CN114791102B - Combustion optimization control method based on dynamic operation data analysis - Google Patents
Combustion optimization control method based on dynamic operation data analysis Download PDFInfo
- Publication number
- CN114791102B CN114791102B CN202210419853.3A CN202210419853A CN114791102B CN 114791102 B CN114791102 B CN 114791102B CN 202210419853 A CN202210419853 A CN 202210419853A CN 114791102 B CN114791102 B CN 114791102B
- Authority
- CN
- China
- Prior art keywords
- operation data
- parameters
- correlation coefficient
- method based
- control method
- 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
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F22—STEAM GENERATION
- F22B—METHODS OF STEAM GENERATION; STEAM BOILERS
- F22B35/00—Control systems for steam boilers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Combustion & Propulsion (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mechanical Engineering (AREA)
- Operations Research (AREA)
- Evolutionary Biology (AREA)
- Chemical & Material Sciences (AREA)
- Thermal Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Regulation And Control Of Combustion (AREA)
- Control Of Steam Boilers And Waste-Gas Boilers (AREA)
Abstract
The invention discloses a combustion optimization control method based on dynamic operation data analysis, which comprises the following steps: acquiring relevant historical operation data stored by a set DCS; grouping the data packets of different loads and air temperature intervals into different data subsets, calculating the average value of each operation parameter of each load and air temperature interval, and carrying out deficiency supplementing and smooth filtering to obtain steady-state components of operation data for analysis; after obtaining the steady-state components, subtracting the corresponding steady-state components from all the running data sets, and obtaining a fluctuation running data set as a result; calculating correlation coefficients between each parameter and the total coal amount and/or the concentration of NOx in the flue gas; and according to the obtained correlation coefficient, giving an optimization suggestion. The invention improves the accuracy of operation control by analyzing and containing dynamic operation data under unsteady state working conditions and extracting feasibility of optimizing operation control rules and revealing the operation characteristics of the unit.
Description
Technical Field
The invention relates to the technical field of correlation analysis and combustion optimization control, in particular to a combustion optimization control method based on dynamic operation data analysis.
Background
Since the intelligent power plant becomes a pursuing hot spot in the power generation industry, the research and development of the intelligent power generation technology in the traditional thermal power industry gradually extends from the application of the advanced information technology on the surface to the research and development level of the underlying core difficult technology. The operation data stored in the DCS system of the power plant is an important basis and condition for the research and development of the intelligent power generation technology. The intelligent power generation technology center can be built in a technical institute of a certain scale power generation group, and the development of an intelligent technology can be intensively carried out; each power plant and generator set transmits real-time data and information to the center, and obtains technical support in aspects of intelligent control, intelligent operation and maintenance, intelligent management and the like from the center. However, so far, the theory and technology for intelligently applying the unit operation history data are insufficient. Researchers in recent years also propose dividing the whole boiler working condition into different partitions, and solving the problem of multi-objective combustion optimization through a data-driven mixing strategy; the method for determining the operation optimization target value based on the fuzzy association rule is provided, and a data mining technology is introduced into the optimization process of the thermal power plant; an integrated combustion optimization system ThermalNet based on a Deep Q Network (DQN) and Long and Short Term Memory (LSTM) module; generating some data by Computational Fluid Dynamics (CFD) simulation as training samples for modeling an artificial neural network, and adding operation history operation data to establish an Artificial Neural Network (ANN) model for predicting the operation and emission characteristics of the boiler; the dynamic data mining model is used for adjusting methods such as door flow characteristic calculation and the like to improve the efficiency and the intelligent degree of unit operation. Because the unit operation is always in the dynamic change process, the average value of the system parameters in the same period is considered to be required to truly reflect the unit operation state under the relatively stable working condition of the unit, and therefore the stable working condition of the unit needs to be defined, and the sample data set is calculated and selected.
In China, a thermal power generating unit NOx combustion optimizing method and system is disclosed (application number: 201310574516.2, authorized bulletin number: CN 103574581B), and boiler operation parameters are collected; calculating a correlation coefficient between the boiler operation parameter and the boiler efficiency and NOx emission, and selecting the boiler operation parameter conforming to the correlation coefficient condition; and calculating the boiler efficiency and the NOx emission according to the selected boiler operation parameters meeting the correlation coefficient conditions, and adjusting the operation parameters of the boiler according to the boiler operation parameters meeting the boiler efficiency and the NOx emission conditions.
Aiming at the patent, a thermal power generating unit NOx combustion optimization method and system find the following defects: since the unit operation parameters change more severely, the unit economic index deviation calculated by the change parameters is larger. Therefore, most documents consider that only data under stable working conditions are valid and have reference value when analyzing the operating economy of the unit. The data in the unit history database records all the operation conditions of the unit, so that the history data needs to be detected and identified in an effective condition.
Disclosure of Invention
The invention provides a combustion optimization control method based on dynamic operation data analysis, which combines steady-state components and fluctuation data to perform correlation analysis.
The invention is realized in the following way: a combustion optimization control method based on dynamic operation data analysis is characterized in that: the method comprises the following steps:
step 1: acquiring relevant historical operation data stored by a DCS in a period of time in the past of the unit;
step 2: let the total operational dataset be: a (M, k), where M is the sampling number, m=1, 2,3. K represents an operating parameter, k=1, 2,3. Grouping data packets with different loads and air temperature intervals into different data subsets, wherein the operation data are expressed as: x (I, j, k, l) I represents the number of divided load sections, i=1, 2,3. J represents the number of divided air temperature intervals, j=1, 2,3. K represents an operating parameter, k=1, 2,3. L represents the number of data packets in the subset, i.e., the number of working points, i=1, 2, 3..l (i, j), where the number of working points in each subset is different, m= Σl (i, j); calculating the average value of all the operating parameters in the operating data subsets of different loads and different air temperature intervals by the formula (1):
step 3: for the calculatedPerforming deficiency compensation and smoothing filtering to obtain steady-state component of the operation data for further analysis>
Step 4: after obtaining the steady-state components of the operating data, the corresponding steady-state components are subtracted from the entire operating data set A (m, k)The result is a wave-running dataset;
step 5: calculating correlation coefficients between each parameter and the total coal amount and/or the concentration of NOx in the flue gas;
step 6: and according to the obtained correlation coefficient, analyzing the influence of the operation parameters with positive correlation coefficient larger than 0.1 and negative correlation coefficient smaller than-0.1 on the combustion economy and pollutant generation, and giving optimization suggestions.
Preferably, in the step 1, relevant historical operation data stored in DCS during a period of time in the past of the unit is obtained, and the whole load and air temperature intervals of the unit can be divided into 20-30 intervals.
Preferably, the operation parameters selected in the step 2 cover main monitoring and control parameters of boiler operation, including actual load, flow, pressure, temperature, water supply flow, total fuel quantity, coal supply quantity of each layer (corner) burner, total air quantity, air supply quantity, air intake quantity, total secondary air valve opening, flue gas oxygen content, flue gas temperature, NOx concentration, and blower inlet air temperature.
Preferably, in the step 4, the relative fluctuation component Δa (m, k) is further calculated as follows, according to the large difference between the values of the different operation parameters:
and (i, j) is the load and air temperature interval serial number of the m sampling time unit.
Preferably, in the step 5, a linear correlation coefficient method is used to calculate a correlation coefficient between each parameter and the total coal amount and/or the flue gas NOx concentration:
wherein: the correlation coefficient r (k, k ') is for all k sampling parameters, when r (k, k ')=r (k ', k) and r (k, k) =1; and analyzing the change condition of the correlation coefficient between each sampling parameter and all other sampling parameters.
Preferably, in the step 6, the size of the DCS fuel quantity is selected to be directly used as a reference index for evaluating the boiler efficiency and the unit economy, and the NOx emission value is added to be jointly used as a screening basis of the optimized working condition;
where L ' (i ', j ') is a subset of L (i, j), k Fuel Is the size, k of DCS fuel quantity NO Is the NOx emission value.
And (3) calculating the average value of each section by using the formula (1) after obtaining L ' (i ', j ') as a basis for optimizing the control parameters.
The invention has the beneficial effects that:
1. according to the method, on the basis that all unit dynamic operation data in a period of time are divided into two-dimensional intervals according to load and air temperature, the average value of the operation data in different load and air temperature intervals is calculated, the correlation coefficient between all operation parameter dynamic components is calculated, fluctuation data is obtained, the characteristic of the correlation change rule among the operation parameters is revealed through the fluctuation data, reference is provided for an operator to control the operation data of the boiler, the stability of boiler+operation is improved, and the number of boiler alarming times is reduced.
2. By selecting the running data of the unit containing the dynamic working condition, the working condition is divided into finer according to the load and the air temperature, the boiler running result using the optimization rule shows that the boiler efficiency is obviously improved, the NOx emission is obviously reduced, the obtained steady-state component and fluctuation component are more accurate, the calculated correlation coefficient is more accurate, and the obtained optimization method is more applicable.
Drawings
FIG. 1 is a flow chart of the operation of the present invention.
FIG. 2 is a schematic diagram of the main steam flow over time.
Fig. 3 is a graph comparing the total coal amount and the total air amount in the actual running value, the average running value and the relative pulsation value of the parameters.
FIG. 4 is a graph comparing the flue gas NOx concentration and the flue gas oxygen content in the actual operating values, the average operating values and the relative pulsation values of the parameters.
Fig. 5 is a graph comparing the actual operating values, average operating values and the relative pulsation values of the main steam temperature and the position of the B back wall over-fire air outlet electric regulating door 1.
Detailed Description
The invention is further outlined below in connection with the accompanying drawings.
A combustion optimizing control method based on dynamic operation data analysis,
step 1: acquiring relevant historical operation data stored by DCS of the past year of the unit;
selecting historical data stored by DCS in the past year period of the unit, dividing the whole load and air temperature interval of the unit into 20-30 intervals respectively by taking 1-3min as a period, and regarding a 600 MW-level unit, basically changing the load in one load section by 10MW, wherein the load is basically unchanged;
step 2: let the total operational dataset be: a (M, k), where M is the sampling number, m=1, 2,3. K represents an operating parameter, k=1, 2,3. Grouping data packets with different loads and air temperature intervals into different data subsets, wherein the operation data are expressed as: x (I, j, k, l) I represents the number of divided load sections, i=1, 2,3. J represents the number of divided air temperature intervals, j=1, 2,3. K represents an operating parameter, k=1, 2,3. L represents the number of data packets in the subset, i.e., the number of working points, i=1, 2, 3..l (i, j), where the number of working points in each subset is different, m= Σl (i, j); the selected operation parameters comprise main monitoring and control parameters of boiler operation, including actual load, flow, pressure, temperature, water supply flow, total fuel quantity, coal supply quantity of each layer (corner) burner, total air quantity, air supply quantity, air intake quantity, total secondary air valve opening, flue gas oxygen content, flue gas exhaust temperature, NOx concentration and blower inlet air temperature;
calculating the average value of all the operating parameters in the operating data subsets of different loads and different air temperature intervals by the formula (1):
step 3: for the calculatedPerforming deficiency compensation and smoothing filtering to obtain steady-state component of operation data for further analysis>
Step 4: after obtaining the steady-state components of the operating data, the corresponding steady-state components are subtracted from the entire operating data set A (m, k)The result is a wave-running dataset;
the relative fluctuation component Δa (m, k) is further calculated as follows, based on the large difference in values of the different operating parameters:
wherein, (i, j) is the load and air temperature interval serial number of the m sampling time unit;
step 5: calculating correlation coefficients between each parameter and the total coal amount and/or the concentration of NOx in the flue gas;
calculating the correlation coefficient between each parameter and the total coal amount and/or the concentration of NOx in the flue gas by adopting a linear correlation coefficient method:
wherein: the correlation coefficient r (k, k ') is for all k sampling parameters, when r (k, k ')=r (k ', k) and r (k, k) =1; analyzing the change condition of the correlation coefficient between each sampling parameter and all other sampling parameters;
step 6: according to the obtained correlation coefficient, analyzing the influence of the operation parameters with positive correlation coefficient more than 0.1 and negative correlation coefficient less than-0.1 on the combustion economy and pollutant generation; giving an optimization suggestion; the DCS fuel quantity is directly used as a boiler efficiency and unit economy evaluation reference index; adding NOx emission values, and jointly using the NOx emission values as an optimization working condition screening basis;
where L ' (i ', j ') is a subset of L (i, j), k Fuel Is the size, k of DCS fuel quantity NO Generating or emitting values for NOx;
after the obtained L ' (i ', j '), the mean value of each section is calculated using formula (1) as a basis for optimizing the control parameters.
A350 MW coal-fired steam turbine generator unit of a certain power plant is adopted for data operation analysis and optimization operation test, a unit boiler is selected as a supercritical parameter variable-pressure operation direct-current furnace, the Oriental boiler (group) is designed and manufactured by the company Limited, and the boiler model is DG1150/25.4-n2 type. The type is a single hearth, front and rear wall opposite firing mode, a tail double-flue structure, and adopts a baffle plate to adjust the temperature of a reheater, one-time reheating, balanced ventilation, solid slag discharge, an all-steel framework, a full-suspension structure and door-type open air arrangement. A membrane water-cooled wall is arranged in a boiler furnace, a screen type superheater is arranged at the outlet of the furnace, a high-temperature and low-temperature two-stage superheater is arranged in a horizontal flue, two-stage economizers and two-stage air preheaters are arranged in a staggered mode in a tail vertical shaft, and the horizontal flue and a steering chamber are membrane wall ceiling pipes Bao Qiangguan. The width of the boiler is 15101.2mm, and the depth of the boiler is 13678.8mm. Adopts a medium speed coal mill, a positive pressure direct blowing and negative pressure hearth of a cold primary air machine and a balanced ventilation powder making combustion system. 5 medium speed coal mills are matched, 4 of the medium speed coal mills are operated, and 1 medium speed coal mill is reserved. Pulverized coal fineness rg=21%. The number of operation data collection is 24000, and the operation data is about 16 days, with 1 minute as a sampling period.
The main steam flow is selected as a marking parameter of the boiler and the unit output, and fig. 2 is a data diagram of the change of the main steam flow along with time. Typical parameter actual operating values, average operating values and relative pulsation value comparisons are shown in fig. 3, 4 and 5, and include total coal amount (a), total air quantity (B), flue gas NOx concentration (c), flue gas oxygen amount (d), main steam temperature (e) and B rear wall overfire air outlet electric adjustment door 1 position (f). The pulsation values are shown below the figures. The position of the electric regulating door 1 of the over-fire air outlet of the rear wall B has obvious change along with the load; the oxygen content of the flue gas changes with the load to a certain extent; the NOx concentration of the flue gas and the temperature of the main steam are not obviously changed along with the load. Their pulsation values are all close to random numbers with 0 mean.
Table 1 shows the total analysis parameters and the total coal amount on the left side; the middle side is the NOx concentration of the flue gas at the inlet of the reactor at the side A of the #2 furnace; the right side is the correlation coefficient of the total coal amount + #2 furnace A side reactor inlet flue gas NOx concentration.
Analysis of the data in Table 1 shows that the positive correlation coefficient between the parameters such as total air quantity, flue gas oxygen quantity, fan A, B movable vane regulating gate control command, air intake quantity, flue gas NOx concentration at the inlet of the reactor on the side of the #2 furnace B, #2A, #2B ammonia gas flow before the mixer, flue gas oxygen quantity, D group of burners A side, B side, C group of burners B side, A side secondary air main regulating gate position and the like and the coal quantity or flue gas NOx concentration is large, and proper reduction of the parameters is beneficial to reducing the total coal consumption, reducing pollutant emission, improving the economy of unit operation and the like.
In table 1, the positive correlation coefficient is greater than the threshold of 0.1, representing a significant co-directional change between the two parameters; the coal feed rate of coal feeder A, B, E, #1, #2SCR reactor ammonia dilution air flow, means that the fuel consumption will respond to a decrease; as shown in Table 1, the NOx concentration at the inlet flue gas of the reactor on the side A of the #2 furnace and the NOx concentration at the inlet flue gas of the reactor on the side B of the #2 furnace, and the steam pressure at the header of the high-temperature superheater on the side A and the B show that the parameter values are inversely related to the total coal quantity, and the parameters should be increased appropriately in order to reduce the total fuel quantity consumption during operation.
In actual operation, the operation economy is not simply pursued, or the emission of nitrogen oxides is generally comprehensively optimized in economy and pollutant generation. Optimizing control rules according to the operation parameters obtained by dynamic data analysis, subtracting the positive and negative of the result obtained by the running average value of each parameter, namely optimizing the adjustment direction; the adjustment direction of the main control parameters with positive correlation coefficient larger than 0.1 obtained by comprehensively considering the coal quantity and NOx on the right side in the table 1 is consistent, and the result obtained by the correlation analysis of the dynamic component of the dynamic operation data is proved to have an internal relation with the combustion optimization.
Working principle: on the basis that the dynamic operation data of all units in a period of time are divided into two-dimensional intervals according to the load and the air temperature, the average value of the operation data in different load and air temperature intervals is calculated, then the average value is subtracted from the actual operation data, the dynamic components of the operation data are obtained, and the correlation coefficient among the dynamic components of all operation parameters is calculated. The calculated correlation coefficients of the total coal amount, the NOx generation amount, and the comprehensive parameters of the total coal amount and the NOx generation amount and the dynamic components of all the operation parameters are given, and the influences of the operation parameters with positive correlation coefficients larger than 0.1 and negative correlation coefficients smaller than-0.1 on the combustion economy and pollutant generation are analyzed, and the suggestion of operation optimization adjustment is made.
The foregoing description is only illustrative of the invention and is not to be construed as limiting the invention. Various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, or the like, which is within the spirit and principles of the present invention, should be included in the scope of the claims of the present invention.
Claims (7)
1. A combustion optimization control method based on dynamic operation data analysis is characterized in that: the method comprises the following steps:
step 1: acquiring relevant historical operation data stored by a DCS in a period of time in the past of the unit;
step 2: let the total operational dataset be: a (M, k), where M is the sampling number, m=1, 2,3. K represents an operating parameter, k=1, 2,3. Grouping data packets with different loads and air temperature intervals into different data subsets, wherein the operation data are expressed as: x (I, j, k, l) I represents the number of divided load sections, i=1, 2,3. J represents the number of divided air temperature intervals, j=1, 2,3. K represents an operating parameter, k=1, 2,3. L represents the number of data packets in the subset, i.e., the number of working points, i=1, 2, 3..l (i, j), where the number of working points in each subset is different, m= Σl (i, j); calculating the average value of all the operating parameters in the operating data subsets of different loads and different air temperature intervals by the formula (1):
step 3: for the calculatedPerforming deficiency compensation and smoothing filtering to obtain steady-state component of the operation data for further analysis>
Step 4: after obtaining the steady-state components of the operating data, the corresponding steady-state components are subtracted from the entire operating data set A (m, k)The result is a wave-running dataset;
step 5: calculating correlation coefficients between each parameter and the total coal amount and/or the concentration of NOx in the flue gas;
step 6: and according to the obtained correlation coefficient, analyzing the influence of the operation parameters with positive correlation coefficient larger than 0.1 and negative correlation coefficient smaller than-0.1 on the combustion economy and pollutant generation, and giving optimization suggestions.
2. The combustion optimization control method based on dynamic operation data analysis according to claim 1, wherein: in the step 1, relevant historical operation data stored in the DCS in a period of time in the past of the unit is obtained, and the whole load and air temperature interval of the unit are divided into 20-30 intervals respectively.
3. The combustion optimization control method based on dynamic operation data analysis according to claim 1, wherein: the operation parameters selected in the step 2 cover main monitoring and control parameters of boiler operation, including actual load, flow, pressure, temperature, water supply flow, total fuel quantity, coal supply quantity of each layer of burner, total air quantity, air supply quantity, air intake quantity, total secondary air valve opening, flue gas oxygen content, flue gas exhaust temperature and NO x Concentration and blower inlet air temperature parameters.
4. The combustion optimization control method based on dynamic operation data analysis according to claim 1, wherein: in the step 4, the relative fluctuation component Δa (m, k) is further calculated as follows according to the larger value difference of different operation parameters:
and (i, j) is the load and air temperature interval serial number of the m sampling time unit.
5. The combustion optimization control method based on dynamic operation data analysis according to claim 1, wherein: in the step 5, a linear correlation coefficient method is adopted to calculate the correlation coefficient between each parameter and the total coal amount and/or the concentration of NOx in the flue gas:
wherein: the correlation coefficient r (k, k ') is r (k, k ')=r (k ', k) and r (k, k) =1 for all k sampling parameters; and analyzing the change condition of the correlation coefficient between each sampling parameter and all other sampling parameters.
6. The combustion optimization control method based on dynamic operation data analysis according to claim 1, wherein: in the step 6, the fuel quantity recorded by DCS is selected to be directly used as a reference index for evaluating the boiler efficiency and the unit economy, and the NOx emission value is added to be jointly used as a screening basis of the optimized working condition;
where L ' (i ', j ') is a subset of L (i, j), k Fuel Is the size, k of DCS fuel quantity NO Is the amount of NOx emissions.
7. The combustion optimization control method based on dynamic operation data analysis according to claim 6, wherein: and (3) calculating the average value of each section by using the formula (1) after obtaining L ' (i ', j ') as a basis for optimizing the control parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210419853.3A CN114791102B (en) | 2022-04-21 | 2022-04-21 | Combustion optimization control method based on dynamic operation data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210419853.3A CN114791102B (en) | 2022-04-21 | 2022-04-21 | Combustion optimization control method based on dynamic operation data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114791102A CN114791102A (en) | 2022-07-26 |
| CN114791102B true CN114791102B (en) | 2023-09-22 |
Family
ID=82462654
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210419853.3A Active CN114791102B (en) | 2022-04-21 | 2022-04-21 | Combustion optimization control method based on dynamic operation data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114791102B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008003304A1 (en) * | 2006-07-07 | 2008-01-10 | Alstom Technology Ltd. | Method for controlling the combustion air supply in a steam generator that is fueled with fossil fuels |
| CN103256719A (en) * | 2013-04-27 | 2013-08-21 | 深圳市佳运通电子有限公司 | Furnace condition optimizing and monitoring device and method using same for optimizing |
| CN103574581A (en) * | 2013-11-15 | 2014-02-12 | 神华集团有限责任公司 | Thermal power generating unit NOx combustion optimization method and system |
| CN103759290A (en) * | 2014-01-16 | 2014-04-30 | 广东电网公司电力科学研究院 | Large coal-fired unit online monitoring and optimal control system and implementation method thereof |
| EP3088803A1 (en) * | 2015-04-30 | 2016-11-02 | General Electric Company | Combustion optimization system and method |
| WO2020088485A1 (en) * | 2018-11-02 | 2020-05-07 | 浙江大学 | Intelligent multi-pollutant ultra-low emission system and global optimization method |
| WO2020181679A1 (en) * | 2019-03-13 | 2020-09-17 | 西安交通大学 | Control method for transient varying load coal supply quantity considering exergy storage modification of coal-fired boiler |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102106827B1 (en) * | 2018-11-30 | 2020-05-06 | 두산중공업 주식회사 | System and method for optimizing boiler combustion |
-
2022
- 2022-04-21 CN CN202210419853.3A patent/CN114791102B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008003304A1 (en) * | 2006-07-07 | 2008-01-10 | Alstom Technology Ltd. | Method for controlling the combustion air supply in a steam generator that is fueled with fossil fuels |
| CN101490476A (en) * | 2006-07-07 | 2009-07-22 | 阿尔斯通技术有限公司 | Method for controlling the combustion air supply in a steam generator that is fueled with fossil fuels |
| CN103256719A (en) * | 2013-04-27 | 2013-08-21 | 深圳市佳运通电子有限公司 | Furnace condition optimizing and monitoring device and method using same for optimizing |
| CN103574581A (en) * | 2013-11-15 | 2014-02-12 | 神华集团有限责任公司 | Thermal power generating unit NOx combustion optimization method and system |
| CN103759290A (en) * | 2014-01-16 | 2014-04-30 | 广东电网公司电力科学研究院 | Large coal-fired unit online monitoring and optimal control system and implementation method thereof |
| EP3088803A1 (en) * | 2015-04-30 | 2016-11-02 | General Electric Company | Combustion optimization system and method |
| WO2020088485A1 (en) * | 2018-11-02 | 2020-05-07 | 浙江大学 | Intelligent multi-pollutant ultra-low emission system and global optimization method |
| WO2020181679A1 (en) * | 2019-03-13 | 2020-09-17 | 西安交通大学 | Control method for transient varying load coal supply quantity considering exergy storage modification of coal-fired boiler |
Non-Patent Citations (4)
| Title |
|---|
| 变负荷工况下NO_x排放量预测控制;唐振浩;张海洋;曹生现;;化工进展(第01期);全文 * |
| 基于工况划分的机组优化运行寻优方法;徐廖斌等;《节能技术》;第第36卷卷(第第2期期);全文 * |
| 基于滑动判别算法的低NO_x燃烧优化分析;张尚志;谭鹏;何彪;张成;方庆艳;陈刚;;热力发电(第05期);全文 * |
| 运行数据动态分量的相关性分析机器在燃烧优化中的应用;王国栋等;《广东电力》;第第35卷卷(第第7期期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114791102A (en) | 2022-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103576655B (en) | A kind of power boiler burning subspace modeling and Multipurpose Optimal Method and system | |
| CN110263452B (en) | Flue gas time distribution characteristic analysis method and system in flue and denitration system | |
| CN104613468B (en) | Circulating fluidized bedboiler combustion optimizing control method based on fuzzy adaptive inference | |
| CN109695892B (en) | Method and device for protecting wall temperature of heating surface of boiler | |
| CN111623369B (en) | Control method for adjusting boiler fuel feeding quantity by using smoke oxygen content signal | |
| CN112628712A (en) | Secondary air closed-loop optimization control system based on air door resistance coefficient | |
| CN111881554B (en) | Optimization control method for boiler changing along with air temperature | |
| CN103279658A (en) | Thermal generator set working condition optimizing method | |
| CN110207094A (en) | IQGA-SVR boiler heating surface fouling characteristics discrimination method based on principal component analysis | |
| CN111457392B (en) | Intelligent setting method for air quantity in urban domestic garbage incineration process | |
| CN112016754A (en) | Power station boiler exhaust gas temperature advanced prediction system and method based on neural network | |
| CN113033873A (en) | Method for predicting content of sulfur oxides at inlet of desulfurization system based on measurement of coal quality entering furnace | |
| CN115145152A (en) | Boiler combustion and denitration process collaborative optimization control method | |
| CN104729888B (en) | Flue fly ash constant-speed sampling system based on BP neural network and control method | |
| CN114035434B (en) | Operation optimization method of gas-steam combined cycle power generation system | |
| CN114791102B (en) | Combustion optimization control method based on dynamic operation data analysis | |
| CN110699502A (en) | Method for high-precision prediction of gas consumption of blast furnace hot blast stove | |
| CN115437245A (en) | Boiler optimization control method based on combustion state prediction model | |
| CN112833409A (en) | Hearth soot blowing optimization method based on dynamic loss prediction | |
| CN115111601B (en) | Multi-target boiler combustion optimization control method based on embedded algorithm fusion under variable load | |
| CN114427688A (en) | Closed-loop combustion optimization control method based on air temperature influence structure on boiler operation | |
| CN213178308U (en) | Slagging-off prevention system of ultra-supercritical pulverized coal boiler | |
| CN205316379U (en) | Boiler operation oxygen volume automatic control system and boiler | |
| CN110647560B (en) | Mechanism and brain-like intelligence combined online soft measurement method for coal quality of fired coal of power plant | |
| CN113609684A (en) | Method for optimizing steam production of coal per ton of boiler based on industrial data and process mechanism |
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 |