CN113052391B - Boiler heating surface coking on-line prediction method - Google Patents
Boiler heating surface coking on-line prediction method Download PDFInfo
- Publication number
- CN113052391B CN113052391B CN202110381281.XA CN202110381281A CN113052391B CN 113052391 B CN113052391 B CN 113052391B CN 202110381281 A CN202110381281 A CN 202110381281A CN 113052391 B CN113052391 B CN 113052391B
- Authority
- CN
- China
- Prior art keywords
- boiler
- data
- coking
- database
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention belongs to the field of application of coal-fired boilers, and particularly relates to an on-line prediction method for coking of a heating surface of a boiler, which comprises the following steps: collecting related data of boiler operation; according to the boiler operation principle, encoding, classifying and modeling boiler operation data; establishing boiler non-coking training databases in different load intervals; cleaning data of a boiler non-coking training database; establishing boiler coking training databases in different load intervals, and cleaning data; establishing a boiler non-coking training model and a boiler coking training model; and predicting the coking state of the boiler based on the boiler operation mechanism and the big data model. The invention provides a system and a method for realizing on-line prediction of coking on a heating surface of a boiler during the operation of the boiler, which can avoid economic loss caused by coke falling of the boiler. The boiler is not required to be shut down in the online prediction, so that the power generation loss and the labor cost are reduced; the existing in-plant information system and data are utilized, and a detection device and additional hardware cost are not required to be newly added.
Description
Technical Field
The invention belongs to the field of application of coal-fired boilers, and particularly relates to an on-line prediction method for coking of a heating surface of a boiler.
Background
The coking problem of the heating surface of the coal-fired boiler of the thermal power generating unit is very common, and the main reasons are that the actual coal for burning of the power plant is different from the designed coal, and the actual operation working conditions such as load change and soot blowing investment are different from the designed working conditions. After the heating surface is coked, the heat exchange efficiency and the boiler operation economy are influenced on the one hand; on the other hand, coke falling easily occurs, a cold ash bucket or a slag conveyor at the bottom of the boiler is smashed to cause temperature and pressure fluctuation in the boiler, even blowing out is caused in severe cases, and the operation safety and stability of the boiler are seriously influenced.
At present, the on-line detection method for coking of the heating surface of the coal-fired power plant boiler mainly comprises the following steps: based on coal quality or coal ash chemical composition (parameters are difficult to obtain); based on the cleanliness of the heating surface in the furnace and the contamination coefficient (inaccurate, only has reference meaning); based on the temperature field in the furnace and the coal ash melting point (only the local area where the smoke temperature measuring point is installed can be measured); judging the coking thickness based on laser ranging (only the partial area covered by the fire hole of the water wall can be measured); an image in the furnace is restored based on an infrared camera and a CT reconstruction technology (the additional hardware cost is high, the influence of smoke dust in the furnace is large, and the algorithm accuracy is low). The detection can also be performed by an off-line method when the boiler is stopped, but the power generation loss and the labor cost are high.
The prior related patents, such as patent number CN201910232761.2, named "boiler coking early warning method based on convolutional neural network", have the following contents: the invention discloses a boiler coking early warning method based on a convolutional neural network, which comprises the following steps: 1) Acquiring data information of coking or non-coking in the boiler; 2) Selecting temperature data of a plurality of measuring points which are coked or not coked in the same time period from the data information in the step 1); 3) Constructing a coked or non-coked convolutional neural network model, which comprises the following steps: an input layer, a convolution layer, a down-sampling layer, a full-link layer and an output layer; 4) Randomly selecting a plurality of measuring point temperature data in the same time period from a boiler data source acquired in real time, inputting the coking or non-coking convolution neural network model in the step 3), obtaining the image characteristics of the measuring point temperature data, and judging the coking or non-coking.
In the invention patent CN201910232761.2 boiler coking early warning method based on convolutional neural network, the data information of coking or non-coking in the boiler is difficult to obtain, according to the method of the above patent, the data information of coking in the boiler can be obtained only after the boiler generates a coke dropping accident, and the coke dropping of the power plant belongs to a large accident, even if the coking is serious, the data information is generated twice a year. Secondly this method does not take into account the principle of boiler operation.
Disclosure of Invention
The method aims to solve the problems and provides the method for accurately, stably, low-cost and systematically realizing the on-line prediction of the coking of the heating surface of the boiler during the operation of the boiler.
In order to achieve the technical effects, the technical scheme protected by the application is as follows:
an on-line prediction method for boiler heating surface coking comprises the following steps:
step (1): collecting related data of boiler operation;
step (2): according to the boiler operation principle, encoding, classifying and modeling boiler operation data;
and (3): establishing boiler non-coking training databases in different load intervals according to the boiler operation principle;
and (4): according to the boiler operation principle, cleaning data of a boiler non-coking training database;
and (5): establishing boiler coking training databases in different load intervals, and cleaning data;
and (6): establishing a boiler non-coking training model and a boiler coking training model;
and (7): and predicting the coking state of the boiler based on the boiler operation mechanism and the big data model.
Further, in the step (1), the boiler operation-related data includes real-time operation data and historical operation data; the boiler operation related data includes, but is not limited to: boiler load, feed water flow, total primary air quantity, total coal quantity and coal quantity of each coal feeder, total secondary air quantity and secondary air quantity of each layer, burnout air quantity of each layer, primary and secondary air pressure, hearth negative pressure, coal quality and ash melting point of furnace entering, superheated steam temperature and pressure of each heating surface, reheated steam temperature and pressure, desuperheating water flow and temperature, smoke exhaust temperature, fly ash carbon content, smoke Component (CO)/H 2 S/O 2 ) And one or more of the alarm signals at all levels. In a practical boiler plant, due to cost and reliability considerations, the installed sensors are limited and typically only a portion of the operational data described above is available.
Further, in the step (1), the data related to the operation of the boiler is collected from various information systems of the power plant, wherein the various information systems include, but are not limited to, one or more of PLC, RTU, DCS, MIS, SIS and SCADA systems of the power plant.
The step (2) comprises the following specific steps:
step (2.1): establishing a boiler operation data classification principle according to a boiler operation principle and data importance;
step (2.2): according to the classification principle of the boiler operation data established in the step (2.1), marking the boiler operation data obtained in the step (1) with an important grade label: the label A1 represents the primary operation data with the highest importance level; the label A2 represents secondary operation data of the second importance level; the label A3 represents the three-level operation data with the lowest importance level;
step (2.3): according to the classification principle of the boiler operation data established in the step (2.1), marking the boiler operation data obtained in the step (2.2) with a class label: the label C1 represents basic operation data of the boiler, the label C2 represents primary air related data, the label C3 represents secondary air related data, the label C4 represents superheated steam related data, the label C5 represents reheated steam related data, and the label C6 represents a flue gas related database;
step (2.4): time stamping the boiler operation data obtained in the step (2.3);
step (2.5): and (3) encoding the boiler operation data obtained in the step (2.4), wherein the encoding rule is as follows: the method comprises the following steps of (1) power plant KKS code + important grade label + category label + time stamp + self-made check code;
step (2.6): at least 6 databases are created, respectively: a boiler basic operation database, a primary air related database, a secondary air related database, a superheated steam related database, a reheated steam related database and a flue gas related database;
step (2.7): and (3) respectively storing the boiler operation data obtained in the step (2.5) into corresponding databases established in the step (2.6) according to the class labels.
The step (3) is specifically as follows:
step (3.1): extracting data from the 6 boiler operation databases established in the step (2.7) and establishing a training database; the extraction rule is as follows: reading a boiler load value and a time stamp in a basic operation database of the boiler, selecting data that the boiler load stays at 90% -100% of rated load in a period of time (such as 1 hour or a user-defined period of time), and extracting all data of 6 databases in the period of time;
step (3.2): performing air balance calculation according to the boiler load, the fuel components, the air volume and the structure of the heating surface;
step (3.3): calculating the volume of the triatomic gases, the volume of the water vapor, the volume fraction and the enthalpy of the smoke and the air in each section of the flue;
step (3.4): calculating the enthalpy value of the flue gas at the outlet of the hearth according to the temperature of the flue gas, the temperature of the flue gas at the outlet of the economizer, the coal quantity, the air quantity, the flow of each heating surface and the temperature and pressure of steam at the inlet and the outlet;
step (3.5): calculating the average temperature ty of the flue gas at the outlet of the hearth and the average heat transfer coefficient h of the hearth l ；
The average temperature of the flue gas at the outlet of the hearth is calculated according to the following formula:
in the formula, T th Theoretical combustion temperature; x is the number of m Arranging a relative height for the burner; epsilon f syn The degree of blackness of the hearth; b is 0 Boltzmann feature numbers.
Average heat transfer coefficient h of hearth l The calculation steps are as follows: respectively calculating heat transfer coefficients of each convection heating surface and each radiation heating surface according to an industrial boiler design standard method, and calculating an average value according to a hearth structure;
step (3.6): and (3) calculating the confidence coefficient alpha of the boiler non-coking training database extracted in the step (3.1) according to the following formula:
in the formula, t y0 Is a design value of the average temperature h of the flue gas at the outlet of the furnace chamber l0 Average heat transfer coefficient h of furnace chamber l A design value;
step (3.7): if alpha is smaller than the non-coking confidence coefficient preset value, the extracted boiler non-coking training data is considered to be unreliable, the database is discarded, and re-extraction is carried out, wherein the non-coking confidence coefficient preset value can be set to be 0.7-1.0;
step (3.8): repeating the steps (3.1) - (3.7) until the confidence coefficient of the extracted boiler non-coking training data is greater than or equal to the preset value of the non-coking confidence coefficient;
step (3.9): and (3.1) repeating the steps (3.8), and respectively constructing an 80-90% rated load boiler non-coking training database, a 70-80% rated load boiler non-coking training database, a 60-70% rated load boiler non-coking training database and a 50-60% rated load boiler non-coking training database. Larger or smaller load intervals may also be used to build the database.
Further, the step (4) is specifically as follows:
step (4.1): setting the maximum value and the minimum value of all operation parameter checks of the boiler according to boiler design data, boiler user manuals, original boiler thermodynamic calculation data or other rules provided by a power plant, wherein the operation parameters comprise but are not limited to boiler load, feed water flow, total primary air quantity, total coal quantity and coal quantity of each coal feeder, total secondary air quantity and secondary air quantity of each layer, burnout air quantity of each layer, primary and secondary air pressure, hearth negative pressure, coal quality and ash melting point of entering boiler, superheated steam temperature and pressure of each heating surface, reheated steam temperature and pressure, desuperheating water flow and temperature, smoke temperature, fly ash carbon content and smoke component (CO/H) 2 S/O 2 ) One or more of;
step (4.2): comparing the data labeled C1 in the sub-database obtained in the step (3.9) with the set parameter verification minimum value and the set parameter verification maximum value in the step (4.1) one by one, reading the time stamp of the data if the data exceeds the set value range, and discarding all data corresponding to the time stamp in the sub-database obtained in the step (3.9);
step (4.3) comparing the data labeled C2, C3, C4, C5 and C6 in the sub-database obtained in step (4.2) with the set parameter check minimum value and the maximum value in step (4.1) one by one, and if a certain data value is smaller than the set minimum value, setting the data value as the set minimum value; if a certain data value is larger than the set maximum value, setting the certain data value as the set maximum value;
and (4.4) sequentially performing data cleaning and data filling on each column of the sub-database data table obtained in the step (4.3) by adopting the following formulas:
if(x ij -x iav >3x ierr ),x ij ＝x iav +3x ierr
if(x ij -x iav <-3x ierr ),x ij ＝x iav -3x ierr
in the formula, x ij J data which is ith data; x is a radical of a fluorine atom iav The average value of the ith column data; x is the number of ierr The standard deviation of the ith column data;
further, the step (5) is specifically:
step (5.1): inquiring the coke-dropping accident occurrence time according to the boiler operation ledger, backward pushing for 0.5-24 hours from the time, and extracting data from the 6 boiler operation databases established in the step (2.7);
step (5.2): reading the coal quality information in the step (5.1), and if the coal in the furnace is not changed, keeping all the data; if the quality of the coal entering the furnace changes, only the operation data of the last coal entering the furnace before the coke-dropping accident happens is reserved;
step (5.3): dividing the data obtained in the step (5.2) according to the load size, and constructing a 90-100% rated load boiler coking training database, an 80-90% rated load boiler coking training database, a 70-80% rated load boiler coking training database, a 60-70% rated load boiler coking training database and a 50-60% rated load boiler coking training database.
Further, the step (6) is specifically:
step (6.1): respectively constructing prediction models by using the data labeled A1, A2 and A3 in the boiler non-coking training database obtained in the step (4.4), and respectively obtaining non-coking analog characteristics of the data A1, A2 and A3;
step (6.2): and (5.3) respectively constructing prediction models by using the data labeled with A1, A2 and A3 in the boiler coking training database obtained in the step (5.3), and respectively obtaining coking analog characteristics of the data A1, A2 and A3.
The model building method of step (6) includes but is not limited to: decision trees, support vector machines, artificial neural networks (e.g., back-propagation neural networks, convolutional neural networks, hofield networks, boltzmann machines, deep belief networks).
Further, the step (7) is specifically:
step (7.1): extracting real-time operation data from the 6 boiler operation databases established in the step (2.7);
step (7.2): respectively sending the real-time operation data into the prediction model established in the step (6.1) according to the labels A1, A2 and A3 for calculation, and comparing the real-time operation data with the non-coking analog characteristics of the data A1, A2 and A3 obtained in the step (6.1) to obtain confidence coefficient alpha A1 、α A2 、α A3 And calculating the confidence coefficient of non-coking of the boiler:
α＝0.7α A1 +0.2α A2 +0.1α A3
in the formula, three coefficients of 0.7, 0.2 and 0.1 can be adjusted according to actual conditions, and the sum is 1.
Step (7.3): respectively sending the real-time operation data into the prediction model established in the step (6.2) according to the labels A1, A2 and A3 for calculation, and comparing the real-time operation data with the coking analogy characteristics of the data A1, A2 and A3 obtained in the step (6.2) to obtain confidence coefficient beta A1 、β A2 、β A3 And calculating boiler coking confidence:
β＝0.7β A1 +0.2β A2 +0.1β A3
in the formula, three coefficients of 0.7, 0.2 and 0.1 can be adjusted according to actual conditions, and the sum is 1.
Step (7.4): and comparing the boiler non-coking confidence coefficient alpha with the boiler coking confidence coefficient beta, and if alpha is less than beta and beta is greater than 0.5, determining that the boiler is high in coking risk.
Further, in the initial operating period of the boiler, if the data is insufficient, the step (7) is specifically:
step (7.1): and (4) extracting real-time operation data from the 6 boiler operation databases established in the step (2.7).
Step (7.2): performing air balance calculation according to the boiler load, the fuel components, the air volume and the structure of the heating surface;
step (7.3): calculating the volume of the triatomic gases, the volume of the water vapor, the volume fraction and the enthalpy of the smoke and the air in each section of the flue;
step (7.4): calculating the enthalpy value of the flue gas at the outlet of the hearth according to the temperature of the flue gas, the temperature of the flue gas at the outlet of the economizer, the coal quantity, the air quantity, the flow of each heating surface and the temperature and pressure of steam at the inlet and the outlet;
step (7.5): calculating the average temperature t of the flue gas at the outlet of the hearth y And average heat transfer coefficient h of furnace chamber l ；
Step (7.6): calculating the coking confidence coefficient of the boiler real-time operation data extracted in the step (7.1) according to the following formula:
in the formula, t y0 Is a design value of the average temperature h of the flue gas at the outlet of the furnace chamber l0 Average heat transfer coefficient h of furnace chamber l A design value;
step (7.7): if β >0.5 (or other values between 0.5 and 1.0) the risk of boiler coking is considered to be high.
The application has the advantages that:
1. the invention provides a system and a method for realizing on-line prediction of coking on a heating surface of a boiler during operation of the boiler, which can avoid economic loss caused by coke dropping of the boiler. The boiler does not need to be shut down in online prediction, so that the power generation loss and the labor cost are reduced; the existing in-plant information system and data are utilized, and a detection device and additional hardware cost are not required to be added. The method has large data volume, and long-term data acquisition and long-term online calculation are carried out instead of only data before and after coke dropping of the boiler. The boiler principle is considered, data are cleaned and preprocessed, and invalid data are removed. And the boiler thermodynamic calculation data is used for constraining the modeling and solving processes, so that the reliability of the solving result is higher.
2. Key parameters (such as coal quality and ash melting point) in a conventional coking prediction method are usually difficult to obtain, and the system and the method provided by the invention can still accurately predict the coking condition of the heating surface of the boiler under the condition that the available boiler operation parameters are limited.
3. The boiler coking prediction module provided by the invention integrates a boiler mechanism model and a big data deep learning model, and can realize boiler coking prediction by adopting the boiler mechanism model (on-line thermodynamic calculation of the boiler) under the condition that a data sample is insufficient at the initial operation stage of the boiler. After the boiler operates for a period of time, the accumulated big data is used for continuously training and optimizing the model in a rolling way, so that the accuracy of boiler coking prediction can be continuously improved.
4. The system and the method provided by the invention can obtain the pollution condition of the heating surface of the boiler, can be used for boiler coking prediction and can also be used for the optimization function of a boiler soot blowing system, reduce soot blowing abrasion of the tube wall and improve the operation economy of the soot blowing system.
5. The system and the method provided by the invention can be used for obtaining the boiler operation structured database, can be used for predicting boiler coking and can also be used for other boiler functions, such as four-pipe leakage detection and NO X Detection, air distribution adjustment and the like.
Drawings
FIG. 1 is a diagram of a prediction method according to the present invention.
Detailed Description
Referring to the attached figure 1 of the specification, the invention relates to an online prediction method for coking of a heating surface of a boiler, which comprises the following steps:
step (1): collecting related data of boiler operation;
step (2): according to the boiler operation principle, encoding, classifying and modeling the boiler operation data;
and (3): establishing boiler non-coking training databases in different load intervals according to the boiler operation principle;
and (4): according to the boiler operation principle, cleaning data of a boiler non-coking training database;
and (5): establishing boiler coking training databases in different load intervals, and cleaning data;
and (6): establishing a boiler non-coking training model and a boiler coking training model;
and (7): and predicting the coking state of the boiler based on the boiler operation mechanism and the big data model.
Further, in the step (1), the boiler operation related data comprises real-time operation data and historical operation data; the boiler operation related data includes, but is not limited to: boiler load, feed water flow, total primary air quantity, total coal quantity and coal quantity of each coal feeder, total secondary air quantity and secondary air quantity of each layer, burnout air quantity of each layer, primary and secondary air pressure, hearth negative pressure, coal quality and ash melting point of furnace entering, superheated steam temperature and pressure of each heating surface, reheated steam temperature and pressure, desuperheating water flow and temperature, smoke exhaust temperature, fly ash carbon content, smoke gas component (CO/H) 2 S/O 2 ) And one or more of the alarm signals at all levels. In a practical boiler plant, due to cost and reliability considerations, the installed sensors are limited and typically only a portion of the operational data described above is available.
Further, in the step (1), the data related to the operation of the boiler is collected from various information systems of the power plant, wherein the various information systems include, but are not limited to, one or more of PLC, RTU, DCS, MIS, SIS and SCADA systems of the power plant.
The step (2) comprises the following specific steps:
step (2.1): establishing a boiler operation data classification principle according to a boiler operation principle and data importance;
step (2.2): according to the classification principle of the boiler operation data established in the step (2.1), marking the boiler operation data obtained in the step (1) with an important grade label: the label A1 represents the primary operation data with the highest importance level; the label A2 represents secondary operation data of the second importance level; the label A3 represents three-level operation data with the lowest importance level;
step (2.3): according to the classification principle of the boiler operation data established in the step (2.1), marking the boiler operation data obtained in the step (2.2) with a class label: the label C1 represents basic operation data of the boiler, the label C2 represents primary air related data, the label C3 represents secondary air related data, the label C4 represents superheated steam related data, the label C5 represents reheated steam related data, and the label C6 represents a flue gas related database;
step (2.4): time stamping the boiler operation data obtained in the step (2.3);
step (2.5): and (3) encoding the boiler operation data obtained in the step (2.4), wherein the encoding rule is as follows: the method comprises the following steps of (1) power plant KKS code + important grade label + category label + time stamp + self-made check code;
step (2.6): at least 6 databases are created, respectively: a boiler basic operation database, a primary air related database, a secondary air related database, a superheated steam related database, a reheated steam related database and a flue gas related database;
step (2.7): and (3) respectively storing the boiler operation data obtained in the step (2.5) into corresponding databases established in the step (2.6) according to the class labels.
The step (3) is specifically as follows:
step (3.1): extracting data from the 6 boiler operation databases established in the step (2.7) and establishing a training database; the extraction rule is as follows: reading a boiler load value and a time stamp in a basic operation database of the boiler, selecting data that the boiler load stays at 90% -100% of rated load in a period of time (such as 1 hour or a user-defined period of time), and extracting all data of 6 databases in the period of time;
step (3.2): performing air balance calculation according to the boiler load, the fuel components, the air volume and the structure of the heating surface;
step (3.3): calculating the volume of the triatomic gases, the volume of the water vapor, the volume fraction and the enthalpy of the smoke and the air in each section of the flue;
step (3.4): calculating the enthalpy value of the flue gas at the outlet of the hearth according to the temperature of the flue gas, the temperature of the flue gas at the outlet of the economizer, the coal quantity, the air quantity, the flow of each heating surface and the temperature and pressure of steam at the inlet and the outlet;
step (3.5): calculating the average temperature ty of the flue gas at the outlet of the hearth and the average heat transfer coefficient h of the hearth l ；
The average temperature of the flue gas at the outlet of the hearth is calculated according to the following formula:
in the formula, T th Theoretical combustion temperature; x is the number of m Arranging a relative height for the burner;
the degree of blackness of the hearth; b is 0 Are boltzmann feature numbers.
Average heat transfer coefficient h of hearth l The calculation steps are as follows: respectively calculating heat transfer coefficients of each convection heating surface and each radiation heating surface according to an industrial boiler design standard method, and calculating an average value according to a hearth structure;
step (3.6): calculating the confidence coefficient alpha of the boiler non-coking training database extracted in the step (3.1), and calculating according to the following formula:
in the formula, t y0 Is the design value of the average temperature h of the flue gas at the outlet of the hearth l0 is Average heat transfer coefficient h of hearth l A design value;
step (3.7): if alpha is smaller than the non-coking confidence coefficient preset value, the extracted boiler non-coking training data is considered to be unreliable, the database is discarded, and re-extraction is carried out, wherein the non-coking confidence coefficient preset value can be set to be 0.7-1.0;
step (3.8): repeating the steps (3.1) - (3.7) until the confidence coefficient of the extracted boiler non-coking training data is greater than or equal to the preset value of the non-coking confidence coefficient;
step (3.9): and (3.1) repeating the steps (3.8), and respectively constructing an 80-90% rated load boiler non-coking training database, a 70-80% rated load boiler non-coking training database, a 60-70% rated load boiler non-coking training database and a 50-60% rated load boiler non-coking training database. Larger or smaller load intervals may also be used to build the database.
Further, the step (4) is specifically as follows:
step (4.1): setting the maximum value and the minimum value of all operation parameter checks of the boiler according to boiler design data, boiler user manuals, original boiler thermodynamic calculation data or other rules provided by a power plant, wherein the operation parameters comprise but are not limited to boiler load, feed water flow, total primary air quantity, total coal quantity and coal quantity of each coal feeder, total secondary air quantity and secondary air quantity of each layer, burnout air quantity of each layer, primary and secondary air pressure, hearth negative pressure, coal quality and ash melting point of entering boiler, superheated steam temperature and pressure of each heating surface, reheated steam temperature and pressure, desuperheating water flow and temperature, smoke temperature, fly ash carbon content and smoke component (CO/H) 2 S/O 2 ) One or more of;
step (4.2): comparing the data labeled C1 in the sub-database obtained in the step (3.9) with the set parameter check minimum value and maximum value in the step (4.1) one by one, reading the timestamp of the data if the data exceeds the set value range, and discarding all data corresponding to the timestamp in the sub-database obtained in the step (3.9);
step (4.3) comparing the data labeled C2, C3, C4, C5 and C6 in the sub-database obtained in step (4.2) with the set parameter check minimum value and the maximum value in step (4.1) one by one, and if a certain data value is smaller than the set minimum value, setting the data value as the set minimum value; if a certain data value is larger than the set maximum value, setting the certain data value as the set maximum value;
and (4.4) sequentially performing data cleaning and data filling on each column of the sub-database data table obtained in the step (4.3) by adopting the following formulas:
if(x ij -x iav >3x ierr ),x ij ＝x iav +3x ierr
if(x ij -x iav <-3x ierr ),x ij ＝x iav -3x ierr
in the formula, x ij J data which is ith data; x is the number of iav The average value of the ith column data; x is the number of ierr The standard deviation of the ith column data;
further, the step (5) is specifically:
step (5.1): inquiring the coke-dropping accident occurrence time according to the boiler operation ledger, reversely pushing for 0.5-24 hours from the time, and extracting data from the 6 boiler operation databases established in the step (2.7);
step (5.2): reading the coal quality information in the step (5.1), and if the coal in the furnace is not changed, keeping all the data; if the quality of the coal entering the furnace changes, only the operation data of the last coal entering the furnace before the coke-dropping accident happens is reserved;
step (5.3): dividing the data obtained in the step (5.2) according to the load size, and constructing a 90% -100% rated load boiler coking training database, an 80% -90% rated load boiler coking training database, a 70% -80% rated load boiler coking training database, a 60% -70% rated load boiler coking training database and a 50% -60% rated load boiler coking training database.
Further, the step (6) is specifically:
step (6.1): respectively constructing prediction models by using the data labeled A1, A2 and A3 in the boiler non-coking training database obtained in the step (4.4), and respectively obtaining non-coking analog characteristics of the data A1, A2 and A3;
step (6.2): and (5.3) respectively constructing prediction models by using the data labeled with A1, A2 and A3 in the boiler coking training database obtained in the step (5.3), and respectively obtaining coking analog characteristics of the data A1, A2 and A3.
The model building method of step (6) includes but is not limited to: decision trees, support vector machines, artificial neural networks (e.g., back-propagation neural networks, convolutional neural networks, hofield networks, boltzmann machines, deep belief networks).
Further, the step (7) is specifically:
step (7.1): extracting real-time operation data from the 6 boiler operation databases established in the step (2.7);
step (7.2): respectively sending the real-time operation data into the prediction model established in the step (6.1) according to the labels A1, A2 and A3 for calculation, and comparing the real-time operation data with the non-coking analog characteristics of the data A1, A2 and A3 obtained in the step (6.1) to obtain confidence coefficient alpha A1 、α A2 、α A3 And calculating the confidence coefficient of non-coking of the boiler:
α＝0.7α A1 +0.2α A2 +0.1α A3
in the formula, three coefficients of 0.7, 0.2 and 0.1 can be adjusted according to actual conditions, and the sum is 1.
Step (7.3): respectively sending the real-time operation data into the prediction model established in the step (6.2) according to the labels A1, A2 and A3 for calculation, and comparing the real-time operation data with the coking analog characteristics of the data A1, A2 and A3 obtained in the step (6.2) to obtain confidence coefficient beta A1 、β A2 、β A3 And calculating boiler coking confidence coefficient:
β＝0.7β A1 +0.2β A2 +0.1β A3
in the formula, three coefficients of 0.7, 0.2 and 0.1 can be adjusted according to actual conditions, and the sum is 1.
Step (7.4): and comparing the boiler non-coking confidence coefficient alpha with the boiler coking confidence coefficient beta, and if alpha is less than beta and beta is greater than 0.5, determining that the boiler is high in coking risk.
Further, in the initial operation stage of the boiler, in case of insufficient data, the step (7) is specifically:
step (7.1): and (4) extracting real-time operation data from the 6 boiler operation databases established in the step (2.7).
Step (7.2): performing air balance calculation according to the boiler load, the fuel components, the air volume and the structure of the heating surface;
step (7.3): calculating the volume of three-atom gas, the volume of water vapor, the volume fraction of the three-atom gas and the enthalpy of the smoke and the air in each section of the flue;
step (7.4): calculating the enthalpy value of the flue gas at the outlet of the hearth according to the temperature of the flue gas, the temperature of the flue gas at the outlet of the economizer, the coal quantity, the air quantity, the flow of each heating surface and the temperature and pressure of steam at the inlet and the outlet;
step (7.5): calculating the average temperature t of the flue gas at the outlet of the hearth y And average heat transfer coefficient h of furnace chamber l ；
Step (7.6): calculating the coking confidence coefficient of the boiler real-time operation data extracted in the step (7.1) according to the following formula:
in the formula, t y0 Is a design value of the average temperature h of the flue gas at the outlet of the furnace chamber l0 Average heat transfer coefficient h of furnace chamber l A design value;
step (7.7): if β >0.5 (or other values between 0.5 and 1.0), the risk of boiler coking is considered to be high.
Claims (3)
1. An on-line prediction method for coking of a heating surface of a boiler is characterized by comprising the following steps: the method comprises the following steps:
step (1): collecting related data of boiler operation;
step (2): according to the boiler operation principle, encoding, classifying and modeling the boiler operation data;
and (3): establishing a boiler non-coking training database in different load intervals according to a boiler operation principle;
and (4): according to the boiler operation principle, cleaning data of a boiler non-coking training database;
and (5): establishing boiler coking training databases in different load intervals, and cleaning data;
and (6): establishing a boiler non-coking training model and a boiler coking training model;
and (7): predicting the coking state of the boiler based on the boiler operation mechanism and the big data model;
the step (2) comprises the following specific steps:
step (2.1): establishing a boiler operation data classification principle according to a boiler operation principle and data importance;
step (2.2): according to the classification principle of the boiler operation data established in the step (2.1), marking the boiler operation data obtained in the step (1) with an important grade label: the label A1 represents the primary operation data with the highest importance level; the label A2 represents secondary operation data of the second importance level; the label A3 represents the three-level operation data with the lowest importance level;
step (2.3): according to the classification principle of the boiler operation data established in the step (2.1), marking the boiler operation data obtained in the step (2.2) with a class label: the label C1 represents basic operation data of the boiler, the label C2 represents primary air related data, the label C3 represents secondary air related data, the label C4 represents superheated steam related data, the label C5 represents reheated steam related data, and the label C6 represents a flue gas related database;
step (2.4): time stamping the boiler operation data obtained in the step (2.3);
step (2.5): and (3) encoding the boiler operation data obtained in the step (2.4), wherein the encoding rule is as follows: the method comprises the following steps of (1) power plant KKS code + important grade label + category label + time stamp + self-made check code;
step (2.6): at least 6 databases are created, respectively: a boiler basic operation database, a primary air related database, a secondary air related database, a superheated steam related database, a reheated steam related database and a flue gas related database;
step (2.7): respectively storing the boiler operation data obtained in the step (2.5) into corresponding databases established in the step (2.6) according to the class labels;
the step (3) is specifically as follows:
step (3.1): extracting data from the 6 boiler operation databases established in the step (2.7) and establishing a training database; the extraction rule is as follows: reading a boiler load value and a time stamp in a basic operation database of the boiler, selecting data that the boiler load stays at 90% -100% of rated load in a period of time, and extracting all data of 6 databases in the period of time;
step (3.2): performing air balance calculation according to the boiler load, the fuel components, the air volume and the structure of the heating surface;
step (3.3): calculating the volume of the triatomic gases, the volume of the water vapor, the volume fraction and the enthalpy of the smoke and the air in each section of the flue;
step (3.4): calculating the enthalpy value of the flue gas at the outlet of the hearth according to the temperature of the flue gas, the temperature of the flue gas at the outlet of the economizer, the coal quantity, the air quantity, the flow of each heating surface and the temperature and pressure of steam at the inlet and the outlet;
step (3.5): calculating the average temperature ty of the flue gas at the outlet of the hearth and the average heat transfer coefficient h of the hearth l ；
The average temperature of the flue gas at the outlet of the hearth is calculated according to the following formula:
in the formula, T th Theoretical combustion temperature; x is the number of m Arranging a relative height for the burner; epsilon f syn The degree of blackness of the hearth; b is 0 Is a Boltzmann feature number;
average heat transfer coefficient h of hearth l The calculation steps are as follows: respectively calculating heat transfer coefficients of each convection heating surface and each radiation heating surface, and calculating an average value according to the structure of the hearth;
step (3.6): and (3) calculating the confidence coefficient alpha of the boiler non-coking training database extracted in the step (3.1) according to the following formula:
in the formula, t y0 Is a design value of the average temperature h of the flue gas at the outlet of the furnace chamber l0 Average heat transfer coefficient h of furnace chamber l A design value;
step (3.7): if alpha is smaller than the non-coking confidence coefficient preset value, the extracted boiler non-coking training data is considered to be unreliable, the database is discarded, and re-extraction is carried out, wherein the non-coking confidence coefficient preset value can be set to be 0.7-1.0;
step (3.8): repeating the steps (3.1) - (3.7) until the confidence coefficient of the extracted boiler non-coking training data is greater than or equal to the preset value of the non-coking confidence coefficient;
step (3.9): repeating the steps (3.1) - (3.8), and respectively constructing an 80% -90% rated load boiler non-coking training database, a 70% -80% rated load boiler non-coking training database, a 60% -70% rated load boiler non-coking training database and a 50% -60% rated load boiler non-coking training database;
the step (4) is specifically as follows:
step (4.1): setting the maximum value and the minimum value of all operation parameter checks of the boiler, wherein the operation parameters comprise but are not limited to one or more of boiler load, water supply flow, total primary air quantity, total coal quantity and coal quantity of each coal feeder, total secondary air quantity and secondary air quantity of each layer, burnout air quantity of each layer, primary air pressure, hearth negative pressure, coal quality and ash melting point of entering boiler, superheated steam temperature and pressure of each heating surface, reheated steam temperature and pressure, desuperheating water flow and temperature, smoke exhaust temperature, fly ash carbon content and smoke component;
