mark of the first state index, the second mark is a finger state abnormal mark, and the state abnormal mark is provided with the mark of the first state index;
Step S740: and rendering the first mark or the second mark to the digital twin model, wherein the digital twin model is used for visually displaying the states of all parts of the target hydroelectric generating set.
Specifically, a digital twin model of the target hydroelectric generating set is constructed, the digital twin model fully utilizes data such as a physical model, sensor updating, operation history and the like, and models entity equipment in a virtual space, and the obtained virtual model is the digital twin model.
After the first state index is obtained, if the first state index accords with the first preset index threshold, a first mark is carried out on the first monitoring category, if the first state index does not accord with the first preset index threshold, a second mark is carried out on the first monitoring category, the first mark is different from the second mark, the first mark is a finger state normal mark, the state normal mark is provided with the identification of the first state index, the second mark is a finger state abnormal mark, the state abnormal mark is provided with the identification of the first state index, and the first state index is marked by different symbols or colors, for example, and meanwhile, the first state index is also marked. The first mark or the second mark is further rendered to the digital twin model, wherein the digital twin model is used for visually displaying the states of all parts of the target water turbine generator set, namely rendering is carried out at the corresponding position of the digital twin model according to the position of the target water turbine generator set in the first monitoring category, so that a worker can clearly see the normal or abnormal states of different characterization parts of the target water turbine generator set, and meanwhile, the first state indexes of the different characterization parts can be clearly known, visual display of the abnormal states is realized, the worker can clearly know the abnormal parts and the state indexes of the target water turbine generator set conveniently, overhaul is carried out timely, and the part with the state normal mark can be overhauled and maintained in advance according to the corresponding first state indexes.
Based on the analysis, the one or more technical schemes provided by the invention can achieve the following technical effects:
1. the method comprises the steps of analyzing historical abnormal state records of similar units of a target hydroelectric generating set to obtain an abnormal state representation category set, taking the abnormal state representation category set as a preset monitoring category, carrying out real-time state monitoring on the target hydroelectric generating set based on the preset monitoring category to obtain a target real-time operation parameter set, randomly extracting any one operation parameter set in the target real-time operation parameter set, and recording the operation parameter set as a first parameter set, wherein the first parameter set is provided with a first monitoring category identification, analyzing the first parameter set through a first estimation channel in a state estimator to obtain a first state index, starting an abnormal recognition unit to carry out analysis and recognition on the first parameter set to obtain a first abnormal prediction result, carrying out regulation and control treatment on the target hydroelectric generating set according to the first abnormal prediction result, carrying out targeted overhaul and maintenance on different parts of the target hydroelectric generating set, and further improving the accuracy and pertinence of the abnormal recognition efficiency.
2. Extracting a first historical record in the historical abnormal state records, wherein the first historical record comprises first abnormal fault representation information of a first abnormal fault, a historical abnormal fault representation information set is built based on the first abnormal fault representation information, clustering analysis is carried out on the historical abnormal fault representation information set based on a preset clustering scheme to obtain a clustering result, the clustering result comprises a plurality of clustering clusters with representation type identifiers, the abnormal state representation type set is built according to the clustering result, the purpose of conveniently carrying out state monitoring analysis on a target water turbine generator set according to a preset monitoring type in a targeted mode is achieved, irrelevant data is prevented from being monitored, waste of monitoring resources is avoided, and then the accuracy and the recognition efficiency of abnormal state recognition are improved.
3. A digital twin model of the target hydroelectric generating set is constructed, if the first state index accords with a first preset index threshold value, a first monitoring category is marked, if the first state index does not accord with the first preset index threshold value, a second monitoring category is marked, wherein the first mark is a finger-like normal mark, the state normal mark is provided with an identification of the first state index, the second mark is a finger-like abnormal mark, the state abnormal mark is provided with an identification of the first state index, the first mark or the second mark is rendered to the digital twin model, the digital twin model is used for carrying out visual display on the states of all parts of the target hydroelectric generating set, visual display on the abnormal states is achieved, and the technical effects that staff can clearly know the abnormal parts and the state index of the target hydroelectric generating set conveniently are achieved, so that overhaul and maintenance are timely carried out are achieved.
