Flue gas oxygen content prediction method, device and electronic equipment based on sample migration

Abstract

The present disclosure relates to the technical field of boiler flue gas oxygen content prediction, and provides a flue gas oxygen content prediction method, device, and electronic device based on sample migration. The method includes: obtaining a first sample data set of a source domain boiler and a second sample data set of a target boiler; based on the sample migration between the first sample data set and the second sample data set, determining the sample weight data of the source domain boiler with respect to the target boiler; using the sample weight data and the first sample data set to learn the flue gas oxygen content prediction model of the target boiler to obtain a target prediction model; predicting the data of the target boiler based on the target prediction model to obtain the flue gas oxygen content value of the target boiler. The present disclosure realizes the migration between the source domain boiler data and the target boiler data, so that the data distribution of different boilers is as similar as possible, thereby improving the prediction accuracy of the target prediction model for the flue gas oxygen content of the target boiler.

Description

Technical Field

[0001] The present disclosure relates to the technical field of boiler flue gas oxygen content prediction, and in particular to a flue gas oxygen content prediction method, device, and electronic equipment based on sample migration. Background Art

[0002] Thermal efficiency is a key metric for measuring gas-fired boilers. In practice, this is typically achieved by controlling the oxygen content of boiler flue gas to the optimal design value to maximize thermal efficiency under varying operating conditions. Zirconia-based instruments are commonly used to measure flue gas oxygen content, but these instruments are expensive to measure and maintain. In the distributed energy sector, to save costs, small gas-fired boilers often rotate instruments across different boilers to collect data. However, due to the short installation time of each boiler, insufficient data can be collected to train an effective model. Furthermore, the data distribution varies from boiler to boiler, significantly impacting data prediction accuracy. Consequently, models trained on source-domain boiler data may have low prediction accuracy on target-domain data. Therefore, improving the accuracy of boiler flue gas oxygen prediction is a current technical challenge in boiler management. Summary of the Invention

[0003] In view of this, the embodiments of the present disclosure provide a method, device and electronic device for predicting the oxygen content in flue gas based on sample migration to solve the problem in the prior art of how to further improve the prediction accuracy of the oxygen content in boiler flue gas.

[0004] In a first aspect of an embodiment of the present disclosure, a method for predicting the oxygen content in flue gas based on sample migration is provided, comprising: obtaining a first sample data set of a source boiler and a second sample data set of a target boiler; determining sample weight data of the source boiler with respect to the target boiler based on sample migration between the first sample data set and the second sample data set; learning a flue gas oxygen content prediction model of the target boiler using the sample weight data and the first sample data set to obtain a target prediction model; and predicting the data of the target boiler based on the target prediction model to obtain a flue gas oxygen content value of the target boiler.

[0005] According to a second aspect of an embodiment of the present disclosure, a device for predicting the oxygen content in flue gas based on sample migration is provided, comprising: an acquisition module configured to acquire a first sample data set of a source domain boiler and a second sample data set of a target boiler; a migration module configured to determine the sample weight data of the source domain boiler with respect to the target boiler based on the sample migration between the first sample data set and the second sample data set; a training module configured to learn a flue gas oxygen content prediction model of the target boiler using the sample weight data and the first sample data set to obtain a target prediction model; and a prediction module configured to predict the data of the target boiler based on the target prediction model to obtain the flue gas oxygen content value of the target boiler.

[0006] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0007] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above method are implemented.

[0008] Compared with the prior art, the beneficial effects of the disclosed embodiment are as follows: by obtaining a first sample data set of a source boiler and a second sample data set of a target boiler; based on the sample migration between the first sample data set and the second sample data set, determining the sample weight data of the source boiler with respect to the target boiler; using the sample weight data and the first sample data set to learn the flue gas oxygen content prediction model of the target boiler to obtain a target prediction model; predicting the data of the target boiler based on the target prediction model to obtain the flue gas oxygen content value of the target boiler, realizing the migration between the source domain boiler data and the target boiler data, making the data distribution of different boilers as similar as possible, thereby improving the prediction accuracy of the target prediction model for the flue gas oxygen content of the target boiler. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0010] Figure 1 is a schematic diagram of an application scenario of an embodiment of the present disclosure;

[0011] Figure 2 1 is a flow chart of a method for predicting flue gas oxygen content based on sample migration provided by an embodiment of the present disclosure;

[0012] Figure 3 is a flow chart of another method for predicting flue gas oxygen content based on sample migration provided by an embodiment of the present disclosure;

[0013] Figure 4 Schematic diagram of the structure of a device for predicting oxygen content in flue gas based on sample migration provided by an embodiment of the present disclosure;

[0014] Figure 5 It is a structural diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0015] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present disclosure. However, it will be apparent to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present disclosure with unnecessary detail.

[0016] A method and device for predicting oxygen content in flue gas based on sample migration according to an embodiment of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0017] Figure 1 Schematic diagram of an application scenario of an embodiment of the present disclosure. The application scenario may include a source terminal 1, a target terminal 2, a server 3, and a network 4. The scenario may be an energy network, for example, a boiler network.

[0018] The source domain terminal 1 can obtain data of one type of boiler, and the target terminal 2 can obtain data of another type of boiler, that is, the source domain terminal 1 and the target terminal 2 can be data nodes, boiler control terminals or terminal devices of different boilers, respectively. For example, when the source domain terminal 1 and the target terminal 2 are data nodes, the data node can be hardware or software. When the data node is hardware, it can be various electronic devices that support communication with the server 3, including but not limited to industrial computers, tablet computers, laptop computers and desktop computers; when the data node is software, it can be installed in the above electronic devices. The data node can be implemented as multiple software or software modules, or as a single software or software module, and the embodiments of the present disclosure are not limited to this. Furthermore, various applications can be installed on the data node, such as data processing applications, data communication tools, model training platform software, boiler load forecasting applications, etc.

[0019] Server 3 can be a server that provides various services, such as a backend server that receives requests sent by source domain terminal 1 and target terminal 2 with which it establishes a communication connection. This backend server can receive and analyze the requests sent by the terminal devices, and generate processing results. Server 3 can be a single server, a server cluster consisting of multiple servers, or a cloud computing service center, all of which are not limited in the present embodiment.

[0020] It should be noted that the server 3 can be either hardware or software. When the server 3 is hardware, it can be various electronic devices that provide various services to the source domain terminal 1 and the target terminal 2. When the server 3 is software, it can be multiple software or software modules that provide various services to the source domain terminal 1 and the target terminal 2, or it can be a single software or software module that provides various services to the source domain terminal 1 and the target terminal 2. This embodiment of the present disclosure is not limited to this.

[0021] Network 4 can be a wired network connected by coaxial cable, twisted pair and optical fiber, or it can be a wireless network that can interconnect various communication devices without wiring, such as carrier, WiFi, near field communication (NFC), etc., which is not limited in the embodiments of the present disclosure.

[0022] The source domain terminal 1 and the target terminal 2 establish a communication connection with the server 3 via the network 4 to send information to the server 3 and receive information sent by the server 3. Specifically, the source domain terminal 1 sends its own first sample data set to the server 3, and the target terminal 2 also sends its own second sample data set to the server 3. The server 3 performs a sample migration operation on the first sample data set and the second sample data set to obtain the sample weight data of the source domain terminal 1 with respect to the target terminal 2, so that the data distribution of different terminals is as similar as possible. The server 3 uses the sample weight data and the first sample data set to perform model training to obtain a target prediction model for the flue gas oxygen content of the target terminal 2, and sends the target prediction model to the target terminal 2 to predict the flue gas oxygen content of the target terminal 2, thereby improving the prediction accuracy of the target prediction model for the flue gas oxygen content of the target terminal 2.

[0023] It should be noted that the specific types, quantities and combinations of the source domain terminal 1, the target terminal device 2, the server 3 and the network 4 can be adjusted according to the actual needs of the application scenario, and the embodiments of the present disclosure do not limit this.

[0024] Figure 2 This is a flow chart of a method for predicting flue gas oxygen content based on sample migration provided by an embodiment of the present disclosure. Figure 2 The flue gas oxygen content prediction method based on sample migration can be obtained by Figure 1 The target terminal or server executes. Figure 2 As shown, the flue gas oxygen content prediction method based on sample migration includes:

[0025] S201, obtaining a first sample data set of a source domain boiler and a second sample data set of a target boiler;

[0026] S202, determining sample weight data of the source domain boiler with respect to the target boiler based on sample migration between the first sample data set and the second sample data set;

[0027] S203, using the sample weight data and the first sample data set to learn a flue gas oxygen content prediction model of a target boiler to obtain a target prediction model;

[0028] S204 , predicting the data of the target boiler based on the target prediction model to obtain the flue gas oxygen content value of the target boiler.

[0029] Specifically, the source boiler and the target boiler are different boilers. For example, they are different types of boilers, or they have different processes or technical indicators. In practical applications, various sensors can be installed on the source and target boilers to measure various boiler parameters, and this parameter data can be used as a sample dataset.

[0030] Among them, the first sample data set can be different types of parameter data of the boiler collected by the source domain boiler. These parameter data may include steam boiler flue gas temperature, economizer outlet temperature, flue gas flow instantaneous value, steam boiler gas temperature, steam boiler flue gas standard flow, steam boiler natural gas inlet pressure, steam boiler flue gas flow rate, steam boiler condenser inlet flue gas temperature, steam boiler exhaust temperature, steam boiler flue gas pressure, steam boiler condenser inlet pressure, steam boiler main steam instantaneous flow, steam boiler operating status and steam boiler natural gas inlet instantaneous flow, etc., and the correspondence between these parameter data on the source domain boiler and the flue gas oxygen content of the boiler is known. Therefore, the relationship between these parameter data of the source domain boiler and the flue gas oxygen content can be used as a sample data, and multiple sample data can be collected to form the first sample data set.

[0031] Similarly, the second sample data set can also be boiler parameter data measured by setting the same sensor on the target boiler. The parameter data of the target boiler is of the same type as the parameter data of the source boiler, and these parameter data are used to form the second sample data set. It is understandable that each sample data in the second data sample set may have a flue gas oxygen content value corresponding to the boiler parameter data, or may not have a flue gas oxygen content value corresponding to the boiler parameter data, or the parameter data of some boilers may have corresponding flue gas oxygen content values, while the parameter data of other boilers may not. In actual applications, the source boiler may already have a trained flue gas oxygen content prediction model deployed, and the prediction accuracy of this flue gas oxygen content prediction model may be very high. However, since the distribution of the above parameter data measured by the source boiler and the target boiler may differ significantly, the flue gas oxygen content prediction model trained on the source boiler using the first sample data set may have low prediction accuracy when applied to the target boiler.

[0032] The embodiment of the present disclosure performs sample migration on the first sample data set of the source domain boiler and the second sample data set of the target boiler to obtain the sample weight data of the source domain boiler with respect to the target boiler, so that the sample data distribution between the source domain boiler and the target boiler is as similar as possible, thereby reusing the sample weight data and the first sample data set to learn the flue gas oxygen content prediction model of the target boiler, and obtaining a target prediction model for predicting the flue gas oxygen content value of the parameter data of the target boiler, thereby quickly obtaining the flue gas oxygen content prediction model of the target boiler and further improving the prediction accuracy of the model.

[0033] In some embodiments, based on the sample migration between the first sample data set and the second sample data set, the sample weight data of the source domain boiler with respect to the target boiler is determined, including: mixing the first sample data set and the second sample data set to obtain mixed sample data; training the kernel density estimation algorithm based on the mixed sample data to obtain a kernel density estimation model; using the first sample data set to input the kernel density estimation model to obtain the sample weight data of the source domain boiler with respect to the target boiler.

[0034] Specifically, the kernel density estimation algorithm is used in probability theory to estimate unknown density functions and is one of the non-parametric test methods. In the embodiment of the present disclosure, the kernel density estimation algorithm is trained by mixing the first sample data set and the second sample data set to obtain a corresponding kernel density estimation model, so that the kernel density estimation model learns the characteristics under the uniform distribution of the two different sample data sets, and the first sample data set is input into the kernel density estimation model to obtain the sample weight data of the source domain boiler with respect to the target boiler, so as to obtain the weight distribution relationship between the second sample data set of the target boiler and the first sample data set of the source domain boiler, thereby adjusting the difference between the first sample data set and the second sample data set and reducing the sample distribution difference between the two different boilers.

[0035] The embodiment of the present disclosure obtains mixed sample data by mixing a first sample data set and a second sample data set; trains a kernel density estimation algorithm based on the mixed sample data to obtain a kernel density estimation model; and uses the first sample data set as input into the kernel density estimation model to obtain sample weight data of the source domain boiler with respect to the target boiler, so that the data distribution between the first sample data set and the second sample data set is as similar as possible.

[0036] In some embodiments, the sample weight data and the first sample data set are used to learn a flue gas oxygen content prediction model of a target boiler to obtain a target prediction model, including: using the sample weight data and the first sample data set to perform neural network learning to obtain a target prediction model for the flue gas oxygen content of the target boiler.

[0037] Specifically, by using the sample weight data and the first sample data set for neural network learning, the objective function relationship between the boiler parameter data and the flue gas oxygen content value in the boiler sample data can be regressed. Since the sample data used to learn the neural network model are the sample weight data after data distribution adjustment and the first sample data set of the source domain boiler, the prediction accuracy of the target prediction model obtained after learning can be further improved compared to the accuracy of directly using the source domain boiler model for the target boiler.

[0038] In some embodiments, each piece of sample data in the first sample data set includes characteristic data of a source boiler and a flue gas oxygen content value corresponding to the characteristic data of the source boiler; each piece of sample data in the second sample data set includes at least characteristic data of a target boiler.

[0039] Specifically, the second sample data set of the target boiler may contain only the target boiler characteristic data that is the same as the source boiler, or may also include the flue gas oxygen content value corresponding to the target boiler characteristic data. For example, the parameter data and corresponding flue gas oxygen content value of the target boiler at the same time can be recorded according to time, and the measured parameter data and corresponding flue gas oxygen content value can be used as sample data. The first sample data set is then formed by using the sample data at different times. In the embodiment of the present disclosure, the first sample data set preferably includes the parameter data of the target boiler and the flue gas oxygen content value corresponding to the parameter data.

[0040] It should be noted that the specific types of parameter data of the source domain boiler and the target boiler may include but are not limited to steam boiler flue gas temperature, economizer outlet temperature, flue gas flow instantaneous value, steam boiler gas temperature, steam boiler flue gas standard flow rate, steam boiler natural gas inlet pressure, steam boiler flue gas flow rate, steam boiler condenser inlet flue gas temperature, steam boiler exhaust temperature, steam boiler flue gas pressure, steam boiler condenser inlet pressure, steam boiler main steam instantaneous flow rate, steam boiler operating status and steam boiler natural gas inlet instantaneous flow rate, etc., that is, the embodiment of the present disclosure does not limit the specific types and quantities of sample features in the first sample data set and the second sample data set.

[0041] In some embodiments, the sample data volume of the first sample data set is substantially the same as the sample data volume of the second sample data set. That is, the sample data volume of the first sample data set is greater than or equal to the sample data volume of the second sample data set. For example, the sample data volume of the first sample data set and the second sample data set is 8,000 or more.

[0042] Figure 3 FIG. 1 is a flow chart of another method for predicting flue gas oxygen content based on sample migration provided by an embodiment of the present disclosure. Figure 3 As shown, the flue gas oxygen content prediction method based on sample migration includes:

[0043] S301, obtaining a first sample data set of a source domain boiler and a second sample data set of a target boiler;

[0044] S302, mixing the first sample data set and the second sample data set, and training a kernel density estimation algorithm based on the mixed first sample data set and the second sample data set to obtain a kernel density estimation model;

[0045] S303, using the first sample data set to input a kernel density estimation model, and obtaining sample weight data of the source domain boiler with respect to the target boiler from the output of the kernel density estimation model;

[0046] S304, training a neural network based on the sample weight data and the first sample data set to obtain a target prediction model for the flue gas oxygen content of the target boiler;

[0047] S305 , predicting the data of the target boiler using the target prediction model to obtain the flue gas oxygen content value of the target boiler, where the data includes a second sample data set.

[0048] The embodiment of the present disclosure performs sample migration on the first sample data set of the source domain boiler and the second sample data set of the target boiler to obtain the sample weight data of the source domain boiler with respect to the target boiler, so that the sample data distribution between the source domain boiler and the target boiler is as similar as possible, thereby reusing the sample weight data and the first sample data set to learn the flue gas oxygen content prediction model of the target boiler, and obtaining a target prediction model for predicting the flue gas oxygen content value of the parameter data of the target boiler, thereby quickly obtaining the flue gas oxygen content prediction model of the target boiler and further improving the prediction accuracy of the model.

[0049] All of the above optional technical solutions can be combined in any way to form optional embodiments of the present application, and will not be described in detail here.

[0050] The following are embodiments of the apparatus disclosed herein, which can be used to implement the method embodiments disclosed herein. For details not disclosed in the apparatus embodiments disclosed herein, please refer to the method embodiments disclosed herein.

[0051] Figure 4 Schematic diagram of a flue gas oxygen content prediction device based on sample migration provided by an embodiment of the present disclosure. Figure 4 As shown, the flue gas oxygen content prediction device based on sample migration includes:

[0052] An acquisition module 401 is configured to acquire a first sample data set of a source boiler and a second sample data set of a target boiler;

[0053] The migration module 402 is configured to determine sample weight data of the source domain boiler with respect to the target boiler based on the sample migration between the first sample data set and the second sample data set;

[0054] The training module 403 is configured to learn a flue gas oxygen content prediction model of a target boiler using the sample weight data and the first sample data set to obtain a target prediction model;

[0055] The prediction module 404 is configured to predict the data of the target boiler based on the target prediction model to obtain the flue gas oxygen content value of the target boiler.

[0056] The embodiment of the present disclosure performs sample migration on the first sample data set of the source domain boiler and the second sample data set of the target boiler to obtain the sample weight data of the source domain boiler with respect to the target boiler, so that the sample data distribution between the source domain boiler and the target boiler is as similar as possible, thereby reusing the sample weight data and the first sample data set to learn the flue gas oxygen content prediction model of the target boiler, and obtaining a target prediction model for predicting the flue gas oxygen content value of the parameter data of the target boiler, thereby quickly obtaining the flue gas oxygen content prediction model of the target boiler and further improving the prediction accuracy of the model.

[0057] In some embodiments, Figure 4 The migration module 402 mixes the first sample data set and the second sample data set to obtain mixed sample data; trains the kernel density estimation algorithm based on the mixed sample data to obtain a kernel density estimation model; uses the first sample data set to input the kernel density estimation model to obtain sample weight data of the source domain boiler with respect to the target boiler.

[0058] In some embodiments, Figure 4 The training module 403 uses the sample weight data and the first sample data set to perform neural network learning to obtain a target prediction model for the flue gas oxygen content of the target boiler.

[0059] In some embodiments, each piece of sample data in the first sample data set includes characteristic data of a source boiler and a flue gas oxygen content value corresponding to the characteristic data of the source boiler; each piece of sample data in the second sample data set includes at least characteristic data of a target boiler.

[0060] In some embodiments, the characteristic data of the source domain boiler and the characteristic data of the target boiler respectively include at least one of the following data: steam boiler flue gas temperature, economizer outlet temperature, flue gas flow instantaneous value, steam boiler gas temperature, steam boiler flue gas standard flow rate, steam boiler natural gas inlet pressure, steam boiler flue gas flow rate, steam boiler condenser inlet flue gas temperature, steam boiler exhaust temperature, steam boiler flue gas pressure, steam boiler condenser inlet pressure, steam boiler main steam instantaneous flow rate, steam boiler operating status and steam boiler natural gas inlet instantaneous flow rate.

[0061] In some embodiments, the sample data volume of the first sample data set is substantially the same as the sample data volume of the second sample data set.

[0062] In some embodiments, the sample data volume of the first sample data set and the second sample data set is greater than or equal to 8,000.

[0063] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

[0064] Figure 5 Schematic diagram of an electronic device 5 provided in an embodiment of the present disclosure. Figure 5 The electronic device 5 can be Figure 1 The target terminal or server in Figure 5 As shown, the electronic device 5 of this embodiment includes: a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable on the processor 501. When the processor 501 executes the computer program 503, the steps of the above-mentioned method embodiments are implemented. Alternatively, when the processor 501 executes the computer program 503, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0065] For example, the computer program 503 may be divided into one or more modules / units, which are stored in the memory 502 and executed by the processor 501 to implement the present disclosure. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 503 in the electronic device 5.

[0066] The electronic device 5 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 5 may include but is not limited to a processor 501 and a memory 502. Those skilled in the art will appreciate that Figure 5 It is only an example of the electronic device 5 and does not constitute a limitation of the electronic device 5. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0067] The processor 501 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0068] The memory 502 can be an internal storage unit of the electronic device 5, such as a hard drive or memory of the electronic device 5. The memory 502 can also be an external storage device of the electronic device 5, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped on the electronic device 5. Furthermore, the memory 502 can include both an internal storage unit of the electronic device 5 and an external storage device. The memory 502 is used to store computer programs and other programs and data required by the electronic device. The memory 502 can also be used to temporarily store data that has been output or is about to be output.

[0069] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0070] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0071] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0072] In the embodiments provided in the present disclosure, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely schematic. For example, the division of modules or units is merely a logical function division. In actual implementation, there may be other division methods. Multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection of devices or units, which may be electrical, mechanical or other forms.

[0073] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0074] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0075] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present disclosure implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. The computer program may include computer program code, which may be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0076] The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present disclosure, and should all be included in the scope of protection of the present disclosure.

Claims

1. A method for predicting flue gas oxygen content based on sample migration, characterized in that: include: Obtain a first sample data set of a source domain boiler and a second sample data set of a target boiler; determining sample weight data of the source domain boiler with respect to the target boiler based on sample migration between the first sample data set and the second sample data set; Using the sample weight data and the first sample data set to learn a flue gas oxygen content prediction model of the target boiler to obtain a target prediction model; Predicting the data of the target boiler based on the target prediction model to obtain the flue gas oxygen content value of the target boiler; The determining, based on the sample migration between the first sample data set and the second sample data set, the sample weight data of the source domain boiler with respect to the target boiler includes: mixing the first sample data set and the second sample data set to obtain mixed sample data; Training a kernel density estimation algorithm based on the mixed sample data to obtain a kernel density estimation model; Using the first sample data set to input the kernel density estimation model, obtaining sample weight data of the source domain boiler with respect to the target boiler; The method of learning the flue gas oxygen content prediction model of the target boiler by using the sample weight data and the first sample data set to obtain a target prediction model includes: Performing neural network learning using the sample weight data and the first sample data set to obtain a target prediction model for the flue gas oxygen content of the target boiler; Each piece of sample data in the first sample data set includes characteristic data of the source domain boiler and a flue gas oxygen content value corresponding to the characteristic data of the source domain boiler; Each piece of sample data in the second sample data set includes at least characteristic data of the target boiler.

2. The method according to claim 1, characterized in that The characteristic data of the source domain boiler and the characteristic data of the target boiler respectively include at least one of the following data: steam boiler flue gas temperature, economizer outlet temperature, flue gas flow instantaneous value, steam boiler gas temperature, steam boiler flue gas standard flow rate, steam boiler natural gas inlet pressure, steam boiler flue gas flow rate, steam boiler condenser inlet flue gas temperature, steam boiler exhaust temperature, steam boiler flue gas pressure, steam boiler condenser inlet pressure, steam boiler main steam instantaneous flow rate, steam boiler operating status and steam boiler natural gas inlet instantaneous flow rate.

3. The method according to claim 1, characterized in that The sample data volume of the first sample data set is greater than or equal to the sample data volume of the second sample data set.

4. The method according to claim 3, characterized in that The sample data volume of the first sample data set and the second sample data set is greater than or equal to 8,000.

5. A device for predicting flue gas oxygen content based on sample migration, characterized in that: include: An acquisition module is configured to acquire a first sample data set of a source domain boiler and a second sample data set of a target boiler; a migration module configured to determine sample weight data of the source domain boiler with respect to the target boiler based on sample migration between the first sample data set and the second sample data set; The method includes: mixing the first sample data set and the second sample data set to obtain mixed sample data; training a kernel density estimation algorithm based on the mixed sample data to obtain a kernel density estimation model; using the first sample data set to input the kernel density estimation model to obtain sample weight data of the source domain boiler with respect to the target boiler; a training module configured to learn a flue gas oxygen content prediction model of the target boiler using the sample weight data and the first sample data set to obtain a target prediction model; the training module includes: performing neural network learning using the sample weight data and the first sample data set to obtain a target prediction model for the flue gas oxygen content of the target boiler; a prediction module configured to predict the data of the target boiler based on the target prediction model to obtain the flue gas oxygen content value of the target boiler; Among them, each sample data in the first sample data set includes the characteristic data of the source domain boiler and the flue gas oxygen content value corresponding to the characteristic data of the source domain boiler; each sample data in the second sample data set at least includes the characteristic data of the target boiler.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images