step (4.2): comparing the data labeled C1 in the sub-database obtained in the step (3.9) with the set parameter check minimum value and maximum value in the step (4.1) one by one, reading the timestamp of the data if the data exceeds the set value range, and discarding all data corresponding to the timestamp in the sub-database obtained in the step (3.9);
step (4.3) comparing the data labeled C2, C3, C4, C5 and C6 in the sub-database obtained in step (4.2) with the set parameter check minimum value and the maximum value in step (4.1) one by one, and if a certain data value is smaller than the set minimum value, setting the data value as the set minimum value; if a certain data value is larger than the set maximum value, setting the certain data value as the set maximum value;
and (4.4) sequentially performing data cleaning and data filling on each column of the sub-database data table obtained in the step (4.3) by adopting the following formulas:
if(x ij -x iav >3x ierr ),x ij ＝x iav +3x ierr
if(x ij -x iav <-3x ierr ),x ij ＝x iav -3x ierr
in the formula, x ij J data which is ith data; x is the number of iav The average value of the ith column data; x is a radical of a fluorine atom ierr The standard deviation of the ith column data;
further, the step (5) is specifically:
step (5.1): inquiring the coke-dropping accident occurrence time according to the boiler operation ledger, reversely pushing for 0.5-24 hours from the time, and extracting data from the 6 boiler operation databases established in the step (2.7);
step (5.2): reading the coal quality information in the step (5.1), and if the coal as fired is not changed, keeping all data; if the quality of the coal entering the furnace changes, only the operation data of the last coal entering the furnace before the coke-dropping accident happens is reserved;
step (5.3): dividing the data obtained in the step (5.2) according to the load size, and constructing a 90-100% rated load boiler coking training database, an 80-90% rated load boiler coking training database, a 70-80% rated load boiler coking training database, a 60-70% rated load boiler coking training database and a 50-60% rated load boiler coking training database;
the step (6) is specifically as follows:
step (6.1): respectively constructing prediction models by using the data labeled A1, A2 and A3 in the boiler non-coking training database obtained in the step (4.4), and respectively obtaining non-coking analog characteristics of the data A1, A2 and A3;
step (6.2): respectively constructing prediction models by using the data labeled A1, A2 and A3 in the boiler coking training database obtained in the step (5.3), and respectively obtaining coking analog characteristics of the data A1, A2 and A3;
the model building method of step (6) includes but is not limited to: decision tree, support vector machine, artificial neural network;
the step (7) is specifically as follows:
step (7.1): extracting real-time operation data from the 6 boiler operation databases established in the step (2.7);
step (7.2): respectively sending the real-time operation data into the prediction model established in the step (6.1) according to the labels A1, A2 and A3 for calculation, and comparing the real-time operation data with the non-coking analog characteristics of the data A1, A2 and A3 obtained in the step (6.1) to obtain confidence coefficient alpha A1 、α A2 、α A3 And calculating the confidence coefficient of non-coking of the boiler:
α＝0.7α A1 +0.2α A2 +0.1α A3
step (7.3): respectively sending the real-time operation data into the prediction model established in the step (6.2) according to the labels A1, A2 and A3 for calculation, and comparing the real-time operation data with the coking analog characteristics of the data A1, A2 and A3 obtained in the step (6.2) to obtain confidence coefficient beta A1 、β A2 、β A3 And calculating boiler coking confidence coefficient:
β＝0.7β A1 +0.2β A2 +0.1β A3
step (7.4): comparing the boiler non-coking confidence coefficient alpha with the boiler coking confidence coefficient beta, and if alpha is less than beta and beta is greater than 0.5, determining that the boiler coking risk is higher;
or in the initial operating stage of the boiler, when the data is insufficient, the step (7) is specifically as follows:
step (7.1): extracting real-time operation data from the 6 boiler operation databases established in the step (2.7);
step (7.2): performing air balance calculation according to the boiler load, the fuel components, the air volume and the structure of the heating surface;
step (7.3): calculating the volume of the triatomic gases, the volume of the water vapor, the volume fraction and the enthalpy of the smoke and the air in each section of the flue;
step (7.4): calculating the enthalpy value of the flue gas at the outlet of the hearth according to the temperature of the flue gas, the temperature of the flue gas at the outlet of the economizer, the coal quantity, the air quantity, the flow of each heating surface and the temperature and pressure of steam at the inlet and the outlet;
step (7.5): calculating the average temperature t of the flue gas at the outlet of the hearth y And average heat transfer coefficient h of furnace chamber l ；
Step (7.6): calculating the coking confidence coefficient of the boiler real-time operation data extracted in the step (7.1), and calculating according to the following formula:
in the formula, t y0 Is a design value of the average temperature h of the flue gas at the outlet of the furnace chamber l0 Average heat transfer coefficient h of furnace chamber l A design value;
step (7.7): if β >0.5 (or other values between 0.5 and 1.0), the risk of boiler coking is considered to be high.
2. The on-line prediction method for the coking of the heating surface of the boiler according to claim 1, characterized in that: in the step (1), the boiler operation related data comprises real-time operation data and historical operation data; the boiler operation related data includes, but is not limited to: one or more of boiler load, water supply flow, total primary air quantity, total coal quantity and coal quantity of each coal feeder, total secondary air quantity and secondary air quantity of each layer, burnout air quantity of each layer, primary air pressure, furnace negative pressure, coal quality and ash melting point of furnace entering, superheated steam temperature and pressure of each heating surface, reheated steam temperature and pressure, desuperheating water flow and temperature, smoke exhaust temperature, fly ash carbon content, smoke component and alarm signals of each level.
3. The on-line prediction method for the coking of the heating surface of the boiler as claimed in claim 1, wherein: in the step (1), the relevant data of the boiler operation is collected from various information systems of the power plant, and the various information systems include but are not limited to one or more of PLC, RTU, DCS, MIS, SIS and SCADA systems of the power plant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110381281.XA CN113052391B (en) | 2021-04-09 | 2021-04-09 | Boiler heating surface coking on-line prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110381281.XA CN113052391B (en) | 2021-04-09 | 2021-04-09 | Boiler heating surface coking on-line prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113052391A CN113052391A (en) | 2021-06-29 |
| CN113052391B true CN113052391B (en) | 2022-10-18 |
Family
ID=76519376
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110381281.XA Active CN113052391B (en) | 2021-04-09 | 2021-04-09 | Boiler heating surface coking on-line prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113052391B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114418184B (en) * | 2021-12-20 | 2023-04-07 | 广东石油化工学院 | Self-adaptive fault-tolerant prediction method for temperature of heating furnace hearth |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102192955A (en) * | 2010-03-03 | 2011-09-21 | 中国石油化工股份有限公司 | Detection method of solid particle coking amount in reactor |
| CN110738328A (en) * | 2019-09-06 | 2020-01-31 | 中国大唐集团科学技术研究院有限公司火力发电技术研究院 | Boiler receives anti-explosion preventive maintenance system of face abrasionproof |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4969408A (en) * | 1989-11-22 | 1990-11-13 | Westinghouse Electric Corp. | System for optimizing total air flow in coal-fired boilers |
| RU2328654C1 (en) * | 2007-05-30 | 2008-07-10 | Игорь Владимирович Иванов | Chamber of fuel firing in melt |
| US7890197B2 (en) * | 2007-08-31 | 2011-02-15 | Emerson Process Management Power & Water Solutions, Inc. | Dual model approach for boiler section cleanliness calculation |
| CN101598688B (en) * | 2009-06-10 | 2011-12-14 | 东南大学 | Boiler fouling monitoring and soot blowing optimization methods based on on-line measurement of coal quality |
| CN105276563B (en) * | 2015-11-11 | 2017-04-05 | 东南大学 | A kind of furnace outlet gas temperature flexible measurement method based on the real-time slagging scorification situation of burner hearth |
| CN106845089B (en) * | 2016-12-30 | 2019-03-29 | 国网浙江省电力公司电力科学研究院 | A kind of boiler thermal efficiency acquisition methods |
| US20190194549A1 (en) * | 2017-12-22 | 2019-06-27 | Exxonmobil Research And Engineering Company | System and process for converting heavy oils to light liquid products and electric power |
| CN108716664B (en) * | 2018-04-28 | 2019-11-15 | 国网山东省电力公司电力科学研究院 | A kind of method and apparatus of on-line measurement burner hearth ash fouling coefficient |
| JP7082931B2 (en) * | 2018-09-03 | 2022-06-09 | 株式会社Ihi | Coal-fired boiler ash adhesion prediction method and equipment, coal-fired boiler ash adhesion prevention method and equipment, and coal-fired boiler operation method and equipment |
| CN109165789B (en) * | 2018-09-04 | 2022-06-21 | 南方电网电力科技股份有限公司 | LSTM-based modeling method and device for boiler NOx emission prediction model |
| CN111242279B (en) * | 2020-01-03 | 2023-09-08 | 浙江浙能技术研究院有限公司 | Slag bonding prediction system and method for ultra-supercritical pulverized coal boiler furnace |
-
2021
- 2021-04-09 CN CN202110381281.XA patent/CN113052391B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102192955A (en) * | 2010-03-03 | 2011-09-21 | 中国石油化工股份有限公司 | Detection method of solid particle coking amount in reactor |
| CN110738328A (en) * | 2019-09-06 | 2020-01-31 | 中国大唐集团科学技术研究院有限公司火力发电技术研究院 | Boiler receives anti-explosion preventive maintenance system of face abrasionproof |
Non-Patent Citations (1)
| Title |
|---|
| 600MW机组锅炉对流受热面灰污在线监测研究;王新等;《江苏电机工程》;20070928(第05期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113052391A (en) | 2021-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101598688B (en) | Boiler fouling monitoring and soot blowing optimization methods based on on-line measurement of coal quality | |
| CN103759277B (en) | Coal-fired power station boiler intelligent ash blowing closed loop control method, device and system | |
| US4996951A (en) | Method for soot blowing automation/optimization in boiler operation | |
| CN109695892B (en) | Method and device for protecting wall temperature of heating surface of boiler | |
| CN113052391B (en) | Boiler heating surface coking on-line prediction method | |
| CN106322412B (en) | Coal unit convection heating surface intelligent ash blowing method based on two-dimentional optimizing | |
| CN113467392B (en) | Open-loop combustion control optimization method for coal-fired boiler | |
| TW202001462A (en) | Operation assistance device for plant, operation assistance method for plant, learning model creation method for plant | |
| CN104090560A (en) | Device monitoring power supply integrated environment evaluation indexes | |
| CN110207094A (en) | IQGA-SVR boiler heating surface fouling characteristics discrimination method based on principal component analysis | |
| CN108021027B (en) | Output power prediction system and method for supercritical circulating fluidized bed unit | |
| CN116720446B (en) | Method for monitoring thickness of slag layer of water-cooled wall of boiler in real time | |
| CN110298502A (en) | Based on the boiler optimum oxygen calculation method that efficiency is optimal | |
| CN112950409A (en) | Production scheduling optimization method of gas and steam energy comprehensive utilization system | |
| Li et al. | Prediction of pollution state of heating surface in coal-fired utility boilers | |
| CN109140474A (en) | A kind of coal-fired power station boiler manually intelligent sootblowing | |
| CN111242279A (en) | System and method for predicting slagging of hearth of ultra-supercritical pulverized coal boiler | |
| CN113946789B (en) | Method for calculating garbage incineration amount of four-furnace three-machine garbage incineration power plant in real time | |
| CN110888403A (en) | Intelligent soot blowing closed-loop control system based on minimum loss boiler convection heating surface | |
| CN213178308U (en) | Slagging-off prevention system of ultra-supercritical pulverized coal boiler | |
| CN110647560B (en) | Mechanism and brain-like intelligence combined online soft measurement method for coal quality of fired coal of power plant | |
| CN113757701A (en) | Intelligent soot blowing control method and system based on multi-dimensional evaluation factor and storage medium | |
| CN112833409A (en) | Hearth soot blowing optimization method based on dynamic loss prediction | |
| CN112923394A (en) | Coal-fired boiler high-temperature convection heating surface contamination and slagging early warning system and method | |
| CN115113519A (en) | Coal-gas co-combustion boiler denitration system outlet NO x Concentration early warning method |
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 |