Example two
Based on the same inventive concept as the method for identifying abnormal states of a hydro-generator set in the foregoing embodiment, as shown in fig. 4, the present invention further provides a system for identifying abnormal states of a hydro-generator set, where the system is communicatively connected to a state estimator, and the system includes:
the preset monitoring category determining module 11 is configured to analyze a historical abnormal state record of a similar unit of the target hydroelectric generating set to obtain an abnormal state representation category set, and take the abnormal state representation category set as a preset monitoring category;
the real-time state monitoring module 12, wherein the real-time state monitoring module 12 is configured to perform real-time state monitoring on the target water turbine generator set based on the predetermined monitoring category, so as to obtain a target real-time operation parameter set;
an operation parameter extraction module 13, where the operation parameter extraction module 13 is configured to randomly extract any one of the operation parameter sets in the target real-time operation parameter set, and record the operation parameter set as a first parameter set, where the first parameter set has an identifier of a first monitoring category;
the state analysis module 14 is configured to analyze the first parameter set through a first estimation channel in the state estimator, so as to obtain a first state index;
The abnormality prediction module 15, where the abnormality prediction module 15 is configured to start an abnormality identification unit to perform analysis and identification on the first parameter set to obtain a first abnormality prediction result if the first state index does not meet a first predetermined index threshold;
and the regulation and control processing module 16 is used for carrying out regulation and control processing on the target hydroelectric generating set according to the first abnormity prediction result.
Further, the predetermined monitoring category determining module 11 is further configured to:
extracting a first history record in the history abnormal state records, wherein the first history record comprises first abnormal fault characterization information of a first abnormal fault;
constructing a historical abnormal fault characterization information set based on the first abnormal fault characterization information;
performing cluster analysis on the historical abnormal fault representation information set based on a preset cluster scheme to obtain a cluster result, wherein the cluster result comprises a plurality of cluster clusters with representation type destination identifiers;
and constructing the abnormal state representation category set according to the clustering result.
Further, the abnormal state representation category set comprises a frame state, a frame shafting, hydraulic energy, an overcurrent component state, a working condition process and a unit temperature.
Further, the real-time status monitoring module 12 is further configured to:
analyzing and determining a frame state representation index of the frame state, wherein the frame state representation index refers to frame vibration signal characteristics;
analyzing and constructing a frame shafting characterization index set of the frame shafting, wherein the frame shafting characterization index set comprises a large-shaft swing degree, a dynamic bending amount of a unit axis and a bending azimuth angle;
analyzing and constructing a hydraulic energy representation index set of the hydraulic energy, wherein the hydraulic energy representation index set comprises unit relative efficiency, machine-passing flow and water consumption rate;
analyzing and constructing an overcurrent component state characterization index set of the overcurrent component state, wherein the overcurrent component state characterization index set comprises a measuring point pressure and a measuring point pressure pulsation value;
analyzing and constructing a working condition process characterization index set of the working condition process, wherein the working condition process characterization index set comprises rotor current, voltage, unit rotating speed, power, guide vane opening, water head and generator outlet switch state;
analyzing and constructing a unit temperature representation index set of the unit temperature, wherein the unit temperature representation index set comprises thrust bearing temperature, cooler temperature, guide bearing bush temperature, stator temperature and oil temperature;
And taking the frame state representation index, the frame shafting representation index set, the hydraulic energy representation index set, the overcurrent part state representation index set, the working condition process representation index set and the unit temperature representation index set as preset monitoring index sets of the preset monitoring category.
Further, the operation parameter extraction module 13 is further configured to:
if the first parameter set is the vibration signal characteristic information of the frame vibration signal characteristic, calling a preset processing scheme;
and carrying out noise reduction processing on the vibration signal characteristic information according to the preset processing scheme to obtain an information noise reduction result, and taking the information noise reduction result as the first parameter set.
