CN112989694B - Segmented monitoring system and method for ash on heating surface - Google Patents
Segmented monitoring system and method for ash on heating surface Download PDFInfo
- Publication number
- CN112989694B CN112989694B CN202110251554.9A CN202110251554A CN112989694B CN 112989694 B CN112989694 B CN 112989694B CN 202110251554 A CN202110251554 A CN 202110251554A CN 112989694 B CN112989694 B CN 112989694B
- Authority
- CN
- China
- Prior art keywords
- parameters
- flue gas
- working medium
- heating surface
- soot
- 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
- 238000010438 heat treatment Methods 0.000 title claims abstract description 95
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012544 monitoring process Methods 0.000 title claims abstract description 41
- 239000004071 soot Substances 0.000 claims abstract description 73
- 238000004364 calculation method Methods 0.000 claims abstract description 66
- 238000004088 simulation Methods 0.000 claims abstract description 42
- 238000012549 training Methods 0.000 claims abstract description 25
- 238000007664 blowing Methods 0.000 claims abstract description 9
- 239000003546 flue gas Substances 0.000 claims description 96
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 93
- 230000008021 deposition Effects 0.000 claims description 84
- 238000012546 transfer Methods 0.000 claims description 60
- 239000003245 coal Substances 0.000 claims description 40
- 239000000428 dust Substances 0.000 claims description 38
- 238000004140 cleaning Methods 0.000 claims description 33
- 230000000704 physical effect Effects 0.000 claims description 21
- 238000002485 combustion reaction Methods 0.000 claims description 17
- 239000000779 smoke Substances 0.000 claims description 17
- 238000013528 artificial neural network Methods 0.000 claims description 16
- 238000005259 measurement Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 6
- 238000010521 absorption reaction Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 4
- 239000012530 fluid Substances 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000013178 mathematical model Methods 0.000 abstract description 3
- 230000007246 mechanism Effects 0.000 abstract description 3
- 238000011160 research Methods 0.000 abstract description 3
- 239000007789 gas Substances 0.000 description 4
- 239000002184 metal Substances 0.000 description 3
- 229910052751 metal Inorganic materials 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004380 ashing Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 210000002307 prostate Anatomy 0.000 description 1
- 239000010865 sewage Substances 0.000 description 1
- 239000002893 slag Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000004861 thermometry Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Computer Hardware Design (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Algebra (AREA)
- Fluid Mechanics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Waste-Gas Treatment And Other Accessory Devices For Furnaces (AREA)
Abstract
The invention discloses a segmented monitoring system and method for ash on a heating surface, and belongs to the technical field of boiler safety monitoring. The invention combines three methods of a mechanism model, a mathematical model and a numerical simulation, corrects a numerical simulation result by utilizing measured data, establishes a segmented model of the heated surface, realizes the refined calculation of the soot state of the heated surface, realizes the real-time monitoring of the soot state of the heated surface by means of an LSTM time series network training method, and has theoretical guiding significance for the subsequent soot blowing research.
Description
Technical Field
The invention belongs to the technical field of boiler safety monitoring, and particularly relates to a segmented monitoring system and method for ash and dirt on a heating surface.
Background
In recent years, the rapid development of the electric power industry in China, high parameterization and large capacity are development directions and trends of coal-fired units of power plants. Along with the increase of the boiler capacity, the parameters of the flue gas are also obviously improved, and the problems of ash deposition and slag bonding on the heating surface are increasingly highlighted. The ash on the heating surface can seriously affect the heat transfer process from the smoke side to the working medium side, so that the smoke exhaust temperature of the boiler is increased, the efficiency of the boiler is greatly reduced, and meanwhile, high-speed ash particles in the smoke can also cause the metal on the heating surface to be worn, the service life of the metal is reduced, steam temperature deviation is caused, and a series of challenges are brought to the safe, efficient and economic operation of a unit. Therefore, the system and the method for monitoring the soot on the heating surface have good popularization prospect and have important significance for improving the safety, the economy and the efficiency of the operation of the power plant unit.
Through the detection discovery of the prior art, the prior art aiming at the monitoring of the dirt on the heating surface is as follows: (1) based on heat flow meter measurements. Taking chinese patent CN201910584787.3 as an example, the temperature signals are collected by a heat flow meter arranged on the heated surface, the heat flow density is calculated, and the calculated heat flow density is compared with the heat flow density early warning value under the same load to judge the pollution degree of the heated surface. However, the sensor arranged on the heating surface is volatile due to being in a high-temperature severe environment, and the heat flow meter is expensive in manufacturing cost, difficult to maintain and insufficient in reliability; (2) based on acoustic/optical thermometry. Taking the chinese patent CN102588943A as an example, based on the principle that the propagation speed of sound in gas varies with temperature and gas composition, the average temperature on one line of the furnace outlet is measured, and indirect diagnosis is performed according to the variation of the smoke temperature at the furnace outlet. However, the method has insufficient universality, errors can occur in fuel change or gas component change, the accuracy of measured data is insufficient, and a required system is huge; (3) monitoring is carried out based on the dust index (cleaning factor, dust deposition thickness, dust thermal resistance and heat transfer effectiveness ratio). Taking CN110578933A as an example, the degree of deposition is determined according to the index of the cleaning factor CF (the ratio of the deposition thickness to the critical deposition thickness calculated online). However, the measurement and calculation result of the method is not accurate enough, and the dust deposition degree and the dust deposition position cannot be accurately fed back on line; (4) the model is fitted based on machine learned data. Taking the chinese patent CN111242279A as an example, according to historical operation data such as inlet smoke temperature, smoke velocity, steam temperature, etc., data fitting such as metal pipe wall temperature neural network training is performed. The method has the defects that only limited measuring point temperatures can be fitted, the data fitting precision is not high, and the real-time performance cannot be realized.
Disclosure of Invention
In order to solve the problems, the invention provides a heating surface ash and dirt segmentation monitoring system and a method, which combine three methods of a mechanism model, a mathematical model and numerical simulation, correct a numerical simulation result by using measured data, establish a heating surface segmentation model, realize the refined calculation of the heating surface ash and dirt state, realize the real-time monitoring of the heating surface ash and dirt state by means of an LSTM time sequence network training method, and have theoretical guiding significance for the subsequent soot blowing research.
