CN113611375B - Method, device, equipment and storage medium for determining data in thermal power plant system - Google Patents

Method, device, equipment and storage medium for determining data in thermal power plant system Download PDF

Info

Publication number
CN113611375B
CN113611375B CN202110907440.5A CN202110907440A CN113611375B CN 113611375 B CN113611375 B CN 113611375B CN 202110907440 A CN202110907440 A CN 202110907440A CN 113611375 B CN113611375 B CN 113611375B
Authority
CN
China
Prior art keywords
data
nitrogen oxide
target
initial data
data set
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110907440.5A
Other languages
Chinese (zh)
Other versions
CN113611375A (en
Inventor
廖强
刘正一
王向勇
陈俊
李辰
段斌
曾金龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chengdu Jiahua Chain Cloud Technology Co ltd
Original Assignee
Chengdu Jiahua Chain Cloud Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Chengdu Jiahua Chain Cloud Technology Co ltd filed Critical Chengdu Jiahua Chain Cloud Technology Co ltd
Priority to CN202110907440.5A priority Critical patent/CN113611375B/en
Publication of CN113611375A publication Critical patent/CN113611375A/en
Application granted granted Critical
Publication of CN113611375B publication Critical patent/CN113611375B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/70—Machine learning, data mining or chemometrics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Crystallography & Structural Chemistry (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Chemical & Material Sciences (AREA)
  • Medical Informatics (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Biology (AREA)
  • Feedback Control In General (AREA)
  • Treating Waste Gases (AREA)

Abstract

The application provides a data determining method, a device, equipment and a storage medium in a thermal power plant system, wherein the method comprises the following steps: inputting the reactor data corresponding to the SCR reactor and the initial data sets into a nitrogen oxide prediction model to obtain a plurality of nitrogen oxide discharge data sets corresponding to the target system, wherein the nitrogen oxide discharge data sets comprise a plurality of nitrogen oxide discharge data; calculating a group qualification degree corresponding to each nitrogen oxide emission data set according to a plurality of nitrogen oxide emission data sets corresponding to the target system, wherein the group qualification degree is used for evaluating the merits of the initial data set; and if the maximum group good evaluation degree in the plurality of group good evaluation degrees does not meet the target condition, generating a plurality of initial data sets which are input into the nitrogen oxide prediction model next time according to the plurality of initial data sets, and obtaining a target data set until the maximum group good evaluation degree meets the target condition.

Description

Method, device, equipment and storage medium for determining data in thermal power plant system
Technical Field
The application relates to the technical field of thermal power plants, in particular to a method, a device and equipment for determining data in a thermal power plant system and a storage medium.
Background
The prior art realizes the prediction of nitrogen oxide emission data of a thermal power plant, usually establishes an ARIMA model, predicts the nitrogen oxide emission data through the established ARIMA model, and adjusts the flow of ammonia steam inlet into a selective catalytic reduction (Selective Catalytic Reduction, SCR) reactor according to the predicted nitrogen oxide emission data of a chimney inlet after the nitrogen oxide emission data of the chimney inlet is obtained through the prediction of the ARIMA model. For example, when the predicted emission data of nitrogen oxides at the inlet of the chimney is serious to environmental pollution, the flow rate of the ammonia steam inlet into the SCR reactor is increased so as to reduce the emission data of nitrogen oxides at the inlet of the chimney.
Although the nitrogen oxide emission data of the chimney inlet is predicted by the ARIMA model, when the nitrogen oxide emission data of the chimney inlet is too large or too small, manual adjustment is still needed, the efficiency is low, and the adjustment to a very proper value is difficult.
Disclosure of Invention
Based on the method, the device, the equipment and the storage medium for determining the data in the thermal power plant system are provided, so that the problem of low manual adjustment efficiency in the prior art is solved.
In a first aspect, a method for determining data in a thermal power plant system is provided, including:
generating a plurality of initial data sets for the SCR reactor in a target system, wherein the initial data sets comprise a plurality of initial data, the initial data comprise ammonia vapor inlet flow rate, and the target system comprises a thermal power plant system;
obtaining reactor data corresponding to the SCR reactor;
inputting the reactor data corresponding to the SCR reactor and the initial data sets into a nitrogen oxide prediction model to obtain a plurality of nitrogen oxide discharge data sets corresponding to the target system, wherein the nitrogen oxide discharge data sets comprise a plurality of nitrogen oxide discharge data;
calculating a group qualification degree corresponding to each nitrogen oxide emission data set according to a plurality of nitrogen oxide emission data sets corresponding to the target system, wherein the group qualification degree is used for evaluating the merits of the initial data set;
and if the maximum group good evaluation degree in the plurality of group good evaluation degrees does not meet the target condition, generating a plurality of initial data sets which are input into the nitrogen oxide prediction model next time according to the plurality of initial data sets, and obtaining a target data set until the maximum group good evaluation degree meets the target condition.
According to the data determining method in the thermal power plant system, a plurality of initial data sets are generated for the SCR reactor in the target system, then the initial data sets and reactor data corresponding to the SCR reactor are input into the nitrogen oxide prediction model, the nitrogen oxide discharge data are predicted through the nitrogen oxide prediction model, then the group preference degree is calculated according to the nitrogen oxide discharge data obtained through prediction, namely, the preference degree of the initial data sets is calculated, and when the maximum group preference degree meets the target condition, the target data sets are obtained. Therefore, according to the method, continuous adjustment is not needed, and only under the condition that the reactor data are determined, the optimal target data set is selected through calculating the group evaluation degree, so that compared with a manual adjustment method, the adjustment efficiency is improved, and in this way, the optimal target data set (ammonia steam inlet flow) can be obtained quickly.
In one embodiment, the calculating the group merit corresponding to each nox emission data set according to the nox emission data sets corresponding to the target system includes: calculating a first-stage emission limiting loss corresponding to a target nitrogen oxide emission data set according to the target nitrogen oxide emission data set corresponding to the target system and first reference nitrogen oxide emission data; calculating a second-level emission limiting loss corresponding to the target nitrogen oxide emission data set according to the target nitrogen oxide emission data set corresponding to the target system and second reference nitrogen oxide emission data; calculating data consumption loss corresponding to the target nitrogen oxide discharge data set according to the initial data set and the reference data set corresponding to the target nitrogen oxide discharge data set; calculating the corresponding balance degree of the target nitrogen oxide discharge data set according to the target nitrogen oxide discharge data set corresponding to the target system; and obtaining the group qualification degree corresponding to the target nitrogen oxide emission data group by using the primary limit emission loss, the secondary limit emission loss, the data elimination loss and the balance degree corresponding to the target nitrogen oxide emission data group.
According to the embodiment, the four losses are combined to generate the group good evaluation degree, so that the accuracy of the group good evaluation degree is improved.
In one embodiment, the generating a plurality of initial data sets for the next input to the nox predictive model from the plurality of initial data sets includes: determining the combination probability corresponding to the initial data set according to the group qualification degree corresponding to the initial data set; and generating a plurality of initial data sets which are input into the nitrogen oxide prediction model next time according to the corresponding combination probability of each initial data set.
In the above embodiment, a method for generating a plurality of initial data sets is provided, specifically, a plurality of initial data sets input into the nox prediction model next time are generated according to the group merit, it is understood that an initial data set with a high group merit will have a higher probability of being used to generate an initial data set input into the nox prediction model next time, so as to increase the speed of obtaining a target data set.
In one embodiment, the determining the combination probability corresponding to the initial data set according to the magnitude of the group goodness corresponding to the initial data set includes: adding the group good scores corresponding to the plurality of initial data groups to obtain a total good score; dividing the group preference degree corresponding to the initial data group by the total preference degree to obtain the combination probability corresponding to the initial data group.
The above embodiment provides a method for determining a combination probability, which can simply obtain the combination probability by solving the way that the group merit degree accounts for the total merit degree.
In one embodiment, the generating a plurality of initial data sets to be input into the nox prediction model next according to the combination probability corresponding to each initial data set includes: according to the combination probability corresponding to each initial data group, combining the plurality of initial data groups in pairs to obtain a plurality of initial data group pairs; crossing the two initial data sets in the plurality of initial data set pairs to obtain a plurality of crossed data set pairs; and carrying out mutation on the two initial data sets in the crossed data set pair to obtain a plurality of initial data sets which are input into the nitrogen oxide prediction model next time.
In the above embodiment, the plurality of initial data sets to be input into the nox prediction model next are generated by combining the data pairs, the cross data pairs, and the variance.
In one embodiment, the reactor data includes operating condition data, time data, derivative data, and time delay data.
In the embodiment, not only a plurality of initial data sets but also a plurality of SCR reactor data are input in the process of obtaining the target data set, so that the finally obtained target data set is more accurate.
In one embodiment, a plurality of SCR reactors are disposed in the target system, and the nitrogen oxide prediction model includes a prediction neural network and a sequence-to-sequence model corresponding to each SCR reactor.
In the above embodiment, when there are a plurality of SCR reactors in the target system, a sequence-to-sequence model is built for each SCR reactor to predict the outlet data (nitrogen oxide discharge data) of each SCR reactor outlet, thereby improving the accuracy of the finally predicted nitrogen oxide discharge data.
In a second aspect, there is provided a data determining apparatus in a thermal power plant system, including:
the generation module is used for generating a plurality of initial data sets for the SCR reactor in a target system, wherein the initial data sets comprise a plurality of initial data, the initial data comprise ammonia vapor inlet flow rates, and the target system comprises a thermal power plant system;
the acquisition module is used for acquiring the reactor data corresponding to the SCR reactor;
the obtaining module is used for inputting the reactor data corresponding to the SCR reactor and the initial data sets into a nitrogen oxide prediction model to obtain a plurality of nitrogen oxide discharge data sets corresponding to the target system, wherein the nitrogen oxide discharge data sets comprise a plurality of nitrogen oxide discharge data;
The calculating module is used for calculating the group qualification degree corresponding to each nitrogen oxide emission data set according to a plurality of nitrogen oxide emission data sets corresponding to the target system, wherein the group qualification degree is used for evaluating the merits of the initial data sets;
and the circulation module is used for generating a plurality of initial data sets which are input into the nitrogen oxide prediction model next according to the plurality of initial data sets if the maximum group good evaluation degree in the plurality of group good evaluation degrees does not meet the target condition, and obtaining the target data sets until the maximum group good evaluation degree meets the target condition.
In one embodiment, the computing module is specifically configured to: calculating a first-stage emission limiting loss corresponding to a target nitrogen oxide emission data set according to the target nitrogen oxide emission data set corresponding to the target system and first reference nitrogen oxide emission data; calculating a second-level emission limiting loss corresponding to the target nitrogen oxide emission data set according to the target nitrogen oxide emission data set corresponding to the target system and second reference nitrogen oxide emission data; calculating data consumption loss corresponding to the target nitrogen oxide discharge data set according to the initial data set and the reference data set corresponding to the target nitrogen oxide discharge data set; calculating the corresponding balance degree of the target nitrogen oxide discharge data set according to the target nitrogen oxide discharge data set corresponding to the target system; and obtaining the group qualification degree corresponding to the target nitrogen oxide emission data group by using the primary limit emission loss, the secondary limit emission loss, the data elimination loss and the balance degree corresponding to the target nitrogen oxide emission data group.
In one embodiment, the circulation module is specifically configured to: determining the combination probability corresponding to the initial data set according to the group qualification degree corresponding to the initial data set; and generating a plurality of initial data sets which are input into the nitrogen oxide prediction model next time according to the corresponding combination probability of each initial data set.
In one embodiment, the circulation module is specifically configured to: adding the group good scores corresponding to the plurality of initial data groups to obtain a total good score; dividing the group preference degree corresponding to the initial data group by the total preference degree to obtain the combination probability corresponding to the initial data group.
In one embodiment, the circulation module is specifically configured to: according to the combination probability corresponding to each initial data group, combining the plurality of initial data groups in pairs to obtain a plurality of initial data group pairs; crossing the two initial data sets in the plurality of initial data set pairs to obtain a plurality of crossed data set pairs; and carrying out mutation on the two initial data sets in the crossed data set pair to obtain a plurality of initial data sets which are input into the nitrogen oxide prediction model next time.
In one embodiment, the reactor data includes operating condition data, time data, derivative data, and time delay data.
In one embodiment, a plurality of SCR reactors are disposed in the target system, and the nitrogen oxide prediction model includes a prediction neural network and a sequence-to-sequence model corresponding to each SCR reactor.
In a third aspect, a computer device is provided, characterized by comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the data determination method in a thermal power plant system as described above when the computer program is executed.
In a fourth aspect, a computer readable storage medium is provided, in which computer program instructions are stored which, when read and run by a processor, perform the steps of the data determination method in a thermal power plant system as described above.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of an implementation flow of a method for determining data in a thermal power plant system according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a sequence-to-sequence model in an embodiment of the application;
FIG. 3 is a schematic diagram of a NOx prediction model according to an embodiment of the present application;
FIG. 4 is a schematic illustration of an intersection in accordance with the present application;
FIG. 5 is a schematic representation of variation in the present application;
FIG. 6 is a schematic diagram of the composition and structure of a data determining device in a thermal power plant system according to an embodiment of the present application;
fig. 7 is a block diagram showing an internal structure of a computer device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In one embodiment, a method of determining data in a thermal power plant system is provided. The execution subject of the data determining method in the thermal power plant system according to the embodiment of the present application is a computer device capable of implementing the data determining method in the thermal power plant system according to the embodiment of the present application, and the computer device may include, but is not limited to, a terminal and a server. The terminal comprises a desktop terminal and a mobile terminal, wherein the desktop terminal comprises, but is not limited to, a desktop computer and a vehicle-mounted computer; mobile terminals include, but are not limited to, cell phones, tablets, notebook computers, and smart watches. The server includes a high-performance computer and a high-performance computer cluster.
In one embodiment, as shown in fig. 1, there is provided a data determining method in a thermal power plant system, including:
step 100, generating a plurality of initial data sets for an SCR reactor in a target system, wherein the initial data sets include a plurality of initial data, the initial data includes an ammonia vapor inlet flow rate, and the target system includes a thermal power plant system.
The SCR reactor selectively reduces nitrogen monoxide and nitrogen dioxide into nitrogen at a certain temperature by the reducing agent ammonia steam in the SCR reactor under the action of the catalyst, and the oxidation reaction of the reducing agent ammonia steam and oxygen hardly occurs, so that the selectivity of the reducing agent to the nitrogen monoxide and the nitrogen dioxide is improved, and the consumption of the reducing agent ammonia steam is reduced.
The flow rate of the ammonia vapor inlet reflects the flow rate of the reducing agent ammonia vapor entering the SCR reactor, and the larger the flow rate of the ammonia vapor inlet, the more the ammonia vapor enters the SCR reactor in unit time, the smaller the flow rate of the ammonia vapor inlet, and the less the ammonia vapor enters the SCR reactor in unit time.
The thermal power plant refers to a thermal power plant.
The number of SCR reactors in the target system may be one or two or more. When the number of SCR reactors in the target system is one, each initial data set includes a plurality of initial data which are input to the unique SCR reactor, for example, there are 100 initial data sets, 5 initial data in each initial data set, and the i-th initial data set is [ Ai1, ai2, ai3, ai4, ai5], and all the 100 initial data sets are input to the unique SCR reactor in the target system; when the number of SCR reactors in the target system is two or more, each initial data set includes a plurality of initial data which are required to be input to each SCR reactor in the target system, for example, there are 100 initial data sets, there are 2 SCR reactors in total in the target system, the SCR reactors 1 and 2 are respectively, the i-th initial data set is [ Ai1, ai2, ai3, ai4, ai5, ai6, ai7, ai8, ai9, ai10], ai1, ai2, ai3, ai4, ai5 in the 100 initial data sets are input to the SCR reactor 1, and Ai6, ai7, ai8, ai9, ai10 in the 100 initial data sets are input to the SCR reactor 2.
Illustratively, generating the plurality of initial data sets includes: a plurality of initial data sets is randomly generated.
When the range of each data in the target data set is not clear, a plurality of initial data sets can be randomly generated, and the method is very suitable for novice operators.
Illustratively, generating the plurality of initial data sets includes: acquiring a reference data range of each initial data in the initial data set; a plurality of initial data sets are generated based on the reference data range of each of the initial data sets.
For example, the initial data group includes 4 initial data, the reference data range of the first initial data is [ P1, P2], the reference data range of the second initial data is [ P3, P4], the reference data range of the third initial data is [ P5, P6], the reference data range of the fourth initial data is [ P7, P8], and thus the first initial data in each generated initial data group needs to be within [ P1, P2], the second initial data needs to be within [ P3, P4], the third initial data needs to be within [ P5, P6], and the fourth initial data needs to be within [ P7, P8 ].
Because the reference data range is preset, the target data set is obtained in the reference data range, compared with the random generation of the initial data set, the optimization range can be reduced, so that the iteration times are reduced, and the speed of obtaining the target data set is further increased to a certain extent.
Step 200, obtaining reactor data corresponding to the SCR reactor.
Reactor data is data relating to SCR reactors. Such as the flue gas temperature at the inlet of the SCR reactor.
When only one SCR reactor is arranged in the target system, acquiring reactor data corresponding to the SCR reactor; when two or more SCR reactors are arranged in the target system, acquiring corresponding reactor data of each SCR reactor.
And 300, inputting the reactor data corresponding to the SCR reactor and the initial data sets into a nitrogen oxide prediction model to obtain a plurality of nitrogen oxide discharge data sets corresponding to the target system, wherein the nitrogen oxide discharge data sets comprise a plurality of nitrogen oxide discharge data.
The nitrogen oxide prediction model is a model capable of predicting nitrogen oxide emission data; nitrogen oxide emission data, which is data reflecting the nitrogen oxide emission condition, for example, nitrogen oxide emission data corresponding to a target system, refers to the concentration of nitrogen oxides at the inlet of a chimney; the NOx emission data set includes a plurality of NOx emission data, and an initial data set corresponds to one of the NOx emission data sets.
And 400, calculating a group qualification degree corresponding to each nitrogen oxide emission data group according to a plurality of nitrogen oxide emission data groups corresponding to the target system, wherein the group qualification degree is used for evaluating the merits of the initial data group.
The set of the nox emission data set is evaluated for the quality of the nox emission data set, and since an initial data set is correspondingly generated into a nox emission data set, the quality of the nox emission data set also reflects the quality of the initial data set. The higher the group merit corresponding to the nox emission data group, the more excellent the nox emission data group, i.e., the more excellent the initial data group, the lower the group merit corresponding to the nox emission data group, the less strong the nox emission data group, i.e., the less strong the initial data group.
Since each of the nitrogen oxide discharge data in the nitrogen oxide discharge data set may pollute the air, the more the discharge is, the more the air pollution is, the less the discharge is, so that the pollution analysis can be performed on each of the nitrogen oxide discharge data in the nitrogen oxide discharge data set, and the group merit corresponding to the nitrogen oxide discharge data set is determined according to the result of the pollution analysis, for example, the more the pollution analysis result is that the pollution is the less the nitrogen oxide discharge data set is, the more the nitrogen oxide discharge data set is excellent, and the group merit corresponding to the nitrogen oxide discharge data set is the greater; the pollution analysis result is that the pollution is larger, the nitrogen oxide discharge data set is worse, and the group acceptance degree corresponding to the nitrogen oxide discharge data set is smaller.
Providing an example of determining the group preference degree corresponding to the nitrogen oxide emission data group, acquiring a reference emission limiting loss, respectively subtracting the reference emission limiting loss from each nitrogen oxide emission data in the nitrogen oxide emission data group to obtain the data preference degree of each nitrogen oxide emission data in the nitrogen oxide emission data group, and adding the data preference degree of each nitrogen oxide emission data in the nitrogen oxide emission data group to obtain the group preference degree corresponding to the nitrogen oxide emission data group. For example, the nox emission data set is [ D1, D2, D3, D4, D5], the reference emission limiting loss is Dc, and then the group merit corresponding to the nox emission data set is: (D1-Dc) + (D2-Dc) (D3-Dc) + (D4-Dc) + (D5-Dc).
And 500, if the maximum group good evaluation degree in the plurality of group good evaluation degrees does not meet the target condition, generating a plurality of initial data sets which are input into the nitrogen oxide prediction model next time according to the plurality of initial data sets, and obtaining a target data set when the maximum group good evaluation degree meets the target condition.
A target condition, for example, the target condition is that the maximum group preference is greater than a preset preference, where the preset preference is one preference that is preset, and a value of the preset preference may be set relatively greater, so that the obtained target data set is more excellent (for example, less pollution to the environment), and correspondingly, if the maximum group preference in the plurality of group preference does not meet the target condition, a plurality of initial data sets input into the nitrogen oxide prediction model next time are generated according to the plurality of initial data sets, including: if the largest group preference among the group preference is smaller than a preset preference, generating a plurality of initial data sets which are input into the nitrogen oxide prediction model next time according to the plurality of initial data sets; for another example, the target condition is that the number of times of calculation corresponding to the largest group preference degree among the plurality of group preference degrees reaches a predetermined number of times, where the predetermined number of times is a preset number of times, and correspondingly, if the largest group preference degree among the plurality of group preference degrees does not meet the target condition, generating a plurality of initial data sets input into the nitrogen oxide prediction model next time according to the plurality of initial data sets, including: if the number of times of calculation corresponding to the largest group preference among the plurality of group preference values is smaller than the preset number of times, generating a plurality of initial data sets which are input into the nitrogen oxide prediction model next time according to the plurality of initial data sets, and increasing the number of times of calculation corresponding to the largest group preference among the plurality of group preference values by 1 every time step 400 is executed; for another example, if the target condition is that the absolute value of the difference between the greatest group merit degree of the plurality of group merit degrees and the last greatest group merit degree is smaller than a preset absolute value, and correspondingly, if the greatest group merit degree of the plurality of group merit degrees does not meet the target condition, generating a plurality of initial data sets input into the nitrogen oxide prediction model next time according to the plurality of initial data sets, including: if the absolute value of the difference between the largest group preference degree of the plurality of group preference degrees and the largest group preference degree of the last "plurality of group preference degrees" is greater than or equal to the absolute value of the preset value, generating a plurality of initial data groups which are input into the nitrogen oxide prediction model next time according to the plurality of initial data groups, for example, assuming that the largest group preference degree of the plurality of group preference degrees is A according to the calculation of the reactor data corresponding to the plurality of initial data groups and the SCR reactor, and obtaining the largest group preference degree of the plurality of group preference degrees according to the calculation of the reactor data corresponding to the plurality of initial data groups and the SCR reactor last time is B, then generating a plurality of initial data groups which are input into the nitrogen oxide prediction model next time if the absolute value of the absolute value is greater than or equal to the preset absolute value C until the largest group preference degree of the plurality of group preference degrees and the largest group preference degree of the last "group preference degree of the plurality of group preference degrees" are smaller than the absolute value of the target data.
Obtaining the maximum group good evaluation degree from the group good evaluation degree corresponding to the plurality of nitrogen oxide discharge data groups, if the maximum group good evaluation degree is still smaller than the preset good evaluation degree, generating a plurality of initial data groups which are input into the nitrogen oxide prediction model next time according to the plurality of initial data groups, and repeatedly executing the steps 300 to 500 until the maximum group good evaluation degree meets the target condition, so as to obtain a target data group, wherein the target data group is the initial data group which can obtain the better nitrogen oxide discharge data group.
In the above embodiment, a plurality of initial data sets are generated for the SCR reactor in the target system, then the initial data sets and the reactor data corresponding to the SCR reactor are input into the nitrogen oxide prediction model, the nitrogen oxide emission data is predicted by the nitrogen oxide prediction model, and then the group preference is calculated according to the predicted nitrogen oxide emission data, that is, the preference of the initial data sets is calculated, and when the maximum group preference satisfies the target condition, the target data sets are obtained. Therefore, according to the method, continuous adjustment is not needed, and only under the condition that the reactor data are determined, the optimal target data set is selected through calculating the group evaluation degree, so that compared with a manual adjustment method, the adjustment efficiency is improved, and in this way, the optimal target data set (ammonia steam inlet flow) can be obtained quickly.
In one embodiment, the reactor data comprises: working condition data, time data, derivative data and time delay data.
The working condition data is data reflecting the working condition of the SCR reactor, and for example, the working condition data comprises SCR inlet pressure, SCR inlet-outlet pressure difference height, SCR inlet flue gas temperature, SCR inlet oxygen and boiler load. The pressure of the SCR inlet is the pressure of the flue gas at the inlet of the SCR reactor; the pressure difference between the inlet and the outlet of the SCR is high, and is the difference between the pressure of the flue gas at the outlet of the SCR and the pressure of the flue gas at the inlet of the SCR; the temperature of the flue gas at the inlet of the SCR reactor is the temperature of the flue gas at the inlet of the SCR reactor; SCR inlet oxygen, reflecting the condition of oxygen entering the SCR reactor; the boiler load, which is the power generated by the boiler, also affects the nitrogen oxides output by the SCR reactor.
Time data, which are times corresponding to the respective data, e.g. initial data [ Ai1, ai2, ai3, ai4, ai5 ]]The time corresponding to the initial data is [ T ] Ai1 ，T Ai2 ，T Ai3 ，T Ai4 ，T Ai5 ]For another example, the data is the boiler load, and the boiler load is assumed to be [ G1, G2, G3, G4, G5 ]]The time corresponding to the boiler load is [ T ] G1 ，T G2 ，T G3 ，T G4 ，T G5 ]。
The derivative data is derived from data, for example, the data is the boiler load, and the boiler load is derived from the derivative data, so that it is possible to determine whether the trend of the boiler load is increasing or decreasing.
Time delay data is time delay data (nitrogen oxide concentration) of the SCR reactor outlet within a current period of time, for example, the current time is 10 points 30 minutes 00 seconds, and the time delay data is 5 minutes, then the time delay data is [ S1, S2, S3, S4, S5], wherein S1 is 10 points 25 minutes 00 seconds of the SCR reactor outlet nitrogen oxide discharge data, S2 is 10 points 26 minutes 00 seconds of the SCR reactor outlet nitrogen oxide discharge data, S3 is 10 points 27 minutes 00 seconds of the SCR reactor outlet nitrogen oxide discharge data, S4 is 10 points 28 minutes 00 seconds of the SCR reactor outlet nitrogen oxide discharge data, and S5 is 10 points 29 minutes 00 seconds of the SCR reactor outlet nitrogen oxide discharge data.
In the embodiment, not only a plurality of initial data sets but also a plurality of SCR reactor data are input in the process of obtaining the target data set, so that the finally obtained target data set is more accurate.
In one embodiment, a plurality of SCR reactors are arranged in the target system, and the nitrogen oxide prediction model comprises a prediction neural network and a sequence-to-sequence model corresponding to each SCR reactor; step 300, inputting the reactor data corresponding to the SCR reactor and the plurality of initial data sets into a nitrogen oxide prediction model to obtain a plurality of nitrogen oxide emission data sets corresponding to the target system, including:
Step 301, for each SCR reactor in the plurality of SCR reactors, inputting, from the plurality of initial data sets, initial data corresponding to the SCR reactor and the operating condition data, time data, derivative data corresponding to the SCR reactor to a sequence model corresponding to the SCR reactor, to obtain a plurality of outlet data sets of outlets of the SCR reactors, where each outlet data set includes a plurality of outlet data, and the outlet data includes nitrogen oxide discharge data.
Sequence-to-sequence model consisting of an encoder for encoding an input to obtain encoded features and a decoder for decoding from the encoded features to obtain a desired output, x1 to x5 forming the input of the sequence-to-sequence model and v1 to v5 forming the output of the sequence-to-sequence model as shown in fig. 2, since hi (i > = 2) is generated by hi-1 and xi, to maintain the overall structural consistency, h0 is set to generate h1 when i=1, and likewise, since qi (i > = 2) is generated by qi-1 and C, to maintain the overall structural consistency, q0 is set to generate q1 when i=1. In the embodiment of the invention, x1 to x5 are data (including initial data, working condition data, time data and derivative data) of different times, and v1 to v5 are output (nitrogen oxide discharge data) of different times.
The nitrogen oxide emission data of the outlet of the SCR reactor is an intermediate result of a nitrogen oxide prediction model, and the nitrogen oxide emission data of the inlet of the chimney needs to be obtained by combining the nitrogen oxide emission data of all the outlets of the SCR reactor in the target system.
For example, in fig. 3, there are 2 SCR reactors, SCR reactor 1 and SCR reactor 2, respectively, and the model for predicting nitrogen oxides includes: the sequence corresponding to the SCR reactor 1 is input into the sequence model 1, and the sequence corresponding to the SCR reactor 2 is input into the sequence model 1, so that a plurality of outlet data groups [ Mi1, mi2, mi3, mi4, mi5] of the outlet of the SCR reactor 1 are obtained, and the working condition data 2, time data 2, derivative data 2 corresponding to the SCR reactor 2, the initial data [ Ai6, ai7, ai8, ai9, ai10] corresponding to the SCR reactor 2 in the ith initial data group, and the initial data [ Ai1, ai2, ai3, ai4, ai5] corresponding to the SCR reactor 1 in the ith initial data group are input into the sequence model 1, so that a plurality of outlet data groups [ Mi6, mi7, mi8, mi9, mi10] of the outlet of the SCR reactor 2 are obtained.
And 302, inputting a plurality of outlet data sets of the outlets of the SCR reactors and corresponding time delay data of the SCR reactors into the prediction neural network to obtain a plurality of nitrogen oxide discharge data sets corresponding to the target system.
And predicting the neural network, namely obtaining the nitrogen oxide discharge data of the chimney inlet by combining the nitrogen oxide discharge data of all the outlets of the SCR reactors in the target system and the time-lapse data.
Referring to fig. 3, a plurality of outlet data sets [ Mi1, mi2, mi3, mi4, mi5] at the outlet of the SCR reactor 1, a plurality of outlet data sets [ Mi6, mi7, mi8, mi9, mi10] at the outlet of the SCR reactor 2, and a plurality of outlet data sets [ Mi2, mi8, mi9, mi10] at the outlet of the SCR reactor 2 are input into a predictive neural network to obtain an ith nitrogen oxide emission data set [ Di1, di2, di3, di4, di5] corresponding to a target system.
In the above embodiment, when there are a plurality of SCR reactors in the target system, a sequence-to-sequence model is built for each SCR reactor to predict the outlet data (nitrogen oxide discharge data) of each SCR reactor outlet, thereby improving the accuracy of the finally predicted nitrogen oxide discharge data.
In one embodiment, before generating the plurality of initial data sets for the SCR reactor in the target system in step 100, the method further includes:
and step 000, training the nitrogen oxide prediction model.
Acquiring reactor training data corresponding to each SCR reactor in a target system; acquiring an initial training data set corresponding to each SCR reactor in a target system, wherein the initial training data set comprises a plurality of initial training data, and the initial training data comprises ammonia steam inlet training flow; acquiring a real nitrogen oxide discharge data set; acquiring a real outlet data set of each SCR reactor outlet; inputting the reactor training data and the initial training data set corresponding to each SCR reactor into a nitrogen oxide prediction model to obtain a training outlet data set and a training nitrogen oxide discharge data set of each SCR reactor outlet; calculating the corresponding outlet loss of each SCR reactor according to the training outlet data set of each SCR reactor outlet and the real outlet data set of the corresponding SCR reactor outlet; calculating a discharge loss from the training nox discharge data set and the real nox discharge data set; summing the discharge loss and the corresponding outlet loss of each SCR reactor to obtain total loss; and training the nitrogen oxide prediction model according to the total loss until the total loss is smaller than the preset total loss, so as to obtain a trained nitrogen oxide prediction model.
The average absolute error MAE is used to calculate the exit loss and the exit loss, for example.
In order to ensure training accuracy, reliability of each data involved in training needs to be ensured, and thus, reactor training data and an initial training data set corresponding to each SCR reactor in the target system are acquired, including: acquiring original training data and an initial original training data set of a reactor corresponding to each SCR reactor in a target system; removing abnormal values from the original training data and the initial original training data set of the reactor corresponding to each SCR reactor in the target system to obtain the normal training data and the initial normal training data set of the reactor corresponding to each SCR reactor in the target system; and carrying out missing data filling processing on the reactor training normal data and the initial training normal data set corresponding to each SCR reactor in the target system to obtain the reactor training data and the initial training data set corresponding to each SCR reactor in the target system.
For example, assuming that 30 initial training data are included in one initial training data set, wherein 2 initial training data are abnormal (for example, abnormal initial training is included in 30 initial training data is identified through a box graph), so that the 2 initial training data with the abnormality are removed to obtain an initial training data set only including 28 initial training data, and after the abnormal data are removed, the initial training data set only includes 28 initial training data, and 2 initial training data are deleted, therefore, the initial training data set needs to be subjected to missing data filling processing, for example, a linear interpolation method is adopted to perform missing data filling processing on boiler load, so as to obtain an initial training data set including 30 initial training data sets.
The embodiment realizes the training of the nitrogen oxide discharge model.
In one embodiment, the calculating, in step 400, a group preference corresponding to each nox emission data set according to a plurality of nox emission data sets corresponding to the target system includes:
step 401, calculating a first-stage emission limiting loss corresponding to the target nox emission data set according to the target nox emission data set corresponding to the target system and the first reference nox emission data.
The first reference nox emission data is preset emission data that may seriously affect the environment, for example, the first reference nox emission data is first-level emission limit data required by the country.
For example, assuming the first reference nox emission data is Y1, the target nox emission data set is [ Di1, di2, di3, di4, di5], then the first order limiting loss is: (Di 1-Y1) + (Di 2-Y1) + (Di 3-Y1) + (Di 4-Y1) + (Di 5-Y1).
Step 402, calculating a second-level emission limiting loss corresponding to the target nox emission data set according to the target nox emission data set corresponding to the target system and the second reference nox emission data.
The second reference nox emission data is preset emission data that may affect the environment to some extent, for example, the second reference nox emission data is national-required second-level emission-limiting data.
For example, assuming the second reference nox emission data is Y2, the target nox emission data set is [ Di1, di2, di3, di4, di5], then the second order emission limiting loss is: (Di 1-Y2) + (Di 2-Y2) + (Di 3-Y2) + (Di 4-Y2) + (Di 5-Y2).
Step 403, calculating data consumption loss corresponding to the target nox emission data set according to the initial data set and the reference data set corresponding to the target nox emission data set.
And referring to the data group, wherein the data group is a preset data group for measuring the size of the data of the initial data group. For example, assuming that the initial data set corresponding to the target nox emission data set is [ Ai1, ai2, ai3, ai4, ai5], the reference data set is [ Ac1, ac2, ac3, ac4, ac5], i.e., the values in the reference data set are different, the data consumption loss corresponding to the target nox emission data set is (Ai 1-Ac 1) + (Ai 2-Ac 2) + (Ai 3-Ac 3) + (Ai 4-Ac 4) + (Ai 5-Ac 5); for another example, the reference data set is [ Ac, ac ], that is, the values in the reference data set are the same, and the data consumption loss corresponding to the target nox removal data set is (Ai 1-Ac) + (Ai 2-Ac) + (Ai 3-Ac) + (Ai 4-Ac) + (Ai 5-Ac).
Step 404, calculating a balance degree corresponding to the target nox emission data set according to the target nox emission data set corresponding to the target system.
Assume that the target nox emission data set is [ Di1, di2, di3, di4, di5]Then, the target nox emission data set corresponds to a degree of balance of: ((Di 1-D) 2 +(Di2-D) 2 +(Di3-D) 2 +(Di4-D) 2 +(Di5-D) 2 ) And/5, wherein D is the average of Di1, di2, di3, di4, di 5.
And step 405, obtaining the group merit degree corresponding to the target nox emission data group by using the first-level emission limiting loss, the second-level emission limiting loss, the data elimination loss and the balance degree corresponding to the target nox emission data group.
Acquiring a first weight corresponding to the first-level limiting loss, a second weight corresponding to the second-level limiting loss, a third weight corresponding to the data consumption loss and a fourth weight corresponding to the balance degree; and carrying out weighted summation on the first-level limit loss, the second-level limit loss, the data elimination loss and the balance degree according to the first weight corresponding to the first-level limit loss, the second weight corresponding to the second-level limit loss, the third weight corresponding to the data consumption loss and the fourth weight corresponding to the balance degree, so as to obtain the group good evaluation degree corresponding to the target nitrogen oxide discharge data group.
For example, the first weight is a1, the second weight is a2, the third weight is a3, the fourth weight is a4, the first-level limiting loss is j1, the second-level limiting loss is j2, the data consumption loss is j3, and the balance is j4, the preliminary set of good scores is: a1×j1+a2×j2+a3×j3+a4×j4+a5×j5; and obtaining the group good score according to the preliminary group good score.
According to the embodiment, the four losses are combined to generate the group good evaluation degree, so that the accuracy of the group good evaluation degree is improved.
In one embodiment, the generating, in step 500, a plurality of initial data sets from the plurality of initial data sets for the next input to the nox prediction model includes:
and step 501, determining the combination probability corresponding to the initial data group according to the group good score corresponding to the initial data group.
The larger the group good score corresponding to the initial data group is, the larger the combination probability corresponding to the initial data group is determined; the smaller the group good score corresponding to the initial data group, the smaller the combination probability corresponding to the initial data group is determined. For example, there are a total of 4 initial data groups, and the group likelihoods corresponding to the 4 initial data groups are respectively: k1, K2, K3 and K4, and K1< K2< K3< K4, then, the corresponding combined probabilities of the 4 initial data sets are determined as R1, R2, R3 and R4, and R1< R2< R3< R4.
Step 502, generating a plurality of initial data sets input into the nitrogen oxide prediction model next time according to the corresponding combination probability of each initial data set.
The higher the probability of combination, the greater the number of initial data sets used to generate the next input nox predictive model; the lower the probability of combining, the fewer the number of initial data sets that are used to generate the next input nox predictive model. In this way, the excellent initial data set can be combined to obtain a plurality of initial data sets to be input into the nox prediction model next time, and the speed of obtaining the target initial data set can be increased by combining the excellent initial data sets.
In the above embodiment, a method for generating a plurality of initial data sets is provided, specifically, a plurality of initial data sets input into the nox prediction model next time are generated according to the group merit, it is understood that an initial data set with a high group merit will have a higher probability of being used to generate an initial data set input into the nox prediction model next time, so as to increase the speed of obtaining a target data set.
In one embodiment, the determining, in step 501, the combination probability corresponding to the initial data set according to the magnitude of the group goodness corresponding to the initial data set includes:
In step 501A, the group desirability corresponding to the plurality of initial data groups is added to obtain a total desirability.
For example, there are a total of 4 initial data groups, and the group likelihoods corresponding to the 4 initial data groups are respectively: k1 K2, K3 and K4, then the overall desirability is k1+k2+k3+k4.
And step 501B, dividing the group preference degree corresponding to the initial data group by the total preference degree to obtain the combination probability corresponding to the initial data group.
As another example, the combined probabilities corresponding to the 4 initial data sets are: r1=k1/(k1+k2+k3+k4), r2=k2/(k1+k2+k3+k4), r=k3/(k1+k2+k3+k4), r4=k4/(k1+k2+k3+k4).
The above embodiment provides a method for determining a combination probability, which can simply obtain the combination probability by solving the way that the group merit degree accounts for the total merit degree.
In one embodiment, generating a plurality of initial data sets for the next input to the nox prediction model according to the combined probability corresponding to each of the initial data sets in step 502 includes:
step 502A, combining the plurality of initial data sets two by two according to the magnitude of the combination probability corresponding to each initial data set, so as to obtain a plurality of initial data set pairs.
For example, there are 6 initial data sets, respectively U1, U2, U3, U4, U5, and U6, and the magnitude relation of the corresponding combination probabilities is: since the number of times of participation in the combination is larger as the combination probability is larger, the number of times of combination of the initial data groups corresponding to R6 > =r5=the number of times of combination of the initial data groups corresponding to R4 > =the number of times of combination of the initial data groups corresponding to R3 > =the number of times of combination of the initial data groups corresponding to R2 > =the number of times of combination of the initial data groups corresponding to R1, and thus, the number of times of combination of the initial data groups corresponding to 3 pairs of initial data groups (U6, U5), (U6, U4), (U5, U3) can be obtained, and of course, the number of times of combination of the initial data groups (U6, U5), (U6, U4), (U6, U3) can be obtained as long as the above-mentioned magnitude relation of the number of times of combination is satisfied.
Step 502B, intersecting two initial data sets in the plurality of initial data set pairs to obtain a plurality of intersecting data set pairs.
For example, the initial data group pair is (U6, U5), where U6 is [ a61, a62, a63, a64, a65, a66, a67, a68, a69, a610], U5 is [ a51, a52, a53, a54, a55, a56, a57, a58, a59, a510], each of the initial data groups U6 and U5 is converted into binary data, for example, the binary data of Aij is represented by Aij' (for example, assuming that the binary data a61 is 01010100) and then the binary data corresponding to the initial data group U6 can be obtained as: a61' a62' a63' a64' a65', the binary data corresponding to the initial data set U5 is: a51' a52' a53' a54' a55', a61' a62' a63' a64' a65' and a51' a52' a53' a54' a55' are represented in binary form as:
010101000101011001011100011101001101010001011100，
010101010111011101001100001100100100110101111101。
And crossing the two initial data sets to obtain a crossed data set pair. Fig. 4 provides an example of interleaving, and it can be seen that since the initial data sets have been represented as binary data, interleaving of two initial data sets can be achieved by interleaving the binary data, and interleaving of two initial data sets can be achieved by one interleaving, or multiple interleaving, as shown in fig. 4, resulting in interleaved data set pairs.
And step 502C, performing mutation on the two initial data sets in the crossed data set pair to obtain a plurality of initial data sets input into the nitrogen oxide prediction model next time.
Fig. 5 shows a mutation process for one crossover to obtain two initial data sets in a crossover data set pair, e.g., performing a mutation twice on 010101000101011001011100011101001101110001011100 to obtain 000100000101011001011100011101001101110001011100, and performing a mutation once on 010101010111011101001100001100100100010101111101 to obtain 000101010111011101001100001100100100010101111101.
In the above embodiment, the plurality of initial data sets to be input into the nox prediction model next are generated by combining the data pairs, the cross data pairs, and the variance.
In one embodiment, there is provided a data determining apparatus 600 in a thermal power plant system, including:
a generating module 601, configured to generate a plurality of initial data sets for an SCR reactor in a target system, where the initial data sets include a plurality of initial data, the initial data includes an ammonia vapor inlet flow rate, and the target system includes a thermal power plant system;
an obtaining module 602, configured to obtain reactor data corresponding to the SCR reactor;
an obtaining module 603, configured to input the reactor data corresponding to the SCR reactor and the plurality of initial data sets into a nitrogen oxide prediction model, to obtain a plurality of nitrogen oxide emission data sets corresponding to the target system, where the nitrogen oxide emission data sets include a plurality of nitrogen oxide emission data;
a calculating module 604, configured to calculate, according to a plurality of nox emission data sets corresponding to the target system, a group merit corresponding to each of the nox emission data sets, where the group merit is used to evaluate the merits of the initial data set;
and the circulation module 605 is configured to generate, according to the plurality of initial data sets, a plurality of initial data sets to be input into the nox prediction model next time if the maximum group preference degree of the plurality of group preference degrees does not meet the target condition, until the maximum group preference degree meets the target condition, and obtain the target data set.
In one embodiment, the computing module 604 is specifically configured to: calculating a first-stage emission limiting loss corresponding to a target nitrogen oxide emission data set according to the target nitrogen oxide emission data set corresponding to the target system and first reference nitrogen oxide emission data; calculating a second-level emission limiting loss corresponding to the target nitrogen oxide emission data set according to the target nitrogen oxide emission data set corresponding to the target system and second reference nitrogen oxide emission data; calculating data consumption loss corresponding to the target nitrogen oxide discharge data set according to the initial data set and the reference data set corresponding to the target nitrogen oxide discharge data set; calculating the corresponding balance degree of the target nitrogen oxide discharge data set according to the target nitrogen oxide discharge data set corresponding to the target system; and obtaining the group qualification degree corresponding to the target nitrogen oxide emission data group by using the primary limit emission loss, the secondary limit emission loss, the data elimination loss and the balance degree corresponding to the target nitrogen oxide emission data group.
In one embodiment, the circulation module 605 is specifically configured to: determining the combination probability corresponding to the initial data set according to the group qualification degree corresponding to the initial data set; and generating a plurality of initial data sets which are input into the nitrogen oxide prediction model next time according to the corresponding combination probability of each initial data set.
In one embodiment, the circulation module 605 is specifically configured to: adding the group good scores corresponding to the plurality of initial data groups to obtain a total good score; dividing the group preference degree corresponding to the initial data group by the total preference degree to obtain the combination probability corresponding to the initial data group.
In one embodiment, the circulation module 605 is specifically configured to: according to the combination probability corresponding to each initial data group, combining the plurality of initial data groups in pairs to obtain a plurality of initial data group pairs; crossing the two initial data sets in the plurality of initial data set pairs to obtain a plurality of crossed data set pairs; and carrying out mutation on the two initial data sets in the crossed data set pair to obtain a plurality of initial data sets which are input into the nitrogen oxide prediction model next time.
In one embodiment, the reactor data includes operating condition data, time data, derivative data, and time delay data.
In one embodiment, a plurality of SCR reactors are disposed in the target system, and the nitrogen oxide prediction model includes a prediction neural network and a sequence-to-sequence model corresponding to each SCR reactor.
In one embodiment, as shown in fig. 7, a computer device is provided, which may be a terminal or a server in particular. The computer device comprises a processor, a memory and a network interface which are connected through a system bus, wherein the memory comprises a nonvolatile storage medium and an internal memory, the nonvolatile storage medium of the computer device stores an operating system and can also store a computer program, and the computer program can enable the processor to realize a data determination method in a thermal power plant system when being executed by the processor. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others. The internal memory may also store a computer program which, when executed by the processor, causes the processor to perform a method of determining data in a thermal power plant system. It will be appreciated by those skilled in the art that the structure shown in FIG. 7 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
The method for determining data in a thermal power plant system provided by the application can be implemented in the form of a computer program, and the computer program can be run on computer equipment shown in fig. 7. The memory of the computer device may store the individual program templates that form the data determination device in the thermal power plant system. Such as a generation module 601, an acquisition module 602, and an acquisition module 603.
A computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of:
generating a plurality of initial data sets for the SCR reactor in a target system, wherein the initial data sets comprise a plurality of initial data, the initial data comprise ammonia vapor inlet flow rate, and the target system comprises a thermal power plant system;
obtaining reactor data corresponding to the SCR reactor;
inputting the reactor data corresponding to the SCR reactor and the initial data sets into a nitrogen oxide prediction model to obtain a plurality of nitrogen oxide discharge data sets corresponding to the target system, wherein the nitrogen oxide discharge data sets comprise a plurality of nitrogen oxide discharge data;
Calculating a group qualification degree corresponding to each nitrogen oxide emission data set according to a plurality of nitrogen oxide emission data sets corresponding to the target system, wherein the group qualification degree is used for evaluating the merits of the initial data set;
and if the maximum group good evaluation degree in the plurality of group good evaluation degrees does not meet the target condition, generating a plurality of initial data sets which are input into the nitrogen oxide prediction model next time according to the plurality of initial data sets, and obtaining a target data set until the maximum group good evaluation degree meets the target condition.
In one embodiment, a computer readable storage medium is provided, storing a computer program which, when executed by a processor, causes the processor to perform the steps of:
generating a plurality of initial data sets for the SCR reactor in a target system, wherein the initial data sets comprise a plurality of initial data, the initial data comprise ammonia vapor inlet flow rate, and the target system comprises a thermal power plant system;
obtaining reactor data corresponding to the SCR reactor;
inputting the reactor data corresponding to the SCR reactor and the initial data sets into a nitrogen oxide prediction model to obtain a plurality of nitrogen oxide discharge data sets corresponding to the target system, wherein the nitrogen oxide discharge data sets comprise a plurality of nitrogen oxide discharge data;
Calculating a group qualification degree corresponding to each nitrogen oxide emission data set according to a plurality of nitrogen oxide emission data sets corresponding to the target system, wherein the group qualification degree is used for evaluating the merits of the initial data set;
and if the maximum group good evaluation degree in the plurality of group good evaluation degrees does not meet the target condition, generating a plurality of initial data sets which are input into the nitrogen oxide prediction model next time according to the plurality of initial data sets, and obtaining a target data set until the maximum group good evaluation degree meets the target condition.
It should be noted that the above method for determining data in a thermal power plant system, the device for determining data in a thermal power plant system, the computer device, and the computer readable storage medium belong to one general inventive concept, and the content in the embodiments of the method for determining data in a thermal power plant system, the device for determining data in a thermal power plant system, the computer device, and the computer readable storage medium may be mutually applicable.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form. Further, the units described as separate units may or may not be physically separate, and units displayed as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Furthermore, functional modules in various embodiments of the present application may be integrated together to form a single portion, or each module may exist alone, or two or more modules may be integrated to form a single portion. In this document, 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. The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and variations will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims (9)

1. A method for determining data in a thermal power plant system, comprising:
generating a plurality of initial data sets for the SCR reactor in a target system, wherein the initial data sets comprise a plurality of initial data, the initial data comprise ammonia vapor inlet flow rate, and the target system comprises a thermal power plant system;
obtaining reactor data corresponding to the SCR reactor;
inputting the reactor data corresponding to the SCR reactor and the initial data sets into a nitrogen oxide prediction model to obtain a plurality of nitrogen oxide discharge data sets corresponding to the target system, wherein the nitrogen oxide discharge data sets comprise a plurality of nitrogen oxide discharge data;
calculating a group qualification degree corresponding to each nitrogen oxide emission data set according to a plurality of nitrogen oxide emission data sets corresponding to the target system, wherein the group qualification degree is used for evaluating the merits of the initial data set;
if the maximum group good evaluation degree in the plurality of group good evaluation degrees does not meet the target condition, generating a plurality of initial data sets which are input into the nitrogen oxide prediction model next time according to the plurality of initial data sets until the maximum group good evaluation degree meets the target condition, and obtaining a target data set;
The calculating the group merit degree corresponding to each nox emission data set according to the nox emission data sets corresponding to the target system includes:
calculating a first-stage emission limiting loss corresponding to a target nitrogen oxide emission data set according to the target nitrogen oxide emission data set corresponding to the target system and first reference nitrogen oxide emission data;
calculating a second-level emission limiting loss corresponding to the target nitrogen oxide emission data set according to the target nitrogen oxide emission data set corresponding to the target system and second reference nitrogen oxide emission data;
calculating data consumption loss corresponding to the target nitrogen oxide discharge data set according to the initial data set and the reference data set corresponding to the target nitrogen oxide discharge data set;
calculating the corresponding balance degree of the target nitrogen oxide discharge data set according to the target nitrogen oxide discharge data set corresponding to the target system;
and obtaining the group qualification degree corresponding to the target nitrogen oxide emission data group by using the primary limit emission loss, the secondary limit emission loss, the data elimination loss and the balance degree corresponding to the target nitrogen oxide emission data group.
2. The method of claim 1, wherein generating a plurality of initial data sets from the plurality of initial data sets for a next input to the nox predictive model comprises:
Determining the combination probability corresponding to the initial data set according to the group qualification degree corresponding to the initial data set;
and generating a plurality of initial data sets which are input into the nitrogen oxide prediction model next time according to the corresponding combination probability of each initial data set.
3. The method of claim 2, wherein the determining the corresponding combined probability of the initial data set according to the magnitude of the group goodness corresponding to the initial data set comprises:
adding the group good scores corresponding to the plurality of initial data groups to obtain a total good score;
dividing the group preference degree corresponding to the initial data group by the total preference degree to obtain the combination probability corresponding to the initial data group.
4. The method of claim 2, wherein the generating a plurality of initial data sets for the next input to the nox predictive model based on the combined probabilities corresponding to each of the initial data sets comprises:
according to the combination probability corresponding to each initial data group, combining the plurality of initial data groups in pairs to obtain a plurality of initial data group pairs;
crossing the two initial data sets in the plurality of initial data set pairs to obtain a plurality of crossed data set pairs;
And carrying out mutation on the two initial data sets in the crossed data set pair to obtain a plurality of initial data sets which are input into the nitrogen oxide prediction model next time.
5. The method of claim 1, wherein the reactor data comprises operating condition data, time data, derivative data, and time delay data.
6. The method of claim 5, wherein a plurality of SCR reactors are disposed in the target system, and the nitrogen oxide prediction model includes a prediction neural network and a sequence-to-sequence model corresponding to each of the SCR reactors.
7. A data determining apparatus in a thermal power plant system, comprising:
the generation module is used for generating a plurality of initial data sets for the SCR reactor in a target system, wherein the initial data sets comprise a plurality of initial data, the initial data comprise ammonia vapor inlet flow rates, and the target system comprises a thermal power plant system;
the acquisition module is used for acquiring the reactor data corresponding to the SCR reactor;
the obtaining module is used for inputting the reactor data corresponding to the SCR reactor and the initial data sets into a nitrogen oxide prediction model to obtain a plurality of nitrogen oxide discharge data sets corresponding to the target system, wherein the nitrogen oxide discharge data sets comprise a plurality of nitrogen oxide discharge data;
The calculating module is used for calculating the group qualification degree corresponding to each nitrogen oxide emission data set according to a plurality of nitrogen oxide emission data sets corresponding to the target system, wherein the group qualification degree is used for evaluating the merits of the initial data sets;
the calculation module is specifically configured to calculate a first-stage emission limiting loss corresponding to the target nox emission data set according to the target nox emission data set corresponding to the target system and the first reference nox emission data; calculating a second-level emission limiting loss corresponding to the target nitrogen oxide emission data set according to the target nitrogen oxide emission data set corresponding to the target system and second reference nitrogen oxide emission data; calculating data consumption loss corresponding to the target nitrogen oxide discharge data set according to the initial data set and the reference data set corresponding to the target nitrogen oxide discharge data set; calculating the corresponding balance degree of the target nitrogen oxide discharge data set according to the target nitrogen oxide discharge data set corresponding to the target system; obtaining the group acceptance degree corresponding to the target nitrogen oxide emission data group by using the primary limit emission loss, the secondary limit emission loss, the data elimination loss and the balance degree corresponding to the target nitrogen oxide emission data group;
And the circulation module is used for generating a plurality of initial data sets which are input into the nitrogen oxide prediction model next according to the plurality of initial data sets if the maximum group good evaluation degree in the plurality of group good evaluation degrees does not meet the target condition, and obtaining the target data sets until the maximum group good evaluation degree meets the target condition.
8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the data determination method in a thermal power plant system according to any one of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein computer program instructions which, when read and run by a processor, perform the steps of the data determination method in a thermal power plant system according to any one of claims 1 to 6.
CN202110907440.5A 2021-08-09 2021-08-09 Method, device, equipment and storage medium for determining data in thermal power plant system Active CN113611375B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110907440.5A CN113611375B (en) 2021-08-09 2021-08-09 Method, device, equipment and storage medium for determining data in thermal power plant system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110907440.5A CN113611375B (en) 2021-08-09 2021-08-09 Method, device, equipment and storage medium for determining data in thermal power plant system

Publications (2)

Publication Number Publication Date
CN113611375A CN113611375A (en) 2021-11-05
CN113611375B true CN113611375B (en) 2023-10-10

Family

ID=78307603

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110907440.5A Active CN113611375B (en) 2021-08-09 2021-08-09 Method, device, equipment and storage medium for determining data in thermal power plant system

Country Status (1)

Country Link
CN (1) CN113611375B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104880536A (en) * 2015-03-30 2015-09-02 北京京能电力股份有限公司石景山热电厂 Multi-point-location nitrogen oxide continuous monitoring device and continuous monitoring method for SCR reactors
CN105224730A (en) * 2015-09-17 2016-01-06 西南林业大学 The original NO of a kind of high pressure common rail electric-controlled diesel engine 2forecasting of discharged quantity method
CN211042859U (en) * 2019-11-14 2020-07-17 上海明华电力科技有限公司 Flue gas grid sampling monitoring device in inverted trapezoidal flue behind denitration reactor
CN111832222A (en) * 2020-06-28 2020-10-27 成都佳华物链云科技有限公司 Pollutant concentration prediction model training method, prediction method and device
CN111897373A (en) * 2020-08-05 2020-11-06 海南创实科技有限公司 Model prediction-based ammonia injection flow adjusting method for SCR denitration device
CN111921377A (en) * 2020-09-25 2020-11-13 大唐环境产业集团股份有限公司 SCR denitration ammonia injection control method and system based on mechanism and data driving
CN111931426A (en) * 2020-09-25 2020-11-13 大唐环境产业集团股份有限公司 Method and equipment for determining influence factors of concentration of nitrogen oxides at inlet of SCR (Selective catalytic reduction) reactor
CN112085277A (en) * 2020-09-10 2020-12-15 南京工业大学 SCR denitration system prediction model optimization method based on machine learning
CN113009890A (en) * 2021-01-25 2021-06-22 南京工业大学 Thermal power plant SCR flue gas denitration control system optimization control method based on BMO-LSSVM

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7634417B2 (en) * 2004-08-27 2009-12-15 Alstom Technology Ltd. Cost based control of air pollution control
US20060047607A1 (en) * 2004-08-27 2006-03-02 Boyden Scott A Maximizing profit and minimizing losses in controlling air pollution

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104880536A (en) * 2015-03-30 2015-09-02 北京京能电力股份有限公司石景山热电厂 Multi-point-location nitrogen oxide continuous monitoring device and continuous monitoring method for SCR reactors
CN105224730A (en) * 2015-09-17 2016-01-06 西南林业大学 The original NO of a kind of high pressure common rail electric-controlled diesel engine 2forecasting of discharged quantity method
CN211042859U (en) * 2019-11-14 2020-07-17 上海明华电力科技有限公司 Flue gas grid sampling monitoring device in inverted trapezoidal flue behind denitration reactor
CN111832222A (en) * 2020-06-28 2020-10-27 成都佳华物链云科技有限公司 Pollutant concentration prediction model training method, prediction method and device
CN111897373A (en) * 2020-08-05 2020-11-06 海南创实科技有限公司 Model prediction-based ammonia injection flow adjusting method for SCR denitration device
CN112085277A (en) * 2020-09-10 2020-12-15 南京工业大学 SCR denitration system prediction model optimization method based on machine learning
CN111921377A (en) * 2020-09-25 2020-11-13 大唐环境产业集团股份有限公司 SCR denitration ammonia injection control method and system based on mechanism and data driving
CN111931426A (en) * 2020-09-25 2020-11-13 大唐环境产业集团股份有限公司 Method and equipment for determining influence factors of concentration of nitrogen oxides at inlet of SCR (Selective catalytic reduction) reactor
CN113009890A (en) * 2021-01-25 2021-06-22 南京工业大学 Thermal power plant SCR flue gas denitration control system optimization control method based on BMO-LSSVM

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Dynamic modeling for NOx emission sequence prediction of SCR system outlet based on sequence to sequence long short-term memory network;Peiran Xie等;Energy;第190卷;第1-12页 *
基于SCR反应器NOx均匀度测试的脱硝系统超低排放改造;李瞳;环境工程学报;第12卷(第4期);第1112-1119页 *
火电厂SCR脱硝系统控制逻辑方案的优化;冯建荣等;硫酸工业(第10期);第26-28+33页 *

Also Published As

Publication number Publication date
CN113611375A (en) 2021-11-05

Similar Documents

Publication Publication Date Title
CN111628499B (en) Method for evaluating new energy consumption capability of power distribution network considering multiple risk factors
CN110798365A (en) Neural network-based traffic prediction method and device
CN112418284A (en) Control method and system for SCR denitration system of full-working-condition power station
CN110165698B (en) Wind power plant smooth grid-connection method for realizing prospective error asset conversion
CN113657668A (en) Power load prediction method and system based on LSTM network
CN113611375B (en) Method, device, equipment and storage medium for determining data in thermal power plant system
Tsai et al. An improved particle swarm optimization for economic dispatch with carbon tax considerations
CN112819279A (en) Planning evaluation method and system for expansion adaptability of distributed energy and power distribution network
Shimizu The relationship between pollution abatement costs and environmental regulation: Evidence from the Chinese industrial sector
CN116418001A (en) Reservoir group multi-energy complementary scheduling method and system for coping with uncertainty of new energy
CN102521510B (en) A kind of electrical network resists concentration power exfoliation ability appraisal procedure
CN116957391A (en) Multi-dimensional evaluation method and system for comprehensive energy operation and maintenance
CN116865318A (en) Power transmission network and energy storage joint planning method and system based on two-stage random optimization
CN107038489B (en) Multi-target unit combination optimization method based on improved NBI method
CN112003281B (en) Optimal configuration method, device and equipment for dynamic voltage restorer
CN115759775A (en) NCFI carbon emission responsibility allocation method and device considering fairness
CN113836819B (en) Bed temperature prediction method based on time sequence attention
Yang et al. Multi-period locally-facet-based MIP formulations for unit commitment problems
Mohammadi Neural network for univariate and multivariate nonlinearity tests
Li et al. Critical clearing time prediction of power system fault based on machine learning
CN112734158B (en) Thermoelectric load distribution method and device of generator set and electronic equipment
CN111799842B (en) Multi-stage power transmission network planning method and system considering flexibility of thermal power generating unit
CN113393059A (en) Method and device for adjusting output distribution of desulfurization system in circulating fluidized bed group
CN113723693A (en) Method for predicting equipment indexes by multi-factor fuzzy time series algorithm
CN111859807A (en) Initial pressure optimizing method, device, equipment and storage medium for steam turbine

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