CN115450710A - Method for optimizing sliding pressure operation of steam turbine - Google Patents
Method for optimizing sliding pressure operation of steam turbine Download PDFInfo
- Publication number
- CN115450710A CN115450710A CN202211085776.9A CN202211085776A CN115450710A CN 115450710 A CN115450710 A CN 115450710A CN 202211085776 A CN202211085776 A CN 202211085776A CN 115450710 A CN115450710 A CN 115450710A
- Authority
- CN
- China
- Prior art keywords
- unit
- historical
- data
- stable operation
- under
- 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
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Mechanical Engineering (AREA)
- Control Of Turbines (AREA)
Abstract
A method for optimizing the sliding pressure operation of a steam turbine belongs to the field of steam turbine control of a thermal power plant. The method solves the problems that the existing method for optimizing the sliding pressure of the steam turbine set is low in accuracy and cannot conduct quantitative guidance. The method comprises the steps of firstly, obtaining historical operation data of a corresponding unit in a preset time period and clustering the historical operation data, so as to divide the historical operation data into data sets under N stable operation working conditions; respectively training N identical initial unit performance evaluation models by using data sets under N stable operation working conditions to obtain unit performance evaluation models suitable for the N stable operation working conditions; real operation data of the unit at the current moment are collected in real time during the unit sliding pressure operation period, and the unit performance evaluation model under N stable operation working conditions is combined to calculate the operation time of each stable operationTaking the minimum value of N load deviations as a performance degradation deviation s, and converting the performance degradation deviation s into a main steam pressure control quantity delta P z And controlling the running state of the unit. The invention is mainly used for the sliding pressure operation of the unit.
Description
Technical Field
The invention belongs to the field of steam turbine control of a thermal power plant, and particularly relates to a method for optimizing the sliding pressure operation control of a steam turbine unit.
Background
The method focuses on the optimization of the sliding pressure operation scheme of the thermal power generating unit, and is beneficial to improving the economy and the safety and stability of the thermal power plant. Typical sliding pressure optimization methods are mainly divided into two major categories in the implementation process: one is an optimal operating pressure determination method based on a proprietary test; another type is a method of operating optimization of sliding pressure based on operating data.
However, the requirement of the thermal power plant for the sliding pressure optimization method is mainly embodied in that the economy is improved as much as possible on the premise that the optimization cost can be reduced. The accuracy requirement of the sliding pressure optimization can be met by developing a special experiment, but the time cost and the technical cost of the optimization process are higher; the sliding pressure operation optimization method based on the operation data can reduce time and technical cost to the maximum extent, but thermal power generating units are always in a variable load process in the operation process, so that thermal inertia noise exists in data samples. If used without processing, this will inevitably degrade the accuracy of the optimization conclusions. In addition, the two algorithms essentially belong to an off-line optimization method, and the sliding pressure operation control strategy cannot be adjusted in real time in a self-adaptive mode according to the unit operation state.
In the existing research on using operating data to perform sliding pressure optimization, a plurality of methods related to sample denoising are discussed, typically, a filtering method, a method of introducing a fuzzy set, and the like. However, the unit operation process is complex, so that all data sets cannot be analyzed as a whole, and the unit needs to be subjected to refined performance evaluation. Most of the existing methods for evaluating the performance of the unit only use a regression algorithm or a machine learning model to establish a global model, and cannot analyze and establish models one by one aiming at the operating characteristics of each working condition, so that the accuracy of the existing method for developing the sliding pressure optimization by using the operating data is poor; on the other hand, the performance evaluation of the unit is mainly applied to fault diagnosis and aging degree evaluation of the unit, but cannot be directly applied to quantitative guidance of a sliding pressure optimization process. Therefore, the above problems need to be solved.
Disclosure of Invention
The invention aims to solve the problems that the existing method for optimizing the sliding pressure of the steam turbine set is low in accuracy and cannot conduct quantitative guidance; the invention provides a method for optimizing the sliding pressure operation of a steam turbine.