The technical scheme of the invention is as follows:
in a first aspect, the invention provides a heating surface soot and dirt segmental monitoring system, which comprises a data acquisition module, a database, a real-time calculation module and a monitoring module;
the data acquisition module is used for reading real-time data from a set DCS server and a sensor arranged in the boiler;
the database is used for storing all boiler related data including the real-time data acquired by the data acquisition module;
the real-time calculation module is used for acquiring relevant data from the database and substituting the relevant data into a pre-constructed model for calculation to obtain cleaning factors CF representing the degree of dirt and dust of different sections of the heating surface; the pre-constructed model comprises a multi-working-condition CFD furnace tank simulation prediction model and a regional ash-removing fine calculation model;
the monitoring module is used for substituting cleaning factors CF of different sections of the heating surface into the LSTM time sequence soot deposition state prediction model to obtain a soot deposition state parameter prediction result for guiding soot blowing subsequently.
In a second aspect, the present invention provides a method for monitoring segmentation of soot on a heated surface using the monitoring system according to the first aspect, comprising the steps of:
s1: the data acquisition module reads real-time data from a unit DCS server and a sensor arranged in the boiler, and the real-time data comprises actual measurement parameters of the flue gas at the outlet of the hearth and working medium inlet parameters;
s2: the data acquisition module inputs acquired real-time data into a database for storage, and the boiler related data stored in the database comprise heating surface structure parameters, coal quality parameters, combustion modes, working medium physical property parameters, air supply quantity, coal supply quantity, working medium inlet parameters, hearth outlet flue gas actual measurement parameters and ash deposition parameter historical data sequences containing time information;
s3: the real-time calculation module acquires relevant data from the database and substitutes the relevant data into a multi-working-condition CFD furnace simulation prediction model and a regional ash-stain fine calculation model which are constructed in advance to calculate to obtain cleaning factors CF of different regions of the heating surface representing the ash-stain degree;
the multi-working-condition CFD hearth simulation prediction model is a BP neural network, the parameters of an input layer are heating surface structure parameters, coal quality parameters, a combustion mode, working medium physical property parameters, air supply quantity, coal supply quantity and working medium inlet parameters, and the parameters of an output layer are flue gas outlet temperatures;
the segmented soot fine calculation model is based on a heated surface segmented model formed by respectively carrying out segmented division on flue gas and working media serving as objects, flue gas outlet temperature output by the multi-working-condition CFD hearth simulation prediction model and working medium inlet parameters in a database are utilized, flue gas side and working medium side parameters of different heated surfaces are obtained through heat balance calculation, then fine calculation is carried out on different segments of different heated surfaces, theoretical heat transfer coefficients and actual heat transfer coefficients of different segments of the heated surfaces are obtained, and further conversion is carried out to be a cleaning factor CF;
s4: the monitoring module substitutes the cleaning factors CF of different sections of the heating surface into a pre-constructed LSTM time sequence soot deposition state prediction model by using as input variables, and outputs prediction results of the soot deposition thickness, the soot deposition area and the soot deposition position representing the soot deposition state for subsequent guidance of soot blowing.
Preferably, the construction method of the multi-working-condition CFD furnace simulation prediction model comprises the following steps:
s11: acquiring heating surface structure parameters, coal quality parameters, combustion modes, working medium physical properties parameters, air supply quantity, coal supply quantity, working medium inlet parameters and actual measurement parameters of furnace outlet flue gas under different working conditions from a database;
s12: based on the heating surface structure parameters, the coal quality parameters, the combustion mode, the working medium physical property parameters, the air supply quantity and the coal supply quantity data obtained in the S11, carrying out multi-working-condition hearth modeling simulation by utilizing computational fluid dynamics software to obtain the temperature field and the velocity field distribution of the flue gas at the outlet of the hearth;
s13: correcting the simulation model by using the actual measurement parameters of the flue gas at the outlet of the hearth in the database;
s14: generating simulation data by using the corrected simulation model, and performing BP neural network learning training by combining with the working medium inlet parameters obtained in S11, wherein the input layer parameters of the BP neural network comprise heating surface structure parameters, coal quality parameters, combustion mode, working medium physical property parameters, air supply quantity, coal supply quantity and working medium inlet parameters, and the output layer is flue gas outlet temperature; and taking the trained BP neural network as a flue gas outlet parameter prediction model.
Preferably, the method for constructing the segmental ashing sewage fine calculation model comprises the following steps:
s21: acquiring the temperature of a flue gas outlet obtained in the multi-working-condition CFD furnace chamber simulation prediction model and the parameters of a working medium inlet obtained in a database;
s22: according to the data obtained in the S21, parameters of the flue gas side and the working medium side of different heating surfaces are obtained through heat balance calculation;
s23: respectively carrying out section division on each heating surface by taking smoke and working media as objects, establishing a section model of the heating surface, and carrying out refined calculation on different sections of different heating surfaces according to parameters of a smoke side and a working media side obtained in S22 to obtain theoretical heat transfer coefficients and actual heat transfer coefficients of different sections;
s24: the cleaning factor CF was calculated for different sections of the heated surface.
Further, in the heated surface segmentation model in S23, with the flue gas as an object, the heated surface is divided into X, Y, Z different regions along the flue gas flow direction, the furnace width direction, and the furnace height direction, respectively; meanwhile, with the working medium as an object, dividing the heating surface into U, V, W different pipe sections along the overall flow direction of the working medium, the width direction of the hearth and the flow direction of the working medium in the pipe; the coordinates of the divided flue gas area are expressed as (x, y, z), and the coordinates of the divided pipe section are expressed as (u, v, w).