Further, the state analysis module 14 is further configured to:
extracting a first numerical parameter in the first parameter set, and performing decimal scaling normalization processing on the first numerical parameter to obtain a first preprocessing parameter;
extracting a first classification parameter in the first parameter set, and carrying out coding treatment on the first classification parameter to obtain a second preprocessing parameter;
the first pretreatment parameters and the second pretreatment parameters form a first pretreatment parameter set;
And carrying out weighted calculation on a plurality of preprocessing parameters in the first preprocessing parameter group to obtain the first state index.
Further, the system also includes a visual display module for:
constructing a digital twin model of the target hydroelectric generating set;
if the first state index meets the first preset index threshold value, first marking the first monitoring category, and if the first state index does not meet the first preset index threshold value, second marking the first monitoring category;
the first mark is a finger state normal mark, the state normal mark is provided with the mark of the first state index, the second mark is a finger state abnormal mark, and the state abnormal mark is provided with the mark of the first state index;
and rendering the first mark or the second mark to the digital twin model, wherein the digital twin model is used for visually displaying the states of all parts of the target hydroelectric generating set.
Further, the anomaly prediction module 15 is further configured to:
constructing a first training data set based on the first abnormal fault and the first abnormal fault characterization information;
Performing supervised learning and inspection on the first training data set to obtain the anomaly identification unit;
analyzing the first parameter set through the abnormality identification unit to obtain a second abnormal fault represented by the first parameter set;
and taking the second abnormal fault as the first abnormal prediction result.
The specific example of the method for identifying an abnormal state of a hydro-generator set in the first embodiment is also applicable to the system for identifying an abnormal state of a hydro-generator set in the present embodiment, and by the foregoing detailed description of the method for identifying an abnormal state of a hydro-generator set, those skilled in the art can clearly know the system for identifying an abnormal state of a hydro-generator set in the present embodiment, so that details thereof will not be described herein for brevity.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and are not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (9)
1. An abnormal state identification method for a hydroelectric generating set, wherein the method is applied to an abnormal state identification system of the hydroelectric generating set, and the system is in communication connection with a state estimator, and the method comprises the following steps:
analyzing the historical abnormal state records of the similar units of the target hydroelectric generating set to obtain an abnormal state representation category set, and taking the abnormal state representation category set as a preset monitoring category;
performing real-time state monitoring on the target hydroelectric generating set based on the preset monitoring category to obtain a target real-time operation parameter set;
randomly extracting any one operation parameter set in the target real-time operation parameter set, and recording the operation parameter set as a first parameter set, wherein the first parameter set is provided with an identifier of a first monitoring category;
Analyzing the first parameter set through a first estimation channel in the state estimator to obtain a first state index;
if the first state index does not accord with a first preset index threshold value, starting an abnormality identification unit to analyze and identify the first parameter set to obtain a first abnormality prediction result;
and regulating and controlling the target hydroelectric generating set according to the first abnormal prediction result.
2. The method of claim 1, wherein analyzing the historical abnormal state records of the same type of target hydro-generator set to obtain the set of abnormal state characterization categories comprises:
extracting a first history record in the history abnormal state records, wherein the first history record comprises first abnormal fault characterization information of a first abnormal fault;
constructing a historical abnormal fault characterization information set based on the first abnormal fault characterization information;
performing cluster analysis on the historical abnormal fault representation information set based on a preset cluster scheme to obtain a cluster result, wherein the cluster result comprises a plurality of cluster clusters with representation type destination identifiers;
and constructing the abnormal state representation category set according to the clustering result.
3. The method of claim 2, wherein the set of abnormal state characterization categories includes rack state, rack shafting, hydraulic energy, over-current component state, operating condition course, unit temperature.
