CN102840571A - Subspace identification based forecasting method for superheated steam output of boiler of firepower power station - Google Patents
Subspace identification based forecasting method for superheated steam output of boiler of firepower power station Download PDFInfo
- Publication number
- CN102840571A CN102840571A CN2012103497375A CN201210349737A CN102840571A CN 102840571 A CN102840571 A CN 102840571A CN 2012103497375 A CN2012103497375 A CN 2012103497375A CN 201210349737 A CN201210349737 A CN 201210349737A CN 102840571 A CN102840571 A CN 102840571A
- Authority
- CN
- China
- Prior art keywords
- boiler
- data
- energy
- model
- superheated steam
- 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
Images
Landscapes
- Feedback Control In General (AREA)
- Control Of Steam Boilers And Waste-Gas Boilers (AREA)
Abstract
The invention discloses a subspace identification based forecasting method for superheated steam output of a boiler of a firepower power station, which comprises the following steps: firstly, acquiring production data from plant-level DCS (Distributed Control System) configuration software at regular time; secondly, correcting bad points, filtering and denoising; thirdly, calculating input and output variables required by model identification; fourthly, constructing an Hankel matrix by utilizing continuous acquired and processed data and rolling to update; fifthly, approximating the boiler process to a linear state space model; sixthly, using a subspace theory to identify a matrix of the state space model [A, B, C and D]; seventhly, utilizing the latest input energy information as the obtained input variables of the state space model after the identification and calculating output energy of future moments; eighthly, calculating the mean value at the same time by utilizing a historical forecast value and a current forecast result and correcting by utilizing the past forecast deviation; and ninthly, rolling to update the data of identification of the model. The forecasting method is applicable to online forecast of superheated steam output energy in the boiler production process and provides guidance and reference for the optimization control of boiler combustion.
Description
Technical field
The present invention relates to the forecasting procedure that a kind of firepower power station boiler based on Subspace Identification exports superheated steam.
Background technology
The target of boiler combustion optimization control is that under certain unit load, the running status that efficient superheated steam exports energy and stable safety is obtained by adjusting the operational factors such as boiler coal feeding, air distribution, air inducing.Energy is an extremely complex production procedure from superheated steam is passed to coal, is difficult to determine model structure and model parameter during using modelling by mechanism, therefore more researchs concentrate on the black-box model of data-driven or the grey-box model of half mechanism half data at present.Being currently based on the boiler modeling method of data-driven mainly has artificial neural network and SVMs etc..The modeling method for the boiler combustion optimization that such as Xue An grams of Electronic University Of Science & Technology Of Hangzhou, Wang Chunlin et al. propose(Patent publication No. CN 101498459A), it is modeled according to the segmentation of the height of unit operation load, radial basis neural network is set up in high load capacity section, and set up supporting vector machine model in underload section, that is, one is set up based on the mixed model under different unit loads section.But, this method only establishes the static association between each service data of boiler, production scene as run into load lifting special operation condition when, mixed model may switch constantly between neutral net and SVMs, the continuity of process data needed for Model Distinguish can not be ensured, dynamic accuracy is relatively low.In addition, First air/secondary air flow and the measuring point such as draught flow rate that the above method is used, the influence of temperature and pressure information is not considered, therefore the application of institute's established model also suffers from the influence of season and weather.
The content of the invention
The technical problem to be solved in the present invention is, it is proposed that a kind of online rolling modeling based on data-driven and the energy forecasting procedure based on institute's established model;Clearly, and without data are carried out with cluster analysis processing, model on-line identification speed is fast for the Data Physical meaning that the energy dynamics model and Model Distinguish that the present invention is set up are used, while introducing model rolls identification scheme, improves the generalization ability of model.The dynamic model recognized to multistep is averaged in the output forecast of following synchronization, and is corrected using last moment forecast departure, further improves the forecast precision that boiler exports superheated steam energy.According to the predicting condition to following 60 seconds superheated steam energy, it can be determined that following combustion case of boiler, the final optimal control for burning provides guidance and referred to.
The technical scheme is that:Boiler overheating steam energy forecasting procedure based on data-driven, is comprised the steps of:
Step 1:Data communication is set up with level of factory DCS configuration softwares, creation data, including boiler operating parameter and the measuring point information for characterizing boiler combustion situation are obtained online.
Step 2:The judgement and processing of abnormity point are carried out to collection measuring point information according to unit load, and using the preceding high-frequency noise that measuring point is removed to weighted filtering method.
Step 3:According to vapor and the calculation of thermodynamics formula of air, the energy of air-supply, air inducing and the superheated steam of current time boiler is calculated.Simultaneously the thermal discharge of coal dust firing is calculated using the as-fired coal matter information of off-line analysis.The input data and output data of boiler model identification are determined, and data are normalized.
Step 4:The data that the energy record obtained by the use of continuous acquisition and calculating is recognized as boiler condition spatial model, while the rolling for completing Model Distinguish data updates, construct input and outputHankelMatrix.
Step 5:By the boiler for producing in short time period similar to a linear process, system separate manufacturing firms expression formula is as follows:
In formula,,It is that system exists respectivelytState vector, input observation vector and the output observation vector at moment,nFor the order of unidentified system,For the white noise sequence of a zero-mean.
Step 6:Using open loop subspace method recognize boiler model sytem matrixA,B,C,D}。
Step 7:Using newest boiler input energy data, the input variable of the state-space model obtained as identification calculates the boiler overheating steam for obtaining future time instance(Main steam and reheat heat steam)Export energy.
Step 8:The superheated steam energy calculated with the model currently recognized is forecast, following predicted value mutually in the same time is averaged with last moment, last moment, to the forecast of current output energy and the deviation of the actual energy currently calculated the output energy following 5 seconds to correct current forecast, obtains the forecast result of following 60 seconds output superheated steam energy of steam generator system simultaneously.
Step 9:The new data for being gathered and being obtained after pretreatment with current time substitutes the legacy data of most original, and the rolling for completing Model Distinguish data updates.Return to step 4 carries out the Model Distinguish and forecast of subsequent time.
The main measuring point information by boiler operating parameter and sign boiler combustion situation of the creation data of collection is constituted, wherein boiler operating parameter includes unit load, feeder gives coal speed, one/secondary air flow, pressure and temperature, air-introduced machine section flue gas flow, pressure and temperature etc.;Characterizing the measuring point information of boiler combustion situation includes main steam and reheated steam flow, pressure and temperature etc..
The judgement and processing and online denoising of the abnormity point, specific practice are, to being distinguished in load with respect to the measuring point that saltus step occurs in the stabilization sub stage, to carry out export-oriented difference using the preceding 2 measuring point information clapped and replace:x n =2x n-1 -x n-2 .It is online to use preceding to 5 weighted filtering methods, to remove high-frequency noise, Filtering Formula:x n =0.04x n-4 -0.08x n-3 +0.13x n-2 +0.25x n-1 +0.5x n 。
Described data normalization processing is as follows:
WhereinXFor the initial data of input and output,X min WithX max Respectively recordXIn minimum value and maximum,X * For the value after normalization.
It is of the invention compared with conventional data-driven modeling method, the data that the dynamic model of foundation and identification are used all possess clear and definite physical meaning.Model accuracy is improved using discrimination method is rolled, while also reflects the objective fact that boiler process parameter can change with time and unit load.In addition this method on-line identification model velocity is fast, the superheated steam energy high precision exported using model prediction boiler.The dynamic model recognized to multistep is averaged in the output forecast of following synchronization, and is corrected using last moment forecast departure, further improves the forecast precision that boiler exports superheated steam energy.According to the predicting condition to following 60 seconds superheated steam energy, it can be determined that following combustion case of boiler, the final optimal control for burning provides guidance and referred to.
Brief description of the drawings
The state-space model input/output variable schematic diagram of Fig. 1 steam generator systems;
Online rolling identification value of forecasting figures of the Fig. 2 based on data-driven;
Wherein, solid line represents the model prediction boiler overheating steam using identification(Main steam and reheat heat steam)Energy is exported, open circles are that the actual superheated steam of the boiler calculated using the measuring point information for characterizing boiler combustion situation exports energy.
Embodiment
The present invention is further described and described by the following examples, the present embodiment is implemented lower premised on technical solution of the present invention, gives detailed embodiment and specific operating process, but protection scope of the present invention is not limited to following embodiments.
Embodiment
Firepower power station boiler operatiopn in the present embodiment needs to meet following condition:
A. boiler for producing is approximately a linear process in a short time;
B. one/secondary air flow, absorbing quantity and burner hearth powder amount of delivering coal are in manual open loop control mode;
C. all control signals are Persistent Excitations;
D. control signal and process random noise are incoherent;
E. the measurement data amount of collection in worksite storage is enough;
The present embodiment step is as follows:
Step 1:OPC data communication is set up with level of factory DCS configuration softwares, a creation data was gathered every 5 seconds online, the measuring point information of acquisition mainly includes:Unit load, feeder gives coal speed, one/secondary air flow, pressure and temperature, and the boiler operating parameter such as air-introduced machine section flue gas flow, pressure and temperature, and main steam and reheated steam flow, pressure and temperature etc. characterize the measuring point information of boiler combustion situation.
Step 2:Judge that current moment collection measuring point information whether there is abnormity point according to unit load, particularly to there is the measuring point of saltus step with respect to the stabilization sub stage in load, the abnormity point that export-oriented difference replaces saltus step is carried out using the preceding 2 measuring point information clapped:x n =2x n-1 -x n-2 .It is online to use preceding to 5 weighted filtering methods, to remove high-frequency noise, Filtering Formula:x n =0.04x n-4 -0.08x n-3 +0.13x n-2 +0.25x n-1 +0.5x n 。
Step 3:According to vapor and the calculation of thermodynamics formula of air, energy of the current time to the air-supply of boiler, air inducing and superheated steam is calculated.Simultaneously the thermal discharge of coal dust firing is calculated using the as-fired coal matter information of off-line analysis.Using one/Secondary Air energy, smoke evacuation energy and the input data that is recognized as boiler model of cold reheated steam energy, using main steam energy and reheat heat steam energy as Model Distinguish output data.The data of input/output are normalized respectively as follows:
WhereinXThe energy datum for inputting or exporting for steam generator system,X min WithX max It is respectively existingXMinimum value and maximum in record,X * For the value after normalization.
Step 4:The half an hour energy record obtained by the use of continuous acquisition and calculating models required Identification Data, wherein First air energy, Secondary Air energy as boiler, energy of discharging fume, to coal combustion thermal discharge and cold reheated steam energy composition input vectoru k , output vectory k It is made up of main steam energy and reheat heat steam energy, output data is set to 60 seconds compared with input data lag time.The input vector of steam generator systemu k ConstructioniOKjRowHankelMatrix is as follows:
The need for according to Model Distinguish, if identification is needed altogether(2i+j-1)Group data, it is precedingiPoint data constitutes first rowHankelMatrix, uses subscriptpRepresent " past ";Fromi+ 1 to 2iThe first row that data are constitutedHankelMatrix, uses subscriptfRepresent " future ".Similarly, to inputy k Vector constructionHankelMatrixWith;And to noise e k Vector constructionHankelMatrixWith.TypicallyiIt is related to system order to be identified, it is unsuitable too small or excessive, andjIt should select sufficiently large, generally ensureCarry out identification system, while can reduce the influence of noise, the present embodiment takesi=12,j=700.Other system " past " and " future " status switch are defined as follows:
Step 5:By the boiler for producing in half an hour similar to a linear process, as shown in Figure 1, the separate manufacturing firms expression formula of system is as follows for its five inputs, two output variable schematic diagram:
In formula,,It is that system exists respectivelytState vector, input observation vector and the output observation vector at moment,nFor the order of unidentified system,For the white noise sequence of a zero-mean.
