CN111309065A - Pressure model establishing method, pressure adjusting method and device - Google Patents
Pressure model establishing method, pressure adjusting method and device Download PDFInfo
- Publication number
- CN111309065A CN111309065A CN202010089741.7A CN202010089741A CN111309065A CN 111309065 A CN111309065 A CN 111309065A CN 202010089741 A CN202010089741 A CN 202010089741A CN 111309065 A CN111309065 A CN 111309065A
- Authority
- CN
- China
- Prior art keywords
- value
- pressure
- target
- data
- independent variable
- 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
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D16/00—Control of fluid pressure
- G05D16/20—Control of fluid pressure characterised by the use of electric means
- G05D16/2006—Control of fluid pressure characterised by the use of electric means with direct action of electric energy on controlling means
- G05D16/2013—Control of fluid pressure characterised by the use of electric means with direct action of electric energy on controlling means using throttling means as controlling means
Landscapes
- Physics & Mathematics (AREA)
- Fluid Mechanics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a pressure model establishing method, a pressure adjusting method and a pressure adjusting device, wherein the pressure model establishing method comprises the following steps: acquiring historical data of original influence parameters of target equipment, wherein the historical data comprises dependent variable data and data of N1 original influence parameters, and N1 is a positive integer greater than one; recombining the original influence parameters according to the historical data to obtain independent variable data, wherein the independent variable data comprises N2 recombined influence parameter data, and N2 is a positive integer larger than N1; and constructing a target pressure model according to the independent variable data and the dependent variable data.
Description
Technical Field
The application relates to the technical field of computers, in particular to a pressure model establishing method, a pressure adjusting method and a pressure adjusting device.
Background
At present, the regulation of the pre-storage chamber pressure is generally carried out by relevant workers according to daily experience and by combining various parameter values collected on site, but the experience may have some subjective errors. Based on this, the existing implementation also performs a series of calculations on the collected data through a model, so as to determine the pre-chamber pressure.
Disclosure of Invention
In view of the above, an object of the embodiments of the present application is to provide a pressure model building method, a pressure adjusting method and a device. The effect of improving the accuracy of pressure detection can be achieved.
In a first aspect, an embodiment of the present application provides a pressure model building method, including:
acquiring historical data of original influence parameters of target equipment, wherein the historical data comprises dependent variable data and N1 items of data of the original influence parameters, and N1 is a positive integer greater than one;
recombining the original influence parameters according to the historical data to obtain independent variable data, wherein the independent variable data comprises N2 recombined influence parameter data, and N2 is a positive integer larger than N1;
and constructing a target pressure model according to the independent variable data and the dependent variable data.
In an optional embodiment, the step of reconstructing the original influence parameters according to the historical data to obtain the independent variable data includes:
combining any at least two original impact parameters of the N1 impact parameters to form a plurality of composite recombined impact parameters;
and taking data corresponding to the plurality of composite recombination influence parameters and the N1 influence parameters as the independent variable data.
According to the pressure model establishing method provided by the embodiment of the application, multiple items of influence parameters can be combined into the composite recombination influence parameter, and the composite recombination influence parameter and the single item of influence parameter are jointly used as independent variable data, so that the independent variable data can more comprehensively express the condition of target equipment, and the established target pressure model can more accurately detect the pressure.
In an alternative embodiment, the step of constructing a target pressure model from the independent variable data and the dependent variable data includes:
and according to the independent variable data and the dependent variable data, constructing the target pressure model by using a partial least squares regression algorithm.
According to the pressure model establishing method provided by the embodiment of the application, the target pressure model can be established by using a partial least squares regression algorithm, so that the established target pressure model can be more fit with the pressure change of target equipment, and the pressure detected by the established target pressure model can be more accurate.
In an alternative embodiment, the step of constructing a target pressure model using a partial least squares regression algorithm according to the independent variable data and the dependent variable data includes:
calculating to obtain a first independent variable principal component value and a first dependent variable principal component value according to the independent variable data and the dependent variable data;
calculating the residual error of the (i-1) th independent variable residual error data to obtain the ith independent variable residual error data, wherein the zeroth independent variable residual error data is equal to the independent variable data;
calculating the residual error of the i-1 th dependent variable residual error data to obtain the i-th dependent variable residual error data, wherein the zero-th dependent variable residual error data is equal to the dependent variable data;
calculating to obtain an i +1 independent variable main component value and an i +1 dependent variable main component value according to the i independent variable residual error data and the i dependent variable residual error data;
determining a first regression equation of the independent variable data according to the multiple independent variable residual error data and the independent variable principal component value corresponding to the independent variable data;
determining a second regression equation of the dependent variable data according to the multi-item dependent variable residual data and the dependent variable principal component values corresponding to the dependent variable data;
and determining a target pressure model representing the transformation relation between the dependent variable data and the N2 recombination influence parameters according to the first regression equation and the second regression equation.
According to the pressure model establishing method provided by the embodiment of the application, through the calculation process, data such as parameters and parameter weights which have larger influence on the pressure can be calculated, so that the determined target pressure model can detect the pressure more accurately.
In an alternative embodiment, the step of determining a target pressure model characterizing a transformation relationship between the dependent variable data and the N2 term recombination influence parameters according to the first regression equation and the second regression equation includes:
determining an initial pressure model according to the first regression equation and the second regression equation;
and screening independent variables in the initial pressure model according to the corresponding coefficients of the recombination influence parameters in the initial pressure model to obtain a target pressure model.
The pressure model establishing method provided by the embodiment of the application can also screen the independent variable, so that the independent variable of the target pressure model is less, the interference of the independent variable is reduced, and the calculation pressure can be reduced under the condition of keeping the calculation accuracy.
In a second aspect, an embodiment of the present application provides a pressure adjustment method, including:
inputting the current value of the influence parameter of the target equipment into a target pressure model to obtain a current predicted value of pressure, wherein the target pressure model is established by the pressure model establishing method;
if the current predicted value of the pressure is smaller than a set value, determining a current adjusting value of the influence parameter of the target equipment according to a set rule and the current value of the influence parameter of the target equipment;
inputting the current adjustment value into the target pressure model for calculation to obtain a pressure adjustment predicted value;
judging whether the current adjustment value is a target adjustment value or not according to the pressure adjustment predicted value;
and if the current adjustment value is the target adjustment value, adjusting the pressure of the target equipment by using the current adjustment value.
In an optional implementation manner, the step of determining whether the current adjustment value is the target adjustment value according to the predicted pressure adjustment value includes:
and judging whether the pressure adjustment predicted value is not larger than a pressure target value, and if the pressure adjustment predicted value is not larger than the pressure target value, determining the current adjustment value as a target adjustment value.
The pressure adjusting method provided by the embodiment of the application can also set the target adjusting value, so that the condition that the pressure of the target equipment is unstable due to invalid adjustment can be reduced, and the accuracy of pressure adjustment can be improved.
In an optional embodiment, the influence parameters of the target device include: opening degree of a pre-storage chamber pressure regulating valve; the step of determining the current adjustment value of the impact parameter of the target device according to the current value of the impact parameter of the target device includes:
and determining the current adjusting value of the influence parameter of the target equipment according to the preset adjusting interval and the current value of the opening degree of the pre-storage chamber pressure adjusting valve.
According to the pressure adjusting method provided by the embodiment of the application, the target device can be a pre-storage chamber, the adjusting value is determined according to the current value of the opening degree of the pressure adjusting valve of the pre-storage chamber, so that the determined adjusting value can be combined with an actual value, and subsequent pressure adjustment of the pre-storage chamber can be relatively more accurate.
In a third aspect, an embodiment of the present application provides a pressure model building apparatus, including:
the device comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring historical data of original influence parameters of target equipment, the historical data comprises dependent variable data and N1 data of the original influence parameters, and N1 is a positive integer greater than one;
the recombination module is used for recombining the original influence parameters according to the historical data to obtain independent variable data, wherein the independent variable data comprises N2 recombination influence parameter data, and N2 is a positive integer larger than N1;
and the construction module is used for constructing a target pressure model according to the independent variable data and the dependent variable data.
In a fourth aspect, an embodiment of the present application provides a pressure adjustment device, including:
a first calculation module, configured to input a current value of an impact parameter of a target device into a target pressure model to obtain a current predicted value of pressure, where the target pressure model is a target pressure model established by the pressure model establishing method provided in the foregoing embodiment;
the determining module is used for determining the current adjusting value of the influence parameter of the target equipment according to the current value of the influence parameter of the target equipment according to a set rule if the current predicted value of the pressure is smaller than a set value;
the second calculation module is used for inputting the current adjustment value into the target pressure model for calculation so as to obtain a pressure adjustment predicted value;
the judging module is used for judging whether the current adjusting value is a target adjusting value according to the pressure adjusting predicted value;
and the adjusting module is used for adjusting the pressure of the target equipment by using the current adjusting value if the current adjusting value is the target adjusting value.
In a fifth aspect, an embodiment of the present application further provides an electronic device, including: a processor, a memory storing machine-readable instructions executable by the processor, the machine-readable instructions, when executed by the processor, performing the steps of the method of the first aspect described above, or any possible implementation of the first aspect, when the electronic device is run.
In a sixth aspect, this application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the method in the first aspect or any one of the possible implementation manners of the first aspect.
According to the pressure model establishing method, the pressure adjusting device, the electronic equipment and the computer readable storage medium, the influence parameter recombination and the mode of modeling the recombined influence parameters are adopted, compared with the mode of experience adjustment or simple calculation of the model on the acquired data in the prior art, the method not only simply uses the acquired data, but also performs importance recombination on the influence parameters, so that the constructed target pressure model can relatively accurately test the pressure condition of the target equipment, and a foundation is laid for pressure adjustment.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a block diagram of an electronic device according to an embodiment of the present disclosure.
Fig. 2 is a flowchart of a pressure model building method according to an embodiment of the present disclosure.
Fig. 3 is a detailed flowchart of step 203 of the pressure model building method provided in the embodiment of the present application.
Fig. 4 is a functional block diagram of a pressure model building apparatus according to an embodiment of the present application.
Fig. 5 is a flowchart of a pressure adjustment method according to an embodiment of the present application.
FIG. 6 is a schematic diagram of functional modules of a pressure regulating device according to an embodiment of the present disclosure
Detailed Description
The technical solution in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
The coke dry quenching technology is a coke quenching method for cooling red coke by adopting inert gas. During the coke dry quenching process, red coke is loaded from the top of a coke dry quenching furnace, low-temperature inert gas is blown into a red coke layer of a cooling chamber of the coke dry quenching furnace by a circulating fan to absorb the sensible heat of the red coke, the cooled coke is discharged from the bottom of the coke dry quenching furnace, high-temperature inert gas discharged from an annular flue of the coke dry quenching furnace flows through the coke dry quenching furnace to carry out heat exchange, steam is generated in a boiler, the cooled inert gas is blown into the coke dry quenching furnace again by the circulating fan, and the inert gas is recycled in a closed system. The coke quality of the dry quenching is obviously improved compared with that of the wet quenching; fully utilizes the sensible heat of the red coke, saves energy and the like.
During the coke dry quenching production process, the hot coke is mixed with 0 in the air when being cooled in the coke dry quenching furnace2And H20 chemically reacting to form CO and H2And, over time, dry-quenching C0 and H in the furnace2The concentration will gradually increase. Therefore, it is necessary to form a negative pressure in the pre-chamber by adjusting the pre-chamber pressure adjusting valve so that air can be sucked from the inlet air valve to combust C0 and H2Reduce the concentration of the active carbon and ensure the safety of the equipmentAnd (4) completing. However, in order to avoid excessive burning of coke due to introduction of excessive air and decrease of coke yield, the pre-chamber pressure needs to be maintained at a slight negative pressure (0-100 pa). However, when the furnace cover of the dry quenching furnace is opened in the coke charging process, a large amount of flame spraying and black smoke are generated in the coke charging process due to the micro negative pressure; when the furnace cover of the coke dry quenching furnace is gradually closed after coke charging is finished, because a large amount of air is sucked into the pre-storage chamber, the pressure of the whole pre-storage chamber is positive pressure (0-100pa) in a short time. Thus again causing C0 and H2The concentration rises sharply, when the concentration of CO exceeds the control standard, the furnace body has the danger of explosion, and in the process of coke charging, a large amount of sprayed CO can poison people. Therefore, the system for controlling the pressure of the pre-storage chamber for dry quenching aims to ensure the pressure balance and stability in the dry quenching furnace in the quenching process and control the pressure of the pre-storage chamber within 0-100 Pa. If the pressure is too high, the smoke dust in the furnace can be diffused into the surrounding atmosphere, and the environmental pollution is caused; if the pressure is too low, a large amount of ambient air is drawn into the furnace to burn the coke, which increases the burn out and affects the boiler inlet temperature and the stability of the circulating gas. Therefore, stabilizing the pre-chamber pressure well has important influence and significance. However, the inventors have studied that pre-chamber pressure control systems are not only linear in variation, but may also be non-linear and time-varying. Therefore, the traditional pre-chamber pressure control mode is difficult to adapt to the current pressure change system, so that the phenomena of large pressure fluctuation and the like are caused.
Because a linear PLS (partial least squares regression) model can only establish a linear equation of each variable such as the opening degree of an air inlet valve, the CO concentration, the material level height, the circulating air volume, the pre-storage chamber pressure regulating valve and the like, the actual working condition is nonlinear, and the linear equation has a large model error. Although the neural network can establish a non-linear equation between related variables, the algorithm of the neural network is too complex, and the operation process is not transparent enough, so that the operation result has great uncertainty and reliability. Therefore, the inventor of the application adopts the nonlinear PLS mathematical model to have the advantages of the nonlinear PLS mathematical model, and can obtain the obvious mathematical model and have the characteristic of nonlinearity. Therefore, the method can effectively adapt to the establishment of a mathematical model for controlling the pressure of the coke dry quenching pre-storage chamber.
Based on the above research, embodiments of the present application provide a pressure model establishing method, a pressure adjusting device, an electronic device, and a computer-readable storage medium, which can adaptively overcome the above problems. The idea of the solution is described below by means of several embodiments.
Example one
To facilitate understanding of the present embodiment, an electronic device that performs the pressure model building method or the pressure adjusting method disclosed in the embodiments of the present application will be described first.
As shown in fig. 1, is a block schematic diagram of an electronic device. The electronic device 100 may include a memory 111, a memory controller 112, a processor 113, a peripheral interface 114, an input-output unit 115, and a display unit 116. It will be understood by those of ordinary skill in the art that the structure shown in fig. 1 is merely exemplary and is not intended to limit the structure of the electronic device 100. For example, electronic device 100 may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The above-mentioned elements of the memory 111, the memory controller 112, the processor 113, the peripheral interface 114, the input/output unit 115 and the display unit 116 are electrically connected to each other directly or indirectly, so as to implement data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The processor 113 is used to execute the executable modules stored in the memory.
The Memory 111 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory 111 is configured to store a program, and the processor 113 executes the program after receiving an execution instruction, and the method executed by the electronic device 100 defined by the process disclosed in any embodiment of the present application may be applied to the processor 113, or implemented by the processor 113.
The processor 113 may be an integrated circuit chip having signal processing capability. The Processor 113 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The peripheral interface 114 couples various input/output devices to the processor 113 and memory 111. In some embodiments, the peripheral interface 114, the processor 113, and the memory controller 112 may be implemented in a single chip. In other examples, they may be implemented separately from the individual chips.
The input/output unit 115 is used to provide input data to the user. The input/output unit 115 may be, but is not limited to, a mouse, a keyboard, and the like.
The display unit 116 provides an interactive interface (e.g., a user operation interface) between the electronic device 100 and the user or is used for displaying image data to the user for reference. In this embodiment, the display unit may be a liquid crystal display or a touch display. In the case of a touch display, the display can be a capacitive touch screen or a resistive touch screen, which supports single-point and multi-point touch operations. The support of single-point and multi-point touch operations means that the touch display can sense touch operations simultaneously generated from one or more positions on the touch display, and the sensed touch operations are sent to the processor for calculation and processing.
In this embodiment, the display unit 116 may display the pressure variation of the specified device obtained by the test in the cycle. Illustratively, the above-mentioned specified device may be a pre-chamber.
The electronic device 100 in this embodiment may be configured to perform each step in each method provided in this embodiment. The following describes the implementation of the pressure model building method and the pressure adjusting method in detail by using several embodiments.
Example two
Please refer to fig. 2, which is a flowchart illustrating a pressure model building method according to an embodiment of the present disclosure. The specific process shown in fig. 2 will be described in detail below.
In one embodiment, a PLC (Programmable Logic Controller) system may be used to collect a data set of historical data of the original impact parameters of the target device as the base data.
The historical data includes dependent variable data and N1 original influence parameter data, and N1 is a positive integer greater than one.
In one embodiment, the method of the present embodiment may be used to establish a target pressure model for predicting the pre-chamber pressure, and in this embodiment, the target device may be a dry quenching furnace. The following description will be given taking as an example a target pressure model for predicting the pre-chamber pressure.
Illustratively, the above-mentioned original influence parameters may include: the opening degree of an air inlet valve X1, the CO concentration X2, the material level height X3, the circulating air volume X4 and the opening degree X5 of a pre-storage chamber pressure regulating valve.
In one example, the value of the opening X1 of the air inlet valve can be in the range of 0-100%; the CO concentration X2 can be in the range of 0-7%; the material level height X3 can be 9-15 m; the value range of the circulating air volume X4 can be 0-175000 cubic meters per hour; the value range of the opening degree X5 of the pre-storage chamber pressure regulating valve can be 10-50%.
In the above example, N1 has a value of 5.
Illustratively, the historical data described above may also include the pre-chamber pressure Y as influenced by the original influencing parameter. Wherein the pre-chamber pressure may be in the range of 0-300 Pa.
And 202, recombining the original influence parameters according to the historical data to obtain independent variable data.
In this embodiment, the independent variable data includes N2 pieces of data of recombination influence parameters, where N2 is a positive integer greater than N1.
Step 202 comprises: and combining any at least two original influence parameters in the N1 influence parameters to form a plurality of compound recombination influence parameters, and taking data corresponding to the compound recombination influence parameters and the N1 influence parameters as the independent variable data.
Because of the strong coupling and nonlinearity among the dry quenching parameters. For example, the opening X1 of the inlet air valve has a large influence on the CO concentration X2 as well as on the pre-chamber pressure. For another example, as the air volume of the circulating air volume X4 increases, the negative pressure in the duct will be stronger, and more air will be sucked into the air duct to burn CO, which will also affect the CO concentration. Based on the above studies, it is known that interaction between the various influencing parameters also occurs.
In this embodiment, the independent variables are nonlinear by recombining the respective influence parameters.
In one embodiment, any two original impact parameters may be combined to form a composite rebinning impact parameter. Illustratively, taking the above five impact parameters as examples, the composite rebinning impact parameter may include: x12、X22、X32、X42、X52、X1X2、X1X3、X1X4、X1X5、X2X3、X2X4、X2X5、X3X4、X3X5、X4X5。
In one embodiment, any three original influence parameters and any four original influence parameters may be combined to form a composite recombination influence parameter. The recombination influencing parameters are not exhaustive here.
Taking the above example as an example, the independent variable data obtained after the recombination may include: x1, X2, X3, X4, X5, X12、X22、X32、X42、X52Twenty variables formed by X1X2, X1X3, X1X4, X1X5, X2X3, X2X4, X2X5, X3X4, X3X5, X4X 5.
Illustratively, the matrix formed by the argument data can be represented as: x ═ X1, X2, X3, X4, X5, X12，X22，X32，X42，X52，X1X2，X1X3，X1X4，X1X5，X2X3，X2X4，X2X5，X3X4，X3X5，X4X5]。
In one example, the matrix of pre-chamber pressure correspondences can be represented as: y ═ Y1, …, yn]. In this example. The above-mentioned X1, X2, X3, X4, X5 and X12，X22，X32，X42，X52X1X2, X1X3, X1X4, X1X5, X2X3, X2X4, X2X5, X3X4, X3X5, and X4X5 are all n-dimensional vectors.
And step 203, constructing a target pressure model according to the independent variable data and the dependent variable data.
In the embodiment, the pressure control system of the pre-chamber of the dry quenching furnace is a multivariable and strongly coupled system, and a plurality of variables are mutually influenced, so that the production data has the characteristic of serious multiple commonalities. Therefore, in the embodiment, PLS (algorithm is adopted, variables such as the opening degree of an inlet air valve, the CO concentration, the material level height, the circulating air volume and a pre-storage chamber pressure regulating valve are converted into a few of main components which are not related to each other through orthogonal rotation transformation, and then a regression equation is established between the main components with simplified data structures and the pre-storage chamber pressure, so that a target pressure model for determining the pre-storage chamber pressure is obtained.
In one embodiment, step 203 comprises: and according to the independent variable data and the dependent variable data, constructing the target pressure model by using a partial least squares regression algorithm.
In one embodiment, as shown in FIG. 3, step 203 may include the following steps.
The following description will be given taking the argument data in the above example as an example.
Independent variable data X ═ X1, X2, X3, X4, X5, X12，X22，X32，X42，X52，X1X2，X1X3，X1X4，X1X5，X2X3，X2X4，X2X5，X3X4，X3X5，X4X5]Performing standardization treatment to obtain E0＝[E01,…,E020]。
Corresponding matrix Y to the pre-chamber pressure [ Y1, …, yn]By performing normalization, a matrix can be obtained: f0＝[F01,…,F0n]。
Wherein the zeroth argument residual data is equal to the argument data. Wherein i is a positive integer.
And the zero dependent variable residual data is equal to the dependent variable data.
First, solve matrix E0 TF0F0 TE0The feature vector W1 corresponding to the maximum feature value of (a). Solving matrix F0 TE0E0 TF0The feature vector C1 corresponding to the maximum feature value of (a).
Illustratively, solving for independent variable principal componentsThe value: t1 ═ E0W1。
Illustratively, solving for dependent variable principal component values: u1 ═ F0C1。
t1 and u1 are the 1 st pair of independent variable principal component values and dependent variable principal component values extracted from the independent variable data X and dependent variable data Y, respectively, at the 1 st time.
Wherein E is0＝t1G1 T+E1；F0＝t1H1 T+F1。
Wherein E is1And F1Is a residual matrix.
Wherein ti is X1, X2, X3, X4, X5, X12，X22，X32，X42，X52X1X2, X1X3, X1X4, X1X5, X2X3, X2X4, X2X5, X3X4, X3X5, X4X5, ui is a linear combination of y1, …, yn.
In this embodiment, E may be calculated according to independent variable principal component values respectively0And F0Regression equation for t 1:
further, using residual matrix E1And F1By substitution of E0And F0Then, solving second feature vectors W2 and C2 and second term independent variable principal component values and dependent variable principal component values t2 and u 2:
t2＝E1W2；
u2＝F1C2。
wherein E is1＝t2G2 T+E2；F1＝t2H2 T+F2。
Respectively solve for E1And F2Regression equation for t 2:
H2＝F1 Tt2/||t2||2。
based on the above cyclic calculation process, continuously iterative calculation is carried out by using the residual error information matrix until Em TEmThe middle major diagonal element is approximately 0 and the loop exits.
Then F0And E0The first and second regression equations at t1, …, tm are expressed as:
E0＝t1G1 T+t2G2 T+…tmGm T+Em；
the second regression equations are respectively expressed as:
F0＝t1H1 T+t2H2 T+…tmHm T+Fm。
Since ti is X1, X2, X3, X4, X5, X12，X22，X32，X42，X52X1X2, X1X3, X1X4, X1X5, X2X3, X2X4, X2X5, X3X4, X3X5, X4X5, so substituting ti into the second regression equation of the formula yields a pressure model for the pre-chamber pressure:
YK＝bk1Z1+…+bKpZP+FmKk＝1,..,n；
wherein, bk1、bkPIs substituted into the second regression equation of the formula according to tiCoefficients of the later determined independent variable data; fmKIs a constant; z1, …, ZPAnd (4) recombining independent variable data. Taking the above example as an example, Z1, …, ZPCan be respectively X1, X2, X3, X4, X5 and X12，X22，X32，X42，X52，X1X2，X1X3，X1X4，X1X5，X2X3，X2X4，X2X5，X3X4，X3X5，X4X5。
step a, determining an initial pressure model according to the first regression equation and the second regression equation;
and b, screening independent variables in the initial pressure model according to the corresponding coefficients of the recombination influence parameters in the initial pressure model to obtain a target pressure model.
In one embodiment, the independent variables may be filtered according to coefficients of the independent variable data.
For example, when the coefficient of the argument data is smaller than a specified value, the corresponding argument may be eliminated. For example, the above-mentioned specified value may be a value set as required. In one example, the specified value may be one tenth of the average of all coefficients. In one example, the specified value may be one-fifteenth of the average of all coefficients.
In another embodiment, the independent variables may be filtered according to the coefficients of the independent variable data, the principal component values and the feature vectors.
For example, arguments satisfying that argument data are less than a specified value and satisfying that Wi is less than 0.4 in ti may be culled as disturbance variables.
In this embodiment, the updated independent variable data obtained after removing part of the independent variables may be returned to step 2031 to step 2037 again until the coefficients of all the independent variable data satisfy that the coefficients of the independent variable data are not less than the specified value and that Wi in ti is not less than 0.4.
Further, the finally obtained pressure model may be subjected to an anti-normalization process, so that a target pressure model of a normalization coefficient of the normal pre-chamber pressure can be obtained.
The independent variable data can be simplified through the training, so that a simplified target pressure model is obtained, the influence of interference factors of independent variables can be reduced, and the prediction precision of the target pressure model is improved.
By the method, a pressure model of the prestoring chamber is established by a nonlinear PLS model algorithm by utilizing production data such as the opening degree of an air inlet valve, the CO concentration, the material level height, the circulating air volume, the opening degree of a prestoring chamber pressure regulating valve and the like, then main parameters influencing the pressure fluctuation of the prestoring chamber are excavated, and finally the main parameters of the pressure model are optimally designed by an optimization algorithm to obtain a target pressure model. The traditional pre-chamber pressure calculation model is effectively changed by adjusting parameters in the target pressure model under the condition of meeting various limiting conditions.
By the method in the embodiment, compared with the method that a neural network is used for constructing a PID (proportion-integral-derivative) controller for controlling the pre-chamber pressure control system, the algorithm in the method provided by the embodiment of the application is relatively simple and has relatively higher precision. And the algorithm in the method provided by the embodiment of the application has small calculation amount, so that the response time of the system is short.
The pressure model establishing method in the embodiment can achieve the following aims: 1) can be used to effectively predict the pre-chamber pressure. 2) The stable state precision of the pre-storage chamber pressure control system is improved while the CO concentration meets the process system, and the phenomenon that the system vibrates greatly is avoided, so that the control purpose of improving the yield and reducing the emission of harmful substances is realized. 3) The coke burning loss can be greatly reduced, thereby reducing the process cost and improving the production efficiency.
Compared with the traditional technical improvement, the algorithm in the embodiment is technically improved by utilizing a nonlinear PLS model algorithm modeling mode, so that the complex analysis and calculation of a plurality of physical models and neural networks can be avoided, and the effect of each independent variable factor on the pressure change of the pre-storage chamber can be calculated, so that the optimized parameters can be automatically adjusted under the condition of meeting the process limitation condition through the optimization algorithm to achieve the fluctuation target of the pre-storage chamber pressure in a very small range.
EXAMPLE III
Based on the same application concept, a pressure model establishing apparatus corresponding to the pressure model establishing method is also provided in the embodiments of the present application, and since the principle of the apparatus in the embodiments of the present application for solving the problem is similar to that in the embodiments of the pressure model establishing method, the apparatus in the embodiments of the present application may be implemented as described in the embodiments of the method, and repeated details are not described.
Please refer to fig. 4, which is a functional block diagram of a pressure model building apparatus according to an embodiment of the present disclosure. The modules in the pressure model building apparatus in this embodiment are used to perform the steps in the above-described method embodiments. The pressure model establishment device includes: an acquisition module 301, a recombination module 302 and a construction module 303; wherein the content of the first and second substances,
an obtaining module 301, configured to obtain historical data of original impact parameters of a target device, where the historical data includes dependent variable data and N1 pieces of data of the original impact parameters, and N1 is a positive integer greater than one;
a restructuring module 302, configured to restructure the original impact parameters according to the historical data to obtain independent variable data, where the independent variable data includes N2 pieces of data of restructuring impact parameters, where N2 is a positive integer greater than N1;
a building module 303, configured to build a target pressure model according to the independent variable data and the dependent variable data.
In a possible implementation, the restructuring module 302 is further configured to:
combining any at least two original impact parameters of the N1 impact parameters to form a plurality of composite recombined impact parameters;
and taking data corresponding to the plurality of composite recombination influence parameters and the N1 influence parameters as the independent variable data.
In a possible implementation, the building module 303 is further configured to:
and according to the independent variable data and the dependent variable data, constructing the target pressure model by using a partial least squares regression algorithm.
In a possible implementation, the building module 303 is further configured to:
calculating to obtain a first independent variable principal component value and a first dependent variable principal component value according to the independent variable data and the dependent variable data;
calculating the residual error of the (i-1) th independent variable residual error data to obtain the ith independent variable residual error data, wherein the zeroth independent variable residual error data is equal to the independent variable data;
calculating the residual error of the a-1 th dependent variable residual error data to obtain the ith dependent variable residual error data, wherein the zeroth dependent variable residual error data is equal to the dependent variable data;
calculating to obtain an i +1 independent variable main component value and an i +1 dependent variable main component value according to the i independent variable residual error data and the i dependent variable residual error data;
determining a first regression equation of the independent variable data according to the multiple independent variable residual error data and the independent variable principal component value corresponding to the independent variable data;
determining a second regression equation of the dependent variable data according to the multi-item dependent variable residual data and the dependent variable principal component values corresponding to the dependent variable data;
and determining a target pressure model representing the transformation relation between the dependent variable data and the N2 recombination influence parameters according to the first regression equation and the second regression equation.
In a possible implementation, the building module 303 is further configured to:
determining an initial pressure model according to the first regression equation and the second regression equation;
and screening independent variables in the initial pressure model according to the corresponding coefficients of the recombination influence parameters in the initial pressure model to obtain a target pressure model.
Example four
Please refer to fig. 5, which is a flowchart illustrating a pressure adjusting method according to an embodiment of the present disclosure. The specific flow shown in fig. 5 will be described in detail below.
The target pressure model in this embodiment is the target pressure model established by the pressure model establishing method provided in the second embodiment.
In this embodiment, the current values of the influence parameters in the dry quenching furnace in real-time production are collected.
For example, a target value (-50pa) of the pre-chamber pressure can be set, and a range (10% -50%) of the opening degree of the pre-chamber pressure regulating valve as a key parameter can be set.
The opening degree X1 of the lead-in air valve is mainly used for adjusting the CO concentration X2, the CO concentration X2 exceeds the control standard, the furnace body is in danger of explosion, the CO concentration X2 needs to be kept in a certain range, the adjusting range of the opening degree of the lead-in air valve is limited, and therefore the lead-in air valve cannot be used as a main key parameter for adjustment, and the CO concentration X2 is a process state value, cannot be directly controlled and cannot be used as a main key parameter for adjustment; the fill level X3 is a process state value and cannot be directly controlled. In addition, the material level height needs to meet the production requirement and cannot be adjusted as a main key parameter. The circulating air volume X4 is a main parameter influencing the coke discharging temperature and the boiler inlet temperature, belongs to a secondary influence parameter for the pre-storage chamber pressure, and can meet the requirements of the coke discharging temperature and the boiler inlet temperature and can not be adjusted as a main key parameter. Based on the above studies, the pre-chamber pressure regulating valve opening degree can be used as a main regulating parameter.
And 402, if the current predicted value of the pressure is smaller than a set value, determining a current adjustment value of the influence parameter of the target equipment according to the current value of the influence parameter of the target equipment according to a set rule.
In one embodiment, the impact parameters of the target device include: the opening degree of the pre-storage chamber pressure regulating valve. Step 402 may include: and determining the current adjusting value of the influence parameter of the target equipment according to the preset adjusting interval and the current value of the opening degree of the pre-storage chamber pressure adjusting valve.
Optionally, the temporary adjustment value of the opening degree of the pre-chamber pressure regulating valve can be obtained after random optimization is performed in a corresponding value range according to the set value range of the opening degree of the pre-chamber pressure regulating valve.
In one example, a temporary adjustment value can be obtained by adding a random value with an interval of [ -2%, 2% ] to the current value of the opening degree of the pre-storage chamber pressure regulating valve, and if the temporary adjustment value is within a value range corresponding to the opening degree of the pre-storage chamber pressure regulating valve, the temporary adjustment value is taken as the current adjustment value; otherwise, a random value with the interval of [ -2%, 2% ] is selected again to repeat the operation until the temporary adjustment value added with the random value is in the value range corresponding to the opening degree of the pre-storage chamber pressure adjusting valve, and the temporary adjustment value is used as the current adjustment value.
The opening degree of the valve of the pre-storage chamber pressure regulating valve is changed by 2%, so that fluctuation of the pre-storage chamber pressure about 50pa can be caused almost, and the pre-storage chamber pressure is prevented from exceeding a set range, therefore, the random value is set in the range of [ -2%, 2% ], and the pre-storage chamber pressure can be well kept in the range of 0-100 pa. It will be appreciated that the range of values of the random value may be different to suit different target devices. The method is suitable for different pre-chamber pressure ranges, the corresponding random value ranges can be different, and the value range of the random value does not cause any limitation to the protection range of the application.
And 403, inputting the current adjustment value into the target pressure model for calculation to obtain a pressure adjustment predicted value.
In this embodiment, the temporary optimal value of the opening degree of the pre-storage chamber pressure regulating valve and the initial values of other influencing parameters can be input into the target pressure model, and the temporary optimal value of the pre-storage chamber pressure can be obtained through calculation.
And step 404, judging whether the current adjusting value is a target adjusting value according to the pressure adjusting predicting value.
In this embodiment, a number parameter may also be set for recording the number of times of pre-chamber pressure adjustment. Each time a valid adjustment value is determined, the number of times parameter may be incremented by one.
In the first embodiment, if the predicted pressure adjustment value is within the range corresponding to the preset target value of the pre-storage chamber pressure and the predicted pressure adjustment value is smaller than the target pressure value, the current adjustment value is an effective adjustment value, and the effective adjustment value is used as the target adjustment value.
In the second embodiment, if the predicted pressure adjustment value is not within the range of the preset target value of the pre-chamber pressure, but the predicted pressure adjustment value is closer to the range corresponding to the preset target value of the pre-chamber pressure than the target pressure value, and the predicted pressure adjustment value is smaller than the target pressure value, the current adjustment value is an effective adjustment value, and the effective adjustment value is set as the target adjustment value.
In the third embodiment, a target number of times that the loop adjustment is required may also be set. Optionally, if the current adjustment value is an effective adjustment value and the value of the frequency parameter reaches the value of the target frequency, the current adjustment value is the target adjustment value. If the current adjustment value is an effective value and the value of the frequency parameter does not reach the value of the target frequency, inputting the effective current adjustment value as the current value of the influence parameter in step 401 into the target pressure model to perform the next pressure adjustment again, and taking the obtained effective adjustment value as the target adjustment value until the value of the frequency parameter reaches the value of the target frequency.
In this embodiment, the manner of determining whether the current adjustment value is the effective adjustment value in the third embodiment described above may be the same as the manner of determining the effective adjustment value in the first and second embodiments.
In this embodiment, the target device is adjusted according to the target adjustment value determined in step 404.
In one embodiment, the pressure of the target device may be adjusted each time a valid adjustment value is determined. In another embodiment, the target device may be adjusted only by using the final valid adjustment value after the target number of times of adjustment. Illustratively, if the value of the number parameter reaches the value of the target number, the pressure of the target device is adjusted by taking the current adjustment value which is valid for the last time as the adjustment target value.
Through the method in the embodiment, the PLC system and the configuration software are utilized to collect and summarize process parameter signals of various electrical equipment of the dry quenching furnace, then effective variable parameters are input into the mathematical model for real-time prediction and optimization, and the optimized result is input into the configuration picture and the PLC control system for real-time online optimization control, so that the parameters are more effectively optimized and controlled, the fluctuation range of the pre-storage chamber pressure can be greatly reduced, the control precision of the pre-storage chamber pressure can be improved, the working efficiency is improved, and the control purpose of improving the yield and reducing the emission of harmful substances is realized.
Furthermore, the system upgrades the PLC primary electric automation system to an intelligent control system, thereby effectively solving the current situation that the traditional prestoring room pressure control mode must adopt manual control, not only realizing the automatic control of the system, but also having higher control precision and faster system response speed, completely adapting to the requirements of load cycle and rapid change during coke charging, simultaneously reducing burning loss and CO2The discharge of the coke dry quenching furnace improves the yield of the coke dry quenching furnace, thereby realizing the control targets of yield increase, energy conservation and emission reduction.
EXAMPLE five
Based on the same application concept, a pressure adjusting device corresponding to the pressure adjusting method is further provided in the embodiment of the present application, and since the principle of the device in the embodiment of the present application for solving the problem is similar to that in the embodiment of the pressure adjusting method, the implementation of the device in the embodiment of the present application can refer to the description in the embodiment of the method, and repeated details are not repeated.
Please refer to fig. 6, which is a schematic diagram of functional modules of a pressure adjustment device according to an embodiment of the present disclosure. The various modules in the pressure regulating device in this embodiment are used to perform the various steps in the method embodiments described above. The pressure adjusting device includes: a first calculation module 501, a determination module 502, a second calculation module 503, a determination module 504, and an adjustment module 505, wherein:
a first calculating module 501, configured to input a current value of an impact parameter of a target device into a target pressure model to obtain a current predicted value of pressure, where the target pressure model is a target pressure model established by the pressure model establishing method provided in embodiment two;
a determining module 502, configured to determine, according to a set rule, a current adjustment value of an impact parameter of the target device according to a current value of the impact parameter of the target device if the current predicted value of the pressure is smaller than a set value;
a second calculating module 503, configured to input the current adjustment value into the target pressure model for calculation, so as to obtain a pressure adjustment prediction value;
a judging module 504, configured to judge whether the current adjustment value is a target adjustment value according to the pressure adjustment prediction value;
an adjusting module 505, configured to adjust the pressure of the target device by using the current adjustment value if the current adjustment value is the target adjustment value.
In a possible implementation, the determining module 504 is further configured to:
and judging whether the pressure adjustment predicted value is not larger than a pressure target value, and if the pressure adjustment predicted value is not larger than the pressure target value, determining the current adjustment value as a target adjustment value.
In a possible implementation, the influence parameters of the target device include: opening degree of a pre-storage chamber pressure regulating valve; the determining module 502 is further configured to:
and determining the current adjusting value of the influence parameter of the target equipment according to the preset adjusting interval and the current value of the opening degree of the pre-storage chamber pressure adjusting valve.
Furthermore, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of the pressure model building method or the pressure adjusting method described in the above method embodiment.
The computer program product of the pressure model building method and the pressure adjusting method provided in the embodiments of the present application includes a computer readable storage medium storing a program code, where instructions included in the program code may be used to execute the steps of the pressure model building method and the pressure adjusting method described in the above method embodiments, which may be specifically referred to in the above method embodiments and are not described herein again.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (12)
1. A method of building a pressure model, comprising:
acquiring historical data of original influence parameters of target equipment, wherein the historical data comprises dependent variable data and N1 items of data of the original influence parameters, and N1 is a positive integer greater than one;
recombining the original influence parameters according to the historical data to obtain independent variable data, wherein the independent variable data comprises N2 recombined influence parameter data, and N2 is a positive integer larger than N1;
and constructing a target pressure model according to the independent variable data and the dependent variable data.
2. The method of claim 1, wherein the step of reconstructing the raw impact parameters from the historical data to obtain independent variable data comprises:
combining any at least two original impact parameters of the N1 impact parameters to form a plurality of composite recombined impact parameters;
and taking data corresponding to the plurality of composite recombination influence parameters and the N1 influence parameters as the independent variable data.
3. The method of claim 1 or 2, wherein the step of constructing a target pressure model from the independent variable data and the dependent variable data comprises:
and according to the independent variable data and the dependent variable data, constructing the target pressure model by using a partial least squares regression algorithm.
4. The method of claim 3, wherein the step of constructing a target pressure model using a partial least squares regression algorithm based on the independent variable data and the dependent variable data comprises:
calculating to obtain a first independent variable principal component value and a first dependent variable principal component value according to the independent variable data and the dependent variable data;
calculating the residual error of the (i-1) th independent variable residual error data to obtain the (i) th independent variable residual error data, wherein the zero independent variable residual error data is equal to the independent variable data, and i is a positive integer;
calculating the residual error of the i-1 th dependent variable residual error data to obtain the i-th dependent variable residual error data, wherein the zero-th dependent variable residual error data is equal to the dependent variable data;
calculating to obtain an i +1 independent variable main component value and an i +1 dependent variable main component value according to the i independent variable residual error data and the i dependent variable residual error data;
determining a first regression equation of the independent variable data according to the multiple independent variable residual error data and the independent variable principal component value corresponding to the independent variable data;
determining a second regression equation of the dependent variable data according to the multi-item dependent variable residual data and the dependent variable principal component values corresponding to the dependent variable data;
and determining a target pressure model representing the transformation relation between the dependent variable data and the N2 recombination influence parameters according to the first regression equation and the second regression equation.
5. The method of claim 4, wherein the step of determining a target pressure model characterizing a transformation relationship of the dependent variable data to the N2 term recombination impact parameters based on the first and second regression equations comprises:
determining an initial pressure model according to the first regression equation and the second regression equation;
and screening independent variables in the initial pressure model according to the corresponding coefficients of the recombination influence parameters in the initial pressure model to obtain a target pressure model.
6. A pressure regulation method, comprising:
inputting the current value of the influence parameter of the target equipment into a target pressure model to obtain a current predicted pressure value, wherein the target pressure model is established by the pressure model establishing method according to any one of claims 1 to 5;
if the current predicted value of the pressure is smaller than a set value, determining a current adjusting value of the influence parameter of the target equipment according to a set rule and the current value of the influence parameter of the target equipment;
inputting the current adjustment value into the target pressure model for calculation to obtain a pressure adjustment predicted value;
judging whether the current adjustment value is a target adjustment value or not according to the pressure adjustment predicted value;
and if the current adjustment value is the target adjustment value, adjusting the pressure of the target equipment by using the current adjustment value.
7. The method of claim 6, wherein the step of determining whether the current adjustment value is a target adjustment value according to the predicted pressure adjustment value comprises:
and judging whether the pressure adjustment predicted value is not larger than a pressure target value, and if the pressure adjustment predicted value is not larger than the pressure target value, determining the current adjustment value as a target adjustment value.
8. The method of claim 6, wherein the impact parameters of the target device comprise: opening degree of a pre-storage chamber pressure regulating valve; the step of determining the current adjustment value of the impact parameter of the target device according to the current value of the impact parameter of the target device includes:
and determining the current adjusting value of the influence parameter of the target equipment according to the preset adjusting interval and the current value of the opening degree of the pre-storage chamber pressure adjusting valve.
9. A pressure modeling apparatus, comprising:
the device comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring historical data of original influence parameters of target equipment, the historical data comprises dependent variable data and N1 data of the original influence parameters, and N1 is a positive integer greater than one;
the recombination module is used for recombining the original influence parameters according to the historical data to obtain independent variable data, wherein the independent variable data comprises N2 recombination influence parameter data, and N2 is a positive integer larger than N1;
and the construction module is used for constructing a target pressure model according to the independent variable data and the dependent variable data.
10. A pressure regulating device, comprising:
a first calculation module, configured to input a current value of an influence parameter of a target device into a target pressure model to obtain a current predicted pressure value, where the target pressure model is the target pressure model established by the pressure model establishing method according to any one of claims 1 to 5;
the determining module is used for determining the current adjusting value of the influence parameter of the target equipment according to the current value of the influence parameter of the target equipment according to a set rule if the current predicted value of the pressure is smaller than a set value;
the second calculation module is used for inputting the current adjustment value into the target pressure model for calculation so as to obtain a pressure adjustment predicted value;
the judging module is used for judging whether the current adjusting value is a target adjusting value according to the pressure adjusting predicted value;
and the adjusting module is used for adjusting the pressure of the target equipment by using the current adjusting value if the current adjusting value is the target adjusting value.
11. An electronic device, comprising: a processor, a memory storing machine-readable instructions executable by the processor, the machine-readable instructions when executed by the processor performing the steps of the method of any of claims 1 to 8 when the electronic device is run.
12. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, is adapted to carry out the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010089741.7A CN111309065B (en) | 2020-02-12 | 2020-02-12 | Pressure model building method, pressure adjusting method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010089741.7A CN111309065B (en) | 2020-02-12 | 2020-02-12 | Pressure model building method, pressure adjusting method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111309065A true CN111309065A (en) | 2020-06-19 |
| CN111309065B CN111309065B (en) | 2023-08-01 |
Family
ID=71148972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010089741.7A Active CN111309065B (en) | 2020-02-12 | 2020-02-12 | Pressure model building method, pressure adjusting method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111309065B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112446599A (en) * | 2020-11-19 | 2021-03-05 | 广东电网有限责任公司 | Power supply reliability index prediction method, device, equipment and storage medium |
| CN112898995A (en) * | 2021-01-15 | 2021-06-04 | 广东韶钢松山股份有限公司 | Coke loading control method and device and electronic equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103472092A (en) * | 2013-09-17 | 2013-12-25 | 华东交通大学 | Partial least squares regression-based modeling method of infrared nondestructive testing electromagnetic excitation mathematical model |
| CN104123451A (en) * | 2014-07-16 | 2014-10-29 | 河海大学常州校区 | Dredging operation yield prediction model building method based on partial least squares regression |
| US20140326049A1 (en) * | 2013-05-06 | 2014-11-06 | Serguei Zelepouga | Method and apparatus for real-time measurement of fuel gas compositions and heating values |
| CN108920850A (en) * | 2018-07-09 | 2018-11-30 | 西安理工大学 | A kind of flexo pressure prediction method based on convolutional neural networks |
| CN108977206A (en) * | 2017-05-31 | 2018-12-11 | 科利特环能科技（大连）有限公司 | A kind of quenching furnace prestores the control pressurer system of room |
| CN109376937A (en) * | 2018-10-31 | 2019-02-22 | 中国水利水电科学研究院 | Adaptive scheduling end of term water level prediction method based on set empirical mode decomposition |
| CN109472088A (en) * | 2018-11-12 | 2019-03-15 | 重庆科技学院 | A kind of shale controlled atmosphere production well production Pressure behaviour prediction technique |
| CN110765679A (en) * | 2019-09-30 | 2020-02-07 | 国电南京自动化股份有限公司 | Dam monitoring web display method based on finite element model and SVM regression algorithm |
-
2020
- 2020-02-12 CN CN202010089741.7A patent/CN111309065B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140326049A1 (en) * | 2013-05-06 | 2014-11-06 | Serguei Zelepouga | Method and apparatus for real-time measurement of fuel gas compositions and heating values |
| CN103472092A (en) * | 2013-09-17 | 2013-12-25 | 华东交通大学 | Partial least squares regression-based modeling method of infrared nondestructive testing electromagnetic excitation mathematical model |
| CN104123451A (en) * | 2014-07-16 | 2014-10-29 | 河海大学常州校区 | Dredging operation yield prediction model building method based on partial least squares regression |
| CN108977206A (en) * | 2017-05-31 | 2018-12-11 | 科利特环能科技（大连）有限公司 | A kind of quenching furnace prestores the control pressurer system of room |
| CN108920850A (en) * | 2018-07-09 | 2018-11-30 | 西安理工大学 | A kind of flexo pressure prediction method based on convolutional neural networks |
| CN109376937A (en) * | 2018-10-31 | 2019-02-22 | 中国水利水电科学研究院 | Adaptive scheduling end of term water level prediction method based on set empirical mode decomposition |
| CN109472088A (en) * | 2018-11-12 | 2019-03-15 | 重庆科技学院 | A kind of shale controlled atmosphere production well production Pressure behaviour prediction technique |
| CN110765679A (en) * | 2019-09-30 | 2020-02-07 | 国电南京自动化股份有限公司 | Dam monitoring web display method based on finite element model and SVM regression algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 刘昕明: "焦炉集气管压力智能预测控制方法及应用研究" * |
| 祁鹏: "基于偏最小二乘的高炉铁水硅含量预测研究" * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112446599A (en) * | 2020-11-19 | 2021-03-05 | 广东电网有限责任公司 | Power supply reliability index prediction method, device, equipment and storage medium |
| CN112446599B (en) * | 2020-11-19 | 2023-01-24 | 广东电网有限责任公司 | Power supply reliability index prediction method, device, equipment and storage medium |
| CN112898995A (en) * | 2021-01-15 | 2021-06-04 | 广东韶钢松山股份有限公司 | Coke loading control method and device and electronic equipment |
| CN112898995B (en) * | 2021-01-15 | 2021-08-31 | 广东韶钢松山股份有限公司 | Coke loading control method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111309065B (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang | Wasserstein distributionally robust stochastic control: A data-driven approach | |
| CN109583585B (en) | Construction method of power station boiler wall temperature prediction neural network model | |
| Zhang et al. | Data-driven modeling using improved multi-objective optimization based neural network for coke furnace system | |
| CN112100916B (en) | Method, device, electronic equipment and medium for constructing reinforcement learning model | |
| CN111309065B (en) | Pressure model building method, pressure adjusting method and device | |
| US20090099667A1 (en) | Plant controlling device and method, thermal power plant, and its control method | |
| CN106909705A (en) | A kind of blast-melted quality prediction method and its system | |
| CN109670625B (en) | NOx emission concentration prediction method based on unscented Kalman filtering least square support vector machine | |
| CN113251670B (en) | Hot blast stove control and training method, device, equipment, hot blast stove system and medium | |
| Wu et al. | Integrated soft sensing of coke-oven temperature | |
| CN112036100B (en) | Method for predicting hearth oxygen concentration by using regression algorithm based on numerical simulation | |
| Chen et al. | Design of image-based control loops for industrial combustion processes | |
| CN108073145A (en) | Drive support device and program | |
| Liu et al. | Temporal hypergraph attention network for silicon content prediction in blast furnace | |
| CN114334025A (en) | Construction and verification method of cement clinker calcination environment variable | |
| Ji et al. | Application of the improved the ELM algorithm for prediction of blast furnace gas utilization rate | |
| Chu et al. | Data‐based multiscale modeling for blast furnace system | |
| Zhou et al. | Data modeling for quality prediction using improved orthogonal incremental random vector functional-link networks | |
| CN113515043A (en) | Method for calculating dry quenching loss rate in real time based on BP neural network | |
| Paul et al. | Sensor network design for maximizing process efficiency: an algorithm and its application | |
| Feng et al. | Fuzzy predictive temperature control for a class of metallurgy lime kiln models | |
| CN104460653B (en) | A kind of heating furnace monitoring system evaluation method | |
| CN111549193A (en) | Furnace changing method, furnace changing device and control equipment for multiple blast furnace hot blast stoves | |
| JP5849612B2 (en) | Combustion control method and combustion control apparatus for hot stove | |
| CN114971258A (en) | Industrial process optimization method and system based on coke quality prediction |
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 |