The method for optimizing the sliding pressure operation of the steam turbine comprises the following processes:
s1, obtaining historical operation data of a corresponding unit in a preset time period from a unit database;
s2, clustering historical operating data in a preset time period, and dividing the historical operating data into data sets under N stable operating conditions; wherein N is an integer;
s3, training N identical initial unit performance evaluation models respectively by using data sets under N stable operation working conditions to obtain unit performance evaluation models suitable for the N stable operation working conditions;
s4, acquiring real operation data of the unit at the current moment in real time during the unit sliding pressure operation period, and calculating load deviation under each stable operation condition by combining unit performance evaluation models under N stable operation conditions so as to obtain N load deviations; taking the minimum value of the N load deviations as a performance degradation deviation s;
s5, converting the performance degradation deviation S into a main steam pressure control quantity delta P z And controlling the running state of the unit so as to complete the optimization of the sliding pressure running of the steam turbine.
Preferably, the historical operating data comprises historical main steam pressure P collected at each collection time z History main steam temperature T z Historical main steam flow F z Historical reheat steam pressure F hrh Historical reheat steam temperature T hrh Historical unit backpressure P b Historical unit heat supply steam extraction flow F g And historical unit load E.
Preferably, the step S2 of clustering the historical operating data in the preset time period, so as to segment the data sets under the N stable operating conditions, includes:
s21, extracting historical main steam pressure P at each acquisition moment from historical operation data in a preset time period z And historical unit load E, and drawing historical main steam pressure P at each acquisition moment z And a relation graph between historical unit loads E;
s22, carrying out clustering analysis on the relation graph in the step S21 by using a clustering algorithm to obtain N clustering areas;
and S23, dividing historical operation data under all acquisition moments corresponding to each clustering region into a data set under a stable operation working condition, so as to obtain data sets under N stable operation working conditions.
Preferably, in step S3, the data sets under the N stable operation conditions are used to train N identical initial unit performance evaluation models, respectively, and the implementation manner of obtaining the unit performance evaluation models suitable for the N stable operation conditions is as follows:
centralizing data under each stable operation condition into historical main steam pressure P at each acquisition moment z History main steam temperature T z History main steam flow F z Historical reheat steam pressure F hrh Historical reheat steam temperature T hrh Historical unit backpressure P b Historical unit heat supply steam extraction flow F g The data set is used as the input of an initial unit performance evaluation model corresponding to the data set under the stable operation working condition; taking the historical unit load E at each acquisition moment in the data set under each stable operation condition as the output of an initial unit performance evaluation model corresponding to the data set under the stable operation condition; and training the initial unit performance evaluation model corresponding to the data set under each stable operation working condition so as to obtain the unit performance evaluation model suitable for N stable operation working conditions.
Preferably, step S4, the real operation data of the unit at the current moment is acquired in real time during the unit sliding pressure operation, and the implementation manner of calculating the load deviation under each stable operation condition is, in combination with the unit performance evaluation models under N stable operation conditions:
the real main steam pressure P in the real operation data of the unit at the current moment z ', true main steam temperature T z ', true main steam flow F z ', true reheat steam pressure F' hrh True reheat steam temperature T' hrh Real unit back pressure P b ' and real machine set heat supply steam extraction flow F g ', as the input of the unit performance evaluation model under N kinds of steady operation working conditions at the same time;
the unit performance evaluation model under each stable operation condition carries out unit load estimation according to the received real operation data of the unit at the current moment and outputs a unit load estimation value E i ″；
Then, the unit load estimated value E is calculated i The difference is made with the real unit load E' to obtain the load deviation delta E under the ith stable operation working condition i ＝E i ″-E′；
Wherein, E i And the estimated value of the unit load output by the unit performance evaluation model under the ith stable operation condition is obtained.
Preferably, in step S5, the performance degradation deviation S is converted into the main steam pressure control amount Δ P z The implementation mode of the method is as follows:
wherein Hr is the ideal heat consumption of the unit, P z ' true main steam pressure, F, in the real operating data of the unit z The 'is the real main steam flow in the real operation data of the unit, and the E' is the real unit load in the real operation data of the unit.
Preferably, in the step S1, the sampling time interval t of the historical operating data in the preset time period is in a value range of 10 < t < 20, and the unit of t is second.
Preferably, the time length of the preset time period in step S1 is more than one week and less than 3 years.
Preferably, the load conditions of the historical operating data of the unit over the preset time period include 30% rated load, 40% rated load, 50% rated load, 60% rated load, 70% rated load, 80% rated load and 90% rated load.
Preferably, in step S1, the unit database is a database in the unit distributed control system.
The invention has the following beneficial effects:
1) According to the method, noise in historical operating data is eliminated by using a clustering method, and the denoised historical operating data is divided into N data sets under stable working conditions; the method removes noise in the training sample, improves the accuracy of the sample data, provides an accurate data base for subsequent model training, and improves the accuracy of subsequent sliding pressure operation control.
2) The unit performance evaluation models under each stable operation condition are respectively established for each stable operation condition, so that the inaccuracy of directly establishing a global model is avoided, and the unit performance evaluation models under each stable operation condition are respectively established under one stable operation condition;
3) The real unit load E' in the real-time operation data and the unit load estimated value E output by the unit performance evaluation model under each stable operation condition are calculated i The inter-deviation can determine the performance degradation deviation and the working condition of the current unit during the sliding pressure operation, and can convert the performance degradation deviation into the main steam pressure control quantity to carry out quantitative control on the operation state of the unit, thereby realizing the quantitative optimization on the sliding pressure operation of the steam turbine.
The method meets the sliding pressure optimization requirements of rapidity, instantaneity and accuracy on the basis of quantitative evaluation.
The method is used for providing a set of optimization which can be used for guiding the unit sliding pressure operation process on line on the basis of quantifying the unit operation performance reduction.
Drawings
FIG. 1 is a flow chart of a method for optimizing the operation of a turbine at a slip pressure according to the present invention;
FIG. 2 is a description diagram of input and output quantities of the model when the initial unit performance evaluation model is trained;
FIG. 3 is a graph of historical main steam pressure P for each acquisition time z The effect graph after clustering analysis is carried out on the relation graph between the historical unit load E and the relation graph;
fig. 4 is a diagram of the optimization effect of the unit sliding pressure operation.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive efforts based on the embodiments of the present invention, shall fall within the scope of protection of the present invention.
It should be noted that the embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Referring to fig. 1, the method for optimizing the sliding pressure operation of the steam turbine according to the embodiment includes the following steps:
s1, obtaining historical operation data of a corresponding unit in a preset time period from a unit database;
s2, clustering historical operating data in a preset time period, and dividing the historical operating data into data sets under N stable operating conditions; wherein, N stable operation working conditions are different, and N is an integer;
s3, training N identical initial unit performance evaluation models respectively by using data sets under N stable operation working conditions to obtain unit performance evaluation models suitable for the N stable operation working conditions;
s4, acquiring real operation data of the unit at the current moment in real time during the unit sliding pressure operation period, and calculating load deviation under each stable operation condition by combining unit performance evaluation models under N stable operation conditions so as to obtain N load deviations; taking the minimum value of the N load deviations as a performance degradation deviation s;
s5, converting the performance degradation deviation S into a main steam pressure control quantity delta P z To the operating state of the unitAnd controlling to complete the optimization of the sliding pressure operation of the steam turbine.
In the embodiment, the clustering method is utilized to eliminate the noise in the historical operating data, and the denoised historical operating data is divided into N data sets under stable working conditions; the method removes noise in the training sample, improves the accuracy of the sample data, provides an accurate data base for subsequent model training, and improves the accuracy of subsequent monitoring. And the unit performance evaluation models under each stable operation condition are respectively established according to each stable operation condition, so that the inaccuracy of directly establishing a global model is avoided, and when the method is applied, the stable operation condition corresponding to the minimum value of the N load deviations is used as the current unit operation condition.
When the model is applied, the initial unit performance evaluation model is an existing model which can be a BP neural network model, a CNN neural network model, an LSTM neural network model or a CNN-GRU neural network model.
Further, referring specifically to fig. 2, the historical operating data includes historical main steam pressure P collected at each collection time z History main steam temperature T z History main steam flow F z Historical reheat steam pressure F hrh Historical reheat steam temperature T hrh Historical unit backpressure P b Historical unit heat supply steam extraction flow F g And historical unit load E.
Further, referring to fig. 3 specifically, S2, clustering historical operating data in a preset time period, so as to segment the data set into N stable operating conditions, where the implementation manner is:
s21, extracting historical main steam pressure P at each acquisition moment from historical operation data in a preset time period z And historical unit load E, and drawing historical main steam pressure P at each acquisition time z And a relation graph between historical unit loads E;
s22, carrying out clustering analysis on the relation graph in the step S21 by using a clustering algorithm to obtain N clustering areas;
and S23, dividing historical operation data under all acquisition moments corresponding to each clustering region into a data set under a stable operation working condition, so as to obtain data sets under N stable operation working conditions.
In the preferred embodiment, a specific implementation manner for obtaining data sets under N stable operation conditions is provided, and when the method is applied specifically, the clustering algorithm can be implemented by using an FCM algorithm or a DBSCAN algorithm. Noise in historical operating data can be removed by dividing the data into N data sets under different stable operating conditions.
Further, step S3, training N same initial unit performance evaluation models by using the data sets under the N stable operation conditions, respectively, and obtaining the unit performance evaluation models suitable for the N stable operation conditions is implemented in the following manner:
centralizing data under each stable operation condition into historical main steam pressure P at each acquisition moment z History main steam temperature T z Historical main steam flow F z Historical reheat steam pressure F hrh Historical reheat steam temperature T hrh Historical unit backpressure P b Historical unit heat supply steam extraction flow F g The data set is used as the input of an initial unit performance evaluation model corresponding to the data set under the stable operation working condition; taking the historical unit load E at each acquisition moment in the data set under each stable operation condition as the output of an initial unit performance evaluation model corresponding to the data set under the stable operation condition; and training the initial unit performance evaluation model corresponding to the data set under each stable operation working condition so as to obtain the unit performance evaluation model suitable for N stable operation working conditions.
In the preferred embodiment, the data sets under N stable operation conditions are used to train N identical initial unit performance evaluation models respectively, so as to obtain the unit performance evaluation model corresponding to each stable operation condition, thereby accurately determining the stable operation condition corresponding to the real operation of the unit at the current time, that is: and the stable operation working condition corresponding to the minimum value in the N load deviations.
Furthermore, step S4, acquiring real operation data of the unit at the current time in real time during the unit sliding pressure operation, and calculating the load deviation under each stable operation condition by combining the unit performance evaluation models under N stable operation conditions:
real main steam pressure P in real operation data of the unit at the current moment z ', true main steam temperature T z ', true main steam flow F z ', true reheat steam pressure F' hrh True reheat steam temperature T' hrh Real unit back pressure P b ' Heat supply and steam extraction flow F of real unit g ', as the input of the unit performance evaluation model under N kinds of steady operation working conditions at the same time;
the unit performance evaluation model under each stable operation condition carries out unit load estimation according to the received real operation data of the unit at the current moment and outputs a unit load estimation value E i ″；
Then, the unit load estimated value E is calculated i "make a difference with the real unit load E', obtain the load deviation Delta E under the ith stable operation condition i ＝E i ″-E′；
Wherein E is i And the estimated value is the unit load estimated value output by the unit performance estimation model under the ith stable operation working condition.
In the preferred embodiment, the unit performance evaluation model under each stable operation condition is obtained by training the initial unit performance evaluation model through the data set under the corresponding stable operation condition.
Further, in step S5, the performance degradation deviation S is converted into the main steam pressure control amount Δ P z The implementation mode of the method is as follows:
wherein Hr is the ideal heat consumption of the unit, P z ' true main steam pressure, F, in the actual operating data of the unit z The 'is the real main steam flow in the real operation data of the unit, and the E' is the real unit load in the real operation data of the unit.
The preferred embodimentIn the method, the performance degradation deviation s is converted into the main steam pressure control quantity delta P z In the specific embodiment, the ideal heat consumption Hr of the unit can be obtained by consulting the thermodynamic specification of the unit, and the delta P z The calculation formula (2) is special for the invention.
Furthermore, in the step S1, the sampling time interval t of the historical operating data in the preset time period is in a value range of 10 < t < 20, and the unit of t is second.
Furthermore, in step S1, the time duration of the preset time period is greater than one week and less than 3 years.
Further, the load conditions of the historical operation data of the unit in the preset time period comprise 30% rated load, 40% rated load, 50% rated load, 60% rated load, 70% rated load, 80% rated load and 90% rated load.
Furthermore, in step S1, the unit database is a database in the unit distributed control system.
The technical effect of the invention can be verified by fig. 4, and fig. 4 is a diagram of the optimization effect of the unit sliding pressure operation; it can be seen from fig. 4 that the main steam pressure follows the load of the unit, and after the unit performance is reduced, the pressure value needs to be increased in order to reach the same load of the unit, and in order to adjust the load deviation, the adjustment amount of the main steam pressure is quantitatively given.
Although the invention herein has been described with reference to particular embodiments, it is to be understood that these embodiments are merely illustrative of the principles and applications of the present invention. It is therefore to be understood that numerous modifications may be made to the illustrative embodiments and that other arrangements may be devised without departing from the spirit and scope of the present invention as defined by the appended claims. It should be understood that various dependent claims and the features described herein may be combined in ways different from those described in the original claims. It is also to be understood that features described in connection with individual embodiments may be used in other described embodiments.
Claims (9)
1. The method for optimizing the sliding pressure operation of the steam turbine is characterized by comprising the following steps of:
s1, obtaining historical operation data of a corresponding unit in a preset time period from a unit database;
s2, clustering historical operating data in a preset time period, and dividing the historical operating data into data sets under N stable operating conditions; wherein N is an integer;
s3, training N same initial unit performance evaluation models respectively by using data sets under N stable operation working conditions to obtain unit performance evaluation models suitable for the N stable operation working conditions;
s4, acquiring real operation data of the unit at the current moment in real time during the unit sliding pressure operation period, and calculating load deviation under each stable operation condition by combining unit performance evaluation models under N stable operation conditions so as to obtain N load deviations; taking the minimum value of the N load deviations as a performance degradation deviation s;
s5, converting the performance degradation deviation S into a main steam pressure control quantity delta P z And controlling the running state of the unit so as to complete the optimization of the sliding pressure running of the steam turbine.
2. The method of optimizing the slip pressure operation of a steam turbine according to claim 1, wherein the historical operating data includes historical main steam pressure P collected at each collection time z History main steam temperature T z Historical main steam flow F z Historical reheat steam pressure F hrh Historical reheat steam temperature T hrh Historical unit backpressure P b Historical unit heat supply steam extraction flow F g And historical unit load E.
3. The method for optimizing the sliding pressure operation of the steam turbine according to claim 2, wherein S2, historical operation data in a preset time period are clustered, and therefore the data sets under N stable operation conditions are obtained by segmenting the historical operation data into the data sets under the N stable operation conditions:
s21, extracting historical main steam pressure P at each acquisition moment from historical operation data in a preset time period z And historical unit load E, and drawing historical main steam pressure P at each acquisition moment z And a relation graph between historical unit loads E;
s22, carrying out clustering analysis on the relation graph in the step S21 by using a clustering algorithm to obtain N clustering areas;
and S23, dividing historical operation data under all acquisition moments corresponding to each clustering region into a data set under a stable operation working condition, so as to obtain data sets under N stable operation working conditions.
4. The method for optimizing the sliding pressure operation of the steam turbine according to claim 2, wherein in the step S3, the data sets under the N stable operation conditions are used for training N same initial unit performance evaluation models respectively, and the implementation manner for obtaining the unit performance evaluation models under the N stable operation conditions is as follows:
centralizing data under each stable operation condition into historical main steam pressure P at each acquisition moment z History main steam temperature T z History main steam flow F z Historical reheat steam pressure F hrh Historical reheat steam temperature T hrh Historical unit backpressure P b Historical unit heat supply steam extraction flow F g The data set is used as the input of an initial unit performance evaluation model corresponding to the data set under the stable operation working condition; taking the historical unit load E at each acquisition moment in the data set under each stable operation condition as the output of an initial unit performance evaluation model corresponding to the data set under the stable operation condition; and training the initial unit performance evaluation model corresponding to the data set under each stable operation working condition so as to obtain the unit performance evaluation model suitable for N stable operation working conditions.
5. The method for optimizing the sliding pressure operation of the steam turbine according to claim 2, wherein step S4 is implemented by acquiring real operation data of the unit at the current moment in real time during the sliding pressure operation of the unit, and calculating the load deviation under each stable operation condition by combining unit performance evaluation models under N stable operation conditions:
real main steam pressure P in real operation data of the unit at the current moment z ', true main steam temperature T z ', true main steam flow F z ', true reheat steam pressure F' hrh True reheat steam temperature T' hrh Real unit back pressure P b ' Heat supply and steam extraction flow F of real unit g ', as the input of the unit performance evaluation model under N kinds of steady operation working conditions at the same time;
the unit performance evaluation model under each stable operation condition carries out unit load estimation according to the received real operation data of the unit at the current moment and outputs a unit load estimation value E i ″；
Then, the unit load estimated value E is calculated i The difference is made with the real unit load E' to obtain the load deviation delta E under the ith stable operation working condition i ＝E i ″-E′；
Wherein E is i And the estimated value is the unit load estimated value output by the unit performance estimation model under the ith stable operation working condition.