Step 6:Identification system matrixA,B,C,D}。
2)The conversion of matrix identification problem
Current time can be derived by the state-space expression of systemtState vectorx t With past statex t-1 , inputy t-1 And outputu t-1 Between relational expression:
To state vectorx t-1 Further spread out:
It is respectively by above formula variable subscriptT=N, N+1 ... N+j-1When expression formula combine and can obtain:
In above formula, due toKIt is Kalman filtering gain,Represent the dynamic error of Kalman filtering.Therefore work asNWhen sufficiently large, Kalman filtering is stable, is had.So when Identification Data is enough, i.e.,NWhen very big, above formula is converged on:
It can be released by the output equation of system state space again:
In formulaIt is the subspace matrices related with output to past input;It is the subspace matrices related to following certainty input;It is to be inputted with following randomness(Noise)Related subspace matrices.And have,,。
When certainty inputWith randomness noiseWhen orthogonal, the problem can be reduced to find one to future outputA linear predictor:
The analytic solutions of the problem are:
Following matrix is carried outQRDecompose:
In above formulaRepresenting matrixMoore-PenroseGeneralized inverse, can pass throughSVDDecompose and solve.Again to subspace matricesCarry outSVDDecomposition has:
In formulaSufficiently small diagonal element is approximately zero, andDimension can be used as the dimension for being identified state space matrices A.ByUnderstandColumn space should be withColumn space it is equal, what its dimension was defined before being systematic education to be identified, recyclingIt can determine respectivelyMatrix and to-beMatrix:
4)Determine unidentified system matrixA,B,C,D}。
By extension ornamental matrixDefinition, preceding m rows are exactly the C matrixes of system state space model, orderForRemove the matrix of preceding m rows,ForRemove the matrix of rear m rows, have
So as to which the A matrixes and C matrixes that obtain steam generator system state-space model are:
In formulaIt isOrthocomplement, orthogonal complement subset, above formula is deployed item by item to have:
Carrying out algebraic transformation to above formula can obtain on sytem matrixBWithDLinear equation, and then try to achieve unidentified systemBMatrix andDMatrix:
The steam generator system separate manufacturing firms model expression tried to achieve is as follows:
Step 7:Using the boiler input energy data of newest 60 seconds, the input variable of the state-space model obtained as identification, calculated value was the boiler overheating steam of steam generator system output in following 60 seconds(Main steam and reheat heat steam)Energy.
Step 8:Roll the energy that the model after identification can be used to the following 60 seconds boilers output of forecast every time, if the predicted value of previous step for [y a1,y a2,…,y a12], the predicted value that current step model is calculated for [y b1,y b2,…,y b12](WhereinyFor 2 dimensional vectors, comprising main steam energy and heat in vapours energy), then the predicted value to following 60 seconds superheated steam energy is [0.5y b1+0.5y a2+r, 0.5y b2+0.5y a3, …, 0.5y b11+0.5y a12, y b12], wherein r is that previous step forecasts output in following 5 seconds and the current actual deviation for calculating output of step system, the output energy following 5 seconds to correct current forecast.
Step 9:The legacy data for the new data replacement most original that pretreatment is obtained is gathered with current time, the rolling for completing Model Distinguish data updates.Return to step 4 carries out the Model Distinguish and forecast of subsequent time.
This example demonstrates the collection of DCS real process data, pretreatment, the method for calculating and updating, and utilize rolling discrimination method and forecasting procedure of the online data after processing to boiler condition spatial model, the energy for forecasting the superheated steam that boiler is produced can be used for, the value of forecasting is shown in accompanying drawing 2, and predicted value can provide reference and instruct for the optimal control of firepower power station boiler combustion.
