CN112181003A - Method for controlling unit pressure and electronic equipment - Google Patents
Method for controlling unit pressure and electronic equipment Download PDFInfo
- Publication number
- CN112181003A CN112181003A CN202010856297.7A CN202010856297A CN112181003A CN 112181003 A CN112181003 A CN 112181003A CN 202010856297 A CN202010856297 A CN 202010856297A CN 112181003 A CN112181003 A CN 112181003A
- Authority
- CN
- China
- Prior art keywords
- target
- working condition
- training
- preset
- sample data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012549 training Methods 0.000 claims abstract description 187
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 29
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 238000013021 overheating Methods 0.000 claims description 8
- 238000003303 reheating Methods 0.000 claims description 8
- 239000000126 substance Substances 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004134 energy conservation Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000010977 unit operation Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 3
- 239000003245 coal Substances 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D16/00—Control of fluid pressure
- G05D16/04—Control of fluid pressure without auxiliary power
- G05D16/10—Control of fluid pressure without auxiliary power the sensing element being a piston or plunger
-
- 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
Abstract
The invention discloses a method for controlling unit pressure and electronic equipment, which are used for solving the problems of large emission and low productivity of the existing unit. This scheme includes: a method of stack pressure control, comprising: acquiring a training data set and a sample data set of a target unit, clustering the sample data set through a proximity algorithm based on the training data set, and determining a preset working condition type of each group of operation sample data; determining a heat consumption rate corresponding to at least one operation sample data of the target preset working condition type according to the at least one operation sample data belonging to the target preset working condition type; determining an operating pressure parameter in operating sample data corresponding to the target heat consumption rate as a target pressure parameter of the target unit under a target preset working condition type; and when the running state of the unit corresponds to the target preset working condition type, performing pressure control on the unit based on the target pressure parameter.
Description
Technical Field
The invention relates to the field of thermal power generation, in particular to a method for controlling unit pressure and electronic equipment.
Background
In the field of thermal power generation, a thermal power generator set is a set which takes coal, oil or combustible gas as fuel, heats water in a boiler to increase the temperature, and then uses steam with certain pressure to drive a gas turbine to generate power.
The unit operating power is related to various parameters, and the operating state of the unit can be controlled by manually adjusting the parameters in the prior art. However, it is often difficult to determine the operation parameters only by manual experience so as to operate the unit under the optimal parameters, and the purposes of improving the productivity and saving energy cannot be achieved.
How to control the unit operation heat rate to realize energy conservation and emission reduction is the technical problem to be solved by the application.
Disclosure of Invention
An embodiment of the present invention provides a method for controlling a unit pressure and an electronic device, so as to solve the problems of large unit emission and low productivity in the prior art.
In a first aspect, a method for controlling a pressure of a machine set is provided, including:
acquiring a training data set and a sample data set of a target unit, wherein the training data set comprises preset training data corresponding to a plurality of preset working condition types respectively, each group of preset training data comprises a training load parameter and a plurality of training pressure parameters corresponding to the training load parameter, the sample data set comprises a plurality of groups of operation sample data during actual operation of the target unit, and each group of operation sample data comprises an operation load parameter and an operation pressure parameter corresponding to the operation load parameter;
clustering the sample data set through a proximity algorithm based on the training data set, and determining a preset working condition category to which each group of operation sample data belongs;
determining a heat consumption rate corresponding to at least one operation sample data of a target preset working condition type according to the at least one operation sample data belonging to the target preset working condition type;
determining an operating pressure parameter in operating sample data corresponding to a target heat consumption rate as a target pressure parameter of the target unit under the target preset working condition type, wherein the target heat consumption rate comprises a heat consumption rate meeting a preset judgment standard in at least one heat consumption rate corresponding to the target preset working condition type;
and when the running state of the target unit corresponds to the target preset working condition type, performing pressure control on the target unit based on the target pressure parameter.
Optionally, each set of operating sample data in the sample data set further includes at least one of the following parameters:
the system comprises a temperature, a main steam flow, a main steam enthalpy value, a main water supply enthalpy value, a reheat steam pipeline hot section flow, a reheat steam hot end enthalpy value, a reheat steam cold end enthalpy value, a chemical make-up water flow, a chemical make-up water enthalpy value, an overheating and desuperheating water flow, an overheating and desuperheating water enthalpy value, a reheating and desuperheating water flow, a reheating and desuperheating water enthalpy value and a generator output power.
Optionally, performing clustering on the sample data set through a proximity algorithm based on the training data set includes:
establishing a two-dimensional coordinate system according to the load parameter and the pressure parameter;
generating a plurality of training points corresponding to the preset training data in the two-dimensional coordinate system according to the training load parameters and the training pressure parameters of each group of preset training data in the training data set;
generating a plurality of sample points corresponding to the operation sample data in the two-dimensional coordinate system according to the operation load parameter and the operation pressure parameter of each group of operation sample data in the sample data set;
performing clustering on the plurality of sample points by a proximity algorithm based on the plurality of training points.
Optionally, performing clustering on the plurality of sample points through a proximity algorithm based on the plurality of training points includes:
determining Euclidean distances between a target sample point and each training point in the two-dimensional coordinate system;
and determining the preset working condition type of the operation sample data corresponding to the target sample point according to the training points with Euclidean distances meeting the preset distance standard.
Optionally, determining a preset working condition category to which the operation sample data corresponding to the target sample point belongs according to the training point with the euclidean distance meeting the preset distance standard includes:
sequencing the training points according to Euclidean distances between the target sample point and the training points;
determining a preset number of training points as training points meeting a preset distance standard according to the sequencing result;
determining the preset working condition types corresponding to the training points which accord with the preset distance standard;
and determining the preset working condition type to which the operation sample data corresponding to the target sample point belongs according to the preset working condition type corresponding to each training point meeting the preset distance standard.
Optionally, determining a preset operating condition type to which the operating sample data corresponding to the target sample point belongs according to the preset operating condition type corresponding to each training point meeting the preset distance standard, including:
when the number of the preset working condition types corresponding to the training points meeting the preset distance standard is multiple, determining the probability that the operation sample data of the target sample point belongs to each preset working condition type according to the preset working condition types corresponding to the training points meeting the preset distance standard;
and determining the preset working condition type to which the target sample point belongs according to the probability that the operation sample data of the target sample point belongs to each preset working condition type.
Optionally, after determining an operating pressure parameter in the operating sample data corresponding to the target heat rate as the target pressure parameter of the target unit under the target preset working condition category, the method further includes:
and performing regression processing on the target pressure parameter under each preset working condition category through a least square method to determine a target sliding pressure curve, wherein the target sliding pressure curve is used for controlling the target unit to operate according to the target pressure parameter under each preset working condition.
In a second aspect, an electronic device is provided, comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module acquires a training data set and a sample data set of a target unit, the training data set comprises preset training data respectively corresponding to a plurality of preset working condition types, each preset training data set comprises a training load parameter and a plurality of training pressure parameters corresponding to the training load parameter, the sample data set comprises a plurality of groups of operation sample data of the target unit in actual operation, and each group of operation sample data comprises an operation load parameter and an operation pressure parameter corresponding to the operation load parameter;
the clustering module is used for clustering the sample data set through a proximity algorithm based on the training data set and determining the preset working condition type of each group of operating sample data;
the first determining module is used for determining the heat consumption rate corresponding to at least one operation sample data of a target preset working condition type according to the at least one operation sample data of the target preset working condition type;
the second determining module is used for determining an operating pressure parameter in operating sample data corresponding to a target heat consumption rate as a target pressure parameter of the target unit under the target preset working condition type, wherein the target heat consumption rate comprises a heat consumption rate meeting a preset judgment standard in at least one heat consumption rate corresponding to the target preset working condition type;
and the control module is used for carrying out pressure control on the target unit based on the target pressure parameter when the running state of the target unit corresponds to the target preset working condition type.
In a third aspect, an electronic device is provided, the electronic device comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the method according to the first aspect.
In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, realizes the steps of the method as in the first aspect.
In the embodiment of the application, a training data set and a sample data set of a target unit are obtained, wherein the training data set comprises preset training data respectively corresponding to a plurality of preset working condition types, each preset training data set comprises a training load parameter and a plurality of training pressure parameters corresponding to the training load parameter, the sample data set comprises a plurality of groups of operation sample data during actual operation of the target unit, and each group of operation sample data comprises an operation load parameter and an operation pressure parameter corresponding to the operation load parameter; clustering the sample data set through a proximity algorithm based on the training data set, and determining a preset working condition category to which each group of operation sample data belongs; determining a heat consumption rate corresponding to at least one operation sample data of a target preset working condition type according to the at least one operation sample data belonging to the target preset working condition type; determining an operating pressure parameter in operating sample data corresponding to a target heat consumption rate as a target pressure parameter of the target unit under the target preset working condition type, wherein the target heat consumption rate comprises a heat consumption rate meeting a preset judgment standard in at least one heat consumption rate corresponding to the target preset working condition type; and when the running state of the target unit corresponds to the target preset working condition type, performing pressure control on the target unit based on the target pressure parameter. According to the scheme provided by the embodiment of the application, the target pressure parameter when the unit is in the target working condition type can be determined through the clustering algorithm, and the unit is controlled to operate according to the target pressure parameter, so that the heat consumption rate of the unit meets the preset judgment standard on the premise of ensuring that the unit operates according to the target working condition type, and the control on the operation heat consumption rate of the unit is realized.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is one of the flow diagrams of a method of unit pressure control according to an embodiment of the present invention;
FIG. 2a is a second schematic flow chart of a method for controlling the unit pressure according to an embodiment of the present invention;
FIG. 2b is a schematic diagram of a two-dimensional coordinate system established by one embodiment of the present invention;
FIG. 2c is a schematic diagram of training points in a two-dimensional coordinate system according to an embodiment of the present invention;
FIG. 2d is a schematic diagram of training points and sample points in a two-dimensional coordinate system in accordance with an embodiment of the present invention;
FIG. 2e is a diagram illustrating the clustering result in a two-dimensional coordinate system according to an embodiment of the present invention;
FIG. 3 is a third schematic flow chart of a method of unit pressure control according to an embodiment of the present invention;
FIG. 4 is a fourth schematic flow chart of a method of unit pressure control according to an embodiment of the present invention;
FIG. 5 is a fifth flowchart illustrating a method for unit pressure control according to an embodiment of the present invention;
FIG. 6 is a sixth schematic flow chart illustrating a method of unit pressure control according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. The reference numbers in the present application are only used for distinguishing the steps in the scheme and are not used for limiting the execution sequence of the steps, and the specific execution sequence is described in the specification.
The sliding pressure optimization is one of the most effective energy-saving methods used by thermal power generating units at present. In practical application, the number of clustering intervals is often determined manually, and automatic control is difficult to realize.
In order to solve the problems in the prior art, an embodiment of the present application provides a method for controlling a unit pressure, including the following steps:
s11: acquiring a training data set and a sample data set of a target unit, wherein the training data set comprises preset training data corresponding to a plurality of preset working condition types respectively, each group of preset training data comprises a training load parameter and a plurality of training pressure parameters corresponding to the training load parameter, the sample data set comprises a plurality of groups of operation sample data during actual operation of the target unit, and each group of operation sample data comprises an operation load parameter and an operation pressure parameter corresponding to the operation load parameter;
s12: clustering the sample data set through a proximity algorithm based on the training data set, and determining a preset working condition category to which each group of operation sample data belongs;
s13: determining a heat consumption rate corresponding to at least one operation sample data of a target preset working condition type according to the at least one operation sample data belonging to the target preset working condition type;
s14: determining an operating pressure parameter in operating sample data corresponding to a target heat consumption rate as a target pressure parameter of the target unit under the target preset working condition type, wherein the target heat consumption rate comprises a heat consumption rate meeting a preset judgment standard in at least one heat consumption rate corresponding to the target preset working condition type;
s15: and when the running state of the target unit corresponds to the target preset working condition type, performing pressure control on the target unit based on the target pressure parameter.
In the above step S11, the operating condition may refer to an operating state of the unit under a condition directly related to the operation thereof. For example, the operating state of the unit when the fuel consumption rate is the lowest may be referred to as "economic condition"; the operating state when the load exceeds the rated value may be referred to as an "overload condition". The preset working condition types can be various, and the various working condition types can be preset by workers and can also be automatically generated by electronic equipment according to the collected data information.
The acquired training data set comprises a plurality of groups of preset training data, and each group of preset training data corresponds to a preset working condition type. Preferably, the data amount in each set of preset training data corresponding to each preset working condition category is the same. For example, the preset condition categories include a category a, a category B, a category C, and a category D. Then, the preset training data corresponding to the four categories each include 5 preset training data. The preset training data may include a training load parameter and a training pressure parameter. In the embodiment of the present application, a two-dimensional feature parameter is taken as an example for explanation, and in practical application, more parameters may be added according to practical application requirements, so as to represent features of preset training data from multiple dimensions.
The acquired sample data set comprises operation sample data of the acquisition island during actual operation of the target unit, and the operation sample data can be acquired and reported by the target unit and can also be acquired by other equipment except the target unit. In practical application, the design data of the unit can be obtained, so that the heat consumption rate can be calculated according to the obtained data aiming at the characteristics of the unit.
The neighbor algorithm described in step S12, i.e., the K-nearest neighbor (KNN) classification algorithm, which may also be referred to as KNN algorithm for short, is a simple and efficient data classification method. In the KNN algorithm, firstly, defining a class training data set; then, calculating the distance between all sample points and training data one by one; sequencing the distances of all training data of each sample point, and taking the first K data points; calculating the probability of each category in the K data points; and finally, the sample points are classified by judging the probability, so that simple and effective classification can be realized.
The scheme provided by the embodiment of the application applies the KNN algorithm, clusters the sample data set based on the training data set, and clusters each operation sample data in the sample data set to the preset working condition type of the training data set so as to determine the preset working condition type of each group of operation sample data.
Subsequently, in step S13, a heat rate corresponding to at least one operation sample data belonging to a target preset condition category is determined according to the at least one operation sample data belonging to the target preset condition category. Wherein, heat rate may refer to the amount of heat consumed per 1kWh of electrical energy generated. Heat rate is now often used as an important indicator to study and measure the thermal economy of a power plant.
Based on the scheme provided in the foregoing embodiment, optionally, each set of operation sample data in the sample data set further includes at least one of the following parameters:
the system comprises a temperature, a main steam flow, a main steam enthalpy value, a main water supply enthalpy value, a reheat steam pipeline hot section flow, a reheat steam hot end enthalpy value, a reheat steam cold end enthalpy value, a chemical make-up water flow, a chemical make-up water enthalpy value, an overheating and desuperheating water flow, an overheating and desuperheating water enthalpy value, a reheating and desuperheating water flow, a reheating and desuperheating water enthalpy value and a generator output power.
In practical applications, there are many factors that affect the heat rate. For example, the performance of the main equipment of the power plant, whether the equipment state is intact, the operation mode of the unit, the operation parameters of the unit, whether some bypass valves and drain valves have serious leakage, and the like.
Subsequently, in step S14, the operating pressure parameter in the operating sample data corresponding to the target heat rate is determined as the target pressure parameter of the target unit under the target preset operating condition type, where the target heat rate includes a heat rate meeting a preset determination standard in at least one heat rate corresponding to the target preset operating condition type.
The preset determination criterion may be preset according to an actual requirement, for example, a heat rate lower than a preset heat rate threshold in at least one heat rate corresponding to the target preset operating condition type is determined as a heat rate meeting the preset determination criterion. Or judging the lowest heat rate in at least one heat rate corresponding to the target preset working condition type as the heat rate meeting the preset judgment standard. After the target heat consumption rate is determined, determining the operating pressure parameter in the operating sample data corresponding to the target heat consumption rate as the target pressure parameter under the working condition category to which the operating sample data belongs.
Finally, in step S15, when the operation state of the target unit corresponds to the target preset working condition type, performing pressure control on the target unit based on the target pressure parameter. In this embodiment, the target heat rate is a heat rate meeting a preset judgment standard in each operation sample data in the target preset working condition category, and the unit is controlled to operate according to a target pressure parameter corresponding to the target heat rate, so that the heat rate of the unit operation can meet the preset judgment standard.
When the target heat consumption rate is the lowest heat consumption rate in at least one heat consumption rate corresponding to the target preset working condition type, the unit is controlled to operate at the target pressure, so that the heat consumption rate is reduced on the premise of ensuring that the unit operates at the required working condition, and energy conservation and emission reduction are realized.
According to the scheme provided by the embodiment of the application, the data category definition problem in practical application can be solved through a KNN clustering algorithm, the automation level of unit sliding pressure optimization is improved, the labor intensity of technical personnel is reduced, in addition, the unit operation can be effectively controlled, and the purposes of reducing the unit heat consumption rate, reducing the coal consumption, saving energy and reducing emission are realized according to practical requirements. According to the scheme provided by the embodiment of the application, the target pressure parameter when the unit is in the target working condition type can be determined through the clustering algorithm, and the unit is controlled to operate according to the target pressure parameter, so that the heat consumption rate of the unit meets the preset judgment standard on the premise of ensuring that the unit operates according to the target working condition type, and the control on the operation heat consumption rate of the unit is realized.
Based on the solution provided by the foregoing embodiment, optionally, as shown in fig. 2a, the above step S12, performing clustering on the sample data set through a proximity algorithm based on the training data set, includes the following steps:
s21: establishing a two-dimensional coordinate system according to the load parameter and the pressure parameter;
s22: generating a plurality of training points corresponding to the preset training data in the two-dimensional coordinate system according to the training load parameters and the training pressure parameters of each group of preset training data in the training data set;
s23: generating a plurality of sample points corresponding to the operation sample data in the two-dimensional coordinate system according to the operation load parameter and the operation pressure parameter of each group of operation sample data in the sample data set;
s24: performing clustering on the plurality of sample points by a proximity algorithm based on the plurality of training points.
In the embodiment of the present application, a two-dimensional coordinate system is established with the load parameter as the abscissa and the pressure parameter as the ordinate, as shown in fig. 2 b. Subsequently, each set of preset training data in the training data set is marked in the two-dimensional coordinate system established above in a form of a coordinate point to form a training point, in this embodiment, there are four preset working condition categories, five preset training data are preset in each preset working condition category, and the preset training data belonging to the same preset working condition category have the same training load parameter, that is, the abscissa in the figure is the same, as shown in fig. 2 c. And marking each group of running sample data in the two-dimensional coordinate system established in the above manner in the form of a coordinate point to form a sample point, and then performing clustering on the plurality of sample points based on a proximity algorithm to determine which preset working condition type each sample point belongs to, wherein a clustering result is shown in fig. 2 e.
Based on the solution provided by the foregoing embodiment, optionally, as shown in fig. 3, in the foregoing step S24, performing clustering on the plurality of sample points through a proximity algorithm based on the plurality of training points includes the following steps:
s31: determining Euclidean distances between a target sample point and each training point in the two-dimensional coordinate system;
s32: and determining the preset working condition type of the operation sample data corresponding to the target sample point according to the training points with Euclidean distances meeting the preset distance standard.
Taking the sample points and the training points shown in fig. 2c to 2d as examples, the euclidean distance between each sample point and each training point in the two-dimensional coordinate system is determined. The euclidean distance may also be referred to as a euclidean distance or a euclidean metric, and refers to a "common" (i.e., straight line) distance between two points in euclidean space. Using this distance, the euclidean space becomes the metric space. The associated norm is called the euclidean norm.
The determined Euclidean distance can represent the distance between the target sample point and each training point, when the Euclidean distance is small, the target sample point is close to the training points, and when the Euclidean distance is large, the target sample point is greatly different from the training points. Therefore, by the scheme provided by this embodiment, the preset condition type to which the training point with the closest euclidean distance to the target sample point belongs may be determined as the preset condition class to which the target sample point belongs.
The preset distance standard in the embodiment of the application can be preset according to actual requirements. For example, the training point having the shortest euclidean distance to the target sample point is the training point that meets the above-described preset distance criterion.
Based on the solution provided in the foregoing embodiment, optionally, as shown in fig. 4, in step S32, determining the preset working condition category to which the operation sample data corresponding to the target sample point belongs according to the training point whose euclidean distance meets the preset distance criterion includes the following steps:
s41: sequencing the training points according to Euclidean distances between the target sample point and the training points;
s42: determining a preset number of training points as training points meeting a preset distance standard according to the sequencing result;
s43: determining the preset working condition types corresponding to the training points which accord with the preset distance standard;
s44: and determining the preset working condition type to which the operation sample data corresponding to the target sample point belongs according to the preset working condition type corresponding to each training point meeting the preset distance standard.
In this embodiment, the training points are first sorted according to the euclidean distance, the training points that are lower than the preset distance from the target sample point or a preset number of training points before ranking are screened out, and the preset working condition category to which the target sample point belongs is determined according to the probability of the preset working condition category to which the screened training points belong. For example, if the number of training points lower than the preset distance from the target sample point is 5, where 4 corresponding preset condition classes are M and 1 corresponding preset condition class is N, the preset condition class to which the target sample point belongs is determined as M.
Based on the solution provided in the foregoing embodiment, optionally, as shown in fig. 5, in step S44, determining the preset operating condition type to which the operation sample data corresponding to the target sample point belongs according to the preset operating condition type corresponding to each training point meeting the preset distance criterion, includes the following steps:
s51: when the number of the preset working condition types corresponding to the training points meeting the preset distance standard is multiple, determining the probability that the operation sample data of the target sample point belongs to each preset working condition type according to the preset working condition types corresponding to the training points meeting the preset distance standard;
s52: and determining the preset working condition type to which the target sample point belongs according to the probability that the operation sample data of the target sample point belongs to each preset working condition type.
For example, the preset working condition categories corresponding to the training points meeting the preset distance criterion include X, Y and Z, and then, the probability that the operation sample data of the target sample point belongs to each preset working condition category is determined according to the preset working condition categories corresponding to the training points meeting the preset distance criterion. In this embodiment, assuming that the number of training points with a condition type X is 2, the number of training points with a condition type Y is 1, and the number of training points with a condition type Z is 5, then the probability that the condition type X of the target sample point is 2/8-25%, the probability that the condition type Y of the target sample point is 1/8-12.5%, and the probability that the condition type Z of the target sample point is 62.5%.
Then, the probability that the working condition type of the target sample point is Z is the largest can be determined according to the probability, and therefore, the preset working condition type to which the target sample point belongs can be determined as Z.
Through the scheme provided by the embodiment of the application, the sample points can be efficiently clustered based on the KNN algorithm so as to determine the preset working condition type to which the target sample point belongs. And comparing the heat consumption rates of the sample points in the preset working condition category to select the heat consumption rate meeting the preset judgment standard. Therefore, when the unit operates according to the target working condition type, the unit operating pressure is controlled to be the target pressure parameter, so that the heat consumption rate of the unit meets the preset judgment standard, the heat consumption rate of the unit is effectively controlled, and the effects of energy conservation and emission reduction are achieved.
Based on the solution provided in the foregoing embodiment, optionally, as shown in fig. 6, after determining the operating pressure parameter in the operating sample data corresponding to the target heat rate as the target pressure parameter of the target unit under the target preset working condition category, the solution further includes the following steps:
s61: performing regression processing on the target pressure parameter under each preset working condition category through a least square method to determine a target sliding pressure curve;
in step S14, when the operating state of the target unit corresponds to the target preset operating condition type, performing pressure control on the target unit based on the target pressure parameter includes:
s62: and when the running state of the target unit corresponds to the target preset working condition type, controlling the target unit to run at a target pressure parameter under the target preset working condition according to the target sliding pressure curve.
After the target pressure parameters under each preset working condition category are determined, the scheme provided by the embodiment performs regression processing on each target pressure parameter through a least square method to obtain a target sliding pressure curve. The target sliding pressure curve represents a corresponding target pressure parameter when the unit is in operation of each working condition type. The sliding pressure curve can be implanted into a DCS (distributed control system) to automatically adjust pressure parameters according to the working condition type of the unit, so that the unit runs with target pressure parameters, the heat consumption rate of the unit in the running process is ensured to meet the preset judgment standard, and the effects of energy conservation and emission reduction are realized.
According to the scheme provided by the embodiment of the application, the target pressure parameter of the unit in the target working condition type can be determined, the heat consumption rate of the unit is controlled by controlling the unit operation pressure parameter, and the method and the device have the advantages of high reliability and stable control. Moreover, the automation level is high, the labor cost is effectively reduced, energy conservation and emission reduction can be effectively realized, and the economic profit is improved. Meanwhile, the safety of the unit in the sliding pressure optimization process can be effectively guaranteed.
In order to solve the problems in the prior art, an embodiment of the present application further provides an electronic device 70, as shown in fig. 7, including:
the acquiring module 71 acquires a training data set and a sample data set of a target unit, wherein the training data set includes preset training data corresponding to a plurality of preset working condition categories, each preset training data set includes a training load parameter and a plurality of training pressure parameters corresponding to the training load parameter, the sample data set includes a plurality of sets of operation sample data during actual operation of the target unit, and each set of operation sample data includes an operation load parameter and an operation pressure parameter corresponding to the operation load parameter;
the clustering module 72 is used for clustering the sample data set through a proximity algorithm based on the training data set and determining the preset working condition category of each group of operation sample data;
the first determining module 73 is used for determining the heat consumption rate corresponding to at least one operation sample data of the target preset working condition type according to the at least one operation sample data belonging to the target preset working condition type;
a second determining module 74, configured to determine an operating pressure parameter in operating sample data corresponding to a target heat rate as a target pressure parameter of the target unit under the target preset operating condition category, where the target heat rate includes a heat rate meeting a preset determination standard in at least one heat rate corresponding to the target preset operating condition category;
and the control module 75 is used for performing pressure control on the target unit based on the target pressure parameter when the running state of the target unit corresponds to the target preset working condition type.
Based on the electronic device provided in the foregoing embodiment, optionally, each set of operation sample data in the sample data set further includes at least one of the following parameters:
the system comprises a temperature, a main steam flow, a main steam enthalpy value, a main water supply enthalpy value, a reheat steam pipeline hot section flow, a reheat steam hot end enthalpy value, a reheat steam cold end enthalpy value, a chemical make-up water flow, a chemical make-up water enthalpy value, an overheating and desuperheating water flow, an overheating and desuperheating water enthalpy value, a reheating and desuperheating water flow, a reheating and desuperheating water enthalpy value and a generator output power.
Based on the electronic device provided in the foregoing embodiment, optionally, the clustering module 72 is configured to:
establishing a two-dimensional coordinate system according to the load parameter and the pressure parameter;
generating a plurality of training points corresponding to the preset training data in the two-dimensional coordinate system according to the training load parameters and the training pressure parameters of each group of preset training data in the training data set;
generating a plurality of sample points corresponding to the operation sample data in the two-dimensional coordinate system according to the operation load parameter and the operation pressure parameter of each group of operation sample data in the sample data set;
performing clustering on the plurality of sample points by a proximity algorithm based on the plurality of training points.
Based on the electronic device provided in the foregoing embodiment, optionally, the clustering module 72 is configured to:
determining Euclidean distances between a target sample point and each training point in the two-dimensional coordinate system;
and determining the preset working condition type of the operation sample data corresponding to the target sample point according to the training points with Euclidean distances meeting the preset distance standard.
Based on the electronic device provided in the foregoing embodiment, optionally, the clustering module 72 is configured to:
sequencing the training points according to Euclidean distances between the target sample point and the training points;
determining a preset number of training points as training points meeting a preset distance standard according to the sequencing result;
determining the preset working condition types corresponding to the training points which accord with the preset distance standard;
and determining the preset working condition type to which the operation sample data corresponding to the target sample point belongs according to the preset working condition type corresponding to each training point meeting the preset distance standard.
Based on the electronic device provided in the foregoing embodiment, optionally, the clustering module 72 is configured to:
when the number of the preset working condition types corresponding to the training points meeting the preset distance standard is multiple, determining the probability that the operation sample data of the target sample point belongs to each preset working condition type according to the preset working condition types corresponding to the training points meeting the preset distance standard;
and determining the preset working condition type to which the target sample point belongs according to the probability that the operation sample data of the target sample point belongs to each preset working condition type.
Based on the electronic device provided in the foregoing embodiment, optionally, the control module 75 is configured to:
performing regression processing on the target pressure parameter under each preset working condition category through a least square method to determine a target sliding pressure curve;
and when the running state of the target unit corresponds to the target preset working condition type, controlling the target unit to run at a target pressure parameter under the target preset working condition according to the target sliding pressure curve.
The method comprises the steps that a training data set and a sample data set of a target unit are obtained through the electronic equipment provided by the embodiment of the application, wherein the training data set comprises preset training data corresponding to a plurality of preset working condition types respectively, each group of preset training data comprises a training load parameter and a plurality of training pressure parameters corresponding to the training load parameter, the sample data set comprises a plurality of groups of operation sample data during actual operation of the target unit, and each group of operation sample data comprises an operation load parameter and an operation pressure parameter corresponding to the operation load parameter; clustering the sample data set through a proximity algorithm based on the training data set, and determining a preset working condition category to which each group of operation sample data belongs; determining a heat consumption rate corresponding to at least one operation sample data of a target preset working condition type according to the at least one operation sample data belonging to the target preset working condition type; determining an operating pressure parameter in operating sample data corresponding to a target heat consumption rate as a target pressure parameter of the target unit under the target preset working condition type, wherein the target heat consumption rate comprises a heat consumption rate meeting a preset judgment standard in at least one heat consumption rate corresponding to the target preset working condition type; and when the running state of the target unit corresponds to the target preset working condition type, performing pressure control on the target unit based on the target pressure parameter. According to the scheme provided by the embodiment of the application, the target pressure parameter when the unit is in the target working condition type can be determined through the clustering algorithm, and the unit is controlled to operate according to the target pressure parameter, so that the heat consumption rate of the unit meets the preset judgment standard on the premise of ensuring that the unit operates according to the target working condition type, and the control on the operation heat consumption rate of the unit is realized.
Optionally, an embodiment of the present invention further provides an electronic device, which includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, where the computer program, when executed by the processor, implements each process of the above method for controlling a set of pressures, and can achieve the same technical effect, and details are not repeated here to avoid repetition.
An embodiment of the present invention 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 implements each process of the above method for controlling a machine group pressure, and can achieve the same technical effect, and in order to avoid repetition, the computer program is not described herein again. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
It should be noted that, in this document, 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 an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A method of stack pressure control, comprising:
acquiring a training data set and a sample data set of a target unit, wherein the training data set comprises preset training data corresponding to a plurality of preset working condition types respectively, each group of preset training data comprises a training load parameter and a plurality of training pressure parameters corresponding to the training load parameter, the sample data set comprises a plurality of groups of operation sample data during actual operation of the target unit, and each group of operation sample data comprises an operation load parameter and an operation pressure parameter corresponding to the operation load parameter;
clustering the sample data set through a proximity algorithm based on the training data set, and determining a preset working condition category to which each group of operation sample data belongs;
determining a heat consumption rate corresponding to at least one operation sample data of a target preset working condition type according to the at least one operation sample data belonging to the target preset working condition type;
determining an operating pressure parameter in operating sample data corresponding to a target heat consumption rate as a target pressure parameter of the target unit under the target preset working condition type, wherein the target heat consumption rate comprises a heat consumption rate meeting a preset judgment standard in at least one heat consumption rate corresponding to the target preset working condition type;
and when the running state of the target unit corresponds to the target preset working condition type, performing pressure control on the target unit based on the target pressure parameter.
2. The method of claim 1, wherein each set of operating sample data in the set of sample data further comprises at least one of:
the system comprises a temperature, a main steam flow, a main steam enthalpy value, a main water supply enthalpy value, a reheat steam pipeline hot section flow, a reheat steam hot end enthalpy value, a reheat steam cold end enthalpy value, a chemical make-up water flow, a chemical make-up water enthalpy value, an overheating and desuperheating water flow, an overheating and desuperheating water enthalpy value, a reheating and desuperheating water flow, a reheating and desuperheating water enthalpy value and a generator output power.
3. The method of claim 1, wherein performing clustering on the sample data set by a proximity algorithm based on the training data set comprises:
establishing a two-dimensional coordinate system according to the load parameter and the pressure parameter;
generating a plurality of training points corresponding to the preset training data in the two-dimensional coordinate system according to the training load parameters and the training pressure parameters of each group of preset training data in the training data set;
generating a plurality of sample points corresponding to the operation sample data in the two-dimensional coordinate system according to the operation load parameter and the operation pressure parameter of each group of operation sample data in the sample data set;
performing clustering on the plurality of sample points by a proximity algorithm based on the plurality of training points.
4. The method of claim 3, wherein performing clustering on the plurality of sample points by a proximity algorithm based on the plurality of training points comprises:
determining Euclidean distances between a target sample point and each training point in the two-dimensional coordinate system;
and determining the preset working condition type of the operation sample data corresponding to the target sample point according to the training points with Euclidean distances meeting the preset distance standard.
5. The method of claim 4, wherein determining the preset working condition class to which the operation sample data corresponding to the target sample point belongs according to the training points with Euclidean distances meeting the preset distance standard comprises:
sequencing the training points according to Euclidean distances between the target sample point and the training points;
determining a preset number of training points as training points meeting a preset distance standard according to the sequencing result;
determining the preset working condition types corresponding to the training points which accord with the preset distance standard;
and determining the preset working condition type to which the operation sample data corresponding to the target sample point belongs according to the preset working condition type corresponding to each training point meeting the preset distance standard.
6. The method of claim 5, wherein determining the preset working condition class to which the operation sample data corresponding to the target sample point belongs according to the preset working condition class corresponding to each training point meeting the preset distance criterion comprises:
when the number of the preset working condition types corresponding to the training points meeting the preset distance standard is multiple, determining the probability that the operation sample data of the target sample point belongs to each preset working condition type according to the preset working condition types corresponding to the training points meeting the preset distance standard;
and determining the preset working condition type to which the target sample point belongs according to the probability that the operation sample data of the target sample point belongs to each preset working condition type.
7. The method according to any one of claims 1 to 6, wherein after determining the operating pressure parameter in the operating sample data corresponding to the target heat rate as the target pressure parameter of the target unit under the target preset operating condition category, the method further comprises:
performing regression processing on the target pressure parameter under each preset working condition category through a least square method to determine a target sliding pressure curve;
when the running state of the target unit corresponds to the target preset working condition type, performing pressure control on the target unit based on the target pressure parameter, wherein the pressure control method comprises the following steps:
and when the running state of the target unit corresponds to the target preset working condition type, controlling the target unit to run at a target pressure parameter under the target preset working condition according to the target sliding pressure curve.
8. An electronic device, comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module acquires a training data set and a sample data set of a target unit, the training data set comprises preset training data respectively corresponding to a plurality of preset working condition types, each preset training data set comprises a training load parameter and a plurality of training pressure parameters corresponding to the training load parameter, the sample data set comprises a plurality of groups of operation sample data of the target unit in actual operation, and each group of operation sample data comprises an operation load parameter and an operation pressure parameter corresponding to the operation load parameter;
the clustering module is used for clustering the sample data set through a proximity algorithm based on the training data set and determining the preset working condition type of each group of operating sample data;
the first determining module is used for determining the heat consumption rate corresponding to at least one operation sample data of a target preset working condition type according to the at least one operation sample data of the target preset working condition type;
the second determining module is used for determining an operating pressure parameter in operating sample data corresponding to a target heat consumption rate as a target pressure parameter of the target unit under the target preset working condition type, wherein the target heat consumption rate comprises a heat consumption rate meeting a preset judgment standard in at least one heat consumption rate corresponding to the target preset working condition type;
and the control module is used for carrying out pressure control on the target unit based on the target pressure parameter when the running state of the target unit corresponds to the target preset working condition type.
9. An electronic device, comprising: memory, processor and computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010856297.7A CN112181003A (en) | 2020-08-24 | 2020-08-24 | Method for controlling unit pressure and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010856297.7A CN112181003A (en) | 2020-08-24 | 2020-08-24 | Method for controlling unit pressure and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112181003A true CN112181003A (en) | 2021-01-05 |
Family
ID=73924300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010856297.7A Pending CN112181003A (en) | 2020-08-24 | 2020-08-24 | Method for controlling unit pressure and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112181003A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013074695A (en) * | 2011-09-27 | 2013-04-22 | Meiji Univ | Device, method and program for predicting photovoltaic generation |
| CN106709662A (en) * | 2016-12-30 | 2017-05-24 | 山东鲁能软件技术有限公司 | Electrical equipment operation condition classification method |
| CN107656154A (en) * | 2017-09-18 | 2018-02-02 | 杭州安脉盛智能技术有限公司 | Based on the Diagnosis Method of Transformer Faults for improving Fuzzy C-Means Cluster Algorithm |
| CN110147820A (en) * | 2019-04-11 | 2019-08-20 | 北京远航通信息技术有限公司 | Recommended method, device, equipment and the storage medium of the additional oil mass of flight |
| CN110262281A (en) * | 2019-05-07 | 2019-09-20 | 东南大学 | Unit sliding pressure operation control method and system |
| CN110400018A (en) * | 2019-07-29 | 2019-11-01 | 上海电力大学 | Progress control method, system and device for coal-fired firepower electrical plant pulverized coal preparation system |
| CN110837226A (en) * | 2019-12-26 | 2020-02-25 | 华润电力技术研究院有限公司 | Thermal power generating unit operation optimization method based on intelligent optimization algorithm and related device |
| CN111178594A (en) * | 2019-12-12 | 2020-05-19 | 湖南大唐先一科技有限公司 | Thermal power generating unit peak regulation capability prediction method, device and system |
| CN111352408A (en) * | 2020-03-11 | 2020-06-30 | 山东科技大学 | Multi-working-condition process industrial process fault detection method based on evidence K nearest neighbor |
-
2020
- 2020-08-24 CN CN202010856297.7A patent/CN112181003A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013074695A (en) * | 2011-09-27 | 2013-04-22 | Meiji Univ | Device, method and program for predicting photovoltaic generation |
| CN106709662A (en) * | 2016-12-30 | 2017-05-24 | 山东鲁能软件技术有限公司 | Electrical equipment operation condition classification method |
| CN107656154A (en) * | 2017-09-18 | 2018-02-02 | 杭州安脉盛智能技术有限公司 | Based on the Diagnosis Method of Transformer Faults for improving Fuzzy C-Means Cluster Algorithm |
| CN110147820A (en) * | 2019-04-11 | 2019-08-20 | 北京远航通信息技术有限公司 | Recommended method, device, equipment and the storage medium of the additional oil mass of flight |
| CN110262281A (en) * | 2019-05-07 | 2019-09-20 | 东南大学 | Unit sliding pressure operation control method and system |
| CN110400018A (en) * | 2019-07-29 | 2019-11-01 | 上海电力大学 | Progress control method, system and device for coal-fired firepower electrical plant pulverized coal preparation system |
| CN111178594A (en) * | 2019-12-12 | 2020-05-19 | 湖南大唐先一科技有限公司 | Thermal power generating unit peak regulation capability prediction method, device and system |
| CN110837226A (en) * | 2019-12-26 | 2020-02-25 | 华润电力技术研究院有限公司 | Thermal power generating unit operation optimization method based on intelligent optimization algorithm and related device |
| CN111352408A (en) * | 2020-03-11 | 2020-06-30 | 山东科技大学 | Multi-working-condition process industrial process fault detection method based on evidence K nearest neighbor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2729891B1 (en) | Automatic identification of operating parameters for power plants | |
| CN108052007B (en) | Thermal power generating unit operation optimization method, device and equipment and computer storage medium | |
| CN109713668B (en) | New energy base direct current outgoing chain off-line early warning and defense system and method | |
| CN112146156B (en) | Multi-mode flexible operation method and system for power plant with electric boiler | |
| CN112130538B (en) | Method, device, equipment and medium for control optimization and model training of coal mill | |
| CN108490790A (en) | A kind of overheating steam temperature active disturbance rejection cascade control method based on multiple-objection optimization | |
| CN111652479A (en) | Data driving method for dynamic security assessment of power system | |
| CN105320114A (en) | Thermal power station boiler combustion adjusting model obtaining method based on data excavation | |
| CN111339713A (en) | Optimal design method and system for wind power plant, electronic device and storage medium | |
| CN112070358A (en) | Method and system for determining electric load adjustment interval of low-vacuum heat supply unit | |
| CN109858125B (en) | Thermal power unit power supply coal consumption calculation method based on radial basis function neural network | |
| CN105074586A (en) | Method for the computerized control and/or regulation of a technical system | |
| CN111126707B (en) | Energy consumption equation construction and energy consumption prediction method and device | |
| CN112181003A (en) | Method for controlling unit pressure and electronic equipment | |
| CN116184828A (en) | Online real-time optimization method and system for high-speed valve characteristic curve of self-adaptive steam turbine | |
| CN115965156A (en) | Scheduling method and scheduling device of energy system | |
| Gu et al. | Quasi-Monte Carlo simulation based economic dispatch with wind power integrated | |
| CN115712976A (en) | Heat energy and electric load optimization method based on multi-element heat supply unit and related equipment | |
| CN114970766A (en) | Power station unit operation parameter reference value obtaining method based on linear fitting | |
| CN115102164A (en) | Multi-unit collaborative optimization load distribution method, system, equipment and storage medium | |
| CN109506248B (en) | Case reasoning boiler combustion optimization method based on online optimization | |
| CN110932334B (en) | Wind power plant power control method with constraint multi-objective optimization | |
| CN113536508A (en) | Method and system for classifying manufacturing network nodes | |
| Ramirez-Gonzalez et al. | Power System Inertia Estimation Using A Residual Neural Network Based Approach | |
| Garbea et al. | Clustering-Using Data Mining-based Application to Identify the Hourly Loading Patterns of the Generation Units from the Hydropower Plants |
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 |