CN117365677A - Steam turbine unit performance health state evaluation method - Google Patents
Steam turbine unit performance health state evaluation method Download PDFInfo
- Publication number
- CN117365677A CN117365677A CN202311094795.2A CN202311094795A CN117365677A CN 117365677 A CN117365677 A CN 117365677A CN 202311094795 A CN202311094795 A CN 202311094795A CN 117365677 A CN117365677 A CN 117365677A
- Authority
- CN
- China
- Prior art keywords
- energy efficiency
- data
- efficiency state
- state index
- turbine unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 49
- 230000036541 health Effects 0.000 title claims abstract description 35
- 238000012544 monitoring process Methods 0.000 claims abstract description 42
- 238000012549 training Methods 0.000 claims abstract description 16
- 238000012216 screening Methods 0.000 claims abstract description 15
- 238000013210 evaluation model Methods 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims description 23
- 239000003245 coal Substances 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 7
- 238000012423 maintenance Methods 0.000 claims description 6
- 230000003862 health status Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 3
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 abstract 1
- 238000005265 energy consumption Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000013441 quality evaluation Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
- F01D—NON-POSITIVE DISPLACEMENT MACHINES OR ENGINES, e.g. STEAM TURBINES
- F01D21/00—Shutting-down of machines or engines, e.g. in emergency; Regulating, controlling, or safety means not otherwise provided for
- F01D21/003—Arrangements for testing or measuring
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Control Of Turbines (AREA)
Abstract
The invention relates to the field of turbine monitoring, and discloses a turbine unit performance health state evaluation method, which comprises the following steps: acquiring historical operation data, and selecting part of monitoring items as energy efficiency state indexes; taking environmental data in the historical operation data as working condition dividing parameters; performing steady-state screening of the monitoring data, and eliminating invalid data in the monitoring data; dividing working conditions and determining the number of clusters; clustering energy efficiency state index data of stable working conditions by adopting an FCM clustering algorithm, and acquiring data of a target class; establishing a sample set from the data of the target class, training a multi-element state evaluation model by using the sample set, and calculating the deviation degree of the predicted value of the energy efficiency state index and the true value of the energy efficiency state index at the current moment; and constructing an energy efficiency state index SI of the turbine unit. The invention can automatically monitor a plurality of energy efficiency state indexes of the turbine unit in real time and give an alarm when the health degree is good and moderate.
Description
Technical Field
The invention relates to the field of turbine monitoring, in particular to a turbine unit performance health state evaluation method.
Background
The turbo generator set occupies a large proportion for the power production required by our country at present, is an important device for power production, and needs to be studied deeply for the running state. As early as 80 s of the last century, china studied the diagnosis work of the turbine unit, and the main research before is on vibration faults of the turbine unit, so that the research on other types of faults is relatively less. In addition to the research on the reasons for the failure of the unit, the research on factors which can improve the efficiency of the unit is also needed. In the past, the operation optimization of the unit is adjusted by relying on the professional knowledge of operators and long-term working experience of the operators, when the operation parameters of the unit change but do not exceed the limit values, the operators cannot timely find the abnormal conditions of the unit, so that the equipment performance of the unit is deteriorated, the coal consumption of the unit is increased, the energy utilization rate of the unit is reduced, and the energy consumption of the unit is improved.
Therefore, in order to improve the operation efficiency of the unit, the invention provides an energy efficiency evaluation method of the thermal power unit, which is necessary to realize the on-line monitoring of the operation state performance of the unit equipment and to evaluate the efficiency level of the thermal power unit in real time, so that a power plant operator can adjust the unit in time according to the evaluation, the energy consumption level of the unit is reduced, and the energy conservation is realized.
CN202210778796 discloses a wind turbine generator system state monitoring method based on multi-source heterogeneous SCADA data, which comprises the following steps: calculating probability distribution of monitoring quantities of all wind turbines in the wind farm, and screening out one wind turbine capable of representing the whole wind farm; cleaning monitoring data; performing feature dimension reduction, and screening out a plurality of sensitive feature parameters with high correlation degree with the monitoring quantity; normalizing the screened sensitive characteristic parameters, then establishing a sample set, and training a long-time short-time memory neural network model by using the sample set; calculating root mean square error of the real value and the predicted value of the monitoring quantity at the current moment, and constructing a health monitoring state index of the wind turbine; and carrying out sliding average by designing a sliding window; when the screened wind turbine generator is monitored, an alarm is sent out when the health monitoring state index exceeds the early warning threshold value. The invention realizes the state monitoring and fault early warning of the wind turbine generator. According to the monitoring method, the predicted value of the average gearbox oil temperature is obtained through a long-short-term memory neural network model by using the sensitive characteristic parameters and is compared, so that the equipment condition can be monitored in real time, but finally, the equipment condition is evaluated by means of a single parameter, and the accuracy is relatively low. The invention combines the correction information entropy weight method and the working condition division and clustering of the data, and can consider the condition of energy efficiency state caused by various parameter changes and working condition changes, thereby realizing the real-time equipment performance quality evaluation of the unit, timely carrying out proper diagnosis measures of the unit aiming at the evaluation and realizing the aim of reducing the energy consumption of the unit.
The technical problems to be solved by the invention are as follows: how to consider the energy efficiency state good and bad conditions caused by various parameter changes and working condition changes, the real-time equipment performance good and bad evaluation of the unit is realized, and the evaluation accuracy is improved.
Disclosure of Invention
The invention mainly aims to provide a turbine unit performance health state evaluation method, which uses working condition dividing parameters to determine the number of clusters, obtains target class data in energy efficiency state index data through a clustering algorithm, thereby realizing the consideration of various parameter changes and working condition change conditions, and obtains a predicted value of each energy efficiency state by combining a correction information entropy weight method and a multi-element state evaluation model, thereby realizing multi-parameter monitoring evaluation and early warning and improving the evaluation accuracy.
In order to achieve the above purpose, the technical scheme adopted in the application is as follows:
a turbine unit performance health state evaluation method comprises the following steps:
step 1: acquiring historical operation data, and selecting part of monitoring items as energy efficiency state indexes; taking the selected monitoring data in the historical operation data as energy efficiency state index data, and taking the environment data in the historical operation data as working condition dividing parameters;
step 2: performing steady-state screening of the monitoring data, and removing invalid data in the monitoring data to obtain energy efficiency state index data of stable working conditions;
step 3: carrying out working condition division by using working condition division parameters, and determining the clustering number; clustering energy efficiency state index data of stable working conditions by adopting an FCM clustering algorithm, and acquiring data of a target class;
step 4: establishing a sample set of the data of the target class, and training a multi-state evaluation model by using the sample set, wherein the sample set is a test set and a training set respectively;
step 5: inputting the test set into a multi-element state evaluation model which has completed training to obtain an energy efficiency state index predicted value of the turbine unit at the current moment; determining the entropy weight value of each energy efficiency state index by a correction information entropy weight method; calculating the deviation degree of the predicted value of the energy efficiency state index at the current moment and the true value of the energy efficiency state index by combining the entropy weight value and the predicted value of the energy efficiency state index at the current moment; and constructing an energy efficiency state index SI of the turbine unit.
Preferably, the turbine unit performance health state evaluation method further includes step 6: setting evaluation thresholds, namely an evaluation threshold and an evaluation threshold;
when the energy efficiency state index SI at the current moment is smaller than the evaluation threshold, the health degree of the turbine unit is excellent;
when the energy efficiency state index SI at the current moment is larger than the evaluation threshold and smaller than the evaluation threshold, the health of the turbine unit is good;
when the energy efficiency state index SI at the current moment is larger than the evaluation threshold, the health degree of the turbine unit is middle;
when the health degree of the turbine unit is good, a maintenance alarm is sent out;
and when the health degree of the turbine unit is middle, a maintenance alarm is sent out.
Preferably, the energy efficiency state indexes are main steam pressure, main steam temperature, reheat steam temperature and feedwater flow; the working condition dividing parameters are load, ambient temperature and ambient pressure; the target class is the class with the lowest coal consumption rate.
Preferably, in step 2, the steady-state screening comprises the steps of:
step A1: carrying out a data sliding window on the monitoring data, and screening out the monitoring data of stable working conditions according to the fact that the difference value between the monitoring data in a period of time is smaller than a stability threshold value;
step A2: and (3) carrying out data processing on the monitoring data of the stable working condition, removing repeated data and start-stop data, supplementing missing data, and screening out the energy efficiency state index data of the stable working condition.
Preferably, the clustering algorithm is as follows:
wherein c is the number of clusters, u ik Membership function of kth energy efficiency state index data to ith clustering center, v i For the ith cluster center, m is a weighting coefficient of membership degree, generally 2, J is the distance from the energy efficiency state index data to each cluster center, and X= { X k K=1, 2, … n } is the training sample.
Preferably, the hyper-parameters of the multivariate state assessment model comprise:
the number of the input energy efficiency state indexes, the number of clusters, the learning rate, the iteration times and the number of the output energy efficiency state indexes.
Preferably, the correction information entropy weighting method is as follows:
wherein,entropy weight value for j-th energy efficiency state index,/>For searching information entropy value of 40, H j And the information entropy value of the j-th energy efficiency state index.
Preferably, the energy efficiency state index SI is as follows:
wherein x is i A reference value y for the ith energy efficiency state index i Is the predicted value omega of the ith energy efficiency state index i And the weight coefficient of the ith energy efficiency state index.
Preferably, the evaluation threshold is a function value with a confidence of 75%; the evaluation threshold is a function value with 95% confidence;
the confidence coefficient calculation formula is as follows:
wherein x is u For the upper confidence limit, x l For the lower confidence limit, f (x) is the density profile.
Compared with the prior art, the scheme has the following beneficial effects:
1. the method can consider the good and bad conditions of the energy efficiency state caused by various parameter changes and working condition changes, thereby realizing the real-time equipment performance quality evaluation of the unit, timely carrying out proper diagnosis measures of the unit aiming at the evaluation, and realizing the aim of reducing the energy consumption of the unit.
2. The energy efficiency of the turbine unit can be evaluated in real time, and the automatic monitoring of the turbine unit is realized.
Drawings
FIG. 1 is a flowchart of a turbine unit performance health evaluation method of example 1;
FIG. 2 is a schematic diagram of the health monitoring of the steam turbine set of example 1.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the implementations of the present application, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations.
Example 1
Referring to fig. 1-2, a turbine unit performance health status evaluation method includes the steps of:
step 1: acquiring historical operation data, and selecting part of monitoring items as energy efficiency state indexes; taking the selected monitoring data in the historical operation data as energy efficiency state index data, and taking the environment data in the historical operation data as working condition dividing parameters;
in this embodiment, the energy efficiency state indexes are main steam pressure, main steam temperature, reheat steam temperature and feedwater flow; the working condition dividing parameters are load, ambient temperature and ambient pressure.
Step 2: performing steady-state screening of the monitoring data, and removing invalid data in the monitoring data to obtain energy efficiency state index data of stable working conditions;
in this embodiment, steady-state screening is performed on the monitored data through the following steps to obtain energy efficiency state index data of stable working conditions.
Step A1: carrying out a data sliding window on the monitoring data, and screening out the monitoring data of stable working conditions according to the fact that the difference value between the monitoring data in a period of time is smaller than a stability threshold value;
in this embodiment, the stability threshold is a threshold of 1MPa for the main steam pressure, a threshold of 10 ℃ for the main steam temperature and the reheat steam temperature, a feed water flow rate of 50t/h, a load threshold of 10MW, and a sliding window length of L (L is the number of data sets selected by the window), but the stability threshold may be set to other values according to practical situations.
Step A2: and (3) carrying out data processing on the monitoring data of the stable working condition, removing repeated data and start-stop data, supplementing missing data, and screening out the energy efficiency state index data of the stable working condition.
In this embodiment, the data is supplemented by using the mean value filling method, specifically, one energy efficiency state index has data missing, and the remaining data is averaged to make the average value the missing data.
Step 3: carrying out working condition division by using working condition division parameters, and determining the clustering number; clustering energy efficiency state index data of stable working conditions by adopting an FCM clustering algorithm, and acquiring data of a target class;
in this embodiment, according to the working condition dividing parameters, when the load variation range is between 400 and 910MW, the interval is 10MW, the ambient temperature variation range is between 5 and 35 ℃, the interval range is 5 ℃, the ambient pressure variation range is 91.55 to 92.55MPa, and the interval range is 0.5MPa, but the dividing number is not limited to this dividing number mode, and the dividing value can be set according to the actual condition of the power plant. The target class is the class with the lowest coal consumption rate. The clustering algorithm is as follows:
wherein c is the number of clusters, u ik Membership function of kth energy efficiency state index data to ith clustering center, v i For the ith cluster center, m is a weighting coefficient of membership degree, generally 2, J is the distance from the energy efficiency state index data to each cluster center, and X= { X k K=1, 2, … n } is the training sample. And obtaining data of the class with the lowest coal consumption rate as sample data through a clustering algorithm, wherein a clustering center of the class with the lowest coal consumption rate is used as a reference value of the class with the lowest coal consumption rate.
Step 4: establishing a sample set of the data of the target class, and training a multi-state evaluation model by using the sample set, wherein the sample set is a test set and a training set respectively;
in this embodiment, 60% of the data in the class with the lowest coal consumption rate is used as the test set, and 40% of the data in the class with the lowest coal consumption rate is used as the training set.
The super parameters of the multi-element state evaluation model comprise the number of input energy efficiency state indexes, the number of clusters, the learning rate, the iteration times and the number of output energy efficiency state indexes.
Structure of the multivariate state assessment model: memory matrix + residual training matrix
The quantity of the input energy efficiency state indexes is 4 in total, namely main steam pressure, main steam temperature, reheat steam temperature and feedwater flow.
The quantity of the output energy efficiency state indexes is 4 in total, namely main steam pressure, main steam temperature, reheat steam temperature and feedwater flow.
Step 5: inputting the test set into a multi-element state evaluation model which has completed training to obtain an energy efficiency state index predicted value of the turbine unit at the current moment; determining the entropy weight value of each energy efficiency state index by a correction information entropy weight method; calculating the deviation degree of the predicted value of the energy efficiency state index at the current moment and the true value of the energy efficiency state index by combining the entropy weight value and the predicted value of the energy efficiency state index at the current moment; and constructing an energy efficiency state index SI of the turbine unit.
In this embodiment, the correction information entropy weighting method is as follows:
wherein,entropy weight value for j-th energy efficiency state index,/>For searching information entropy value of 40, H j Is the j-th energy efficiency stateInformation entropy value of the index.
And obtaining a weight coefficient omega by a correction information entropy weight method.
The energy efficiency state index SI is as follows:
wherein x is i A reference value y for the ith energy efficiency state index i Is the predicted value omega of the ith energy efficiency state index i And the weight coefficient of the ith energy efficiency state index.
And obtaining the SI value of the energy efficiency state index of the power plant equipment at the current moment through the energy efficiency state index SI.
Preferably, the turbine unit performance health state evaluation method further includes step 6: setting evaluation thresholds, namely an evaluation threshold and an evaluation threshold;
when the energy efficiency state index SI at the current moment is smaller than the evaluation threshold, the health degree of the turbine unit is excellent;
when the energy efficiency state index SI at the current moment is larger than the evaluation threshold and smaller than the evaluation threshold, the health of the turbine unit is good;
when the energy efficiency state index SI at the current moment is larger than the evaluation threshold, the health degree of the turbine unit is middle;
when the health degree of the turbine unit is good, a maintenance alarm is sent out;
and when the health degree of the turbine unit is middle, a maintenance alarm is sent out.
Preferably, the evaluation threshold is a function value with a confidence of 75%; the evaluation threshold is a function value with 95% confidence; the evaluation threshold in this embodiment is 0.0767, and the evaluation threshold is 0.1369;
the confidence coefficient calculation formula is as follows:
wherein x is u For the upper limit of the confidence level,x l for the lower confidence limit, f (x) is the density profile.
Fig. 2 shows a specific application of the method for evaluating the performance health state of the turbine unit in the power plant, and the health degree of the energy efficiency state index of the power plant equipment at the current moment can be obtained through calculation of the method. And the obtained health degree evaluation is consistent with the actual situation.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
Claims (9)
1. A turbine unit performance health state evaluation method is characterized by comprising the following steps:
step 1: acquiring historical operation data, and selecting part of monitoring items as energy efficiency state indexes; taking the selected monitoring data in the historical operation data as energy efficiency state index data, and taking the environment data in the historical operation data as working condition dividing parameters;
step 2: performing steady-state screening of the monitoring data, and removing invalid data in the monitoring data to obtain energy efficiency state index data of stable working conditions;
step 3: carrying out working condition division by using working condition division parameters, and determining the clustering number; clustering energy efficiency state index data of stable working conditions by adopting an FCM clustering algorithm, and acquiring data of a target class;
step 4: establishing a sample set of the data of the target class, and training a multi-state evaluation model by using the sample set, wherein the sample set is a test set and a training set respectively;
step 5: inputting the test set into a multi-element state evaluation model which has completed training to obtain an energy efficiency state index predicted value of the turbine unit at the current moment; determining the entropy weight value of each energy efficiency state index by a correction information entropy weight method; calculating the deviation degree of the predicted value of the energy efficiency state index at the current moment and the true value of the energy efficiency state index by combining the entropy weight value and the predicted value of the energy efficiency state index at the current moment; and constructing an energy efficiency state index SI of the turbine unit.
2. The method for evaluating the performance health state of the steam turbine unit is characterized by further comprising the following step 6: setting evaluation thresholds, namely an evaluation threshold and an evaluation threshold;
when the energy efficiency state index SI at the current moment is smaller than the evaluation threshold, the health degree of the turbine unit is excellent;
when the energy efficiency state index SI at the current moment is larger than the evaluation threshold and smaller than the evaluation threshold, the health of the turbine unit is good;
when the energy efficiency state index SI at the current moment is larger than the evaluation threshold, the health degree of the turbine unit is middle;
when the health degree of the turbine unit is good, a maintenance alarm is sent out;
and when the health degree of the turbine unit is middle, a maintenance alarm is sent out.
3. The method for evaluating the performance health status of a steam turbine unit according to claim 1, wherein the energy efficiency status indicators are main steam pressure, main steam temperature, reheat steam temperature, and feedwater flow; the working condition dividing parameters are load, ambient temperature and ambient pressure; the target class is the class with the lowest coal consumption rate.
4. The method for evaluating the performance health of a steam turbine unit according to claim 1, wherein in step 2, the steady-state screening comprises the steps of:
step A1: carrying out a data sliding window on the monitoring data, and screening out the monitoring data of stable working conditions according to the fact that the difference value between the monitoring data in a period of time is smaller than a stability threshold value;
step A2: and (3) carrying out data processing on the monitoring data of the stable working condition, removing repeated data and start-stop data, supplementing missing data, and screening out the energy efficiency state index data of the stable working condition.
5. The method for evaluating the performance health status of a steam turbine unit according to claim 1, wherein the clustering algorithm is as follows:
wherein c is the number of clusters, u ik Membership function of kth energy efficiency state index data to ith clustering center, v i For the ith cluster center, m is a weighting coefficient of membership degree, generally 2, J is the distance from the energy efficiency state index data to each cluster center, and X= { X k K=1, 2, … n } is the training sample.
6. The method of claim 1, wherein the hyper-parameters of the multi-state assessment model comprise:
the number of the input energy efficiency state indexes, the number of clusters, the learning rate, the iteration times and the number of the output energy efficiency state indexes.
7. The method for evaluating the performance health status of a steam turbine unit according to claim 1, wherein the correction information entropy weighting method is as follows:
wherein,entropy weight value for j-th energy efficiency state index,/>For searching information entropy value of 40, H j And the information entropy value of the j-th energy efficiency state index.
8. The method for evaluating the performance health of a steam turbine unit according to claim 7, wherein the energy efficiency state index SI is as follows:
wherein x is i A reference value y for the ith energy efficiency state index i Is the predicted value omega of the ith energy efficiency state index i And the weight coefficient of the ith energy efficiency state index.
9. The method for evaluating the performance health status of a steam turbine unit according to claim 2, wherein the evaluation threshold is a function value with a confidence of 75%; the evaluation threshold is a function value with 95% confidence;
the confidence coefficient calculation formula is as follows:
wherein x is u For the upper confidence limit, x l For the lower confidence limit, f (x) is the density profile.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311094795.2A CN117365677A (en) | 2023-08-28 | 2023-08-28 | Steam turbine unit performance health state evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311094795.2A CN117365677A (en) | 2023-08-28 | 2023-08-28 | Steam turbine unit performance health state evaluation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117365677A true CN117365677A (en) | 2024-01-09 |
Family
ID=89391838
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311094795.2A Pending CN117365677A (en) | 2023-08-28 | 2023-08-28 | Steam turbine unit performance health state evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117365677A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117591839A (en) * | 2024-01-19 | 2024-02-23 | 华电电力科学研究院有限公司 | Gas turbine fault early warning method, system, electronic equipment and storage medium |
-
2023
- 2023-08-28 CN CN202311094795.2A patent/CN117365677A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117591839A (en) * | 2024-01-19 | 2024-02-23 | 华电电力科学研究院有限公司 | Gas turbine fault early warning method, system, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108376298B (en) | Early warning and diagnosing method for temperature faults of engine of wind turbine generator | |
| CN110362045B (en) | Marine doubly-fed wind turbine generator fault discrimination method considering marine meteorological factors | |
| CN111581597A (en) | Wind turbine generator gearbox bearing temperature state monitoring method based on self-organizing kernel regression model | |
| CN117365677A (en) | Steam turbine unit performance health state evaluation method | |
| CN112994101B (en) | Neural network-based wind power plant generated power post-evaluation and monitoring method | |
| CN113780375B (en) | Digital twinning-based virtual-real interaction wind power plant wind power monitoring system and application | |
| CN111814848B (en) | Self-adaptive early warning strategy design method for temperature faults of wind turbine generator | |
| CN110544184A (en) | fan performance analysis method based on operation parameters | |
| CN105117591A (en) | Power device running status analysis method | |
| CN109800931A (en) | Wind power plant generated energy loss measurement method and system based on blower SCADA data | |
| CN116609055A (en) | Method for diagnosing wind power gear box fault by using graph convolution neural network | |
| Shi et al. | Study of wind turbine fault diagnosis and early warning based on SCADA data | |
| CN115977855A (en) | Hydropower station fault diagnosis system based on artificial intelligence | |
| CN113221453A (en) | Fault monitoring and early warning method for output shaft of gearbox of wind turbine generator | |
| CN116505663A (en) | Farm power consumption safety state monitoring and early warning system | |
| CN113777351B (en) | Fault diagnosis method and device for wind speed sensor of wind power plant | |
| CN115095487A (en) | Wind turbine state monitoring method based on multi-source heterogeneous SCADA data | |
| CN113505448B (en) | Wind turbine generator dynamic reliability evaluation method based on improved Bayesian network | |
| CN113505909B (en) | Error compensation method for short-term wind power trend prediction | |
| CN113610285A (en) | Power prediction method for distributed wind power | |
| CN117287352A (en) | Wind turbine generator system state monitoring method | |
| CN111178601B (en) | Wind turbine generator power prediction method based on meteorological data post-processing | |
| CN110334951B (en) | Intelligent evaluation method and system for high-temperature capacity reduction state of wind turbine generator | |
| Guo et al. | Early fault detection of wind turbine gearbox based on Adam-trained LSTM | |
| CN114595989A (en) | Wind turbine generator performance evaluation method and device |
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 |