4. A method according to claim 3, comprising, prior to said real-time status monitoring of said target hydro-generator set based on said predetermined monitoring categories, obtaining a target real-time operating parameter set:
analyzing and determining a frame state representation index of the frame state, wherein the frame state representation index refers to frame vibration signal characteristics;
analyzing and constructing a frame shafting characterization index set of the frame shafting, wherein the frame shafting characterization index set comprises a large-shaft swing degree, a dynamic bending amount of a unit axis and a bending azimuth angle;
analyzing and constructing a hydraulic energy representation index set of the hydraulic energy, wherein the hydraulic energy representation index set comprises unit relative efficiency, machine-passing flow and water consumption rate;
analyzing and constructing an overcurrent component state characterization index set of the overcurrent component state, wherein the overcurrent component state characterization index set comprises a measuring point pressure and a measuring point pressure pulsation value;
Analyzing and constructing a working condition process characterization index set of the working condition process, wherein the working condition process characterization index set comprises rotor current, voltage, unit rotating speed, power, guide vane opening, water head and generator outlet switch state;
analyzing and constructing a unit temperature representation index set of the unit temperature, wherein the unit temperature representation index set comprises thrust bearing temperature, cooler temperature, guide bearing bush temperature, stator temperature and oil temperature;
and taking the frame state representation index, the frame shafting representation index set, the hydraulic energy representation index set, the overcurrent part state representation index set, the working condition process representation index set and the unit temperature representation index set as preset monitoring index sets of the preset monitoring category.
5. A method according to claim 3, comprising, prior to said analyzing said first set of parameters by a first estimation pass in said state estimator:
if the first parameter set is the vibration signal characteristic information of the frame vibration signal characteristic, calling a preset processing scheme;
and carrying out noise reduction processing on the vibration signal characteristic information according to the preset processing scheme to obtain an information noise reduction result, and taking the information noise reduction result as the first parameter set.
6. The method of claim 5, wherein said analyzing said first set of parameters through a first estimation pass in said state estimator to obtain a first state index comprises:
extracting a first numerical parameter in the first parameter set, and performing decimal scaling normalization processing on the first numerical parameter to obtain a first preprocessing parameter;
extracting a first classification parameter in the first parameter set, and carrying out coding treatment on the first classification parameter to obtain a second preprocessing parameter;
the first pretreatment parameters and the second pretreatment parameters form a first pretreatment parameter set;
and carrying out weighted calculation on a plurality of preprocessing parameters in the first preprocessing parameter group to obtain the first state index.
7. The method of claim 6, further comprising, after said deriving said first state index:
constructing a digital twin model of the target hydroelectric generating set;
if the first state index meets the first preset index threshold value, first marking the first monitoring category, and if the first state index does not meet the first preset index threshold value, second marking the first monitoring category;
The first mark is a finger state normal mark, the state normal mark is provided with the mark of the first state index, the second mark is a finger state abnormal mark, and the state abnormal mark is provided with the mark of the first state index;
and rendering the first mark or the second mark to the digital twin model, wherein the digital twin model is used for visually displaying the states of all parts of the target hydroelectric generating set.
8. The method of claim 2, wherein if the first state index does not meet a first predetermined index threshold, the starting the anomaly identification unit to perform analysis and identification on the first parameter set to obtain a first anomaly prediction result includes:
constructing a first training data set based on the first abnormal fault and the first abnormal fault characterization information;
performing supervised learning and inspection on the first training data set to obtain the anomaly identification unit;
analyzing the first parameter set through the abnormality identification unit to obtain a second abnormal fault represented by the first parameter set;
and taking the second abnormal fault as the first abnormal prediction result.
