CN115656461A - Coal electric unit real-time carbon emission monitoring method based on coal quality soft measurement - Google Patents
Coal electric unit real-time carbon emission monitoring method based on coal quality soft measurement Download PDFInfo
- Publication number
- CN115656461A CN115656461A CN202211014212.6A CN202211014212A CN115656461A CN 115656461 A CN115656461 A CN 115656461A CN 202211014212 A CN202211014212 A CN 202211014212A CN 115656461 A CN115656461 A CN 115656461A
- Authority
- CN
- China
- Prior art keywords
- coal
- daf
- data
- real
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/84—Greenhouse gas [GHG] management systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/84—Greenhouse gas [GHG] management systems
- Y02P90/845—Inventory and reporting systems for greenhouse gases [GHG]
Landscapes
- Regulation And Control Of Combustion (AREA)
Abstract
The invention relates to a coal-electricity unit real-time carbon emission monitoring method based on coal quality soft measurement, which is used for accurately monitoring real-time carbon emission data of various coal-blended coal-electricity units, and comprises the following steps: step1, collecting data; step2, data cleaning and preprocessing; step3, judging the stable working condition of the unit; step4, establishing a fly ash slag carbon content neural network prediction model, and predicting the ash content through soft measurement; step5, establishing a coal quality soft measurement model; and 6, calculating the carbon emission in real time. Compared with the prior art, the invention has the advantages that the real-time carbon emission data of various coal-blending coal electric units can be further accurately mastered by a reliable means under the condition that the characteristics of the fire coal are changed in real time, and the like.
Description
Technical Field
The invention relates to the field of carbon emission monitoring, in particular to a coal electric unit real-time carbon emission monitoring method based on coal quality soft measurement.
Background
The control and reduction of carbon emissions in the power industry, particularly in the coal and electricity field, is undoubtedly a very important factor to achieve the goals of "carbon peaking" and even "carbon neutralization" early on. On the other hand, the energy consumption structure of China also determines that the power generation pattern mainly based on coal and electricity cannot be fundamentally changed in a long time. Therefore, under a new situation, how to accurately master the development and operation rules of the coal-electricity industry and scientifically and effectively calculate the real-time carbon emission of the coal-electricity generating set so as to promote the improvement of the efficiency of the coal-fired generating set and the utilization rate of coal resources, further improve the environmental quality and have very important guiding significance for the optimization development of coal-electricity enterprises and the reasonable arrangement, scheduling and planning of a power grid.
At present, the main basis for carrying out the accounting on the carbon emission in China is the part 1 of greenhouse gas emission accounting and report requirements: power generation enterprises (GB/T32151.1-2015), "methods and reporting guidelines for accounting for greenhouse gas emission from Chinese power generation enterprises (trial implementation)," methods and reporting for accounting for greenhouse gas emission from enterprises in the ecological environment part of 2022 "means and reporting to south power generation facilities (revised version of 2022)". The accounting method is mainly suitable for accounting the total carbon emission amount in a long time or period, and the real-time carbon emission amount calculation of the coal-electricity unit is difficult to realize.
In order to solve the problems, currently, widely recognized in the domestic field of real-time carbon emission monitoring mainly include three technical paths for realizing the calculation of the real-time carbon emission of the coal-electric machine set, namely an emission factor method, an actual measurement method and a mass balance method.
The emission factor method, also known as the emission coefficient method, calculates the basic equation from the carbon provided by the IPCC: greenhouse gas (GHG) emission = Activity Data (AD) x Emission Factor (EF), wherein EF is a coefficient corresponding to activity level data, including carbon content per calorific value or elemental carbon content, oxidation rate and the like, and represents a greenhouse gas emission coefficient per unit production or consumption activity. The method has the disadvantages that on one hand, the default emission factor library of the IPCC national greenhouse gas list is mainly obtained from developed countries and can not accurately reflect the actual conditions of China, and on the other hand, the method is easy to cause larger deviation in various energy consumption statistics and carbon emission factor measurement due to the reasons of different energy quality differences, different unit combustion efficiency and the like in different regions of China, and the method also becomes a main source of carbon emission accounting result errors.
The actual measurement method is to calculate the carbon emission by the content of carbon elements such as CO2 and CO in the existing CEMS (continuous emission monitoring system) system of the power plant and the smoke amount. For example, chinese patent application No. 202111112049.2, a system and a method for monitoring carbon emission indexes of a coal-fired power plant in real time. The invention discloses a system and a method for monitoring carbon emission indexes of a coal-fired power plant in real time, which are used for calculating the carbon emission of a unit in real time by acquiring inlet data of a primary air fan and an air feeder, air composition data and flue gas composition data. The method is a typical actual measurement method, and the main problem is that the detection means has higher cost; secondly, the volatility of the measuring method is high, especially the measuring stability of the air and flue gas flow is poor, and the long-term stability requirement of a power plant cannot be met.
The mass balance method is to calculate carbon emission data under different loads and different working conditions by utilizing the energy balance principle of the unit through real-time operation data of the unit. The method is mainly used for calculating the emission based on a carbon mass balance method of specific facilities and process flows, and can reflect the actual emission of carbon emission places. For example, chinese patent application No. 202111112049.2, a method for calculating carbon emission of a coal-fired power plant. The invention discloses a calculation method for predicting carbon emission of a coal-fired power plant, which comprises the steps of obtaining a relational expression of fuel characteristic coefficients by establishing a mathematical model, calculating the fuel characteristic coefficient value of coal combusted by the power plant, calculating the percentage content of carbon dioxide in flue gas, calculating the total emission amount of the flue gas and calculating the total emission amount of the carbon dioxide. However, the data adopted by the calculation method are all basic detection data of a conventional coal-fired power plant, the influence of real-time coal type change conditions on carbon emission is not considered, and the practicability of the operation unit for blending the coal type is not high. Liu Ke of Shandong province Power saving company in China network and the like provide 'research on carbon emission characteristics of a coal-fired unit based on real-time monitoring', in order to research the carbon emission characteristics of the coal-fired unit in different running states, a carbon calculation method based on energy balance and material conservation is adopted, and minute-level continuous monitoring on carbon emission intensity of the coal-fired unit is realized, but the carbon content and coal quality analysis components of fly ash in the method are based on statistical results of various shifts of a power plant, and the method is only suitable for units with little coal quality change.
Therefore, under the current large background that many power plants purchase coal in various types due to shortage of coal resources and shortage of coal market supply, and coal blending and burning are adopted in an operation mode, how to accurately calculate the real-time carbon emission of the coal-electric machine set relatively according to the existing real-time data of the coal-fired power plants also becomes a key point worthy of deep analysis and research, and the technical problem to be solved by the invention is also provided.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide a method for monitoring the carbon emission of a coal electric unit in real time based on coal quality soft measurement.
The purpose of the invention can be realized by the following technical scheme:
according to one aspect of the invention, a coal electric unit real-time carbon emission monitoring method based on coal quality soft measurement is provided, and is used for accurately monitoring real-time carbon emission data of various coal-blended coal electric units, and the monitoring method comprises the following steps:
step1, collecting data;
step2, data cleaning and preprocessing;
step3, judging the stable working condition of the unit;
step4, establishing a fly ash slag carbon content neural network prediction model, and predicting the ash content through soft measurement;
step5, establishing a coal quality soft measurement model;
and 6, calculating the carbon emission in real time.
As a preferred technical solution, the step1 specifically includes: collecting and calculating related data through a real-time data interface;
wherein said collecting computational-related data comprises:
(a) Calculating data related to coal moisture, including real-time output, inlet air quantity, power, inlet and outlet air temperature and environment temperature of each coal mill;
(b) Calculating the oxygen quantity at the outlet of the economizer, the exhaust gas temperature and the air leakage rate required by the real-time boiler efficiency;
(c) Calculating data related to the coal quality heat value, wherein the data comprises main steam flow, main steam pressure, main steam temperature, main water supply pressure, main water supply temperature, cold and re-flow, re-heated steam hot end pressure, re-heated steam hot end temperature, re-heated steam cold end pressure, re-heated steam cold end temperature, re-heater de-temperature water amount, re-heater de-temperature water pressure, re-heater de-temperature water temperature, superheater de-temperature water spray amount, superheater de-temperature water spray pressure, superheater de-temperature water spray temperature, boiler coal real-time consumption and unit current load;
(d) And the unit operation data required by the fly ash carbon content prediction model comprises coal low-grade heating value, coal moisture, coal ash content, coal quantity of each coal mill, primary air quantity, outlet air temperature, main water supply flow, air preheater inlet flue gas temperature, total primary air quantity, total secondary air quantity, total air quantity and SCR inlet oxygen quantity.
As a preferred technical solution, the step2 specifically comprises the following steps:
step 2.1, interpolation: for the data missing situation, interpolation processing needs to be performed on the missing value according to a set target value or a historical optimal value, and the target value or the historical optimal value is inserted into a corresponding attribute of a measuring point where data is missing;
step 2.2, repeating data checking: directly judging whether the acquired data is repeated or not according to an agreed repeated data judgment principle, and directly discarding the repeated data if the acquired data is the repeated data;
step 2.3, range checking: directly judging the upper limit and the lower limit of the operation parameters, and judging that the operating parameters exceeding the upper limit and the lower limit are dead spots;
step 2.4, precision checking: determining a reference curve of the operation parameters, judging the actual parameters by taking the reference curve as a standard, and judging that the measuring point is a bad point according to the measuring point value of which the data precision does not conform to the actual operation condition;
step 2.5, parameter identification: and establishing a normal state matrix model of the parameters, and when the model inputs actual operation parameters, finding out the correlation degree of the actual data and the normal data on the basis of the normal state matrix so as to perform parameter identification on the normal expected value of the actual operation data.
As a preferred technical solution, the step3 of determining the stable operating condition by a moving average variance method specifically includes:
wherein, P 1 ,...,P 10 Represents the unit power value, fc, of the first 10 minutes with a frequency interval of 1 minute under the current operating conditions 1 ,...,Fc 10 Representing the total coal quantity value of the first 10 minutes with a frequency interval of 1 minute under the current working condition, P avg Represents the average value of the first 10 ten minute unit power, fc avg Represents the average, σ, of the total coal amounts in the first 10 minutes P Representing the square difference, sigma, allowed by the unit power under stable conditions Fc Representing the square error allowed by the total coal quantity under the stable working condition; under the condition that the formulas 3-2 and 3-3 are simultaneously met, the operation data of the first 10 minutes which meet the acquisition requirement under the current working condition are averaged, and then the numerical calculation is carried out in the calculation model, so that the condition of large calculation result deviation caused by large load or coal quantity change in the calculation process is avoided.
And 4, as a preferred technical scheme, performing prediction modeling and online prediction on average carbon content of ash by adopting a deep neural network algorithm, and calculating a loss function value according to part of training set data.
As a preferred technical solution, the sample input and output variables of the deep neural network algorithm are shown in the following table:
the network structure of the deep neural network algorithm model is 25-100-1, namely 49 input nodes, 100 hidden nodes and 1 output node; a gradient descent algorithm is adopted in the process of solving the weight and the bias, and an Adam optimization algorithm is adopted for the self-adaptive adjustment of the learning rate and the problem of local extremum.
As a preferred technical solution, the step5 specifically includes:
step 5.1, calculating the received base moisture of each coal mill based on the running state of the coal mill;
and 5.2, analyzing and monitoring the low-level calorific value and elements of the coal as fired.
As a preferred technical solution, the step 5.1 specifically comprises:
the heat entering the coal mill comprises: physical heat of desiccant q gz Physical heat q of cold air leaking in lf Heat q generated by the polishing member nm And physical heat of raw coal q r (ii) a The heat exiting the coal mill comprises: heat of evaporation of water q z Heat quantity q consumed by heating fuel jr Heat q of the drying agent carrying out of the system 2 And heat dissipation loss q of coal mill 5 According to the principle of conservation of energy, the heat entering the coal mill is equal to the heat exiting the coal mill, namely:
q gz +q lf +q nm +q r ＝q z +q jr +q 2 +q 5 ；(5-1)
unfolding the formula 5-1, and finishing to obtain:
wherein:
m m real-time output is provided for the coal mill; m is f The air quantity is the inlet air quantity of the coal mill; w is the power consumed by the coal mill; t is t 1 Is the temperature of the inlet primary air; t is t 2 The temperature of the outlet air of the coal mill; t is t A Is ambient temperature; c 1 The mass ratio of the drying agent at the inlet of the mill is heat; c 2 The mass specific heat of the grinding outlet drying agent; c rd Is the dry basis specific heat of the coal; c lk The mass specific heat of cold air; k lf The air leakage coefficient of the coal mill; r 90 Is the fineness of the coal powder; q 5 The total heat dissipation loss of the pulverizing system; k nm The coefficient of the grinding power converted into heat;
in the above formula M ar Is an unknown number unique to the left and right sides of the equation by assuming M ar0 Continuously enabling the values of the left side and the right side of the square equation to approach continuously, and finally calculating to obtain the received base moisture M of each coal mill of the coal mills ar 。
As a preferred technical solution, the step 5.2 specifically comprises:
step 5.2.1, the total heat absorption capacity of the working medium in the boiler is as follows:
Q boiler ＝G ms (h ms -h fw )+G rc (h rh -h rc )+G rj (h rh -h rj )+G sj (h ms -h sj )
in the formula G ms Main steam flow, h ms Is the main steam enthalpy, h fw Enthalpy of main feed water, G rc For cold reflow, h rh For the enthalpy of the hot end of the reheated steam, h rc For reheat steam cold end enthalpy, G rj Amount of desuperheating water for reheater, h rj For reducing the enthalpy of water for reheaters, G sj The amount of water sprayed for reducing the temperature of the superheater h sj Spraying water enthalpy for reducing the temperature of the superheater;
step 5.2.2, setting initial boiler efficiency eta 0 ；
Step 5.2.3, calculating the initial value Q of the low calorific value of the coal as fired of the boiler at the moment ar0 ：
In the formula (I), the compound is shown in the specification,
G coal the coal quantity of the boiler is the sum of the coal quantities of all the running coal mills in the direct-fired pulverizing system;
and 5.2.4, according to the substance balance and the coal combustion chemical analysis principle, expressing various gases generated by coal combustion into an equation of dry ashless base element content:
C daf ＝53.59γ co2 (V RO2,daf +V N2,daf +V O2,daf )+(1-γ CO2 )X cucr
S daf ＝142.86γ so2 (V RO2,daf +V N2,daf +V O2,daf )
O daf ＝k 1 C daf +k 2
N daf ＝k 3 H daf
C daf +H daf +O daf +N daf +S daf ＝100
V RO2,daf ＝0.01866(C daf +0.375S daf )-0.01866X cucr
V gk,daf ＝0.0889(C daf +0.375S daf )+0.265H ar -0.0333O ar -0.0889X cucr
C cucr ＝α fh C fh +α lz C lz
Q ar ＝339C ar +1028H ar -109(O ar -S ar )-25M ar
in the formula:
k 1 、k 2 、k 3 the correlation coefficient of the dry ash-free base component is obtained by fitting according to a large number of different coal types; c cucr Average unburned carbon content in the slag; gamma ray CO2 、γ SO2 、γ O2 The gas volume fraction in the smoke exhaust gas is shown; c daf 、 H daf 、O daf 、N daf 、S daf Is a dry ash-free base element component of coal; c ar 、H ar 、O ar 、N ar 、S ar Is the received base element component of the coal; v RO2,daf 、V N2,daf 、V O2,daf Various standard gas amounts calculated on a dry basis; alpha is the excess air factor;
is the volume fraction of oxygen in air; x cucr Correction amount for burnout carbon loss; alpha (alpha) ("alpha") fh ，α lz As a share of ash and slag; c fh ，C lz Carbon content of fly ash and slag;
step 5.2.5, solving the equation set in the step 5.2.4 to obtain a low calorific value Q of the coal as fired ar And receiving the elemental components of the base;
step 5.2.6, calculating the boiler efficiency, wherein the carbon content of the fly ash and the carbon content of the slag are calculated according to the step 4; the coal quality data used by the boiler efficiency is calculated in the step 5.2.3 to the step 5.2.5;
step 5.2.7, returning to step 5.2.3 for iterative calculation of coal quality data according to the calculated boiler efficiency until the lower calorific value Q in the coal quality data calculated in step 5.2.5 ar And the lower calorific value Q calculated in the step 5.2.3 ar0 Is less than a certain value:
as a preferred technical solution, the step6 specifically includes:
the calculation formula is as follows:
E r ＝FCc×C ar,c ×OF C ×44/12
wherein:
E r carbon emission intensity for generating power in real time by the unit;
FC C real-time coal quantity for unit coal burning;
C ar,c the content of the received base carbon element in the coal element analysis is shown;
O FC carbon oxidation rate of the fuel coal;
44/12 is the ratio of the relative molecular masses of the two species CO2 and C;
because the carbon oxidation rates of different coal types are different, the formula calculates:
wherein:
G lz the slag yield per hour;
G fh fly ash yield per hour;
C lz the carbon content of the slag is obtained;
C fh the carbon content of fly ash;
η cc the average dust removal efficiency of the dust removal system is obtained;
wherein G is lz And G fh Firstly, determining a coefficient k according to the ratio of the annual slag and fly ash yield and the annual power generation lz And k fh The real-time calculation is performed according to the current generator power, and the calculation formula is as follows:
and performing linear fitting on the hour statistical data under different generator powers to obtain a calculated value, namely:
G lz ＝k lz ×Pe
G fh ＝k fh ×Pe
where Pe is the generator power.
Compared with the prior art, the invention has the following advantages:
1) The invention also has reliable means to further accurately master the real-time carbon emission data of various coal-blending coal electric units under the condition that the characteristics of the fire coal are changed in real time.
2) Furthermore, the real-time carbon emission is controlled by a scientific and effective technical means, and a foundation is laid for the early realization of a double-carbon target.
3) With the continuous opening of the carbon trading market, the real-time, accurate and continuous monitoring of the carbon emission is a key factor for realizing the accurate control of the unit carbon emission in the future, and has a very important effect on improving the intelligent management level and the operational benefit of the coal power enterprises.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of the present invention.
With the definition of the national dual-carbon target policy and the continuous development of the future carbon trading market, the control of the carbon emission in the coal and electricity industry gradually becomes a very important and difficult task, and the coal and electricity enterprises are confronted with the dilemma of the power generation cost to cause the characteristics of the currently combusted coal to change greatly, so that the accurate calculation of the carbon emission of a unit under the unit power generation capacity under the existing conditions also becomes a very difficult subject. In the future, with the continuous opening of the carbon trading market, the real-time, accurate and continuous monitoring of the carbon emission is a key factor for realizing the accurate control of the carbon emission of the unit in the future, and has a very important role in improving the intelligent management level and the operational benefits of coal and electricity enterprises.
As shown in fig. 1, a coal-electric machine set real-time carbon emission monitoring method based on coal quality soft measurement is used for accurately monitoring real-time carbon emission data of various coal-mixed coal-electric machine sets, and the method includes the following steps:
step1 data collection:
1.1, acquiring and calculating related data through a real-time data interface, wherein the acquisition frequency is 1 time in 1 minute, and main data sources comprise the air quantity, the coal quantity and the air temperature of an inlet and an outlet of a coal mill; inlet and outlet parameters (temperature, pressure, flow) of the turbine thermodynamic system; the boiler efficiency calculates the needed real-time parameters (such as oxygen quantity and exhaust gas temperature) and the fly ash carbon content neural network forecast input parameters.
Step2 data cleaning and preprocessing:
2.1 interpolation;
2.2 repeating data check;
2.3 range checking;
2.4, checking the precision;
2.5 parameter identification
Step3 unit stable working condition judgment
Especially when the unit power changes greatly, due to the influence of greatly increasing and decreasing the coal quantity, the calculation result of the low-level calorific value of the coal quality is inaccurate, and therefore, the deviation of the calculation result caused by the large fluctuation of the unit power is avoided through a unit stable working condition judgment calculation method.
Step4, establishing a fly ash slag carbon content neural network prediction model, and predicting the ash content through soft measurement
Step5, establishing a coal quality soft measurement model:
5.1 received base moisture monitoring based on coal mill operating conditions.
5.2 Low-level heating value of coal as fired and element analysis monitoring (iterative computation)
Step6 real-time carbon emission calculation
Step1 data Collection
And (3) establishing a calculation model by taking variables related in the real-time carbon emission calculation formula as the basis, and integrating data of relevant indexes in the real-time database.
The principle of energy balance of the inlet and the outlet of the coal mill is used in the calculation of the coal moisture, and related data mainly comprise real-time output, inlet air quantity, power, inlet and outlet air temperature and environment temperature of each coal mill.
And calculating the oxygen quantity at the outlet of the economizer, the smoke discharge temperature and the air leakage rate required by the real-time boiler efficiency.
Calculating main steam flow, main steam pressure, main steam temperature, main water supply pressure, main water supply temperature, cold re-flow, reheated steam hot end pressure, reheated steam hot end temperature, reheated steam cold end pressure, reheated steam cold end temperature, reheater desuperheating water quantity, reheater desuperheating water pressure, reheater desuperheating water temperature, superheater desuperheating water spray quantity, superheater desuperheating water spray pressure, superheater desuperheating water spray temperature, boiler coal real-time consumption and unit current load.
The fly ash carbon content prediction model requires unit operation data such as coal low heating value, coal moisture, coal ash content, coal quantity of each coal mill, primary air quantity, outlet air temperature, main feed water flow, air preheater inlet flue gas temperature, total primary air quantity, total secondary air quantity, total air quantity and SCR inlet oxygen quantity.
Step2 data preprocessing
The collected data is subjected to validity check and preprocessing by adopting a data processing technology, so that the accuracy, validity and stability of the data are ensured. Meanwhile, the data cleaning service has an error data replacement function, and fault data is replaced by some mode (such as data combination, data interpolation, data rearrangement, data replacement and the like). The data collected by the measuring points can be cleaned in the following modes according to different types of data:
2.1 interpolation: for the data missing situation, interpolation processing needs to be performed on the missing value according to the set target value or the historical optimal value, and the target value or the historical optimal value is inserted into the corresponding attribute of the measuring point where the data is missing;
2.2, repeating data checking: directly judging whether the acquired data is repeated or not according to an agreed repeated data judgment principle, and directly discarding the repeated data if the acquired data is the repeated data;
2.3 range check: directly judging the upper limit and the lower limit of the operation parameters, and judging that the operation parameters exceed the upper limit and the lower limit as bad points;
2.4 precision checking: determining a reference curve of the operation parameters, judging the actual parameters by taking the reference curve as a standard, and judging that the measuring point is a bad point according to the measuring point value of which the data precision does not conform to the actual operation working condition;
2.5 parameter identification: and establishing a normal state matrix model of certain key parameters such as the post-regulation temperature and the like, and finding out the correlation degree of actual data and normal data on the basis of the normal state matrix when the model inputs actual operation parameters so as to perform parameter identification on the normal expected value of the actual operation data.
Step3 unit stable working condition judgment
In the actual real-time program calculation process, the stable working condition can be judged by a moving average variance calculation method, and the judgment method comprises the following steps:
wherein, P 1 ,...,P 10 Represents the unit power value, fc, of the first 10 minutes with a frequency interval of 1 minute under the current operating conditions 1 ,...,Fc 10 Representing the total coal quantity value of the first 10 minutes with a frequency interval of 1 minute under the current working condition, P avg Represents the average of the first 10 ten minute power of the stack, hence Fc avg Represents the average, σ, of the total coal amounts in the first 10 minutes P The square error allowed by the unit power under the stable working condition is represented, and the value in the system is 20, sigma Fc Mean square error system representing allowable total coal amount under stable working conditionThe system value is 20. Under the condition that the formulas 3-2 and 3-3 are simultaneously met, the running data of the first 10 minutes which meets the acquisition requirement under the current working condition is averaged, and then the numerical calculation is carried out in the calculation model, so that the condition that the deviation of the calculation result is large due to large load or coal quantity change in the calculation process is avoided.
Prediction model for carbon content of Step4 fly ash slag
The measurement error of the fly ash slag carbon content online measurement device of the existing unit is large, but the real-time value of the fly ash slag is an indispensable variable for the calculation of carbon emission, so that the method adopts a deep neural network algorithm in combination with test and daily test data to carry out prediction modeling and online prediction of the average carbon content of the slag. DNN model training is a process of supervised learning based on a loss function (loss function), which is generally defined as a mean square error function for a regression model. In order to accelerate the training efficiency of the DNN model, a Batch-based training mode is used in the training process, that is, when calculating the loss function value and performing gradient back-pass, the loss function value is calculated according to part of the training set data instead of calculating all samples in the training set.
Sample input and output variables are as follows:
the process of solving the weight and the bias generally adopts a gradient descent algorithm, and meanwhile, some optimization algorithms such as Adam optimization algorithm can be adopted aiming at the problems of self-adaptive adjustment of the learning rate and local extremum. The network structure of the model is 25-100-1, namely 49 input nodes, 100 hidden nodes and 1 output node.
Step5 coal quality soft measurement
5.1 moisture content of coal charged into furnace
The coal pulverizer is the main equipment of coal pulverizing system, and the coal quality and the drying of raw coal all go on in the coal pulverizer, and the heat that gets into the coal pulverizer includes: physical heat of desiccant q gz Physical heat q of cold air leaking in lf Heat q generated from the polishing member nm And physical heat of raw coal q r The heat exiting the coal mill comprises: heat of evaporation of water q z Heat quantity q consumed by heating fuel jr Heat q of the drying agent carrying out of the system 2 And heat dissipation loss q of coal mill 5 According to the principle of conservation of energy, the heat entering the coal mill is equal to the heat flowing out of the coal mill, namely:
q gz +q lf +q nm +q r ＝q z +q jr +q 2 +q 5 ；(5-1)
unfolding the formula 5-1, and finishing to obtain:
wherein:
m m -real-time output of the coal mill, t/h;
m f -coal mill inlet air volume, t/h;
w-power consumed by the coal pulverizer, kW;
t 1 -inlet primary air temperature, ° c;
t 2 -coal mill outlet air temperature, deg.c;
t A -ambient temperature, ° c;
C 1 mass specific heat of the mill inlet desiccant, kJ/(kg ℃);
C 2 mass specific heat of the drying agent at the outlet of the mill, kJ/(kg ℃);
C rd -the dry basis specific heat of the coal, kJ/(kg ℃);
C lk -mass specific heat of cold air, kJ/(kg ℃);
K lf -air leakage factor of the coal mill;
R 90 -coal fines fineness;
Q 5 -total heat dissipation loss of the pulverizing system, kW;
K nm -the coefficient of the conversion of mill power into heat;
in the above formula M ar Is an unknown number unique to the left and right sides of the equation by assuming M ar0 Continuously enabling the values of the left side and the right side of the square equation to approach continuously, and finally calculating to obtain the received base moisture M of each coal mill of the coal mills ar 。
5.2 Low-level calorific power of as-fired coal and element analysis monitoring
5.2.1 the total heat absorption of the working medium in the boiler is as follows:
Q boiler ＝G ms (h ms -h fw )+G rc (h rh -h rc )+G rj (h rh -h rj )+G sj (h ms -h sj )
in the formula G ms Main steam flow, h ms Is the main steam enthalpy, h fw Enthalpy of main feed water, G rc For cold re-flow, h rh For the enthalpy of the hot end of the reheated steam, h rc For reheat steam cold end enthalpy, G rj Amount of desuperheating water for reheater, h rj For reheaters to reduce water enthalpy, G sj The amount of water sprayed for reducing the temperature of the superheater h sj Spraying water enthalpy for reducing the temperature of the superheater.
5.2.2 setting the initial boiler efficiency η 0
5.2.3 calculating the initial value Q of the low calorific value of the coal as fired of the boiler at the moment ar0 ：
In the formula:
G coal the coal charge of the boiler is the sum of the coal quantities of all the running coal mills in the case of the direct-fired pulverizing system.
5.2.4 according to the principle of material balance and coal combustion chemical analysis, various gases generated by coal combustion are expressed as an equation of dry ashless element content:
C daf ＝53.59γ co2 (V RO2,daf +V N2,daf +V O2,daf )+(1-γ CO2 )X cucr
S daf ＝142.86γ so2 (V RO2,daf +V N2,daf +V O2,daf )
O daf ＝k 1 C daf +k 2
N daf ＝k 3 H daf
C daf +H daf +O daf +N daf +S daf ＝100
V RO2,daf ＝0.01866(C daf +0.375S daf )-0.01866X cucr
V gk,daf ＝0.0889(C daf +0.375S daf )+0.265H ar -0.0333O ar -0.0889X cucr
C cucr ＝α fh C fh +α lz C lz
Q ar ＝339C ar +1028H ar -109(O ar -S ar )-25M ar
in the formula:
k 1 、k 2 、k 3 -dry ashless basis component correlation coefficients are fitted from a large number of different coal types;
C cucr -average unburned carbon content in the slag,%;
γ CO2 、γ SO2 、γ O2 -gas volume fraction in the exhaust fumes;
C daf 、H daf 、O daf 、N daf 、S daf -dry ashless elemental constituents of the coal,%;
C ar 、H ar 、O ar 、N ar 、S ar -the composition of the received base elements of the coal,%;
V RO2,daf 、V N2,daf 、V O2,daf -the amount of each standard gas calculated on dry basis; m3/kg;
α -excess air ratio;
X cucr -correction of burnout carbon loss;
α fh ，α lz -ash and slag fraction,%;
C fh ，C lz -carbon content of fly ash and cinders,%;
5.2.5 solving the equation set in item 5.2.4 to obtain the lower calorific value Q of the coal as fired ar And receiving the elemental composition of the base.
5.2.6 the boiler efficiency can be calculated according to GB10184-2015 'Power station boiler performance test regulations', wherein the carbon content of fly ash and the carbon content of slag are calculated according to the Step 4. The coal quality data for boiler efficiency was calculated from items 5.2.3-5.2.5.
5.2.7 returns to the 5.2.3 th iteration to calculate coal quality data according to the calculated boiler efficiency until the lower calorific value Q in the 5.2.5 th iteration ar Lower calorific value Q calculated in item 5.2.3 ar The difference of 0 is less than a certain value:
step6 real-time carbon emission calculation
6.1 carbon emission calculation formula
According to "method for accounting for greenhouse gas emissions from enterprises and reporting guidelines for power generation facilities (revised 2022)", it is pointed out that the main factor considered when calculating carbon emission characteristics of power generation enterprises is fossil fuel combustion emissions (Er), and the calculation formula is as follows:
E r ＝FCc×C ar,c ×OF C ×44/12
wherein:
E r carbon emission intensity for real-time power generation of unit
FC C Real-time coal quantity, t/h, for units firing coal
C ar,c For the received base carbon element content in the coal element analysis%
O FC Is the carbon oxidation rate of the coal, is%
44/12 is the ratio of the relative molecular masses of the two CO2 and C species
Since the carbon oxidation rates of different coal species are different, the greenhouse gas emission accounting and reporting adopted herein requires section 1: the power generation enterprise (GB/T32151.1-2015) formula calculates:
wherein:
G lz the slag yield per hour, t/h
G fh Fly ash yield per hour, t/h
C lz Is the carbon content of the slag%
C fh Is the carbon content of fly ash%
η cc For the average dust removal efficiency of the dust removal system%
Wherein G is lz And G fh Firstly, determining a coefficient k according to the ratio relation of the annual slag and fly ash yield (t) and the annual power generation (MWh) lz And k fh The real-time calculation is performed according to the current generator power, and the calculation formula is shown in the following figure:
and performing linear fitting on the hour statistical data under different generator powers to obtain a calculated value, namely:
G lz ＝k lz ×Pe
G fh ＝k fh ×Pe
pe is the generator power, MW
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A coal electric unit real-time carbon emission monitoring method based on coal quality soft measurement is characterized in that the method is used for accurately monitoring real-time carbon emission data of various coal-blended coal electric units, and the monitoring method comprises the following steps:
step1, collecting data;
step2, data cleaning and preprocessing;
step3, judging the stable working condition of the unit;
step4, establishing a fly ash slag carbon content neural network prediction model, and predicting the ash content through soft measurement;
step5, establishing a coal quality soft measurement model;
and 6, calculating the carbon emission in real time.
2. The coal electric machine set real-time carbon emission monitoring method based on coal quality soft measurement according to claim 1, wherein the step1 specifically comprises: collecting and calculating related data through a real-time data interface;
wherein said collecting computational-related data comprises:
(a) Calculating data related to coal moisture, including real-time output, inlet air quantity, power, inlet and outlet air temperature and environment temperature of each coal mill;
(b) Calculating the oxygen quantity at the outlet of the economizer, the smoke exhaust temperature and the air leakage rate required by the real-time boiler efficiency;
(c) Calculating data related to the coal quality heat value, wherein the data comprises main steam flow, main steam pressure, main steam temperature, main water supply pressure, main water supply temperature, cold and re-flow, reheat steam hot end pressure, reheat steam hot end temperature, reheat steam cold end pressure, reheat steam cold end temperature, reheater desuperheating water volume, reheater desuperheating water pressure, reheater desuperheating water temperature, superheater desuperheating water spray volume, superheater desuperheating water spray pressure, superheater desuperheating water spray temperature, boiler coal-fired real-time consumption and unit current load;
(d) The unit operation data required by the fly ash carbon content prediction model comprises low-grade calorific value of coal, coal moisture, coal ash content, coal quantity of each coal mill, primary air quantity, outlet air temperature, main water supply flow, inlet flue gas temperature of an air preheater, total primary air quantity, total secondary air quantity, total air quantity and SCR inlet oxygen quantity.
3. The coal electric machine set real-time carbon emission monitoring method based on coal quality soft measurement according to claim 1, wherein the step2 specifically comprises the following steps:
step 2.1, interpolation: for the data missing condition, interpolation processing is required to be carried out on the missing value according to the set target value or the historical optimal value, and the target value or the historical optimal value is inserted into the corresponding attribute of the measuring point with the data missing;
step 2.2, repeating data checking: directly judging whether the acquired data is repeated or not according to an agreed repeated data judgment principle, and directly discarding the repeated data if the acquired data is the repeated data;
step 2.3, range checking: directly judging the upper limit and the lower limit of the operation parameters, and judging that the operating parameters exceeding the upper limit and the lower limit are dead spots;
step 2.4, precision checking: determining a reference curve of the operation parameters, judging the actual parameters by taking the reference curve as a standard, and judging that the measuring point is a bad point according to the measuring point value of which the data precision does not conform to the actual operation working condition;
step 2.5, parameter identification: and establishing a normal state matrix model of the parameters, and when the model inputs actual operation parameters, finding out the correlation degree of the actual data and the normal data on the basis of the normal state matrix so as to perform parameter identification on the normal expected value of the actual operation data.
4. The coal electric unit real-time carbon emission monitoring method based on coal quality soft measurement according to claim 1, wherein the stable working condition is judged by a moving average variance-finding method in step3, and the method specifically comprises the following steps:
wherein, P 1 ,...,P 10 To the current working conditionThe unit power value, fc, of the first 10 minutes with a frequency interval of 1 minute 1 ,...,Fc 10 Representing the total coal quantity value of the first 10 minutes with a frequency interval of 1 minute under the current working condition, P avg Represents the average value of the first 10 ten minute power of the cell, fc avg Represents the average, σ, of the total coal amounts in the first 10 minutes P Expressing the permissible squared difference, sigma, of the power of the unit under stable conditions Fc Representing the square error allowed by the total coal quantity under the stable working condition; under the condition that the formulas 3-2 and 3-3 are met simultaneously, the operation data of the first 10 minutes which meet the acquisition requirement under the current working condition are averaged, and then the numerical calculation is carried out in the calculation model, so that the condition that the calculation result deviation is large due to large load or coal quantity change in the calculation process is avoided.
5. The coal electric unit real-time carbon emission monitoring method based on the coal quality soft measurement as claimed in claim 1, wherein the step4 is to use a deep neural network algorithm to perform prediction modeling and online prediction of average carbon content of ash slag, and to perform the calculation of the loss function value according to part of training set data.
6. The coal electric unit real-time carbon emission monitoring method based on the coal quality soft measurement as claimed in claim 5, characterized in that sample input and output variables of the deep neural network algorithm are as shown in the following table:
the network structure of the deep neural network algorithm model is 25-100-1, namely 49 input nodes, 100 hidden nodes and 1 output node; a gradient descent algorithm is adopted in the process of solving the weight and the bias, and an Adam optimization algorithm is adopted for the self-adaptive adjustment of the learning rate and the problem of local extremum.
7. The coal electric machine set real-time carbon emission monitoring method based on coal quality soft measurement according to claim 1, wherein the step5 specifically comprises:
step 5.1, calculating the received base moisture of each coal mill based on the running state of the coal mill;
and 5.2, analyzing and monitoring the low-level calorific value and elements of the coal as fired.
8. The coal electric machine set real-time carbon emission monitoring method based on coal quality soft measurement according to claim 7, characterized in that the step 5.1 specifically comprises:
the heat entering the coal mill comprises: physical heat of desiccant q gz Physical heat q of cold air leaking in lf Heat q generated by the polishing member nm And physical heat of raw coal q r (ii) a The heat exiting the coal mill comprises: heat of evaporation of water q z Heat quantity q consumed by heating fuel jr Heat q of the desiccant carrying-out system 2 And heat dissipation loss q of coal mill 5 According to the principle of conservation of energy, the heat entering the coal mill is equal to the heat exiting the coal mill, namely:
q gz +q lf +q nm +q r ＝q z +q jr +q 2 +q 5 ； (5-1)
unfolding the formula 5-1, and finishing to obtain:
wherein:
m m real-time output is provided for the coal mill; m is f The air quantity is the inlet air quantity of the coal mill; w is the power consumed by the coal mill; t is t 1 Is the temperature of the primary air at the inlet; t is t 2 The outlet air temperature of the coal mill is measured; t is t A Is ambient temperature; c 1 The mass specific heat of the drying agent at the inlet of the mill; c 2 The mass specific heat of the grinding outlet drying agent; c rd Is the dry basis specific heat of the coal; c lk The mass specific heat of cold air; k lf The air leakage coefficient of the coal mill is obtained; r 90 Is the fineness of the coal powder; q 5 The total heat dissipation loss of the pulverizing system; k nm The coefficient of the grinding power converted into heat;
m in the above formula ar Is an unknown number unique to the left and right sides of the equation by assuming M ar0 Continuously enabling values of the left side and the right side of the equation to approach continuously, and finally calculating to obtain the received base moisture M of each coal mill of the coal mills ar 。
9. The coal electric machine set real-time carbon emission monitoring method based on coal quality soft measurement according to claim 7, wherein the step 5.2 specifically comprises:
step 5.2.1, the total heat absorption capacity of the working medium in the boiler is as follows:
Q boiler ＝G ms (h ms -h fw )+G rc (h rh -h rc )+G rj (h rh -h rj )+G sj (h ms -h sj )
in the formula G ms Main steam flow, h ms Is the main steam enthalpy, h fw Enthalpy of main feed water, G rc For cold re-flow, h rh For the enthalpy of the hot end of the reheated steam, h rc For reheat steam cold end enthalpy, G rj Amount of desuperheating water for reheater, h rj For reducing the enthalpy of water for reheaters, G sj The amount of water sprayed for reducing the temperature of the superheater h sj Spraying water enthalpy for reducing the temperature of the superheater;
step 5.2.2, setting initial boiler efficiency eta 0 ；
Step 5.2.3, calculating the initial value Q of the low calorific value of the coal as fired of the boiler at the moment ar0 ：
In the formula (I), the compound is shown in the specification,
G coal the coal quantity of the boiler is the sum of the coal quantities of all the running coal mills in the direct-fired pulverizing system;
and 5.2.4, expressing various gases generated by coal combustion into an equation of dry ashless element content according to the substance balance and the coal combustion chemical analysis principle:
C daf ＝53.59γ co2 (V RO2,daf +V N2,daf +V O2,daf )+(1-γ CO2 )X cucr
S daf ＝142.86γ so2 (V RO2,daf +V N2,daf +V O2,daf )
O daf ＝k 1 C daf +k 2
N daf ＝k 3 H daf
C daf +H daf +O daf +N daf +S daf ＝100
V RO2,daf ＝0.01866(C daf +0.375S daf )-0.01866X cucr
V gk,daf ＝0.0889(C daf +0.375S daf )+0.265H ar -0.0333O ar -0.0889X cucr
C cucr ＝α fh C fh +α lz C lz
Q ar ＝339C ar +1028H ar -109(O ar -S ar )-25M ar
in the formula:
k 1 、k 2 、k 3 the correlation coefficient of the dry ash-free base component is obtained by fitting according to a large number of different coal types; c cucr Average unburned carbon content in the slag; gamma ray CO2 、γ SO2 、γ O2 The gas volume fraction in the smoke exhaust gas is shown; c daf 、H daf 、O daf 、N daf 、S daf Is a dry ash-free base element component of coal; c ar 、H ar 、O ar 、N ar 、S ar Is the received base element composition of the coal; v RO2,daf 、V N2,daf 、V O2,daf Various standard gas amounts calculated on a dry basis; alpha is the excess air factor;
is the volume fraction of oxygen in air; x cucr Correction for burnout carbon loss; alpha is alpha fh ，α lz As a share of ash and slag; c fh ，C lz Carbon content of fly ash and slag;
step 5.2.5, solving the equation set in the step 5.2.4 to obtain a low calorific value Q of the coal as fired ar And receiving the elemental composition of the base;
step 5.2.6, calculating the boiler efficiency, wherein the carbon content of the fly ash and the carbon content of the slag are calculated according to the step 4; the coal quality data used by the boiler efficiency is calculated in the step 5.2.3 to the step 5.2.5;
step 5.2.7, returning to step 5.2.3 for iterative calculation of coal quality data according to the calculated boiler efficiency until the coal quality data calculated in step 5.2.5Lower calorific value Q ar And the lower calorific value Q calculated in the step 5.2.3 ar0 Is less than a certain value:
10. the coal electric machine set real-time carbon emission monitoring method based on coal quality soft measurement according to claim 7, wherein the step6 specifically comprises:
the calculation formula is as follows:
E r ＝FCc×C ar,c ×OF C ×44/12
wherein:
E r the carbon emission intensity of the unit for real-time power generation;
FC C real-time coal quantity for unit coal burning;
C ar,c the content of the received base carbon element in the coal element analysis is shown;
O FC carbon oxidation rate of the fuel coal;
44/12 is the ratio of the relative molecular masses of the two species CO2 and C;
because the carbon oxidation rates of different coal types are different, the formula calculates:
wherein:
G lz the slag yield per hour;
G fh fly ash yield per hour;
C lz the carbon content of the slag;
C fh the carbon content of fly ash;
η cc the average dust removal efficiency of the dust removal system is obtained;
wherein G lz And G fh Is calculated first based on the annual slag and fly ash production statistics and the annualDetermination coefficient k of specific relation of power generation amount lz And k fh The real-time calculation is performed according to the current generator power, and the calculation formula is as follows:
and performing linear fitting on the hour statistical data under different generator powers to obtain a calculated value, namely:
G lz ＝k lz ×Pe
G fh ＝k fh ×Pe
where Pe is the generator power.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211014212.6A CN115656461A (en) | 2022-08-23 | 2022-08-23 | Coal electric unit real-time carbon emission monitoring method based on coal quality soft measurement |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211014212.6A CN115656461A (en) | 2022-08-23 | 2022-08-23 | Coal electric unit real-time carbon emission monitoring method based on coal quality soft measurement |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115656461A true CN115656461A (en) | 2023-01-31 |
Family
ID=85024502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211014212.6A Pending CN115656461A (en) | 2022-08-23 | 2022-08-23 | Coal electric unit real-time carbon emission monitoring method based on coal quality soft measurement |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115656461A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116151134A (en) * | 2023-04-23 | 2023-05-23 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Carbon dioxide emission metering method |
-
2022
- 2022-08-23 CN CN202211014212.6A patent/CN115656461A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116151134A (en) * | 2023-04-23 | 2023-05-23 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Carbon dioxide emission metering method |
| CN116151134B (en) * | 2023-04-23 | 2023-07-18 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Carbon dioxide emission metering method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1841422B (en) | Use the method and apparatus that the operation of artificial intelligence technology to generating plant is optimized | |
| WO2005083447A1 (en) | On-line monitoring method and device for a fossil fuel converter apparatus | |
| CN103759277A (en) | Intelligent soot blowing closed-loop control method, device and system for coal-fired power station boiler | |
| CN111695249B (en) | Prediction method for heat efficiency of gas boiler | |
| CN104008297A (en) | Method for calculating thermal efficiency of coal dust and blast furnace gas co-combustion boiler | |
| CN103697946A (en) | Method for calculating flue gas flow of coal-fired boiler in heat-engine plant and method for controlling pollutant discharge amount | |
| CN109523180B (en) | Coal consumption and heat supply online monitoring system of thermal power plant | |
| CN106768068A (en) | Fired power generating unit fire coal calorific value and consumption of standard coal for power generation index on-line monitoring system and method | |
| CN110263452B (en) | Flue gas time distribution characteristic analysis method and system in flue and denitration system | |
| CN111754093A (en) | Fly ash carbon content prediction method based on coal quality prediction and PSO-SVM | |
| CN107831651A (en) | Coal dust station boiler SCR and SNCR denitration system cooperative control method | |
| CN103208035A (en) | Energy-saving dispatching optimization method for sets | |
| CN104075341A (en) | Low-nitrogen combustion control method and system based on feedback | |
| CN115656461A (en) | Coal electric unit real-time carbon emission monitoring method based on coal quality soft measurement | |
| CN108197723B (en) | Optimized energy-saving scheduling method for coal consumption and pollutant discharge of coal-electricity unit power supply | |
| US7398652B1 (en) | System for optimizing a combustion heating process | |
| CN108021027B (en) | Output power prediction system and method for supercritical circulating fluidized bed unit | |
| CN1771439B (en) | On-line monitoring method for a fossil fuel converter apparatus | |
| CN117350458A (en) | Thermal power generating unit carbon emission analysis method based on-line monitoring | |
| Dong et al. | Evaluation of TPGU using entropy-improved TOPSIS-GRA method in China | |
| CN109655489B (en) | Method and device for metering standard coal consumption of coal-fired unit | |
| CN108875165B (en) | Boiler characteristic calibration method based on operation data | |
| CN112417684A (en) | Coal quality component dynamic calculation method for coal-fired unit | |
| Zheng et al. | Prediction of NOx concentration from coal combustion using LS-SVR | |
| CN112255978A (en) | Intelligent operation and maintenance system and method for coal-fired 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 |