A method and device for predicting oxygen content of boiler flue gas

Abstract

The present invention discloses a method, device, computer-readable storage medium and electronic device for predicting oxygen content in boiler flue gas. The method comprises: determining a probability distribution model of characteristic data of a source boiler and a probability distribution model of characteristic data of a target boiler, wherein the characteristic data of the source boiler is non-shared data; determining the weight of the characteristic data of the source boiler according to the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler; determining a flue gas oxygen content prediction soft measurement model according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler and the historical flue gas oxygen content corresponding to the characteristic data of the source boiler; predicting the flue gas oxygen content of the target boiler according to the flue gas oxygen content prediction soft measurement model. Through the technical solution provided by the present invention, the characteristic data of the source boiler is migrated to the target boiler, so that there is no need to share data between the source boiler and the target boiler, thereby ensuring data security.

Description

Technical Field

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

[0002] Flue gas oxygen content is closely related to boiler combustion efficiency, exhaust gas emissions, etc. When the flue gas oxygen content is too high, it will lead to an increase in pollutants (NOx, SOx, etc.) in exhaust gas emissions; when the flue gas oxygen content is too low, it will lead to incomplete fuel combustion and reduce boiler efficiency. Therefore, it is necessary to predict the flue gas oxygen content, which helps to improve combustion quality, reduce coal consumption, and help effectively control the air-coal ratio and improve boiler combustion efficiency.

[0003] At present, for the prediction of the target boiler without a label, the mapping relationship between the characteristic data of the target boiler and the flue gas oxygen content is established through data sharing between the target boiler and other multiple boilers, and the flue gas oxygen content prediction model is obtained. The flue gas oxygen content prediction model is used to realize the prediction of the flue gas oxygen content of the target boiler.

[0004] However, the above technical solution needs to share data between multiple boilers during the model process, which results in low data security between the multiple boilers. Summary of the invention

[0005] In view of the above-mentioned technical problems existing in the prior art, the present invention provides a method, device, computer-readable storage medium and electronic device for predicting the oxygen content of boiler flue gas, which migrate the characteristic data of the source boiler to the target boiler, so that there is no need to share data between the source boiler and the target boiler, thereby ensuring data security.

[0006] In a first aspect, the present invention provides a method for predicting oxygen content of boiler flue gas, comprising:

[0007] Acquire characteristic data of a source boiler, historical flue gas oxygen content corresponding to the characteristic data of the source boiler, and characteristic data of a target boiler, wherein the characteristic data of the source boiler is non-shared data;

[0008] Determining a probability distribution model of the characteristic data of the source boiler and a probability distribution model of the characteristic data of the target boiler;

[0009] determining a weight of the characteristic data of the source boiler according to a probability distribution model of the characteristic data of the source boiler and a probability distribution model of the characteristic data of the target boiler;

[0010] Determine a flue gas oxygen content prediction soft sensing model according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler, and the historical flue gas oxygen content corresponding to the characteristic data of the source boiler;

[0011] The flue gas oxygen content of the target boiler is predicted according to the flue gas oxygen content prediction soft measurement model.

[0012] In a second aspect, the present invention provides a device for predicting oxygen content in boiler flue gas, comprising:

[0013] A data acquisition module, used to acquire characteristic data of a source boiler, historical flue gas oxygen content corresponding to the characteristic data of the source boiler, and characteristic data of a target boiler, wherein the characteristic data of the source boiler is non-shared data;

[0014] A probability distribution model determination module, used to determine a probability distribution model of the characteristic data of the source boiler and a probability distribution model of the characteristic data of the target boiler;

[0015] A weight determination module, used to determine the weight of the characteristic data of the source boiler according to the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler;

[0016] A soft measurement model determination module, used to determine a flue gas oxygen content prediction soft measurement model according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler, and the historical flue gas oxygen content corresponding to the characteristic data of the source boiler;

[0017] The prediction module is used to predict the flue gas oxygen content of the target boiler according to the flue gas oxygen content prediction soft measurement model.

[0018] In a third aspect, the present invention provides a computer-readable storage medium, comprising execution instructions. When a processor of an electronic device executes the execution instructions, the processor executes any method described in the first aspect.

[0019] In a fourth aspect, the present invention provides an electronic device, comprising a processor and a memory storing execution instructions, wherein when the processor executes the execution instructions stored in the memory, the processor executes any method described in the first aspect.

[0020] The present invention provides a method, device, computer-readable storage medium and electronic device for predicting oxygen content in boiler flue gas. The method obtains characteristic data of a source boiler, historical flue gas oxygen content corresponding to the characteristic data of the source boiler and characteristic data of a target boiler, wherein the characteristic data of the source boiler is non-shared data, and then determines the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler, and then determines the weight of the characteristic data of the source boiler according to the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler, and then determines the flue gas oxygen content prediction soft measurement model according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler and the historical flue gas oxygen content corresponding to the characteristic data of the source boiler, and then predicts the flue gas oxygen content of the target boiler according to the flue gas oxygen content prediction soft measurement model. The technical solution provided by the present invention determines the weight of the characteristic data of the source boiler through the non-shared characteristic data probability distribution model of the source boiler and the probability distribution model of the characteristic data of the target boiler, establishes data association between the source boiler and the target boiler, migrates the characteristic data of the source boiler to the target boiler, and does not require data sharing between the source boiler and the target boiler, thereby ensuring data security.

[0021] The further effects of the above-mentioned non-conventional preferred manner will be described below in conjunction with specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the existing technical solutions, 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 recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0023] Figure 1 A schematic flow chart of a method for predicting oxygen content in boiler flue gas provided by one embodiment of the present invention;

[0024] Figure 2 A schematic flow chart of another method for predicting oxygen content in boiler flue gas provided by one embodiment of the present invention;

[0025] Figure 3 A schematic diagram of the structure of a device for predicting oxygen content in boiler flue gas provided by one embodiment of the present invention;

[0026] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] like Figure 1 As shown, an embodiment of the present invention provides a method for predicting flue gas oxygen content, which is applied to an edge node of a boiler to be predicted, and includes the following steps:

[0029] Step 101: Acquire characteristic data of a source boiler, historical flue gas oxygen content corresponding to the characteristic data of the source boiler, and characteristic data of a target boiler, wherein the characteristic data of the source boiler is non-shared data.

[0030] Specifically, the source boiler and the target boiler are both equipment that can generate flue gas. For example, the target boiler and the source boiler are both gas boilers, but information such as production units and equipment models may be different.

[0031] Specifically, there are multiple characteristic data of the target boiler, and each characteristic data includes several characteristics corresponding to the characteristic values ​​of the target boiler. Several characteristics are influencing factors that affect the oxygen content of the flue gas of the target boiler, which need to be determined in combination with the actual scenario. For example, if the target boiler is a gas boiler, the several characteristics include but are not limited to gas flow, gas temperature, exhaust temperature, flue gas flow, gas pressure, flue gas humidity and flue gas pressure.

[0032] Specifically, there are multiple feature data of the source boiler, and each feature data of the source boiler includes several features corresponding to feature values ​​of the source boiler, wherein several features are the same as features corresponding to the feature data of the target boiler.

[0033] It should be noted that the characteristic data of the source boiler is non-shared data, thereby ensuring the data security of the characteristic data of the source boiler.

[0034] Optionally, multiple characteristic data of the target boiler are obtained through the edge node corresponding to the target boiler. The edge node of the target boiler can be understood as a node that is closest to the target boiler and can perform data processing and data interaction. The node includes but is not limited to any one or more of an edge server, an edge gateway, and an edge controller.

[0035] Optionally, multiple characteristic data of the source boiler are obtained through the edge node corresponding to the source boiler. The edge node of the source boiler can be understood as the node closest to the source boiler and capable of data processing and data interaction. The node includes but is not limited to any one or more of an edge server, an edge gateway, and an edge controller. Correspondingly, if the characteristic data of the source boiler is non-shared data, it means that the characteristic data of the source boiler does not come out of the edge node corresponding to the source boiler.

[0036] Specifically, flue gas oxygen content refers to the oxygen content in the flue gas exhausted after fuel combustion.

[0037] Step 102: Determine a probability distribution model of the characteristic data of the source boiler and a probability distribution model of the characteristic data of the target boiler.

[0038] Specifically, the characteristic data of the target boiler obeys a continuous probability distribution. The continuous probability distribution model may be a normal distribution model or an exponential distribution model. The embodiment of the present invention does not limit this. Preferably, the probability distribution model of the characteristic data of the target boiler is a mixed Gaussian model formed by mixing multiple Gaussian distribution models, wherein the Gaussian model is also called a normal distribution model.

[0039] Specifically, the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler are both mixed Gaussian models. Of course, they can also be other probability distribution models, which need to be determined in combination with actual conditions and are not specifically limited here.

[0040] In one embodiment of the present invention, the determining of the probability distribution model of the characteristic data of the source boiler includes:

[0041] The data distribution of the characteristic data of the source boiler is calculated according to the parameter model, and the parameter model with the determined model parameters is determined as the probability distribution model of the characteristic data of the source boiler.

[0042] Specifically, the parameter model may be a mixed Gaussian model or an exponential distribution model. Preferably, the parameter model is a mixed Gaussian model.

[0043] Specifically, the probability distribution model of the characteristic data of the source boiler is obtained by substituting the characteristic data of the source boiler into a mixed Gaussian model to calculate and determine the model parameters, wherein the calculation method may be an EM algorithm, and then the mixed Gaussian model with the determined model parameters is determined as the probability distribution model of the characteristic data of the source boiler.

[0044] In one embodiment of the present invention, the determining of the probability distribution model of the characteristic data of the target boiler includes:

[0045] The data distribution of the characteristic data of the target boiler is calculated according to the mixed Gaussian model, and the mixed Gaussian model with determined model parameters is determined as the probability distribution model of the characteristic data of the target boiler.

[0046] Specifically, the probability distribution model of the characteristic data of the target boiler is obtained by substituting the characteristic data of the target boiler into a mixed Gaussian model to calculate and determine the model parameters, wherein the calculation method may be an EM algorithm, and then the mixed Gaussian model with the determined model parameters is determined as the probability distribution model of the characteristic data of the target boiler.

[0047] Step 103: Determine the weight of the characteristic data of the source boiler according to the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler.

[0048] In this embodiment, the weight of the characteristic data of the source boiler is determined by combining the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler, and a data association between the source boiler and the target boiler is established, thereby migrating the characteristic data of the source boiler to the target boiler. Here, the characteristic data of the source boiler is non-shared data, in other words, the source boiler will not directly obtain the characteristic data of the target boiler, that is, there is no data sharing between the target boiler and the source boiler, thereby ensuring data security.

[0049] In one embodiment, the weight of the characteristic data of the source boiler is determined specifically by the following method:

[0050] determining, according to a probability distribution model of the characteristic data of the source boiler, a distribution probability of the characteristic data of the source boiler relative to the source boiler;

[0051] Determining the distribution probability of the characteristic data of the source boiler relative to the target boiler according to the probability distribution model of the characteristic data of the target boiler;

[0052] The weight of the characteristic data of the source boiler is determined as the weight of the characteristic data of the source boiler by the probability ratio of the distribution probability of the characteristic data of the source boiler relative to the target boiler and the distribution probability relative to the source boiler.

[0053] In this embodiment, the weight of the characteristic data of the source boiler is determined by taking the distribution probability of the characteristic data of the source boiler relative to the target boiler and the approximate ratio of the distribution probability relative to the source boiler, and establishing a data association between the source boiler and the target boiler, thereby migrating the characteristic data of the source boiler to the target boiler. At the same time, there is no need to share the characteristic data of the source boiler and the target boiler, thereby ensuring data security.

[0054] Specifically, the characteristic data of the source boiler is substituted into the probability distribution model of the characteristic data of the source boiler, and the output value of the probability distribution model of the characteristic data of the source boiler is the distribution probability of the characteristic data of the source boiler relative to the source boiler.

[0055] Specifically, the characteristic data of the source boiler is substituted into the probability distribution model of the characteristic data of the target boiler, and the value output by the probability distribution model of the characteristic data of the target boiler is the distribution probability of the characteristic data of the source boiler relative to the target boiler.

[0056] Step 104 : determining a flue gas oxygen content prediction soft-sensing model according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler, and the historical flue gas oxygen content corresponding to the characteristic data of the source boiler.

[0057] In this embodiment, the relationship between the oxygen content of the flue gas of the target boiler and the boiler is established through the characteristic data of the source boiler, the weight of the characteristic data of the source boiler, and the historical flue gas content corresponding to the characteristic data of the source boiler, and the flue gas oxygen content prediction soft measurement model is determined. There is no need to share the characteristic data of the source boiler and the target boiler, thereby ensuring data security.

[0058] In one embodiment of the present invention, a flue gas oxygen content prediction soft sensor model is determined according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler, and the historical flue gas oxygen content corresponding to the characteristic data of the source boiler, including:

[0059] The preset model is trained according to the weight of the characteristic data of the source boiler relative to the target boiler and the historical flue gas content corresponding to the characteristic data of the source boiler, and the trained model is determined as a flue gas oxygen content prediction soft measurement model, which indicates the relationship between the characteristic data of the target boiler and the flue gas oxygen content.

[0060] Specifically, the edge node corresponding to the source boiler trains the preset model based on the characteristic data of the source boiler, the weight of the characteristic data of the source boiler corresponding to the target boiler, and the historical flue gas oxygen content corresponding to the characteristic data of the source boiler, and determines the trained preset model as a flue gas oxygen content prediction soft measurement model. The trained flue gas oxygen content prediction soft measurement model takes into account the weight of the characteristic data of the source boiler relative to the target boiler and therefore can indicate the relationship between the characteristic data of the target boiler and the flue gas oxygen content.

[0061] Specifically, the characteristic data of the source boiler and the weight of the characteristic data of the source boiler corresponding to the target boiler can realize the migration of the characteristic data of the source boiler to the target boiler. Subsequently, the parameters of the preset model are adjusted by the weights corresponding to the multiple characteristic data of the source boiler, so that the parameters of the adjusted preset model can reflect the relationship between the characteristic data of the target boiler and the oxygen content of the flue gas, and do not involve data sharing between the source boiler and the target boiler, thereby ensuring data security.

[0062] Specifically, the preset model can be any model in the prior art, such as a neural network model or a regression model, and is not specifically limited here.

[0063] Specifically, the preset model can be iterated in the following ways:

[0064] A1. Performing model training according to multiple characteristic data of the source boiler, historical flue gas oxygen content corresponding to the multiple characteristic data of the source boiler, and weights corresponding to the multiple characteristic data of the source boiler to determine a preset model;

[0065] A2. Determine whether the model error of the preset model meets the iteration condition. If so, determine the preset model as the final model and send it to the edge node of the target boiler. If not, execute A3.

[0066] A3. Send the model parameters of the preset model to the edge node of the target boiler;

[0067] A4. Receive the updated model parameters sent by the edge node of the target boiler, and adjust the updated model parameters according to the multiple feature data of the source boiler, the historical flue gas oxygen content corresponding to the multiple feature data of the source boiler, and the weights corresponding to the multiple feature data of the source boiler to determine the adjusted model parameters, replace the model parameters of the preset model with the adjusted model parameters, and execute A2.

[0068] It should be noted that the data of the target boiler and the source boiler are distributed in different edge nodes in the Internet of Things. Sharing data for model training will cause data security issues. The embodiment of the present invention calculates the weight of the characteristic data of the source boiler based on the data distribution of the characteristic data of the two edge nodes in the Internet of Things, thereby ensuring that in the process of obtaining the flue gas oxygen content prediction soft measurement model, the data between the target boiler and the source boiler does not leave their edge nodes in the Internet of Things, thereby ensuring the privacy of the data.

[0069] Step 105: predicting the flue gas oxygen content of the target boiler according to the flue gas oxygen content prediction soft measurement model.

[0070] Specifically, the current characteristic data of the target boiler is collected, and the current characteristic data is substituted into the flue gas oxygen content prediction to determine the flue gas oxygen content of the target boiler.

[0071] In order to better understand the data processing process between the edge node of the target boiler and the edge node of the source boiler, for example, assume that the edge node of the source boiler is set to A, and the edge node of the target boiler is set to B. B sends the probability distribution model of the characteristic data of the target boiler to A, and then, combined with the probability distribution model of the characteristic data of the source boiler locally in A, the weight of the characteristic data of the source boiler is determined. After that, the regression model is trained using the characteristic data of the source boiler, the weight of the characteristic data of the source boiler, and the historical flue gas oxygen content corresponding to the characteristic data of the source boiler to obtain a flue gas oxygen content prediction soft measurement model, and the flue gas oxygen content prediction soft measurement model is sent to B, and B predicts the flue gas oxygen content of the target boiler through the flue gas oxygen content prediction soft measurement model.

[0072] It can be seen from the above technical solutions that the embodiments of the present invention have at least the following effective effects: through the probability distribution model of the characteristic data of the target boiler and the probability distribution model of the characteristic data of the source boiler, the weight of the characteristic data of the source boiler is determined, and the data association between the source boiler and the target boiler is established, and the characteristic data of the source boiler is migrated to the target boiler without sharing the characteristic data between the source boiler and the target boiler, thereby ensuring data security.

[0073] Figure 1 What 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.

[0074] In order to more clearly illustrate the technical solution of the present invention, please refer to Figure 2 The embodiment of the present invention provides another method for predicting the oxygen content of boiler flue gas. This embodiment is further described based on the above embodiment and combined with a specific application scenario. In this embodiment, the following steps may be specifically included:

[0075] Step 201: Acquire characteristic data of a source boiler, historical flue gas oxygen content corresponding to the characteristic data of the source boiler, and characteristic data of a target boiler, wherein the characteristic data of the source boiler is non-shared data.

[0076] Assume that the edge node corresponding to the source boiler is A, and the edge node corresponding to the target boiler is B. A can obtain all the feature data of the source boiler, and B can obtain all the feature data of the target boiler.

[0077] Step 202: Calculate the data distribution of the characteristic data of the source boiler according to the mixed Gaussian model, and determine the mixed Gaussian model with the determined model parameters as the probability distribution model of the characteristic data of the source boiler; calculate the data distribution of the characteristic data of the target boiler according to the mixed Gaussian model, and determine the mixed Gaussian model with the determined model parameters as the probability distribution model of the characteristic data of the target boiler.

[0078] A calculates the data distribution of the characteristic data of the source boiler according to the mixed Gaussian model, thereby obtaining a probability distribution model of the characteristic data of the source boiler.

[0079] B calculates the probability distribution model of the characteristic data of the target boiler based on the mixed Gaussian model, thereby obtaining the probability distribution model of the characteristic data of the target boiler, and sends the probability distribution model of the characteristic data of the target source boiler to A.

[0080] It should be noted that the mixed Gaussian model for calculating the data distribution of the characteristic data of the source boiler and the mixed Gaussian model for calculating the data distribution of the characteristic data of the target boiler may be different, for example, the number of Gaussian models included is different.

[0081] Step 203: Determine the distribution probability of the characteristic data of the source boiler relative to the target boiler based on the probability distribution model of the characteristic data of the source boiler, and determine the distribution probability of the characteristic data of the source boiler relative to the source boiler based on the probability distribution model of the characteristic data of the target boiler.

[0082] A receives the probability distribution model of the characteristic data of the target boiler sent by B, and substitutes the characteristic data of the source boiler obtained by A into the probability distribution model of the characteristic data of the target boiler to obtain the distribution probability of the characteristic data of the source boiler relative to the target boiler.

[0083] A obtains the distribution probability of the characteristic data of the source boiler relative to the source boiler by substituting the characteristic data of the source boiler into the probability distribution model of the characteristic data of the local source boiler.

[0084] Step 204: Determine the weight of the characteristic data of the source boiler by taking the probability ratio of the distribution probability of the characteristic data of the source boiler relative to the target boiler and the distribution probability relative to the source boiler.

[0085] A determines the weight of the characteristic data of the source boiler as the probability ratio of the distribution probability of the characteristic data of the source boiler relative to the target boiler and the distribution probability relative to the source boiler, and obtains the weight of the characteristic data of the source boiler, so that the data connection between the origin boiler and the target boiler can be established.

[0086] Step 205: Perform preset model training based on the characteristic data of the source boiler, the weight of the characteristic data of the source boiler relative to the target boiler, and the historical flue gas oxygen content corresponding to the characteristic data of the source boiler, and determine the trained preset model as the flue gas oxygen content prediction soft measurement model.

[0087] A trains a preset model according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler relative to the target boiler, and the historical flue gas oxygen content corresponding to the characteristic data of the source boiler, determines the trained preset model as the flue gas oxygen content prediction soft measurement model, and sends the flue gas oxygen content prediction soft measurement model to B.

[0088] Step 206: predict the flue gas oxygen content of the target boiler according to the flue gas oxygen content prediction soft measurement model.

[0089] B receives the flue gas oxygen content prediction soft measurement model sent by A, and uses the flue gas oxygen content prediction soft measurement model to predict the boiler flue gas oxygen content of the target boiler.

[0090] It can be seen from the above technical scheme that the beneficial effects of this embodiment are: according to the probability distribution model of the characteristic data of the target boiler and the probability distribution model of the characteristic data of the source boiler respectively possessed by the two edge nodes in the Internet of Things, the weight of the characteristic data of the source boiler is determined, and the data association between the source boiler and the target boiler is established, and the data on the source boiler is migrated to the target boiler, thereby realizing that the nodes of the target boiler and the source boiler do not involve data sharing, and the data between the target boiler and the source boiler do not leave their edge nodes in the Internet of Things, thereby ensuring the privacy of the data.

[0091] Based on the same concept as the method for predicting the oxygen content of boiler flue gas provided in the embodiment of the present invention, please refer to Figure 3 The present invention implements a boiler flue gas oxygen content prediction device, comprising:

[0092] A data acquisition module 301 is used to acquire characteristic data of a source boiler, historical flue gas oxygen content corresponding to the characteristic data of the source boiler, and characteristic data of a target boiler, wherein the characteristic data of the source boiler is non-shared data;

[0093] A probability distribution model determination module 302 is used to determine a probability distribution model of characteristic data of a target boiler and a probability distribution model of characteristic data of a source boiler;

[0094] A weight determination module 303, configured to determine the weight of the characteristic data of the source boiler according to the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler;

[0095] A soft measurement model determination module 304 is used to determine a flue gas oxygen content prediction soft measurement model according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler, and the historical flue gas oxygen content corresponding to the characteristic data of the source boiler;

[0096] The prediction module 305 is used to predict the flue gas oxygen content of the target boiler according to the flue gas oxygen content prediction soft measurement model.

[0097] In one embodiment of the present invention, the weight determination module 303 includes: a first distribution probability determination unit, a second distribution probability determination unit and a weight determination unit; wherein,

[0098] The first distribution probability determination unit is used to determine the distribution probability of the characteristic data of the source boiler relative to the source boiler according to the probability distribution model of the characteristic data of the source boiler;

[0099] The second distribution probability determination unit is used to determine the distribution probability of the characteristic data of the source boiler relative to the target boiler according to the probability distribution model of the characteristic data of the target boiler;

[0100] The weight determination unit is used to determine the ratio of the distribution probability of the characteristic data of the source boiler relative to the target boiler and the distribution probability relative to the source boiler as the weight of the characteristic data of the source boiler.

[0101] In one embodiment of the present invention, the probability distribution model determination module 302 includes: a first probability distribution model determination unit and a second probability distribution model determination unit; wherein,

[0102] The first probability distribution model determination unit is used to calculate the data distribution of the characteristic data of the source boiler according to the parameter model, and determine the parameter model with the determined model parameters as the probability distribution model of the characteristic data of the source boiler.

[0103] The second probability distribution model determination unit is used to calculate the data distribution of the characteristic data of the target boiler according to the mixed Gaussian model, and determine the mixed Gaussian model with determined model parameters as the probability distribution model of the characteristic data of the target boiler.

[0104] In one embodiment of the present invention, the parameter model includes a mixed Gaussian model.

[0105] In one embodiment of the present invention, the soft measurement model determination module 304 is used to perform model training on a preset model based on the characteristic data of the source boiler, the weight of the characteristic data of the source boiler relative to the target boiler, and the historical flue gas content corresponding to the characteristic data of the source boiler, and determine the trained preset model as a flue gas oxygen content prediction soft measurement model, wherein the flue gas oxygen content prediction soft measurement model indicates the relationship between the characteristic data of the target boiler and the flue gas oxygen content.

[0106] In one embodiment of the present invention, the prediction model includes a neural network model or a regression model.

[0107] Figure 4 It is a structural diagram of an electronic device provided by an embodiment of the present invention. At the hardware level, the electronic device includes a processor 401 and a memory 402 storing execution instructions, and optionally also includes an internal bus 403 and a network interface 404. Among them, the memory 402 may include a memory 4021, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory 4022 (non-volatile memory), such as at least one disk storage, etc.; the processor 401, the network interface 404 and the memory 402 can be interconnected through an internal bus 403, and the internal bus 403 can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc.; the internal bus 403 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of bus. Of course, the electronic device may also include hardware required for other services. When the processor 401 executes the execution instruction stored in the memory 402, the processor 401 executes the method in any embodiment of the present invention, and is at least used to execute the following steps: Figure 1 or Figure 2 The method shown.

[0108] In a possible implementation, the processor reads the corresponding execution instruction from the non-volatile memory into the memory and then runs it, and can also obtain the corresponding execution instruction from other devices to form a prediction device for the oxygen content of boiler flue gas at the logical level. The processor executes the execution instruction stored in the memory to implement a prediction method for the oxygen content of boiler flue gas provided in any embodiment of the present invention through the execution of the execution instruction.

[0109] The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or instructions in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present invention can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0110] The embodiment of the present invention further provides a computer-readable storage medium, including an execution instruction. When a processor of an electronic device executes the execution instruction, the processor executes the method provided in any embodiment of the present invention. The electronic device may be specifically as follows: Figure 4 The electronic device shown; the execution instruction is a computer program corresponding to a method for predicting the oxygen content of boiler flue gas.

[0111] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods or computer program products. Therefore, the present invention may be implemented in the form of a complete hardware embodiment, a complete software embodiment, or a combination of software and hardware.

[0112] The multiple embodiments of the present invention are described in a progressive manner, and the same or similar parts between the multiple embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0113] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0114] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A method for predicting oxygen content in boiler flue gas, characterized in that: include: Acquire characteristic data of a source boiler, historical flue gas oxygen content corresponding to the characteristic data of the source boiler, and characteristic data of a target boiler, wherein the characteristic data of the source boiler is non-shared data; Determining a probability distribution model of the characteristic data of the source boiler and a probability distribution model of the characteristic data of the target boiler; determining a weight of the characteristic data of the source boiler according to a probability distribution model of the characteristic data of the source boiler and a probability distribution model of the characteristic data of the target boiler; Determine a flue gas oxygen content prediction soft sensing model according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler, and the historical flue gas oxygen content corresponding to the characteristic data of the source boiler; Predicting the flue gas oxygen content of the target boiler according to the flue gas oxygen content prediction soft measurement model; The step of determining the weight of the characteristic data of the source boiler according to the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler comprises: determining, according to a probability distribution model of the characteristic data of the source boiler, a distribution probability of the characteristic data of the source boiler relative to the source boiler; Determining the distribution probability of the characteristic data of the source boiler relative to the target boiler according to the probability distribution model of the characteristic data of the target boiler; Determine the weight of the characteristic data of the source boiler by the ratio of the distribution probability of the characteristic data of the source boiler relative to the target boiler and the distribution probability relative to the source boiler; The step of determining the flue gas oxygen content prediction soft sensor model according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler, and the historical flue gas oxygen content corresponding to the characteristic data of the source boiler includes: The preset model is trained according to the weight of the characteristic data of the source boiler relative to the target boiler and the historical flue gas content corresponding to the characteristic data of the source boiler, and the trained preset model is determined as a flue gas oxygen content prediction soft measurement model, which indicates the relationship between the characteristic data of the target boiler and the flue gas oxygen content.

2. The method according to claim 1, characterized in that The determining of the probability distribution model of the characteristic data of the source boiler comprises: The data distribution of the characteristic data of the source boiler is calculated according to the parameter model, and the parameter model with the determined model parameters is determined as the probability distribution model of the characteristic data of the source boiler.

3. The method according to claim 2, characterized in that The parameter model includes a Gaussian mixture model.

4. The method according to claim 1, characterized in that: The determining of the probability distribution model of the characteristic data of the target boiler comprises: The data distribution of the characteristic data of the target boiler is calculated according to the mixed Gaussian model, and the mixed Gaussian model with determined model parameters is determined as the probability distribution model of the characteristic data of the target boiler.

5. The method according to claim 1, characterized in that The preset model includes a neural network model or a regression model.

6. A device for predicting oxygen content in boiler flue gas, characterized in that: include: A data acquisition module, used to acquire characteristic data of a source boiler, historical flue gas oxygen content corresponding to the characteristic data of the source boiler, and characteristic data of a target boiler, wherein the characteristic data of the source boiler is non-shared data; A probability distribution model determination module, used to determine a probability distribution model of the characteristic data of the source boiler and a probability distribution model of the characteristic data of the target boiler; A weight determination module, used to determine the weight of the characteristic data of the source boiler according to the probability distribution model of the characteristic data of the source boiler and the probability distribution model of the characteristic data of the target boiler; A soft measurement model determination module, used to determine a flue gas oxygen content prediction soft measurement model according to the characteristic data of the source boiler, the weight of the characteristic data of the source boiler, and the historical flue gas oxygen content corresponding to the characteristic data of the source boiler; A prediction module, used for predicting the flue gas oxygen content of the target boiler according to the flue gas oxygen content prediction soft measurement model; The weight determination module is specifically used to: determine the distribution probability of the characteristic data of the source boiler relative to the source boiler according to the probability distribution model of the characteristic data of the source boiler; determine the distribution probability of the characteristic data of the source boiler relative to the target boiler according to the probability distribution model of the characteristic data of the target boiler; determine the ratio of the distribution probability of the characteristic data of the source boiler relative to the target boiler and the distribution probability relative to the source boiler as the weight of the characteristic data of the source boiler; The soft measurement model determination module is specifically used to: perform model training on a preset model according to the weight of the characteristic data of the source boiler relative to the target boiler and the historical flue gas content corresponding to the characteristic data of the source boiler, and determine the trained preset model as a flue gas oxygen content prediction soft measurement model, wherein the flue gas oxygen content prediction soft measurement model indicates the relationship between the characteristic data of the target boiler and the flue gas oxygen content.

7. A readable medium comprising an execution instruction. When a processor of an electronic device executes the execution instruction, the electronic device executes the method according to any one of claims 1 to 5.

8. An electronic device, comprising a processor and a memory storing execution instructions, wherein when the processor executes the execution instructions stored in the memory, the processor executes the method according to any one of claims 1 to 5.

Images