9. An abnormal state identification system for a hydro-generator set, for performing the steps of any one of the methods for identifying abnormal states of a hydro-generator set of claims 1-8, said system being in communication with a state estimator, said system comprising:
the system comprises a preset monitoring category determining module, a target hydroelectric generating set, a monitoring category determining module and a monitoring category determining module, wherein the preset monitoring category determining module is used for analyzing historical abnormal state records of similar units of the target hydroelectric generating set to obtain an abnormal state representation category set, and the abnormal state representation category set is used as a preset monitoring category;
the real-time state monitoring module is used for monitoring the real-time state of the target water turbine generator set based on the preset monitoring category to obtain a target real-time operation parameter set;
the operation parameter extraction module is used for randomly extracting any one operation parameter set in the target real-time operation parameter set and recording the operation parameter set as a first parameter set, wherein the first parameter set is provided with an identifier of a first monitoring category;
the state analysis module is used for analyzing the first parameter set through a first estimation channel in the state estimator to obtain a first state index;
The abnormality prediction module is used for starting an abnormality identification unit to analyze and identify the first parameter set if the first state index does not accord with a first preset index threshold value, so as to obtain a first abnormality prediction result;
and the regulation and control processing module is used for carrying out regulation and control processing on the target hydroelectric generating set according to the first abnormal prediction result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310978913.XA CN117010191B (en) | 2023-08-04 | 2023-08-04 | Abnormal state identification method and system for hydroelectric generating set |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310978913.XA CN117010191B (en) | 2023-08-04 | 2023-08-04 | Abnormal state identification method and system for hydroelectric generating set |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117010191A true CN117010191A (en) | 2023-11-07 |
CN117010191B CN117010191B (en) | 2024-03-19 |
Family
ID=88572239
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310978913.XA Active CN117010191B (en) | 2023-08-04 | 2023-08-04 | Abnormal state identification method and system for hydroelectric generating set |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117010191B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118242234A (en) * | 2024-05-28 | 2024-06-25 | 陕西立拓科源科技有限公司 | Monitoring method and system for wind driven machine |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190230119A1 (en) * | 2018-01-19 | 2019-07-25 | General Electric Company | Dynamic concurrent learning method to neutralize cyber attacks and faults for industrial asset monitoring nodes |
CN114298080A (en) * | 2021-08-30 | 2022-04-08 | 西安理工大学 | Hydro-turbo generator set monitoring method based on throw data mining |
CN114912640A (en) * | 2022-05-30 | 2022-08-16 | 华能大理风力发电有限公司洱源分公司 | Method and system for detecting abnormal mode of generator set based on deep learning |
CN115034483A (en) * | 2022-06-16 | 2022-09-09 | 西安热工研究院有限公司 | Method and system for monitoring running fault of hydroelectric generating set |
CN115423158A (en) * | 2022-08-17 | 2022-12-02 | 贵州北盘江电力股份有限公司光照分公司 | Predictive analysis method and system for data trend of hydroelectric generating set |
CN116049654A (en) * | 2023-02-07 | 2023-05-02 | 北京奥优石化机械有限公司 | Safety monitoring and early warning method and system for coal preparation equipment |
CN116110203A (en) * | 2023-01-04 | 2023-05-12 | 大唐万宁天然气发电有限责任公司 | Natural gas power generation early warning management method and system based on intelligent monitoring technology |
CN116123042A (en) * | 2023-03-08 | 2023-05-16 | 大唐凉山新能源有限公司 | Intelligent monitoring and early warning method and system for wind generating set |
CN116187027A (en) * | 2023-01-09 | 2023-05-30 | 广西桂冠电力股份有限公司 | Intelligent prediction and early warning method and system for photovoltaic power generation faults |
-
2023
- 2023-08-04 CN CN202310978913.XA patent/CN117010191B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190230119A1 (en) * | 2018-01-19 | 2019-07-25 | General Electric Company | Dynamic concurrent learning method to neutralize cyber attacks and faults for industrial asset monitoring nodes |
CN114298080A (en) * | 2021-08-30 | 2022-04-08 | 西安理工大学 | Hydro-turbo generator set monitoring method based on throw data mining |
CN114912640A (en) * | 2022-05-30 | 2022-08-16 | 华能大理风力发电有限公司洱源分公司 | Method and system for detecting abnormal mode of generator set based on deep learning |
CN115034483A (en) * | 2022-06-16 | 2022-09-09 | 西安热工研究院有限公司 | Method and system for monitoring running fault of hydroelectric generating set |
CN115423158A (en) * | 2022-08-17 | 2022-12-02 | 贵州北盘江电力股份有限公司光照分公司 | Predictive analysis method and system for data trend of hydroelectric generating set |
CN116110203A (en) * | 2023-01-04 | 2023-05-12 | 大唐万宁天然气发电有限责任公司 | Natural gas power generation early warning management method and system based on intelligent monitoring technology |
CN116187027A (en) * | 2023-01-09 | 2023-05-30 | 广西桂冠电力股份有限公司 | Intelligent prediction and early warning method and system for photovoltaic power generation faults |
CN116049654A (en) * | 2023-02-07 | 2023-05-02 | 北京奥优石化机械有限公司 | Safety monitoring and early warning method and system for coal preparation equipment |
CN116123042A (en) * | 2023-03-08 | 2023-05-16 | 大唐凉山新能源有限公司 | Intelligent monitoring and early warning method and system for wind generating set |
Non-Patent Citations (2)
Title |
---|
JI HYEON SHIN等: "Abnormal state diagnosis model tolerant to noise in plant data", pages 1 - 8, Retrieved from the Internet <URL:《网页在线公开:https://www.sciencedirect.com/science/article/pii/S1738573320308871》> * |
樊帅等: "基于AdaBoost-SAMME 的风力发电机组变桨异常识别***", 《电力***保护与控制》, vol. 48, no. 21, 30 November 2020 (2020-11-30), pages 31 - 40 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118242234A (en) * | 2024-05-28 | 2024-06-25 | 陕西立拓科源科技有限公司 | Monitoring method and system for wind driven machine |
Also Published As
Publication number | Publication date |
---|---|
CN117010191B (en) | 2024-03-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN117010191B (en) | Abnormal state identification method and system for hydroelectric generating set | |
CN112613646A (en) | Equipment state prediction method and system based on multi-dimensional data fusion | |
Soylemezoglu et al. | Mahalanobis-Taguchi system as a multi-sensor based decision making prognostics tool for centrifugal pump failures | |
CN112906969B (en) | Engine fault prediction method and device, electronic equipment and storage medium | |
CN114619292B (en) | Milling cutter wear monitoring method based on fusion of wavelet denoising and attention mechanism with GRU network | |
CN111537219B (en) | Fan gearbox performance detection and health assessment method based on temperature parameters | |
CN104976139B (en) | A kind of mechanical equipment state diagnostic method based on Gauss model | |
CN109100648A (en) | Ocean current generator impeller based on CNN-ARMA-Softmax winds failure fusion diagnosis method | |
CN114580666A (en) | Multi-mode fusion motor intelligent maintenance system | |
CN116976707B (en) | User electricity consumption data anomaly analysis method and system based on electricity consumption data acquisition | |
CN112816898B (en) | Battery failure prediction method and device, electronic equipment and storage medium | |
CN115758083A (en) | Motor bearing fault diagnosis method based on time domain and time-frequency domain fusion | |
Li et al. | A multi-label method of state partition and fault diagnosis based on binary relevance algorithm | |
CN116976531B (en) | Integrated management method and system for underground electric control equipment | |
CN114298080A (en) | Hydro-turbo generator set monitoring method based on throw data mining | |
CN109165396A (en) | A kind of equipment remaining life prediction technique of failure evolution trend | |
CN116467592A (en) | Production equipment fault intelligent monitoring method and system based on deep learning | |
CN111934903A (en) | Docker container fault intelligent prediction method based on time sequence evolution genes | |
CN113435228A (en) | Motor bearing service life prediction and analysis method based on vibration signal modeling | |
CN114320773B (en) | Wind turbine generator system fault early warning method based on power curve analysis and neural network | |
CN115326393A (en) | Wind turbine generator bearing pair fault diagnosis method based on temperature information | |
CN111199246B (en) | Working condition classification method | |
CN114841061A (en) | Wind power gear box health assessment method and system integrating timing sequence information | |
Chu | Anomaly detection of hydropower generating set using operation condition and adaptive PCA | |
CN117034157B (en) | Hydropower equipment fault identification method and system combining multimodal operation data |
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 |