Method and device for predicting oxygen content in flue gas of gas boiler

Abstract

The present invention is applicable to the field of gas-fired distributed energy, and provides a method and device for predicting the flue gas oxygen content of a gas-fired boiler, the method comprising: obtaining a flue gas oxygen content prediction model request and a model database of a gas-fired boiler in an energy station; determining whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database; determining a flue gas oxygen content prediction model according to the judgment result; predicting the flue gas oxygen content of the gas-fired boiler in the energy station according to the flue gas oxygen content prediction model and the operating data of the gas-fired boiler. This embodiment achieves the goal of not using a sensor to measure the flue gas oxygen content, being able to predict the flue gas oxygen content in real time, being easy to maintain, and reducing measurement errors. At the same time, the combined flue gas oxygen content prediction model relies on real data, is not easily affected by the external environment, and can more accurately determine the flue gas oxygen content.

Description

Technical Field

[0001] The present invention belongs to the field of gas-fired distributed energy, and in particular relates to a method and a device for predicting the oxygen content of flue gas of a gas-fired boiler. Background Art

[0002] Flue gas oxygen content refers to the content of flue gas discharged after fuel combustion. It is an important indicator of gas boiler combustion. Its value is related to factors such as gas boiler structure, fuel type and nature, load size, operating air supply conditions and equipment sealing conditions. In the actual operation of the gas boiler, in order to allow the fuel to burn fully, the actual amount of air supplied is much larger than the theoretical amount of air supplied. This extra amount of air supplied is usually called excess air. The excess air coefficient is the ratio of the actual amount of air supplied to the theoretical amount of air supplied. If the flue gas oxygen content is too low, that is, the smaller the excess air coefficient, the less oxygen will be supplied to the gas boiler for combustion, the fuel cannot be fully burned, and the heat loss will increase; if the flue gas oxygen content is too high, that is, the larger the excess air coefficient, the thermal efficiency of the gas boiler will be reduced, which will not only affect the combustion, but also easily cause excessive emissions of environmental pollutants and increase the power consumption of flue gas exhaust. Therefore, controlling the oxygen content of the flue gas of the gas boiler within a reasonable range is of great significance for saving energy, maintaining the economical combustion of the gas boiler, and achieving safe, efficient and low-pollution emissions. In other words, the oxygen content of the flue gas of the gas boiler is one of the important indicators to measure whether the gas boiler is operating safely, economically and environmentally friendly.

[0003] At present, zirconium oxide sensors are generally used in industry to measure the oxygen content of flue gas.

[0004] However, this type of sensor has many disadvantages such as high cost, large measurement lag, difficult maintenance, large measurement error, and short life. It is not suitable for long-term use in scenarios where distributed energy is mainly small and medium-sized gas boilers. Summary of the invention

[0005] In view of this, the embodiments of the present invention provide a method and device for predicting the oxygen content of flue gas of a gas boiler, which only requires a small amount of label data, can overcome the shortcomings of the sensor's complete actual measurement, and does not need to rely on a large number of physical parameters like physical modeling.

[0006] A first aspect of an embodiment of the present invention provides a method for predicting the oxygen content in flue gas of a gas boiler, comprising: obtaining a flue gas oxygen content prediction model request and a model database of the gas boiler in an energy station; determining whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database; determining a flue gas oxygen content prediction model based on a result of determining whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database; predicting the flue gas oxygen content of the gas boiler in the energy station based on the flue gas oxygen content prediction model and the operating data of the gas boiler.

[0007] A second aspect of an embodiment of the present invention provides a device for predicting the oxygen content in flue gas of a gas boiler, comprising: an acquisition module, configured to obtain a flue gas oxygen content prediction model request and a model database of the gas boiler in an energy station; a judgment module, configured to judge whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database; a determination module, configured to determine the flue gas oxygen content prediction model based on a judgment result of whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database; a prediction module, configured to predict the flue gas oxygen content of the gas boiler in the energy station based on the flue gas oxygen content prediction model and the operating data of the gas boiler.

[0008] A third aspect of an embodiment of the present invention provides a terminal device, 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 method when executing the computer program.

[0009] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and is characterized in that the steps of the method are implemented when the computer program is executed by a processor.

[0010] Compared with the prior art, the beneficial effects of the embodiments of the present invention are as follows: first, a flue gas oxygen content prediction model request and a model database of a gas boiler in an energy station are obtained; then, it is determined whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database; thereafter, the flue gas oxygen content prediction model is determined according to the judgment result of whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database; finally, the flue gas oxygen content of the gas boiler in the energy station is predicted according to the flue gas oxygen content prediction model and the operating data of the gas boiler. In summary, through the technical solution of the present invention, there is no need to use a sensor to measure the flue gas oxygen content, the flue gas oxygen content can be predicted in real time, maintenance is convenient, and measurement errors are reduced. At the same time, the combined flue gas oxygen content prediction model relies on real data and is not easily affected by the external environment, so the flue gas oxygen content can be determined more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0012] Figure 1 A schematic flow chart of a method for predicting oxygen content in flue gas of a gas boiler provided in one embodiment of the present invention;

[0013] Figure 2 A schematic diagram of the structure of another method for predicting oxygen content in flue gas of a gas boiler provided in one embodiment of the present invention;

[0014] Figure 3 A schematic diagram of the structure of a device for predicting oxygen content in flue gas of a gas boiler provided in one embodiment of the present invention;

[0015] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention;

[0016] Figure 5 A scenario application diagram provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention 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 prevent unnecessary details from obstructing the description of the present invention.

[0018] In order to illustrate the technical solution of the present invention, a specific embodiment is provided below for illustration.

[0019] like Figure 1 As shown, a method for predicting the oxygen content of flue gas of a gas boiler provided by an embodiment of the present invention. The method provided by an embodiment of the present invention can be applied to electronic devices, and can be specifically applied to servers or general computers. An embodiment of the present invention provides a method for predicting the oxygen content of flue gas of a gas boiler, comprising the following steps:

[0020] Step 101, obtaining a flue gas oxygen content prediction model request and a model database of a gas boiler in an energy station.

[0021] In some embodiments, the execution entity may obtain the flue gas oxygen content prediction model request and the model database of the gas boiler in the energy station in a wired or wireless manner.

[0022] Specifically, the client of the energy station sends a flue gas oxygen content prediction model request of the gas boiler in the energy station through the API interface. The energy station is generally configured to provide energy to a designated area, such as an area adjacent to the energy station. The energy system may include multiple energy stations, and the multiple energy stations supply energy to multiple areas.

[0023] The model database can be understood as a database for storing the joint learning model. In practical applications, a joint learning Internet of Things platform can be developed. The joint learning Internet of Things platform is used to perform joint learning with a joint learning client (a client performing joint learning), obtain a joint learning model, and store the joint learning model. It can be understood that the flue gas oxygen content prediction method provided in the embodiment of the present application involves the interaction between the joint learning Internet of Things platform and the client. In addition, it can be applied to the scene of the interaction between at least one client and a joint learning Internet of Things platform, or it can also be applied to the scene of at least one client and multiple joint learning Internet of Things platforms, that is, by arranging the model database to be called on each joint learning Internet of Things platform, any of which can provide services for the client and realize the call of the model in the model database. It can also be understood that in the above two scenarios, each joint learning Internet of Things platform can be provided with a model database and a control layer. At least one joint learning model is stored in the model database, and the control layer can realize the call of the model in the model database based on the call request of the client. Here, the joint learning Internet of Things platform is equivalent to the server.

[0024] Step 102 , determining whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database.

[0025] In some embodiments, the execution subject may determine whether there is a model corresponding to the smoke oxygen content prediction model request in the model database. Here, before calling the model, it is necessary to determine whether there is a smoke oxygen content prediction model corresponding to the smoke oxygen content prediction model request in the model database. Only if there is a model in the model database can the model call be realized.

