CN117352079A - Method and system for obtaining step response curve of pressure change rate to fuel - Google Patents
Method and system for obtaining step response curve of pressure change rate to fuel Download PDFInfo
- Publication number
- CN117352079A CN117352079A CN202311410665.5A CN202311410665A CN117352079A CN 117352079 A CN117352079 A CN 117352079A CN 202311410665 A CN202311410665 A CN 202311410665A CN 117352079 A CN117352079 A CN 117352079A
- Authority
- CN
- China
- Prior art keywords
- training data
- boiler
- final
- response curve
- fuel
- 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.)
- Granted
Links
- 239000000446 fuel Substances 0.000 title claims abstract description 126
- 230000008859 change Effects 0.000 title claims abstract description 118
- 230000004044 response Effects 0.000 title claims abstract description 110
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 201
- 238000002485 combustion reaction Methods 0.000 claims abstract description 80
- 230000001419 dependent effect Effects 0.000 claims abstract description 18
- 238000010801 machine learning Methods 0.000 claims abstract description 18
- 238000004519 manufacturing process Methods 0.000 claims description 65
- 230000007704 transition Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 10
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/10—Analysis or design of chemical reactions, syntheses or processes
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
- F23N—REGULATING OR CONTROLLING COMBUSTION
- F23N5/00—Systems for controlling combustion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
- F23N—REGULATING OR CONTROLLING COMBUSTION
- F23N2223/00—Signal processing; Details thereof
- F23N2223/10—Correlation
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Crystallography & Structural Chemistry (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Analytical Chemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Control Of Steam Boilers And Waste-Gas Boilers (AREA)
Abstract
The invention relates to a method and a system for acquiring a step response curve of a pressure change rate to fuel, wherein the method comprises the following steps: s1, inputting the current furnace temperature of a boiler into a pre-acquired combustion speed model, and acquiring a current heat release time predicted value; taking a designated time mark as a dependent variable in advance, taking a combustion temperature mark value corresponding to the designated time mark as an independent variable, training a preset unitary linear machine learning regression model, and obtaining a combustion speed model; s2, inputting a typical combustion temperature corresponding to a first step response curve obtained in advance into the combustion speed model, and obtaining a typical heat release time predicted value; the first step response curve is a step response curve of the rate of pressure change versus fuel; and S3, obtaining a step response curve of the final pressure change rate to the fuel based on the current heat release time predicted value, the typical heat release time predicted value and a first step response curve obtained in advance.
Description
Technical Field
The invention relates to the technical field of fluidized bed boilers, in particular to a method and a system for acquiring a step response curve of a pressure change rate to fuel.
Background
The steam pressure of the industrial fluidized bed boiler is a main control parameter of the operation of the unit, and directly affects the safe and economic operation of the unit. Among existing pressure control methods, controlling pressure using Model Predictive Control (MPC) is a relatively advanced and effective control method. Wherein, the step response curve of the pressure change rate relative to the fuel is obtained and is a core part in the model prediction operation.
However, to obtain an accurate step response curve, it typically takes a significant amount of time and effort to perform the step response test, which makes the cost of implementing model predictive control typically quite high; meanwhile, when the load change of the boiler is large, the influence of the combustion temperature on the combustion speed is remarkable, so that the step response curve of the pressure on the fuel is also influenced. Therefore, to cover the actual production load of the boiler, a plurality of experiments are required, which further increases the actual cost of the model predictive control work.
Disclosure of Invention
In view of the above-described shortcomings and drawbacks of the prior art, the present invention provides a method and system for obtaining a step response curve of a rate of pressure change versus fuel.
In order to achieve the above purpose, the main technical scheme adopted by the invention comprises the following steps:
in a first aspect, an embodiment of the present invention provides a method of obtaining a step response curve of a rate of pressure change versus fuel, comprising:
s1, inputting the current furnace temperature of a boiler into a pre-acquired combustion speed model, and acquiring a current heat release time predicted value;
taking a designated time mark as a dependent variable in advance, taking a combustion temperature mark value corresponding to the designated time mark as an independent variable, and training a preset unitary linear machine learning regression model to obtain the combustion speed model;
s2, inputting a typical combustion temperature corresponding to a first step response curve obtained in advance into the combustion speed model, and obtaining a typical heat release time predicted value;
the first step response curve is a step response curve of the pressure change rate relative to the fuel;
and S3, obtaining a step response curve of the final pressure change rate to the fuel based on the current heat release time predicted value, the typical heat release time predicted value and a first step response curve obtained in advance.
Preferably, the step S3 specifically includes:
s31, acquiring a ratio of the current heat release time predicted value to the typical heat release time predicted value based on the current heat release time predicted value and the typical heat release time predicted value;
s32, multiplying all time marks corresponding to the first step response curve obtained in advance by the ratio to obtain a new time mark, and obtaining a step response curve of the final pressure change rate to combustion.
Preferably, before S1, the method further comprises:
s01, acquiring a first training data set according to boiler historical production data acquired in advance;
the boiler historical production data comprises a plurality of pieces of first production data acquired according to a preset time interval;
wherein each piece of first production data includes: a time stamp, a fuel flow, a boiler furnace temperature, a boiler main steam pressure, a boiler main steam flow, a boiler main steam temperature, a boiler feed water pressure corresponding to the first production data;
s02, respectively acquiring step response curves of heat to fuel under different combustion temperature mark values according to the first training data set;
s03, acquiring a combustion speed model according to step response curves of heat to fuel under different combustion temperature mark values.
Preferably, the S01 specifically includes:
s01-1, according to pre-acquired boiler historical production data, forming an initial first training data corresponding to any first production data with a time mark in a first appointed time period, wherein the time mark, the fuel flow and the boiler furnace temperature are in the first production data;
s01-2, acquiring total heat of main boiler steam corresponding to initial first training data according to the first production data corresponding to the initial first training data;
the total heat obtained by the main steam of the boiler is obtained by multiplying the unit obtained heat of the main steam of the boiler by the main steam flow of the boiler; the unit obtained heat of the main steam of the boiler is obtained by differencing the unit enthalpy value of the main steam of the boiler and the unit enthalpy value of the water supply of the boiler; the unit enthalpy value of the main steam of the boiler is calculated by the main steam pressure of the boiler and the main steam temperature of the boiler; the boiler feed water unit enthalpy value is calculated by the boiler feed water temperature and the boiler feed water pressure;
s01-3, adding the total heat obtained by the main steam of the boiler into corresponding initial first training data respectively to obtain intermediate first training data, and sequentially arranging all the intermediate first training data according to time marks to form a first training data set.
Preferably, the S02 specifically includes:
s02-1, respectively differentiating the total heat obtained by the fuel flow and the main steam in each middle first training data in the first training data set with the total heat obtained by the main steam in the middle first training data before a first preset difference time period of a time mark in the middle first training data to obtain a fuel flow variation corresponding to the middle first training data and a total heat variation obtained by the main steam of the boiler, and adding the fuel flow variation and the total heat variation obtained by the main steam of the boiler into the middle first training data to obtain final second production data;
s02-2, forming a final first training data set by all final second production data;
s02-3, dividing the final first training data set into k subsets according to the sequence of the boiler furnace temperatures in the final second production data from high to low, and taking the average value of the boiler furnace temperatures in all the final second production data in each subset as a combustion temperature marking value corresponding to the subset; wherein k is a preset value;
s02-4, taking the total heat variation obtained by the main steam of the boiler in any final second production data in any subset as a dependent variable, taking the fuel flow variation in all final second production data in a first time period before the time marking of the final second production data as the independent variable, and training a preset multi-element linear machine learning regression model to obtain a heat variation model corresponding to the subset;
S02-5, regarding a pre-constructed unit step fuel change curve corresponding to any subset, taking a first preset differential time period as a first step length, taking the step transition time of the unit step fuel change curve as a time starting point, sequentially calling a heat change model corresponding to the subset in a first duration to obtain a heat change predicted value of each first step length, and accumulating the heat change predicted value of each first step length to obtain a heat change total predicted value of each first step length corresponding to the subset;
s02-6, the predicted value of the total heat change amount of each first step length in the first time period corresponding to the subset is sequentially connected to form a step response curve of heat to fuel under the combustion temperature mark value corresponding to the subset.
Preferably, the step S03 specifically includes:
s03-1, aiming at a step response curve of heat corresponding to any subset and fuel, screening out a time mark corresponding to the ratio meeting a preset first condition from the ratio of the predicted value of the total heat change amount of each first step in the step response curve of heat corresponding to the subset and the predicted value of the total heat change amount of the last first step in the step response curve of heat corresponding to the subset, and taking the time mark as a first time mark corresponding to the subset;
The time mark corresponding to the ratio meeting the preset first condition is a time mark with the first ratio being more than or equal to x% of the preset heat release amount parameter; wherein x is a preset value;
s03-2, training a preset unitary linear machine learning regression model by taking the first time marks corresponding to each subset as dependent variables and taking the combustion temperature mark values corresponding to the subsets as independent variables to obtain a combustion speed model.
Preferably, before S1, the method further comprises:
s04, acquiring a second training data set according to boiler historical production data acquired in advance;
s05, acquiring a first step response curve according to the second training data set.
Preferably, the S04 specifically includes:
s04-1, according to the boiler historical production data acquired in advance, forming an initial second training data corresponding to any piece of first production data with a time mark in a second designated time period, wherein the initial second training data corresponds to the first production data, and the initial second training data corresponds to the initial second training data;
s04-2, sequentially arranging all initial second training data according to a time mark sequence to form a second training data set.
Preferably, the step S05 specifically includes:
s05-1, respectively differentiating the fuel flow and the main steam pressure of the boiler in each initial second training data in the second training data set with the fuel flow and the main steam pressure of the boiler in the initial second training data before a second preset difference time period of the time mark in the initial second training data to obtain a fuel flow variable quantity and a main steam pressure variable quantity corresponding to the initial second training data, and adding the fuel flow variable quantity and the main steam pressure variable quantity into the initial second training data to obtain middle second training data;
s05-2, forming all the intermediate second training data into an intermediate second training data set;
s05-3, differentiating the boiler main steam pressure variable quantity in each intermediate second training data in the intermediate second training data set with the boiler main steam pressure variable quantity in the intermediate second training data before a second preset differential time period in the intermediate second training data to obtain a boiler main steam pressure second-order variable quantity corresponding to the intermediate second training data, adding the boiler main steam pressure second-order variable quantity into the intermediate second training data to obtain final second training data, and forming all final second training data into a final second training data set;
S05-4, taking the second-order variable quantity of the main steam pressure of the boiler in any one of the final second training data in the final second training data set as a dependent variable, taking the variable quantity of the fuel flow in all final second training data in a second time period before the time mark of the final second training data as the independent variable, and training a preset multi-element linear machine learning regression model to obtain a pressure trend change model;
s05-5, aiming at a pre-constructed unit step fuel change amount curve corresponding to a final second training data set, taking a second preset difference time period as a second step length, taking the step transition time of the unit step fuel change amount curve as a time starting point, sequentially calling the pressure trend change model in a second duration to obtain a second-order change amount predicted value of the main steam pressure of each second step length, and accumulating the second-order change amount predicted value of the main steam pressure of each second step length to obtain a pressure change rate predicted value of each second step length corresponding to the final second training data set;
s05-6, sequentially connecting the predicted value of the pressure change rate of each second step corresponding to the final second training data set to form a step response curve of the pressure change rate corresponding to the final second training data set to fuel;
Wherein the typical combustion temperature corresponding to the step response curve of the pressure change rate versus fuel is the average of the boiler furnace temperatures in all of the final second training data in the final second training data set.
In another aspect, the present embodiment also provides a system for obtaining a step response curve of a rate of change of pressure versus fuel, comprising:
at least one processor; and at least one memory communicatively coupled to the processor, wherein the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform a method of obtaining a step response curve of a rate of change of pressure versus fuel as any of the above.
The beneficial effects of the invention are as follows: according to the method and the system for acquiring the step response curve of the pressure change rate to the fuel, the influence of the combustion temperature on the combustion speed is considered, so that a pre-acquired combustion speed model is adopted, the prediction time is respectively carried out on the current boiler hearth temperature and the typical combustion temperature corresponding to the first step response curve, and then the pre-acquired first step response curve is subjected to the adjustment of the final pressure change rate to the step response curve of the fuel according to the current heat release time predicted value and the typical heat release time predicted value, so that the method and the system are suitable for boiler states at different combustion temperatures in online use.
Drawings
FIG. 1 is a flow chart of a method of obtaining a step response curve of pressure change rate versus fuel in accordance with the present invention;
FIG. 2 is a first step response curve;
FIG. 3 is a step response curve of heat versus fuel for each of the 4 subsets;
FIG. 4 is a schematic view of a combustion speed model in an embodiment of the invention;
FIG. 5 is a step response curve of the final rate of pressure change versus fuel in an embodiment of the invention.
Detailed Description
The invention will be better explained by the following detailed description of the embodiments with reference to the drawings.
In order that the above-described aspects may be better understood, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Example 1
Referring to fig. 1, the present embodiment provides a method of obtaining a step response curve of a rate of pressure change versus fuel, comprising:
S1, inputting the current boiler furnace temperature into a pre-acquired combustion speed model, and acquiring a current heat release time predicted value.
The combustion speed model is obtained after training a preset unitary linear machine learning regression model by taking a designated time mark as a dependent variable and taking a combustion temperature mark value corresponding to the designated time mark as an independent variable in advance.
S2, inputting the typical combustion temperature corresponding to the first step response curve obtained in advance into the combustion speed model, and obtaining a typical heat release time predicted value.
Referring to fig. 2, the first step response curve is a step response curve of a rate of pressure change versus fuel.
The abscissa of the step response curve of the pressure change rate with respect to the fuel in this embodiment is the time and the pressure change rate, respectively. Wherein the abscissa indicates time, i.e. the time axis in which a step change in the fuel system occurs. The ordinate indicates the rate of change of the fuel pressure, typically in terms of the amount of change in pressure per unit time, for example, in units of pressure per unit of time (e.g., kPa/s). The rate of change of fuel pressure in the step response may be strictly continuous, but is typically plotted in a finite period of time for ease of understanding in plotting the graph.
By plotting a step response curve, a rapid response of the fuel system to fuel supply or blockage and subsequent progressive stabilization can be observed. These curves can help engineers and technicians analyze the stability, dynamic performance, etc. of the fuel system with the necessary adjustments and improvements.
And S3, obtaining a step response curve of the final pressure change rate to the fuel based on the current heat release time predicted value, the typical heat release time predicted value and a first step response curve acquired in advance, as shown in FIG. 5.
In practical application of this embodiment, the step S3 specifically includes:
s31, based on the current heat release time predicted value and the typical heat release time predicted value, acquiring a ratio of the current heat release time predicted value to the typical heat release time predicted value.
For example, the current boiler furnace temperature is assumed to be 833.8 degrees celsius and the current heat release time predicted value is 11.94 minutes; assuming a typical combustion temperature corresponding to the pre-acquired first step response curve of 853.2 degrees celsius, the typical heat release time prediction value is 10.51 minutes, then the specific value of the ratio is equal to 11.94 minutes divided by 10.51 minutes and is 1.136.
S32, multiplying all time marks (namely time abscissa) corresponding to the first step response curve obtained in advance by the ratio to obtain a new time mark (time abscissa), and obtaining a step response curve of the final pressure change rate relative to combustion.
For example, multiplying all (time abscissa) time stamps corresponding to the pre-acquired first step response curve by 1.136 is used as a new time stamp, and the corresponding pressure change rate value in the pre-acquired first step response curve is kept unchanged, so as to obtain a step response curve of the final pressure change rate with respect to combustion.
According to the method and the system for acquiring the step response curve of the pressure change rate to the fuel, the influence of the combustion temperature on the combustion speed is considered, so that a pre-acquired combustion speed model is adopted, prediction time is respectively carried out on the current boiler furnace temperature and the typical combustion temperature corresponding to the first step response curve, and then the pre-acquired first step response curve is subjected to adjustment according to the current heat release time predicted value and the typical heat release time predicted value, so that the final pressure change rate is obtained, and the step response curve of the fuel is adjusted to adapt to boiler states at different combustion temperatures in online use.
Specifically, the method for obtaining the step response curve of the pressure change rate to the fuel provided in the embodiment further includes, before S1:
s01, acquiring a first training data set according to boiler historical production data acquired in advance.
The boiler history production data includes a plurality of pieces of first production data collected at predetermined time intervals.
The preset time interval in this embodiment ranges from 1s to 60s.
Wherein each piece of first production data includes: the time stamp, the fuel flow, the boiler furnace temperature, the boiler main steam pressure, the boiler main steam flow, the boiler main steam temperature, the boiler feed water pressure corresponding to the first production data.
Wherein, the S01 specifically includes:
s01-1, according to the boiler historical production data acquired in advance, forming an initial first training data corresponding to any first production data with a time mark in a first appointed time period, wherein the time mark, the fuel flow and the boiler furnace temperature in the first production data.
The first specified period of time in this embodiment ranges from 3 days to 30 days.
S01-2, acquiring total heat of main boiler steam corresponding to initial first training data according to the first production data corresponding to the initial first training data.
The total heat obtained by the main steam of the boiler is obtained by multiplying the unit obtained heat of the main steam of the boiler by the main steam flow of the boiler; the unit obtained heat of the main steam of the boiler is obtained by differencing the unit enthalpy value of the main steam of the boiler and the unit enthalpy value of the water supply of the boiler; the unit enthalpy value of the main steam of the boiler is calculated by the main steam pressure of the boiler and the main steam temperature of the boiler; the boiler feed water unit enthalpy value is calculated by the boiler feed water temperature and the boiler feed water pressure.
S01-3, adding the total heat obtained by the main steam of the boiler into corresponding initial first training data respectively to obtain intermediate first training data, and sequentially arranging all the intermediate first training data according to time marks to form a first training data set.
S02, respectively acquiring step response curves of heat quantity to fuel under different combustion temperature mark values according to the first training data set.
In this embodiment, the S02 specifically includes:
s02-1, respectively differentiating the total heat obtained by the fuel flow and the main steam in each middle first training data in the first training data set with the total heat obtained by the fuel flow and the main steam in the middle first training data before a first preset difference time period of a time mark in the middle first training data to obtain the fuel flow variable corresponding to the middle first training data and the total heat variable obtained by the main steam of the boiler, and adding the fuel flow variable and the total heat variable obtained by the main steam of the boiler into the middle first training data to obtain final second production data.
The first preset differential time period in this embodiment is 15 seconds. For example, S02-1 includes: and in two dimensions of obtaining total heat for the fuel flow and the main steam of the boiler in each middle first training data in the first training data set, differentiating the corresponding dimensions before 15 seconds of time marking the middle first training data and the middle first training data, obtaining the total heat variation obtained by the fuel flow variation and the main steam of the boiler, and adding the total heat variation into the middle first training data as a new data dimension.
S02-2, forming all final second production data into a final first training data set.
S02-3, dividing the final first training data set into k subsets according to the sequence of the boiler furnace temperatures in the final second production data from high to low, and taking the average value of the boiler furnace temperatures in all the final second production data in each subset as a combustion temperature marking value corresponding to the subset; wherein k is a preset value; in practical application, the value range of k is 2 to 6.
In this embodiment, k is 4. For example, the final first training data set is divided into 4 parts according to the number of the first training data in the middle from high to low according to the boiler furnace temperature, and the average boiler furnace temperatures of the 4 subsets are counted respectively and used as the combustion temperature marking values of the 4 subsets respectively, which are 818.1, 839.1, 855.4 and 878.2 respectively.
S02-4, taking the total heat variation obtained by the main steam of the boiler in any final second production data in any subset as a dependent variable, taking the fuel flow variation in all final second production data in a first time period before the time marking of the final second production data as the independent variable, training a preset multi-element linear machine learning regression model (the number of the variable elements is equal to the number of the fuel flow variation in all final second production data in the first time period before the time marking of the final second production data), and obtaining a heat variation model corresponding to the subset.
The first duration in this embodiment is 20 minutes, and S02-4 includes: taking the total heat variation obtained by the main boiler steam in any final second production data in any subset as a dependent variable, taking all the fuel flow variation in all the final second production data which are earlier than the time marks of the final second production data and have the difference between the time marks not more than 20 minutes as independent variables, and training a multiple linear machine learning regression model by the subset to obtain a heat variation model corresponding to the subset.
S02-5, regarding a pre-constructed unit step fuel change curve corresponding to any subset, taking a first preset differential time period as a first step length, taking the step transition time of the unit step fuel change curve as a time starting point, sequentially calling a heat change model corresponding to the subset in a first duration, obtaining a heat change predicted value of each first step length, and accumulating the heat change predicted value of each first step length to obtain a heat change total predicted value of each first step length corresponding to the subset.
Specifically, for the 4 subsets, respectively constructing corresponding fuel variation curves with unit steps, taking the step variation time as a time starting point according to the difference time length parameter of 15 seconds, sequentially calling a thermal variation model in the time dimension within the range that the total time length is not more than 20 minutes to obtain a thermal variation predicted value of 15 seconds in each time, and accumulating the thermal variation predicted value of 15 seconds in each time to obtain a thermal variation total predicted value of 15 seconds in each time corresponding to the subset.
S02-6, the predicted value of the total heat change amount of each first step length in the first time period corresponding to the subset is sequentially connected to form a step response curve of heat to fuel under the combustion temperature mark value corresponding to the subset.
In practical application, for 4 subsets, the predicted value of the total heat change amount with the total time length not exceeding 20 minutes is collected according to time marks to form a heat change vector, and referring to fig. 3, the step response curves of the heat corresponding to the 4 subsets to the fuel are obtained, and each curve uses the combustion temperature mark value of the corresponding heat data subset as the combustion temperature mark value of the corresponding heat data subset.
S03, acquiring a combustion speed model according to step response curves of heat to fuel under different combustion temperature mark values.
In practical applications, the S03 specifically includes:
s03-1, aiming at the step response curve of the heat corresponding to any subset to the fuel, screening out a time mark corresponding to the ratio meeting a preset first condition from the ratio of the predicted value of the total heat change amount of each first step in the step response curve of the heat corresponding to the subset to the predicted value of the total heat change amount of the last first step in the step response curve of the heat corresponding to the subset to the heat corresponding to the fuel, and taking the time mark as the first time mark corresponding to the subset.
The time mark corresponding to the ratio meeting the preset first condition is a time mark with the first ratio being greater than or equal to x% of the preset heat release amount parameter. Wherein x is a preset value. In this embodiment, the value of x ranges from 50 to 99. The specific value of x in the practical application of this embodiment is chosen to be 90.
S03-2, referring to FIG. 4, training a preset unitary linear machine learning regression model by taking the first time marks corresponding to each subset as dependent variables and the combustion temperature mark values corresponding to the subset as independent variables to obtain a combustion speed model.
That is, a combustion speed model is obtained by training a preset one-dimensional linear machine learning regression model with a specified time stamp as a dependent variable and a combustion temperature stamp value corresponding to the specified time stamp as an independent variable.
Wherein the designated time stamp includes a first time stamp corresponding to each subset, respectively.
The combustion temperature flag value corresponding to the specified time stamp includes a combustion temperature flag value corresponding to each subset, respectively.
In a practical application of the present embodiment, before S1, the method further includes:
s04, acquiring a second training data set according to boiler historical production data acquired in advance.
Specifically, the S04 specifically includes:
s04-1, according to the boiler historical production data acquired in advance, forming an initial second training data corresponding to any one piece of first production data with the time mark in a second designated time period, wherein the initial second training data corresponds to the first production data, and the initial second training data corresponds to the first production data.
The second specified period of time in this embodiment ranges from 12 hours to 84 hours. The second specified period of time is 24 hours in practical application of the present embodiment.
S04-2, sequentially arranging all initial second training data according to a time mark sequence to form a second training data set.
S05, acquiring a first step response curve according to the second training data set.
Wherein, the S05 specifically includes:
s05-1, respectively differentiating the fuel flow and the main steam pressure of the boiler in each initial second training data in the second training data set with the fuel flow and the main steam pressure of the boiler in the initial second training data before a second preset difference time period of the time mark in the initial second training data to obtain a fuel flow variable quantity and a main steam pressure variable quantity corresponding to the initial second training data, and adding the fuel flow variable quantity and the main steam pressure variable quantity into the initial second training data to obtain middle second training data.
The second preset differential time period of this embodiment is 1 minute.
Specifically, in two dimensions of fuel flow and main steam pressure of the boiler in the second training data set, the difference is obtained between each initial second training data and the corresponding dimension before 1 minute of the time mark of the initial second training data, and the fuel flow variation and the main steam pressure variation of the boiler are obtained and added into the initial second training data as new data dimensions.
In practical application, the method further comprises the following steps before the step S05-1: and (3) carrying out mean value aggregation on the second training data set according to the pre-configured time aggregation length parameter for 1 minute, namely, each piece of data represents the average condition in the time length of 1 minute.
S05-2, forming all the intermediate second training data into an intermediate second training data set.
S05-3, differentiating the boiler main steam pressure variable quantity in each intermediate second training data in the intermediate second training data set with the boiler main steam pressure variable quantity in the intermediate second training data before a second preset differential time period in the intermediate second training data to obtain a boiler main steam pressure second-order variable quantity corresponding to the intermediate second training data, adding the boiler main steam pressure second-order variable quantity into the intermediate second training data to obtain final second training data, and forming all final second training data into a final second training data set.
In this embodiment, the preset difference time period is 1 minute, for example, in the dimension of the main steam pressure variation in the middle second training data set, the difference is obtained between each middle second training data and the corresponding dimension before 1 minute of the time stamp of the middle second training data, the second order variation of the main steam pressure of the boiler is obtained and is used as the new data dimension to add the middle second training data, the final second training data is obtained, and all the final second training data form the final second training data set.
S05-4, taking the second order variation of the main steam pressure of the boiler in any one final second training data in the final second training data set as a dependent variable, taking the variation of the fuel flow in all final second training data in a second time period before the time marking of the final second training data as the independent variable, and training a preset multi-element linear machine learning regression model (wherein the number of the variation is equal to the number of the variation of the fuel flow in all final second training data in the second time period before the time marking of the final second training data) to obtain a pressure trend variation model.
In practical application, taking the second-order variable quantity of the main steam pressure of the boiler in each piece of final second training data as a dependent variable in the final second training data set, taking all the fuel flow variable quantities in all the final second training data which are earlier than the time mark of the final second training data and have the time mark difference of not more than 10 minutes as independent variables, and training a preset multi-element linear machine learning regression model to obtain a pressure trend change model.
S05-5, aiming at a pre-constructed unit step fuel change amount curve corresponding to a final second training data set, taking a second preset difference time period as a second step length, taking the step transition time of the unit step fuel change amount curve as a time starting point, sequentially calling the pressure trend change model in a second duration to obtain a second-order change amount predicted value of the main steam pressure of each second step length, and accumulating the second-order change amount predicted value of the main steam pressure of each second step length to obtain a pressure change rate predicted value of each second step length corresponding to the final second training data set.
For example, for a pre-constructed unit step fuel change amount curve corresponding to the final second training data set, taking the step change time as a time starting point according to the second step length of 1 minute, and sequentially calling a pressure trend change model along the time dimension within the range that the total time length is not more than 10 minutes to obtain a pressure second-order change amount predicted value of 1 minute at each time.
S05-6, sequentially connecting the predicted value of the pressure change rate of each second step corresponding to the final second training data set to form a step response curve of the pressure change rate corresponding to the final second training data set to fuel; in practical application, the predicted value of the pressure change rate, which is collected according to the time mark and has the total time length of not more than 10 minutes, forms a pressure change rate vector, and all adjacent two points in the vector are connected by line segments to form a step response curve of the pressure change rate to fuel.
Wherein the typical combustion temperature corresponding to the step response curve of the pressure change rate versus fuel is the average of the boiler furnace temperatures in all of the final second training data in the final second training data set.
The typical combustion temperature for the step response curve of the pressure change rate versus fuel in this example is 853.2 degrees celsius.
In the prior art, the step response curve mode of obtaining the pressure change rate relative to the fuel is obtained through a large amount of time in a step response test, so that the cost for realizing model predictive control is quite high generally, and in the embodiment, the step response curve of the pressure change rate relative to the fuel of the fluidized bed boiler is identified at low cost by using historical operation data, so that the cost for obtaining the step response curve of the pressure change rate relative to the fuel is reduced.
The present embodiment also provides a system for obtaining a step response curve of a rate of pressure change versus fuel, comprising: at least one processor; and at least one memory communicatively coupled to the processor, wherein the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform a method of obtaining a step response curve of a rate of change of pressure versus fuel as in the embodiment.
Example two
Referring to fig. 1, the present embodiment provides a method of obtaining a step response curve of a rate of pressure change versus fuel, comprising:
s1, inputting the current boiler furnace temperature into a pre-acquired combustion speed model, and acquiring a current heat release time predicted value.
The combustion speed model is obtained after training a preset unitary linear machine learning regression model by taking a designated time mark as a dependent variable and taking a combustion temperature mark value corresponding to the designated time mark as an independent variable in advance.
In the combustion speed model in this embodiment, for the step response curve of heat corresponding to any subset of the k subsets with respect to fuel, in the ratio of the predicted total heat change amount value of each first step in the step response curve of heat corresponding to the subset with respect to fuel and the predicted total heat change amount value of the last first step in the step response curve of heat corresponding to the subset with respect to fuel, a time stamp corresponding to the ratio satisfying a preset first condition is screened out, and is used as a first time stamp (i.e., a designated time stamp) corresponding to the subset, then, the first time stamp corresponding to each subset is used as a dependent variable, and the combustion temperature stamp value corresponding to the subset (i.e., the combustion temperature stamp value corresponding to the designated time stamp) is used as an independent variable, so as to train a preset unitary linear machine learning regression model.
The time mark corresponding to the ratio meeting the preset first condition is a time mark with the first ratio being greater than or equal to x% of the preset heat release amount parameter. Wherein x is a preset value. In this embodiment, the value of x ranges from 50 to 99. The specific value of x in practical application of this embodiment is 90.
S2, inputting the typical combustion temperature corresponding to the first step response curve obtained in advance into the combustion speed model, and obtaining a typical heat release time predicted value.
And S3, obtaining a step response curve of the final pressure change rate to the fuel based on the current heat release time predicted value, the typical heat release time predicted value and a first step response curve obtained in advance.
According to the method and the system for acquiring the step response curve of the pressure change rate to the fuel, the pre-acquired combustion speed model is adopted, the prediction time is respectively carried out on the current boiler furnace temperature and the typical combustion temperature corresponding to the first step response curve, and then the pre-acquired first step response curve is subjected to adjustment according to the current heat release time predicted value and the typical heat release time predicted value, so that the step response curve of the final pressure change rate to the fuel is obtained, and the method and the system are suitable for different boiler states in online use.
In the description of the present invention, it should be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium; may be a communication between two elements or an interaction between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
In the present invention, unless expressly stated or limited otherwise, a first feature is "on" or "under" a second feature, which may be in direct contact with the first and second features, or in indirect contact with the first and second features via an intervening medium. Moreover, a first feature "above," "over" and "on" a second feature may be a first feature directly above or obliquely above the second feature, or simply indicate that the first feature is higher in level than the second feature. The first feature being "under", "below" and "beneath" the second feature may be the first feature being directly under or obliquely below the second feature, or simply indicating that the first feature is level lower than the second feature.
In the description of the present specification, the terms "one embodiment," "some embodiments," "examples," "particular examples," or "some examples," etc., refer to particular features, structures, materials, or characteristics described in connection with the embodiment or example as being included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that alterations, modifications, substitutions and variations may be made in the above embodiments by those skilled in the art within the scope of the invention.
Claims (10)
1. A method of obtaining a step response curve of a rate of pressure change versus fuel, comprising:
S1, inputting the current furnace temperature of a boiler into a pre-acquired combustion speed model, and acquiring a current heat release time predicted value;
taking a designated time mark as a dependent variable in advance, taking a combustion temperature mark value corresponding to the designated time mark as an independent variable, and training a preset unitary linear machine learning regression model to obtain the combustion speed model;
s2, inputting a typical combustion temperature corresponding to a first step response curve obtained in advance into the combustion speed model, and obtaining a typical heat release time predicted value;
the first step response curve is a step response curve of the pressure change rate relative to the fuel;
and S3, obtaining a step response curve of the final pressure change rate to the fuel based on the current heat release time predicted value, the typical heat release time predicted value and a first step response curve obtained in advance.
2. The method according to claim 1, wherein S3 specifically comprises:
s31, acquiring a ratio of the current heat release time predicted value to the typical heat release time predicted value based on the current heat release time predicted value and the typical heat release time predicted value;
S32, multiplying all time marks corresponding to the first step response curve obtained in advance by the ratio to obtain a new time mark, and obtaining a step response curve of the final pressure change rate to combustion.
3. The method of claim 1, further comprising, prior to S1:
s01, acquiring a first training data set according to boiler historical production data acquired in advance;
the boiler historical production data comprises a plurality of pieces of first production data acquired according to a preset time interval;
s02, respectively acquiring step response curves of heat to fuel under different combustion temperature mark values according to the first training data set;
s03, acquiring a combustion speed model according to step response curves of heat to fuel under different combustion temperature mark values.
4. A method according to claim 3, wherein S01 comprises:
s01-1, according to pre-acquired boiler historical production data, forming an initial first training data corresponding to any first production data with a time mark in a first appointed time period, wherein the time mark, the fuel flow and the boiler furnace temperature are in the first production data;
S01-2, acquiring total heat of main boiler steam corresponding to initial first training data according to the first production data corresponding to the initial first training data;
s01-3, adding the total heat obtained by the main steam of the boiler into corresponding initial first training data respectively to obtain intermediate first training data, and sequentially arranging all the intermediate first training data according to time marks to form a first training data set.
5. The method according to claim 4, wherein S02 specifically comprises:
s02-1, respectively differentiating the total heat obtained by the fuel flow and the main steam in each middle first training data in the first training data set with the total heat obtained by the main steam in the middle first training data before a first preset difference time period of a time mark in the middle first training data to obtain a fuel flow variation corresponding to the middle first training data and a total heat variation obtained by the main steam of the boiler, and adding the fuel flow variation and the total heat variation obtained by the main steam of the boiler into the middle first training data to obtain final second production data;
S02-2, forming a final first training data set by all final second production data;
s02-3, dividing the final first training data set into k subsets according to the sequence of the boiler furnace temperatures in the final second production data from high to low, and taking the average value of the boiler furnace temperatures in all the final second production data in each subset as a combustion temperature marking value corresponding to the subset; wherein k is a preset value;
s02-4, taking the total heat variation obtained by the main steam of the boiler in any final second production data in any subset as a dependent variable, taking the fuel flow variation in all final second production data in a first time period before the time marking of the final second production data as the independent variable, and training a preset multi-element linear machine learning regression model to obtain a heat variation model corresponding to the subset;
s02-5, regarding a pre-constructed unit step fuel change curve corresponding to any subset, taking a first preset differential time period as a first step length, taking the step transition time of the unit step fuel change curve as a time starting point, sequentially calling a heat change model corresponding to the subset in a first duration to obtain a heat change predicted value of each first step length, and accumulating the heat change predicted value of each first step length to obtain a heat change total predicted value of each first step length corresponding to the subset;
S02-6, the predicted value of the total heat change amount of each first step length in the first time period corresponding to the subset is sequentially connected to form a step response curve of heat to fuel under the combustion temperature mark value corresponding to the subset.
6. The method according to claim 5, wherein S03 specifically comprises:
s03-1, aiming at a step response curve of heat corresponding to any subset and fuel, screening out a time mark corresponding to the ratio meeting a preset first condition from the ratio of the predicted value of the total heat change amount of each first step in the step response curve of heat corresponding to the subset and the predicted value of the total heat change amount of the last first step in the step response curve of heat corresponding to the subset, and taking the time mark as a first time mark corresponding to the subset;
s03-2, training a preset unitary linear machine learning regression model by taking the first time marks corresponding to each subset as dependent variables and taking the combustion temperature mark values corresponding to the subsets as independent variables to obtain a combustion speed model.
7. The method of claim 6, further comprising, prior to S1:
S04, acquiring a second training data set according to boiler historical production data acquired in advance;
s05, acquiring a first step response curve according to the second training data set.
8. The method according to claim 7, wherein S04 specifically comprises:
s04-1, according to the boiler historical production data acquired in advance, forming an initial second training data corresponding to any piece of first production data with a time mark in a second designated time period, wherein the initial second training data corresponds to the first production data, and the initial second training data corresponds to the initial second training data;
s04-2, sequentially arranging all initial second training data according to a time mark sequence to form a second training data set.
9. The method according to claim 8, wherein S05 specifically comprises:
s05-1, respectively differentiating the fuel flow and the main steam pressure of the boiler in each initial second training data in the second training data set with the fuel flow and the main steam pressure of the boiler in the initial second training data before a second preset difference time period of the time mark in the initial second training data to obtain a fuel flow variable quantity and a main steam pressure variable quantity corresponding to the initial second training data, and adding the fuel flow variable quantity and the main steam pressure variable quantity into the initial second training data to obtain middle second training data;
S05-2, forming all the intermediate second training data into an intermediate second training data set;
s05-3, differentiating the boiler main steam pressure variable quantity in each intermediate second training data in the intermediate second training data set with the boiler main steam pressure variable quantity in the intermediate second training data before a second preset differential time period in the intermediate second training data to obtain a boiler main steam pressure second-order variable quantity corresponding to the intermediate second training data, adding the boiler main steam pressure second-order variable quantity into the intermediate second training data to obtain final second training data, and forming all final second training data into a final second training data set;
s05-4, taking the second-order variable quantity of the main steam pressure of the boiler in any one of the final second training data in the final second training data set as a dependent variable, taking the variable quantity of the fuel flow in all final second training data in a second time period before the time mark of the final second training data as the independent variable, and training a preset multi-element linear machine learning regression model to obtain a pressure trend change model;
S05-5, aiming at a pre-constructed unit step fuel change amount curve corresponding to a final second training data set, taking a second preset difference time period as a second step length, taking the step transition time of the unit step fuel change amount curve as a time starting point, sequentially calling the pressure trend change model in a second duration to obtain a second-order change amount predicted value of the main steam pressure of each second step length, and accumulating the second-order change amount predicted value of the main steam pressure of each second step length to obtain a pressure change rate predicted value of each second step length corresponding to the final second training data set;
s05-6, sequentially connecting the predicted value of the pressure change rate of each second step corresponding to the final second training data set to form a step response curve of the pressure change rate corresponding to the final second training data set to fuel;
wherein the typical combustion temperature corresponding to the step response curve of the pressure change rate versus fuel is the average of the boiler furnace temperatures in all of the final second training data in the final second training data set.
10. A system for obtaining a step response curve of a rate of pressure change versus fuel, comprising:
At least one processor; and
at least one memory communicatively coupled to the processor, wherein the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of obtaining a step response curve of pressure change rate versus fuel as in any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311410665.5A CN117352079B (en) | 2023-10-27 | 2023-10-27 | Method and system for obtaining step response curve of pressure change rate to fuel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311410665.5A CN117352079B (en) | 2023-10-27 | 2023-10-27 | Method and system for obtaining step response curve of pressure change rate to fuel |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117352079A true CN117352079A (en) | 2024-01-05 |
| CN117352079B CN117352079B (en) | 2024-06-28 |
Family
ID=89369050
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311410665.5A Active CN117352079B (en) | 2023-10-27 | 2023-10-27 | Method and system for obtaining step response curve of pressure change rate to fuel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117352079B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009084620A (en) * | 2007-09-28 | 2009-04-23 | Jfe Steel Kk | Method and apparatus for controlling combustion in hot blast stove |
| CN105180136A (en) * | 2015-10-08 | 2015-12-23 | 南京信息工程大学 | Thermal-power-plant boiler main steam temperature control method based on fractional order proportional-integral (PI) dynamic matrix |
| RU2757521C1 (en) * | 2021-04-02 | 2021-10-18 | Общество с ограниченной ответственностью «Ракурс-инжиниринг» | System and method for regulating fuel consumption for steam boiler |
| CN114036834A (en) * | 2021-11-05 | 2022-02-11 | 国网河北能源技术服务有限公司 | Coal-fired boiler coking prediction method and device and terminal equipment |
| CN114622048A (en) * | 2022-03-15 | 2022-06-14 | 恒创数字科技(江苏)有限公司 | Combustion optimization system and method for hot blast stove |
| CN114719242A (en) * | 2022-04-07 | 2022-07-08 | 华北电力大学 | Method for controlling main steam pressure of circulating fluidized bed boiler directly doped with wet sludge |
| CN116753536A (en) * | 2023-05-08 | 2023-09-15 | 北京全应科技有限公司 | Boiler pressure control method based on pressure prediction model |
-
2023
- 2023-10-27 CN CN202311410665.5A patent/CN117352079B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009084620A (en) * | 2007-09-28 | 2009-04-23 | Jfe Steel Kk | Method and apparatus for controlling combustion in hot blast stove |
| CN105180136A (en) * | 2015-10-08 | 2015-12-23 | 南京信息工程大学 | Thermal-power-plant boiler main steam temperature control method based on fractional order proportional-integral (PI) dynamic matrix |
| RU2757521C1 (en) * | 2021-04-02 | 2021-10-18 | Общество с ограниченной ответственностью «Ракурс-инжиниринг» | System and method for regulating fuel consumption for steam boiler |
| CN114036834A (en) * | 2021-11-05 | 2022-02-11 | 国网河北能源技术服务有限公司 | Coal-fired boiler coking prediction method and device and terminal equipment |
| CN114622048A (en) * | 2022-03-15 | 2022-06-14 | 恒创数字科技(江苏)有限公司 | Combustion optimization system and method for hot blast stove |
| CN114719242A (en) * | 2022-04-07 | 2022-07-08 | 华北电力大学 | Method for controlling main steam pressure of circulating fluidized bed boiler directly doped with wet sludge |
| CN116753536A (en) * | 2023-05-08 | 2023-09-15 | 北京全应科技有限公司 | Boiler pressure control method based on pressure prediction model |
Non-Patent Citations (3)
| Title |
|---|
| YUL YUNAZWIN NAZARUDDIN等: "Improving performance of PID controller using artificial neural network for disturbance rejection of high pressure steam temperature control in industrial boiler", 《 2008 INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS》, 2 December 2008 (2008-12-02) * |
| 侯国莲, 刘洋, 张建华: "预测函数控制在火电厂单元机组协调控制系统中的应用", 动力工程, no. 02, 15 April 2005 (2005-04-15) * |
| 孙青秀: "压力场下火电厂锅炉主汽温度控制算法研究", 《环境技术 》, 25 October 2020 (2020-10-25) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117352079B (en) | 2024-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE60120192T2 (en) | Optimum operation of a power plant | |
| CN100561390C (en) | Secondary cooling dynamic control system for continuous casting billet | |
| CN100423929C (en) | Self-adapting temperature controlling method for injection moulding forming machine and circuit thereof | |
| CN102374518B (en) | Steam temperature control using dynamic matrix control | |
| DE102005006008A1 (en) | Method and device for level control in steam boilers of the drum type | |
| CN117352079B (en) | Method and system for obtaining step response curve of pressure change rate to fuel | |
| CN104583676B (en) | Steam generator system | |
| DE102010011044B4 (en) | Method for controlling a glow plug | |
| EP1655590A1 (en) | Method for determining the mass averaged temperature across the flow section of a gas stream in a gas turbine | |
| CN105955026B (en) | Fuzzy PID control method, device and system | |
| DE102011052629A1 (en) | Dynamic setting of a dynamic matrix control of steam temperatures | |
| DE102009050083B4 (en) | Method for determining a volume flow in a closed flow system provided with a turbomachine and with a control unit | |
| CN108508870A (en) | A kind of method of Drum Water Level Control System for Boiler Performance Evaluation and parameter optimization | |
| DE102009030206A1 (en) | Method for determining the exhaust gas temperature of a vehicle engine | |
| EP3557357B1 (en) | Operation monitoring method | |
| WO1995004936A1 (en) | Process and device for monitoring the temperature of an electric generator | |
| DE102012019736B4 (en) | control system | |
| CN107870611A (en) | Workshop analogue means and workshop analogy method | |
| CN104653239B (en) | Steam turbine installation opens dynamic control device | |
| CN105385843B (en) | A kind of hot rolling slab method for heating and controlling based on the last temperature of section | |
| CN114035620A (en) | Intelligent flow control method and system for mold temperature controller | |
| CN111530941B (en) | Water temperature compensation method for improving control precision of strip steel coiling temperature in laminar cooling | |
| WO1996002737A1 (en) | Process and device for the diagnosis and prognosis of the operating behaviour of a turbine plant | |
| EP2443320B1 (en) | Method for operating a power station | |
| CN112666828A (en) | Method, device, equipment and medium for self-adaptive adjustment of output equipment |
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 |