6. The method for optimizing the sliding pressure operation of a steam turbine according to claim 1, wherein in step S5, the performance degradation deviation S is converted into a main steam pressure control amount Δ P z The implementation mode of the method is as follows:
wherein Hr is the ideal heat consumption of the unit, P z ' true main steam pressure, F, in the actual operating data of the unit z The 'is the real main steam flow in the real operation data of the unit, and the E' is the real unit load in the real operation data of the unit.
7. The method for optimizing the sliding pressure operation of the steam turbine according to claim 1, wherein the sampling time interval t of the historical operating data in the preset time period in the step S1 is in a range of 10 < t < 20, and t is in seconds.
8. The method for optimizing the sliding pressure operation of a steam turbine according to claim 1, wherein the predetermined period of time in step S1 is longer than one week and shorter than 3 years.
9. The method for optimizing the sliding pressure operation of a steam turbine according to claim 1, wherein the database of the steam turbine in step S1 is a database in a distributed control system of the steam turbine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211085776.9A CN115450710A (en) | 2022-09-06 | 2022-09-06 | Method for optimizing sliding pressure operation of steam turbine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211085776.9A CN115450710A (en) | 2022-09-06 | 2022-09-06 | Method for optimizing sliding pressure operation of steam turbine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115450710A true CN115450710A (en) | 2022-12-09 |
Family
ID=84302310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211085776.9A Pending CN115450710A (en) | 2022-09-06 | 2022-09-06 | Method for optimizing sliding pressure operation of steam turbine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115450710A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117307266A (en) * | 2023-08-31 | 2023-12-29 | 中科合肥技术创新工程院 | Control system for vortex cavitation flow in low-temperature liquid expander |
-
2022
- 2022-09-06 CN CN202211085776.9A patent/CN115450710A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117307266A (en) * | 2023-08-31 | 2023-12-29 | 中科合肥技术创新工程院 | Control system for vortex cavitation flow in low-temperature liquid expander |
| CN117307266B (en) * | 2023-08-31 | 2024-03-19 | 中科合肥技术创新工程院 | Control system for vortex cavitation flow in low-temperature liquid expander |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111159844B (en) | Abnormity detection method for exhaust temperature of gas turbine of power station | |
| CN111505943B (en) | Steam turbine flow characteristic optimization method based on full-stroke modeling | |
| CN110197296B (en) | Unit load prediction method based on time series similarity | |
| CN112180739A (en) | Parameter optimization method for superheated steam temperature control system | |
| CN115450710A (en) | Method for optimizing sliding pressure operation of steam turbine | |
| CN110705042A (en) | Steam turbine valve flow characteristic identification method, system and medium based on T-S fuzzy model | |
| WO2023045425A1 (en) | Method and system for evaluating risk of intradialytic hypotension event | |
| CN109032117A (en) | Single loop control system method of evaluating performance based on arma modeling | |
| US7269466B2 (en) | Optimal operation controller of plant | |
| CN109270917B (en) | Intelligent power plant steam turbine bearing-oriented closed-loop control system fault degradation state prediction method | |
| CN103631991B (en) | Parameter identification system and method of prime mover speed regulating system | |
| CN113268921B (en) | Condenser cleaning coefficient estimation method and system, electronic device and readable storage medium | |
| CN110032791B (en) | Turbine low-pressure cylinder efficiency real-time calculation method based on generalized regression neural network | |
| CN114315058A (en) | Water treatment control method, system, computer equipment and storage medium | |
| CN110322063A (en) | A kind of power consumption simulated prediction method and storage medium | |
| CN111367255A (en) | Performance evaluation test system and method for multi-variable control system | |
| CN105607477A (en) | Industrial control circuit oscillation detection method based on improved local mean value decomposition | |
| CN114819743B (en) | Energy consumption diagnosis and analysis method for chemical enterprises | |
| CN111695300A (en) | Steam turbine valve flow fitting method and system | |
| CN113078638B (en) | Thermal power generating unit AGC performance index calculation method and system based on fuzzy model | |
| CN117452989B (en) | BP neural network-based temperature regulation and control valve performance regulation and test method | |
| CN113361748B (en) | Unit power supply coal consumption prediction method suitable for online load distribution | |
| CN117011092B (en) | Intelligent building equipment management monitoring system and method | |
| CN116500898B (en) | Thermal power generating unit AGC load control system based on characteristic flow identification | |
| CN114322321B (en) | Gray prediction extension constant temperature control method for gas water heater |
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 |