CN113657778A - Coal blending and burning optimization method - Google Patents

Coal blending and burning optimization method Download PDF

Info

Publication number
CN113657778A
CN113657778A CN202110958506.3A CN202110958506A CN113657778A CN 113657778 A CN113657778 A CN 113657778A CN 202110958506 A CN202110958506 A CN 202110958506A CN 113657778 A CN113657778 A CN 113657778A
Authority
CN
China
Prior art keywords
data
boiler
coal
samples
temperature
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
Application number
CN202110958506.3A
Other languages
Chinese (zh)
Inventor
潘富停
杨勇
李金霞
陈海涛
曾勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Power Investment Group Pingdingshan Thermal Power Co ltd
Original Assignee
State Power Investment Group Pingdingshan Thermal Power Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by State Power Investment Group Pingdingshan Thermal Power Co ltd filed Critical State Power Investment Group Pingdingshan Thermal Power Co ltd
Priority to CN202110958506.3A priority Critical patent/CN113657778A/en
Publication of CN113657778A publication Critical patent/CN113657778A/en
Pending legal-status Critical Current

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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G06F16/284—Relational databases
    • G06F16/285—Clustering or classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Health & Medical Sciences (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Quality & Reliability (AREA)
  • Computing Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Computational Linguistics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Regulation And Control Of Combustion (AREA)

Abstract

The invention discloses a coal blending combustion optimization method, which comprises the following steps: s1, data acquisition, namely acquiring superheated steam flow, pressure and temperature data of the coal-fired boiler, boiler exhaust smoke temperature, exhaust smoke oxygen content, exhaust smoke carbon monoxide concentration data and boiler unit temperature data through a data acquisition module; s2, storing data, and correspondingly setting a unit database and a configuration database for coal-fired boiler steam data, smoke exhaust data and boiler temperature data; s3, analyzing data; s4, performing system evaluation, namely performing system evaluation and fault judgment on the system boiler unit, the smoke exhaust system and the boiler thermal efficiency through data analysis and processing to obtain a system evaluation report and a fault report; the system is evaluated through collected data analysis, data errors are reduced through analysis and processing of the collected data, accuracy of system evaluation is improved, reduction of system failure rate is facilitated, and stability of system operation is improved.

Description

Coal blending and burning optimization method
Technical Field
The invention belongs to the field of blending combustion of thermal power generation blending coal, and particularly relates to a blending combustion optimization method.
Background
Fuel costs are a significant component of the operating costs of coal-fired power plants. In the face of unfavorable situation of coal market, optimize coal-fired structure, develop the work of blending coal and burning scientifically and rationally, be the important measure of coping with market change, reducing the operation cost of power generation enterprise.
The current blending coal blending combustion system is mostly in an experimental research stage, little and few in investment, and mostly in researches on fuel proportioning, heat efficiency calculation and the like, and fault evaluation and detection of the blending coal blending combustion system lack corresponding effective technical means, so that the blending coal blending combustion system is unstable in operation, high in fault rate, influences normal use of the blending coal blending combustion system, and increases economic use cost.
In order to improve the economic benefit of a power plant, strengthen fuel management, promote fuel fine work, optimize a coal blending and burning mode, effectively control and reduce the unit price of standard coal and reduce the fuel cost of a company, the scheme guides the coal blending and burning work of a production site by optimizing the functions of a blending and burning scheme, reverse balance verification, blending and burning verification, low-order heat value inspection, evaluating a system through data acquisition analysis and the like, and has important significance for guiding the economic operation of a unit.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a blending coal blending optimization method, which can strengthen fuel management, optimize a blending coal blending combustion mode and reduce fuel cost by optimizing functions such as blending combustion scheme, reverse balance check, blending combustion check, low calorific value check and the like; the system is evaluated through collected data analysis, data errors are reduced through analysis and processing of the collected data, accuracy of system evaluation is improved, reduction of system failure rate is facilitated, and stability of system operation is improved.
The invention provides the following technical scheme:
a coal blending combustion optimization method comprises the following steps:
s1, data acquisition, namely acquiring superheated steam flow, pressure and temperature data of the coal-fired boiler, boiler exhaust smoke temperature, exhaust smoke oxygen content, exhaust smoke carbon monoxide concentration data and boiler unit temperature data through a data acquisition module;
s2, storing data, namely, correspondingly setting a unit database and a configuration database for coal-fired boiler steam data, smoke exhaust data and boiler temperature data, wherein the unit database stores collected data information, and the configuration database stores configuration information;
s3, analyzing the data, comprising the following steps: a, clustering and fusing all collected sample data; b, arranging the samples of most types from high to low according to the instability degree; c, deleting most classes with higher instability degree by introducing deletion factors; d, obtaining a new sample data set;
and S4, performing system evaluation, namely performing system evaluation and fault judgment on the system boiler unit, the smoke exhaust system and the boiler thermal efficiency through data analysis and processing to obtain a system evaluation report and a fault report.
Preferably, in step S2, the signal data collected in the unit database includes real-time data, current data, historical data, and abnormal data, and are stored separately.
Preferably, in step S3, the specific steps include: firstly, clustering and calculating the collected flow, pressure and temperature of superheated steam, the pressure and temperature of reheated steam, the pressure and temperature of feed water and the temperature data set of a boiler unit and designating the number of clusters; and B, calculating the number of each cluster in each clustering, comparing the number of the majority samples and the number of the minority samples in the cluster, and if the number of the minority samples is more than that of the majority samples, positioning the positive cluster in the cluster, otherwise, determining the negative cluster.
Preferably, the step S3 further includes a step C of traversing all sample objects, and if the real type of the negative type sample is consistent with the type of the cluster, the sample type function y (x) is set to 0, otherwise, the sample type function y (x) is set to 1; d, repeating the steps A-C; e, calculating a category function value of the final negative type data sample, and sequencing most types of samples from high to low according to the size of the function value; and F, deleting a plurality of types of samples according to the selected deletion factor according to the proportion to obtain a new data set sample, and then carrying out classification training on the newly generated data set by using a classification algorithm.
Preferably, in step S3, a deletion factor δ is introduced, δ ═ the (deleted majority class)/(unstable majority class); the value of delta is larger than 0 and smaller than or equal to 1, the value range in the scheme is 0.45-0.85, the situation that multiple samples are deleted too much or too little is prevented, the sample classification accuracy of the classifier is improved, and the accuracy of system risk and fault evaluation is improved.
Preferably, in step S4, after step S3, balanced sample data samples are obtained, feature extraction is performed on the new sample data set, and time domain, frequency domain, and time-frequency domain data features are selected.
Preferably, the data characteristics are layered according to the running state of the system coal-fired boiler and the system fault frequency, and a clustering center is found out for each layer by utilizing a clustering algorithm to obtain a small boiler temperature and system fault type set; and re-layering fewer data sets, calculating the center of each cluster of data of a new data type set by clustering, calculating Euclidean distance with each cluster center of each layer of the fewer boiler temperature and system fault type sets, adding the distances of each cluster center of the new data set, classifying the new data according to the distances, layering the new data, judging whether the new data belongs to the minimum set to the bottom layer or not after the new data is layered to a certain layer, performing classification operation on the trained classifier, performing system evaluation and fault judgment on the system boiler unit, the smoke exhaust system and the boiler thermal efficiency to obtain a system evaluation report and a fault report.
In the above step, the positive cluster is a cluster in a certain cluster, the number of the minority samples is greater than the number of the majority samples, and conversely, the number of the minority samples is less than the number of the majority samples, and the negative cluster is a cluster; if G isi(u) represents the cluster class described by the majority class sample point u in the ith cluster, andthe clustering times are m times, the class formula of the majority samples satisfies
Figure BDA0003220798150000041
Figure BDA0003220798150000042
Y (X) is a class function, when the majority class samples are positive classes, the function value is 1, and when the majority class samples are positive classes, the function value is-1; fuIs the final class function value, after multiple clustering, if FuIf the number of the samples is more than 0, the samples are considered as unstable points, the samples are actually negative, and the number of times that the samples fall into the positive cluster after clustering is more than that of the negative cluster; if FuAnd if the sample number is less than 0, the majority of samples are considered as stable points, the samples are actually negative, and the number of times that the samples fall in the negative cluster after clustering is greater than that of the positive cluster. Finally F is obtaineduThe values of (A) are arranged from large to small, FuThe larger the value, the more unstable the value can be selectively deleted, and the stability and the accuracy of data classification are increased; but deleting too many samples of most classes will reduce the classification accuracy of the classifier for most classes significantly, and if deleting too few samples, the classification accuracy of the classifier for few classes will reduce.
Preferably, the sampling and blending optimization system of the coal blending and blending optimization method comprises a monitoring host; the monitoring host comprises a management module, a data acquisition module and a communication module; the data acquisition module and the monitoring host are in data storage by adopting wireless signal transmission, the monitoring host processes the stored acquired data through the data analysis processing module, and the data analysis processing module comprises an alarm module and an evaluation module; the management module comprises a basic data module, a co-combustion scheme module, a verification module and a help module of the coal-fired boiler unit;
the checking module comprises reverse balance checking, doped burning checking and low-order heat value checking; the data acquisition module comprises data of a coal-fired boiler unit, smoke exhaust data and boiler thermal efficiency data; the coal-fired boiler data comprises superheated steam flow, pressure and temperature data, the smoke discharge data comprises smoke discharge temperature, smoke discharge oxygen content and smoke discharge carbon monoxide concentration data, and the boiler thermal efficiency data comprises boiler unit temperature data; the data acquisition module also comprises a plurality of sensors and data acquisition cards of different types, and the plurality of sensors and the data acquisition cards are transmitted through wireless signals.
Preferably, the various sensors comprise a steam flow sensor, a steam pressure sensor, a steam temperature sensor, a feed water pressure sensor and a feed water temperature sensor of the coal-fired boiler unit; a smoke exhaust temperature sensor, a smoke exhaust oxygen sensor and a carbon monoxide sensor for monitoring smoke exhaust data; the steam flow sensor, the steam pressure sensor and the steam temperature sensor are arranged in a steam pipeline of the boiler; the exhaust gas temperature sensor, the exhaust gas oxygen sensor and the carbon monoxide sensor are uniformly arranged in the boiler exhaust gas pipeline.
Preferably, the management module is divided into a data layer, a middle layer and an application layer, the data layer stores basic data by adopting a distributed P2P data storage environment, and the management system module is built by using the open cell block; the middle layer comprises an intelligent contract layer and Web3, the application layer is an interaction layer of the monitoring host, and data in the management module is viewed through a visual section of the monitoring host.
Preferably, the basic data module comprises two parts of raw coal basic data and production basic data; the raw coal basic data is basic data for calculating standard coal unit price; the production basic data is the basic data for calculating the evaporation capacity and the consumption theoretical standard coal quantity of the coal blending boiler; the basic data module is the basis of other part of calculation, and all basic data must be checked and adjusted before each calculation.
Preferably, the blending combustion scheme module is divided into a standard coal unit price target module and a furnace entering heat value target module; the coal marking unit price target module is a blending combustion scheme which takes controlling the coal marking unit price as a target; the furnace heat value target module is a mixed burning scheme which takes controlling the furnace heat value as a target.
Preferably, the reverse balance checking module can measure and calculate the efficiency of a reverse balance boiler, the reverse balance heat consumption rate, the reverse balance power generation coal consumption, the reverse balance power supply coal consumption, the reverse balance heat supply coal consumption, the reverse balance standard coal quantity, the reverse balance raw coal quantity and the reverse balance coal heat value entering the furnace according to actual data of a production field; defects and deficiencies in the operation of the unit can be analyzed, decision basis is provided for improving the performance of the unit, and positive balance data can be verified through comparison and a negative balance result.
Preferably, the blending combustion checking module is used for checking the unit price, the heat value and the variable quantity of the blended combustion standard coal according to the coal quantity and the heat value of the high-quality coal and the low-quality coal by a user so as to guide the blending combustion.
Preferably, a low-grade heat value checking module is used, so that a user can check the evaporation capacity of the boiler, the total standard coal quantity, the heat value and the raw coal quantity according to each index of production, and the professional management level of the coal as fired is improved.
Preferably, the step of preprocessing the collected data by the monitoring host through the data analysis processing module includes: a, clustering and fusing all collected sample data; b, arranging the samples of most types from high to low according to the instability degree; c, deleting most classes with higher instability degree by introducing deletion factors; d, obtaining a new sample data set; the problem that most classes and few classes of the collected data set are unbalanced is solved, the accuracy of the collected data is improved, and errors are reduced.
By the method, the collected data of the exhaust gas temperature, the exhaust gas oxygen concentration and the carbon monoxide concentration are processed, the accuracy of the collected data is increased, the accurate calculation of the emission amount of nitrogen oxides is facilitated, the emission standard is met, the exhaust gas problem and the exhaust fault are conveniently found out in time, and the stable operation of the system is guaranteed.
After data acquisition is carried out by a data acquisition module, data signatures are stored in an IPFS, the IPFS returns a stored data index hash, the index hash is encrypted by a system public key and then is stored in a block chain, the IPFS can carry out decentralized distributed storage on a large amount of data, the data of a data processing module of a monitoring host server is received in the system and stored on a node of the IPFS, and then data calling of a management module is received; the data acquisition safety and the data storage safety are enhanced.
When abnormal data appear in the evaluation result of the system, the alarm module alarms through the buzzer, in order to increase the accuracy of fault alarm, when the alarm threshold value z of the abnormal data does not obtain the data analysis result of the monitoring host, the data indexes are calculated according to the normal data of each index under each working state of the system, and then according to the mean value mu and the standard variance sigma of the data indexes, the alarm threshold value z meets the following relation:
z＝φ·(μ2+3σ2)1/2(ii) a Phi is a relation factor and has a value range of 0.366-2.626.
In the anti-balance checking module, according to the data acquisition module, the following data are acquired,
steam flow, steam pressure, steam temperature, feed water pressure and feed water temperature of the coal-fired boiler unit; boiler flue gas temperature, flue gas oxygen concentration, carbon monoxide concentration. The following data were obtained from actual production monitoring: the method comprises the steps of accumulating generated energy, accumulating steam supply, accumulating main steam flow, main steam pressure, main steam temperature, heat supply pressure, steam supply temperature, cold and re-temperature, heat and re-pressure, heat and re-temperature, water supply pressure, water supply temperature, accumulating water supply flow, main desuperheating water pressure, main desuperheating water temperature, main desuperheating water accumulated quantity, reheating desuperheating water temperature, reheating desuperheating water accumulated quantity, fly ash carbon content, slag carbon content, power generation electricity consumption rate, smoke exhaust temperature, air supply temperature, fired coal heat value, consumed raw coal quantity and air-to-air pre-leakage rate, and comparing the values with data obtained by a system evaluation module to check to obtain an anti-balance check result. The result of the anti-balance check mainly comprises parameters such as anti-balance boiler efficiency, anti-balance heat consumption rate, generation balance power generation coal consumption, anti-balance power supply coal consumption, anti-balance heat supply coal consumption, anti-balance standard coal quantity, anti-balance raw coal quantity, anti-balance fired coal heat value and the like.
Compared with the prior art, the invention has the following beneficial effects:
(1) according to the coal blending optimization method, fuel management is enhanced through functions of optimizing a blending scheme, reverse balance verification, blending verification, low-grade heat value inspection and the like, a coal blending mode is optimized, the economic benefit of a power plant is improved, the fuel management is enhanced, fine fuel operation is promoted, the unit price of standard coal is effectively controlled and reduced, and the fuel cost is reduced; the system is evaluated through collected data analysis, data errors are reduced through analysis and processing of the collected data, accuracy of system evaluation is improved, reduction of system failure rate is facilitated, and stability of system operation is improved.
(2) According to the coal blending and burning optimization method, most samples mixed in minority samples can be removed through a data processing and analyzing module, most samples on fuzzy boundaries of the minority samples and the majority samples can be removed, data with obvious errors are removed, the accuracy of data for collecting superheated steam flow, pressure, temperature, reheated steam pressure, temperature, feedwater pressure and temperature and boiler unit temperature is improved, the majority samples and the minority samples are guaranteed to reach balance, and the error influence of the collected data on an evaluation result is reduced.
(3) According to the coal blending combustion optimization method, the collected data of the exhaust gas temperature, the exhaust gas oxygen concentration and the carbon monoxide concentration are processed through the data processing and analyzing module, so that the accuracy of the collected data is improved, the accurate calculation of the emission of nitrogen oxides is facilitated, the emission standard is met, the exhaust gas problem can be found out in time, the fault is eliminated, and the stable operation of the system is guaranteed.
(4) The coal blending and burning optimization method adopts a classification training method to carry out system evaluation and fault judgment on the boiler unit, the smoke exhaust system and the boiler thermal efficiency of the system to obtain a system evaluation report and a fault report, so that the accuracy of the system evaluation and judgment is increased, the stable operation of the system is ensured, the system fault is timely eliminated, and the system safety is ensured.
(5) According to the coal blending and burning optimization method, the management module of the monitoring host machine adopts distributed storage for the collected data and the basic data, and compared with the safety problem of the traditional information management system, the method further enhances the data collection safety and the data storage safety.
(6) The invention relates to a coal blending combustion optimization method, which is implemented by carrying out F pairuThe values of (A) are arranged from large to small, and unstable classes are selectively deletedThe sample improves the stability and accuracy of data classification, and introduces a deletion factor delta to prevent the deletion of a plurality of samples, improve the classification accuracy of the classifier on the sample, and improve the accuracy of system risk and fault evaluation.
(7) According to the coal blending and burning optimization method, the alarm module limits the relation between the mean value and the standard variance, the alarm threshold value and the vibration signal to use a combined alarm method, so that the alarm accuracy is improved, the false alarm probability is reduced, system faults can be found and eliminated in time, and the stable operation of the system is ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a block diagram of the system framework of the present invention.
FIG. 2 is a data flow block diagram of the data acquisition module of the present invention.
FIG. 3 is a block diagram of a data acquisition module framework of the present invention.
FIG. 4 is a block diagram of the structure of the verification module of the present invention.
FIG. 5 is a flow chart of the data analysis process of the present invention.
Fig. 6 is a flow chart of a method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be described in detail and completely with reference to the accompanying drawings. It is to be understood that the described embodiments are only a few embodiments of the present invention, and not all embodiments. 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, are within the scope of the present invention.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the 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, are within the scope of the present invention.
The first embodiment is as follows:
as shown in fig. 6, a coal blending optimization method includes the following steps:
s1, data acquisition, namely acquiring superheated steam flow, pressure and temperature data of the coal-fired boiler, boiler exhaust smoke temperature, exhaust smoke oxygen content, exhaust smoke carbon monoxide concentration data and boiler unit temperature data through a data acquisition module;
s2, storing data, namely, correspondingly setting a unit database and a configuration database for coal-fired boiler steam data, smoke exhaust data and boiler temperature data, wherein the unit database stores collected data information, and the configuration database stores configuration information;
s3, analyzing the data, comprising the following steps: a, clustering and fusing all collected sample data; b, arranging the samples of most types from high to low according to the instability degree; c, deleting most classes with higher instability degree by introducing deletion factors; d, obtaining a new sample data set;
and S4, performing system evaluation, namely performing system evaluation and fault judgment on the system boiler unit, the smoke exhaust system and the boiler thermal efficiency through data analysis and processing to obtain a system evaluation report and a fault report.
In step S2, the signal data collected in the unit database includes real-time data, current data, historical data, and abnormal data, and are stored separately.
In step S3, the specific steps include, a: firstly, clustering and calculating the collected flow, pressure and temperature of superheated steam, the pressure and temperature of reheated steam, the pressure and temperature of feed water and the temperature data set of a boiler unit and designating the number of clusters; and B, calculating the number of each cluster in each clustering, comparing the number of the majority samples and the number of the minority samples in the cluster, and if the number of the minority samples is more than that of the majority samples, positioning the positive cluster in the cluster, otherwise, determining the negative cluster.
Step S3 further includes step C, traversing all sample objects, if the true type of the negative type sample is consistent with the type of the cluster, setting the sample type function y (x) to 0, otherwise setting to 1; d, repeating the steps A-C; e, calculating a category function value of the final negative type data sample, and sequencing most types of samples from high to low according to the size of the function value; and F, deleting a plurality of types of samples according to the selected deletion factor according to the proportion to obtain a new data set sample, and then carrying out classification training on the newly generated data set by using a classification algorithm.
In step S3, a deletion factor δ is introduced, δ ═ the (deleted majority class)/(unstable majority class); the value of delta is larger than 0 and smaller than or equal to 1, the value range in the scheme is 0.45-0.85, the situation that multiple samples are deleted too much or too little is prevented, the sample classification accuracy of the classifier is improved, and the accuracy of system risk and fault evaluation is improved.
In step S4, after step S3, a balanced sample data sample is obtained, a new sample data set is subjected to feature extraction, and time domain, frequency domain, and time-frequency domain data features are selected.
Layering data characteristics according to the operation state of a system coal-fired boiler and the system fault frequency, and finding out a clustering center for each layer by using a clustering algorithm to obtain a small boiler temperature and system fault type set; and re-layering fewer data sets, calculating the center of each cluster of data of a new data type set by clustering, calculating Euclidean distance with each cluster center of each layer of the fewer boiler temperature and system fault type sets, adding the distances of each cluster center of the new data set, classifying the new data according to the distances, layering the new data, judging whether the new data belongs to the minimum set to the bottom layer or not after the new data is layered to a certain layer, performing classification operation on the trained classifier, performing system evaluation and fault judgment on the system boiler unit, the smoke exhaust system and the boiler thermal efficiency to obtain a system evaluation report and a fault report.
Example two:
as shown in FIG. 1, a coal blending optimization system comprises a monitoring host; the monitoring host comprises a management module, a data acquisition module and a communication module; the data acquisition module and the monitoring host are in data storage by adopting wireless signal transmission, the monitoring host processes the stored acquired data through the data analysis processing module, and the data analysis processing module comprises an alarm module and an evaluation module; the management module comprises a basic data module, a co-combustion scheme module, a verification module and a help module of the coal-fired boiler unit;
the checking module comprises reverse balance checking, doped burning checking and low-order heat value checking; the data acquisition module comprises data of a coal-fired boiler unit, smoke exhaust data and boiler thermal efficiency data; the coal-fired boiler data comprises superheated steam flow, pressure and temperature data, the smoke discharge data comprises smoke discharge temperature, smoke discharge oxygen content and smoke discharge carbon monoxide concentration data, and the boiler thermal efficiency data comprises boiler unit temperature data; the data acquisition module also comprises a plurality of sensors and data acquisition cards of different types, and the plurality of sensors and the data acquisition cards are transmitted through wireless signals.
The basic data module comprises two parts of raw coal basic data and production basic data; the raw coal basic data is basic data for calculating standard coal unit price; the production basic data is the basic data for calculating the evaporation capacity and the consumption theoretical standard coal quantity of the coal blending boiler; the basic data module is the basis of other part of calculation, and all basic data must be checked and adjusted before each calculation. The blending combustion scheme module is divided into a standard coal unit price target module and a furnace entering heat value target module; the coal marking unit price target module is a blending combustion scheme which takes controlling the coal marking unit price as a target; the furnace heat value target module is a mixed burning scheme which takes controlling the furnace heat value as a target.
The anti-balance checking module can measure and calculate the efficiency of an anti-balance boiler, the anti-balance heat consumption rate, the anti-balance power generation coal consumption, the anti-balance power supply coal consumption, the anti-balance heat supply coal consumption, the anti-balance standard coal quantity, the anti-balance raw coal quantity and the anti-balance coal-as-fired heat value according to actual data of a production field; defects and deficiencies in the operation of the unit can be analyzed, decision basis is provided for improving the performance of the unit, and positive balance data can be verified through comparison and a negative balance result. And the blending combustion checking module can check the unit price, the heat value and the variable quantity of the blended combustion standard coal according to the coal quantity and the heat value of the high-quality coal and the low-quality coal for guiding blending combustion. And the low-grade heat value checking module can check the boiler evaporation capacity, the total standard coal quantity, the heat value and the raw coal quantity according to each index of production, so that the professional management level of the coal as fired is improved.
After data acquisition is carried out by a data acquisition module, data signatures are stored in an IPFS, the IPFS returns a stored data index hash, the index hash is encrypted by a system public key and then is stored in a block chain, the IPFS can carry out decentralized distributed storage on a large amount of data, the data of a data processing module of a monitoring host server is received in the system and stored on a node of the IPFS, and then data calling of a management module is received; the data acquisition safety and the data storage safety are enhanced.
Example three:
as shown in fig. 2-4, on the basis of the first embodiment, the multiple sensors of different types include a steam flow sensor, a steam pressure sensor, a steam temperature sensor, a feed water pressure sensor, and a feed water temperature sensor of the coal-fired boiler unit; a smoke exhaust temperature sensor, a smoke exhaust oxygen sensor and a carbon monoxide sensor for monitoring smoke exhaust data; the steam flow sensor, the steam pressure sensor and the steam temperature sensor are arranged in a steam pipeline of the boiler; the exhaust gas temperature sensor, the exhaust gas oxygen sensor and the carbon monoxide sensor are uniformly arranged in the boiler exhaust gas pipeline.
The management module is divided into a data layer, a middle layer and an application layer, the data layer stores basic data by adopting a distributed P2P data storage environment, and the management system module is built by using the open cell block; the middle layer comprises an intelligent contract layer and Web3, the application layer is an interaction layer of the monitoring host, and data in the management module is viewed through a visual section of the monitoring host.
Example four:
as shown in fig. 5, the step of preprocessing the collected data by the monitoring host through the data analysis processing module includes: a, clustering and fusing all collected sample data; b, arranging the samples of most types from high to low according to the instability degree; c, deleting most classes with higher instability degree by introducing deletion factors; d, obtaining a new sample data set; the problem that most classes and few classes of the collected data set are unbalanced is solved, the accuracy of the collected data is improved, and errors are reduced.
The monitoring host computer analyzes the collected data through the data analysis processing module in the following specific steps: a: firstly, clustering and calculating the collected flow, pressure and temperature of superheated steam, the pressure and temperature of reheated steam, the pressure and temperature of feed water and the temperature data set of a boiler unit and designating the number of clusters; b, calculating the number of each cluster in each clustering, comparing the number of most samples and the number of few samples in the cluster, and if the number of few samples is more than the number of most samples, positioning a positive cluster by the cluster, otherwise, determining a negative cluster; c, traversing all sample objects, if the real type of the negative type sample is consistent with the type of the cluster, setting a sample type function Y (X) to be 0, and otherwise, setting the sample type function Y (X) to be 1; d, repeating the steps A-C; e, calculating a category function value of the final negative type data sample, and sequencing most types of samples from high to low according to the size of the function value; and F, deleting a plurality of types of samples according to the selected deletion factor according to the proportion to obtain a new data set sample, and then carrying out classification training on the newly generated data set by using a classification algorithm. Through the data processing, most samples mixed in the minority samples can be removed, most samples on the fuzzy boundary of the minority samples and the majority samples can be removed, data with obvious errors are removed, the accuracy of data for collecting the flow, pressure and temperature of superheated steam, the pressure and temperature of reheated steam, the pressure and temperature of feed water and the temperature of a boiler unit is improved, the majority samples and the minority samples are guaranteed to reach balance, and the error influence of the collected data on an evaluation result is reduced.
In the above steps, the positive cluster is a cluster in a certain clusterIn the method, the number of the minority samples is greater than that of the majority samples, otherwise, the number of the minority samples is less than that of the majority samples, and the minority samples are negative clusters; if G isi(u) represents the cluster type of the majority sample point u in the ith clustering, and the clustering frequency is m times, then the category formula of the majority sample satisfies
Figure BDA0003220798150000171
Figure BDA0003220798150000172
Y (X) is a class function, when the majority class samples are positive classes, the function value is 1, and when the majority class samples are positive classes, the function value is-1; fuIs the final class function value, after multiple clustering, if FuIf the number of the samples is more than 0, the samples are considered as unstable points, the samples are actually negative, and the number of times that the samples fall into the positive cluster after clustering is more than that of the negative cluster; if FuAnd if the sample number is less than 0, the majority of samples are considered as stable points, the samples are actually negative, and the number of times that the samples fall in the negative cluster after clustering is greater than that of the positive cluster. Finally F is obtaineduThe values of (A) are arranged from large to small, FuThe larger the value, the more unstable the value can be selectively deleted, and the stability and the accuracy of data classification are increased; however, if the majority of samples are deleted too much, the classification accuracy of the classifier on the majority of samples is obviously reduced, and if the deletion is too little, the classification accuracy of the classifier on the minority of samples is reduced; so a deletion factor δ is introduced, δ ═ the (deleted majority class)/(unstable majority class); the value of delta is more than 0 and less than or equal to 1, and the value range in the scheme is 0.45-0.85.
By the method, the collected data of the exhaust gas temperature, the exhaust gas oxygen concentration and the carbon monoxide concentration are processed, the accuracy of the collected data is increased, the accurate calculation of the emission amount of nitrogen oxides is facilitated, the emission standard is met, the exhaust gas problem and the exhaust fault are conveniently found out in time, and the stable operation of the system is guaranteed.
Example five:
on the basis of the fourth embodiment, after obtaining the new sample data set sample in step F, performing feature extraction on the new sample data set, and selecting time domain, frequency domain and time-frequency domain data features; layering data characteristics according to the temperature of a system coal-fired boiler and the system fault frequency, and finding out a clustering center for each layer by using a clustering algorithm to obtain a few boiler temperature and system fault type sets; the method comprises the steps of re-layering fewer data sets, calculating the center of each cluster of data of a new data type set through clustering, calculating Euclidean distance between the new data type set and each cluster center of each layer of the fewer boiler temperature and system fault type sets, adding the distance of each cluster center of the new data set, classifying the new data according to the distance, layering the new data, judging whether the new data belongs to the smallest set to the bottom layer after the new data is layered to a certain layer, performing classification operation on the trained classifier, performing system evaluation and fault judgment on the boiler unit, the smoke exhaust system and the boiler thermal efficiency of the system to obtain a system evaluation report and a fault report, increasing the accuracy of the system evaluation and judgment, ensuring stable operation of the system, timely eliminating system faults and ensuring system safety.
When abnormal data appear in the evaluation result of the system, the alarm module alarms through the buzzer, in order to increase the accuracy of fault alarm, when the alarm threshold value z of the abnormal data does not obtain the data analysis result of the monitoring host, the data indexes are calculated according to the normal data of each index under each working state of the system, and then according to the mean value mu and the standard variance sigma of the data indexes, the alarm threshold value z meets the following relation:
z＝φ·(μ2+3σ2)1/2(ii) a Phi is a relation factor and has a value range of 0.366-2.626.
Example six:
on the basis of the first embodiment, the basic data module comprises raw coal basic data and production basic data, wherein the raw coal basic data is basic data for calculating standard coal unit price. The data input to the system by the user according to the actual needs of the production field mainly comprises: the method comprises the steps of raw coal execution price lower, heat value demarcation point, low-quality coal execution price, coal slurry execution price, fuel commission, raw coal execution price upper, raw coal heat value entering a plant, low-quality heat value entering the plant and coal slurry heat value entering the plant. When the coal price changes, the basic data of the raw coal changes, and the data is not generally modified. The calorific value of each coal entering a plant is basic data of a blending combustion scheme, and the data needs to be modified during each calculation. The production basic data module is basic data for calculating the evaporation capacity and the consumption theoretical standard coal quantity of the coal blending boiler. The data input by the user according to the actual needs of the production field mainly comprises: generating capacity, steam supply amount, steam supply pressure, circulating water temperature, coal heat value entering a furnace, fly ash carbon content, slag carbon content, exhaust gas temperature, boiler air leakage rate, time period, double-machine time and low water removal and supplement flow. And updating the data according to actual conditions when the user calculates each time.
In the anti-balance checking module, the following data, namely the steam flow, the steam pressure, the steam temperature, the water supply pressure and the water supply temperature of the coal-fired boiler unit are acquired according to the data acquisition module; boiler flue gas temperature, flue gas oxygen concentration, carbon monoxide concentration. The following data were obtained from actual production monitoring: the method comprises the steps of accumulating generated energy, accumulating steam supply, accumulating main steam flow, main steam pressure, main steam temperature, heat supply pressure, steam supply temperature, cold and re-temperature, heat and re-pressure, heat and re-temperature, water supply pressure, water supply temperature, accumulating water supply flow, main desuperheating water pressure, main desuperheating water temperature, main desuperheating water accumulated quantity, reheating desuperheating water temperature, reheating desuperheating water accumulated quantity, fly ash carbon content, slag carbon content, power generation electricity consumption rate, smoke exhaust temperature, air supply temperature, fired coal heat value, consumed raw coal quantity and air-to-air pre-leakage rate, and comparing the values with data obtained by a system evaluation module to check to obtain an anti-balance check result. The result of the anti-balance check mainly comprises parameters such as anti-balance boiler efficiency, anti-balance heat consumption rate, generation balance power generation coal consumption, anti-balance power supply coal consumption, anti-balance heat supply coal consumption, anti-balance standard coal quantity, anti-balance raw coal quantity, anti-balance fired coal heat value and the like. The low calorific value checking module obtains the following parameters: the main steam pressure, the main steam temperature, the reheated steam quantity, the circulating water quantity, the superheating and temperature-reducing water quantity, the reheating and temperature-reducing water quantity, the heat supply temperature and the raw coal quantity for statistics. The user selects whether the electric pump runs according to the running condition of the steam feed pump or the electric feed pump, and the following verification result is obtained through verification: checking the evaporation capacity of the boiler, checking the total standard coal consumption, checking the heat value of the coal as fired, checking the raw coal amount, checking whether the heat value of the coal as fired is higher or lower, and counting the coal amount.
The device obtained by the technical scheme is a coal blending optimization method, and fuel management is enhanced and a coal blending mode is optimized by optimizing functions such as a blending scheme, reverse balance check, blending check, low-grade heat value check and the like, so that the economic benefit of a power plant is improved, the fuel management is enhanced, the fuel refining work is promoted, the standard coal unit price is effectively controlled and reduced, and the fuel cost is reduced; the system is evaluated through collected data analysis, data errors are reduced through analysis and processing of the collected data, accuracy of system evaluation is improved, reduction of system failure rate is facilitated, and stability of system operation is improved. By the method for processing the data through the data processing and analyzing module, most samples mixed in minority samples can be removed, most samples on fuzzy boundaries of the minority samples and the majority samples can be removed, data with obvious errors can be removed, the accuracy of data for collecting superheated steam flow, pressure, temperature, reheat steam pressure, temperature, feedwater pressure temperature and boiler unit temperature is improved, the majority samples and the minority samples are guaranteed to reach balance, and the error influence of the collected data on an evaluation result is reduced. Through the data processing and analyzing module, the collected data of the exhaust gas temperature, the exhaust gas oxygen concentration and the carbon monoxide concentration are processed, the accuracy of the collected data is improved, the accurate calculation of the emission amount of oxynitride is conveniently carried out subsequently, the emission standard is met, the exhaust gas problem and the emission fault are conveniently found out in time, and the stable operation of the system is guaranteed. The classification training method is adopted to carry out system evaluation and fault judgment on the boiler unit, the smoke exhaust system and the boiler thermal efficiency of the system to obtain a system evaluation report and a fault report, so that the accuracy of the system evaluation and judgment is improved, the stable operation of the system is ensured, the system fault is timely eliminated, and the system safety is ensured. The management module of the monitoring host adopts distributed storage for the acquired data and the basic data, and compared with the safety problem of the traditional information management system, the data acquisition safety is further enhancedSex, storage security. By making a pair FuThe values of the data classification method are arranged from large to small, unstable multi-class samples are selectively deleted, the stability and the accuracy of data classification are improved, a deletion factor delta is introduced, the multi-class samples are prevented from being deleted too much or too little, the classification accuracy of the classifier on the samples is improved, and the accuracy of system risk and fault evaluation is improved. The alarm module improves the accuracy of alarm, reduces the probability of false alarm, is beneficial to finding out system faults in time and eliminating the system faults in time by limiting the relation of the mean value, the standard variance and the alarm threshold value and using a combined alarm method for the vibration signal, and ensures the stable operation of the system.
Other technical solutions not described in detail in the present invention are prior art in the field, and are not described herein again.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and it will be apparent to those skilled in the art that various modifications and variations can be made in the present invention; any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (7)

1. A coal blending and burning optimization method is characterized by comprising the following steps:
s1, data acquisition, namely acquiring superheated steam flow, pressure and temperature data of the coal-fired boiler, boiler exhaust smoke temperature, exhaust smoke oxygen content, exhaust smoke carbon monoxide concentration data and boiler unit temperature data through a data acquisition module;
s2, storing data, namely, correspondingly setting a unit database and a configuration database for coal-fired boiler steam data, smoke exhaust data and boiler temperature data, wherein the unit database stores collected data information, and the configuration database stores configuration information;
s3, analyzing the data, comprising the following steps: a, clustering and fusing all collected sample data; b, arranging the samples of most types from high to low according to the instability degree; c, deleting most classes with higher instability degree by introducing deletion factors; d, obtaining a new sample data set;
and S4, performing system evaluation, namely performing system evaluation and fault judgment on the system boiler unit, the smoke exhaust system and the boiler thermal efficiency through data analysis and processing to obtain a system evaluation report and a fault report.
2. The coal blending and burning optimization method of claim 1, wherein in step S2, the signal data collected in the unit database includes real-time data, current data, historical data and abnormal data, and are stored respectively.
3. The coal blending and burning optimization method according to claim 1, wherein in the step S3, the specific steps include A: firstly, clustering and calculating the collected flow, pressure and temperature of superheated steam, the pressure and temperature of reheated steam, the pressure and temperature of feed water and the temperature data set of a boiler unit and designating the number of clusters; and B, calculating the number of each cluster in each clustering, comparing the number of the majority samples and the number of the minority samples in the cluster, and if the number of the minority samples is more than that of the majority samples, positioning the positive cluster in the cluster, otherwise, determining the negative cluster.
4. The coal blending combustion optimization method of claim 1, wherein the step S3 further includes a step C of traversing all sample objects, and if the true category of the negative type sample is consistent with the category of the cluster, the sample category function y (x) is set to 0, otherwise, to 1; d, repeating the steps A-C; e, calculating a category function value of the final negative type data sample, and sequencing most types of samples from high to low according to the size of the function value; and F, deleting a plurality of types of samples according to the selected deletion factor according to the proportion to obtain a new data set sample, and then carrying out classification training on the newly generated data set by using a classification algorithm.
5. The coal blending optimization method according to claim 1, wherein in step S3, deletion factors δ, δ = (deleted majority class samples)/(unstable majority class samples) are introduced; the value of delta is larger than 0 and smaller than or equal to 1, the value range in the scheme is 0.45-0.85, the situation that multiple samples are deleted too much or too little is prevented, the sample classification accuracy of the classifier is improved, and the accuracy of system risk and fault evaluation is improved.
6. The coal blending optimization method of claim 1, wherein in step S4, after step S3, balanced sample data samples are obtained, feature extraction is performed on a new sample data set, and time domain, frequency domain and time-frequency domain data features are selected.
7. The coal blending optimization method according to claim 6, wherein the data features are layered according to the operation state of the system coal-fired boiler and the system fault frequency, and a clustering center is found for each layer by using a clustering algorithm to obtain a small boiler temperature and system fault type set; and re-layering fewer data sets, calculating the center of each cluster of data of a new data type set by clustering, calculating Euclidean distance with each cluster center of each layer of the fewer boiler temperature and system fault type sets, adding the distances of each cluster center of the new data set, classifying the new data according to the distances, layering the new data, judging whether the new data belongs to the minimum set to the bottom layer or not after the new data is layered to a certain layer, performing classification operation on the trained classifier, performing system evaluation and fault judgment on the system boiler unit, the smoke exhaust system and the boiler thermal efficiency to obtain a system evaluation report and a fault report.
CN202110958506.3A 2021-08-19 2021-08-19 Coal blending and burning optimization method Pending CN113657778A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110958506.3A CN113657778A (en) 2021-08-19 2021-08-19 Coal blending and burning optimization method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110958506.3A CN113657778A (en) 2021-08-19 2021-08-19 Coal blending and burning optimization method

Publications (1)

Publication Number Publication Date
CN113657778A true CN113657778A (en) 2021-11-16

Family

ID=78491707

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110958506.3A Pending CN113657778A (en) 2021-08-19 2021-08-19 Coal blending and burning optimization method

Country Status (1)

Country Link
CN (1) CN113657778A (en)

Similar Documents

Publication Publication Date Title
CN104035331B (en) Unit running optimization instructs system and equipment thereof
CN108280047A (en) A kind of fired power generating unit carbon emission accounting method based on field monitoring data
AU2019305721B2 (en) Boiler coal saving control method
CN107103421A (en) The overall evaluation system and its construction method of industry boiler energy-conservation scheme
CN111144609A (en) Boiler exhaust emission prediction model establishing method, prediction method and device
CN107516174B (en) Generation method of power plant technical supervision strategy library
CN116186624A (en) Boiler assessment method and system based on artificial intelligence
CN110298534A (en) F grades of gas-steam combined circulating generation unit energy consumption index on-line monitorings and power consumption analysis method
CN116432123A (en) Electric energy meter fault early warning method based on CART decision tree algorithm
CN109858125B (en) Thermal power unit power supply coal consumption calculation method based on radial basis function neural network
CN116805065B (en) Intelligent management method for monitoring data of coal powder heating furnace burner
Xu et al. A new online optimization method for boiler combustion system based on the data-driven technique and the case-based reasoning principle
CN113504765A (en) Method for optimizing operation of circulating fluidized bed boiler of power plant
CN106056168B (en) The determination method of gas-steam combined circulating generation unit operating condition optimal value
CN113657778A (en) Coal blending and burning optimization method
CN113627679A (en) Coal blending and burning optimization system
CN111797883B (en) Coal type identification method based on random forest
CN114970766A (en) Power station unit operation parameter reference value obtaining method based on linear fitting
CN114139785A (en) Boiler combustion thermal efficiency prediction method and device
CN111091251A (en) Boiler operation optimization method and system based on big data technology
Zhou et al. Prediction Model of Coal Consumption Based on Random Forest Variable Selection and Random-Grid Hyperparametric Optimization Algorithm
CN111651938B (en) Variable coal quality unit output prediction method based on thermodynamic calculation and big data
CN110705881A (en) Boiler efficiency online calculation method and system based on artificial neural network
CN114791102B (en) Combustion optimization control method based on dynamic operation data analysis
Gu et al. A modified fuzzy clustering framework for catalyst activity monitoring in the selective catalytic reduction system

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