A boiler induced draft fan control method, a storage medium and a computer device

Abstract

The present application relates to a kind of boiler induced draft fan control method, storage medium and computer equipment, comprising: S1, current boiler independent variable data is obtained, using first flue regression model model1, the pressure difference of furnace and induced draft fan inlet is obtained;First flue regression model model1 is established using machine learning one polynomial algorithm to take the regression model of boiler independent variable data as independent variable, the square root of the pressure difference of furnace and induced draft fan inlet is dependent variable;S2, according to current furnace negative pressure and furnace negative pressure safety range, obtain current target furnace negative pressure;S3, using second flue regression model model2, obtain induced draft fan frequency recommended value;Second flue regression model model2 is established using machine learning two polynomial algorithm to take the regression model of boiler independent variable data and induced draft fan inlet pressure as independent variable, induced draft fan frequency is dependent variable;S4, control induced draft fan is operated according to induced draft fan frequency recommended value.

Description

Technical Field

[0001] This invention relates to the field of energy production technology, and in particular to a boiler induced draft fan control method, storage medium, and computer equipment. Background Technology

[0002] The induced draft fan is one of the important auxiliary machines in boiler equipment. Its main function is to draw the flue gas generated by boiler combustion from the furnace, so as to achieve a balance between the amount of air entering the furnace and the amount of flue gas flowing out of the furnace during the combustion process, regulate and maintain the negative pressure in the furnace within a certain range, and ensure the safe and stable operation of the boiler. Therefore, precise induced draft control is crucial to the stable combustion and safe operation of the boiler.

[0003] Most existing induced draft fan controls rely on PID feedback regulation based on furnace negative pressure, or combine with neural networks, fuzzy control, etc., to tune the proportional, derivative, and integral parameters of the PID controller online in order to improve control accuracy. Such control methods are mainly based on feedback, are complex to design, and are easily affected by fluctuations in boiler operating parameters and unstable combustion, lacking the ability to respond quickly to drastic fluctuations in furnace negative pressure. Summary of the Invention

[0004] (a) Technical problems to be solved

[0005] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a boiler induced draft fan control method, storage medium and computer equipment, which solves the technical problems of the complexity of the existing boiler induced draft fan control method and the untimely response to furnace negative pressure.

[0006] (II) Technical Solution

[0007] To achieve the above objectives, the main technical solutions adopted by the present invention include:

[0008] In a first aspect, embodiments of the present invention provide a boiler induced draft fan control method based on a machine learning model, the method comprising:

[0009] S1. Obtain the current boiler independent variable data, and use the pre-trained first flue regression model model1 to calculate the pressure difference between the furnace and the induced draft fan inlet.

[0010] The boiler independent variable data are one of the following: the volumetric air volume of the air entering the furnace at the furnace outlet, the volumetric air volume of the air entering the furnace at the flue outlet, and the total mass air volume entering the furnace.

[0011] The first flue gas regression model, model1, is a regression model established using a first-order polynomial algorithm of machine learning, with boiler independent variable data as independent variables and the square root of the pressure difference between the furnace and the induced draft fan inlet as the dependent variable.

[0012] S2. Based on the current furnace negative pressure and the preset safe range of furnace negative pressure. Obtain the current target furnace negative pressure;

[0013] S3. Based on the pressure difference between the furnace and the induced draft fan inlet and the current target furnace negative pressure, the recommended value of the induced draft fan frequency is calculated using the second flue regression model model2.

[0014] The second flue gas regression model, model2, is a regression model established using a machine learning quadratic polynomial algorithm, with boiler independent variable data and induced draft fan inlet pressure as independent variables and induced draft fan frequency as dependent variable.

[0015] S4. Control the induced draft fan in the boiler to operate according to the recommended induced draft fan frequency value.

[0016] Preferably,

[0017] The volumetric air volume at the furnace outlet is the total mass air volume entering the furnace divided by the air density at the furnace outlet.

[0018] The volumetric air volume at the flue outlet is the total mass air volume entering the furnace divided by the air density at the flue outlet.

[0019] The boiler's independent variable data is the volumetric airflow at the furnace outlet.

[0020] Preferably, the process further includes the following steps before step S1:

[0021] S01. Collect boiler operation data within a preset time period according to the preset collection frequency;

[0022] The boiler operation data corresponding to each collection time point includes: primary air volume, secondary air volume, furnace outlet temperature and pressure, flue outlet temperature and pressure, furnace negative pressure, induced draft fan frequency, and induced draft fan inlet pressure.

[0023] S02. Based on the collected boiler operation data, establish the first flue regression model (model1) and the second flue regression model (model2).

[0024] Preferably, S02 includes:

[0025] S021. Based on the collected boiler operation data, obtain the pressure difference between the furnace and the induced draft fan inlet and the volume of air entering the furnace at the furnace outlet at each collection time point.

[0026] Wherein, the volumetric air volume at the furnace outlet is the total mass air volume entering the furnace corresponding to the pre-collected collection time point / the air density at the furnace outlet corresponding to the pre-collected collection time point.

[0027] S022. Using the volume and volume of air entering the furnace at the furnace outlet corresponding to each collection time point as the independent variable and the square root of the pressure difference between the furnace and the induced draft fan inlet as the dependent variable, a regression model model1 is established using a first-order polynomial algorithm of machine learning.

[0028] The first-order polynomial regression equation in this first-order polynomial algorithm is:

[0029] ;

[0030] The pressure difference between the furnace and the induced draft fan inlet;

[0031] v1 represents the volume and flow rate of air entering the furnace at the furnace outlet.

[0032] These are the fit coefficients of the regression model.

[0033] Preferably,

[0034] The pressure difference between the furnace and the inlet of the induced draft fan for:

[0035] ;

[0036] in, This creates a negative pressure in the furnace.

[0037] This refers to the inlet pressure of the induced draft fan.

[0038] Preferably, S02 includes:

[0039] Using the furnace outlet air volume and induced draft fan inlet pressure at each collection time point as independent variables and the induced draft fan frequency as dependent variable, a regression model model2 was established using a machine learning quadratic polynomial algorithm.

[0040] The quadratic polynomial regression equation in this quadratic polynomial algorithm is:

[0041] ;

[0042] freq is the frequency of the induced draft fan;

[0043] in: These are the fitting coefficients for the regression model.

[0044] Preferably, S2 specifically includes:

[0045] Furnace negative pressure safety range The current furnace negative pressure is p0;

[0046] like The current target furnace negative pressure is p0;

[0047] like The current target furnace negative pressure is ;

[0048] like The current target furnace negative pressure is .

[0049] Preferably,

[0050] The preset sampling frequency is: 1 time / minute;

[0051] The preset time period is 1 day.

[0052] On the other hand, this embodiment also provides a computer-readable storage medium storing a boiler induced draft fan control program thereon, which, when executed by a processor, implements the boiler induced draft fan control method as described above.

[0053] On the other hand, this embodiment also provides a computer device, including a memory, a processor, and a boiler induced draft fan control program stored in the memory and executable on the processor. When the processor executes the program, it implements the boiler induced draft fan control method as described above.

[0054] (III) Beneficial Effects

[0055] The beneficial effects of the present invention are as follows: The boiler induced draft fan control method, storage medium and computer equipment of the present invention use a first flue regression model model1 and a second flue regression model model2 to represent the functional relationship between furnace negative pressure, induced draft fan inlet pressure, furnace air volume and induced draft fan operating frequency. Then, based on the real-time furnace air volume and target furnace negative pressure, predictive control of the induced draft fan is performed. The method is simple, controllable and highly interpretable. The feedforward control also improves the control accuracy of the induced draft fan and the rapid response capability to furnace negative pressure. Attached Figure Description

[0056] Figure 1 This is a flowchart of a boiler induced draft fan control method according to the present invention;

[0057] Figure 2 This is a flowchart of a boiler induced draft fan control method according to Embodiment 2 of the present invention;

[0058] Figure 3 This is a schematic diagram illustrating part of the performance of a boiler induced draft fan control method according to the present invention. Detailed Implementation

[0059] To better explain and facilitate understanding of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0060] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present invention can be understood more clearly and thoroughly, and that the scope of the present invention can be fully conveyed to those skilled in the art.

[0061] Example 1

[0062] See Figure 1 This embodiment provides a boiler induced draft fan control method, the method including:

[0063] S1. Obtain the current boiler independent variable data, and use the pre-trained first flue regression model model1 to calculate the pressure difference between the furnace and the induced draft fan inlet.

[0064] The boiler independent variable data are one of the following: the volumetric air volume of the air entering the furnace at the furnace outlet, the volumetric air volume of the air entering the furnace at the flue outlet, and the total mass air volume entering the furnace.

[0065] The volumetric air volume at the furnace outlet is the ratio of the total mass air volume entering the furnace to the air density at the furnace outlet.

[0066] The volumetric air volume at the flue outlet is the total mass air volume entering the furnace divided by the air density at the flue outlet.

[0067] The boiler's independent variable data is the volumetric airflow at the furnace outlet.

[0068] The first flue gas regression model, model1, is a regression model established using a first-order polynomial algorithm in machine learning, with boiler independent variable data as the independent variable and the square root of the pressure difference between the furnace and the induced draft fan inlet as the dependent variable.

[0069] S2. Based on the current furnace negative pressure and the preset safe range of furnace negative pressure. Obtain the current target furnace negative pressure.

[0070] S3. Based on the pressure difference between the furnace and the induced draft fan inlet and the current target furnace negative pressure, the recommended value of the induced draft fan frequency is calculated using the second flue regression model model2.

[0071] The second flue gas regression model, model2, is a regression model established using a machine learning quadratic polynomial algorithm, with boiler independent variable data and induced draft fan inlet pressure as independent variables and induced draft fan frequency as dependent variable.

[0072] S4. Control the induced draft fan in the boiler to operate according to the recommended induced draft fan frequency value.

[0073] In practical applications of this embodiment, the step S1 is further preceded by:

[0074] S01. Collect boiler operation data within a preset time period according to the preset collection frequency;

[0075] The boiler operation data corresponding to each collection time point includes: primary air volume, secondary air volume, furnace outlet temperature and pressure, flue outlet temperature and pressure, furnace negative pressure, induced draft fan frequency, and induced draft fan inlet pressure.

[0076] S02. Based on the collected boiler operation data, establish the first flue regression model (model1) and the second flue regression model (model2).

[0077] Specifically, S02 includes:

[0078] S021. Based on the collected boiler operation data, obtain the pressure difference between the furnace and the induced draft fan inlet and the volume of air entering the furnace at the furnace outlet at each collection time point.

[0079] Wherein, the volumetric air volume at the furnace outlet is the total mass air volume entering the furnace corresponding to the pre-collected collection time point / the air density at the furnace outlet corresponding to the pre-collected collection time point.

[0080] S022. Using the volume and volume of air entering the furnace at the furnace outlet corresponding to each collection time point as the independent variable and the square root of the pressure difference between the furnace and the induced draft fan inlet as the dependent variable, a regression model model1 is established using a first-order polynomial algorithm of machine learning.

[0081] The first-order polynomial regression equation in this first-order polynomial algorithm is:

[0082] ;

[0083] The pressure difference between the furnace and the induced draft fan inlet; for: ;in, This creates a negative pressure in the furnace. This refers to the inlet pressure of the induced draft fan.

[0084] v1 represents the volume of air entering the furnace at the furnace outlet.

[0085] These are the fit coefficients of the regression model.

[0086] In the practical application of this embodiment, S02 includes:

[0087] Using the furnace outlet air volume and induced draft fan inlet pressure at each collection time point as independent variables and the induced draft fan frequency as dependent variable, a regression model model2 was established using a machine learning quadratic polynomial algorithm.

[0088] The quadratic polynomial regression equation in this quadratic polynomial algorithm is:

[0089] ;

[0090] freq is the frequency of the induced draft fan;

[0091] in: These are the fitting coefficients for the regression model.

[0092] The boiler induced draft fan control method in this embodiment uses a first flue gas regression model (model1) and a second flue gas regression model (model2) to represent the functional relationship between furnace negative pressure, induced draft fan inlet pressure, furnace air volume, and induced draft fan operating frequency. Based on the real-time furnace air volume and target furnace negative pressure, predictive control of the induced draft fan is performed. The method is simple, controllable, and highly interpretable. The feedforward-based control also improves the control accuracy of the induced draft fan and its rapid response capability to furnace negative pressure.

[0093] Example 2

[0094] See Figure 2 This embodiment provides a boiler induced draft fan control method, the method including:

[0095] A1. Collect boiler operation data within a pre-set time period according to the pre-set collection frequency.

[0096] The boiler operation data corresponding to each collection time point includes: primary air volume, secondary air volume, furnace outlet temperature and pressure, flue outlet temperature and pressure, furnace negative pressure, induced draft fan frequency, and induced draft fan inlet pressure; the preset collection frequency is 1 time / minute; the preset time period is 1 day.

[0097] A2. Based on the collected boiler operation data, establish the first flue regression model (model1) and the second flue regression model (model2).

[0098] A2 includes:

[0099] Based on the collected boiler operation data, the pressure difference between the furnace and the induced draft fan inlet, as well as the volume of air entering the furnace at the furnace outlet, are obtained at each collection time point.

[0100] Wherein, the volumetric air volume at the furnace outlet is the total mass air volume entering the furnace corresponding to the pre-collected collection time point / the air density at the furnace outlet corresponding to the pre-collected collection time point.

[0101] Using the volume and volume of air entering the furnace at the furnace outlet corresponding to each collection time point as the independent variable and the square root of the pressure difference between the furnace and the induced draft fan inlet as the dependent variable, a regression model model1 was established using a first-order polynomial algorithm based on machine learning.

[0102] The first-order polynomial regression equation in this first-order polynomial algorithm is:

[0103] ;

[0104] The pressure difference between the furnace and the induced draft fan inlet; for: ;in, This creates a negative pressure in the furnace. This refers to the inlet pressure of the induced draft fan.

[0105] v1 represents the volume and flow rate of air entering the furnace at the furnace outlet. These are the fit coefficients of the regression model.

[0106] A2 also includes:

[0107] Using the furnace outlet air volume and induced draft fan inlet pressure at each data collection time point as independent variables and the induced draft fan frequency as the dependent variable, a regression model model2 was established using a machine learning quadratic polynomial algorithm.

[0108] The quadratic polynomial regression equation in this quadratic polynomial algorithm is:

[0109] ;

[0110] freq represents the frequency of the induced draft fan.

[0111] in: These are the fitting coefficients for the regression model.

[0112] A3. Obtain the current boiler independent variable data, and use the pre-trained first flue regression model model1 to calculate the pressure difference between the furnace and the induced draft fan inlet.

[0113] The boiler independent variable data are one of the following: the volumetric air volume of the air entering the furnace at the furnace outlet, the volumetric air volume of the air entering the furnace at the flue outlet, and the total mass air volume entering the furnace.

[0114] The volumetric air volume at the furnace outlet is calculated as the total mass air volume entering the furnace divided by the air density at the furnace outlet. The volumetric air volume at the flue outlet is also calculated as the total mass air volume entering the furnace divided by the air density at the flue outlet. The boiler's independent variable data is the volumetric air volume at the furnace outlet.

[0115] The first flue gas regression model, model1, is a regression model established using a first-order polynomial algorithm in machine learning, with boiler independent variable data as the independent variable and the square root of the pressure difference between the furnace and the induced draft fan inlet as the dependent variable.

[0116] A4. Based on the current furnace negative pressure and the preset safe range of furnace negative pressure. To obtain the current target furnace negative pressure, specifically including:

[0117] like The current target furnace negative pressure is p0.

[0118] like The current target furnace negative pressure is .

[0119] like The current target furnace negative pressure is .

[0120] A5. Based on the pressure difference between the furnace and the induced draft fan inlet and the current target furnace negative pressure, the recommended value of the induced draft fan frequency is calculated using the second flue regression model model2.

[0121] The second flue gas regression model, model2, is a regression model established using a machine learning quadratic polynomial algorithm, with boiler independent variable data and induced draft fan inlet pressure as independent variables and induced draft fan frequency as dependent variable.

[0122] A6. Control the induced draft fan in the boiler to operate according to the recommended induced draft fan frequency value.

[0123] In this embodiment, after obtaining the first flue gas regression model (model1) and the second flue gas regression model (model2), the boiler induced draft fan control method of the present invention is used. The furnace negative pressure for the next minute is used as the target furnace negative pressure to predict the corresponding induced draft fan frequency for the next minute. This prediction is then compared with the actual induced draft fan frequency for the next minute. The closer the two are, the better the effect of the first flue gas regression model (model1) and the second flue gas regression model (model2) in the boiler induced draft fan control method of the present invention. Specifically, Figure 3 The boiler induced draft fan control method of the present invention is shown to perform very close to the actual induced draft fan frequency on a partial test dataset.

[0124] In summary, the boiler induced draft fan control method presented in this embodiment establishes a quantifiable functional relationship between the induced draft fan operating frequency and the boiler operating state, namely, establishing a first flue regression model (model1) and a second flue regression model (model2). When the furnace negative pressure changes, the optimal induced draft fan operating frequency can be predicted and recommended based on the current operating parameters such as the inlet air volume, temperature, and pressure, and then controlled accordingly. This improves control accuracy while increasing the induced draft fan's rapid response capability to the boiler operating state.

[0125] This embodiment also provides a computer-readable storage medium storing a boiler induced draft fan control program thereon, which, when executed by a processor, implements the boiler induced draft fan control method as described above.

[0126] This embodiment also provides a computer device, including a memory, a processor, and a boiler induced draft fan control program stored in the memory and executable on the processor. When the processor executes the program, it implements the boiler induced draft fan control method as described above.

[0127] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0128] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions.

[0129] It should be noted that any reference numerals placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In claims that enumerate several means, several of these means may be embodied by the same hardware. The use of the terms first, second, third, etc., is merely for convenience of expression and does not indicate any order. These terms can be understood as part of the component names.

[0130] Furthermore, it should be noted that in the description of this specification, the terms "one embodiment," "some embodiments," "embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0131] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the claims should be interpreted to include both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0132] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, then this invention should also include these modifications and variations.

Claims

1. A method for controlling a boiler induced draft fan, characterized in that, The method includes: S1. Obtain the current boiler independent variable data, and use the pre-trained first flue regression model model1 to calculate the pressure difference between the furnace and the induced draft fan inlet. The boiler independent variable data are: the volume and flow rate of air entering the furnace at the furnace outlet; The first flue gas regression model, model1, is a regression model established using a first-order polynomial algorithm of machine learning, with boiler independent variable data as independent variables and the square root of the pressure difference between the furnace and the induced draft fan inlet as the dependent variable. S2. Based on the current furnace negative pressure and the preset safe range of furnace negative pressure. Obtain the current target furnace negative pressure; S3. Based on the pressure difference between the furnace and the induced draft fan inlet and the current target furnace negative pressure, the recommended value of the induced draft fan frequency is calculated using the second flue regression model model2. The second flue gas regression model, model2, is a regression model established using a machine learning quadratic polynomial algorithm, with boiler independent variable data and induced draft fan inlet pressure as independent variables and induced draft fan frequency as dependent variable. S4. Control the induced draft fan in the boiler to operate according to the recommended induced draft fan frequency value.

2. The boiler induced draft fan control method according to claim 1, characterized in that, The volumetric air volume at the furnace outlet is the ratio of the total mass air volume entering the furnace to the air density at the furnace outlet.

3. The boiler induced draft fan control method according to claim 2, characterized in that, Before S1, the following also applies: S01. Collect boiler operation data within a preset time period according to the preset collection frequency; The boiler operation data corresponding to each collection time point includes: primary air volume, secondary air volume, furnace outlet temperature and pressure, flue outlet temperature and pressure, furnace negative pressure, induced draft fan frequency, and induced draft fan inlet pressure. S02. Based on the collected boiler operation data, establish the first flue regression model (model1) and the second flue regression model (model2).

4. The boiler induced draft fan control method according to claim 3, characterized in that, The S02 includes: S021. Based on the collected boiler operation data, obtain the pressure difference between the furnace and the induced draft fan inlet and the volume of air entering the furnace at the furnace outlet at each collection time point. Wherein, the volumetric air volume at the furnace outlet is the total mass air volume entering the furnace corresponding to the pre-collected collection time point / the air density at the furnace outlet corresponding to the pre-collected collection time point. S022. Using the volume and volume of air entering the furnace at the furnace outlet corresponding to each collection time point as the independent variable and the square root of the pressure difference between the furnace and the induced draft fan inlet as the dependent variable, a regression model model1 is established using a first-order polynomial algorithm of machine learning. The first-order polynomial regression equation in this first-order polynomial algorithm is: ； The pressure difference between the furnace and the induced draft fan inlet; v1 represents the volume and flow rate of air entering the furnace at the furnace outlet. , i=0, 1, are the fitting coefficients of the regression model.

5. The boiler induced draft fan control method according to claim 4, characterized in that, The pressure difference between the furnace and the inlet of the induced draft fan for: ； in, This creates a negative pressure in the furnace. This refers to the inlet pressure of the induced draft fan.

6. The boiler induced draft fan control method according to claim 5, characterized in that, The S02 includes: Using the furnace outlet air volume and induced draft fan inlet pressure at each collection time point as independent variables and the induced draft fan frequency as dependent variable, a regression model model2 was established using a machine learning quadratic polynomial algorithm. The quadratic polynomial regression equation in this quadratic polynomial algorithm is: ； freq is the frequency of the induced draft fan; in: , i=0,1,2...5, are the regression model fitting coefficients.

7. The boiler induced draft fan control method according to claim 6, characterized in that, S2 specifically includes: Furnace negative pressure safety range The current furnace negative pressure is p0; like The current target furnace negative pressure is p0; like The current target furnace negative pressure is ; like The current target furnace negative pressure is .

8. The boiler induced draft fan control method according to claim 7, characterized in that, The preset sampling frequency is: 1 time / minute; The preset time period is 1 day.

9. A computer-readable storage medium, characterized in that, It stores a boiler induced draft fan control program based on a machine learning model, which, when executed by a processor, implements the boiler induced draft fan control method as described in any one of claims 1-8.

10. A computer device, characterized in that, The system includes a memory, a processor, and a boiler induced draft fan control program based on a machine learning model stored in the memory and executable on the processor. When the processor executes the program, it implements the boiler induced draft fan control method as described in any one of claims 1-8.

Images