[0026] In some optional implementations of some embodiments, the model database includes the model to be called and the model information of each of the models to be called; specifically, it can be judged whether there is a flue gas oxygen content prediction model corresponding to the flue gas oxygen content prediction model request in the model database in the following way: according to the model information of each of the models to be called, it is judged whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database.

[0027] The model database is used to store the models to be called and the model information of the models to be called. Specifically, the models to be called are joint learning models. The model information is used to describe the information of the models to be called, such as the purpose of the model, the name of the model, the number of model downloads, the model download user, the source of model training data, the amount of model training data, the model accuracy, the model generation time, the number of model updates, and other information.

[0028] Specifically, according to the model information of the model to be called, it is determined whether the model to be called is the model corresponding to the flue gas oxygen content prediction model request. In practical applications, if the model information contains the name of the flue gas oxygen content prediction model, or a word with the same meaning as the name of the flue gas oxygen content prediction model but with a different expression, it means that the model to be called corresponding to the model information is the model corresponding to the flue gas oxygen content prediction model request. At this time, the model corresponding to the flue gas oxygen content prediction model request can be extracted from the model database to complete the model call.

[0029] Step 103 , determining a flue gas oxygen content prediction model according to a result of determining whether a model corresponding to the flue gas oxygen content prediction model request exists in the model database.

[0030] In some embodiments, the execution entity may determine the flue gas oxygen content prediction model according to a result of determining whether a model corresponding to the flue gas oxygen content prediction model request exists in the model database.

[0031] In some optional implementations of some embodiments, the judgment result includes that a model corresponding to the flue gas oxygen content prediction model request exists in the model database; then step 103 includes:

[0032] A model corresponding to the flue gas oxygen content prediction model request is determined from the model database, and the model corresponding to the flue gas oxygen content prediction model request is determined as the flue gas oxygen content prediction model.

[0033] In some feasible implementations, the judgment result includes that the model corresponding to the flue gas oxygen content prediction model request does not exist in the model database; then step 103 includes the following steps:

[0034] Selecting a joint object corresponding to the gas boiler from a joint learning alliance;

[0035] Joint learning is performed according to the model training data sets of each of the joint objects to construct a joint model, and the joint model is determined as a flue gas oxygen content prediction model.

[0036] Each energy station is a node in the Internet of Things and is provided with a client. If the data in the energy station is used for joint learning, the energy station is called a joint energy station, the gas boiler in the energy station is called a joint gas boiler, and the client corresponding to the energy station is called a joint learning client. Among them, joint learning ensures that user privacy data is protected to the maximum extent through distributed training and encryption technology to enhance user trust in artificial intelligence technology. In an embodiment of the present application, under the joint learning mechanism, each participant (the joint learning client corresponding to each joint object) contributes the encrypted data model to the alliance to jointly train a joint model. The gas boiler operation data of the joint object is uploaded to the corresponding joint learning client, and the joint learning client stores the gas boiler operation data.

[0037] Specifically, the federated learning alliance can be understood as a set of all objects that can participate in the federated learning, in other words, the federated gas boilers.

[0038] In this embodiment, when there is no model corresponding to the flue gas oxygen content prediction model request in the model database, a model needs to be built at this time. From the joint learning alliance, a joint gas boiler similar to the gas boiler in the energy station is determined, and these joint gas boilers are respectively determined as joint objects; then, joint learning is performed based on the model training data sets of each joint object to build a joint model. The model training data set includes the gas boiler operation data of the joint object. Specifically, the gas boiler operation data includes the switch state, gas flow, gas temperature, gas pressure, air temperature, air flow, feed water flow, feed water temperature, main steam pressure, main steam temperature, main steam flow and historical flue gas oxygen content (label). It should be understood that the model training data is data after data preprocessing. Here, data preprocessing includes but is not limited to outlier removal, missing value filling, normalization processing and delay processing. Among them, normalization processing refers to uniformly mapping the data to the [0,1] interval. Delay processing refers to moving the time point of the data forward by the delay time, thereby reducing the impact of equipment startup, wherein the delay time refers to the time when the equipment is started.

[0039] Step 104: predicting the flue gas oxygen content of the gas boiler in the energy station according to the flue gas oxygen content prediction model and the operating data of the gas boiler.

[0040] In some embodiments, the execution entity may predict the oxygen content of the flue gas of the gas boiler in the energy station based on the flue gas oxygen content prediction model and the operating data of the gas boiler.

[0041] Specifically, the operation data of the gas boiler is substituted into the flue gas oxygen content prediction model to predict the flue gas oxygen content of the gas boiler. It should be understood that the obtained flue gas oxygen content prediction model comprehensively considers the operation data of other gas boilers, so it has a relatively high accuracy and realizes model migration.

[0042] In some feasible implementations, there are multiple flue gas oxygen content prediction models. Based on the business information of the flue gas oxygen content prediction model, multiple flue gas oxygen content prediction models are screened to determine the target flue gas oxygen content. Based on the target flue gas oxygen content and the operating data of the gas boiler, the flue gas oxygen content of the gas boiler is predicted. It should be understood that the business information indicates the application of the model, and the reference value of the predicted flue gas oxygen content of the gas boiler is ensured based on the actual application of the model. It can be understood that the business information refers to the relevant information generated by the application of the flue gas oxygen content prediction model and the relevant information of the flue gas oxygen content prediction model itself. Specifically, the business information includes the number of model downloads, the model download user, the model training data source, the model training data volume, the model accuracy, the model generation time, and the number of model updates. Among them, the model accuracy is determined based on the feedback data uploaded by the user using the model, and the feedback data includes the predicted value and the actual value. It should be noted that the above business information is only used as an example. In actual applications, the business information can be diverse. The field names corresponding to the business information you want to obtain can be pre-set according to actual business needs, and encapsulated in the request so that the request carries the field content corresponding to the business information.

[0043] As a possible scenario, based on the business information of the flue gas oxygen content prediction model, multiple flue gas oxygen content prediction models are automatically screened to determine the target flue gas oxygen content model to improve user experience.

[0044] Specifically, the target flue gas oxygen content model can be determined in the following way:

[0045] In some possible cases, the flue gas oxygen content prediction model request carries the model requirements.

[0046] As another possible situation, the business information of the flue gas oxygen content prediction model is displayed to interact with the user, and the user selects the target flue gas oxygen content model to determine the target flue gas oxygen content model to meet the user's needs. Specifically, the target flue gas oxygen content model can be determined in the following way:

[0047] In the above embodiment, when there are multiple target flue gas oxygen content models, the flue gas oxygen content of the gas boiler predicted by each target flue gas oxygen content model is averaged to obtain the flue gas oxygen content of the gas boiler.

[0048] Furthermore, it also includes:

[0049] Acquire historical flue gas oxygen content of historical operation data matching the operation data of the gas boiler;

[0050] Determining the error of the predicted flue gas oxygen content of the gas boiler according to the historical flue gas oxygen content of the historical operation data;

[0051] The flue gas oxygen content prediction model is adjusted according to the predicted error of the flue gas oxygen content of the gas boiler.

[0052] In practical applications, multiple joint objects corresponding to the flue gas oxygen content prediction model are determined, and the flue gas oxygen content of historical operating data that is identical or similar to the operating data of the gas boiler is determined from the model training data sets of each of the multiple joint objects, with priority given to the identical ones. By comparing the flue gas oxygen content of the historical operating data with the predicted flue gas oxygen content of the gas boiler, the error of the predicted flue gas oxygen content of the gas boiler is determined, and based on multiple errors, it is decided whether to continue joint learning. If the error is large, joint learning is continued, and the joint learning Internet of Things platform redefines the model parameters based on the error and performs model iteration.

[0053] In some optional implementations of this embodiment, in response to the oxygen content of the flue gas being greater than a preset threshold, an alarm message is sent to a terminal device with a display function corresponding to the gas boiler and displayed.

[0054] Some embodiments of the present disclosure disclose a method for predicting the flue gas oxygen content of a gas boiler, first, obtaining a flue gas oxygen content prediction model request and a model database of the gas boiler in the energy station; then, determining whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database; thereafter, determining the flue gas oxygen content prediction model according to the judgment result of whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database; finally, predicting the flue gas oxygen content of the gas boiler in the energy station according to the flue gas oxygen content prediction model and the operating data of the gas boiler. In summary, through the technical solution of the present invention, there is no need to use a sensor to measure the flue gas oxygen content, and the flue gas oxygen content can be predicted in real time, which is convenient for maintenance and reduces measurement errors. At the same time, the combined flue gas oxygen content prediction model relies on real data and is not easily affected by the external environment, so the flue gas oxygen content can be determined more accurately.

[0055] It should be understood that the order of execution of the steps in the above embodiment does not necessarily 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 embodiment of the present invention.

[0056] Figure 1What is shown is only a basic embodiment of the method of the present invention. By performing certain optimization and expansion on this basis, other preferred embodiments of the method can be obtained.

[0057] like Figure 2 FIG. 1 is another specific embodiment of the method for predicting the oxygen content of flue gas of a gas boiler according to the present invention. Based on the above embodiments, this embodiment is described in more detail in combination with application scenarios.

[0058] The specific scenario combined with this embodiment is: assuming that there are three energy stations (several gas boilers in the energy stations are similar) and a joint learning Internet of Things platform T, the three energy stations are joint energy station A, joint energy station B and energy station C, the joint learning Internet of Things platform T interacts with the joint learning client Ac, the joint learning client Bc and the prediction client Cc, wherein the joint energy stations A and B have relatively rich data, and can use their own gas boiler operation data to train the local flue gas oxygen content prediction model, that is, the contributor of the joint learning model; the gas boiler in the energy station C has no exhaust gas oxygen content measurement point; the joint learning client Ac stores the operation data of the gas boilers A1, A2, and A3 in the joint energy station A, the joint learning client Bc stores the operation data of the gas boilers B1, B2, and B3 in the joint energy station B, and the prediction client Cs stores the operation data of the gas boilers C1, C2, and C3 in the energy station C; the joint learning client Ac, the joint learning client Bc and the prediction client Cc are deployed on the local operation and maintenance servers As, Bc, and Cc, respectively, where the local operation and maintenance server refers to the server used for gas boiler operation and maintenance. The method described in this embodiment aims to determine a model for predicting the exhaust oxygen content of a gas boiler by combining the model database and the relationship in the model corresponding to the flue gas oxygen content model request.

[0059] The method described in this embodiment comprises the following steps:

[0060] Step 201: Obtain a flue gas oxygen content prediction model request and a model database for a gas boiler in an energy station.

[0061] Energy station C initiates a request for a flue gas oxygen content prediction model for gas boiler C1 to the federated learning IoT platform T through the API interface via the prediction client Cc deployed on the local operation and maintenance server Cs, i.e., a flue gas oxygen content prediction model request.

[0062] The federated learning IoT platform T contains a model database, which includes multiple models to be called and model information corresponding to each model to be called.

[0063] Step 202: determine whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database. If yes, execute step 2031a; if not, execute step 2032a.

[0064] For each model to be called, according to the model information corresponding to the model to be called, it is determined whether the model to be called matches the model corresponding to the flue gas oxygen content prediction model request. If it matches, it indicates whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database.

[0065] Step 2031a: determine the model corresponding to the flue gas oxygen content prediction model request from the model database, and determine the model corresponding to the flue gas oxygen content prediction model request as the flue gas oxygen content prediction model.

[0066] Step 2031b: acquiring the business information of each of the flue gas oxygen content prediction models according to the model database; and determining the target flue gas oxygen content prediction model from the flue gas oxygen content prediction models according to the business information of each of the flue gas oxygen content prediction models.

[0067] Step 2031c: predict the flue gas oxygen content of the gas boiler according to the target flue gas oxygen content prediction model and the operating data of the gas boiler.

[0068] The joint learning IoT platform T sends the target flue gas oxygen content prediction model to the prediction client Cc. The prediction client Cc downloads the target flue gas oxygen content prediction model to predict the flue gas oxygen content of the gas boiler C1, and feeds the predicted flue gas oxygen content back to the joint learning IoT platform T. The joint learning IoT platform T decides whether to iterate the target flue gas oxygen content prediction model.

[0069] Step 2032a: select a joint object corresponding to the gas boiler from the joint learning alliance; perform joint learning according to the model training data sets of each of the joint objects to construct a joint model; and determine the joint model as a flue gas oxygen content prediction model.

[0070] Assume that the joint objects are gas boilers A1, gas boiler A3, gas boiler B1, and gas boiler B2. The joint learning IoT platform T and the joint energy stations A and B conduct joint learning to obtain a joint model. Specifically, the joint learning client Ac performs model training based on the operating data of the gas boilers A1 and A3, and uploads the model parameters to the joint learning IoT platform T. The joint learning client Bc performs model training based on the operating data of the gas boilers B1 and B2, and uploads the model parameters to the joint learning IoT platform T. The joint learning IoT platform T sends the aggregated model parameters to the joint learning client Ac and the joint learning client Bc for model iteration. The joint learning client Ac and the joint learning client Bc each obtain a local model. The joint learning IoT platform T fuses the local models obtained by the joint learning client Ac and the joint learning client Bc to obtain a joint model.

[0071] Step 2032b: predict the flue gas oxygen content of the gas boiler in the energy station according to the flue gas oxygen content prediction model and the operating data of the gas boiler.

[0072] The joint learning IoT platform T sends the flue gas oxygen content prediction model to the prediction client Cc, and the prediction client Cc downloads the flue gas oxygen content prediction model to predict the flue gas oxygen content of the gas boiler C1.

[0073] Figure 3 It is a schematic diagram of a flue gas oxygen content prediction device for a gas boiler provided in an embodiment of the present invention; the above-mentioned flue gas oxygen content prediction device 300 for a gas boiler comprises: an acquisition module 301, a judgment module 302, a determination module 303 and a prediction module 304. Among them, the acquisition module 301 is configured to obtain a flue gas oxygen content prediction model request and a model database of a gas boiler in an energy station; the judgment module 302 is configured to determine whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database; the determination module 303 is configured to determine the flue gas oxygen content prediction model according to the judgment result of whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database; the prediction module 304 is configured to predict the flue gas oxygen content of the gas boiler in the energy station according to the flue gas oxygen content prediction model and the operation data of the gas boiler.

[0074] In some optional implementations of some embodiments, the above-mentioned model database includes the model to be called and the model information of each of the models to be called; the judgment whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database is further configured to: judge whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database according to the model information of each of the models to be called.

[0075] In some optional implementations of some embodiments, the judgment result includes whether the model corresponding to the flue gas oxygen content prediction model request exists in the model database; the flue gas oxygen content prediction model is determined based on the judgment result of whether the model corresponding to the flue gas oxygen content prediction model request exists in the model database, and is further configured to: determine the model corresponding to the flue gas oxygen content prediction model request from the model database, and determine the model corresponding to the flue gas oxygen content prediction model request as the flue gas oxygen content prediction model.

[0076] In some optional implementations of some embodiments, the judgment result includes that the model corresponding to the flue gas oxygen content prediction model request does not exist in the model database; the flue gas oxygen content prediction model is determined based on the judgment result of whether the model corresponding to the flue gas oxygen content prediction model request exists in the model database, and is further configured to: select a joint object corresponding to the gas boiler from a joint learning alliance; perform joint learning based on the model training data sets of each of the joint objects, construct a joint model, and determine the joint model as the flue gas oxygen content prediction model.

[0077] In some optional implementations of some embodiments, the prediction module 304 in the flue gas oxygen content prediction device 300 of the above-mentioned gas boiler is further configured to: obtain the business information of each of the flue gas oxygen content prediction models according to the model database; determine the target flue gas oxygen content prediction model from each of the flue gas oxygen content prediction models according to the business information of each of the flue gas oxygen content prediction models; predict the flue gas oxygen content of the gas boiler according to the target flue gas oxygen content prediction model and the operating data of the gas boiler.

[0078] In some optional implementations of some embodiments, the flue gas oxygen content prediction model is a joint learning model; it is further configured to: obtain historical flue gas oxygen content of historical operating data matching the operating data of the gas boiler; determine the error of the predicted flue gas oxygen content of the gas boiler based on the historical flue gas oxygen content of the historical operating data; adjust the flue gas oxygen content prediction model based on the error of the predicted flue gas oxygen content of the gas boiler.

[0079] In some optional implementations of some embodiments, the above-mentioned flue gas oxygen content prediction device 300 of the gas boiler is further configured to: in response to the flue gas oxygen content being greater than a preset threshold, send an alarm message to a terminal device with a display function corresponding to the gas boiler and display it.

[0080] It is understood that the units described in the device 300 are similar to those described in the reference Figure 1Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 300 and the units contained therein, and will not be described in detail here.

[0081] Figure 4 FIG. 1 is a schematic diagram of a flue gas oxygen content prediction device / terminal device for a gas boiler provided in one embodiment of the present invention. Figure 4 As shown, the flue gas oxygen content prediction device / terminal device 4 of the gas boiler of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps of the flue gas oxygen content prediction method embodiments of the gas boiler are implemented, such as Figure 1 Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 4 Functions of modules 401 to 404 are shown.

[0082] Exemplarily, the computer program 42 can be divided into one or more modules / units, and the one or more modules / units are stored in the memory 41 and executed by the processor 40 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program 42 in the flue gas oxygen content prediction device / terminal device 4 of the gas boiler. For example, the computer program 42 can be divided into a synchronization module, a summary module, an acquisition module, and a return module (module in the virtual device), and the specific functions of each module are as follows:

[0083] The gas boiler flue gas oxygen content prediction device / terminal device 4 can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The gas boiler flue gas oxygen content prediction device / terminal device can include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art can understand that Figure 4 It is only an example of the flue gas oxygen content prediction device / terminal equipment 4 of the gas boiler, and does not constitute a limitation of the flue gas oxygen content prediction device / terminal equipment 4 of the gas boiler. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the flue gas oxygen content prediction device / terminal equipment of the gas boiler may also include input and output devices, network access equipment, buses, etc.

[0084] The processor 40 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. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0085] The memory 41 may be an internal storage unit of the gas boiler flue gas oxygen content prediction device / terminal device 4, such as a hard disk or memory of the gas boiler flue gas oxygen content prediction device / terminal device 4. The memory 41 may also be an external storage device of the gas boiler flue gas oxygen content prediction device / terminal device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the gas boiler flue gas oxygen content prediction device / terminal device 4. Further, the memory 41 may also include both the internal storage unit and the external storage device of the gas boiler flue gas oxygen content prediction device / terminal device 4. The memory 41 is used to store the computer program and other programs and data required by the gas boiler flue gas oxygen content prediction device / terminal device. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0086] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be 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 in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in 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, which will not be repeated here.

[0087] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0088] 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. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0089] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0090] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0091] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0092] 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 invention 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 the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can 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 the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), 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.

[0093] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for predicting oxygen content in flue gas of a gas boiler, characterized in that: include: Obtain a flue gas oxygen content prediction model request and model database for a gas boiler in an energy station; Determine whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database, wherein, if the model information contains a flue gas oxygen content prediction model name or a word with the same meaning as the flue gas oxygen content prediction model name but with a different expression, it means that the model to be called corresponding to the model information is the model corresponding to the flue gas oxygen content prediction model request; Determining a flue gas oxygen content prediction model according to a result of determining whether a model corresponding to the flue gas oxygen content prediction model request exists in the model database; Predicting the flue gas oxygen content of the gas boiler in the energy station according to the flue gas oxygen content prediction model and the operating data of the gas boiler; The judgment result includes that the model corresponding to the flue gas oxygen content prediction model request does not exist in the model database; The determining of the flue gas oxygen content prediction model according to the judgment result of whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database comprises: Selecting a joint object corresponding to the gas boiler from a joint learning alliance; Joint learning is performed according to the model training data sets of each of the joint objects to construct a joint model, and the joint model is determined as a flue gas oxygen content prediction model.

2. The method for predicting oxygen content in flue gas of a gas boiler according to claim 1, characterized in that: The model database includes models to be called and model information of each model to be called; The determining whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database includes: According to the model information of each of the models to be called, it is determined whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database.

3. The method for predicting oxygen content in flue gas of a gas boiler according to claim 1, characterized in that: The judgment result includes that the model corresponding to the flue gas oxygen content prediction model request exists in the model database; The determining of the flue gas oxygen content prediction model according to the judgment result of whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database comprises: A model corresponding to the flue gas oxygen content prediction model request is determined from the model database, and the model corresponding to the flue gas oxygen content prediction model request is determined as the flue gas oxygen content prediction model.

4. The method for predicting oxygen content in flue gas of a gas boiler according to claim 3, characterized in that: The predicting of the flue gas oxygen content of the gas boiler in the energy station according to the flue gas oxygen content prediction model and the operation data of the gas boiler includes: According to the model database, obtaining the business information of each of the flue gas oxygen content prediction models; Determining a target flue gas oxygen content prediction model from each of the flue gas oxygen content prediction models according to the respective business information of each of the flue gas oxygen content prediction models; The oxygen content of the flue gas of the gas boiler is predicted according to the target flue gas oxygen content prediction model and the operating data of the gas boiler.

5. The method for predicting oxygen content in flue gas of a gas boiler according to claim 1, characterized in that: The flue gas oxygen content prediction model is a joint learning model; it also includes: Acquire historical flue gas oxygen content of historical operation data matching the operation data of the gas boiler; Determining the error of the predicted flue gas oxygen content of the gas boiler according to the historical flue gas oxygen content of the historical operation data; The flue gas oxygen content prediction model is adjusted according to the predicted error of the flue gas oxygen content of the gas boiler.

6. The method for predicting oxygen content in flue gas of a gas boiler according to claim 1, characterized in that: The method further comprises: In response to the oxygen content of the flue gas being greater than a preset threshold, an alarm message is sent to a terminal device with a display function corresponding to the gas boiler and displayed.

7. A device for predicting oxygen content in flue gas of a gas boiler, characterized in that: include: An acquisition module is configured to acquire a flue gas oxygen content prediction model request and a model database of a gas boiler in an energy station; a judgment module configured to judge whether there is a model corresponding to the flue gas oxygen content prediction model request in the model database, wherein when the model information contains a flue gas oxygen content prediction model name or a word having the same meaning as the flue gas oxygen content prediction model name but with a different expression, it indicates that the model to be called corresponding to the model information is the model corresponding to the flue gas oxygen content prediction model request; A determination module is configured to determine a flue gas oxygen content prediction model according to a determination result of whether a model corresponding to the flue gas oxygen content prediction model request exists in the model database; A prediction module, configured to predict the flue gas oxygen content of the gas boiler in the energy station according to the flue gas oxygen content prediction model and the operation data of the gas boiler; The judgment result includes that the model corresponding to the flue gas oxygen content prediction model request does not exist in the model database; the flue gas oxygen content prediction model is determined based on the judgment result of whether the model corresponding to the flue gas oxygen content prediction model request exists in the model database, and is further configured to: select a joint object corresponding to the gas boiler from a joint learning alliance; perform joint learning based on the model training data sets of each of the joint objects, construct a joint model, and determine the joint model as the flue gas oxygen content prediction model.

8. A terminal 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, the steps of the method according to any one of claims 1 to 6 are implemented.

9. 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 6 are implemented.

Images