CN105240822A - Control method and system for three gas duct baffles of boiler based on neural network - Google Patents
Control method and system for three gas duct baffles of boiler based on neural network Download PDFInfo
- Publication number
- CN105240822A CN105240822A CN201510592072.4A CN201510592072A CN105240822A CN 105240822 A CN105240822 A CN 105240822A CN 201510592072 A CN201510592072 A CN 201510592072A CN 105240822 A CN105240822 A CN 105240822A
- Authority
- CN
- China
- Prior art keywords
- boiler
- load
- fluctuation
- temperature
- neutral net
- 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
Landscapes
- Control Of Steam Boilers And Waste-Gas Boilers (AREA)
Abstract
The invention relates to the technical field of boilers and discloses a control method and system for three gas duct baffles of a boiler based on a neural network. The control method specifically comprises the following steps that firstly, sample data for control over the three gas duct baffles of the boiler are collected, a neural network model is established, and the network model is trained through a learning method; secondly, final state load and steam temperatures {Load; T0; T1; T2} at an outlet of the boiler are obtained after fluctuation; thirdly, the network model trained in the first step serves as a solution objective function, the final state load and the steam temperatures at the outlet of the boiler after fluctuation obtained in the second step serve as input conditions, and opening degree sets {K1; K2; K3} of the three gas baffles at the tail portion of a gas duct are obtained through operation; and fourthly, the movement of the baffles is controlled according to the opening degree sets , and accordingly temperature adjustment is achieved. The invention further discloses a control system for the three gas duct baffles of the boiler based on the neural network. A self-learning function is introduced into the control over the power station boiler through a neural network algorithm, and therefore the intelligence level of operation of the power station boiler is improved.
Description
Technical field
The present invention relates to boiler technology field, particularly the double reheat boiler of afterbody three flue, it relates to a kind of boiler three damper control method based on neutral net and system.
Background technology
At present, fired power generating unit is towards the future development of Large Copacity, high parameter.Double reheat power generation sets makes boiler increase one-level reheat vapor cycle, compared with single reheat boiler, generatine set heat efficiency is higher, but along with reheating progression increases, boiler heating surface is arranged and is tending towards complicated, the complexity and difficulties also corresponding increase that Steam Temperature for Boiler controls, the wherein topmost control being double reheating steam temperature, regulate the steam temperature of reheated steam and have higher requirement, rational steam temperature regulative mode is the strong guarantee of unit safety, economy, reliability.
In the method for temperature control of double reheat boiler, the method for temperature control of reheater comprises the modes such as tilting burner, flue gas recirculation, reheated steam bypass, spray desuperheating, gas baffle adjustment.Under Integrated comparative, the double reheat boiler of afterbody three flue is wherein adopted (namely respectively to arrange a controllable register in the below of each flue, each baffle plate regulates separately steam temperature at different levels) reliability is high, bidirectional temp regulation can be realized, do not increase unit station service in actual moving process, and investment operation and maintenance cost is low.
Double reheat power generation sets, when boiler startup, load variations, the adjustment between Stream temperature degree and the temperature of double reheating can influence each other, and how to find the equalization point between three, and in temperature adjustment process, ensure heating surface not overtemperature, is key issue place.
Arrange in the double reheat boiler of three flues at afterbody, three gas baffles, just be equipped with six executing agencies, in actual moving process, baffle plate on flue is controlled by logical order, need to make steam reach rated temperature by adjustment through the exhaust gas volumn of this side flue, the action of each executing agency can have an impact to the superheated steam of boiler export, single reheat steam and double reheat steam, and therefore this adjustment process is a process of repeatedly mating.And the adjustment of baffle plate has hysteresis quality, after baffle plate action, need one section of phase buffer can reflect on steam steam temperature.Therefore, after unit load variation, rely on conventional control logic instruction to realize the adjustment of three gas baffles, need the process that longer.
Existing method passes through Boiler debugging, by the curve of the baffle opening of each flue under various ature of coal with load variations (namely with exhaust gas volumn change), be programmed in boiler implosion program, when load is about to change, by preset three baffle openings of design load, on this basis, finely tuned successively by temperature adjustment control sequence.Here temperature adjustment control sequence refers to, three baffle plates move successively, is first turned down side shield now, and after the caloric receptivity summation of single reheat device and secondary reheater reaches rated value (T1+T2=rated value), low side shield aperture of crossing is determined.And then regulate single reheat device side shield, after the caloric receptivity deviation of single reheat device and secondary reheater reaches rated value (T1-T2=rated value), single reheat device side shield aperture is determined.Then three baffle openings are determined all completely.
And boiler is changeable because use coal, the result of the test of the baffle opening under boiler plant each load that the reason such as replacing can cause the original debug phase to obtain because of overhaul departs from optimal value or invalid, make when boiler load changes, the temperature adjustment of three gas baffles can not get a desired effect.
Summary of the invention
The object of the invention is to there is the bad technical problem of temperature adjustment for existing three damper control methods, provide a kind of boiler three damper control method based on neutral net and system.
Technical scheme of the present invention is as follows:
The invention discloses a kind of boiler three damper control method based on neutral net, it specifically comprises the following steps:
The sample data that step one, collection boiler three damper control, sets up neural network model, and adopts learning method training network model;
Boiler export final state load and vapor (steam) temperature { Load after step 2, acquisition fluctuation; T0; T1; T2 }, wherein Load is boiler export final state load after fluctuation; T0 is superheated steam outlet temperature; T1 is single reheat steam exit temperature; T2 is double reheat steam exit temperature;
Step 3, step one complete the network model of training as solving object function, and after the fluctuation that step 2 obtains, boiler export final state load and vapor (steam) temperature are as initial conditions, solve the aperture array { K1 obtaining back-end ductwork three gas baffles; K2; K3 }, wherein K1 is a low aperture of damper again; K2 is the two low apertures of side shield again; K3 is low side shield aperture excessively;
Step 4, the aperture array of back-end ductwork three gas baffles obtained according to step 3, control the motion of baffle plate, thus realize temperature adjustment.
Further, said method also comprises allows three baffle plates obtain respective running orbit by neutral net, and three baffle plates fall final position by respective running orbit.
Further, said method also comprises the optimal solution adopting optimization algorithm to obtain aperture number, be specially when the aperture array number that step 3 solves back-end ductwork three gas baffles met the demands obtained is greater than or equal to 2, optimization algorithm is adopted to judge in the whole process that three baffle plates run, ensure T0, T1, T2 not overtemperatures, and from the stable state before fluctuation to fluctuation after the shortest time required for stable state be optimal solution.
Further, when said method is also included in and builds neutral net, introduce boiler load before and after fluctuation simultaneously, coal consumption, air quantity, load, confluent, economizer exit flue-gas temperature, oxygen content at economizer outlet, desuperheating water of superheater amount, vapor (steam) temperature after desuperheating water injection point, boiler export steam pressure and coal characteristic, thus build Mathematical Modeling.
Further, said method also comprises the basic calculating principle formation algorithm according to convection heat transfer' heat-transfer by convection, once input { Load; T0; T1; T2 }, namely calculate { K1 online by Mathematical Modeling; K2; K3 }.
Further, said method also comprises the self-learning function using neutral net, revises by the result of calculation of actual result to Mathematical Modeling of neural network learning.
The invention also discloses a kind of boiler three damper control system based on neutral net, it specifically comprises model and sets up unit, data capture unit, computing unit and control unit; The sample data that unit controls for gathering boiler three damper set up by described model, sets up neural network model, and adopts learning method training network model; Described data capture unit is for obtaining the rear boiler export final state load of fluctuation and vapor (steam) temperature { Load; T0; T1; T2 }, wherein Load is boiler export final state load after fluctuation; T0 is superheated steam outlet temperature; T1 is single reheat steam exit temperature; T2 is double reheat steam exit temperature; Described computing unit is used for completing the network model of training as solving object function, and after the fluctuation of acquisition, boiler export final state load and vapor (steam) temperature are as initial conditions, solve the aperture array { K1 obtaining back-end ductwork three gas baffles; K2; K3 }, wherein K1 is a low aperture of damper again; K2 is the two low apertures of side shield again; K3 is low side shield aperture excessively; Described control unit is used for the aperture array according to back-end ductwork three gas baffles obtained, and controls the motion of baffle plate, thus realizes temperature adjustment.
Further, said system also comprises baffle plate track acquiring unit, and described baffle plate track acquiring unit is used for allowing three baffle plates obtain respective running orbit by neutral net, and three baffle plates fall final position by respective running orbit.
Further, said system also comprises optimal solution acquiring unit, the optimal solution of described optimal solution acquiring unit for adopting optimization algorithm to obtain aperture number, be specially when the aperture array number solving back-end ductwork three gas baffles met the demands obtained is greater than or equal to 2, optimization algorithm is adopted to judge in the whole process that three baffle plates run, ensure T0, T1, T2 not overtemperatures, and from the stable state before fluctuation to fluctuation after the shortest time required for stable state be optimal solution.
By adopting above technical scheme, the invention has the beneficial effects as follows: by the use of neural network algorithm, self-learning function is incorporated in utility boiler control, thus improve the intelligent level of station boiler operation.In double reheat boiler, three dampers are adopted to carry out the temperature adjustment means of temperature adjustment relative to other, as flue gas recirculation temperature adjustment, to have station service low, the feature that reliability is high, but not as gas recirculation temperature adjustment in control and responding ability, method of the present invention compensate for the shortcoming of the responding ability difference of existing three damper temperature adjustments, and the responding ability that three dampers are controlled improves and can be applicable to various different operating mode.In each grade double reheat boiler, adopt method of the present invention effectively can play the feature of the low station service of three damper regulation technologies, high reliability, and be aided with intelligentized adjustment and adaptive capacity, therefore can obtain in double reheat boiler and apply widely.Allow three baffle plates obtain respective running orbit, adopt optimized algorithm to obtain optimum running orbit simultaneously.
Accompanying drawing explanation
Examples of the present invention will be described by way of reference to the accompanying drawings, wherein:
Fig. 1 is the double reheat boiler structure schematic diagram that afterbody three flue is arranged, in Fig. 1,1 is burner hearth, and 2 is horizontal flue, and 3 is back-end ductwork, and 4 is low temperature superheater, and 5 is secondary reheater low-temperature zone, and 6 is single reheat device low-temperature zone, and 7 is controllable register.
Fig. 2 is the flow chart that neural net model establishing and optimal solution are optimized.
Detailed description of the invention
Below in conjunction with Figure of description, describe specific embodiments of the invention in detail.
The double reheat boiler structure schematic diagram that afterbody three flue is as shown in Figure 1 arranged, control method of the present invention and system are applicable to the double reheat station boiler that afterbody three flue is arranged.
The invention discloses a kind of boiler three damper control method based on neutral net, it specifically comprises the following steps:
The sample data that step one, collection boiler three damper control, sets up neural network model, and adopts learning method training network model;
Boiler export final state load and vapor (steam) temperature { Load after step 2, acquisition fluctuation; T0; T1; T2 }, wherein Load is boiler export final state load after fluctuation; T0 is superheated steam outlet temperature; T1 is single reheat steam exit temperature; T2 is double reheat steam exit temperature;
Step 3, step one complete the network model of training as solving object function, and after the fluctuation that step 2 obtains, boiler export final state load and vapor (steam) temperature are as initial conditions, solve the aperture array { K1 obtaining back-end ductwork three gas baffles; K2; K3 }, wherein K1 is a low aperture of damper again; K2 is the two low apertures of side shield again; K3 is low side shield aperture excessively;
Step 4, the aperture array of back-end ductwork three gas baffles obtained according to step 3, control the motion of baffle plate, thus realize temperature adjustment.
By the use of neural network algorithm, self-learning function is incorporated in utility boiler control, thus improves the intelligent level of station boiler operation.In double reheat boiler, three dampers are adopted to carry out the temperature adjustment means of temperature adjustment relative to other, as flue gas recirculation temperature adjustment, to have station service low, the feature that reliability is high, but not as gas recirculation temperature adjustment in control and responding ability, method of the present invention compensate for the shortcoming of the responding ability difference of existing three damper temperature adjustments, and the responding ability that three dampers are controlled improves and can be applicable to various different operating mode.In each grade double reheat boiler, adopt method of the present invention effectively can play the feature of the low station service of three damper regulation technologies, high reliability, and be aided with intelligentized adjustment and adaptive capacity, therefore can obtain in double reheat boiler and apply widely.
Further preferred method is after said method is also included in load change, the aperture of afterbody three flues three baffle plates all will do corresponding change, complete the artificial neural network of training as solving object function, application genetic algorithm seeks the optimal solution within the scope of boiler operating parameter, three baffle plates are allowed to obtain respective running orbit, until three baffle plates have all fallen final position, enter the steady-state operation in next stage.
Further preferred method is the use of optimization algorithm, in control procedure, seek locally optimal solution.Be specially the baffle opening { K1 before fluctuation
i; K2
i; K3
i, change to the stable state lower baffle plate aperture { K1 after fluctuation; K2; K3 }, in actual solution procedure, may ambiguity be had, namely at function f ({ Load; T0; T1; T2 }) have in solution procedure and organize aperture { K1 more; K2; K3 } can meet the demands, but in actual moving process, need an optimal solution to realize quick response and the safe operation of unit.Therefore the solution of seeking is needed to be the running orbit set of three baffle openings, { g
1(t); g
2(t)
i; g
3(t) } (wherein g
1(t): a low aperture of damper is again along with the track of time variations; g
2(t): the two low apertures of damper are again along with the track of time variations; g
3(t): low side damper aperture is excessively along with the track of time variations; ).In the whole process of the operation of three baffle plates, ensure T0, T1, T2 not overtemperatures, and from the stable state before fluctuation to fluctuation after the shortest time required for stable state.
Namely optimization algorithm is adopted to obtain the optimal solution of aperture number, be specially when the aperture array number that step 3 solves back-end ductwork three gas baffles met the demands obtained is greater than or equal to 2, optimization algorithm is adopted to judge in the whole process that three baffle plates run, ensure T0, T1, T2 not overtemperatures, and from the stable state before fluctuation to fluctuation after the shortest time required for stable state be optimal solution.Thus realize quick response and the safe operation of unit.
Further preferred method is when building neutral net, introduce boiler load before and after fluctuation simultaneously, coal consumption, air quantity, load, confluent, economizer exit flue-gas temperature, oxygen content at economizer outlet, desuperheating water of superheater amount, vapor (steam) temperature after desuperheating water injection point, boiler export steam pressure and coal characteristic etc.Introducing these parameters is all as the auxiliary parameter in object function, after building network model, adds these parameters, just can build Mathematical Modeling, makes at input { Load; T0; T1; T2 }, namely calculate { K1 fast online by Mathematical Modeling; K2; K3 }.
Parameter is as the input point building neutral net, and except this non-adjustable factor of coal characteristic, need outside manual entry, all the other parameters all can take from DCS system in real time, as known conditions during neural computing.DCS is the english abbreviation (DistributedControlSystem) of dcs, and automatic control industry is at home referred to as Distributed Control System again, refers to the control centre in power plant in present specification.
Generally, just can formation algorithm according to the basic calculating principle of convection heat transfer' heat-transfer by convection, once input { Load; T0; T1; T2 }, { K1 can be calculated online; K2; K3 }.Calculating mechanism relies on the mechanism of convection heat transfer' heat-transfer by convection to build Mathematical Modeling, and building this Mathematical Modeling needs some auxiliary parameters, such as " fluctuation front and back boiler load; coal consumption; air quantity, load, confluent; economizer exit flue-gas temperature; oxygen content at economizer outlet, desuperheating water of superheater amount, vapor (steam) temperature after desuperheating water injection point; boiler export steam pressure and coal characteristic etc. ", then once input { Load; T0; T1; T2 }, namely calculate { K1 online by Mathematical Modeling; K2; K3 } parameter that exports is exactly the aperture of three baffle plates.
Although baffle opening can be obtained by calculated with mathematical model, still need by neutral net, main cause is:
1. a lot of auxiliary parameter is that on-line measurement obtains, and not precisely, is inaccurate, can passes through self-learning function, revise by actual result to result of calculation by neutral net so only obtain final parameter by calculating.
2. such as original aperture is { K1; K2; K3 }, after change the aperture of target be K1 '; K2 '; K3 ' }, although can by Mathematical Modeling obtain target aperture K1 '; K2 '; K3 ' }, but in this change procedure, K1 changes to K1 ', K2 changes to K2 ', and K3 changes to K3 ', needs the variation track of three parameters exactly, this track does not obtain by mathematical computations, needs to find an optimum variation track by self study process.In other words Mathematical Modeling can calculate final result, but calculates the track of not out intermediate change.
And any non-linear mapping capability of neutral net can simulate the functional relation of this complexity, this is operation principle of the present invention.Neutral net can be expressed as f({ Load; T0; T1; T2 })={ K1; K2; K3 }
Artificial neural network why can the modeling process of extensive use and various complication system input/output relation, is because artificial neural network is by sample learning, by continuous correction, realizes the modelling to complication system.Along with the change of combustion conditions, heating surface stains the change of degree, and the functional relation only relying on heat-transfer mechanism to obtain can not meet the needs of boundary condition in the practical engineering application of change, therefore f({ Load; T0; T1; T2 })={ K1; K2; K3 } need constantly online correction in real time, make the output of network close to desired output, until error meets the demands, study terminates.Obtain the weights after study.
Preferably, said method also comprises the running of three baffle plates is enrolled neural network model as a new sample.Neutral net and genetic Optimization Algorithm are combined, instructs thermoregulating system, promote operation control and the regulating power of unit.
Fig. 2 is the flow chart that neural net model establishing and optimal solution are optimized.
The invention also discloses a kind of boiler three damper control system based on neutral net, it specifically comprises model and sets up unit, data capture unit, computing unit and control unit; The sample data that unit controls for gathering boiler three damper set up by described model, sets up neural network model, and adopts learning method training network model; Described data capture unit is for obtaining the rear boiler export final state load of fluctuation and vapor (steam) temperature { Load; T0; T1; T2 }, wherein Load is boiler export final state load after fluctuation; T0 is superheated steam outlet temperature; T1 is single reheat steam exit temperature; T2 is double reheat steam exit temperature; Described computing unit is used for completing the network model of training as solving object function, and after the fluctuation of acquisition, boiler export final state load and vapor (steam) temperature are as initial conditions, solve the aperture array { K1 obtaining back-end ductwork three gas baffles; K2; K3 }, wherein K1 is a low aperture of damper again; K2 is the two low apertures of side shield again; K3 is low side shield aperture excessively; Described control unit is used for the aperture array according to back-end ductwork three gas baffles obtained, and controls the motion of baffle plate, thus realizes temperature adjustment.
Above-mentioned model belongs to learning-oriented artificial nerve network model, by the study to sample, constantly revises, and realizes the modelling to complication system.
When calculating, adopting artificial nerve network model to obtain the running orbit of three baffle plates, then obtaining optimal solution by excellent algorithm, thus realizing temperature adjustment real-time.
All features disclosed in this description, or the step in disclosed all methods or process, except mutually exclusive feature and/or step, all can combine by any way.
Arbitrary feature disclosed in this description (comprising any accessory claim, summary and accompanying drawing), unless specifically stated otherwise, all can be replaced by other equivalences or the alternative features with similar object.That is, unless specifically stated otherwise, each feature is an example in a series of equivalence or similar characteristics.
The present invention is not limited to aforesaid detailed description of the invention.The present invention expands to any new feature of disclosing in this manual or any combination newly, and the step of the arbitrary new method disclosed or process or any combination newly.
Claims (9)
1., based on a boiler three damper control method for neutral net, it specifically comprises the following steps:
The sample data that step one, collection boiler three damper control, sets up neural network model, and adopts learning method training network model;
Boiler export final state load and vapor (steam) temperature { Load after step 2, acquisition fluctuation; T0; T1; T2 }, wherein Load is boiler export final state load after fluctuation; T0 is superheated steam outlet temperature; T1 is single reheat steam exit temperature; T2 is double reheat steam exit temperature;
Step 3, step one complete the network model of training as solving object function, and after the fluctuation that step 2 obtains, boiler export final state load and vapor (steam) temperature are as initial conditions, solve the aperture array { K1 obtaining back-end ductwork three gas baffles; K2; K3 }, wherein K1 is a low aperture of damper again; K2 is the two low apertures of side shield again; K3 is low side shield aperture excessively;
Step 4, the aperture array of back-end ductwork three gas baffles obtained according to step 3, control the motion of baffle plate, thus realize temperature adjustment.
2. as claimed in claim 1 based on the boiler three damper control method of neutral net, it is characterized in that described method also comprises allows three baffle plates obtain respective running orbit by neutral net, and three baffle plates fall final position by respective running orbit.
3. as claimed in claim 2 based on the boiler three damper control method of neutral net, it is characterized in that described method also comprises the optimal solution adopting optimization algorithm to obtain aperture number, be specially when the aperture array number that step 3 solves back-end ductwork three gas baffles met the demands obtained is greater than or equal to 2, optimization algorithm is adopted to judge in the whole process that three baffle plates run, ensure T0, T1, T2 not overtemperatures, and from the stable state before fluctuation to fluctuation after the shortest time required for stable state be optimal solution.
4., as claimed in claim 1 based on the boiler three damper control method of neutral net, when it is characterized in that described method is also included in structure neutral net, introduce boiler load before and after fluctuation simultaneously, coal consumption, air quantity, load, confluent, economizer exit flue-gas temperature, oxygen content at economizer outlet, desuperheating water of superheater amount, vapor (steam) temperature after desuperheating water injection point, boiler export steam pressure and coal characteristic, thus build Mathematical Modeling.
5. as claimed in claim 4 based on the boiler three damper control method of neutral net, it is characterized in that described method also comprises the basic calculating principle formation algorithm according to convection heat transfer' heat-transfer by convection, once input { Load; T0; T1; T2 }, namely calculate { K1 online by Mathematical Modeling; K2; K3 }.
6., as claimed in claim 5 based on the boiler three damper control method of neutral net, it is characterized in that described method also comprises the self-learning function using neutral net, revise by the result of calculation of actual result to Mathematical Modeling of neural network learning.
7., based on a boiler three damper control system for neutral net, it is characterized in that specifically comprising model sets up unit, data capture unit, computing unit and control unit; The sample data that unit controls for gathering boiler three damper set up by described model, sets up neural network model, and adopts learning method training network model; Described data capture unit is for obtaining the rear boiler export final state load of fluctuation and vapor (steam) temperature { Load; T0; T1; T2 }, wherein Load is boiler export final state load after fluctuation; T0 is superheated steam outlet temperature; T1 is single reheat steam exit temperature; T2 is double reheat steam exit temperature; Described computing unit is used for completing the network model of training as solving object function, and after the fluctuation of acquisition, boiler export final state load and vapor (steam) temperature are as initial conditions, solve the aperture array { K1 obtaining back-end ductwork three gas baffles; K2; K3 }, wherein K1 is a low aperture of damper again; K2 is the two low apertures of side shield again; K3 is low side shield aperture excessively; Described control unit is used for the aperture array according to back-end ductwork three gas baffles obtained, and controls the motion of baffle plate, thus realizes temperature adjustment.
8. as claimed in claim 7 based on the boiler three damper control system of neutral net; it is characterized in that described system also comprises baffle plate track acquiring unit; described baffle plate track acquiring unit is used for allowing three baffle plates obtain respective running orbit by neutral net, and three baffle plates fall final position by respective running orbit.
9. as claimed in claim 8 based on the boiler three damper control method of neutral net, it is characterized in that described system also comprises optimal solution acquiring unit, the optimal solution of described optimal solution acquiring unit for adopting optimization algorithm to obtain aperture number, be specially when the aperture array number solving back-end ductwork three gas baffles met the demands obtained is greater than or equal to 2, optimization algorithm is adopted to judge in the whole process that three baffle plates run, ensure T0, T1, T2 not overtemperatures, and from fluctuation before stable state to fluctuation after stable state required for shortest time be optimal solution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510592072.4A CN105240822B (en) | 2015-09-17 | 2015-09-17 | A kind of the damper control method of boiler three and system based on neutral net |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510592072.4A CN105240822B (en) | 2015-09-17 | 2015-09-17 | A kind of the damper control method of boiler three and system based on neutral net |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105240822A true CN105240822A (en) | 2016-01-13 |
CN105240822B CN105240822B (en) | 2017-07-11 |
Family
ID=55038575
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510592072.4A Active CN105240822B (en) | 2015-09-17 | 2015-09-17 | A kind of the damper control method of boiler three and system based on neutral net |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105240822B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109084293A (en) * | 2018-08-06 | 2018-12-25 | 东方电气集团东方锅炉股份有限公司 | A kind of three damper adjustment control method of double reheat boiler |
CN111120983A (en) * | 2019-12-18 | 2020-05-08 | 中国大唐集团科学技术研究院有限公司火力发电技术研究院 | Automatic adjusting method for opening of tail flue baffle of secondary reheating ultra-supercritical boiler |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB965180A (en) * | 1961-12-27 | 1964-07-29 | Combustion Eng | Method and apparatus for generating power in a vapor generator-turbine plant |
CN202501442U (en) * | 2012-02-29 | 2012-10-24 | 东方电气集团东方锅炉股份有限公司 | Boiler with three flues arranged at tail part thereof |
CN203336569U (en) * | 2013-07-04 | 2013-12-11 | 哈尔滨锅炉厂有限责任公司 | Dual-reheating temperature adjusting device used for tower-type boiler |
CN103759290A (en) * | 2014-01-16 | 2014-04-30 | 广东电网公司电力科学研究院 | Large coal-fired unit online monitoring and optimal control system and implementation method thereof |
-
2015
- 2015-09-17 CN CN201510592072.4A patent/CN105240822B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB965180A (en) * | 1961-12-27 | 1964-07-29 | Combustion Eng | Method and apparatus for generating power in a vapor generator-turbine plant |
CN202501442U (en) * | 2012-02-29 | 2012-10-24 | 东方电气集团东方锅炉股份有限公司 | Boiler with three flues arranged at tail part thereof |
CN203336569U (en) * | 2013-07-04 | 2013-12-11 | 哈尔滨锅炉厂有限责任公司 | Dual-reheating temperature adjusting device used for tower-type boiler |
CN103759290A (en) * | 2014-01-16 | 2014-04-30 | 广东电网公司电力科学研究院 | Large coal-fired unit online monitoring and optimal control system and implementation method thereof |
Non-Patent Citations (3)
Title |
---|
何丽娜: "基于现场数据和神经网络的主汽温系统建模方法研究", 《中国优秀硕士学位论文全文数据库》 * |
刘长良等: "二次再热机组汽温联合控制策略仿真", 《自动化与仪表》 * |
陈端雨等: "神经网络在超临界锅炉热偏差优化调整中的应用", 《锅炉技术》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109084293A (en) * | 2018-08-06 | 2018-12-25 | 东方电气集团东方锅炉股份有限公司 | A kind of three damper adjustment control method of double reheat boiler |
CN109084293B (en) * | 2018-08-06 | 2019-10-25 | 东方电气集团东方锅炉股份有限公司 | A kind of three damper adjustment control method of double reheat boiler |
CN111120983A (en) * | 2019-12-18 | 2020-05-08 | 中国大唐集团科学技术研究院有限公司火力发电技术研究院 | Automatic adjusting method for opening of tail flue baffle of secondary reheating ultra-supercritical boiler |
CN111120983B (en) * | 2019-12-18 | 2022-10-11 | 中国大唐集团科学技术研究院有限公司火力发电技术研究院 | Automatic adjusting method for opening of tail flue baffle of secondary reheating ultra-supercritical boiler |
Also Published As
Publication number | Publication date |
---|---|
CN105240822B (en) | 2017-07-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104482525B (en) | The control method of extra-supercritical unit reheat steam temperature and system | |
CN109084293B (en) | A kind of three damper adjustment control method of double reheat boiler | |
CN101713536B (en) | Control method of combustion system of circulating fluidized bed boiler | |
CN103759290A (en) | Large coal-fired unit online monitoring and optimal control system and implementation method thereof | |
CN108227488B (en) | Sliding mode prediction control-based ultra-supercritical thermal power generating unit coordination control method | |
CN104571022B (en) | Power consumption analysis model experimental systems and method based on coal consumption Yu controllable factor relationship | |
Wang et al. | Flexibility and efficiency co-enhancement of thermal power plant by control strategy improvement considering time varying and detailed boiler heat storage characteristics | |
CN104865830A (en) | Dual-intelligent-optimization control method for unit load | |
CN106765052A (en) | A kind of intelligence computation forecast Control Algorithm of station boiler vapor (steam) temperature | |
CN106642069B (en) | Ultra supercritical double reheat generating set reheat steam temperature Compound Control Strategy | |
Zeng et al. | Optimization control for the coordinated system of an ultra-supercritical unit based on stair-like predictive control algorithm | |
CN101556038A (en) | Optimization control system for stable operation and economical combustion of circulating fluidized-bed boiler | |
CN102425790B (en) | Circulating fluid bed boiler online optimized self-learning control method | |
CN111637444B (en) | Nuclear power steam generator water level control method based on Q learning | |
CN106382615A (en) | Verification system and method for ultra-supercritical unit multi-time reheat steam temperature control strategy | |
CN108490790A (en) | A kind of overheating steam temperature active disturbance rejection cascade control method based on multiple-objection optimization | |
CN105546508A (en) | Main steam temperature control system and method for thermal power plant based on event-triggered mechanism | |
CN108954293A (en) | A kind of double reheat power generation sets Reheated-steam Temperature Control System and method that " graded combination " integrally controls | |
CN107831652A (en) | A kind of unit load intelligent optimized control method based on cold end system energy storage | |
CN105299612A (en) | Main steam temperature control method based on multi-model switching and control system | |
CN104881714A (en) | Boiler high-temperature heating surface pendant to pendant heat deviation module predication method | |
CN110515304A (en) | Overheating steam temperature PID forecast Control Algorithm based on ARX-Laguerre function model | |
CN110298502B (en) | Optimal oxygen quantity calculation method for boiler based on optimal energy efficiency | |
CN105240822B (en) | A kind of the damper control method of boiler three and system based on neutral net | |
CN111708333A (en) | Intelligent prediction coordination control system of power plant |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |