Boiler flue gas temperature data correction method and system based on hydrodynamic analysis

Abstract

The invention relates to a boiler flue gas temperature data correction method and system based on hydrodynamic analysis, and belongs to the technical field of boiler flue gas temperature correction. The method comprises the following steps: acquiring historical operation parameters of a boiler, modeling through hydrodynamic analysis to obtain a flue gas temperature field turbulence model, and solving the flue gas temperature field turbulence model through CFD software to obtain a flue gas temperature simulation value; according to the flue gas temperature simulation value and actually measured flue gas temperature data under the corresponding simulation condition, a boiler flue gas temperature data set is constructed through data preprocessing; according to the boiler flue gas temperature data set, a boiler flue gas temperature correction model is obtained through improved DNN network training and testing; boiler flue gas temperature data are detected in real time, and the boiler flue gas correction temperature is obtained through the boiler flue gas temperature correction model, so that boiler flue gas temperature measurement errors caused by factors such as cold surface radiation are reduced, rapid and accurate boiler flue gas correction temperature prediction is achieved, and combustion process control in boiler operation is optimized.

Description

Technical Field

[0001] The present invention belongs to the technical field of boiler flue gas temperature correction, and in particular relates to a boiler flue gas temperature data correction method and system based on fluid dynamics analysis. Background Art

[0002] In boiler operation, accurate measurement of flue gas temperature is crucial for optimizing the combustion process, improving thermal efficiency, and reducing pollutant emissions. However, the complex thermal flow field and radiation effect inside the boiler can cause errors in the measured flue gas temperature data, especially the influence of cold surface radiation. Cold surface radiation error is the influence of high-temperature heating surfaces inside the boiler (such as water-cooled walls, superheaters, etc.) on flue gas temperature measurement.

[0003] At present, although the standard method of boiler thermal calculation and the fluid dynamic analysis simulation method can predict the flue gas temperature to a certain extent, these methods have the following problems when dealing with cold surface radiation errors: The traditional standard method of boiler thermal calculation relies on simplified models and empirical formulas, which makes it difficult to accurately consider the impact of cold surface radiation. Although the fluid dynamic analysis simulation method can analyze the flue gas temperature field inside the boiler in detail, the calculation cost is high, time-consuming, and there are still challenges in dealing with complex radiation problems.

[0004] Therefore, there is an urgent need for an efficient and accurate boiler flue gas temperature data correction method and system that can reduce the cold surface radiation error while reducing the calculation cost and time. Summary of the invention

[0005] In order to solve the above problems existing in the prior art, the present invention proposes a boiler flue gas temperature data correction method and system based on fluid dynamics analysis.

[0006] The purpose of the present invention can be achieved by the following technical solutions: A boiler flue gas temperature data correction method based on fluid dynamics analysis, comprising: Obtain historical operating parameters of the boiler, obtain a flue gas temperature field turbulence model through fluid dynamics analysis modeling based on the historical operating parameters of the boiler, and solve the flue gas temperature field turbulence model through CFD software to obtain a flue gas temperature simulation value; Constructing a boiler flue gas temperature data set through data preprocessing according to the flue gas temperature simulation value and the measured flue gas temperature data under the corresponding simulation conditions; According to the boiler flue gas temperature data set, a boiler flue gas temperature correction model is obtained by improving DNN network training and testing; The boiler flue gas temperature data is detected in real time, and the boiler flue gas correction temperature is obtained through the boiler flue gas temperature correction model according to the boiler flue gas temperature data.

[0007] Preferably, the flue gas temperature field turbulence model obtained by fluid dynamics analysis modeling according to the historical operating parameters of the boiler includes: According to the three-dimensional structure of the boiler, a three-dimensional model of the boiler is established through CFD meshing; The flue gas temperature field turbulence model is obtained through the SST k-ω turbulence model according to the three-dimensional model of the boiler and the historical operating parameters of the boiler. The historical operating parameters of the boiler include but are not limited to load, air volume, air temperature, coal volume, burnout air inclination angle, and burnout air opening.

[0008] Preferably, the flue gas temperature field turbulence model satisfies the conservation of flue gas mass, the conservation of flue gas energy and the conservation of flue gas momentum.

[0009] Preferably, the measured flue gas temperature data includes measured flue gas temperature data value, radiation factor data, boiler operation parameters, and the radiation factor data includes but is not limited to ash wall temperature, wall porosity, and wall radiation exchange amount.

[0010] Preferably, constructing a boiler flue gas temperature data set through data preprocessing according to the flue gas temperature simulation value and the measured flue gas temperature data under the corresponding simulation conditions includes: A turbulence model of the flue gas temperature field was constructed using CFD software for numerical simulation. Multiple sets of flue gas temperature simulation values ​​were collected. At the same time, the measured flue gas temperature data under the corresponding simulation conditions were collected. The data were then cleaned and normalized to construct a high-quality boiler flue gas temperature data set.

[0011] Preferably, the improved DNN network includes an input layer, a hidden layer, and an output layer. The input layer receives the measured flue gas temperature data under the simulation conditions corresponding to the flue gas temperature simulation value. The hidden layer captures the complex patterns and relationships in the input data through a nonlinear activation function. The output layer outputs the boiler flue gas corrected temperature. A batch normalization layer is added after the hidden layer, and a structural norm regularization term is added during the training process to reduce overfitting.

[0012] A boiler flue gas temperature data correction system based on fluid dynamics analysis, the system is applied to the boiler flue gas temperature data correction method based on fluid dynamics analysis as described above, comprising a boiler flue gas temperature data acquisition module, a fluid dynamics analysis module, a data set construction module, an improved DNN network module, and a boiler flue gas temperature correction module; the boiler flue gas temperature data acquisition module is used to monitor the measured flue gas temperature data in real time; The fluid dynamics analysis module is used to obtain the historical operating parameters of the boiler and obtain the flue gas temperature field turbulence model through fluid dynamics analysis modeling, and solve the flue gas temperature field turbulence model through CFD software to obtain the flue gas temperature simulation value; The data set construction module is used to construct a boiler flue gas temperature data set through data preprocessing according to the flue gas temperature simulation value and the measured flue gas temperature data under the corresponding simulation conditions; The improved DNN network module is used to construct an improved DNN network, and a boiler flue gas temperature correction model is obtained through training and testing the improved DNN network according to the boiler flue gas temperature data set; The boiler flue gas temperature correction module is used to input boiler flue gas temperature data detected in real time, and obtain boiler flue gas correction temperature through the boiler flue gas temperature correction model.

[0013] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the boiler flue gas temperature data correction method based on fluid dynamics analysis is implemented.

[0014] A storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute the boiler flue gas temperature data correction method based on fluid dynamic analysis when executed by a computer processor.

[0015] The beneficial effects of the present invention are: (1) Through fluid dynamics analysis and numerical simulation with CFD software, the distribution of the flue gas temperature field inside the boiler can be modeled more accurately, thereby improving the accuracy of flue gas temperature measurement. By improving the DNN network training and testing, the boiler flue gas temperature correction model is obtained, which can effectively reduce the measurement error caused by factors such as cold surface radiation, realize the correction of the measured flue gas temperature, and provide more accurate data support for boiler operation, which helps to optimize the combustion process, improve boiler efficiency and energy saving effects, and at the same time improve the safety of boiler operation.

[0016] (2) The boiler flue gas temperature correction model is obtained through the improved DNN network. A batch normalization layer is added after the hidden layer of the DNN network to improve the training stability. The structural norm regularization term is added during the training process. By penalizing the network weights, the network complexity can be limited, thereby reducing the risk of overfitting and improving the generalization ability and prediction accuracy of the boiler flue gas temperature correction model. At the same time, the improved model can better adapt to different boiler operating conditions and maintain a high prediction accuracy even when the operating conditions change greatly.

[0017] (3) The boiler flue gas temperature correction model is used to correct the measured boiler flue gas temperature data. This solves the problem that the traditional boiler thermal calculation standard method relies on simplified models and empirical formulas, and solves the problem that the fluid dynamic analysis simulation method has high calculation cost and long time consumption. At the same time, the influence of cold surface radiation on boiler flue gas temperature measurement is taken into account. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0019] Figure 1 The figure is a flow chart of a boiler flue gas temperature data correction method based on fluid dynamics analysis according to the present invention. DETAILED DESCRIPTION

[0020] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0021] See also Figure 1 , a boiler flue gas temperature data correction method based on fluid dynamics analysis, comprising: S1: Obtain historical operating parameters of the boiler, obtain a flue gas temperature field turbulence model through fluid dynamics analysis modeling according to the historical operating parameters of the boiler, and solve the flue gas temperature field turbulence model through CFD software to obtain a flue gas temperature simulation value; S2: constructing a boiler flue gas temperature data set through data preprocessing according to the flue gas temperature simulation value and the measured flue gas temperature data under the corresponding simulation conditions, wherein the measured flue gas temperature data includes measured flue gas temperature data value, radiation factor data, and boiler operation parameters, wherein the radiation factor data includes but is not limited to ash wall temperature, wall porosity, and wall radiation exchange amount; S3: Obtaining a boiler flue gas temperature correction model according to the boiler flue gas temperature data set by improving DNN network training and testing; S4: Real-time detection of boiler flue gas temperature data, and obtaining boiler flue gas correction temperature through the boiler flue gas temperature correction model according to the boiler flue gas temperature data.

[0022] In this embodiment, the flue gas temperature field turbulence model is obtained by fluid dynamics analysis modeling according to the historical operating parameters of the boiler, specifically including: S101: Establish a three-dimensional model of the boiler through CFD meshing according to the three-dimensional structure of the boiler; S102: Obtain a flue gas temperature field turbulence model through an SST k-ω turbulence model according to the three-dimensional model of the boiler and the historical operating parameters of the boiler, wherein the historical operating parameters of the boiler include but are not limited to load, air volume, air temperature, coal volume, burnout air inclination angle, and burnout air opening.

[0023] Specifically, a geometric model is built to represent key parts such as the burner, furnace, and flue. The internal flow field of the boiler is meshed in the CFD software, especially in the near-wall and combustion areas, to obtain a detailed mesh distribution to ensure the accuracy of the simulation. According to the historical operating parameters of the boiler, boundary conditions and initial conditions are set in the CFD software to obtain reasonable inlet velocity, temperature, composition, outlet pressure, and wall temperature, emissivity, roughness and other parameters, so that numerical simulation can be carried out using the SST k-ω turbulence model.

[0024] It should be noted that the boundary conditions include inlet boundary conditions, outlet boundary conditions and wall boundary conditions.

[0025] In this embodiment, the flue gas temperature field turbulence model satisfies the conservation of flue gas mass, the conservation of flue gas energy and the conservation of flue gas momentum; The mathematical expression of the flue gas mass conservation is: , In steady-state flow, ignoring the time term can be simplified to: , Wherein, L is the flue gas flow rate of the heated surface, ρ is the flue gas density, v is the flue gas flow velocity, ρ1 is the flue gas density of section A1, ρ2 is the flue gas density of section A2, v1 is the flue gas flow velocity of section A1, and v2 is the flue gas flow velocity of section A2.

[0026] The simplified mathematical expression of the flue gas energy conservation is: , Among them, H is the heat on the flue gas side, α is the heat retention coefficient, x1 is the flue gas enthalpy at the inlet of the heating surface, x2 is the flue gas enthalpy at the outlet of the heating surface, c is the air leakage coefficient, X is the theoretical air leakage enthalpy, and Q is the heat absorption of the additional heating surface connected in parallel or in series with the calculated heating surface according to the direction of the flue gas flow.

[0027] The simplified mathematical expression of the flue gas momentum conservation is: , Among them, F1 is the smoke flow resistance, F2 is the smoke acceleration pressure drop, and F3 is the smoke self-generated ventilation force.

[0028] In this embodiment, the construction of a boiler flue gas temperature data set through data preprocessing based on the flue gas temperature simulation values ​​and the measured flue gas temperature data under the corresponding simulation conditions specifically includes: constructing a flue gas temperature field turbulence model through CFD software for numerical simulation, collecting multiple groups of flue gas temperature simulation values, and collecting the measured flue gas temperature data under the corresponding simulation conditions, and performing data cleaning and normalization to ensure data quality, thereby constructing a high-quality boiler flue gas temperature data set.

[0029] In this embodiment, the improved DNN network includes an input layer, a hidden layer, and an output layer. The input layer receives the measured flue gas temperature data under the simulation conditions corresponding to the flue gas temperature simulation value. The hidden layer captures the complex patterns and relationships in the input data through a nonlinear activation function. The output layer outputs the boiler flue gas corrected temperature. A batch normalization layer is added after the hidden layer, and a structural norm regularization term is added during the training process to reduce overfitting.

[0030] Specifically, 80% of the data in the boiler flue gas temperature data set is selected as the boiler flue gas temperature training set for the network training process; the remaining data is used as the boiler flue gas temperature test set for subsequent model performance evaluation; the improved DNN network is trained according to the boiler flue gas temperature data set, so that the network can learn from the measured temperature data and predict the temperature value corrected for the cold surface radiation effect. During the training stage, the parameters are continuously adjusted, and the network is iteratively trained until the model error drops to within the preset threshold range to ensure that the model achieves optimal performance.

[0031] In the testing phase, the coefficient of determination and mean absolute error were used as evaluation criteria to quantify the prediction accuracy and reliability of the model.

[0032] A boiler flue gas temperature data correction system based on fluid dynamics analysis includes a boiler flue gas temperature data acquisition module, a fluid dynamics analysis module, a data set construction module, an improved DNN network module, and a boiler flue gas temperature correction module; The boiler flue gas temperature data acquisition module is used to monitor the measured flue gas temperature data in real time; The fluid dynamics analysis module is used to obtain the historical operating parameters of the boiler and obtain the flue gas temperature field turbulence model through fluid dynamics analysis modeling, and solve the flue gas temperature field turbulence model through CFD software to obtain the flue gas temperature simulation value; The data set construction module is used to construct a boiler flue gas temperature data set through data preprocessing according to the flue gas temperature simulation value and the measured flue gas temperature data under the corresponding simulation conditions; The improved DNN network module is used to construct an improved DNN network, and a boiler flue gas temperature correction model is obtained through training and testing the improved DNN network according to the boiler flue gas temperature data set; The boiler flue gas temperature correction module is used to input boiler flue gas temperature data detected in real time, and obtain boiler flue gas correction temperature through the boiler flue gas temperature correction model.

[0033] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0034] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0035] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0036] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A boiler flue gas temperature data correction method based on fluid dynamics analysis, characterized in that: include: Obtaining historical operating parameters of the boiler, obtaining a flue gas temperature field turbulence model through fluid dynamics analysis modeling according to the historical operating parameters of the boiler, and solving the flue gas temperature field turbulence model through CFD software to obtain a flue gas temperature simulation value; Constructing a boiler flue gas temperature data set through data preprocessing according to the flue gas temperature simulation value and the measured flue gas temperature data under the corresponding simulation conditions; According to the boiler flue gas temperature data set, a boiler flue gas temperature correction model is obtained by improving DNN network training and testing; The boiler flue gas temperature data is detected in real time, and the boiler flue gas correction temperature is obtained through the boiler flue gas temperature correction model according to the boiler flue gas temperature data.

2. The boiler flue gas temperature data correction method based on fluid dynamics analysis according to claim 1 is characterized in that: The flue gas temperature field turbulence model obtained by fluid dynamics analysis modeling according to the historical operating parameters of the boiler includes: According to the three-dimensional structure of the boiler, a three-dimensional model of the boiler is established through CFD meshing; The flue gas temperature field turbulence model is obtained through the SST k-ω turbulence model according to the three-dimensional model of the boiler and the historical operating parameters of the boiler. The historical operating parameters of the boiler include but are not limited to load, air volume, air temperature, coal volume, burnout air inclination angle, and burnout air opening.

3. The boiler flue gas temperature data correction method based on fluid dynamics analysis according to claim 1 is characterized in that: The flue gas temperature field turbulence model satisfies the conservation of flue gas mass, the conservation of flue gas energy and the conservation of flue gas momentum.

4. The boiler flue gas temperature data correction method based on fluid dynamics analysis according to claim 1 is characterized in that: The measured flue gas temperature data includes measured flue gas temperature data value, radiation factor data, and boiler operation parameters. The radiation factor data includes but is not limited to ash wall temperature, wall porosity, and wall radiation exchange amount.

5. The boiler flue gas temperature data correction method based on fluid dynamics analysis according to claim 1 is characterized in that: The constructing of the boiler flue gas temperature data set by data preprocessing according to the flue gas temperature simulation value and the measured flue gas temperature data under the corresponding simulation conditions comprises: A turbulence model of the flue gas temperature field was constructed using CFD software for numerical simulation. Multiple sets of flue gas temperature simulation values ​​were collected. At the same time, the measured flue gas temperature data under the corresponding simulation conditions were collected. The data were then cleaned and normalized to construct a high-quality boiler flue gas temperature data set.

6. The boiler flue gas temperature data correction method based on fluid dynamics analysis according to claim 1 is characterized in that: The improved DNN network includes an input layer, a hidden layer, and an output layer. The input layer receives the measured flue gas temperature data under the simulation conditions corresponding to the flue gas temperature simulation value. The hidden layer captures the complex patterns and relationships in the input data through a nonlinear activation function. The output layer outputs the boiler flue gas corrected temperature. A batch normalization layer is added after the hidden layer, and a structural norm regularization term is added during the training process to reduce overfitting.

7. A boiler flue gas temperature data correction system based on fluid dynamics analysis, characterized in that: The system is applied to the boiler flue gas temperature data correction method based on fluid dynamic analysis as described in any one of claims 1 to 6, comprising a boiler flue gas temperature data acquisition module, a fluid dynamic analysis module, a data set construction module, an improved DNN network module, and a boiler flue gas temperature correction module; The boiler flue gas temperature data acquisition module is used to monitor the measured flue gas temperature data in real time; The fluid dynamics analysis module is used to obtain the historical operating parameters of the boiler and obtain the flue gas temperature field turbulence model through fluid dynamics analysis modeling, and solve the flue gas temperature field turbulence model through CFD software to obtain the flue gas temperature simulation value; The data set construction module is used to construct a boiler flue gas temperature data set through data preprocessing according to the flue gas temperature simulation value and the measured flue gas temperature data under the corresponding simulation conditions; The improved DNN network module is used to construct an improved DNN network, and a boiler flue gas temperature correction model is obtained through training and testing the improved DNN network according to the boiler flue gas temperature data set; The boiler flue gas temperature correction module is used to input boiler flue gas temperature data detected in real time, and obtain boiler flue gas correction temperature through the boiler flue gas temperature correction model.

8. An electronic 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 boiler flue gas temperature data correction method based on fluid dynamic analysis as described in any one of claims 1 to 6 is implemented.

9. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the boiler flue gas temperature data correction method based on fluid dynamic analysis as described in any one of claims 1 to 6 when executed by a computer processor.

Images