Claims (4)
1. a kind of firepower power station boiler based on Subspace Identification exports the forecasting procedure of superheated steam, its feature exists:The method includes the steps of:
Step 1:Data communication is set up with level of factory DCS configuration softwares, creation data, including boiler operating parameter and the measuring point information for characterizing boiler combustion situation are obtained online;
Step 2:The judgement and processing of abnormity point are carried out to collection measuring point information according to unit load, and using the preceding high-frequency noise that measuring point is removed to weighted filtering method;
Step 3:According to vapor and the calculation of thermodynamics formula of air, the energy of air-supply, air inducing and the superheated steam of current time boiler is calculated;Simultaneously the thermal discharge of coal dust firing is calculated using the as-fired coal matter information of off-line analysis;The input data and output data of boiler model identification are determined, and data are normalized;
Step 4:The data that the energy record obtained by the use of continuous acquisition and calculating is recognized as boiler condition spatial model, while the rolling for completing Model Distinguish data updates, construct input and outputHankelMatrix;
Step 5:By the boiler for producing in short time period similar to a linear process, system separate manufacturing firms expression formula is as follows:
In formula,,It is that system exists respectivelytState vector, input observation vector and the output observation vector at moment,nFor the order of unidentified system,For the white noise sequence of a zero-mean;
Step 6:Using open loop subspace method recognize boiler model sytem matrixA,B,C,D};
Step 7:Using newest boiler input energy data, the input variable of the state-space model obtained as identification calculates the boiler overheating steam for obtaining future time instance(Main steam and reheat heat steam)Export energy;
Step 8:The superheated steam energy calculated with the model currently recognized is forecast, following predicted value mutually in the same time is averaged with last moment, last moment, to the forecast of current output energy and the deviation of the actual energy currently calculated the output energy following 5 seconds to correct current forecast, obtains the forecast result of following 60 seconds output superheated steam energy of steam generator system simultaneously;
Step 9:The new data for being gathered and being obtained after pretreatment with current time substitutes the legacy data of most original, and the rolling for completing Model Distinguish data updates;Return to step 4 carries out the Model Distinguish and forecast of subsequent time.
2. the firepower power station boiler according to claim 1 based on Subspace Identification exports the forecasting procedure of superheated steam, it is characterised in that:The main measuring point information by boiler operating parameter and sign boiler combustion situation of the creation data of collection is constituted, and boiler operating parameter includes unit load, and feeder gives coal speed, one/secondary air flow, pressure and temperature, air-introduced machine section flue gas flow, pressure and temperature;Characterizing the measuring point information of boiler combustion situation includes main steam and reheated steam flow, pressure and temperature.
3. the firepower power station boiler according to claim 1 based on Subspace Identification exports the forecasting procedure of superheated steam, it is characterised in that:The specific practice of judgement and processing and the online denoising of abnormity point is, to being distinguished in load with respect to the measuring point that saltus step occurs in the stabilization sub stage, to carry out export-oriented difference using the preceding 2 measuring point information clapped and replace:x n =2x n-1 -x n-2 ;It is online to use preceding to 5 weighted filtering methods, to remove high-frequency noise, Filtering Formula:x n =0.04x n-4 -0.08x n-3 +0.13x n-2 +0.25x n-1 +0.5x n 。
4. the firepower power station boiler according to claim 1 based on Subspace Identification exports the forecasting procedure of superheated steam, it is characterised in that:Data normalization processing is as follows:
WhereinXFor the initial data of input and output,X min WithX max Respectively recordXIn minimum value and maximum,X * For the value after normalization.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210349737.5A CN102840571B (en) | 2012-09-20 | 2012-09-20 | Firepower power station boiler based on Subspace Identification exports the forecasting procedure of superheated steam |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210349737.5A CN102840571B (en) | 2012-09-20 | 2012-09-20 | Firepower power station boiler based on Subspace Identification exports the forecasting procedure of superheated steam |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102840571A true CN102840571A (en) | 2012-12-26 |
CN102840571B CN102840571B (en) | 2015-08-12 |
Family
ID=47368178
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210349737.5A Active CN102840571B (en) | 2012-09-20 | 2012-09-20 | Firepower power station boiler based on Subspace Identification exports the forecasting procedure of superheated steam |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102840571B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105629736A (en) * | 2016-03-22 | 2016-06-01 | 东南大学 | Data-driven thermal power generation unit SCR denitration disturbance suppression prediction control method |
CN106339788A (en) * | 2016-08-02 | 2017-01-18 | 华电电力科学研究院 | DCS (distributed control system)-based thermal power unit performance index calculating device and method |
CN108255063A (en) * | 2018-01-26 | 2018-07-06 | 深圳禾苗通信科技有限公司 | A kind of small-sized rotor unmanned aircraft system modeling method based on Closed-Loop Subspace Identification |
CN109507910A (en) * | 2018-10-31 | 2019-03-22 | 国网河南省电力公司电力科学研究院 | A kind of fired power generating unit modeling and control method based on data-driven |
CN110095982A (en) * | 2019-04-22 | 2019-08-06 | 江苏中科云控智能工业装备有限公司 | The control method of load characteristic automatic identification method, state-space model and power supply |
CN112036088A (en) * | 2020-09-03 | 2020-12-04 | 华能国际电力股份有限公司玉环电厂 | Superheated steam temperature prediction method based on multi-innovation random gradient optimization |
CN113359441A (en) * | 2021-05-26 | 2021-09-07 | 东南大学溧阳研究院 | Uncertainty compensation based combustion chamber thermal acoustic oscillation model prediction control method |
CN114492956A (en) * | 2022-01-07 | 2022-05-13 | 上海烁恒科技有限责任公司 | Working condition prediction method and equipment based on historical data search and storage medium |
CN115234936A (en) * | 2022-09-22 | 2022-10-25 | 海安玻克超硬材料有限公司 | Identification processing method for combustion efficiency of biomass combustor |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101709863A (en) * | 2009-12-18 | 2010-05-19 | 杭州电子科技大学 | Hybrid control method for furnace pressure system of coal-fired boiler |
CN101825869A (en) * | 2010-05-13 | 2010-09-08 | 上海交通大学 | Method for identifying superheater model parameters based on data drive |
CN102103376A (en) * | 2010-12-16 | 2011-06-22 | 浙江大学 | Method for evaluating control performance of PID (Proportion Integration Differentiation) loop based on subspace identification |
JP2011196658A (en) * | 2010-03-23 | 2011-10-06 | Miura Co Ltd | Program, controller and boiler system |
-
2012
- 2012-09-20 CN CN201210349737.5A patent/CN102840571B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101709863A (en) * | 2009-12-18 | 2010-05-19 | 杭州电子科技大学 | Hybrid control method for furnace pressure system of coal-fired boiler |
JP2011196658A (en) * | 2010-03-23 | 2011-10-06 | Miura Co Ltd | Program, controller and boiler system |
CN101825869A (en) * | 2010-05-13 | 2010-09-08 | 上海交通大学 | Method for identifying superheater model parameters based on data drive |
CN102103376A (en) * | 2010-12-16 | 2011-06-22 | 浙江大学 | Method for evaluating control performance of PID (Proportion Integration Differentiation) loop based on subspace identification |
Non-Patent Citations (1)
Title |
---|
李经昊: "子空间预测控制及其在CFB锅炉燃烧***的研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105629736B (en) * | 2016-03-22 | 2018-03-20 | 东南大学 | The fired power generating unit SCR denitration Disturbance Rejection forecast Control Algorithm of data-driven |
CN105629736A (en) * | 2016-03-22 | 2016-06-01 | 东南大学 | Data-driven thermal power generation unit SCR denitration disturbance suppression prediction control method |
CN106339788B (en) * | 2016-08-02 | 2020-04-24 | 华电电力科学研究院 | Thermal power generating unit performance index calculation device and method based on DCS |
CN106339788A (en) * | 2016-08-02 | 2017-01-18 | 华电电力科学研究院 | DCS (distributed control system)-based thermal power unit performance index calculating device and method |
