CN113420467B - Wind powder concentration measuring method integrating mechanism and data driving - Google Patents

Wind powder concentration measuring method integrating mechanism and data driving Download PDF

Info

Publication number
CN113420467B
CN113420467B CN202110964515.3A CN202110964515A CN113420467B CN 113420467 B CN113420467 B CN 113420467B CN 202110964515 A CN202110964515 A CN 202110964515A CN 113420467 B CN113420467 B CN 113420467B
Authority
CN
China
Prior art keywords
data
value
concentration
wind powder
pressure drop
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
Application number
CN202110964515.3A
Other languages
Chinese (zh)
Other versions
CN113420467A (en
Inventor
曹文广
辛凤
刘银波
郭帅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Junlian Yineng Beijing Technology Co ltd
Original Assignee
Changsha University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Changsha University of Science and Technology filed Critical Changsha University of Science and Technology
Priority to CN202110964515.3A priority Critical patent/CN113420467B/en
Publication of CN113420467A publication Critical patent/CN113420467A/en
Application granted granted Critical
Publication of CN113420467B publication Critical patent/CN113420467B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume, or surface-area of porous materials
    • G01N15/06—Investigating concentration of particle suspensions
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply

Abstract

The invention discloses a wind powder concentration measuring method integrating mechanism and data drive, which comprises the following steps: firstly, establishing a mechanism model for calculating the concentration of wind powder based on the pressure drop of a primary air pipeline; secondly, acquiring a pressure drop value and a speed value of a mixture in the air duct in the actual operation process of the primary air duct through measurement; thirdly, collecting historical data and real-time data of a coal-fired power plant in the production operation, such as the output of a coal mill, the mass flow of airflow at a mill inlet, the temperature and the pressure of the airflow at the mill inlet, the temperature and the pressure at a mill outlet, the current of the coal mill, the differential pressure between AB, the speed of a primary air pipeline, the moisture of raw coal and the like, and blending the data; and step four, correcting the wind powder concentration calculation model in real time, and step five, calculating the concentration value of pulverized coal at the mill outlet after acquiring field real-time data. The invention has the beneficial effect that the measurement result can be effectively corrected according to the field working condition, so that the measurement is more accurate.

Description

Wind powder concentration measuring method integrating mechanism and data driving
Technical Field
The invention relates to the technical field of thermal power generation, in particular to a measuring method for accurately measuring the concentration of wind powder in a primary air pipeline based on mechanism and artificial intelligence fusion.
Background
At present, a novel power system with new energy as a main body is an important gripper for realizing the purposes of carbon peak reaching and carbon neutralization, new energy power represented by solar power generation and wind power generation will become a main power source in the future, but the new energy power cannot provide stable electric quantity due to obvious randomness and intermittency, and in order to solve the problem, a peak regulation power source needs to be developed synchronously besides energy storage; because the coal power is stable and reliable, the coal power can be used as a peak regulation power supply, plays the bottom guarantee role of the coal power and undertakes an emergency standby power supply to serve a new energy power system. The flexibility transformation of coal electricity is an important means for realizing the peak shaving of a coal electricity unit, and the stability of boiler combustion plays a decisive role in the low limit of the peak shaving of the unit in the process of the flexibility transformation. Along with the reduction of unit load, boiler combustion load also need reduce, this means that the air and the buggy that get into the furnace will reduce, and the lower the load is, and air and buggy just reduce more, and the heat of burning this moment probably is not enough to maintain the thermal stability of whole furnace, and improper control can cause the furnace to put out a fire, and then the unit shuts down. Therefore, during the load reduction process, the coal dust is the key point for maintaining the combustion, and the quality of the coal dust and the distribution condition of the coal dust in the whole hearth are included.
At present, pulverized coal is mainly distributed to a hearth through a plurality of primary air pipelines for combustion, and the air speed and the pulverized coal concentration in the primary air pipelines are important factors influencing pulverized coal distribution and are important monitoring parameters for ensuring the combustion stability and efficiency of a boiler. Generally speaking, the inconsistency of the flow velocity and the pulverized coal concentration in each primary air pipeline in the same layer of combustor causes problems such as combustion deflection, uneven thermal load of the boiler, adherence of flame, scouring of water wall, coking, flameout and the like to the operation of the boiler. In order to realize the distribution of the coal powder concentration in the primary air pipeline, the accurate measurement of the coal powder concentration in the primary air pipeline is the key, and the measure can be taken to regulate and control the coal powder concentration in the primary air pipeline only when the coal powder concentration in the primary air pipeline is accurately measured.
In the prior art, the method for measuring the concentration of pulverized coal in a primary air pipeline mainly comprises the following steps: the inventor of the present application finds, after practice, that these methods mostly adopt a single mechanism modeling method or a single data-driven modeling method to calculate the concentration of pulverized coal, are greatly influenced by the environment, have poor field adaptability, and simultaneously have high requirements on data quality and weak generalization capability of a single data-driven model, which finally causes inaccurate or unstable measurement results.
Therefore, a measuring method capable of effectively correcting the measuring result according to the field working condition and measuring the coal dust concentration in the primary air pipeline more accurately is lacked.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a method for measuring the concentration of the air and the dust in the primary air pipeline, which can effectively correct the measurement result according to the field working condition, so that the measurement is more accurate.
In order to solve the technical problems, the technical scheme provided by the invention is as follows: a wind powder concentration measuring method integrating mechanism and data drive comprises the following steps:
firstly, establishing a mechanism model for calculating the concentration of wind powder based on the pressure drop of a primary air pipeline; the mechanism model is introduced with field data to correct the correction coefficient;
secondly, acquiring a pressure drop value and a speed value of a mixture in the air duct in the actual operation process of the primary air duct through measurement;
thirdly, acquiring historical data and real-time data of parameters related to the wind powder concentration of equipment needing to measure the wind powder concentration in production operation through a sensor or a data acquisition unit;
step four, converting the data obtained in the step two and the step three into correction coefficients and substituting the correction coefficients into the mechanism model established in the step one to correct the model in real time;
and fifthly, operating the corrected mechanism model to calculate the outlet powder concentration value of the primary air pipeline of the device needing to measure the air powder concentration.
Preferably, the specific modeling method in the step one is as follows:
when the fully developed air-powder-containing air flow flows through a primary air pipeline with the length L at a certain speed, a certain pressure drop is generated, and the pressure drop is delta PtExpressed as the pressure drop Δ P generated by the pure gas flowgAnd pressure drop Δ P due to the delivery of the dustsAnd (c) the sum, i.e.: delta Pt＝ΔPs+ΔPg(ii) a The pressure drop for the pure gas stream was modeled as follows:
Figure GDA0003290899910000021
wherein f isg、ε、ρg、ugAnd D sequentially represents: air flow and pipeline frictionFriction coefficient, void fraction, air flow density, air flow velocity and pipe diameter; meanwhile, the pressure drop generated by the conveying wind powder is modeled as follows:
Figure GDA0003290899910000022
in the formula fs、ρs、usSequentially represents: the friction coefficient of the wind powder and the pipeline, the density of the wind powder and the wind powder speed are shown as the formula, the porosity epsilon is expressed as a function of the wind powder concentration mu, and the relationship between the wind powder and the pipeline is as follows:
Figure GDA0003290899910000023
the pressure drop ratio is calculated from the above formula as follows:
Figure GDA0003290899910000024
for a fully developed primary air pipeline, the air-powder concentration is small, and the gas-solid two-phase speeds are basically consistent, so that rho can be determinedsus＞＞ρgugμ, so we can derive:
Figure GDA0003290899910000031
where K is the concentration correction factor, in the above formula, Δ P is obtained by measurementtΔ P is calculated by the formula and parameters defined previouslyg(ii) a Then the two are divided to obtain an alpha value; and further defining a K value calculation model in the model as follows:
Figure GDA0003290899910000032
in the formula BMΔ M represents the grinding force and the mass of water dried in the medium, i ═ 1,2,3,4, respectivelyThe number of the powder outlet pipe of the equipment; Δ M can be obtained from conservation of mass of the gas stream, i.e.
Figure GDA0003290899910000033
MinThe mass flow of the airflow at the inlet of the mill is calculated, and the calculated delta M can be verified according to the water content of the medium; substituting the confirmed parameters into a K value formula, and calculating the K value, wherein the calculation formula of the specific reverse performance is as follows:
Figure GDA0003290899910000034
after confirming two data of alpha and K, the concentration of the wind powder can be obtained, and the specific calculation formula is as follows:
Figure GDA0003290899910000035
thus, the establishment of a mathematical model of the relation between the field data and the concentration of the wind powder is completed.
Preferably, in the second step, the specific method for obtaining the pressure drop value is as follows: selecting A, B pressure measuring points on a primary air pipeline, correspondingly installing 1-6 pressure sensors on each measuring point, wherein the distance between the measuring points is more than 1 meter, and the pressure drop value is the average value of the differential pressure between the two measuring points and is defined as: differential pressure between AB; meanwhile, the speed value of the air duct in the actual operation process of the primary air duct is obtained through measurement;
preferably, the historical data and the real-time data of the parameters related to the wind powder concentration in the third step comprise: historical data and real-time data of equipment needing to be measured in production operation, such as equipment output, equipment inlet airflow mass flow, equipment inlet airflow temperature and pressure, equipment outlet temperature and pressure, equipment current, differential pressure between AB, primary air pipeline speed, measurement medium moisture and the like; and the data are subjected to the reconciliation treatment, which specifically comprises the following steps: establishing reasonable data based on the mass, energy and momentum balance principle; deleting unreasonable data based on production and practical experience; filling the current time data and other harmonic processing modes by adopting an average value of t time before the current time;
preferably, the real-time correction specifically comprises: firstly, establishing a machine learning model y (f) (x) for calculating a K value, wherein the input x of the model is historical data and real-time data of parameters related to the concentration of the wind powder in the third step, and the output y of the model is the K value; secondly, according to the analysis of the working condition change situation, historical data of a certain period of time (such as half a year or 1 year) is subjected to machine learning model training, and a model y is obtained as f (x).
Preferably, the method for measuring the speed value in the air duct in the actual operation process of the primary air duct comprises the following steps: "backrest tube" measurement method.
Preferably, the field data acquisition directly obtains the historical data and the real-time data of the production operation from the sis system through the self-carried sis system interface program of the measured equipment, and stores the obtained data in a local database.
After adopting the structure, the invention has the following beneficial effects: the invention creatively combines the mechanism of measuring the concentration of the wind powder by a pressure drop method and an artificial intelligence method together to establish a mixed model for measuring the concentration of the wind powder, considers the mass conservation law in the mechanism model, integrates the output data of equipment and increases the rationality of the model. In addition, the model adopts the fusion of mechanism and data to uniformly consider the conservation law of the nature and the complexity of the field environment, has obvious advantages compared with a single mechanism modeling method or a single data-driven modeling method for calculating the wind powder concentration, can overcome the problems that a single mechanism model is greatly influenced by the environment and has poor field adaptability, can also overcome the problems that a single data-driven model has high requirement on data quality and weak generalization capability, and can accurately calculate the wind powder concentration.
In conclusion, the invention provides the method for measuring the concentration of the wind powder in the primary air pipeline, which can effectively correct the measurement result according to the field working condition and enables the measurement to be more accurate.
Drawings
FIG. 1 is a simplified flow chart of a method for measuring the concentration of wind powder by integrating mechanism and data driving in the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
A wind powder concentration measuring method integrating mechanism and data drive comprises the following steps:
firstly, establishing a mechanism model for calculating the concentration of wind powder based on the pressure drop of a primary air pipeline; the mechanism model is introduced with field data to correct the correction coefficient;
secondly, acquiring a pressure drop value and a speed value of a mixture in the air duct in the actual operation process of the primary air duct through measurement;
thirdly, acquiring historical data and real-time data of parameters related to the wind powder concentration of equipment needing to measure the wind powder concentration in production operation through a sensor or a data acquisition unit;
step four, converting the data obtained in the step two and the step three into correction coefficients and substituting the correction coefficients into the mechanism model established in the step one to correct the model in real time;
and fifthly, operating the corrected mechanism model to calculate the outlet powder concentration value of the primary air pipeline of the device needing to measure the air powder concentration.
Preferably, the specific modeling method in the step one is as follows:
when the fully developed air-powder-containing air flow flows through a primary air pipeline with the length L at a certain speed, a certain pressure drop is generated, and the pressure drop is delta PtExpressed as the pressure drop Δ P generated by the pure gas flowgAnd pressure drop Δ P due to the delivery of the dustsAnd (c) the sum, i.e.: delta Pt＝ΔPs+ΔPg(ii) a The pressure drop for the pure gas stream was modeled as follows:
Figure GDA0003290899910000051
wherein f isg、ε、ρg、ugAnd D sequentially represents: the friction coefficient of the air flow and the pipeline, the void ratio, the air flow density, the air flow speed and the diameter of the pipeline; while generated for conveying the dustThe pressure drop was modeled as follows:
Figure GDA0003290899910000052
in the formula fs、ρs、usSequentially represents: the friction coefficient of the wind powder and the pipeline, the density of the wind powder and the wind powder speed are shown as the formula, the porosity epsilon is expressed as a function of the wind powder concentration mu, and the relationship between the wind powder and the pipeline is as follows:
Figure GDA0003290899910000053
the pressure drop ratio is calculated from the above formula as follows:
Figure GDA0003290899910000054
for a fully developed primary air pipeline, the air-powder concentration is small, and the gas-solid two-phase speeds are basically consistent, so that rho can be determinedsus＞＞ρgugμ, so we can derive:
Figure GDA0003290899910000055
where K is the concentration correction factor, in the above formula, Δ P is obtained by measurementtΔ P is calculated by the formula and parameters defined previouslyg(ii) a Then the two are divided to obtain an alpha value; and further defining a K value calculation model in the model as follows:
Figure GDA0003290899910000056
in the formula BMAnd delta M is the grinding force and the quality of the dried moisture in the medium respectively, and i is 1,2,3 and 4 which represent the pipe number of the powder outlet pipe of the device; Δ M can be obtained from conservation of mass of the gas stream, i.e.
Figure GDA0003290899910000057
MinThe mass flow of the airflow at the inlet of the mill is calculated, and the calculated delta M can be verified according to the water content of the medium; substituting the confirmed parameters into a K value formula, and calculating the K value, wherein the calculation formula of the specific reverse performance is as follows:
Figure GDA0003290899910000058
after confirming two data of alpha and K, the concentration of the wind powder can be obtained, and the specific calculation formula is as follows:
Figure GDA0003290899910000061
thus, the establishment of a mathematical model of the relation between the field data and the concentration of the wind powder is completed.
Preferably, in the second step, the specific method for obtaining the pressure drop value is as follows: selecting A, B pressure measuring points on a primary air pipeline, correspondingly installing 1-6 pressure sensors on each measuring point, wherein the distance between the measuring points is more than 1 meter, and the pressure drop value is the average value of the differential pressure between the two measuring points and is defined as: differential pressure between AB; meanwhile, the speed value of the air duct in the actual operation process of the primary air duct is obtained through measurement;
preferably, the historical data and the real-time data of the parameters related to the wind powder concentration in the third step comprise: historical data and real-time data of equipment needing to be measured in production operation, such as equipment output, equipment inlet airflow mass flow, equipment inlet airflow temperature and pressure, equipment outlet temperature and pressure, equipment current, differential pressure between AB, primary air pipeline speed, measurement medium moisture and the like; and the data are subjected to the reconciliation treatment, which specifically comprises the following steps: establishing reasonable data based on the mass, energy and momentum balance principle; deleting unreasonable data based on production and practical experience; filling the current time data and other harmonic processing modes by adopting an average value of t time before the current time;
preferably, the real-time correction specifically comprises: firstly, establishing a machine learning model y (f) (x) for calculating a K value, wherein the input x of the model is historical data and real-time data of parameters related to the concentration of the wind powder in the third step, and the output y of the model is the K value; secondly, according to the analysis of the working condition change situation, historical data of a certain period of time (such as half a year or 1 year) is subjected to machine learning model training, and a model y is obtained as f (x).
Preferably, the method for measuring the speed value in the air duct in the actual operation process of the primary air duct comprises the following steps: "backrest tube" measurement method.
Preferably, the field data acquisition directly obtains the historical data and the real-time data of the production operation from the sis system through the self-carried sis system interface program of the measured equipment, and stores the obtained data in a local database.
Further referring to fig. 1, taking calculation of coal dust concentration in a primary air pipe of a coal mill as an example, a method for measuring air dust concentration by integrating mechanism and data drive comprises the following steps: firstly, establishing a mechanism model for calculating the concentration of the wind powder based on the pressure drop of a pipeline; since a sufficiently developed coal dust-containing gas stream will have a certain pressure drop when flowing through a primary air duct of length L at a certain velocity, this pressure drop ap can be settExpressed as the pressure drop Δ P generated by the pure gas flowgAnd the pressure drop Δ P generated by the transport of pulverized coalsAnd (c) the sum, i.e.: delta Pt＝ΔPs+ΔPgPressure drop for pure gas flow
Figure GDA0003290899910000062
Wherein f isg、ε、ρg、ugAnd D is the friction coefficient, the void ratio, the air flow density, the air flow speed and the pipeline diameter of the air flow and the pipeline respectively. Similarly, the pressure drop generated for conveying pulverized coal is
Figure GDA0003290899910000063
The porosity can be expressed as a function of the coal dust concentration mu, i.e.
Figure GDA0003290899910000064
Thus I amOne can derive the ratio of the pressure drop
Figure GDA0003290899910000065
Figure GDA0003290899910000071
For a fully developed primary air pipeline, the concentration of the pulverized coal is small, and the speeds of a gas phase and a solid phase are basically consistent, so that rho can be knownsus＞＞ρgugμ, so that
Figure GDA0003290899910000072
Therefore, the mass flow of the pulverized coal can be obtained only by knowing the sizes of alpha and K
Figure GDA0003290899910000073
ΔPtCan be measured to obtain, delta PgCan be calculated, alpha can be known. The K value is related to the coal powder properties (such as density, particle size and distribution and the like), the pipeline properties (such as diameter, pipe wall roughness and the like), the pipeline form (vertical, horizontal or inclined) and the air flow properties (such as speed, density, viscosity and the like), and researches show that when the air flow speed exceeds 20m/s, the K value is independent of the air flow speed and can be obtained through experiments. In an actual pulverizing system, assuming that a medium-speed mill has four primary air pipelines, a section of pipeline is selected from 4 pipelines respectively, and the 4 pipelines are as consistent as possible (or extremely similar, such as same position, length, form and the like), the K values of the pipelines are considered to be the same, so that the K values of the pipelines are the same, and the K values of the pipelines are considered to be the same
Figure GDA0003290899910000074
In the formula BMAnd Δ M are the grinding output and the mass of water dried in the coal, respectively, and i is 1,2,3, 4.Δ M can be obtained from conservation of mass of the gas stream, i.e.
Figure GDA0003290899910000075
Figure GDA0003290899910000076
MinFor mill inlet air flow mass flow, the Δ M obtained from this calculation can also be based onAnd (5) checking the water content of the coal. Therefore, a relational expression of field data and coal dust concentration is established, and the coal dust concentration can be obtained by acquiring pressure drop data and acquiring and harmonizing the field data. Secondly, measuring the pressure drop speed; before the concentration of the pulverized coal is obtained, a pressure drop value and a speed value need to be obtained, and the pressure drop and the speed can be directly obtained by measurement:
(1) pressure drop is obtained: a, B on the primary air pipeline are installed two pressure measuring points to measure the differential pressure between two points, the measuring points can be installed with > 1 pressure (differential pressure) sensor, the installation form is shown in figure 1, the distance between the measuring points should be more than 1m, and the pressure drop data is the average value of the differential pressure between the two measuring points.
(2) Speed acquisition: the speed can be obtained by various methods, such as the most commonly used method of measuring by using a 'backrest tube', and the speed is not the core of the invention and is not described in detail herein.
Thirdly, data acquisition and reconciliation; the actual powder making system is very complex in field condition, is influenced by a plurality of factors in production and operation, and the accurate result cannot be obtained by completely adopting the mechanism model to calculate the coal powder concentration in real time, so that the mechanism model fails. Therefore, the mechanism model needs to be corrected by combining field data. This correction process includes the following several
The method comprises the following steps:
firstly, field data acquisition: coal-fired power plants are generally equipped with a sis system for storing operation data in the production process, so that historical data and real-time data of production operation can be obtained from the sis system through an interface program of the sis system, the obtained data is stored in a local database, and data points mainly required to be obtained comprise: coal mill output, mill inlet airflow mass flow, mill inlet airflow temperature and pressure, mill outlet temperature and pressure, coal mill current, differential pressure between AB, primary air pipeline speed, raw coal moisture, and the like. Of course, the field real-time data may also be obtained from a DCS system equipped with the coal-fired power plant.
Data reconciliation processing: the limitation of being influenced by field instruments and test environments, the reliability of directly acquiring data on the field does not completely meet the requirement of the prior knowledge principle, and certain reconciliation processing must be carried out on the data, which mainly comprises the following steps: establishing reasonable data based on the mass, energy and momentum balance principle; deleting unreasonable data based on production and practical experience; the current time data is filled with an average value of time t (e.g., 10s sampling time interval, t 50s) before the current time, and so on.
Fourthly, correcting the wind powder concentration calculation model in real time; according to the mechanism model, when the coal powder concentration is calculated, the K value is obtained from a laboratory, and the adaptability of the value to a complex field environment is difficult to guarantee, so that the K value is corrected by adopting field data, the corrected K value can meet the application requirement of a field, and the specific correction steps are as follows:
inverse calculation model of K value by mechanism model, i.e.
Figure GDA0003290899910000081
And secondly, establishing a machine learning model y (f) (x) for calculating the K value, wherein the input x of the model is mill output, mill inlet airflow mass flow, mill inlet airflow temperature and pressure, mill outlet temperature and pressure, coal mill current, differential pressure between AB, primary air pipeline speed and raw coal moisture, and the output y of the model is the K value.
And thirdly, performing machine learning model training on historical data of a proper time period (such as half a year or 1 year) according to the analysis of the change condition of the coal type entering the mill, and obtaining a model y (f) (x).
And step five, substituting the obtained K value into a mechanism model, obtaining field real-time data and then calculating the concentration of pulverized coal at the outlet of the mill.
Practice proves that the coal powder concentration prediction mechanism model based on the pressure drop method is established, and for one coal mill, model parameters contain coal mill output data, so that the conservation of coal powder quality in calculation can be effectively guaranteed. Meanwhile, in the coal dust concentration measurement subdivision field, a mechanism-data fusion mixed model is creatively established, the mechanism side of the model takes a pressure drop method as a principle, the data side of the model takes a machine learning algorithm as a basis, such as SVM, RNN, LSTM and the like, a model with a coefficient K is obtained by training the machine learning model, and then the K is substituted into the mechanism model and is combined with real-time data to calculate the coal dust concentration.
The following are specifically mentioned: the method related to the patent application of the invention can not only measure the pulverized coal in the air pipe, but also measure other powder in the air pipe, so the theme is named as air powder, but in the practical embodiment, the pulverized coal is taken as the main body, so the pulverized coal adopted in part of description is taken as the medium for description.
The present invention and its embodiments have been described above, and the description is not intended to be limiting, and the drawings are only one embodiment of the present invention, and the actual configuration is not limited thereto. In summary, those skilled in the art should appreciate that they can readily use the disclosed conception and specific embodiments as a basis for designing or modifying other structures for carrying out the same purposes of the present invention without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (5)

1. A wind powder concentration measurement method integrating mechanism and data drive is characterized in that: it comprises the following steps:
firstly, establishing a mechanism model for calculating the wind powder concentration based on the pressure drop of a primary air pipeline, wherein the specific modeling method comprises the following steps:
when the fully developed air-powder-containing air flow flows through a primary air pipeline with the length L at a certain speed, a certain pressure drop is generated, and the pressure drop is delta PtExpressed as the pressure drop Δ P generated by the pure gas flowgAnd pressure drop Δ P due to the delivery of the dustsAnd (c) the sum, i.e.:
ΔPt＝ΔPs+ΔPg(ii) a The pressure drop for the pure gas stream was modeled as follows:
Figure FDA0003290899900000011
wherein f isg、ε、ρg、ugAnd D sequentially represents: the friction coefficient of the air flow and the pipeline, the void ratio, the air flow density, the air flow speed and the diameter of the pipeline; simultaneously for conveyingThe pressure drop due to wind dust was modeled as follows:
Figure FDA0003290899900000012
in the formula fs、ρs、usSequentially represents: the friction coefficient of the wind powder and the pipeline, the density of the wind powder and the wind powder speed are shown as the formula, the porosity epsilon is expressed as a function of the wind powder concentration mu, and the relationship between the wind powder and the pipeline is as follows:
Figure FDA0003290899900000013
the pressure drop ratio is calculated from the above formula as follows:
Figure FDA0003290899900000014
for a fully developed primary air pipeline, the air-powder concentration is small, and the gas-solid two-phase speeds are basically consistent, so that rho can be determinedsus＞＞ρgugμ, so we can derive:
Figure FDA0003290899900000015
where K is the concentration correction factor, in the above formula, Δ P is obtained by measurementtΔ P is calculated by the formula and parameters defined previouslyg(ii) a Then the two are divided to obtain an alpha value; and further defining a K value calculation model in the model as follows:
Figure FDA0003290899900000016
in the formula BMAnd Δ M represents the grinding force and the mass of water dried in the medium, respectively, and i ═ 1,2,3, and 4 represent the powder discharged from the apparatusThe tube number; Δ M can be obtained from conservation of mass of the gas stream, i.e.
Figure FDA0003290899900000017
MinThe mass flow of the airflow at the inlet of the mill is calculated, and the calculated delta M can be verified according to the water content of the medium; substituting the confirmed parameters into a K value formula, and calculating the K value, wherein the calculation formula of the specific reverse performance is as follows:
Figure FDA0003290899900000018
after confirming two data of alpha and K, the concentration of the wind powder can be obtained, and the specific calculation formula is as follows:
Figure FDA0003290899900000021
thus, the establishment of a mathematical model of the relation between the field data and the concentration of the wind powder is completed;
secondly, acquiring a pressure drop value and a speed value of a mixture in the air duct in the actual operation process of the primary air duct through measurement;
thirdly, acquiring historical data and real-time data of parameters related to the wind powder concentration of equipment needing to measure the wind powder concentration in production operation through a sensor or a data acquisition unit;
step four, establishing a machine learning model y (f) (x) for calculating the K value, wherein the input x of the model is historical data and real-time data of parameters related to the concentration of the wind powder in the step two and the step three, and the output y of the model is the K value; secondly, according to the analysis of the working condition change condition, machine learning model training is carried out on half-year or 1-year historical data, and a model y is f (x); substituting the trained K value into the mechanism model established in the first step to correct the model in real time;
and fifthly, operating the corrected mechanism model to calculate the outlet powder concentration value of the primary air pipeline of the device needing to measure the air powder concentration.
2. The method for measuring wind powder concentration by fusing mechanism and data driving according to claim 1, characterized in that: in the second step, the specific method for obtaining the pressure drop value comprises the following steps: selecting A, B pressure measuring points on a primary air pipeline, correspondingly installing 1-6 pressure sensors on each measuring point, wherein the distance between the measuring points is more than 1 meter, and the pressure drop value is the average value of the differential pressure between the two measuring points and is defined as: differential pressure between AB; and meanwhile, the speed value of the air duct in the actual operation process of the primary air duct is obtained through measurement.
3. The method for measuring wind powder concentration by fusing mechanism and data driving according to claim 1, characterized in that: the historical data and the real-time data of the parameters related to the wind powder concentration in the third step comprise: historical data and real-time data of equipment needing to be measured in production operation, such as equipment output, equipment inlet airflow mass flow, equipment inlet airflow temperature and pressure, equipment outlet temperature and pressure, equipment current, differential pressure between AB, primary air pipeline speed, measurement medium moisture and the like; and the data are subjected to the reconciliation treatment, which specifically comprises the following steps: establishing reasonable data based on the mass, energy and momentum balance principle; deleting unreasonable data based on production and practical experience; and filling the current time data with the average value of t time before the current time in a harmonic processing mode.
4. The wind-powder concentration measurement method integrating mechanism and data driving according to claim 2, characterized in that: the method for measuring the speed value of the air duct in the actual operation process of the primary air duct comprises the following steps: "backrest tube" measurement method.
5. The method for measuring wind powder concentration by fusing mechanism and data driving according to claim 1, characterized in that: and the field data acquisition directly obtains historical data and real-time data of production operation from the sis system through a sis system interface program carried by the measured equipment, and stores the obtained data into a local database.
CN202110964515.3A 2021-08-23 2021-08-23 Wind powder concentration measuring method integrating mechanism and data driving Active CN113420467B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110964515.3A CN113420467B (en) 2021-08-23 2021-08-23 Wind powder concentration measuring method integrating mechanism and data driving

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110964515.3A CN113420467B (en) 2021-08-23 2021-08-23 Wind powder concentration measuring method integrating mechanism and data driving

Publications (2)

Publication Number Publication Date
CN113420467A CN113420467A (en) 2021-09-21
CN113420467B true CN113420467B (en) 2021-11-12

Family

ID=77719693

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110964515.3A Active CN113420467B (en) 2021-08-23 2021-08-23 Wind powder concentration measuring method integrating mechanism and data driving

Country Status (1)

Country Link
CN (1) CN113420467B (en)

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102853870B (en) * 2012-09-24 2018-07-27 中国石油化工股份有限公司 The detection method and device of pulverized coal mass flow in a kind of coal dust transmission process
CN109821646A (en) * 2019-01-14 2019-05-31 华北电力大学 A kind of coal pulverizer outlet pulverized coal flow flexible measurement method

Also Published As

Publication number Publication date
CN113420467A (en) 2021-09-21

Similar Documents

Publication Publication Date Title
CN104750131B (en) A kind of fluidized-bed temperature control method based on parameter identification
CN105276563B (en) A kind of furnace outlet gas temperature flexible measurement method based on the real-time slagging scorification situation of burner hearth
CN111829003B (en) Power plant combustion control system and control method
CN112283689B (en) On-line monitoring system and detection method for accumulated ash on heating surface of coal-fired power plant boiler
CN109184933B (en) Cooperative optimization control method and system for methane internal combustion generator set
CN103699780B (en) Ature of coal parameter is in the chaos optimization method of line computation
CN104268433B (en) Method for monitoring unit power generation coal consumption deviation caused by variation of gas boiler operating parameters
CN106322412B (en) Coal unit convection heating surface intelligent ash blowing method based on two-dimentional optimizing
CN107016176A (en) A kind of hybrid intelligent overall boiler burning optimization method
CN108197723B (en) Optimized energy-saving scheduling method for coal consumption and pollutant discharge of coal-electricity unit power supply
CN105536490B (en) The automatic desulphurization system of one kind sintering flue gas and its method
CN104729888B (en) Flue fly ash constant-speed sampling system based on BP neural network and control method
CN106548032B (en) Based on boiler flue grid detection flue gas CO and O2The distribution field method for reconstructing of concentration
CN111339716A (en) Boiler high-temperature flue gas flow field online proxy model construction method
CN104061589B (en) Adapt to low nitrogen burning control method and the device of coal varitation
CN106594794A (en) Hybrid and intelligent updating method for boiler efficiency combustion optimization model
CN105808945B (en) A kind of hybrid intelligent boiler efficiency burning optimization method
CN109086949B (en) Blast furnace gas generation amount and heat value prediction method based on gas component change
CN113420467B (en) Wind powder concentration measuring method integrating mechanism and data driving
CN110864855A (en) Device and method for measuring air leakage rate of air preheater of power station boiler under medium and low loads
CN106838979B (en) Based on boiler furnace grid detection CO and O2The distribution field construction method of concentration
CN113074459A (en) Boiler control optimization method and system
CN103324991B (en) The method and system of pulverized-coal fired boiler NOx emission predictive
CN207455557U (en) A kind of injection boiler mass dryness fraction is monitored automatically with the thermal efficiency and Optimal Control System
CN104102842A (en) Nitrogen oxide emission predicting method and device based on economic index parameters

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
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20221104

Address after: No. 18-D18471, Jianshe Road, Kaixuan Street, Liangxiang, Fangshan District, Beijing 102488 (cluster registration)

Patentee after: JUNLIAN YINENG (BEIJING) TECHNOLOGY CO.,LTD.

Address before: 410114 No. 960, Section 2, Wanjiali South Road, Tianxin District, Changsha City, Hunan Province

Patentee before: CHANGSHA University OF SCIENCE AND TECHNOLOGY