CN114429795A - Method and device for predicting oxygen content of boiler flue gas - Google Patents
Method and device for predicting oxygen content of boiler flue gas Download PDFInfo
- Publication number
- CN114429795A CN114429795A CN202011179064.4A CN202011179064A CN114429795A CN 114429795 A CN114429795 A CN 114429795A CN 202011179064 A CN202011179064 A CN 202011179064A CN 114429795 A CN114429795 A CN 114429795A
- Authority
- CN
- China
- Prior art keywords
- boiler
- characteristic data
- model
- source
- 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
Images
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
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Computing Systems (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Regulation And Control Of Combustion (AREA)
Abstract
The invention discloses a method and a device for predicting oxygen content of boiler flue gas, a computer readable storage medium and electronic equipment, wherein the method comprises the following steps: determining a probability distribution model of the characteristic data of the source boiler and a probability distribution model of the characteristic data of the target boiler, wherein the characteristic data of the source boiler is non-shared data; determining the weight of the characteristic data of the source boiler according to the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler; determining a soft measurement model for predicting the oxygen content of the flue gas according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler and the historical oxygen content of the flue gas corresponding to the characteristic data of the source boiler; and predicting the oxygen content of the flue gas of the target boiler according to the soft measurement model for predicting the oxygen content of the flue gas. By the technical scheme provided by the invention, the characteristic data of the source boiler is migrated to the target boiler, so that data sharing is not needed between the source boiler and the target boiler, and the data safety is ensured.
Description
Technical Field
The invention relates to the technical field of energy, in particular to a method and a device for predicting oxygen content of boiler flue gas.
Background
The oxygen content of the flue gas is closely related to the combustion efficiency of the boiler, the exhaust emission and the like. When the oxygen content of the flue gas is too high, pollutants (NOx, SOx and the like) in the exhaust emission can be increased; and when the oxygen content of the flue gas is too low, the fuel combustion is insufficient, and the boiler efficiency is reduced. Therefore, the prediction of the oxygen content of the flue gas is necessary, which is helpful for improving the combustion quality and reducing the coal consumption, and simultaneously can help effectively control the air-coal ratio and improve the combustion efficiency of the boiler.
At present, for the prediction of a target boiler without a label, a mapping relation between characteristic data of the target boiler and the oxygen content of flue gas is established through data sharing between the target boiler and other boilers to obtain a flue gas oxygen content prediction model, and the flue gas oxygen content prediction model is used for realizing the prediction of the flue gas oxygen content of the target boiler.
However, the above technical solution needs to share data among a plurality of boilers in the model process, so that the data security among a plurality of boilers is low.
Disclosure of Invention
The invention provides a method and a device for predicting the oxygen content of boiler flue gas, a computer-readable storage medium and electronic equipment, aiming at the technical problems in the prior art, and the method and the device are used for migrating the characteristic data of a source boiler to a target boiler, so that data sharing is not needed between the source boiler and the target boiler, and the data security is ensured.
In a first aspect, the invention provides a method for predicting oxygen content of boiler flue gas, comprising the following steps:
acquiring characteristic data of a source boiler, historical flue gas oxygen content corresponding to the characteristic data of the source boiler and characteristic data of a target boiler, wherein the characteristic data of the source boiler is non-shared data;
determining a probability distribution model of the feature data of the source boiler and a probability distribution model of the feature data of the target boiler;
determining the weight of the characteristic data of the source boiler according to the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler;
determining a soft measurement model for predicting the oxygen content of the flue gas according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler and the historical oxygen content of the flue gas corresponding to the characteristic data of the source boiler;
and predicting the oxygen content of the flue gas of the target boiler according to the soft measurement model for predicting the oxygen content of the flue gas.
In a second aspect, the present invention provides a device for predicting oxygen content in boiler flue gas, comprising:
the data acquisition module is used for acquiring characteristic data of a source boiler, historical flue gas oxygen content corresponding to the characteristic data of the source boiler and characteristic data of a target boiler, wherein the characteristic data of the source boiler is non-shared data;
a probability distribution model determination module for determining a probability distribution model of the feature data of the source boiler and a probability distribution model of the feature data of the target boiler;
the weight determining module is used for determining the weight of the characteristic data of the source boiler according to the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler;
the soft measurement model determining module is used for determining a smoke oxygen content prediction soft measurement model according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler and the historical smoke oxygen content corresponding to the characteristic data of the source boiler;
and the prediction module is used for predicting the oxygen content of the flue gas of the target boiler according to the soft measurement model for predicting the oxygen content of the flue gas.
In a third aspect, the invention provides a computer-readable storage medium comprising executable instructions which, when executed by a processor of an electronic device, cause the processor to perform the method according to any one of the first aspect.
In a fourth aspect, the present invention provides an electronic device, comprising a processor and a memory storing execution instructions, wherein when the processor executes the execution instructions stored in the memory, the processor performs the method according to any one of the first aspect.
The invention provides a method, a device, a computer readable storage medium and an electronic device for predicting the oxygen content of boiler flue gas, the method comprises the steps of obtaining characteristic data of a source boiler, historical flue gas oxygen content corresponding to the characteristic data of the source boiler and characteristic data of a target boiler, determining a probability distribution model of the characteristic data of the source boiler and a probability distribution model of the characteristic data of the target boiler, determining the weight of the characteristic data of the source boiler according to the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler, determining a soft measurement model for predicting the oxygen content of the flue gas according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler and the historical flue gas oxygen content corresponding to the characteristic data of the source boiler, and then predicting the soft measurement model according to the oxygen content of the flue gas, and predicting the oxygen content of the flue gas of the target boiler. According to the technical scheme provided by the invention, the weight of the characteristic data of the source boiler is determined through the unshared characteristic data probability distribution model of the source boiler and the probability distribution model of the characteristic data of the target boiler, the data association between the source boiler and the target boiler is established, the characteristic data of the source boiler is migrated to the target boiler, and the source boiler and the target boiler do not need data sharing, so that the data safety is ensured.
Further effects of the above-mentioned unconventional preferred modes will be described below in conjunction with specific embodiments.
Drawings
In order to more clearly illustrate the embodiments or the prior art solutions of the present invention, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
FIG. 1 is a schematic flow chart illustrating a method for predicting oxygen content in flue gas of a boiler according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating another method for predicting oxygen content in flue gas of a boiler according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a device for predicting oxygen content in flue gas of a boiler according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail and completely with reference to the following embodiments and accompanying drawings. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the 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.
As shown in fig. 1, an embodiment of the present invention provides a method for predicting oxygen content in flue gas, which is applied to an edge node of a boiler to be predicted, and includes the following steps:
Specifically, the source boiler and the target boiler are both devices capable of generating flue gas, for example, the target boiler and the source boiler are both gas boilers, but information such as production units and device models may be different.
Specifically, the target boiler has a plurality of characteristic data, each of the characteristic data includes a plurality of characteristics respectively corresponding to a characteristic value of the target boiler, the plurality of characteristics are influence factors influencing the oxygen content of the flue gas of the target boiler, and the specific requirement is determined by combining an actual scene, for example, if the target boiler is a gas boiler, the plurality of characteristics include, but are not limited to, a gas flow rate, a gas temperature, a smoke exhaust temperature, a flue gas flow rate, a gas pressure, a flue gas humidity, a flue gas pressure, and the like.
Specifically, the characteristic data of the source boiler are multiple, each characteristic data of the source boiler comprises a plurality of characteristic values of which the characteristics respectively correspond to the source boiler, and the characteristics corresponding to the characteristic data of the target boiler are the same.
It should be noted that the characteristic data of the source boiler is unshared data, so that the data security of the characteristic data of the source boiler is ensured.
Optionally, a plurality of feature data of the target boiler are obtained through the edge node corresponding to the target boiler. Wherein, the edge node of the target boiler can be understood as the node which is closest to the target boiler and can perform data processing and data interaction. The node includes, but is not limited to, any one or more of an edge server, an edge gateway, and an edge controller.
Optionally, a plurality of feature data of the source boiler are obtained through corresponding edge nodes of the source boiler. Wherein, the edge node of the source boiler can be understood as the node which is closest to the source boiler and can perform data processing and data interaction. The node includes, but is not limited to, any one or more of an edge server, an edge gateway, and an edge controller. Correspondingly, if the feature data of the source boiler is unshared data, it is indicated that the feature data of the source boiler does not appear in the edge node corresponding to the source boiler.
Specifically, the flue gas oxygen content refers to the content of oxygen in the flue gas discharged after the fuel is combusted.
And 102, determining a probability distribution model of the characteristic data of the source boiler and a probability distribution model of the characteristic data of the target boiler.
Specifically, the feature data of the target boiler obeys continuous probability distribution, the continuous probability distribution model may be a normal distribution model or an exponential distribution model, which is not limited in the embodiment of the present invention, and preferably, the probability distribution model of the feature data of the target boiler is a mixed gaussian model formed by mixing a plurality of gaussian distribution models, where the gaussian model is also called a normal distribution model.
Specifically, the probability distribution model of the feature data of the source boiler and the probability distribution model of the feature data of the target boiler are both mixed gaussian models, and may be other probability distribution models, which need to be determined by combining with the actual situation, and this is not limited specifically here.
In one embodiment of the present invention, the determining a probability distribution model of the feature data of the source boiler comprises:
and calculating the data distribution of the characteristic data of the source boiler according to the parameter model, and determining the parameter model with the determined model parameters as a probability distribution model of the characteristic data of the source boiler.
Specifically, the parametric model may be a gaussian mixture model or an exponential distribution model, and preferably, the parametric model is a gaussian mixture model.
Specifically, the probability distribution model of the feature data of the source boiler is obtained by substituting the feature data of the source boiler into a gaussian mixture model to calculate and determine model parameters, wherein the calculation method can be an EM algorithm, and then determining the gaussian mixture model of the determined model parameters as the probability distribution model of the feature data of the source boiler.
In an embodiment of the present invention, the determining a probability distribution model of the feature data of the target boiler includes:
and calculating the data distribution of the characteristic data of the target boiler according to the Gaussian mixture model, and determining the Gaussian mixture model with the determined model parameters as a probability distribution model of the characteristic data of the target boiler.
Specifically, the probability distribution model of the feature data of the target boiler is obtained by substituting the feature data of the target boiler into a gaussian mixture model to calculate and determine model parameters, wherein the calculation method can be an EM algorithm, and then determining the gaussian mixture model of the determined model parameters as the probability distribution model of the feature data of the target boiler.
And 103, determining the weight of the characteristic data of the source boiler according to the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler.
In the embodiment, the weight of the feature data of the source boiler is determined by using the probability distribution model of the feature data of the source boiler and the probability distribution model of the feature data of the target boiler, and the data association between the source boiler and the target boiler is established, so that the feature data of the source boiler is migrated to the target boiler. Here, the characteristic data of the source boiler is unshared data, in other words, the source boiler does not directly acquire the characteristic data of the target boiler, that is, there is no data sharing between the target boiler and the source boiler, thereby ensuring data security.
In one embodiment, the weight of the source boiler's signature data is determined by specifically:
determining the distribution probability of the feature data of the source boiler relative to the source boiler according to the probability distribution model of the feature data of the source boiler;
determining the distribution probability of the feature data of the source boiler relative to the target boiler according to the probability distribution model of the feature data of the target boiler;
determining an approximate value of the distribution probability of the feature data of the source boiler with respect to the target boiler and the distribution probability with respect to the source boiler as a weight of the feature data of the source boiler.
In the embodiment, the weight of the feature data of the source boiler is determined by the ratio of the distribution probability of the feature data of the source boiler relative to the target boiler to the probability of the distribution of the feature data of the source boiler relative to the target boiler, and the data association between the source boiler and the target boiler is established, so that the feature data of the source boiler is migrated to the target boiler, and meanwhile, the feature data of the source boiler and the feature data of the target boiler are not required to be shared, and the data safety is ensured.
Specifically, the feature data of the source boiler is substituted into the probability distribution model of the feature data of the source boiler, and the output value of the probability distribution model of the feature data of the source boiler is the distribution probability of the feature data of the source boiler relative to the source boiler.
Specifically, the feature data of the source boiler is substituted into the probability distribution model of the feature data of the target boiler, and the value output by the probability distribution model of the feature data of the target boiler is the distribution probability of the feature data of the source boiler relative to the target boiler.
And step 104, determining a smoke oxygen content prediction soft measurement model according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler and the historical smoke oxygen content corresponding to the characteristic data of the source boiler.
In the embodiment, the relationship between the flue gas oxygen contents of the target boiler and the boiler is established through the characteristic data of the source boiler, the weight of the characteristic data of the source boiler and the historical flue gas content corresponding to the characteristic data of the source boiler, and the flue gas oxygen content prediction soft measurement model is determined, so that the characteristic data of the source boiler and the characteristic data of the target boiler do not need to be shared, and the data safety is ensured.
In an embodiment of the present invention, determining a soft measurement model for predicting an oxygen content in flue gas according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler, and a historical oxygen content in flue gas corresponding to the characteristic data of the source boiler includes:
and performing model training on a preset model according to the weight of the characteristic data of the source boiler relative to the target boiler and the historical smoke content corresponding to the characteristic data of the source boiler, determining the trained model as a smoke oxygen content prediction soft measurement model, wherein the smoke oxygen content prediction soft measurement model indicates the relationship between the characteristic data of the target boiler and the smoke oxygen content.
Specifically, the edge node corresponding to the source boiler trains the preset model based on the feature data of the source boiler, the weight of the feature data of the source boiler corresponding to the target boiler and the historical flue gas oxygen content corresponding to the feature data of the source boiler, and determines the trained preset model as a flue gas oxygen content prediction soft measurement model, and the trained flue gas oxygen content prediction soft measurement model takes the weight of the feature data of the source boiler relative to the target boiler into consideration, so that the relationship between the feature data of the target boiler and the flue gas oxygen content can be indicated.
Specifically, the characteristic data of the source boiler and the characteristic data of the source boiler correspond to the weight of the target boiler, the characteristic data of the source boiler can be migrated to the target boiler, and subsequently, the parameters of the preset model are adjusted through the weights corresponding to the characteristic data of the source boiler respectively, so that the adjusted parameters of the preset model can reflect the relationship between the characteristic data of the target boiler and the oxygen content of flue gas, data sharing between the source boiler and the target boiler is not involved, and data safety is ensured.
Specifically, the preset model may be any one of models in the prior art, such as a neural network model or a regression model, and is not limited herein.
Specifically, the preset model may be iterated by:
a1, performing model training according to the multiple characteristic data of the source boiler, the historical flue gas oxygen contents corresponding to the multiple characteristic data of the source boiler respectively and the weights corresponding to the multiple characteristic data of the source boiler respectively to determine a preset model;
a2, judging whether the model error of the preset model meets the iteration condition, if so, determining the preset model as the final model and sending the final model to the edge node of the target boiler, and if not, executing A3;
a3, sending model parameters of a preset model to edge nodes of a target boiler;
a4, receiving updated model parameters sent by edge nodes of a target boiler, adjusting the updated model parameters according to the multiple characteristic data of a source boiler, the historical flue gas oxygen content corresponding to the multiple characteristic data of the source boiler respectively and the weights corresponding to the multiple characteristic data of the source boiler respectively, so as to determine the adjusted model parameters, replacing the adjusted model parameters with the model parameters of a preset model, and executing A2.
The data of the target boiler and the data of the source boiler are distributed at different edge nodes in the Internet of things, and the data security problem can be caused when the data are shared for model training.
And 105, predicting the oxygen content of the flue gas of the target boiler according to the flue gas oxygen content prediction soft measurement model.
Specifically, the current characteristic data of the target boiler is collected and substituted into the flue gas oxygen content prediction, so that the flue gas oxygen content of the target boiler can be determined.
In order to better understand the data processing process between the edge node of the target boiler and the edge node of the source boiler, for example, assume that the edge node of the source boiler is set as A, the edge node of the target boiler is set as B, B sends the probability distribution model of the feature data of the target boiler to A, then determines the weight of the feature data of the source boiler by combining the probability distribution model of the feature data of the local source boiler A, then performs training of a regression model by using the feature data of the source boiler, the weight of the feature data of the source boiler and the historical flue gas oxygen content corresponding to the feature data of the source boiler to obtain a flue gas oxygen content prediction soft measurement model, sends the flue gas oxygen content prediction soft measurement model to B, and the B performs flue gas oxygen content prediction of the target boiler through the flue gas oxygen content prediction soft measurement model.
According to the technical scheme, the embodiment of the invention has at least the following effective effects: the method comprises the steps of determining the weight of the characteristic data of the source boiler through a probability distribution model of the characteristic data of the target boiler and a probability distribution model of the characteristic data of the source boiler, establishing data association between the source boiler and the target boiler, and migrating the characteristic data of the source boiler to the target boiler without sharing the characteristic data between the source boiler and the target boiler, so that the data safety is ensured.
Fig. 1 shows only a basic embodiment of the method of the present invention, and based on this, certain optimization and expansion can be performed, and other preferred embodiments of the method can also be obtained.
To more clearly illustrate the technical solution of the present invention, please refer to fig. 2, an embodiment of the present invention provides another method for predicting the oxygen content of the boiler flue gas, and the embodiment is further described with reference to specific application scenarios on the basis of the foregoing embodiment. In this embodiment, the method may specifically include the following steps:
Assuming that an edge node corresponding to a source boiler is A and an edge node corresponding to a target boiler is B, the A can acquire all feature data of the source boiler, and the B can acquire all feature data of the target boiler.
And A, calculating the data distribution of the characteristic data of the source boiler according to the Gaussian mixture model, thereby obtaining a probability distribution model of the characteristic data of the source boiler.
And B, calculating the probability distribution model of the characteristic data of the target boiler according to the Gaussian mixture model to obtain the probability distribution model of the characteristic data of the target boiler, and sending the probability distribution model of the characteristic data of the target source boiler to A.
It should be noted that the gaussian mixture model for calculating the data distribution of the feature data of the source boiler and the gaussian mixture model for calculating the data distribution of the feature data of the target boiler may be different, for example, the number of gaussian models included may be different.
And A receives the probability distribution model of the characteristic data of the target boiler sent by B, and simultaneously substitutes the characteristic data of the source boiler obtained by A into the probability distribution model of the characteristic data of the target boiler to obtain the distribution probability of the characteristic data of the source boiler relative to the target boiler.
And A, substituting the characteristic data of the source boiler into the probability distribution model of the characteristic data of the local source boiler to obtain the distribution probability of the characteristic data of the source boiler relative to the source boiler.
And 204, determining the probability ratio of the distribution probability of the characteristic data of the source boiler relative to the target boiler and the distribution probability relative to the source boiler as the weight of the characteristic data of the source boiler.
And A, determining the weight of the characteristic data of the source boiler by determining the probability ratio of the distribution probability of the characteristic data of the source boiler relative to the target boiler to the distribution probability of the characteristic data of the source boiler relative to the source boiler as the weight of the characteristic data of the source boiler, and thus establishing the data relation between the source boiler and the target boiler.
And A, carrying out preset model training according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler relative to the target boiler and the historical smoke oxygen content corresponding to the characteristic data of the source boiler, determining the trained preset model as a smoke oxygen content prediction soft measurement model, and sending the smoke oxygen content prediction soft measurement model to B.
And step 206, predicting the oxygen content of the flue gas of the target boiler according to the flue gas oxygen content prediction soft measurement model.
B, receiving the flue gas oxygen content prediction soft measurement model sent by A, and predicting the boiler flue gas oxygen content of the target boiler by using the flue gas oxygen content prediction soft measurement model.
According to the technical scheme, the beneficial effects of the embodiment are as follows: according to the probability distribution model of the feature data of the target boiler and the probability distribution model of the feature data of the source boiler, which are respectively arranged on two edge nodes in the Internet of things, the weight of the feature data of the source boiler is determined, data association between the source boiler and the target boiler is established, and the backup data of the source boiler is migrated to the target boiler, so that sharing of data between the nodes of the target boiler and the source boiler is realized, the edge nodes of the data between the target boiler and the source boiler in the Internet of things are not generated, and privacy of the data is guaranteed.
Referring to fig. 3, based on the same concept as the method for predicting the oxygen content in the flue gas of the boiler provided by the embodiment of the method of the present invention, the present invention implements a device for predicting the oxygen content in the flue gas of the boiler, including:
the data acquisition module 301 is configured to acquire feature data of a source boiler, a historical flue gas oxygen content corresponding to the feature data of the source boiler, and feature data of a target boiler, where the feature data of the source boiler is non-shared data;
a probability distribution model determining module 302, configured to determine a probability distribution model of the feature data of the target boiler and a probability distribution model of the feature data of the source boiler;
a weight determining module 303, configured to determine a weight of the feature data of the source boiler according to the probability distribution model of the feature data of the source boiler and the probability distribution model of the feature data of the target boiler;
a soft measurement model determining module 304, configured to determine a smoke oxygen content prediction soft measurement model according to the feature data of the source boiler, the weight of the feature data of the source boiler, and a historical smoke oxygen content corresponding to the feature data of the source boiler;
and the prediction module 305 is configured to predict the oxygen content of the flue gas of the target boiler according to the soft measurement model for predicting the oxygen content of the flue gas.
In an embodiment of the present invention, the weight determining module 303 includes: a first distribution probability determining unit, a second distribution probability determining unit and a weight determining unit; wherein the content of the first and second substances,
the first distribution probability determining unit is used for determining the distribution probability of the characteristic data of the source boiler relative to the source boiler according to the probability distribution model of the characteristic data of the source boiler;
the second distribution probability determining unit is used for determining the distribution probability of the feature data of the source boiler relative to the target boiler according to the probability distribution model of the feature data of the target boiler;
the weight determining unit is used for determining the ratio of the distribution probability of the characteristic data of the source boiler relative to the target boiler and the distribution probability relative to the source boiler as the weight of the characteristic data of the source boiler.
In an embodiment of the present invention, the probability distribution model determining module 302 includes: a first probability distribution model determining unit and a second probability distribution model determining unit; wherein the content of the first and second substances,
and the first probability distribution model determining unit is used for calculating the data distribution of the characteristic data of the source boiler according to the parameter model and determining the parameter model with determined model parameters as the probability distribution model of the characteristic data of the source boiler.
And the second probability distribution model determining unit is used for calculating the data distribution of the characteristic data of the target boiler according to the Gaussian mixture model and determining the Gaussian mixture model with determined model parameters as the probability distribution model of the characteristic data of the target boiler.
In one embodiment of the invention, the parametric model comprises a Gaussian mixture model.
In an embodiment of the present invention, the soft measurement model determining module 304 is configured to perform model training on a preset model according to the feature data of the source boiler, the weight of the feature data of the source boiler relative to the target boiler, and the historical flue gas content corresponding to the feature data of the source boiler, and determine the trained preset model as a flue gas oxygen content prediction soft measurement model, where the flue gas oxygen content prediction soft measurement model indicates a relationship between the feature data of the target boiler and the flue gas oxygen content.
In one embodiment of the invention, the predictive model comprises a neural network model or a regression model.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. On the hardware level, the electronic device includes a processor 401 and a memory 402 storing execution instructions, and optionally an internal bus 403 and a network interface 404. The Memory 402 may include a Memory 4021, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory 4022 (e.g., at least 1 disk Memory); the processor 401, the network interface 404, and the memory 402 may be connected to each other by an internal bus 403, and the internal bus 403 may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like; the internal bus 403 may be divided into an address bus, a data bus, a control bus, etc., which is indicated by only one double-headed arrow in fig. 4 for convenience of illustration, but does not indicate only one bus or one type of bus. Of course, the electronic device may also include hardware required for other services. When the processor 401 executes execution instructions stored by the memory 402, the processor 401 performs the method in any of the embodiments of the present invention and at least is used to perform the method as shown in fig. 1 or fig. 2.
In a possible implementation manner, the processor reads the corresponding execution instruction from the nonvolatile memory to the memory and then runs the corresponding execution instruction, and can also obtain the corresponding execution instruction from other equipment so as to form a prediction device of the oxygen content of the boiler flue gas on a logic level. The processor executes the execution instruction stored in the memory, so that the method for predicting the oxygen content of the boiler flue gas provided by any embodiment of the invention is realized through the executed execution instruction.
The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Embodiments of the present invention further provide a computer-readable storage medium, which includes an execution instruction, and when a processor of an electronic device executes the execution instruction, the processor executes a method provided in any one of the embodiments of the present invention. The electronic device may specifically be the electronic device shown in fig. 4; the execution instruction is a computer program corresponding to the prediction method of the oxygen content of the boiler flue gas.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
The multiple embodiments of the present invention are described in a progressive manner, and the same and similar parts among the multiple embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
It should also be noted that 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.
The above description is only an example of the present invention, and is not intended to limit the present invention. Various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (10)
1. A method for predicting the oxygen content of boiler flue gas is characterized by comprising the following steps:
acquiring characteristic data of a source boiler, historical flue gas oxygen content corresponding to the characteristic data of the source boiler and characteristic data of a target boiler, wherein the characteristic data of the source boiler is non-shared data;
determining a probability distribution model of the feature data of the source boiler and a probability distribution model of the feature data of the target boiler;
determining the weight of the characteristic data of the source boiler according to the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler;
determining a soft measurement model for predicting the oxygen content of the flue gas according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler and the historical oxygen content of the flue gas corresponding to the characteristic data of the source boiler;
and predicting the oxygen content of the flue gas of the target boiler according to the soft measurement model for predicting the oxygen content of the flue gas.
2. The method according to claim 1, wherein the weight of the characteristic data of the source boiler is determined from the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler;
determining the distribution probability of the feature data of the source boiler relative to the source boiler according to the probability distribution model of the feature data of the source boiler;
determining the distribution probability of the feature data of the source boiler relative to the target boiler according to the probability distribution model of the feature data of the target boiler;
and determining the ratio of the distribution probability of the characteristic data of the source boiler relative to the target boiler and the distribution probability relative to the source boiler as the weight of the characteristic data of the source boiler.
3. The method of claim 1, wherein determining the probability distribution model of the source boiler's signature data comprises:
and calculating the data distribution of the characteristic data of the source boiler according to the parameter model, and determining the parameter model with the determined model parameters as a probability distribution model of the characteristic data of the source boiler.
4. The method of claim 3, wherein the parametric model comprises a Gaussian mixture model.
5. The method of claim 1, wherein determining the probability distribution model of the signature data of the target boiler comprises:
and calculating the data distribution of the characteristic data of the target boiler according to the Gaussian mixture model, and determining the Gaussian mixture model with the determined model parameters as a probability distribution model of the characteristic data of the target boiler.
6. The method of claim 1, wherein determining a soft measurement model for flue gas oxygen content prediction according to the source boiler characteristic data, the weight of the source boiler characteristic data and the historical flue gas oxygen content corresponding to the source boiler characteristic data comprises:
and performing model training on a preset model according to the weight of the characteristic data of the source boiler relative to the target boiler and the historical smoke content corresponding to the characteristic data of the source boiler, determining the trained preset model as a smoke oxygen content prediction soft measurement model, wherein the smoke oxygen content prediction soft measurement model indicates the relationship between the characteristic data of the target boiler and the smoke oxygen content.
7. The method of claim 6, wherein the pre-set model comprises a neural network model or a regression model.
8. A prediction device of boiler flue gas oxygen content, characterized by comprising:
the data acquisition module is used for acquiring characteristic data of a source boiler, historical flue gas oxygen content corresponding to the characteristic data of the source boiler and characteristic data of a target boiler, wherein the characteristic data of the source boiler is non-shared data;
a probability distribution model determination module for determining a probability distribution model of the feature data of the source boiler and a probability distribution model of the feature data of the target boiler;
the weight determining module is used for determining the weight of the characteristic data of the source boiler according to the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler;
the soft measurement model determining module is used for determining a smoke oxygen content prediction soft measurement model according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler and the historical smoke oxygen content corresponding to the characteristic data of the source boiler;
and the prediction module is used for predicting the oxygen content of the flue gas of the target boiler according to the soft measurement model for predicting the oxygen content of the flue gas.
9. A readable medium comprising executable instructions which, when executed by a processor of an electronic device, cause the electronic device to perform the method of any of claims 1 to 7.
10. An electronic device comprising a processor and a memory storing execution instructions, the processor performing the method of any of claims 1-7 when the processor executes the execution instructions stored by the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011179064.4A CN114429795A (en) | 2020-10-29 | 2020-10-29 | Method and device for predicting oxygen content of boiler flue gas |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011179064.4A CN114429795A (en) | 2020-10-29 | 2020-10-29 | Method and device for predicting oxygen content of boiler flue gas |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114429795A true CN114429795A (en) | 2022-05-03 |
Family
ID=81309599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011179064.4A Pending CN114429795A (en) | 2020-10-29 | 2020-10-29 | Method and device for predicting oxygen content of boiler flue gas |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114429795A (en) |
-
2020
- 2020-10-29 CN CN202011179064.4A patent/CN114429795A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111414999B (en) | Method and device for monitoring running state of equipment | |
| CN111861464B (en) | Node consensus method and system for block chain | |
| US11151475B2 (en) | Method and device for generating a machine learning system and virtual sensor device | |
| JP7037066B2 (en) | Evaluation device, evaluation method and evaluation program | |
| CN115794393A (en) | Method, device, server and storage medium for executing business model | |
| CN111553529A (en) | Load prediction method and device, computer readable storage medium and electronic equipment | |
| CN114429795A (en) | Method and device for predicting oxygen content of boiler flue gas | |
| CN109740235B (en) | Method and device for determining coal saving amount of coal-fired boiler, readable medium and electronic equipment | |
| CN112733454B (en) | Equipment predictive maintenance method and device based on joint learning | |
| CN111625753B (en) | Method, device, equipment and storage medium for calculating energy parameters of direct combustion engine | |
| CN114254791A (en) | Method and device for predicting oxygen content of flue gas | |
| CN114254792A (en) | Method and device for predicting oxygen content of flue gas | |
| CN109858119B (en) | Dynamic energy efficiency modeling method and device, readable medium and electronic equipment | |
| CN114593920B (en) | Method and device for measuring oxygen content of exhaust gas of gas combustion engine and readable storage medium | |
| CN108881272B (en) | Attack surface modeling method and device suitable for redundant information system | |
| CN114298361A (en) | Equipment state information prediction method and device | |
| CN114580257A (en) | Method and device for measuring oxygen content in flue gas of gas internal combustion engine and readable storage medium | |
| JP5029584B2 (en) | Development support equipment | |
| CN111611167A (en) | Embedded software testing method and system based on DSP | |
| CN114577481B (en) | Pollution index monitoring method and device for gas internal combustion engine | |
| Jean et al. | Trustworthy estimation and control of engine knocking level for transient operation | |
| CN116187094B (en) | Quality work prediction system based on real-time analysis of working conditions | |
| CN112883631B (en) | Method and device for predicting oxygen content of exhaust gas of gas turbine | |
| CN113821481B (en) | Method and device for generating test data source and server | |
| CN111553044A (en) | Method and device for determining design parameters of biogas burner in biogas boiler |
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 |