CN108255063A (en) * | 2018-01-26 | 2018-07-06 | 深圳禾苗通信科技有限公司 | A kind of small-sized rotor unmanned aircraft system modeling method based on Closed-Loop Subspace Identification |
CN109507910A (en) * | 2018-10-31 | 2019-03-22 | 国网河南省电力公司电力科学研究院 | A kind of fired power generating unit modeling and control method based on data-driven |
CN110095982A (en) * | 2019-04-22 | 2019-08-06 | 江苏中科云控智能工业装备有限公司 | The control method of load characteristic automatic identification method, state-space model and power supply |
CN112036088A (en) * | 2020-09-03 | 2020-12-04 | 华能国际电力股份有限公司玉环电厂 | Superheated steam temperature prediction method based on multi-innovation random gradient optimization |
CN113359441A (en) * | 2021-05-26 | 2021-09-07 | 东南大学溧阳研究院 | Uncertainty compensation based combustion chamber thermal acoustic oscillation model prediction control method |
CN114492956A (en) * | 2022-01-07 | 2022-05-13 | 上海烁恒科技有限责任公司 | Working condition prediction method and equipment based on historical data search and storage medium |
CN114492956B (en) * | 2022-01-07 | 2024-03-12 | 上海烁恒科技有限责任公司 | Working condition prediction method, equipment and storage medium based on historical data search |
CN115234936A (en) * | 2022-09-22 | 2022-10-25 | 海安玻克超硬材料有限公司 | Identification processing method for combustion efficiency of biomass combustor |
CN115234936B (en) * | 2022-09-22 | 2022-12-13 | 海安玻克超硬材料有限公司 | Identification processing method for combustion efficiency of biomass combustor |
Also Published As
Publication number | Publication date |
---|---|
CN102840571B (en) | 2015-08-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102840571A (en) | Subspace identification based forecasting method for superheated steam output of boiler of firepower power station | |
EP2729891B1 (en) | Automatic identification of operating parameters for power plants | |
EP1921280B1 (en) | Systems and methods for multi-level optimizing control systems for boilers | |
Tong et al. | Observer-based adaptive fuzzy backstepping output feedback control of uncertain MIMO pure-feedback nonlinear systems | |
Fang et al. | Backstepping-based nonlinear adaptive control for coal-fired utility boiler–turbine units | |
CN106765052A (en) | A kind of intelligence computation forecast Control Algorithm of station boiler vapor (steam) temperature | |
CN106873381A (en) | Spray ammonia control system | |
CN106406101B (en) | A kind of intelligence computation forecast Control Algorithm of fired power generating unit coordinated control system | |
CN110285403A (en) | Main Steam Temperature Control method based on controlled parameter prediction | |
CN111130106B (en) | Attack detection method for multi-region power system | |
CN103728879A (en) | Power station boiler emission soft measuring method based on least squares support vector machine and on-line updating | |
CN105787583A (en) | Metallurgical gas integrated dynamic balance scheduling system and method | |
US20150227121A1 (en) | Method for controlling and/or regulating a technical system in a computer-assisted manner | |
CN110941186B (en) | Steam temperature control optimization method based on neural network and universal gravitation search algorithm | |
CN103729569A (en) | Soft measurement system for flue gas of power-station boiler on basis of LSSVM (Least Squares Support Vector Machine) and online updating | |
Ding et al. | Application of Fuzzy Immune Algorithm and Soft Computing in the Design of 2‐DOF PID Controller | |
Dokht Shakibjoo et al. | Online adaptive type-2 fuzzy logic control for load frequency of multi-area power system | |
JP2016537729A (en) | Method, system, and computer program product for analyzing generation processes and / or process engineering processes and / or process steps in a plant | |
US11287126B2 (en) | System and method for controlling operation of boiler | |
CN113885607B (en) | Steam temperature control method and device, electronic equipment and computer storage medium | |
CN109670636B (en) | Optimization method and device of energy scheduling model for universal energy station | |
Sujatha et al. | Soft sensor with shape descriptors for flame quality prediction based on lstm regression | |
Song et al. | Optimization of temporal processes: a model predictive control approach | |
CN114562713A (en) | Main steam temperature control method and system for power generation boiler | |
Ma et al. | ANN and PSO based intelligent model predictive optimal control for large-scale supercritical power unit |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |