CN110173710B - Energy-saving type climate feedback dynamic regulation and control device and method for eliminating smoke plume - Google Patents
Energy-saving type climate feedback dynamic regulation and control device and method for eliminating smoke plume Download PDFInfo
- Publication number
- CN110173710B CN110173710B CN201910376483.8A CN201910376483A CN110173710B CN 110173710 B CN110173710 B CN 110173710B CN 201910376483 A CN201910376483 A CN 201910376483A CN 110173710 B CN110173710 B CN 110173710B
- Authority
- CN
- China
- Prior art keywords
- flue gas
- smoke
- heat exchanger
- temperature
- reheater
- 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.)
- Active
Links
- 239000000779 smoke Substances 0.000 title claims abstract description 212
- 238000000034 method Methods 0.000 title claims abstract description 46
- 239000003546 flue gas Substances 0.000 claims abstract description 245
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims abstract description 242
- 238000009833 condensation Methods 0.000 claims abstract description 53
- 230000005494 condensation Effects 0.000 claims abstract description 52
- 238000003379 elimination reaction Methods 0.000 claims abstract description 46
- 230000008030 elimination Effects 0.000 claims abstract description 40
- 238000012423 maintenance Methods 0.000 claims abstract description 13
- 238000013461 design Methods 0.000 claims abstract description 12
- 230000001105 regulatory effect Effects 0.000 claims abstract description 12
- 238000011156 evaluation Methods 0.000 claims abstract description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 97
- 238000013528 artificial neural network Methods 0.000 claims description 60
- 238000001816 cooling Methods 0.000 claims description 46
- 238000012549 training Methods 0.000 claims description 39
- 210000002569 neuron Anatomy 0.000 claims description 27
- 238000003303 reheating Methods 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 17
- 229920006395 saturated elastomer Polymers 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 11
- 239000000498 cooling water Substances 0.000 claims description 9
- 238000004088 simulation Methods 0.000 claims description 9
- 238000012546 transfer Methods 0.000 claims description 9
- 238000010438 heat treatment Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 239000007788 liquid Substances 0.000 claims description 4
- 238000005260 corrosion Methods 0.000 claims description 3
- 230000007797 corrosion Effects 0.000 claims description 3
- 238000009792 diffusion process Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000005265 energy consumption Methods 0.000 claims description 3
- 239000010410 layer Substances 0.000 description 27
- 230000008901 benefit Effects 0.000 description 6
- 239000000443 aerosol Substances 0.000 description 5
- 239000007789 gas Substances 0.000 description 5
- 150000003839 salts Chemical class 0.000 description 5
- 239000002253 acid Substances 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000003344 environmental pollutant Substances 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 231100000719 pollutant Toxicity 0.000 description 2
- 235000019738 Limestone Nutrition 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000945 filler Substances 0.000 description 1
- 239000010440 gypsum Substances 0.000 description 1
- 229910052602 gypsum Inorganic materials 0.000 description 1
- 239000006028 limestone Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005399 mechanical ventilation Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 238000001179 sorption measurement Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000002918 waste heat Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
- B01D53/26—Drying gases or vapours
- B01D53/265—Drying gases or vapours by refrigeration (condensation)
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
- F23J—REMOVAL OR TREATMENT OF COMBUSTION PRODUCTS OR COMBUSTION RESIDUES; FLUES
- F23J15/00—Arrangements of devices for treating smoke or fumes
- F23J15/02—Arrangements of devices for treating smoke or fumes of purifiers, e.g. for removing noxious material
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
- F23J—REMOVAL OR TREATMENT OF COMBUSTION PRODUCTS OR COMBUSTION RESIDUES; FLUES
- F23J15/00—Arrangements of devices for treating smoke or fumes
- F23J15/06—Arrangements of devices for treating smoke or fumes of coolers
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
- F23J—REMOVAL OR TREATMENT OF COMBUSTION PRODUCTS OR COMBUSTION RESIDUES; FLUES
- F23J15/00—Arrangements of devices for treating smoke or fumes
- F23J15/08—Arrangements of devices for treating smoke or fumes of heaters
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
- G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E20/00—Combustion technologies with mitigation potential
- Y02E20/30—Technologies for a more efficient combustion or heat usage
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Mechanical Engineering (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Chemical & Material Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Automation & Control Theory (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Thermal Sciences (AREA)
- Public Health (AREA)
Abstract
The invention discloses an energy-saving climate feedback dynamic regulation and control device and a method for eliminating smoke plume.A lowest outlet smoke temperature of a smoke reheater under the condition of eliminating smoke plume is predicted by changing the outlet smoke temperature of a smoke condensing heat exchanger under the condition of inputting atmospheric temperature, humidity and wind speed; by adopting the method, the outlet smoke temperature of the smoke condensing heat exchanger and the outlet smoke temperature of the smoke reheater can be accurately and quickly predicted and regulated under any meteorological conditions, so that the real-time operation cost is lowest; a smoke plume elimination parameter database is constructed by constructing MySQL, a system evaluation system is established, the outlet smoke temperature of a group of flue gas condensation heat exchanger and flue gas reheater with the lowest total life cycle cost is selected as the target design temperature of the heat exchanger, the temperature of the flue gas condensation heat exchanger and the design parameters of the flue gas reheater are determined, dynamic regulation and control are carried out by utilizing a regulation and control device, and the initial investment cost and the operation and maintenance cost of the heat exchanger are reduced.
Description
Technical Field
The invention relates to the field of dynamic control of smoke plume elimination (commonly called white elimination) through condensation and heating of smoke, in particular to an energy-saving type climate feedback dynamic regulation and control device and method for eliminating smoke plume.
Background
With the continuous and high-speed development of economy in China, the consumption of fossil energy is increased year by year, and the air quality is increasingly deteriorated.
In order to meet the requirement of ultralow emission, most thermal power plants adopt limestone/gypsum wet desulphurization mode to remove SO2. The method can discharge SO2The concentration is controlled at 20mg/m3The discharged flue gas contains a large amount of saturated water vapor, soluble salt aerosol with the particle size of less than 5m and SO3/H2SO4Acid gases such as HF and HCl. SO (SO)3And soluble salt aerosols with particle sizes less than 5 μm are one factor contributing to haze; SO (SO)3/H2SO4Acid gases such as HF and HCl inThe tail flue and the chimney are condensed and separated out, so that the tail flue and the chimney have extremely strong corrosivity and bring hidden troubles to the safe operation of the boiler. Due to the influence of factors such as atmospheric temperature, atmospheric relative humidity, wind speed and the like, the flue gas containing a large amount of saturated vapor is continuously diffused and cooled after being discharged from a chimney, a large amount of small liquid drops are condensed and separated out, the sun light is refracted and scattered, and white smoke plume appears. In order to remove most of the soluble salt aerosol and SO3/H2SO4Acid gases such as HF and HCl eliminate white smoke plume under most weather conditions, and in the condensation process, the smoke is cooled along a saturated humidity curve, the smoke reaches a supersaturated state, a large amount of water vapor is condensed and separated out, and the absolute moisture content of the smoke in the process is greatly reduced. Through the condensation process of the condensation heat exchanger, not only can the soluble salt aerosol and SO be removed through phase change condensation3/H2SO4Acid gases such as HF and HCl, and can make soluble salt aerosol and SO by electrostatic adsorption and thermal surge effect3/H2SO4PM pollutants such as HF and HCl are trapped on the surface of the heat exchanger, so that the pollutant removing effect is better. The main purpose of flue gas reheating is to raise the temperature of flue gas and reduce the relative moisture content of wet flue gas at the outlet of a chimney, and the reheating process can also increase the lifting height of the flue gas and reduce local pollution. In order to reduce the phenomenon of white smoke, some developed countries use the emission of wet smoke after the temperature of the wet smoke is raised as a hard regulation, such as Germany regulation that the smoke discharge temperature is higher than 72 ℃, British regulation that the smoke discharge temperature is higher than 80 ℃, and Japan regulation that the smoke discharge temperature is 90-100 ℃. However, the exhaust gas temperature is too high, so that more heat consumption is invested in the reheating process, and the cost of the whole enterprise is increased. And whether "white smoke" is generated or not is greatly related to not only the exhaust smoke temperature but also the atmospheric temperature, relative humidity and wind speed.
Disclosure of Invention
In order to overcome the problems of the prior art, the invention aims to provide an energy-saving type climate feedback dynamic regulation and control device and method for eliminating smoke plume, a BP neural network is used as a control method for eliminating smoke plume by climate feedback, the combination of the temperatures of a plurality of flue gas condensing heat exchangers and the temperatures of flue gas reheaters under any climate condition can be accurately and quickly obtained, a group of temperatures with the lowest life-saving cost is selected from the combination of the temperatures of the plurality of flue gas condensing heat exchangers and the temperatures of the flue gas reheaters by adopting a MySQL database as a target temperature, the temperatures of the flue gas condensing heat exchangers and the temperatures of the flue gas reheaters are regulated and controlled to the target temperature by a dynamic regulation and control device, the dynamic prediction and regulation and control of the outlet flue gas temperature of the flue gas condensing heat exchangers and the outlet flue gas temperature of the flue gas reheaters under any climate condition can be realized by adopting the invention, the design, the initial investment cost and the operation and maintenance cost of the heat exchanger are reduced.
In order to achieve the purpose, the invention adopts the following technical scheme:
an energy-saving climate feedback dynamic regulation and control device for eliminating smoke plume comprises a smoke condensing heat exchanger 1, a demister 2, a smoke reheater 3 and a chimney 4 which are sequentially connected through a flue according to the flow direction of smoke; the 1 st-stage heat exchanger of the flue gas condensation heat exchanger 1 is connected between a vacuum pump 6 and a shaft seal heater 7 through a pipeline, a regulating valve 12 is arranged on the pipeline, and condensed water taken out from the condenser 5 and the space between the vacuum pump 6 and the shaft seal heater 7 is used as a cooling working medium of the first heat collector; the 2 nd-stage heat exchanger of the flue gas condensation heat exchanger 1 is connected with a cooling tower 8 through a pipeline, a regulating valve 12 is arranged on the pipeline, circulating water of the cooling tower 8 is used as a cooling working medium of the 2 nd-stage heat exchanger to cool flue gas, the flue gas reheater 3 is connected between a deaerator 10 and a main water-feeding pump 11 through a pipeline, and the flue gas is heated through part of boiler feed water taken out from the low-pressure heater 9, the deaerator 10 to the main water-feeding pump 11; the flow of condensed water, circulating water and boiler feed water is adjusted through the adjusting valve 12, and then the temperature of the flue gas at the outlet of the flue gas condensing heat exchanger 1 and the flue gas reheater 3 is adjusted.
An energy-saving climate feedback dynamic regulation and control method for eliminating smoke plume comprises the steps of firstly, predicting the reheating temperature of a smoke reheater 3 by setting the smoke temperature of an outlet of a smoke condensing heat exchanger 1 under the real-time atmospheric condition in an energy-saving climate feedback dynamic regulation and control device for eliminating smoke plume based on a BP neural network; the outlet flue gas temperatures of a group of flue gas condensing heat exchangers 1 and flue gas reheaters 3 with the lowest total life cycle cost are selected as final target temperatures by utilizing a relational database management system MySQL, so that the temperature of the flue gas condensing heat exchangers 1 and the design parameters of the flue gas reheaters 3 are determined; finally, the dynamic regulation and control device based on the condensation reheating technical route realizes the dynamic regulation and control of the outlet flue gas temperature of the flue gas condensation heat exchanger 1 and the flue gas reheater 3, reduces the initial investment cost and the operation and maintenance cost of the heat exchanger, and comprises the following steps:
s1, building a climate feedback dynamic regulation and control device based on energy-saving smoke plume elimination:
s2, predicting the combination of the outlet flue gas temperatures of the flue gas condensing heat exchanger 1 and the flue gas reheater 2 through a BP neural network:
s2-1, data processing: acquiring the outlet temperature of the flue gas reheater 3 under the conditions of different atmospheric temperatures, different atmospheric relative humidities, different wind speeds and different outlet flue gas temperatures of the flue gas condensing heat exchanger 1, thereby obtaining a calibrated smoke plume elimination data set R of an experimental sample, wherein the data set R comprises M groups of experimental data and corresponding experimental results, and carrying out normalization processing on the smoke plume elimination data set R; .
S2-2, data grouping: dividing the normalized smoke plume elimination data set R into three types of data, namely a training set D, a variable set V and a test set T;
s2-3, finding the optimal BP neural network and initializing: initializing a BP neural network, creating the BP neural network containing two hidden layers, finding out the optimal number of neurons of the hidden layers, and setting a learning rate, a neuron activation function, a transfer function, a training minimum mean square error target, a speed and a maximum training frequency according to actual needs;
s2-4, predicting the combination of the flue gas condensing heat exchanger and the flue gas reheater outlet flue gas temperature: under a given atmospheric condition, predicting the outlet smoke temperature of the smoke reheater 3 by changing the outlet smoke temperature of the smoke condensing heat exchanger 1, training all weight values and threshold values of a BP neural network with generalization capability meeting actual requirements of a factory, and directly predicting the outlet smoke temperature combination of the smoke condensing heat exchanger 1 and the smoke reheater 3 under the real-time atmospheric condition;
s2-5, improving the generalization ability of the BP neural network: inputting the smoke plume elimination data set R obtained in real time in the step S2-1 into a BP neural network to obtain a BP neural network simulation result, comparing the simulation result with an actual result, continuously reducing the error between the simulation result and the actual result, and optimizing the whole BP neural network;
s3, through S2, under different atmospheric conditions, a series of different combinations of outlet flue gas temperatures of the flue gas condenser 1 and the flue gas reheater 3 can be predicted, and in order to dynamically select a group with lowest cost in the whole life cycle as an actual regulation and control target, a system evaluation system is established by utilizing a relational database management system MySQL:
s3-1, parameters of the smoke plume elimination process comprise: when the saturated wet flue gas with the unit flow rate of 45-70 ℃ is condensed to 30-48 ℃, the flow rate of the flue gas, the cooling water temperature and the weight, the flue gas wind resistance, the water side resistance, the heat exchanger power and the condensed water amount of the flue gas condensing heat exchanger 1 under the conditions of the heat exchanger material are different; when the saturated wet flue gas with the unit flow rate of 30-48 ℃ is heated to 54-90 ℃, the flow rate of different flue gases, the temperature of a heating working medium and the weight, the flue gas wind resistance, the working medium side resistance and the heat exchanger power of a flue gas reheater under the condition of heat exchanger materials are different; the unit flow of the circulating cooling water of the flue gas condensation heat exchanger 1 consumes power in operation under the conditions of different atmospheric temperatures, relative humidity, wind speeds and circulating temperatures;
s3-2, establishing an evaluation system: according to parameters of a smoke plume elimination process, calculating initial investment cost and operation and maintenance cost of different smoke temperature combinations at the outlets of the smoke condensing heat exchanger 1 and the smoke reheater 3 in MySQL, selecting the outlet smoke temperatures of a group of smoke condensing heat exchanger 1 and the smoke reheater 3 with the lowest total life cycle cost as target temperatures under the conditions of given smoke plume elimination temperature points and equipment operation years, and determining the temperature of the smoke condensing heat exchanger 1 and the design parameters of the smoke reheater 3;
s3-3, wherein the initial investment cost comprises:
the prices of the flue gas condensing heat exchanger 1 and the flue gas reheater 3 are 8 × 1.4 × the weight of the heat exchangers; in the formula, the price unit of the flue gas condensing heat exchanger 1 and the flue gas reheater 3 is ten thousand yuan, and the weight unit of the heat exchanger is ton;
the cost of the cooling tower is 250 x the weight of the circulating water; wherein the cost unit of the cooling tower is Yuan, and the weight unit of the circulating water is ton;
s3-4, the operation and maintenance cost comprises:
the power consumption of cooling water is set to be 27.5kW per 100 t;
the power consumption of the induced draft fan is Pa Q/(1000 3600.8), wherein the unit of the power consumption of the induced draft fan is kw, Pa is the full wind pressure of the fan, Q is the wind volume, and the unit is m3/h;
2t of steam heating at 130 ℃ is needed for each MW of wet saturated steam;
and (3) water replenishing of the system: 2 t;
electric charge: 0.5 yuan/kwh; steam: 130 yuan/t, water rate 3 yuan/t;
s4, dynamically regulating the outlet flue gas temperature of the flue gas condensing heat exchanger and the flue gas reheater 3 to a target temperature by the dynamic regulation device according to real-time meteorological conditions, so that the cost of the operation process is the lowest:
s4-1, the flue gas condensation heat exchanger 1 utilizes the condensed water and the cooling tower circulating water to recover high-grade heat energy in the flue gas, and the purpose of dynamically adjusting the outlet temperature of the flue gas condensation heat exchanger 1 is achieved by adjusting the flow rate of the condensed water and the cooling tower circulating water, the power of a variable frequency fan and closing part of the flue gas condensation heat exchanger to change the heat transfer area;
s4-2, the flue gas reheater 3 heats the flue gas by using steam extracted by a steam turbine or partial boiler feed water taken out from the outlet of the deaerator 10 to the main feed water pump 11, and the aim of dynamically adjusting the flue gas temperature at the outlet of the flue gas reheater 3 is fulfilled by adjusting the flow and the temperature of the extracted steam or the feed water and closing the partial flue gas reheater to change the heat transfer area.
The calculation formula of the normalization processing in step S2-1 is:
pn=2*(p-pmin)/(pmax-pmin)-1
in the formula, pn,p,pminAnd pmaxThe normalized sample data, the original sample data, the minimum value of the original sample data and the maximum value of the original sample data are respectively.
The data packet in the step S2-2 includes:
taking 60% of the normalized M groups of smoke plume elimination data sets as normal training data, 20% of the normalized M groups of smoke plume elimination data sets as variable data, and 20% of the normalized M groups of smoke plume elimination data sets as test data; wherein, variable data is set in the network training to prevent an overfitting state; test data is input in network training to check the prediction capability of the trained network.
The step S2-3 of finding the optimal BP neural network and initializing includes:
establishing a four-layer BP neural network which is an input layer, two hidden layers and an output layer respectively, wherein the number of neurons in the input layer is 4, and the number of neurons in the output layer is 1; neuron number of hidden layer is represented by formulaIs determined in which n1The number of hidden layer neurons is all integers in a set range of the number of hidden layer neurons, and the optimal number of hidden layer neurons is searched in a traversal search mode;
initializing all weights and thresholds of the BP neural network by using Gaussian distribution random numbers; all neuron activation functions adopt Sigmoid functions; respectively setting a training minimum mean square error, a training minimum performance gradient, a maximum training frequency and a training function;
the step S2-4 of predicting the combination of the flue gas temperature at the outlet of the flue gas condensing heat exchanger 1 and the flue gas temperature at the outlet of the flue gas reheater 3 includes:
according to the step S2-3, an optimal BP neural network is selected, the obtained atmospheric temperature, the atmospheric relative humidity, the wind speed and the outlet smoke temperature of the smoke condensing heat exchanger 1 are normalized under the real-time atmospheric condition and input into the BP neural network, the reheating temperature of the smoke reheater 3 can be predicted by performing inverse normalization on the obtained result, and the obtained result and the corresponding outlet smoke temperature of the smoke condensing heat exchanger 1 form a smoke condensing heat exchanger 1 and smoke reheater 3 outlet smoke temperature combination.
The purpose of the flue gas condensation heat exchanger 1 in the step S4-1 is to condense 45-70 ℃ saturated wet flue gas to 30-48 ℃, and because the temperature difference between the inlet and the outlet of the working medium is small, the latent heat of water vapor in the flue gas is huge, and the flow of the working medium is huge, so in order to reduce the flow velocity of the working medium in the flue gas condensation heat exchanger 1 and reduce the flow resistance of the working medium, the flue gas condensation heat exchanger 1 is divided into 2-6 stages connected in parallel along the flow direction of the flue gas, and each stage is provided with an independent inlet and outlet header; the inlet smoke temperature of the first-stage smoke condensing heat exchanger is highest, the working medium is condensed water, high-grade heat energy in the smoke is recovered, and the temperature of the condensed water is raised to be higher than 42 ℃; for the unit without condensed water, the working medium of the first-stage and later flue gas condensation heat exchangers selects circulating water of a cooling tower, and the cooling tower selects a hyperbolic natural draft cooling tower, a mechanical draft cooling tower and a closed air cooling tower.
In the step S4-2, the flue gas reheater 3 heats the flue gas to 54-85 ℃ by using steam extracted by a steam turbine at 110-400 ℃ or part of boiler feed water at 100-140 ℃ taken out from the outlet of the deaerator 10 to the main feed water pump 11, the drain water generated after steam extraction is used is sent to the deaerator 10, and the boiler feed water is sent back to a pipeline in front of the main feed water pump; the demister 2 is arranged at the inlet of the flue gas reheater 3 to remove small liquid drops carried in the flue gas, so that the problems of corrosion and scaling of the flue gas reheater 3 are reduced, and the reheating energy consumption is reduced; the smoke is reheated to reduce the relative humidity of the discharged smoke, so that the steam is prevented from being condensed to form small droplets in the diffusion and cooling process, and the white smoke is eliminated visually.
Compared with the prior art, the invention has the advantages that:
1) the control method for eliminating smoke plume by adopting the BP neural network as climate feedback can accurately and quickly obtain the lowest temperature of the flue gas reheater under any climate condition, thereby reducing the test cost, reducing the operation cost and enabling the system to be more flexible.
2) The BP neural network has nonlinear mapping capability, self-learning and self-adaption capability, generalization capability and fault-tolerant capability. The BP neural network is adopted to optimize and predict the system, and compared with the traditional method, the method has the innovative advantages.
3) Compared with a model algorithm based on Logistic regression, the BP neural network is a feedforward neural network with more than two layers, compared with a single-layer neural network based on Logistic regression, the BP neural network can reversely propagate errors, timely correct the weight and bias of each layer of unit, and has the advantage of higher accuracy.
4) The method considers the influence of external factor parameters such as atmospheric temperature, relative humidity, wind speed and the like on the smoke plume elimination system, and enlarges the dimensionality of the data set.
5) The invention continuously optimizes the network through the data fed back in the actual production and improves the generalization capability of the network.
6) The invention realizes the purpose of selecting the smoke plume elimination temperature combination with the lowest total operation cost under the given atmospheric condition through the evaluation system of the smoke plume elimination system established based on the MySQL database. Through the optimization of the control system, the smoke plume elimination cost is reduced, and the environmental protection benefit and the economic benefit are considered.
7) The system evaluation system not only comprises the initial investment costs such as the cost of the flue gas condensation heat exchanger, the flue gas reheater and the cooling tower, but also considers the factors of the operation and maintenance costs such as the power consumption, the power consumption of the induced draft fan, the water cost, the power cost and the like, considers the factors influencing the system more comprehensively, and realizes the aim of the lowest cost of the flue gas elimination smoke plume full life cycle.
8) The dynamic regulation and control device not only can realize the dynamic regulation and control of the temperature of the flue gas condensation heat exchanger and the flue gas reheater and eliminate smoke plume, but also can heat condensed water while eliminating the smoke plume, recover the waste heat of the flue gas and reduce the operating cost of a flue gas system for eliminating the smoke plume.
Drawings
FIG. 1 is a schematic connection diagram of a smoke side of an energy-saving dynamic climate feedback control device for eliminating smoke plume provided by the present invention.
FIG. 2 is a flow chart of a climate feedback dynamic control method for energy-saving smoke plume elimination according to the present invention.
FIG. 3 is a graph comparing the predicted results and experimental results of the BP neural network model.
FIG. 4 is an error map of the BP neural network training process.
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments.
For the technical route for eliminating the smoke plume in condensation reheating, the factors influencing the smoke plume eliminating effect and the whole life cycle cost of the system are many, wherein the most important factors are the outlet smoke temperature of the smoke condensation heat exchanger and the smoke reheater. The smoke temperature at the outlet of the condensation outlet is reduced, and the smoke temperature at the outlet of the smoke reheater is increased, so that the aim of eliminating smoke plume can be achieved, but a large amount of power consumption and heat consumption investment can be increased, and the investment and operation and maintenance cost of enterprises are overhigh. And the outlet flue gas temperature of the flue gas condensing heat exchanger and the flue gas reheater is related to the temperature, the relative humidity and the wind speed of the atmosphere. Therefore, when designing the white elimination system, according to local climate conditions, the outlet smoke temperatures of the condensing heat exchanger and the reheating heat exchanger with the lowest life cycle cost need to be determined, so as to determine the design parameters of the heat exchanger.
The invention aims to provide an energy-saving climate feedback dynamic regulation and control device and method for eliminating smoke plume.
The main approach of dynamic prediction is based on a BP neural network, and the smoke temperature at the outlet of a smoke reheater is dynamically predicted through real-time atmospheric temperature, humidity, wind speed and smoke temperature at the outlet of a smoke condensing heat exchanger, so that smoke plume is eliminated;
as a further scheme of the invention, because different reheating temperatures influence the heat consumption and reheating heat exchanger cost of the reheating process at the temperature, and different condensing temperatures influence the pumping power loss and condensing heat exchanger cost of the condensing process at the temperature, the invention realizes that the outlet smoke temperature of a group of smoke condensing heat exchangers and smoke reheaters with lowest full life cycle cost is selected as the final target temperature under the conditions of given atmospheric temperature, relative humidity, wind speed and operation time by constructing a model and a design function based on a MySQL database.
In order to realize the final target temperature combination, the invention designs a dynamic regulation and control device, and in the condensation process, condensed water or cooling tower circulating water is selected to recover high-grade heat energy in the flue gas; in the reheating process, the flue gas is heated by using steam extracted by a steam turbine or part of boiler feed water taken out from the outlet of a deaerator to a main feed water pump.
As shown in fig. 1, the energy-saving climate feedback dynamic regulation and control device for eliminating smoke plume comprises a flue gas condensing heat exchanger 1, a demister 2, a flue gas reheater 3 and a chimney 4 which are sequentially connected through a flue according to the flow direction of flue gas; the 1 st grade heat exchanger of the flue gas condensation heat exchanger 1 is connected between a vacuum pump 6 and a shaft seal heater 7 through a pipeline, a regulating valve 12 is arranged on the pipeline, and condensed water taken out from the condenser 5 and the space between the vacuum pump 6 and the shaft seal heater 7 is used as a cooling working medium of the 1 st grade heat exchanger; the 2 nd-stage heat exchanger of the flue gas condensation heat exchanger 1 is connected with a cooling tower 8 through a pipeline, a regulating valve 12 is arranged on the pipeline, circulating water of the cooling tower 8 is used as a cooling working medium of the 2 nd-stage heat exchanger to cool flue gas, the flue gas reheater 3 is connected between a deaerator 10 and a main water-feeding pump 11 through a pipeline, and the flue gas is heated through part of boiler feed water taken out from the low-pressure heater 9, the deaerator 10 to the main water-feeding pump 11; the flow of condensed water, circulating water and boiler feed water is adjusted through the adjusting valve 12, and then the temperature of the flue gas at the outlet of the flue gas condensing heat exchanger 1 and the flue gas reheater 3 is adjusted.
As shown in fig. 2, a climate feedback dynamic control method for energy-saving elimination of smoke plume, which comprises the steps of firstly, in an energy-saving climate feedback dynamic control device for elimination of smoke plume, predicting the reheating temperature of a smoke reheater 3 by setting the smoke temperature of an outlet of a smoke condensing heat exchanger 1 under the real-time atmospheric condition based on a BP neural network; the outlet flue gas temperature of a group of flue gas condensing heat exchangers and flue gas reheaters with the lowest total life cycle cost is selected as the final regulation temperature by utilizing a relational database management system MySQL, so that the temperature of the flue gas condensing heat exchangers 1 and the design parameters of the flue gas reheaters 3 are determined; finally, the dynamic regulation and control device based on the condensation reheating technical route realizes the dynamic regulation and control of the flue gas temperature at the outlets of the flue gas condensation heat exchanger 1 and the flue gas reheater 3, and reduces the initial investment cost and the operation and maintenance cost of the heat exchanger; the method comprises the following steps:
s1, building a climate feedback dynamic regulation and control device based on energy-saving smoke plume elimination:
s2, predicting the combination of the flue gas temperature at the outlet of the flue gas condensing heat exchanger 1 and the flue gas reheater 3 through a BP neural network:
s2-1, data processing: acquiring the outlet temperature of the flue gas reheater 3 under the conditions of different atmospheric temperatures, different atmospheric relative humidities, different wind speeds and different outlet flue gas temperatures of the flue gas condensing heat exchanger 1, thereby obtaining a calibrated smoke plume elimination data set R of an experimental sample, wherein the data set R comprises N groups of experimental data and corresponding experimental results, and carrying out normalization processing on the smoke plume elimination data set R; .
S2-2, data grouping: dividing the normalized smoke plume elimination data set R into three types of data, namely a training set D, a variable set V and a test set T;
s2-3, finding the optimal BP neural network and initializing: initializing a BP neural network, creating the BP neural network containing two hidden layers, finding out the optimal number of neurons of the hidden layers, and setting a learning rate, a neuron activation function, a transfer function, a training minimum mean square error target, a speed and a maximum training frequency according to actual needs;
s2-4, predicting the combination of the flue gas condensing heat exchanger and the flue gas reheater outlet flue gas temperature: under a given atmospheric condition, predicting the outlet smoke temperature of the smoke reheater 3 by changing the outlet smoke temperature of the smoke condensing heat exchanger 1, training all weight values and threshold values of a BP neural network with generalization capability meeting actual requirements of a factory, and directly predicting the outlet smoke temperature combination of the smoke condensing heat exchanger 1 and the smoke reheater 3 under the real-time atmospheric condition;
s2-5, improving the generalization ability of the BP neural network: inputting the smoke plume elimination data set R obtained in real time in the step S2-1 into a BP neural network to obtain a BP neural network simulation result, comparing the simulation result with an actual result, continuously reducing the error between the simulation result and the actual result, and optimizing the whole BP neural network;
s3, through S2, under different atmospheric conditions, a series of different combinations of outlet flue gas temperatures of the flue gas condenser 1 and the flue gas reheater 3 can be predicted, and in order to dynamically select a group with lowest cost in the whole life cycle as an actual regulation and control target, a system evaluation system is established by utilizing a relational database management system MySQL:
s3-1, parameters of the smoke plume elimination process comprise: when the saturated wet flue gas with the unit flow rate of 45-70 ℃ is condensed to 30-48 ℃, the flow rate of the flue gas, the cooling water temperature and the weight, the flue gas wind resistance, the water side resistance, the heat exchanger power and the condensed water amount of the flue gas condensing heat exchanger 1 under the conditions of the heat exchanger material are different; when the saturated wet flue gas with the unit flow rate of 30-48 ℃ is heated to 54-90 ℃, the flow rate of different flue gases, the temperature of a heating working medium and the weight, the flue gas wind resistance, the working medium side resistance and the heat exchanger power of a flue gas reheater under the condition of heat exchanger materials are different; the unit flow of the circulating cooling water of the flue gas condensation heat exchanger 1 consumes power in operation under the conditions of different atmospheric temperatures, relative humidity, wind speeds and circulating temperatures;
s3-2, establishing an evaluation system: according to parameters of a smoke plume elimination process, calculating initial investment cost and operation and maintenance cost of different smoke temperature combinations at the outlets of the smoke condensing heat exchanger 1 and the smoke reheater 3 in MySQL, selecting the outlet smoke temperatures of a group of smoke condensing heat exchanger 1 and the smoke reheater 3 with the lowest total life cycle cost as target temperatures under the conditions of given smoke plume elimination temperature points and equipment operation years, and determining the temperature of the smoke condensing heat exchanger 1 and the design parameters of the smoke reheater 3;
s3-3, wherein the initial investment cost comprises:
the prices of the flue gas condensing heat exchanger 1 and the flue gas reheater 3 are 8 × 1.4 × the weight of the heat exchangers; in the formula, the price unit of the flue gas condensing heat exchanger 1 and the flue gas reheater 3 is ten thousand yuan, and the weight unit of the heat exchanger is ton;
the cost of the cooling tower is 250 x the weight of the circulating water; wherein the cost unit of the cooling tower is Yuan, and the weight unit of the circulating water is ton;
s3-4, the operation and maintenance cost comprises:
the power consumption of cooling water is set to be 27.5kW per 100 t;
the power consumption of the induced draft fan is Pa Q/(1000 3600.8), wherein the unit of the power consumption of the induced draft fan is kw, Pa is the full wind pressure of the fan, Q is the wind volume, and the unit is m3/h;
2t of steam heating at 130 ℃ is needed for each MW of wet saturated steam;
and (3) water replenishing of the system: 2 t;
electric charge: 0.5 yuan/kwh; steam: 130 yuan/t, water rate 3 yuan/t;
s4, dynamically regulating the outlet flue gas temperature of the flue gas condensing heat exchanger and the flue gas reheater 3 to a target temperature by the dynamic regulation device according to real-time meteorological conditions, so that the cost of the operation process is the lowest:
s4-1, the flue gas condensation heat exchanger utilizes the condensed water and the cooling tower circulating water to recover high-grade heat energy in the flue gas, and the aim of dynamically adjusting the outlet temperature of the flue gas condensation heat exchanger is fulfilled by adjusting the flow rate of the condensed water and the cooling tower circulating water, the power of a frequency conversion fan of the cooling tower and closing part of the flue gas condensation heat exchanger to change the heat transfer area;
s4-2, the flue gas reheating heat exchanger 1 heats flue gas by using steam extracted by a steam turbine or partial boiler feed water taken out from the outlet of the deaerator 10 to the main feed water pump 11, and the aim of dynamically adjusting the flue gas temperature at the outlet of the flue gas reheater 3 is fulfilled by adjusting the flow and the temperature of the extracted steam or the feed water and closing a partial flue gas reheater to change the heat transfer area.
In a preferred embodiment of the present invention, the calculation formula of the normalization process in step S2-1 is:
pn=Z*(p-pmin)/(pmax-pmin)-1
in the formula, pn,p,pminAnd pmaxThe normalized sample data, the original sample data, the minimum value of the original sample data and the maximum value of the original sample data are respectively.
As a preferred embodiment of the present invention, the data packet in step S2-2 includes:
taking 60% of the normalized N groups of smoke plume elimination data sets as normal training data, 20% of the normalized N groups of smoke plume elimination data sets as variable data, and 20% of the normalized N groups of smoke plume elimination data sets as test data; wherein, variable data is set in the network training to prevent an overfitting state; test data is input in network training to check the prediction capability of the trained network.
As a preferred embodiment of the present invention, the finding an optimal BP neural network and initializing in step S2-3 includes:
establishing a four-layer BP neural network which is an input layer, two hidden layers and an output layer respectively, wherein the number of neurons in the input layer is 4, and the number of neurons in the output layer is 1; neuron number of hidden layer is represented by formulaIs determined in which n1The number of hidden layer neurons is all integers in a set range of the number of hidden layer neurons, and the optimal number of hidden layer neurons is searched in a traversal search mode;
initializing all weights and thresholds of the BP neural network by using Gaussian distribution random numbers; all neuron activation functions adopt Sigmoid functions, and the calculation formula is
Respectively setting a training minimum mean square error, a training minimum performance gradient, a maximum training frequency and a training function;
the steps of training and learning the BP neural network topological model are as follows:
(1) inputting data: step S2, after preprocessing the collected data for eliminating the smoke plume in step S3, different working conditions can be represented by N variables, and then the training set has L pairs of input and output to form { X }N,ANWhere X is 1,2,3, training)NFor input, ANIs the true value;
(2) and calculating the standard deviation: xNThe prediction output obtained after propagation through the neural network is YNThen Y isNThe error exists between the predicted value and the true value, and the error between the predicted value and the true value is measured by using the standard deviation;
(3) and (3) reverse feedback: adjusting the values of w and b to minimize the value of the error function;
(4) repeatedly executing reverse feedback to update the weight of each connecting line and the bias of each layer in the neural network, and repeating the process under the condition that the stop condition is not reached; the stop conditions may be the following two:
a) the predicted error rate e is below a threshold of 0.01;
b) up to 200 iterations.
The method for predicting the combination of the flue gas temperature of the outlet of the flue gas condensing heat exchanger and the flue gas temperature of the outlet of the flue gas reheater through the BP neural network comprises the following steps:
according to the step S2-3, selecting an optimal BP neural network, setting the outlet smoke temperature normalization of the smoke condensation heat exchanger 1 under the real-time atmospheric condition, inputting the normalization result into the BP neural network, performing inverse normalization on the obtained result, namely predicting the reheating temperature of the smoke reheater 3, and forming a smoke condensation heat exchanger 1 and smoke temperature combination of the smoke reheater 3 with the corresponding outlet smoke temperature of the smoke condensation heat exchanger 1. And is regulated and controlled by a dynamic regulation and control device.
The purpose of the flue gas condensation heat exchanger 1 in the step S4-1 is to condense 45-70 ℃ saturated wet flue gas to 30-48 ℃, and because the temperature difference between the inlet and the outlet of the working medium is small, the latent heat of water vapor in the flue gas is huge, and the flow of the working medium is huge, so in order to reduce the flow velocity of the working medium in the flue gas condensation heat exchanger 1 and reduce the flow resistance of the working medium, the flue gas condensation heat exchanger 1 is divided into 2-6 stages connected in parallel along the flow direction of the flue gas, and each stage is provided with an independent inlet and outlet header; the inlet smoke temperature of the first-stage smoke condensing heat exchanger is highest, the working medium is condensed water, high-grade heat energy in the smoke is recovered, and the temperature of the condensed water is raised to be higher than 42 ℃; for the unit without condensed water, the working medium of the first-stage and later flue gas condensation heat exchangers selects circulating water of a cooling tower, and the cooling tower selects a hyperbolic natural draft cooling tower, a mechanical draft cooling tower and a closed air cooling tower.
The mechanical ventilation cooling tower mainly comprises a variable frequency fan, a tower body, a filler, a water collector, a shutter and the like.
In the step S4-2, the flue gas reheater 3 heats the flue gas to 54-85 ℃ by using steam extracted by a steam turbine at 110-400 ℃ or part of boiler feed water at 100-140 ℃ taken out from the outlet of the deaerator 10 to the main feed water pump 11, the drain water generated after steam extraction is used is sent to the deaerator 10, and the boiler feed water is sent back to a pipeline in front of the main feed water pump; the demister 2 is arranged at the inlet of the flue gas reheater 3 to remove small liquid drops carried in the flue gas, so that the problems of corrosion and scaling of the flue gas reheater 3 are reduced, and the reheating energy consumption is reduced; the smoke is reheated to reduce the relative humidity of the discharged smoke, so that the steam is prevented from being condensed to form small droplets in the diffusion and cooling process, and the white smoke is eliminated visually.
FIG. 3 is a graph comparing the predicted results of the optimal BP neural network model under test with the experimental results; as can be seen from the figure: through training, the network can realize high-precision prediction.
FIG. 4 is an error diagram of the optimal BP neural network training process under test; as can be seen from the figure: when iterating 6 times, the verification performance is 0.0010442, reaching the optimum.
Claims (7)
1. An energy-saving climate feedback dynamic regulation and control method for eliminating smoke plume, the energy-saving climate feedback dynamic regulation and control device for eliminating smoke plume adopted by the method comprises a smoke condensing heat exchanger (1), a demister (2), a smoke reheater (3) and a chimney (4) which are sequentially connected through a flue according to the flow direction of smoke; a 1 st-stage heat exchanger of the flue gas condensation heat exchanger (1) is connected between a vacuum pump (6) and a shaft seal heater (7) through a pipeline, a regulating valve (12) is arranged on the pipeline, and condensed water taken out from the space between the condenser (5) and the vacuum pump (6) and the shaft seal heater (7) is used as a cooling working medium of the 1 st-stage heat exchanger; the second-stage heat exchanger of the flue gas condensation heat exchanger (1) is connected with a cooling tower (8) through a pipeline, a regulating valve (12) is arranged on the pipeline, circulating water of the cooling tower (8) is used as a cooling working medium of the second-stage heat exchanger to cool flue gas, the flue gas reheater (3) is connected between a deaerator (10) and a main water-feeding pump (11) through a pipeline, and part of boiler water taken out from the deaerator (10) to the main water-feeding pump (11) is used for heating the flue gas through a low-pressure heater (9); the flow of condensed water, circulating water and boiler feed water is adjusted through an adjusting valve (12), and then the temperature of flue gas at the outlet of the flue gas condensing heat exchanger (1) and the flue gas reheater (3) is adjusted;
the method comprises the following steps: firstly, predicting the reheating temperature of a flue gas reheater (3) by setting the outlet flue gas temperature of a flue gas condensing heat exchanger (1) under the real-time atmospheric condition based on a BP neural network in an energy-saving type climate feedback dynamic regulation and control device for eliminating smoke plume; selecting a group of outlet flue gas temperatures of the flue gas condensing heat exchanger and the flue gas reheater with the lowest total life cycle cost as final target temperatures by utilizing a relational database management system MySQL, so as to determine the design parameters of the flue gas condensing heat exchanger and the flue gas reheater; finally, the dynamic regulation and control device based on the condensation reheating technical route realizes the dynamic regulation and control of the flue gas temperature at the outlet of the flue gas condensation heat exchanger and the flue gas reheater, reduces the initial investment cost and the operation and maintenance cost of the heat exchanger, and is characterized by comprising the following steps:
s1, building a climate feedback dynamic regulation and control device based on energy-saving smoke plume elimination;
s2, predicting the combination of the flue gas temperature at the outlet of the flue gas condensing heat exchanger (1) and the flue gas temperature at the outlet of the flue gas reheater (3) through a BP neural network:
s2-1, data processing: acquiring the outlet temperature of a flue gas reheater (3) under different conditions of atmospheric temperature, atmospheric relative humidity, wind speed and flue gas temperature at the outlet of a flue gas condensation heat exchanger (1), thereby obtaining a calibrated smoke plume elimination data set R of an experimental sample, wherein the data set R comprises M groups of experimental data and corresponding experimental results, and carrying out normalization processing on the smoke plume elimination data set R;
s2-2, data grouping: dividing the normalized smoke plume elimination data set R into three types of data, namely a training set D, a variable set V and a test set T;
s2-3, finding the optimal BP neural network and initializing: initializing a BP neural network, creating the BP neural network containing two hidden layers, finding out the optimal number of neurons of the hidden layers, and setting a learning rate, a neuron activation function, a transfer function, a training minimum mean square error target, a speed and a maximum training frequency according to actual needs;
s2-4, predicting the combination of the flue gas condensing heat exchanger and the flue gas reheater outlet flue gas temperature: under a given atmospheric condition, predicting the outlet smoke temperature of a smoke reheater (3) by changing the outlet smoke temperature of a smoke condensing heat exchanger (1), training all weights and thresholds of a BP neural network with generalization capability meeting the actual requirements of a factory, and directly predicting the outlet smoke temperature combination of the smoke condensing heat exchanger (1) and the smoke reheater (3) under the real-time atmospheric condition;
s2-5, improving the generalization ability of the BP neural network: inputting the smoke plume elimination data set R obtained in real time in the step S2-1 into a BP neural network to obtain a BP neural network simulation result, comparing the simulation result with an actual result, continuously reducing the error between the simulation result and the actual result, and optimizing the whole BP neural network;
s3, predicting outlet flue gas temperature combinations of a series of different flue gas condensing heat exchangers (1) and flue gas reheaters (3) under different atmospheric conditions through S2, and establishing a system evaluation system by utilizing a relational database management system MySQL to dynamically select a group with lowest full life cycle cost as an actual regulation and control target:
s3-1, parameters of the smoke plume elimination process comprise: when the saturated wet flue gas with the temperature of 45-70 ℃ of unit flow is condensed to 30-48 ℃, the weight, the flue gas wind resistance, the water side resistance, the heat exchanger power and the condensed water amount of the flue gas condensing heat exchanger (1) under different flue gas flow rates, cooling water temperatures and heat exchanger material conditions are adopted; when the saturated wet flue gas with the unit flow rate of 30-48 ℃ is heated to 54-90 ℃, the flow rate of different flue gases, the temperature of a heating working medium and the weight, the flue gas wind resistance, the working medium side resistance and the heat exchanger power of a flue gas reheater under the condition of heat exchanger materials are different; the unit flow of flue gas condensation heat exchanger (1) circulates the running power consumption of cooling water under different atmospheric temperature, relative humidity, wind speed and circulation temperature conditions;
s3-2, establishing an evaluation system: according to parameters of a smoke plume elimination process, calculating initial investment cost and operation maintenance cost of different smoke temperature combinations of outlets of a smoke condensing heat exchanger (1) and a smoke reheater (3) in MySQL, selecting the outlet smoke temperatures of a group of smoke condensing heat exchanger (1) and the smoke reheater (3) with the lowest total life cycle cost as target temperatures under the conditions of given climatic conditions, smoke plume elimination temperature points and equipment operation years, and determining the temperature of the smoke condensing heat exchanger (1) and design parameters of the smoke reheater (3);
s3-3, wherein the initial investment cost comprises:
the prices of the flue gas condensing heat exchanger (1) and the flue gas reheater (3) are 8 x 1.4 x the weight of the heat exchangers; in the formula, the price unit of the flue gas condensing heat exchanger (1) and the flue gas reheater (3) is ten thousand yuan, and the weight unit of the heat exchanger is ton;
the cost of the cooling tower is 250 x the weight of the circulating water; wherein the cost unit of the cooling tower is Yuan, and the weight unit of the circulating water is ton;
s3-4, the operation and maintenance cost comprises:
the power consumption of cooling water is set to be 27.5kW per 100 t;
the power consumption of the induced draft fan is Pa Q/(1000 3600.8), wherein the unit of the power consumption of the induced draft fan is kw, Pa is the full wind pressure of the fan, Q is the wind volume, and the unit is m3/h;
2t of steam heating at 130 ℃ is needed for each MW of wet saturated steam;
and (3) water replenishing of the system: 2 t;
electric charge: 0.5 yuan/kwh; steam: 130 yuan/t, water rate 3 yuan/t;
s4, dynamically regulating the outlet flue gas temperature of the flue gas condensing heat exchanger and the flue gas reheater (3) to a target temperature by the dynamic regulation device according to real-time meteorological conditions, so that the cost of the operation process is the lowest:
s4-1, the flue gas condensation heat exchanger (1) utilizes the condensed water and the cooling tower circulating water to recover high-grade heat energy in the flue gas, and the purpose of dynamically adjusting the outlet temperature of the flue gas condensation heat exchanger (1) is achieved by adjusting the flow rate of the condensed water and the cooling tower circulating water, the power of a variable frequency fan and closing part of the flue gas condensation heat exchanger to change the heat transfer area;
s4-2, the flue gas reheater (3) heats flue gas by using steam extracted by a steam turbine or partial boiler feed water taken out from the outlet of the deaerator (10) to the main feed water pump (11), and the aim of dynamically adjusting the flue gas temperature at the outlet of the flue gas reheater (3) is fulfilled by adjusting the flow and the temperature of the extracted steam or the feed water and closing the partial flue gas reheater to change the heat transfer area.
2. The energy-saving dynamic climate feedback control method for eliminating smoke plume as claimed in claim 1, wherein the normalization processing in step S2-1 is performed according to the following formula:
pn=2*(p-pmin)/(pmax-pmin)-1
in the formula, pn,p,pminAnd pmaxThe normalized sample data, the original sample data, the minimum value of the original sample data and the maximum value of the original sample data are respectively.
3. The energy-saving dynamic climate feedback control method for eliminating smoke plume as claimed in claim 1, wherein the data grouping in step S2-2 comprises:
taking 60% of the normalized M groups of smoke plume elimination data sets as normal training data, 20% of the normalized M groups of smoke plume elimination data sets as variable data, and 20% of the normalized M groups of smoke plume elimination data sets as test data; wherein, variable data is set in the network training to prevent an overfitting state; test data is input in network training to check the prediction capability of the trained network.
4. The energy-saving climate feedback dynamic regulation method for smoke plume elimination according to claim 1, wherein the step S2-3 of finding the optimal BP neural network and initializing comprises:
establishing a four-layer BP neural network which is an input layer, two hidden layers and an output layer respectively, wherein the number of neurons in the input layer is 4, and the number of neurons in the output layer is 1; neuron number of hidden layer is represented by formulaIs determined in which n1The number of hidden layer neurons is all integers in a set range of the number of hidden layer neurons, and the optimal number of hidden layer neurons is searched in a traversal search mode;
initializing all weights and thresholds of the BP neural network by using Gaussian distribution random numbers; all neuron activation functions adopt Sigmoid functions; and respectively setting a training minimum mean square error, a training minimum performance gradient, a maximum training frequency and a training function.
5. The energy-saving dynamic climate feedback control method for eliminating smoke plume as claimed in claim 1, wherein the step S2-4 of predicting the combination of the flue gas condensing heat exchanger (1) and the flue gas reheater (3) outlet smoke temperatures comprises:
according to the step S2-3, an optimal BP neural network is selected, the obtained atmospheric temperature, the atmospheric relative humidity, the wind speed and the outlet smoke temperature of the smoke condensing heat exchanger (1) are normalized under the real-time atmospheric condition and input into the BP neural network, the obtained result is subjected to inverse normalization, the reheating temperature of the smoke reheater (3) can be predicted, and the obtained result and the outlet smoke temperature of the corresponding smoke condensing heat exchanger (1) form a smoke condensing heat exchanger (1) and smoke reheater (3) outlet smoke temperature combination.
6. The energy-saving climate feedback dynamic control method for eliminating smoke plume as claimed in claim 1, wherein: the purpose of the flue gas condensation heat exchanger (1) in the step S4-1 is to condense 45-70 ℃ saturated wet flue gas to 30-48 ℃, and because the temperature difference between the inlet and the outlet of the working medium is small, the latent heat of water vapor in the flue gas is huge, and the flow of the working medium is huge, in order to reduce the flow velocity of the working medium in the flue gas condensation heat exchanger (1) and reduce the flow resistance of the working medium, the flue gas condensation heat exchanger (1) is divided into 2-6 stages which are connected in parallel along the flow direction of the flue gas, and each stage is provided with an independent inlet and outlet water header; the inlet smoke temperature of the first-stage smoke condensing heat exchanger is highest, the working medium is condensed water, high-grade heat energy in the smoke is recovered, and the temperature of the condensed water is raised to be higher than 42 ℃; for the unit without condensed water, the working medium of the first-stage and later flue gas condensation heat exchangers selects circulating water of a cooling tower, and the cooling tower selects a hyperbolic natural draft cooling tower, a mechanical draft cooling tower and a closed air cooling tower.
7. The energy-saving climate feedback dynamic control method for eliminating smoke plume as claimed in claim 1, wherein: in the step S4-2, the flue gas reheater (3) heats the flue gas to 54-85 ℃ by utilizing steam extraction of a steam turbine at 110-400 ℃ or partial boiler feed water at 100-140 ℃ taken out from the outlet of the deaerator (10) to the main feed water pump (11), the drain water generated after steam extraction is used is sent to the deaerator (10), and the boiler feed water is sent to a pipeline in front of the main feed water pump; the demister (2) is arranged at the inlet of the flue gas reheater (3) to remove small liquid drops carried in the flue gas, so that the problems of corrosion and scaling of the flue gas reheater (3) are reduced, and the reheating energy consumption is reduced; the smoke is reheated to reduce the relative humidity of the discharged smoke, so that the steam is prevented from being condensed to form small droplets in the diffusion and cooling process, and the white smoke is eliminated visually.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910376483.8A CN110173710B (en) | 2019-05-07 | 2019-05-07 | Energy-saving type climate feedback dynamic regulation and control device and method for eliminating smoke plume |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910376483.8A CN110173710B (en) | 2019-05-07 | 2019-05-07 | Energy-saving type climate feedback dynamic regulation and control device and method for eliminating smoke plume |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110173710A CN110173710A (en) | 2019-08-27 |
CN110173710B true CN110173710B (en) | 2020-03-31 |
Family
ID=67691242
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910376483.8A Active CN110173710B (en) | 2019-05-07 | 2019-05-07 | Energy-saving type climate feedback dynamic regulation and control device and method for eliminating smoke plume |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110173710B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111871164B (en) * | 2020-06-15 | 2023-03-21 | 浙江工业大学 | Intelligent regulation and control method for low-temperature plasma catalytic degradation of CVOCs |
CN113050728B (en) * | 2021-03-26 | 2022-04-08 | 西安热工研究院有限公司 | Temperature rising system and method for controlling self-starting of deaerator based on data model |
CN113350980A (en) * | 2021-05-27 | 2021-09-07 | 中冶赛迪技术研究中心有限公司 | Energy-saving system for removing white slag of blast furnace and control method |
CN114740713A (en) * | 2021-12-31 | 2022-07-12 | 北京工业大学 | Multi-objective optimization control method for wet flue gas desulfurization process |
CN114742300B (en) * | 2022-04-14 | 2023-05-09 | 西安热工研究院有限公司 | Denitration device boiler flue resistance early warning method and system |
CN118274650A (en) * | 2024-06-03 | 2024-07-02 | 四川德润钢铁集团航达钢铁有限责任公司 | Steel production waste heat recovery optimization method based on heat exchanger |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH1114007A (en) * | 1997-06-26 | 1999-01-22 | Ishikawajima Harima Heavy Ind Co Ltd | Reheat steam temperature controller of boiler |
CN107261699A (en) * | 2017-06-15 | 2017-10-20 | 上海交通大学 | A kind of apparatus and method of the ultra-clean dedusting eliminating white smoke of desulfurization fume |
CN206810050U (en) * | 2017-02-24 | 2017-12-29 | 天津华赛尔传热设备有限公司 | A kind of flue gas of wet desulphurization disappears white system |
CN107930309A (en) * | 2017-12-29 | 2018-04-20 | 福建龙净环保股份有限公司 | A kind of wet plume eliminates system |
CN108126482A (en) * | 2017-12-07 | 2018-06-08 | 天津华赛尔传热设备有限公司 | A kind of heating agent flue gas of tower condensed exterior disappears white system |
CN108413654A (en) * | 2018-04-25 | 2018-08-17 | 双良节能***股份有限公司 | A kind of processing unit of wet desulfurization flue gas |
CN108704463A (en) * | 2018-07-25 | 2018-10-26 | 北京京诚科林环保科技有限公司 | Sintering flue gas desulfurization and denitrification and flue gas whitening comprehensive treatment system and process |
CN109045953A (en) * | 2018-10-16 | 2018-12-21 | 西安交通大学 | A kind of cooling dehumidification by condensation decontamination reheating of flue gas disappears white system and method |
-
2019
- 2019-05-07 CN CN201910376483.8A patent/CN110173710B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH1114007A (en) * | 1997-06-26 | 1999-01-22 | Ishikawajima Harima Heavy Ind Co Ltd | Reheat steam temperature controller of boiler |
CN206810050U (en) * | 2017-02-24 | 2017-12-29 | 天津华赛尔传热设备有限公司 | A kind of flue gas of wet desulphurization disappears white system |
CN107261699A (en) * | 2017-06-15 | 2017-10-20 | 上海交通大学 | A kind of apparatus and method of the ultra-clean dedusting eliminating white smoke of desulfurization fume |
CN108126482A (en) * | 2017-12-07 | 2018-06-08 | 天津华赛尔传热设备有限公司 | A kind of heating agent flue gas of tower condensed exterior disappears white system |
CN107930309A (en) * | 2017-12-29 | 2018-04-20 | 福建龙净环保股份有限公司 | A kind of wet plume eliminates system |
CN108413654A (en) * | 2018-04-25 | 2018-08-17 | 双良节能***股份有限公司 | A kind of processing unit of wet desulfurization flue gas |
CN108704463A (en) * | 2018-07-25 | 2018-10-26 | 北京京诚科林环保科技有限公司 | Sintering flue gas desulfurization and denitrification and flue gas whitening comprehensive treatment system and process |
CN109045953A (en) * | 2018-10-16 | 2018-12-21 | 西安交通大学 | A kind of cooling dehumidification by condensation decontamination reheating of flue gas disappears white system and method |
Also Published As
Publication number | Publication date |
---|---|
CN110173710A (en) | 2019-08-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110173710B (en) | Energy-saving type climate feedback dynamic regulation and control device and method for eliminating smoke plume | |
CN115238597B (en) | Construction method of source network carbon-loaded emission model of park level comprehensive energy system | |
CN108131848B (en) | A kind of DSG slot type photo-thermal power station heat collecting field fluid properties prediction technique | |
CN104534507B (en) | A kind of boiler combustion optimization control method | |
Zarei et al. | Study on parameters effective on the performance of a humidification-dehumidification seawater greenhouse using support vector regression | |
CN109325255B (en) | Optimal vacuum on-line guiding system of wet cooling steam turbine based on fixed power | |
CN104613468B (en) | Circulating fluidized bedboiler combustion optimizing control method based on fuzzy adaptive inference | |
CN111461439A (en) | Urban atmospheric diffusion process-based simulation prediction multi-heat-source heat supply system load scheduling distribution method and system | |
CN103455635A (en) | Thermal process soft sensor modeling method based on least squares and support vector machine ensemble | |
CN109084613B (en) | Air-cooling condenser dust deposition state monitoring and cleaning control system based on convolutional neural network and image recognition and regulation and control method thereof | |
CN109492319A (en) | A kind of power plant boiler flue gas oxygen content flexible measurement method | |
CN105787211A (en) | Pressure adjustment method for combined cycle heat recovery boiler with deteriorated gas turbine | |
CN110207094A (en) | IQGA-SVR boiler heating surface fouling characteristics discrimination method based on principal component analysis | |
CN112016754A (en) | Power station boiler exhaust gas temperature advanced prediction system and method based on neural network | |
CN115510904B (en) | Boiler heating area ash monitoring method based on time sequence prediction | |
CN104700147A (en) | Cooling tower water outlet temperature predicating method | |
CN103150581A (en) | Method and device for optimizing boiler based on least square support vector machine (LSSVM) combustion model | |
CN110728031B (en) | Multi-objective optimization method for balancing complex petrochemical process production energy based on ANN modeling | |
CN112818589A (en) | Heat supply system optimization method based on Bayesian optimization algorithm | |
CN109539291B (en) | Waste heat storage and recovery method for multi-heat-source heat dissipation | |
CN111723331A (en) | Equity distribution calculation method for combined cycle two-in-one unit steam turbine load | |
Wang et al. | A steady-state detection method based on Gaussian discriminant analysis for the on-line gas turbine process | |
CN112632728B (en) | Turbine mechanical blade profile design and performance prediction method based on deep learning | |
CN1763478A (en) | Hot spot detection method for air preheater based on fuzzy kernel function support vector machine | |
CN210004796U (en) | cooling towers capable of carrying out circulating water concentration ratio fitting |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |