CN112628712A - Secondary air closed-loop optimization control system based on air door resistance coefficient - Google Patents
Secondary air closed-loop optimization control system based on air door resistance coefficient Download PDFInfo
- Publication number
- CN112628712A CN112628712A CN202110032762.XA CN202110032762A CN112628712A CN 112628712 A CN112628712 A CN 112628712A CN 202110032762 A CN202110032762 A CN 202110032762A CN 112628712 A CN112628712 A CN 112628712A
- Authority
- CN
- China
- Prior art keywords
- boiler
- secondary air
- closed
- air
- module
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 40
- 238000002485 combustion reaction Methods 0.000 claims abstract description 41
- 239000003245 coal Substances 0.000 claims abstract description 35
- 238000009838 combustion analysis Methods 0.000 claims abstract description 15
- 230000000694 effects Effects 0.000 claims abstract description 15
- 238000013507 mapping Methods 0.000 claims abstract description 8
- 238000003062 neural network model Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 6
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 4
- 239000003546 flue gas Substances 0.000 claims description 4
- 238000010298 pulverizing process Methods 0.000 claims description 4
- 230000002441 reversible effect Effects 0.000 claims description 4
- 241000544061 Cuculus canorus Species 0.000 claims description 3
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 3
- 230000002068 genetic effect Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000005065 mining Methods 0.000 claims description 3
- 239000001301 oxygen Substances 0.000 claims description 3
- 229910052760 oxygen Inorganic materials 0.000 claims description 3
- 239000000843 powder Substances 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000002922 simulated annealing Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 230000000737 periodic effect Effects 0.000 claims description 2
- 230000000306 recurrent effect Effects 0.000 claims description 2
- 239000003570 air Substances 0.000 description 129
- MWUXSHHQAYIFBG-UHFFFAOYSA-N Nitric oxide Chemical compound O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 21
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000011217 control strategy Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000000227 grinding Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 239000000779 smoke Substances 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 239000010881 fly ash Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000009423 ventilation Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 240000004282 Grewia occidentalis Species 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 239000012080 ambient air Substances 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F22—STEAM GENERATION
- F22B—METHODS OF STEAM GENERATION; STEAM BOILERS
- F22B35/00—Control systems for steam boilers
- F22B35/18—Applications of computers to steam boiler control
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F22—STEAM GENERATION
- F22B—METHODS OF STEAM GENERATION; STEAM BOILERS
- F22B33/00—Steam-generation plants, e.g. comprising steam boilers of different types in mutual association
- F22B33/18—Combinations of steam boilers with other apparatus
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
- F23N—REGULATING OR CONTROLLING COMBUSTION
- F23N5/00—Systems for controlling combustion
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
- F23N—REGULATING OR CONTROLLING COMBUSTION
- F23N2223/00—Signal processing; Details thereof
- F23N2223/10—Correlation
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
- F23N—REGULATING OR CONTROLLING COMBUSTION
- F23N2900/00—Special features of, or arrangements for controlling combustion
- F23N2900/05006—Controlling systems using neuronal networks
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Regulation And Control Of Combustion (AREA)
- Control Of Steam Boilers And Waste-Gas Boilers (AREA)
Abstract
The invention relates to a secondary air closed-loop optimization control system based on an air door resistance coefficient, which comprises: the secondary air accurate control module is used for establishing a mapping relation between the opening of each layer of secondary air doors and the air quantity; the boiler combustion analysis module is used for obtaining a characteristic value of a boiler combustion boundary and a characteristic value of a combustion effect; the intelligent modeling module is used for establishing a neural network model between the boiler combustion boundary characteristic value and the combustion effect characteristic value; the optimizing module is used for obtaining an optimal solution by utilizing an optimizing algorithm based on the established neural network model; and the closed-loop control module is used for acquiring all parameters in real time, reversely calculating the optimal value of the opening degree of the secondary air door of the boiler after the parameters are processed by the boiler combustion analysis module and the optimization module, and executing closed-loop control in the DCS. The invention can adapt to the changes of the load, the coal quality and the operation mode of the power station boiler to carry out dynamic real-time optimization, can greatly improve the automation level of the boiler, effectively improve the boiler efficiency and reduce the NOx emission concentration at the outlet of the hearth.
Description
Technical Field
The invention belongs to the technical field of pulverized coal boiler combustion optimization, and particularly relates to a secondary air closed-loop optimization control system based on an air door resistance coefficient.
Background
The cold state aerodynamic field is a test item which is often carried out after the overhaul of the boiler, and a secondary air door characteristic test is an important item. The traditional method for testing the characteristics of the air door comprises the following steps: keeping the pressure of the secondary air box unchanged, sequentially adjusting the opening degrees of the air doors to be 100%, 75%, 50%, 25% and 0%, measuring the wind speed at multiple points of each nozzle by using an anemometer, and drawing the opening degrees of the air doors and the dimensionless wind speeds of the nozzles to obtain a characteristic curve of each air door. The method can provide reference for leveling the secondary air quantity of each corner, but cannot provide further air distribution adjustment data.
Pulverized coal fired boilers rely on the entrainment of efflux to organize the burning in the stove, and reasonable air distribution is the key of guaranteeing boiler combustion effect. The existing power station boiler generally adopts an air distribution mode of large air boxes, and is difficult to realize fine adjustment due to the fact that the air boxes are compactly arranged and lack of enough premixing sections to meet the requirement of accurately measuring the air volume of each air box. If the scheme of independently designing the secondary air duct is adopted, although quantitative control can be realized, the problem brought about is that the pipeline arrangement is complicated and is not suitable for the national conditions of China. At present, domestic engineers generally adopt an empirical adjustment mode for controlling the air box/hearth differential pressure and adjusting the opening degree of each layer of air door.
Influenced by policies such as coal capacity removal and renewable energy consumption, the boiler combustion of the coal-fired power plant is generally deviated from the designed coal type. The traditional boiler coordination automation is usually carried out by tracking a constant value curve of load, and cannot adapt to the change of coal quality. When the deviation of coal quality is great, the problems that the concentration of nitrogen oxide at the outlet of a hearth is increased, the carbon content of fly ash is increased and the like often occur, and the boiler efficiency and the nitrogen oxide at the outlet of the hearth are hardly considered at the same time.
The boiler combustion boundary determines the combustion effect. Under the working condition of thermal state operation, the primary air rate of organized air intake of the boiler is about 20-30%, and the rest is secondary air. The adjustable space of the primary air quantity is limited due to the influence of factors such as drying output of a pulverizing system, and the adjustment of the air side is mainly the adjustment of a secondary air part, namely oxygen quantity, small secondary air doors of each layer and the like. At present, the adjustment of secondary air is mainly manually adjusted by operators according to experience, an effective secondary air closed-loop control method is developed, the real-time optimization of coal quality and load is realized, and the method has important significance for the long-term safe, stable, clean and efficient operation of the coal-fired boiler.
Disclosure of Invention
The invention aims to provide a secondary air closed-loop optimization control system based on an air door resistance coefficient, and aims to solve the problems that secondary air distribution of an active power station boiler is difficult to realize automatic adjustment with basis, and the high-efficiency cleaning of the boiler operation cannot be guaranteed in real time.
The invention provides a secondary air closed-loop optimization control system based on an air door resistance coefficient, which comprises:
the secondary air accurate control module is used for establishing a mapping relation between the opening degree of each layer of secondary air doors and the air quantity, and the mapping relation is based on the corresponding relation between the opening degree of each layer of secondary air doors and the resistance coefficient;
the boiler combustion analysis module is used for processing parameters related to boiler combustion in real time and obtaining a characteristic value of a boiler combustion boundary and a characteristic value of a combustion effect after dimension reduction processing;
the intelligent modeling module is used for deeply mining big data information of boiler operation by adopting a supervised learning algorithm and establishing a neural network model between a boiler combustion boundary characteristic value and a combustion effect characteristic value; modeling data is obtained from a boiler combustion analysis module database and is carried out in an off-line periodic modeling mode;
the optimizing module is used for processing by utilizing an optimizing algorithm based on the established neural network model to obtain an optimal solution;
and the closed-loop control module is used for establishing two-way stable communication between the DCS and each module, acquiring parameters of a powder making system, a secondary air system and a flue gas system of the DCS in real time, reversely calculating an optimal value of the opening degree of a secondary air door of the boiler after the parameters are processed by the boiler combustion analysis module and the optimization searching module, transmitting the optimal value to the DCS and executing closed-loop control in the DCS.
Furthermore, the resistance coefficient is the sum of an on-way resistance coefficient, a local resistance coefficient and an outflow resistance coefficient of the whole process of air supply entering the hearth from the large air box, and the corresponding relation between the opening degree of the air door and the resistance system is obtained through a refined cold-state secondary air door characteristic test; and the mapping relation between the opening degree of the secondary air door and the air volume takes pressure compensation into consideration in a thermal state.
Furthermore, the boiler combustion analysis module processes parameters of a boiler pulverizing system, a secondary air system and a flue gas system, checks and calculates boiler air balance from positive and negative dimensions, and performs dimension reduction processing on characteristic parameters of a boiler combustion boundary and a combustion effect to obtain characteristic quantities of the combustion boundary and the combustion effect.
Further, the intelligent modeling module establishes a prediction model of boiler efficiency and NOx emission concentration; the input variables for both models include: the main steam flow of the boiler, the coal amount of each coal mill, the outlet temperature of each coal mill, the secondary air volume coefficient of each combustion area and the oxygen content of the outlet of the hearth; the output variables of the two models are boiler efficiency and NOx emission concentration, respectively.
Further, the neural network model established by the intelligent modeling is a recurrent neural network derivative model.
Further, the optimizing module preferentially judges whether the operation working condition of the boiler is a conventional working condition or an unconventional working condition; under the normal working condition, calculating the prediction model by using an optimization algorithm, and calculating an optimization value in a reverse direction according to the obtained result; under the unconventional working condition, a preset algorithm is used for directly outputting the instruction.
Furthermore, the closed-loop control module sets a screening mechanism for the output result to ensure the applicability of the output result.
Further, the data communicated back to the DCS by the closed-loop control module is the offset value of the opening degree of each layer of secondary air door.
Further, the optimization algorithm adopted by the optimization module is a simulated annealing algorithm, a genetic algorithm, a cuckoo algorithm or an artificial bee colony algorithm.
By means of the scheme, the secondary air closed-loop optimization control system based on the air door resistance coefficient can adapt to changes of boiler load, coal quality and operation mode of the power station to perform dynamic real-time optimization, can greatly improve the automation level of the boiler, effectively improves the boiler efficiency and reduces the NOx emission concentration at the outlet of the hearth.
The foregoing is a summary of the present invention, and in order to provide a clear understanding of the technical means of the present invention and to be implemented in accordance with the present specification, the following is a detailed description of the preferred embodiments of the present invention.
Drawings
FIG. 1 is a schematic view of a combustion system of a pulverized coal fired boiler with four tangential corners;
FIG. 2 is a structural schematic view of a single-side large air box of a tangential boiler with four corners;
FIG. 3 is a structural schematic diagram of each layer of nozzle of a pulverized coal furnace burner with four tangential corners;
FIG. 4 is a schematic diagram of a control strategy for a secondary air closed-loop control system based on a resistance coefficient of a damper according to the present invention;
FIG. 5 is a schematic control flow chart of a secondary air closed-loop control system based on the resistance coefficient of the air door according to the present invention;
FIG. 6 is a graph illustrating a secondary damper characteristic test according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Referring to fig. 1, taking a pulverized coal boiler combustion system with tangential circles at four corners as an example, the whole boiler combustion system is composed of a body 1, an air preheater 2, a primary air fan 3, a blower 4, a medium-speed coal mill 5, a sealing air fan 6, a coal feeder 7, a pulverized coal pipeline 8, a burner 9, a large air box 10 and a primary air pipeline 11. The primary air generated by the primary fan 3 is heated by the air preheater 2, enters the medium-speed coal mill 5 through the primary air pipeline 11, carries the pulverized coal, passes through the pulverized coal pipeline 8, and enters the hearth through the combustor 9. The secondary air generated by the blower 4 is heated by the air preheater 2, enters the large air box 10 and enters the hearth through the combustor 9.
Referring to fig. 2, a structure of a single-side large wind box of a pulverized coal boiler with four tangential corners is taken as an example. The large air box on one side supplies air for 2 adjacent angles, the air supply enters the large air box, then is bent to flow to the front side and the rear side, is bent forwards by 45 degrees along each air box, and then enters the furnace through each nozzle. The structure of each layer of nozzle of the burner is shown in figure 3. The inlet of each air chamber is provided with 1 air door, and the outlet (the left side of figure 3) of each air chamber is connected with 1 burner nozzle (the right side of figure 3).
FIG. 4 is a schematic diagram of a secondary air closed-loop control system control strategy based on a damper resistance coefficient. The method comprises the steps of utilizing a secondary air accurate control method to conduct dimension reduction processing on a large number of parameters of a secondary air system of the boiler to obtain air distribution data of a combustion boundary of the boiler, taking data such as main steam flow, coal quantity of each coal mill and outlet temperature of each mill as characteristic quantities, taking data such as boiler efficiency and NOx emission as target quantities, and establishing a prediction model by applying a machine learning method based on a large number of historical parameters of past operation. In practical application, on the basis of data such as main steam flow, coal grinding amount and outlet temperature of each mill at the current moment, certain limiting conditions are added to the air distribution data at the current moment to optimize a target value, and the opening of each secondary air door obtained by optimizing is processed into an offset value to be used as an instruction to communicate back to the DCS.
Fig. 5 is a schematic control flow diagram of a secondary air closed-loop control system. The secondary air closed-loop control system takes software as a carrier and is deployed on a server, and the server is arranged between DCS electronics and is connected with a DCS module through a data line. The software is compiled by C + +, a communication program compiled based on a Modbus TCP protocol is arranged in a closed-loop control module, and the module acquires parameters of an air smoke, a powder process and a steam-water system of the DCS in real time, sends the parameters to a boiler combustion analysis module, an optimization module and a secondary air accurate control module in sequence, and sends bias instructions of each secondary air door back to the DCS after the parameters are processed. In the configuration logic of DCS, the offset instruction is added after the floor operation instruction, and the closed-loop control system can receive the instruction as long as each small air door is automatically put into operation and the closed-loop control system is automatically put into operation, thereby realizing the closed-loop control.
The secondary air closed-loop control system provided by the embodiment comprehensively utilizes professional technologies and advanced intelligent algorithms, and can adapt to changes of boiler load, coal quality and operation modes to perform dynamic real-time optimization. Compared with the traditional secondary air door control strategy, the system carries out prediction control based on an optimization algorithm and can give consideration to the comprehensive benefits of the boiler in real time. Compared with other similar intelligent optimization systems, the system has the advantages that the number of dimensions of modeling parameters is reduced due to the application of a large number of professional algorithms, the calculation efficiency of the system is improved, and the modeling algorithm has perfect physical significance. The invention can be applied to any four-corner tangential pulverized coal boiler in active service. By adopting the invention, the automation level of the secondary air door of the power station boiler can be greatly improved, and the boiler efficiency and the nitrogen oxide at the outlet of the hearth can be considered in real time.
The present invention is described in further detail below.
The invention applies professional technology and machine learning technology to establish a prediction model between boiler combustion boundary quantity and combustion effect quantity and carries out real-time optimization.
The system comprises 5 submodules, specifically, a secondary air accurate control module, a boiler combustion analysis module, an intelligent modeling module, an optimization module and a closed-loop control module. The secondary air accurate control module is used for establishing a bidirectional mapping relation between the opening degree of the air door and the air quantity of each nozzle based on the resistance coefficient of the air door, so that the accurate adjustment of the secondary air quantity of each nozzle is realized; the boiler combustion analysis module is used for carrying out dimension reduction processing on a plurality of boiler combustion boundary quantities and combustion effect quantities, obtaining a characteristic value and a target value of modeling and storing the characteristic value and the target value into a modeling database; the intelligent modeling module is used for establishing a nonlinear prediction model between a boiler combustion characteristic value and a target value by using a supervised learning algorithm; the optimizing module is used for optimizing within a certain range by utilizing an algorithm based on the current state parameters and outputting a result; the closed-loop control module is used for acquiring data from the DCS in real time based on a communication protocol, sending the data to each module for processing, then sending the bias instruction of the opening degree of each secondary air door back to the DCS in a communication mode, and realizing closed-loop control of the secondary air by using configuration logic in the DCS.
In order to realize the function of the secondary air accurate control module, the following scheme is proposed in the embodiment:
(1) and during the blowing out period, the opening and closing states of the secondary air doors and the actuators at all corners are checked in detail, and related thermal meter meters are checked to ensure that related equipment is normal.
(2) A flow rate measuring device is arranged on each spout. Under the cold state ventilation test condition, the differential pressure of the large air box/the hearth is adjusted to be 0.6kPa-0.7kPa, the opening degrees of the secondary air door baffles of each layer are sequentially adjusted to be 100%, 75%, 50%, 40%, 30%, 20%, 10% and 0% layer by layer, the differential pressure values of the air doors of each angle under different opening degrees are recorded, and the secondary air dynamic pressure values at the outlets of the nozzles are synchronously recorded. By using the data, the corresponding relationship between the opening degree of the air door, the air speed of the nozzle and the resistance coefficient can be obtained, as shown in fig. 6. The resistance coefficient refers to the sum of the on-way resistance coefficient, the local resistance coefficient and the outflow resistance coefficient of the whole process of the air supply entering the hearth from the large air box, and is calculated by the formula (1).
In the formula:the values of the resistance coefficients corresponding to different opening degrees of the air doors;the corresponding large air box/hearth differential pressure values under different opening degrees of each air door;the dynamic pressure values of the nozzle outlets corresponding to different opening degrees of the air doors are obtained.
(3) In a hot state, because the hearth has self-generated ventilation force, the calculation value of the wind speed of each nozzle is smaller by simply adopting the air box/hearth differential pressure. Pressure compensation is introduced, and a compensation value is calculated according to the density difference between ambient air and smoke in the furnace. After correction, the nozzle wind speed is calculated by adopting a formula (2). And obtaining the air volume value of each nozzle by using the air velocity value. And conversely, the opening degree of each air door can be obtained according to the required air volume value at each position by reverse calculation.
In order to realize the function of the boiler combustion analysis module, a large number of professional algorithms are applied in the embodiment, and the deep mining of boiler data information specifically includes:
(1) and (4) performing real-time wind balance calculation of the boiler by using the parameters of the inlet and the outlet of the air preheater.
(2) And calculating the average temperature of the hearth in real time according to the main steam flow of the boiler, the coal grinding amount and other information.
(3) And calculating the flow distribution coefficient of each layer of secondary air in real time by using each parameter of the secondary air system.
(4) And calculating the moisture of each grinding coal in real time by using each parameter of the pulverizing system.
(5) And calculating the boiler efficiency in real time by using the online data of the content of combustible substances in the fly ash, CO, the temperature of exhaust smoke and the like.
(6) And calculating the heat absorption deviation of each heating surface of the hearth outlet in real time by using each parameter of the steam-water system.
(7) And calculating the denitration cost per unit time in real time by using the content of nitrogen oxide imported for denitration.
(8) And storing parameters such as time, main steam flow of the boiler, flow distribution coefficients of secondary air of each layer, furnace efficiency, nitrogen oxide at the outlet of the hearth and the like into a database.
In order to realize the function of the intelligent modeling module, the embodiment applies a machine learning method, takes time as a label value, takes parameters such as main steam flow of the boiler, coal quantity of each coal mill, outlet temperature of each coal mill, flow distribution coefficient of each layer of secondary air and the like as characteristic values, takes parameters such as boiler efficiency, nitrogen oxide content at the outlet of a hearth and the like as target values, and establishes a prediction model between a combustion boundary (characteristic value) and a combustion effect (target value) of the boiler by means of a model library such as RNN, LSTM, GRU and the like packaged on a Tensorflow platform after normalization processing and data cleaning.
Preferably, in order to improve the modeling efficiency, the modeling database adopts a k-means clustering algorithm to classify data by taking the main steam flow as a parameter. Model modeling is performed for each data classification dataset. When the model is actually called, the main steam flow is used for judging which model is selected.
Preferably, the established model can take individual boiler efficiency, furnace outlet nitrogen oxides as target values; or the amount of the two indexes after being combined is taken as a target value. The influence of the CO content and the exhaust gas temperature on the boiler efficiency is mainly considered.
In order to realize the function of the optimizing module, in the embodiment, aiming at the current boiler combustion boundary parameter and the prediction model, the optimizing algorithm, such as a simulated annealing algorithm, a genetic algorithm, a cuckoo algorithm, an artificial bee colony algorithm and the like, is utilized to optimize the parameters of the opening degree of each secondary air door within a certain range, and the optimal result is obtained and then the opening degree of the air door is obtained through reverse calculation.
Preferably, the optimizing module preferentially judges whether the current operation condition of the boiler is a normal condition or an abnormal condition. Under the conventional working condition, carrying out optimization calculation by utilizing the optimization algorithm; under an unconventional working condition, after a certain degree of correction is considered, the optimization algorithm is utilized for optimization calculation; if the working condition is extremely special, a professional algorithm is directly used for giving instructions.
In order to realize the function of the closed-loop control module, the embodiment realizes the mutual communication between the DCS and the server based on communication protocols such as Modbus TCP, Modbus RTU, or Profibus DP. The specific control implementation process is as follows: the DCS communicates a large number of parameters collected in real time to the server, the parameters are processed by the boiler combustion analysis module, the optimizing module and the secondary air accurate control module to obtain the optimal opening degree of each layer of secondary air door at the next moment, and after the optimal opening degree of each layer of secondary air door is compared with the current value, the offset of the opening degree instruction of each layer of secondary air door is communicated back to the DCS.
Preferably, the closed-loop control module sets a screening mechanism for each instruction returned to the DCS to ensure correctness of an output result without causing control abnormality.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, it should be noted that, for those skilled in the art, many modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (9)
1. A overgrate air closed loop optimal control system based on air door resistance coefficient is characterized by comprising:
the secondary air accurate control module is used for establishing a mapping relation between the opening degree of each layer of secondary air doors and the air quantity, and the mapping relation is based on the corresponding relation between the opening degree of each layer of secondary air doors and the resistance coefficient;
the boiler combustion analysis module is used for processing parameters related to boiler combustion in real time and obtaining a characteristic value of a boiler combustion boundary and a characteristic value of a combustion effect after dimension reduction processing;
the intelligent modeling module is used for deeply mining big data information of boiler operation by adopting a supervised learning algorithm and establishing a neural network model between a boiler combustion boundary characteristic value and a combustion effect characteristic value; modeling data is obtained from a boiler combustion analysis module database and is carried out in an off-line periodic modeling mode;
the optimizing module is used for processing by utilizing an optimizing algorithm based on the established neural network model to obtain an optimal solution;
and the closed-loop control module is used for establishing two-way stable communication between the DCS and each module, acquiring parameters of a powder making system, a secondary air system and a flue gas system of the DCS in real time, reversely calculating an optimal value of the opening degree of a secondary air door of the boiler after the parameters are processed by the boiler combustion analysis module and the optimization searching module, transmitting the optimal value to the DCS and executing closed-loop control in the DCS.
2. The closed-loop optimization control system for the secondary air based on the air door resistance coefficient is characterized in that the resistance coefficient is the sum of an on-way resistance coefficient, a local resistance coefficient and an outflow resistance coefficient of the whole process of air supply entering a hearth from a large air box, and the corresponding relation between the air door opening and the resistance system is obtained through a refined cold-state secondary air door characteristic test; and the mapping relation between the opening degree of the secondary air door and the air volume takes pressure compensation into consideration in a thermal state.
3. The overfire air closed-loop optimization control system based on the air door resistance coefficient as recited in claim 1, wherein the boiler combustion analysis module processes parameters of a boiler pulverizing system, an overfire air system and a flue gas system, performs check calculation of boiler air balance from positive and negative dimensions, and performs dimension reduction processing on characteristic parameters of a boiler combustion boundary and a combustion effect to obtain characteristic quantities of the combustion boundary and the combustion effect.
4. The secondary air closed-loop optimization control system based on the damper resistance coefficient of claim 1, wherein the intelligent modeling module establishes a predictive model of boiler efficiency and NOx emission concentration; the input variables for both models include: the main steam flow of the boiler, the coal amount of each coal mill, the outlet temperature of each coal mill, the secondary air volume coefficient of each combustion area and the oxygen content of the outlet of the hearth; the output variables of the two models are boiler efficiency and NOx emission concentration, respectively.
5. The closed-loop optimization control system for secondary air based on the resistance coefficient of the damper as recited in claim 1, wherein the neural network model established by the intelligent modeling is a recurrent neural network-derived model.
6. The secondary air closed-loop optimization control system based on the resistance coefficient of the air door as claimed in claim 1, wherein the optimizing module preferentially judges whether the operation condition of the boiler is a normal condition or an abnormal condition; under the normal working condition, calculating the prediction model by using an optimization algorithm, and calculating an optimization value in a reverse direction according to the obtained result; under the unconventional working condition, a preset algorithm is used for directly outputting the instruction.
7. The closed-loop optimization control system for overwind based on the resistance coefficient of the air door as claimed in claim 1, wherein the closed-loop control module establishes a screening mechanism for the output result to ensure the applicability of the output result.
8. The closed-loop optimization control system for secondary air based on the resistance coefficient of the air door of claim 7, wherein the data communicated back to the DCS by the closed-loop control module is the offset value of the opening degree of the secondary air door of each layer.
9. The closed-loop optimization control system for secondary air based on the resistance coefficient of the air door as recited in claim 1, wherein the optimization algorithm adopted by the optimization module is a simulated annealing algorithm, a genetic algorithm, a cuckoo algorithm or an artificial bee colony algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110032762.XA CN112628712A (en) | 2021-01-11 | 2021-01-11 | Secondary air closed-loop optimization control system based on air door resistance coefficient |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110032762.XA CN112628712A (en) | 2021-01-11 | 2021-01-11 | Secondary air closed-loop optimization control system based on air door resistance coefficient |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112628712A true CN112628712A (en) | 2021-04-09 |
Family
ID=75293908
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110032762.XA Pending CN112628712A (en) | 2021-01-11 | 2021-01-11 | Secondary air closed-loop optimization control system based on air door resistance coefficient |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112628712A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113339787A (en) * | 2021-06-11 | 2021-09-03 | 华北电力大学(保定) | Fluidized bed boiler operation optimization method and system based on digital twinning |
CN113531581A (en) * | 2021-06-11 | 2021-10-22 | 江苏未来智慧信息科技有限公司 | Future intelligent steady-state combustion intelligent environmental protection island system |
CN113864812A (en) * | 2021-10-08 | 2021-12-31 | 大唐陕西发电有限公司 | Intelligent optimization method and control system for boiler secondary air door |
CN114046533A (en) * | 2021-08-31 | 2022-02-15 | 汉谷云智(武汉)科技有限公司 | Pulverized coal furnace combustion optimization method based on flame analysis optimization |
CN114135899A (en) * | 2021-11-10 | 2022-03-04 | 吉林省电力科学研究院有限公司 | Device and method for improving combustion optimization rate of boiler |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101415995A (en) * | 2006-07-04 | 2009-04-22 | 三浦工业株式会社 | Combustion device |
CN102032590A (en) * | 2010-12-31 | 2011-04-27 | 北京华电天仁电力控制技术有限公司 | Boiler combustion optimizing control system and optimizing control method based on accurate measurement system |
CN103576655A (en) * | 2013-11-06 | 2014-02-12 | 华北电力大学(保定) | Method and system for utility boiler combustion subspace modeling and multi-objective optimization |
CN105783025A (en) * | 2016-03-11 | 2016-07-20 | 国网山东省电力公司电力科学研究院 | Method for monitoring distribution of pulverized coal in low-NOx tangential coal-fired boiler |
JP2020119443A (en) * | 2019-01-28 | 2020-08-06 | 東京瓦斯株式会社 | Combustion-related information provision control device, and combustion-related information provision control program |
CN111596548A (en) * | 2020-05-29 | 2020-08-28 | 华润电力技术研究院有限公司 | Boiler secondary air regulating and controlling method, device, equipment and medium |
-
2021
- 2021-01-11 CN CN202110032762.XA patent/CN112628712A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101415995A (en) * | 2006-07-04 | 2009-04-22 | 三浦工业株式会社 | Combustion device |
CN102032590A (en) * | 2010-12-31 | 2011-04-27 | 北京华电天仁电力控制技术有限公司 | Boiler combustion optimizing control system and optimizing control method based on accurate measurement system |
CN103576655A (en) * | 2013-11-06 | 2014-02-12 | 华北电力大学(保定) | Method and system for utility boiler combustion subspace modeling and multi-objective optimization |
CN105783025A (en) * | 2016-03-11 | 2016-07-20 | 国网山东省电力公司电力科学研究院 | Method for monitoring distribution of pulverized coal in low-NOx tangential coal-fired boiler |
JP2020119443A (en) * | 2019-01-28 | 2020-08-06 | 東京瓦斯株式会社 | Combustion-related information provision control device, and combustion-related information provision control program |
CN111596548A (en) * | 2020-05-29 | 2020-08-28 | 华润电力技术研究院有限公司 | Boiler secondary air regulating and controlling method, device, equipment and medium |
Non-Patent Citations (1)
Title |
---|
陈光朝: "《催化裂化新工艺与设备检修维护技术手册 第3卷》", 31 October 2004, 吉林电子出版社 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113339787A (en) * | 2021-06-11 | 2021-09-03 | 华北电力大学(保定) | Fluidized bed boiler operation optimization method and system based on digital twinning |
CN113531581A (en) * | 2021-06-11 | 2021-10-22 | 江苏未来智慧信息科技有限公司 | Future intelligent steady-state combustion intelligent environmental protection island system |
CN113339787B (en) * | 2021-06-11 | 2022-03-22 | 华北电力大学(保定) | Fluidized bed boiler operation optimization method and system based on digital twinning |
CN114046533A (en) * | 2021-08-31 | 2022-02-15 | 汉谷云智(武汉)科技有限公司 | Pulverized coal furnace combustion optimization method based on flame analysis optimization |
CN114046533B (en) * | 2021-08-31 | 2024-03-12 | 汉谷云智(武汉)科技有限公司 | Pulverized coal furnace combustion optimization method based on flame analysis optimization |
CN113864812A (en) * | 2021-10-08 | 2021-12-31 | 大唐陕西发电有限公司 | Intelligent optimization method and control system for boiler secondary air door |
CN114135899A (en) * | 2021-11-10 | 2022-03-04 | 吉林省电力科学研究院有限公司 | Device and method for improving combustion optimization rate of boiler |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112628712A (en) | Secondary air closed-loop optimization control system based on air door resistance coefficient | |
Shi et al. | Combustion optimization of ultra supercritical boiler based on artificial intelligence | |
CN103576655B (en) | A kind of power boiler burning subspace modeling and Multipurpose Optimal Method and system | |
CN103322547B (en) | Boiler control and combustion optimization method | |
CN105972585B (en) | A kind of circulating fluidized bed boiler soot blowing and optimal system and method | |
US20110224830A1 (en) | Control system for operation of a fossil fuel power generating unit | |
CN106681381A (en) | SCR denitration system ammonia spraying quantity optimal control system and method based on intelligent feedforward signals | |
CN109695892B (en) | Method and device for protecting wall temperature of heating surface of boiler | |
CN110848733B (en) | Combustion optimization method based on coal quality on-line monitoring | |
CN107763657A (en) | A kind of Boiler Combustion Optimization System of thermal power plant's thermoisopleth sound wave temperature measuring unit | |
CN110263452B (en) | Flue gas time distribution characteristic analysis method and system in flue and denitration system | |
CN112228901B (en) | Online adjustment system and method for secondary air distribution of boiler | |
CN111881554A (en) | Optimization control method for boiler changing along with air temperature | |
CN111239360B (en) | Based on pulverized coal combustion overall process gas composition monitoring air distribution system | |
CN104729888B (en) | Flue fly ash constant-speed sampling system based on BP neural network and control method | |
CN107355812A (en) | A kind of Boiler Combustion Optimization System | |
CN108488831B (en) | Boiler combustion control system and method | |
CN214198729U (en) | Large-scale power plant boiler draught fan air volume adjusting device | |
CN112240566B (en) | Online adjustment system and method for offset firing of boiler | |
CN113341713B (en) | Coal-air synchronous dynamic coordination control method for coal-fired unit | |
CN115657466A (en) | Boiler system of intelligent control ammonia input volume | |
CN115145152A (en) | Boiler combustion and denitration process collaborative optimization control method | |
CN112856479A (en) | Heating furnace low oxygen burner and system | |
CN114791102B (en) | Combustion optimization control method based on dynamic operation data analysis | |
CN114779722B (en) | Intelligent combustion optimization control system and method for coal-fired power station boiler |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210409 |
|
RJ01 | Rejection of invention patent application after publication |