Flue Gas Oxygen Content Load Prediction Method and Device Based on Sample Migration

Abstract

The present invention discloses a method and device for predicting the oxygen content load of flue gas based on sample migration. The method includes: obtaining the device data of a first participant and a second participant under a joint learning architecture; wherein, the first participant is the participant who puts forward the prediction requirement, and the second participant is other participants except the first participant; training a prediction classifier by using the device data of the first participant and the device data of the second participant; determining the weight data of the device data of the first participant with respect to the device data of the second participant according to the prediction classifier; training a predictive gradient boosting model based on the device data of the second participant and the weight data; and predicting the oxygen content load of the flue gas of the device of the first participant by using the predictive gradient boosting model. The present invention solves the problem of inaccurate prediction of the oxygen content load of flue gas caused by the data distribution difference of energy equipment generated under different processes, and saves the cost of energy equipment sensors.

Description

Technical Field

[0001] The present disclosure relates to the field of energy technologies, and in particular, to a method, apparatus, computer device, and computer-readable storage medium for predicting the oxygen content load in flue gas based on sample migration. Background Art

[0002] At present, the application of integrated energy is an indispensable application in today's society. With the wide application, the requirements for energy equipment are also getting higher and higher. However, in industrial applications, many large-scale energy equipment cannot be updated at any time, or it is not easy to detect the over-standard heat load during application.

[0003] For example, in industrial energy applications, the distribution differences of relevant equipment data generated by boiler equipment under different processes may be very large, which often leads to low prediction accuracy of the oxygen content in flue gas, and is not conducive to later equipment warning and scheduling operations. These problems urgently need to be solved by us. Summary of the Invention

[0004] In view of this, embodiments of the present disclosure provide a method, apparatus, computer device, and computer-readable storage medium for predicting the oxygen content load in flue gas based on sample migration, so as to solve the problem of inaccurate prediction of the oxygen content load in flue gas caused by the distribution differences of energy equipment data generated under different processes in the prior art.

[0005] In the first aspect of the embodiments of the present disclosure, a method for predicting the oxygen content load in flue gas based on sample migration is provided, which is applied to a federated learning framework and includes:

[0006] Obtain the device data of the first participant and the device data of the second participant under the federated learning architecture; wherein, the first participant is the participant who proposes the prediction requirement, and the second participant is other participants except the first participant;

[0007] Use the device data of the first participant and the device data of the second participant to train a prediction classifier;

[0008] According to the prediction classifier, determine the weight data of the device data of the first participant with respect to the device data of the second participant;

[0009] Based on the device data of the second participant and the weight data, train a predictive gradient boosting model;

[0010] Use the predictive gradient boosting model to predict the oxygen content load of the device of the first participant.

[0011] In the second aspect of the embodiments of the present disclosure, a device for predicting the oxygen content load in flue gas based on sample migration is provided, which is applied to a federated learning framework and includes:

[0012] An acquisition module for acquiring the device data of the first participant and the device data of the second participant under the federated learning architecture; wherein, the first participant is the participant who raises the prediction requirement, and the second participant is other participants except the first participant;

[0013] A first training module for training a prediction classifier using the device data of the first participant and the device data of the second participant;

[0014] A calculation module for determining the weight data of the device data of the first participant with respect to the device data of the second participant according to the prediction classifier;

[0015] A second training module for training a predictive gradient boosting model based on the device data of the second participant and the weight data;

[0016] A prediction module for predicting the oxygen content load of the flue gas of the first participant's device using the predictive gradient boosting model.

[0017] In a third aspect of the embodiments of the present disclosure, there is provided a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above method are implemented.

[0018] In a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0019] The beneficial effects of the embodiments of the present disclosure compared with the prior art are as follows: By acquiring the device data of the first participant and the device data of the second participant under the federated learning architecture; wherein, the first participant is the participant who raises the prediction requirement, and the second participant is other participants except the first participant; training a prediction classifier using the device data of the first participant and the device data of the second participant; determining the weight data of the device data of the first participant with respect to the device data of the second participant according to the prediction classifier; training a predictive gradient boosting model based on the device data of the second participant and the weight data; and predicting the oxygen content load of the flue gas of the first participant's device using the predictive gradient boosting model. To solve the problem of inaccurate prediction of the oxygen content load of the flue gas caused by the data distribution differences of energy equipment generated under different processes in the prior art, and to save the cost of energy equipment sensors. Description of the Drawings

[0020] To more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the accompanying drawings required for use in the embodiments or the description of the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0021] Figure 1 is a schematic diagram of the application scenario of the embodiments of the present disclosure;

[0022] Figure 2 is a flowchart of a method for predicting the oxygen content load in flue gas based on sample migration provided by the embodiments of the present disclosure;

[0023] Figure 3 is a block diagram of a device for predicting the oxygen content load in flue gas based on sample migration provided by the embodiments of the present disclosure;

[0024] Figure 4 is a schematic diagram of a computer device provided by the embodiments of the present disclosure. Detailed implementation manners

[0025] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system architectures and technologies are presented in order to thoroughly understand the embodiments of the present disclosure. However, those skilled in the art should clearly understand that the present disclosure can also 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 unnecessary details from interfering with the description of the present disclosure.

[0026] Federated learning refers to, on the premise of ensuring data security and user privacy, comprehensively using a variety of AI (Artificial Intelligence) technologies, jointly cooperating among multiple parties to jointly explore data value, and giving birth to new intelligent business forms and models based on joint modeling. Federated learning has at least the following characteristics:

[0027] (1) A weakly centralized joint training mode in which participating nodes control their own data, ensuring data privacy and security in the process of jointly creating intelligence.

[0028] (2) In different application scenarios, by using screening and / or combining AI algorithms and privacy-preserving computing, establishing various model aggregation and optimization strategies to obtain high-level and high-quality models.

[0029] (3) On the premise of ensuring data security and user privacy, based on a variety of model aggregation and optimization strategies, a method for improving the efficiency of the federated learning engine is obtained. The efficiency method can be to improve the overall efficiency of the federated learning engine by solving problems including parallel computing architectures, information interaction under large-scale cross-domain networks, intelligent perception, and anomaly handling mechanisms.

[0030] (4) Obtain the requirements of multi-party users in various scenarios, and through a mutual trust mechanism, determine a reasonable evaluation of the true contribution of each federated participant and conduct distribution incentives.

[0031] Based on the above methods, an AI technology ecosystem based on federated learning can be established to fully utilize the value of industry data and promote the implementation of scenarios in vertical fields.

[0032] Next, a method and device for predicting the oxygen content load in flue gas based on sample migration according to an embodiment of the present disclosure will be described in detail with reference to the accompanying drawings.

[0033] Figure 1 It is a schematic diagram of the application scenario of the embodiment of the present disclosure. An application scenario of the embodiment of the present disclosure is a federated learning scenario. Figure 1 As shown, it is a schematic diagram of the architecture of a federated learning. As Figure 1 shown, the architecture of the federated learning may include a server (central node) 101 and participants 102, 103, and 104. The participants can be a single client or a combination of multiple clients.

[0034] During the federated learning process, the basic model can be established by the server 101, and the server 101 sends the model to the participants 102, 103, and 104 that have established a communication connection with it. The basic model can also be established by any participant and uploaded to the server 101, and the server 101 sends the model to other participants that have established a communication connection with it. The participants 102, 103, and 104 build models according to the downloaded basic structure and model parameters, use local data for model training, obtain updated model parameters, and encrypt and upload the updated model parameters to the server 101. The server 101 aggregates the model parameters sent by the participants 102, 103, and 104 to obtain global model parameters, and sends the global model parameters back to the participants 102, 103, and 104. The participants 102, 103, and 104 iterate their respective models according to the received global model parameters until the model finally converges, thereby realizing the training of the model. During the federated learning process, the data uploaded by the participants 102, 103, and 104 are model parameters, and the local data will not be uploaded to the server 101, and all participants can share the final model parameters. Therefore, common modeling can be achieved on the basis of ensuring data privacy.

[0035] It should be noted that the number of participating parties is not limited to the three as described above, but can be set according to needs, and the embodiments of the present disclosure do not limit this.

[0036] Figure 2 It is a flowchart of a method for predicting the oxygen content load in flue gas based on sample migration provided by the embodiments of the present disclosure. Figure 2 The method for predicting the oxygen content load in flue gas based on sample migration can be executed by Figure 1 the server of. As Figure 2 shown, the method for predicting the oxygen content load in flue gas based on sample migration includes:

[0037] S201, obtaining the device data of the first participating party and the device data of the second participating party under the collaborative learning architecture.

[0038] Among them, the first participating party is the participating party that puts forward the prediction requirement, and the second participating party is other participating parties except the first participating party.

[0039] Specifically, it can be realized by receiving the device data sets of the first participating party and the second participating party; then, according to the preset screening features, screening the device data sets of the first participating party and the second participating party to respectively obtain the sample quantity of the device data of the first participating party and the quantity of the device data of the second participating party; furthermore, determining the sample quantity of the device data of the first participating party and the quantity of the device data of the second participating party as the device data of the first participating party and the device data of the second participating party respectively.

[0040] S202, training a prediction classifier by using the device data of the first participating party and the device data of the second participating party.

[0041] Specifically, it can be realized by performing labeling processing on the device data of the first participating party and the device data of the second participating party to obtain the labeled data of the device data of the first participating party and the labeled data of the device data of the second participating party; furthermore, merging the labeled data of the device data of the first participating party and the labeled data of the device data of the second participating party to obtain the merged labeled data; finally, training a prediction classifier according to the merged labeled data.

[0042] S203, determining the weight data of the device data of the first participating party with respect to the device data of the second participating party according to the prediction classifier.

[0043] Specifically, by using a prediction classifier, the equipment failure probability values corresponding to the equipment data of the first participant and the equipment failure probability values corresponding to the equipment data of the second participant can be obtained respectively; then, based on the equipment failure probability values corresponding to the equipment data of the first participant and the equipment failure probability values corresponding to the equipment data of the second participant, the weight data of the equipment data of the first participant with respect to the equipment data of the second participant can be determined.

[0044] Furthermore, for realizing the use of the prediction classifier to respectively obtain the equipment failure probability values corresponding to the equipment data of the first participant and the equipment failure probability values corresponding to the equipment data of the second participant, the equipment data of the first participant and the equipment data of the second participant can be classified respectively by using the prediction classifier to obtain the equipment failure data corresponding to the equipment data of the first participant and the equipment failure data corresponding to the equipment data of the second participant; then, the equipment failure probability values corresponding to the equipment failure data corresponding to the equipment data of the first participant and the equipment failure data corresponding to the equipment data of the second participant are calculated respectively.

[0045] S204. Train a predictive gradient boosting model based on the equipment data of the second participant and the weight data.

[0046] Specifically, a predictive gradient boosting model can be trained based on the equipment data of the second participant and the weight data of the equipment data of the first participant with respect to the equipment data of the second participant; then, the test data of the first participant is used to train the predictive gradient boosting model to obtain the equipment prediction value of the first participant; then, according to the norm of the error matrix between the equipment prediction value of the first participant and the equipment expected value, the fitness value of the predictive gradient boosting model is obtained; finally, according to the fitness value of the predictive gradient boosting model, the particles in the population of the predictive gradient boosting model are updated to obtain an optimized predictive gradient boosting model.

[0047] Furthermore, the optimization of the predictive gradient boosting model can be achieved in the following manner:

[0048] First, determine the population in the predictive gradient boosting model and the particles in the population;

[0049] Then, determine whether the fitness value corresponding to the current particle in the population is greater than the fitness value of the previous old particle; if it is less, the population and the particles in the population in the predictive gradient boosting model need to be updated.

[0050] S205. Use the predictive gradient boosting model to predict the oxygen content load of the flue gas of the equipment of the first participant.

[0051] According to the technical solution provided by the embodiments of the present disclosure, device data of a first participant and device data of a second participant under a federated learning architecture are obtained; wherein, the first participant is the participant who raises a prediction requirement, and the second participant is other participants except the first participant; the prediction classifier is trained by using the device data of the first participant and the device data of the second participant; according to the prediction classifier, weight data of the device data of the first participant with respect to the device data of the second participant is determined; a predictive gradient boosting model is trained based on the device data of the second participant and the weight data; the predictive gradient boosting model is used to predict the oxygen content load of the flue gas of the device of the first participant. To solve the problem of inaccurate prediction of the oxygen content load of the flue gas caused by the difference in data distribution of energy devices generated under different processes in the prior art, and to save the cost of energy device sensors.

[0052] Any combination of the above all optional technical solutions can form an optional embodiment of the present application, which will not be elaborated herein one by one.

[0053] The following are the device embodiments of the present disclosure, which can be used to execute the method embodiments of the present disclosure. For details not disclosed in the device embodiments of the present disclosure, please refer to the method embodiments of the present disclosure.

[0054] Figure 3 is a schematic diagram of a device for predicting the oxygen content load of flue gas based on sample migration provided by the embodiments of the present disclosure. As Figure 3 shown, the device for predicting the oxygen content load of flue gas based on sample migration, which is applied to a federated learning framework, includes:

[0055] An acquisition module 301, configured to acquire device data of a first participant and device data of a second participant under a federated learning architecture; wherein, the first participant is the participant who raises a prediction requirement, and the second participant is other participants except the first participant;

[0056] A first training module 302, configured to train a prediction classifier by using the device data of the first participant and the device data of the second participant;

[0057] A calculation module 303, configured to determine weight data of the device data of the first participant with respect to the device data of the second participant according to the prediction classifier;

[0058] A second training module 304, configured to train a predictive gradient boosting model based on the device data of the second participant and the weight data;

[0059] A prediction module 305, configured to predict the oxygen content load of the flue gas of the device of the first participant by using the predictive gradient boosting model.

[0060] According to the technical solution provided by the embodiments of the present disclosure, obtain the device data of the first participant and the device data of the second participant under the collaborative learning architecture; wherein, the first participant is the participant who puts forward the prediction requirement, and the second participant is other participants except the first participant; use the device data of the first participant and the device data of the second participant to train a prediction classifier; according to the prediction classifier, determine the weight data of the device data of the first participant with respect to the device data of the second participant; based on the device data of the second participant and the weight data, train a predictive gradient boosting model; use the predictive gradient boosting model to predict the oxygen content load of the flue gas of the first participant's device. To solve the problem in the prior art that the prediction of the oxygen content load of the flue gas is inaccurate due to the data distribution differences of energy devices generated under different processes, and to save the cost of energy device sensors.

[0061] It should be understood that the sequence numbers of the steps in the above embodiments do not imply the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present disclosure.

[0062] Figure 4 is a schematic diagram of the computer device 4 provided by the embodiments of the present disclosure. As Figure 4 shown, the computer device 4 of this embodiment includes: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, the steps in the above-mentioned various method embodiments are implemented. Alternatively, when the processor 401 executes the computer program 403, the functions of each module / unit in the above-mentioned various device embodiments are implemented.

[0063] Exemplarily, the computer program 403 can be divided into one or more modules / units. One or more modules / units are stored in the memory 402 and executed by the processor 401 to complete the present disclosure. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 403 in the computer device 4.

[0064] The computer device 4 can be a desktop computer, a notebook, a palm computer, a cloud server, and other computer devices. The computer device 4 may include, but is not limited to, the processor 401 and the memory 402. Those skilled in the art can understand that Figure 4 is only an example of the computer device 4, and does not constitute a limitation to the computer device 4. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the computer device may further include input / output devices, network access devices, a bus, etc.

[0065] The processor 401 can be a Central Processing Unit (CPU), or other general-purpose processors, 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, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0066] The memory 402 can be an internal storage unit of the computer device 4. For example, the hard disk or memory of the computer device 4. The memory 402 can also be an external storage device of the computer device 4. For example, a plug-in hard disk equipped on the computer device 4, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 402 can also include both the internal storage unit and the external storage device of the computer device 4. The memory 402 is used to store computer programs and other programs and data required by the computer device. The memory 402 can also be used to temporarily store data that has been output or is to be output.

[0067] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments 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 integrated units can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0068] In the above embodiments, the descriptions of the various embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0069] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this disclosure.

[0070] In the embodiments provided in this disclosure, it should be understood that the disclosed device / computer device and method can be implemented in other ways. For example, the device / computer device embodiments described above are only illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. Multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical or other form.

[0071] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0072] In addition, the functional units in each embodiment of this disclosure can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0073] When an 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, to implement all or part of the processes in the above-mentioned embodiment methods of the present disclosure, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program can include computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice within the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0074] 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 foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present disclosure, and should all be included in the protection scope of the present disclosure.

Claims

1. A method for predicting the oxygen content load of flue gas based on sample migration, characterized in that The method is applied to a federated learning framework and includes: Obtaining the device data of a first participant and the device data of a second participant under a federated learning architecture; wherein, the first participant is the participant who puts forward the prediction requirement, and the second participant is other participants except the first participant; Training a prediction classifier using the device data of the first participant and the device data of the second participant; Determining weight data of the device data of the first participant with respect to the device data of the second participant according to the prediction classifier; Training a predictive gradient boosting model based on the device data of the second participant and the weight data; Predicting the oxygen content load of the flue gas of the first participant's device using the predictive gradient boosting model; Training a prediction classifier using the device data of the first participant and the device data of the second participant includes: performing labeling processing on the device data of the first participant and the device data of the second participant to obtain the labeled data of the device data of the first participant and the labeled data of the device data of the second participant; merging the labeled data of the device data of the first participant and the labeled data of the device data of the second participant to obtain the merged labeled data; training a prediction classifier according to the merged labeled data; Determining weight data of the device data of the first participant with respect to the device data of the second participant according to the prediction classifier includes: using the prediction classifier to respectively obtain the device failure probability value corresponding to the device data of the first participant and the device failure probability value corresponding to the device data of the second participant; determining the weight data of the device data of the first participant with respect to the device data of the second participant according to the device failure probability value corresponding to the device data of the first participant and the device failure probability value corresponding to the device data of the second participant.

2. The method according to claim 1, characterized in that, Obtaining the device data of the first participant and the device data of the second participant under a federated learning architecture includes: Receiving the device data set from the first participant and the device data set from the second participant; Filtering the device data set of the first participant and the device data set of the second participant according to preset filtering features to respectively obtain the device data sample size of the first participant and the device data volume of the second participant; Determining the device data sample size of the first participant and the device data volume of the second participant as the device data of the first participant and the device data of the second participant respectively.

3. The method according to claim 1, wherein Using the prediction classifier to respectively obtain the device failure probability value corresponding to the device data of the first participant and the device failure probability value corresponding to the device data of the second participant includes: Using the prediction classifier to classify the device data of the first participant and the device data of the second participant respectively to obtain the device failure data corresponding to the device data of the first participant and the device failure data corresponding to the device data of the second participant; Respectively calculating the device failure probability values corresponding to the device failure data corresponding to the device data of the first participant and the device failure data corresponding to the device data of the second participant.

4. The method according to claim 1, wherein Training a predictive gradient boosting model based on the device data of the second participant and the weight data further includes: Train a predictive gradient boosting model based on the device data of the second participant and the weight data; Obtain the test data of the first participant to train the predictive gradient boosting model to obtain the device prediction value of the first participant; Obtain the fitness value of the predictive gradient boosting model according to the norm of the error matrix between the device prediction value and the device expected value of the first participant; Update the particles in the population of the predictive gradient boosting model according to the fitness value to obtain an optimized predictive gradient boosting model.

5. The method according to claim 4, wherein Updating the particles in the population of the predictive gradient boosting model according to the fitness value to obtain an optimized predictive gradient boosting model includes: Determine the population in the predictive gradient boosting model and the particles in the population; Judge whether the fitness value corresponding to the particles in the current population is greater than the fitness value of the previous old particles; If it is less than, it is necessary to update the population in the predictive gradient boosting model and the particles in the population.

6. A flue gas oxygen content load prediction device based on sample migration, characterized in that, The application of the device in the federated learning framework includes: An acquisition module, configured to acquire the device data of the first participant and the device data of the second participant under the federated learning architecture; wherein, the first participant is the participant who proposes the prediction requirement, and the second participant is other participants except the first participant; The first training module uses the device data of the first participant and the device data of the second participant to train a prediction classifier; using the device data of the first participant and the device data of the second participant to train a prediction classifier includes: performing labeling processing on the device data of the first participant and the device data of the second participant to obtain the labeled data of the device data of the first participant and the labeled data of the device data of the second participant; merging the labeled data of the device data of the first participant and the labeled data of the device data of the second participant to obtain the merged labeled data; training a prediction classifier according to the merged labeled data; A calculation module, configured to determine the weight data of the device data of the first participant with respect to the device data of the second participant according to the prediction classifier; determining the weight data of the device data of the first participant with respect to the device data of the second participant according to the prediction classifier includes: using the prediction classifier to respectively obtain the device failure probability value corresponding to the device data of the first participant and the device failure probability value corresponding to the device data of the second participant; determining the weight data of the device data of the first participant with respect to the device data of the second participant according to the device failure probability value corresponding to the device data of the first participant and the device failure probability value corresponding to the device data of the second participant; A second training module, configured to train a predictive gradient boosting model based on the device data of the second participant and the weight data group; A prediction module, configured to predict the oxygen content load of the flue gas of the first participant's device by using the predictive gradient boosting model.

7. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 5.

Images