Further, the refinement calculation method in S23 is as follows:
s231: calculating the mass flow q of each pipeline forming the heating surface according to a hydrodynamic calculation methodm(u,v)；
S232: assuming that the heat transfer capacity of each tube section is Qf(u, v, w) calculating corresponding radiant heat transfer amounts respectively
And convective heat transfer capacity
The control equation in the calculation process is as follows:
Qf＝∑Qf(u,v,w)
Qf＝Qg
Qg＝∑Qg(x,y,z)＝∑[h'(x,y,z)-h*(x,y,z)]
C*(x-1,y,z)＝C'(x,y,z)
C*(u,v,w-1)＝C'(u,v,w)
qm＝∑qm(u,v)
wherein Q isfRepresenting the total heat absorption, Q, of the working medium on the heating surfacegRepresents the total heat release, Q, of the heating surface flue gasg(x, y, z) represents the heat release of the smoke region (x, y, z); h' (x, y, z) represents the inlet enthalpy of a zone of flue gas, h*(x, y, z) represents the outlet enthalpy of a zone of flue gas, C*(x-1, y, z) denotes the outlet characteristic of the flue gas region (x-1, y, z), C' (x, y, z) denotes the inlet characteristic of the flue gas region (x, y, z), C*(u, v, w-1) represents an outlet characteristic variable of the working medium pipe section (u, v, w-1), C' (u, v, w) represents an inlet characteristic variable of the working medium pipe section (u, v, w), qmWorking medium flow of all lines, qm(u, v) represents the working medium flow of the pipeline (u, v);
s233: calculating the total heat transfer quantity Q 'of each pipe section after S232'f(u, v, w), which is calculated as follows:
s234: after S233, judging whether the current error meets the precision requirement epsilon, wherein the calculation formula is as follows:
if the current error meets the precision requirement, the iterative calculation is completed, and the parameters of the flue gas side and the working medium side of each pipe section, namely the radiant heat transfer quantity of the flue gas side and the working medium side of each pipe section are obtained
And convective heat transfer capacity
Otherwise, resetting the assumed value of the heat transfer quantity of each pipe section and returning to S232;
s235: after the parameters of the flue gas side and the working medium side of each pipe section are obtained after the iteration is finished, the theoretical heat transfer coefficient k of each pipe section is calculatedtCoefficient of heat transfer k to the actualrThe calculation formula is as follows:
wherein,
representing the convective heat transfer of the pipe section to be calculated, BjIndicating standard coal consumption, A indicating heat transfer area, delta t indicating temperature and pressure, delta tmaxIndicating the end of a large temperature differenceTemperature difference of medium, Δ tminThe temperature difference of the medium, k, at the end of smaller temperature differencegDenotes the side heat transfer coefficient of the flue gas, kfExpressing the heat transfer coefficient of the working medium side, C expressing the empirical coefficient, lambda expressing the heat transfer coefficient of the flue gas at the average flue gas temperature, d expressing the outer diameter of the pipe, Re expressing the Reynolds number, Pr expressing the Prandtl number, ClDenotes the influence of the change in physical properties on the exotherm coefficient, CzCorrection factor representing the number of rows of tubes along the flue gas path, CsRepresents a pitch correction coefficient, abThe blackness of the tube wall of the radiant heating surface is shown, a is the blackness of the flue gas at the temperature T, TbThe absolute temperature of the heated surface is shown, and the indices m, n, and l are constants.
Further, the formula for calculating the cleaning factor CF in S24 is as follows:
preferably, the method for constructing the LSTM time series accumulated dust state prediction model comprises the following steps:
s41: acquiring a historical data sequence of the dust deposition parameters containing time information from a database, wherein each piece of data in the sequence comprises a cleaning factor, a dust deposition thickness, a dust deposition area and a dust deposition position corresponding to one moment;
s42: carrying out sample division on the obtained data sequence, and dividing the data sequence into a training sample and a test sample;
s43: carrying out initial training on an LSTM time sequence network by using a training sample to obtain an initial prediction model of a dust deposition state, wherein input variables of the model are cleaning factors, and output variables are dust deposition thickness, dust deposition area and dust deposition position representing the dust deposition state respectively;
s44: optimizing the hyper-parameters in the initial prediction model to obtain an optimized LSTM ash deposition state prediction model;
s45: verifying the trained LSTM soot deposition state prediction model by using a test sample, completing construction of the LSTM time sequence soot deposition state prediction model when an error meets a requirement, and continuing to return to model training if the error does not meet the requirement;
s46: the LSTM time-series soot deposition state prediction model constructed in S45 is used to predict the soot deposition state.
The invention has the beneficial effects that:
1. the method of combining numerical simulation and a neural network is adopted, and the model is corrected by using the actually measured data, so that the calculation accuracy is improved;
2. the heating surface is divided in sections, so that three-dimensional fine calculation of cleaning factors is realized, the dirt states of different positions can be monitored, and the accuracy and reliability of results are improved;
3. by adopting a big data fitting method, the nonlinear relation between the cleaning factor and the parameter representing the soot deposition state is revealed, the deep grasp of the soot deposition state information such as the thickness, the area and the position of the soot deposition is improved, and the monitoring effect and the monitoring efficiency are improved;
4. and processing the data by using an LSTM time sequence network to realize accurate online real-time feedback of the dust accumulation information.
Drawings
FIG. 1 is a sectional monitoring system and method for soot contamination on a heating surface according to the present invention.
FIG. 2 is a segmented model of the heated surface region of the present invention.
Detailed Description
The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
In a preferred embodiment of the present invention, as shown in fig. 1, a segmented monitoring system for soot on a heated surface is provided, whose main functional modules include a data acquisition module, a database, a real-time calculation module and a monitoring module. The specific functions of each module are as follows:
the data acquisition module is used for reading real-time data related to the state of the boiler from the DCS server of the unit and a sensor arranged in the boiler, and mainly comprises the current flue gas speed and temperature of a hearth outlet, working medium inlet parameters (namely working medium temperature, working medium pressure and working medium flow) and the like.
The database is used for storing all the relevant boiler data including the real-time data acquired by the data acquisition module. Besides the current real-time data, the database also stores other data and historical data related to heating surface soot deposition, including heating surface structure parameters, coal quality parameters (i.e. physicochemical property parameters of fire coal, such as coal type and particle size), combustion mode, working medium physical property parameters (i.e. physical property parameters of working medium, such as specific heat capacity and density), air supply quantity, coal supply quantity, working medium inlet parameters (working medium temperature, working medium pressure and working medium flow), actual measurement parameters of furnace outlet flue gas (i.e. real-time temperature, speed and pressure of the flue gas at the furnace outlet) and a soot deposition parameter historical data sequence containing time information. The ash deposition parameter historical data sequence is a section of time sequence data, each piece of data contains timestamp information for recording the data, and represents cleaning factors, ash deposition thickness, ash deposition area and ash deposition positions of the heating surface at different moments.
And the real-time calculation module is used for acquiring related data from the database and substituting the related data into a pre-constructed model for calculation to obtain cleaning factors CF representing the degree of dirt and dust in different sections of the heating surface. The pre-constructed model comprises a multi-working-condition CFD hearth simulation prediction model and a regional ash-removing fine calculation model, wherein the multi-working-condition CFD hearth simulation prediction model calculates the temperature of a flue gas outlet in a hearth according to structural parameters of a heating surface, coal quality parameters, a combustion mode, working medium physical property parameters, air supply quantity, coal supply quantity and working medium inlet parameters so as to simulate temperature field distribution; and then, a sectional chemical fouling fine calculation model is used for finely calculating theoretical heat transfer coefficients and actual heat transfer coefficients of different sections of a heating surface in the hearth according to the flue gas outlet temperature obtained in the multi-working-condition CFD hearth simulation prediction model and the working medium inlet parameters obtained in the database, so that the cleaning factors CF of the different sections of the heating surface are obtained.
The monitoring module is used for substituting cleaning factors CF of different sections of the heating surface into a pre-constructed LSTM time sequence soot deposition state prediction model to obtain a soot deposition state parameter prediction result of the heating surface for guiding soot blowing subsequently.
The method for monitoring segmentation of soot on a heating surface in the present invention is described in detail below with further reference to the monitoring system shown in fig. 1, and comprises the following steps:
s1: the data acquisition module reads real-time data from a unit DCS server and a sensor arranged in the boiler, wherein the real-time data comprises actual measurement parameters of flue gas at a hearth outlet, working medium inlet parameters and the like;
s2: the data acquisition module inputs acquired real-time data into a database for storage, and the boiler related data stored in the database comprise heating surface structure parameters, coal quality parameters (coal types and particle sizes), combustion modes, working medium physical property parameters (specific heat capacity and density), air supply quantity, coal supply quantity, working medium inlet parameters, actual measurement parameters (temperature, speed and pressure) of flue gas at a hearth outlet and ash deposition parameter historical data sequences containing time information;
s3: the real-time calculation module obtains related data from the database and substitutes the related data into a pre-constructed multi-working-condition CFD (computational Fluid dynamics) hearth simulation prediction model and a regional sooting fine calculation model for calculation to obtain cleaning factors CF of different regions of the heating surface representing the sooting degree.
The multi-working-condition CFD hearth simulation prediction model is a BP neural network, the parameters of an input layer are heating surface structure parameters, coal quality parameters, a combustion mode, working medium physical property parameters, air supply quantity, coal supply quantity and working medium inlet parameters, and the parameters of an output layer are flue gas outlet temperatures.
The method comprises the steps of firstly, obtaining a section-to-section ash fine calculation model based on a heated surface section model formed by section division with flue gas and working media as objects, obtaining flue gas side and working medium side parameters of different heated surfaces through heat balance calculation by utilizing flue gas outlet temperature output by the multi-working-condition CFD furnace simulation prediction model and working medium inlet parameters in a database, then carrying out fine calculation aiming at different sections of different heated surfaces to obtain theoretical heat transfer coefficients and actual heat transfer coefficients of different sections of the heated surfaces, and converting the theoretical heat transfer coefficients and the actual heat transfer coefficients into a cleaning factor CF.
The multi-working-condition CFD furnace simulation prediction model and the section ashing pollution fine calculation model are required to be constructed in advance before the system is put into practical use and are built in the system. The following describes the specific construction process of the two models in detail:
1) the construction method of the multi-working-condition CFD furnace simulation prediction model comprises the following steps:
s11: and acquiring heating surface structure parameters, coal quality parameters, combustion modes, working medium physical properties parameters, air supply quantity, coal supply quantity, working medium inlet parameters and actual measurement parameters of furnace outlet flue gas under different working conditions from a database.
S12: based on the heating surface structure parameters, the coal quality parameters, the combustion mode, the working medium physical property parameters, the air supply quantity and the coal supply quantity data obtained in the S11, multi-working-condition hearth modeling simulation is carried out by utilizing Computational Fluid Dynamics (CFD) software to obtain the distribution of a hearth outlet flue gas temperature field and a velocity field, so that the prediction of the flue gas temperature at different positions of the hearth outlet is further realized, and a foundation is laid for providing sufficient data samples for the subsequent neural network training.
S13: and correcting the simulation model by using the actual measurement parameters of the flue gas at the outlet of the hearth in the database, so that the simulation model can simulate the real situation in the hearth to the maximum extent.
S14: and generating a large amount of simulation data by using the corrected simulation model, combining the working medium inlet parameters obtained in the step S11, using the simulation data as training sample data sets, and performing BP neural network learning training based on the training sample data sets. The specific structure of the BP neural network belongs to the prior art and is not described in detail. The parameters of an input layer of the BP neural network comprise heating surface structure parameters, coal quality parameters, a combustion mode, working medium physical property parameters, air supply quantity, coal supply quantity and working medium inlet parameters, and an output layer is flue gas outlet temperature; and taking the trained BP neural network as a flue gas outlet parameter prediction model.
2) The construction method of the segmental fine ash calculation model comprises the following steps:
s21: and acquiring the flue gas outlet temperature obtained in the multi-working-condition CFD furnace chamber simulation prediction model and the working medium inlet parameters (working medium temperature, working medium pressure and working medium flow) obtained in the database.
S22: according to the data obtained in S21, parameters of the flue gas side and the working medium side (namely the inlet temperature and the outlet temperature of the gas side and the working medium side) of different heating surfaces are obtained through heat balance calculation.
The specific process of the heat balance calculation can be performed by using the prior art, and in the embodiment, the specific calculation process is as follows:
the total heat absorption Q of the working medium of the final heating surface can be calculated according to the known parameters of the working medium side of the final heating surfaceFAccording to the fact that the total heat absorption capacity of the working medium is equal to the total heat release capacity Q of the smokeGAnd calculating to obtain the inlet enthalpy value of the flue gas of the final heating surface, and looking up a table to obtain the inlet temperature of the flue gas.
QFAnd QGThe specific calculation formula used can be seen as follows:
QF＝QG
wherein q ismExpressing the flow of the working medium on the heating surface, i 'expressing the outlet enthalpy of the working medium, i' expressing the inlet enthalpy of the working medium, BjRepresents the calculated fuel quantity, phi represents the heat preservation coefficient, I 'represents the enthalpy value of the flue gas outlet, I' represents the enthalpy value of the flue gas inlet, and delta alpha represents the air leakage coefficient,
representing the cold air enthalpy.
And repeating the steps to obtain the inlet and outlet temperature parameters of the flue gas side and the working medium side of each heating surface.
S23: and (4) respectively carrying out section division on each heating surface by taking the smoke and the working medium as objects, establishing a section model of the heating surface, and carrying out refined calculation on different sections of different heating surfaces according to the parameters of the smoke side and the working medium side obtained in S22 to obtain theoretical heat transfer coefficients and actual heat transfer coefficients of different sections.
In the present embodiment, as shown in fig. 2, in the established heated surface area segmentation model, the segmentation division is performed in two aspects. On one hand, the heating surface is divided into X, Y, Z different areas along the flue gas flowing direction, the furnace width direction and the furnace height direction by taking the flue gas as an object. On the other hand, the heating surface is divided into U, V, W different pipe sections along the overall flowing direction of the working medium, the width direction of the hearth and the flowing direction of the working medium in the pipe by taking the working medium as an object. The divided smoke region coordinates are represented as (x, y, z) and the divided pipe segment coordinates are represented as (u, v, w) for the first three dimensions of X, Y, Z and U, V, W, respectively.
In this embodiment, based on the heated surface segmentation model, a method for performing refined calculation specifically for different segments of different heated surfaces is as follows:
s231: calculating the mass flow q of each pipeline forming the heating surface according to a hydrodynamic calculation methodm(u, v). Here, since the mass flow of each pipe section on the same pipeline is constant, the W dimension does not need to be introduced, and only two dimensions of U, V are needed to represent qmThe corresponding index number.
S232: assuming that the heat transfer capacity of each tube section is Qf(u, v, w) calculating corresponding radiant heat transfer amounts respectively
And convective heat transfer capacity
The control equation in the calculation process is as follows:
Qf＝ΣQf(u,v,w)
Qf＝Qg
Qg＝∑Qg(x,y,z)＝∑[h'(x,y,z)-h*(x,y,z)]
C*(x-1,y,z)＝C'(x,y,z)
C*(u,v,w-1)＝C'(u,v,w)
qm＝∑qm(u,v)
wherein Q isfIndicates the heat receivedTotal heat absorption of surface working medium, QgRepresents the total heat release, Q, of the heating surface flue gasg(x, y, z) represents the heat release of the smoke region (x, y, z); h' (x, y, z) represents the inlet enthalpy of a zone of flue gas, h*(x, y, z) represents the outlet enthalpy of a zone of flue gas, C*(x-1, y, z) denotes the outlet characteristic of the flue gas region (x-1, y, z), C' (x, y, z) denotes the inlet characteristic of the flue gas region (x, y, z), C*(u, v, w-1) represents an outlet characteristic variable of the working medium pipe section (u, v, w-1), C' (u, v, w) represents an inlet characteristic variable of the working medium pipe section (u, v, w), qmWorking medium flow of all lines, qm(u, v) represents the working medium flow of the pipeline (u, v);
s233: calculating the total heat transfer quantity Q 'of each pipe section after S232'f(u, v, w), which is calculated as follows:
s234: after S233, judging whether the current error meets the precision requirement epsilon, wherein the calculation formula is as follows:
if the current error meets the precision requirement, the iterative calculation is completed, and the parameters of the flue gas side and the working medium side of each pipe section, namely the radiant heat transfer quantity of the flue gas side and the working medium side of each pipe section are obtained
And convective heat transfer capacity
Otherwise, resetting the assumed value of the heat transfer quantity of each pipe section and returning to S232;
s235: after the parameters of the flue gas side and the working medium side of each pipe section are obtained after the iteration is finished, the theoretical heat transfer coefficient k of each pipe section is calculatedtCoefficient of heat transfer k to the actualrThe calculation formula is as follows:
wherein,
representing the convective heat transfer capacity of the pipe section to be calculated (i.e. corresponding to the convective heat transfer capacity described above)
The convection heat transfer quantity of which pipe section is adopted is calculated specifically
BjIndicating standard coal consumption, A indicating heat transfer area, delta t indicating temperature and pressure, delta tmaxThe temperature difference of the medium at the end with larger temperature difference, delta tminThe temperature difference of the medium, k, at the end of smaller temperature differencegDenotes the side heat transfer coefficient of the flue gas, kfExpressing the heat transfer coefficient of the working medium side, C expressing the empirical coefficient, lambda expressing the heat transfer coefficient of the flue gas at the average flue gas temperature, d expressing the outer diameter of the pipe, Re expressing the Reynolds number, Pr expressing the Prandtl number, ClDenotes the influence of the change in physical properties on the exotherm coefficient, CzCorrection factor representing the number of rows of tubes along the flue gas path, CsRepresents a pitch correction coefficient, abThe blackness of the tube wall of the radiant heating surface is shown, a is the blackness of the flue gas at the temperature T, TbThe absolute temperature of the heated surface is shown, and the indices m, n, and l are constants.
S24: the cleaning factor CF was calculated for different sections of the heated surface.
In this embodiment, according to the definition of the cleaning factor CF, the calculation formula is:
s4: the monitoring module substitutes the cleaning factors CF of different sections of the heating surface into a pre-constructed LSTM time sequence soot deposition state prediction model by using as input variables, and outputs prediction results of the soot deposition thickness, the soot deposition area and the soot deposition position representing the soot deposition state for subsequent guidance of soot blowing.
Similarly, before the monitoring system of the invention is put into practical use, the LSTM time series soot deposition state prediction model needs to be constructed and trained in advance and then is built in the system. In this embodiment, the method for constructing the LSTM time series accumulated dust state prediction model includes the following steps:
s41: and acquiring a historical data sequence of the dust deposition parameters containing time information from a database, wherein each piece of data in the sequence comprises a cleaning factor, a dust deposition thickness, a dust deposition area and a dust deposition position corresponding to one moment.
S42: and carrying out sample division on the acquired data sequence, and dividing the data sequence into a training sample and a test sample. When the training samples and the test samples are divided, the specific proportion can be adjusted according to actual needs, in the embodiment, 80% of the training samples and 20% of the test samples are divided, and the original data are normalized. The normalization processing formula is as follows:
wherein x isijIndicates normalized position at [ i, j]Element of (1), pijIndicates the position before normalization at [ i, j]The elements of (a) and (b),
represents the smallest element in the normalized front row,
representing the largest element in the normalized prostate.
S43: and carrying out initial training on the LSTM time sequence network by using the training sample to obtain an initial prediction model of the dust deposition state, wherein input variables of the model are cleaning factors, and output variables are the dust deposition thickness, the dust deposition area and the dust deposition position representing the dust deposition state respectively.
S44: and optimizing the hyper-parameters in the initial prediction model to obtain an optimized LSTM soot deposition state prediction model.
S45: and (3) verifying the trained LSTM soot state prediction model by using a test sample, completing construction of the LSTM time sequence soot state prediction model when the error meets the requirement, and continuing to return to model training if the error does not meet the requirement.
S46: the LSTM time-series soot deposition state prediction model constructed in S45 is used to predict the soot deposition state.
The LSTM network is very suitable for processing the problem highly related to the time series, can fully excavate the existing soot deposition information before the current prediction time in the hearth, and is used for accurately predicting the future soot deposition state on line in real time. The specific model structure and training process of LSTM belongs to the prior art, and parameters in the model can be optimized by minimizing a loss function.
Therefore, the method combines three methods of a mechanism model, a mathematical model and numerical simulation, corrects the numerical simulation result by utilizing the measured data, establishes a segmented model of the heated surface, realizes the fine calculation of the soot state of the heated surface, and realizes the real-time monitoring of the soot state of the heated surface by means of the time series network training method of the LSTM. In the practical application process, the method can accurately realize the segmental monitoring of soot on the heating surface, and the monitoring result is consistent with the reality, so that the method has higher guiding significance for the subsequent soot blowing research. In addition, in the actual use process, the prediction result of the LSTM can be used for enriching the historical data sequence, and the prediction accuracy of the whole model is further improved.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the present invention in its spirit and scope. Are intended to be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (6)
1. A heating surface soot and dirt segmental monitoring method utilizing a heating surface soot and dirt segmental monitoring system is characterized in that the heating surface soot and dirt segmental monitoring system comprises a data acquisition module, a database, a real-time calculation module and a monitoring module; the data acquisition module is used for reading real-time data from a set DCS server and a sensor arranged in the boiler; the database is used for storing all boiler related data including the real-time data acquired by the data acquisition module; the real-time calculation module is used for acquiring relevant data from the database and substituting the relevant data into a pre-constructed model for calculation to obtain cleaning factors CF representing the degree of dirt and dust of different sections of the heating surface; the pre-constructed model comprises a multi-working-condition CFD furnace tank simulation prediction model and a regional ash-removing fine calculation model; the monitoring module is used for substituting cleaning factors CF of different sections of the heating surface into a pre-constructed LSTM time sequence soot deposition state prediction model to obtain a soot deposition state parameter prediction result of the heating surface for guiding soot blowing subsequently;
the method for monitoring the segmentation of the soot on the heating surface comprises the following steps:
s1: the data acquisition module reads real-time data from a unit DCS server and a sensor arranged in the boiler, and the real-time data comprises actual measurement parameters of the flue gas at the outlet of the hearth and working medium inlet parameters;
s2: the data acquisition module inputs acquired real-time data into a database for storage, and the boiler related data stored in the database comprise heating surface structure parameters, coal quality parameters, combustion modes, working medium physical property parameters, air supply quantity, coal supply quantity, working medium inlet parameters, hearth outlet flue gas actual measurement parameters and ash deposition parameter historical data sequences containing time information;
s3: the real-time calculation module acquires relevant data from the database and substitutes the relevant data into a multi-working-condition CFD furnace simulation prediction model and a regional ash-stain fine calculation model which are constructed in advance to calculate to obtain cleaning factors CF of different regions of the heating surface representing the ash-stain degree;
the multi-working-condition CFD hearth simulation prediction model is a BP neural network, the parameters of an input layer are heating surface structure parameters, coal quality parameters, a combustion mode, working medium physical property parameters, air supply quantity, coal supply quantity and working medium inlet parameters, and the parameters of an output layer are flue gas outlet temperatures;
the segmented soot fine calculation model is based on a heated surface segmented model formed by respectively carrying out segmented division on flue gas and working media serving as objects, flue gas outlet temperature output by the multi-working-condition CFD hearth simulation prediction model and working medium inlet parameters in a database are utilized, flue gas side and working medium side parameters of different heated surfaces are obtained through heat balance calculation, then fine calculation is carried out on different segments of different heated surfaces, theoretical heat transfer coefficients and actual heat transfer coefficients of different segments of the heated surfaces are obtained, and further conversion is carried out to be a cleaning factor CF;
s4: the monitoring module substitutes cleaning factors CF of different sections of the heating surface into a pre-constructed LSTM time sequence soot deposition state prediction model by using as input variables, and outputs prediction results of soot deposition thickness, soot deposition area and soot deposition position representing the soot deposition state for subsequent guidance of soot blowing;
the construction method of the multi-working-condition CFD furnace simulation prediction model comprises the following steps:
s11: acquiring heating surface structure parameters, coal quality parameters, combustion modes, working medium physical properties parameters, air supply quantity, coal supply quantity, working medium inlet parameters and actual measurement parameters of furnace outlet flue gas under different working conditions from a database;
s12: based on the heating surface structure parameters, the coal quality parameters, the combustion mode, the working medium physical property parameters, the air supply quantity and the coal supply quantity data obtained in the S11, carrying out multi-working-condition hearth modeling simulation by utilizing computational fluid dynamics software to obtain the temperature field and the velocity field distribution of the flue gas at the outlet of the hearth;
s13: correcting the simulation model by using the actual measurement parameters of the flue gas at the outlet of the hearth in the database;
s14: generating simulation data by using the corrected simulation model, and performing BP neural network learning training by combining with the working medium inlet parameters obtained in S11, wherein the input layer parameters of the BP neural network comprise heating surface structure parameters, coal quality parameters, combustion mode, working medium physical property parameters, air supply quantity, coal supply quantity and working medium inlet parameters, and the output layer is flue gas outlet temperature; and taking the trained BP neural network as a flue gas outlet parameter prediction model.
2. The method for monitoring segmentation of soot on heating surface according to claim 1, wherein the method for constructing the fine calculation model of segmentation of soot comprises the following steps:
s21: acquiring the temperature of a flue gas outlet obtained in the multi-working-condition CFD furnace chamber simulation prediction model and the parameters of a working medium inlet obtained in a database;
s22: according to the data obtained in the S21, parameters of the flue gas side and the working medium side of different heating surfaces are obtained through heat balance calculation;
s23: respectively carrying out section division on each heating surface by taking smoke and working media as objects, establishing a section model of the heating surface, and carrying out refined calculation on different sections of different heating surfaces according to parameters of a smoke side and a working media side obtained in S22 to obtain theoretical heat transfer coefficients and actual heat transfer coefficients of different sections;
s24: the cleaning factor CF was calculated for different sections of the heated surface.
3. The method of claim 2, wherein the heating surface segmentation model in S23 is used to divide the heating surface into X, Y, Z different regions along the flow direction of flue gas, the width direction of the furnace, and the height direction of the furnace; meanwhile, with the working medium as an object, dividing the heating surface into U, V, W different pipe sections along the overall flow direction of the working medium, the width direction of the hearth and the flow direction of the working medium in the pipe; the coordinates of the divided flue gas area are expressed as (x, y, z), and the coordinates of the divided pipe section are expressed as (u, v, w).
4. The method for monitoring segmentation of soot on heating surface as claimed in claim 2, wherein the refinement in S23 is calculated as follows:
s231: calculating the mass flow q of each pipeline forming the heating surface according to a hydrodynamic calculation methodm(u,v)；
S232: assuming that the heat transfer capacity of each tube section is Qf(u, v, w) calculating corresponding radiant heat transfer amounts respectively
And convective heat transfer capacity
The control equation in the calculation process is as follows:
Qf＝∑Qf(u,v,w)
Qf＝Qg
Qg＝∑Qg(x,y,z)＝∑[h'(x,y,z)-h*(x,y,z)]
C*(x-1,y,z)＝C'(x,y,z)
C*(u,v,w-1)＝C'(u,v,w)
qm＝∑qm(u,v)
wherein Q isfRepresenting the total heat absorption, Q, of the working medium on the heating surfacegRepresents the total heat release, Q, of the heating surface flue gasg(x, y, z) represents the heat release of the smoke region (x, y, z); h' (x, y, z) represents the inlet enthalpy of a zone of flue gas, h*(x, y, z) represents the outlet enthalpy of a zone of flue gas, C*(x-1, y, z) denotes the outlet characteristic of the flue gas region (x-1, y, z), C' (x, y, z) denotes the inlet characteristic of the flue gas region (x, y, z), C*(u, v, w-1) represents an outlet characteristic variable of the working medium pipe section (u, v, w-1), C' (u, v, w) represents an inlet characteristic variable of the working medium pipe section (u, v, w), qmWorking medium flow of all lines, qm(u, v) represents the working medium flow of the pipeline (u, v);
s233: calculating the total heat transfer quantity Q 'of each pipe section after S232'f(u, v, w), which is calculated as follows:
s234: after S233, judging whether the current error meets the precision requirement epsilon, wherein the calculation formula is as follows:
if the current error meets the precision requirement, the iterative calculation is completed, and the parameters of the flue gas side and the working medium side of each pipe section are obtained, otherwise, the assumed value of the heat transfer quantity of each pipe section is reset and the S232 is returned;
s235: after the parameters of the flue gas side and the working medium side of each pipe section are obtained after the iteration is finished, the theoretical heat transfer coefficient k of each pipe section is calculatedtCoefficient of heat transfer k to the actualrThe calculation formula is as follows:
wherein,
representing the convective heat transfer of the pipe section to be calculated, BjIndicating standard coal consumption, A indicating heat transfer area, delta t indicating temperature and pressure, delta tmaxThe temperature difference of the medium at the end with larger temperature difference, delta tminThe temperature difference of the medium, k, at the end of smaller temperature differencegDenotes the side heat transfer coefficient of the flue gas, kfExpressing the heat transfer coefficient of the working medium side, C expressing the empirical coefficient, lambda expressing the heat transfer coefficient of the flue gas at the average flue gas temperature, d expressing the outer diameter of the pipe, Re expressing the Reynolds number, Pr expressing the Prandtl number, ClDenotes the influence of the change in physical properties on the exotherm coefficient, CzCorrection factor representing the number of rows of tubes along the flue gas path, CsRepresents a pitch correction coefficient, abThe blackness of the tube wall of the radiant heating surface is shown, a is the blackness of the flue gas at the temperature T, TbThe absolute temperature of the heated surface is shown, and the indices m, n, and l are constants.
5. The method according to claim 2, wherein the cleaning factor CF in S24 is calculated by the following formula:
6. the method for monitoring segmentation of soot on heating surface according to claim 1, wherein the method for constructing the LSTM time series soot deposition state prediction model comprises the following steps:
s41: acquiring a historical data sequence of the dust deposition parameters containing time information from a database, wherein each piece of data in the sequence comprises a cleaning factor, a dust deposition thickness, a dust deposition area and a dust deposition position corresponding to one moment;
s42: carrying out sample division on the obtained data sequence, and dividing the data sequence into a training sample and a test sample;
s43: carrying out initial training on an LSTM time sequence network by using a training sample to obtain an initial prediction model of a dust deposition state, wherein input variables of the model are cleaning factors, and output variables are dust deposition thickness, dust deposition area and dust deposition position representing the dust deposition state respectively;
s44: optimizing the hyper-parameters in the initial prediction model to obtain an optimized LSTM ash deposition state prediction model;
s45: verifying the trained LSTM soot deposition state prediction model by using a test sample, completing construction of the LSTM time sequence soot deposition state prediction model when an error meets a requirement, and continuing to return to model training if the error does not meet the requirement;
s46: the LSTM time-series soot deposition state prediction model constructed in S45 is used to predict the soot deposition state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110251554.9A CN112989694B (en) | 2021-03-08 | 2021-03-08 | Segmented monitoring system and method for ash on heating surface |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110251554.9A CN112989694B (en) | 2021-03-08 | 2021-03-08 | Segmented monitoring system and method for ash on heating surface |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112989694A CN112989694A (en) | 2021-06-18 |
| CN112989694B true CN112989694B (en) | 2022-04-12 |
Family
ID=76335797
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110251554.9A Active CN112989694B (en) | 2021-03-08 | 2021-03-08 | Segmented monitoring system and method for ash on heating surface |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112989694B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113761794B (en) * | 2021-08-17 | 2024-05-31 | 浙江浙能技术研究院有限公司 | Boiler soot blowing optimization method for supplementing pollution factors based on time sequence prediction algorithm |
| CN114088253A (en) * | 2021-11-17 | 2022-02-25 | 华电国际电力股份有限公司十里泉发电厂 | Water-cooled wall backfire side heat flowmeter and online monitoring method |
| CN115031247B (en) * | 2022-05-30 | 2024-08-02 | 上海发电设备成套设计研究院有限责任公司 | Online monitoring method and device for ash deposition degree of radiation heated surface of boiler |
| CN115510904B (en) * | 2022-09-26 | 2023-08-01 | 天津大学 | Boiler heating area ash monitoring method based on time sequence prediction |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112283689A (en) * | 2020-10-29 | 2021-01-29 | 西安工业大学 | On-line monitoring system and detection method for accumulated ash on heating surface of coal-fired power station boiler |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106845089B (en) * | 2016-12-30 | 2019-03-29 | 国网浙江省电力公司电力科学研究院 | A kind of boiler thermal efficiency acquisition methods |
| CN110390420A (en) * | 2019-06-06 | 2019-10-29 | 广州特种承压设备检测研究院 | Superheater slagging prediction technique based on particle group optimizing artificial neural network |
| CN111241744B (en) * | 2020-01-07 | 2022-08-09 | 浙江大学 | Low-pressure casting machine time sequence data abnormity detection method based on bidirectional LSTM |
-
2021
- 2021-03-08 CN CN202110251554.9A patent/CN112989694B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112283689A (en) * | 2020-10-29 | 2021-01-29 | 西安工业大学 | On-line monitoring system and detection method for accumulated ash on heating surface of coal-fired power station boiler |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112989694A (en) | 2021-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112989694B (en) | Segmented monitoring system and method for ash on heating surface | |
| CN111339716B (en) | Boiler high-temperature flue gas flow field online agent model construction method | |
| CN109583585B (en) | Construction method of power station boiler wall temperature prediction neural network model | |
| CN113361192A (en) | Boiler internal heating surface wall temperature safety monitoring and evaluating system | |
| CN109492319B (en) | Soft measurement method for oxygen content of boiler flue gas of thermal power plant | |
| CN111695249B (en) | Prediction method for heat efficiency of gas boiler | |
| CN113011010A (en) | Boiler fault diagnosis method and diagnosis system based on structural mechanism and operation data | |
| CN111855547B (en) | Visual intelligent monitoring system and method for ash deposition corrosion wear state of medium-low temperature flue gas heat exchange equipment | |
| CN106322412B (en) | Coal unit convection heating surface intelligent ash blowing method based on two-dimentional optimizing | |
| CN110207094B (en) | IQGA-SVR boiler heating surface contamination characteristic identification method based on principal component analysis | |
| CN109829189B (en) | Hearth slagging thickness judgment method based on numerical simulation | |
| CN115510904B (en) | Boiler heating area ash monitoring method based on time sequence prediction | |
| CN114429003A (en) | System of boiler four-tube service life prediction method | |
| CN112923349A (en) | Dynamic dirt monitoring method and system for low-temperature economizer of coal-fired boiler | |
| CN101825869A (en) | Method for identifying superheater model parameters based on data drive | |
| Shi et al. | Ash fouling monitoring and key variables analysis for coal fired power plant boiler | |
| CN117473887A (en) | Method for monitoring thermal state and predicting corrosion of high-temperature heating surface of garbage incinerator | |
| CN102588943A (en) | Monitoring system and monitoring method for soot on boiler convection heating surface | |
| Mojica-Cabeza et al. | A review of the different boiler efficiency calculation and modeling methodologies | |
| CN114036758A (en) | Boiler combustion state dynamic display method based on numerical simulation and machine learning | |
| CN118039004A (en) | Online monitoring method for temperature and hydrogen sulfide gas concentration in pulverized coal boiler | |
| KR101839274B1 (en) | System and method for predicting wear of power plant boiler tube | |
| Zou et al. | Online evaluation of the boiler energy efficiency associated with the soot blowing in coal‐fired power plants | |
| CN102607009A (en) | Fouling monitoring system for convection heating surface of boiler | |
| CN202546721U (en) | Ash fouling monitoring system for convection heating surface of 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |