Boiler combustion optimization control method and system

Abstract

The invention discloses a boiler combustion optimization control method and system, and the method comprises the steps: obtaining boiler combustion conditions and boiler combustion key performance indexes, and building a dynamic updating model based on the boiler combustion conditions; according to boundary conditions of the boiler combustion conditions, nonlinear rolling optimization is conducted on the boundary conditions, and control parameters corresponding to the boundary conditions are generated; and the boiler combustion condition is adjusted based on the control parameters, and the difference value between the predicted output of the dynamic updating model and the boiler combustion key performance index is calculated. According to the method, the dynamic updating model is established, the boiler combustion condition is used as the input condition to predict the boiler combustion key performance index, the prediction result and the actual result of the boiler combustion key performance index are compared, feedback correction is conducted on the optimization process of the boiler combustion condition according to the comparison result, closed-loop control is formed, manual intervention is not needed, and operation is easy. Meanwhile, the method can adapt to the change of the coal type through dynamic data correction.

Description

Technical Field

[0001] The present invention relates to the field of boiler combustion, and particularly to a method and system for optimizing boiler combustion control. Background Art

[0002] As a core device for industrial production and energy supply, the effectiveness of boiler combustion control directly affects energy utilization efficiency, pollutant emissions, and operation safety. With the expansion of industrial scale, the improvement of environmental protection standards, and the increase in energy costs, boiler combustion control technology has experienced a development process from manual regulation to intelligent and refined control.

[0003] Currently, during the boiler combustion process, the air volume measurement, oxygen content, carbon monoxide, and carbon content in fly ash inside the boiler are usually monitored, and then the coal amount and air distribution inside the boiler are adjusted through manual control to achieve the expected combustion efficiency.

[0004] However, during the boiler combustion process, there are many influencing factors. For example, the oxygen content, the opening degree of the burnout damper, and the instability of the coal feeding amount will all affect the concentration of nitrogen oxides and boiler efficiency, thereby affecting production efficiency. Summary of the Invention

[0005] Based on this, the objective of the present invention is to provide a method and system for optimizing boiler combustion control, aiming to solve the problem that during the current boiler combustion process, there are many influencing factors. For example, the oxygen content, the opening degree of the burnout damper, and the instability of the coal feeding amount will all affect the concentration of nitrogen oxides and boiler efficiency, thereby affecting production efficiency.

[0006] To achieve the above objective, the present invention proposes a method for optimizing boiler combustion control, and the method for optimizing boiler combustion control includes:

[0007] Obtain boiler combustion conditions and key boiler combustion performance indicators, and establish a dynamically updated model based on the boiler combustion conditions;

[0008] According to the boundary conditions of the boiler combustion conditions, perform non - linear rolling optimization on the boundary conditions, and generate control parameters corresponding to the boundary conditions;

[0009] Adjust the boiler combustion conditions based on the control parameters, and calculate the difference between the predicted output of the dynamically updated model and the key boiler combustion performance indicators.

[0010] According to one aspect of the above technical solution, the step of obtaining boiler combustion conditions and key boiler combustion performance indicators, and establishing a dynamically updated model based on the boiler combustion conditions includes:

[0011] The boiler combustion conditions at least include the oxygen content set value, the burnout air damper opening, the secondary air damper opening, and the coal feed offset, and the key boiler combustion performance indicators at least include the boiler efficiency, the NOx concentration, and the reheater steam temperature;

[0012] Set the oxygen content set value, the burnout air damper opening, the secondary air damper opening, and the coal feed offset as input variables, and set the boiler efficiency, the NOx concentration, and the reheater steam temperature as output variables to establish a dynamic update model.

[0013] According to one aspect of the above technical solution, the establishment process of the dynamic update model is as follows:

[0014] Respectively determine the oxygen content set value of the boiler under different loads and coal qualities, and the boiler efficiency and the discharged NOx concentration corresponding to the oxygen content set value; adjust the burnout air ratio through the burnout air damper to ensure complete combustion of the fuel, and adjust the opening of each layer of air damper according to the burner load distribution and the flame center position to avoid local oxygen deficiency or excessive air; adjust the fuel distribution of each burner to avoid local overload or underload;

[0015] By analyzing the non-linear relationship between the input variables of the oxygen content set value, the burnout air damper opening, the secondary air damper opening, and the coal feed offset and the output variables of the boiler efficiency, the NOx concentration, and the reheater steam temperature in the historical moment data, construct a dynamic update model;

[0016] Establish a dynamic update model:

[0017]

[0018] Among them, f(x) is the predicted output of the conversion model, x is the input variable, x i is the i-th input sample vector in the training data, b is the bias term, α i is the Lagrange multiplier, σ is the width parameter, and N is the number of samples;

[0019] x(t) = [Load(t), CoalQuality(t), O2(t - 1), D ofa (t

[0020] - 1), D sec (t - 1), Δm(t - 1)]

[0021] Among them, t is the current moment, t - 1 is the historical moment, x(t) is the input variable at the current moment, Load(t) is the boiler load at the current moment, CoalQuality(t) is the coal quality at the current moment, O2(t - 1) is the oxygen content set value at the historical moment, D ofa (t - 1) is the burnout air damper opening at the historical moment, D sec(t - 1) is the opening of the secondary air damper at the historical moment, Δm(t - 1) is the coal feed bias at the historical moment, and V(t) is the predicted output of the boiler efficiency, NOx concentration, and reheated steam temperature.

[0022] According to one aspect of the above technical solution, the step of performing non - linear rolling optimization on the boundary conditions according to the boundary conditions of the boiler combustion conditions and generating control parameters corresponding to the boundary conditions includes:

[0023] Determine the upper limit threshold of the NOx concentration and the upper and lower limit thresholds of the reheated steam temperature as the optimization objectives, and set the boundary conditions of the boiler combustion conditions. The boundary conditions at least include the upper and lower limit thresholds of the oxygen content set value, the upper and lower limit thresholds of the burnout air damper opening, and the upper and lower limit thresholds of the secondary air damper opening;

[0024] Based on each sampling moment, based on the current combustion state of the boiler and the optimization objective, analyze the boundary condition data at the historical moment, and generate control parameters using the least - squares support vector machine dynamic model.

[0025] According to one aspect of the above technical solution, the step of adjusting the boiler combustion conditions based on the control parameters and calculating the difference between the predicted output of the dynamic update model and the key performance indicators of the boiler combustion includes:

[0026] After obtaining the control parameters, apply the control parameters obtained at the current sampling moment to the oxygen content set value, the burnout air damper opening, and the secondary air damper opening to update the boiler combustion conditions, and synchronously update the key performance indicators of the boiler combustion within one sampling moment period.

[0027] According to one aspect of the above technical solution, the steps after updating the boiler combustion conditions and updating the key performance indicators of the boiler combustion are:

[0028] Take the updated boiler combustion conditions as input variables, input them into the dynamic update model to generate a predicted output, calculate the difference between the predicted output and the updated key performance indicators of the boiler combustion, and feedback the difference to the optimization process of the key performance indicators of the boiler combustion to correct the boiler combustion conditions.

[0029] The present invention also proposes a boiler combustion optimization control system. The boiler combustion optimization control system is used to implement the above - mentioned boiler combustion optimization control method. The system includes:

[0030] A model - building module, which is used to obtain the boiler combustion conditions and the key performance indicators of the boiler combustion, and establish a dynamic update model based on the boiler combustion conditions;

[0031] A rolling optimization module, configured to perform non-linear rolling optimization on the boundary conditions according to the boundary conditions of the boiler combustion conditions, and generate control parameters corresponding to the boundary conditions;

[0032] A difference calculation module, configured to adjust the boiler combustion conditions based on the control parameters, and calculate the difference between the predicted output of the dynamic update model and the key performance indicators of the boiler combustion.

[0033] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the boiler combustion optimization control method as described above is implemented.

[0034] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and running on the processor. When the processor executes the computer program, the boiler combustion optimization control method as described above is implemented.

[0035] In summary, according to a boiler combustion optimization control method provided by the present invention, boiler combustion conditions and key performance indicators of boiler combustion are obtained, and a dynamic update model is established based on the boiler combustion conditions; according to the boundary conditions of the boiler combustion conditions, non-linear rolling optimization is performed on the boundary conditions, and control parameters corresponding to the boundary conditions are generated; the boiler combustion conditions are adjusted based on the control parameters, and the difference between the predicted output of the dynamic update model and the key performance indicators of the boiler combustion is calculated. By establishing a dynamic update model, the present invention uses the boiler combustion conditions as input conditions to predict the key performance indicators of boiler combustion, compares the predicted results of the key performance indicators of boiler combustion with the actual results, and feeds back and corrects the optimization process of the boiler combustion conditions with the comparison results to form a closed-loop control without manual intervention. At the same time, the present invention can also adaptively conform to the change of coal types through dynamic data correction. Compared with the traditional boiler combustion control method, the prediction effect in this method is greatly improved. Under the same error threshold, the new update strategy can achieve better prediction results with fewer model update times. At the same time, historical operation data is used to screen the historical best operation mode, and the best secondary air damper opening and burnout air damper opening that take into account boiler efficiency and NOx under steady-state operation conditions are obtained to achieve preliminary combustion optimization.

[0036] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present invention. Description of the Drawings

[0037] Figure 1 It is a flowchart of the boiler combustion optimization control method in Embodiment 1 of the present invention;

[0038] Figure 2It is a schematic structural diagram of the boiler combustion optimization control system in the second embodiment of the present invention;

[0039] Figure 3 It is a block diagram of the structure of the electronic device in the fourth embodiment of the present invention. Specific embodiments

[0040] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Several embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided to make the disclosure of the present invention more thorough and comprehensive.

[0041] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly on the other element or there can also be a middle element. When an element is considered to be "connected" to another element, it can be directly connected to the other element or there may be a middle element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are only for the purpose of illustration.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0043] In this application, a three-dimensional space holographic multi-object digital twin monitoring system can be set in the boiler for flame image temperature field monitoring and early warning, on-line measurement of the flow rates of primary air, secondary air, and burnout air, and on-line monitoring of oxygen content, carbon monoxide, and carbon content in fly ash. The data monitored by the above monitoring system and the real-time operation data of the boiler in the DCS system are jointly input into the combustion optimization control software. Through big data self-learning and model training optimization, an optimized offset is output to the DCS system, thereby realizing on-line measurement and leveling of primary air powder, on-line adjustment of secondary air and burnout air, and on-line measurement and adjustment of pulverized coal fineness. After the on-line adjustment of the boiler, it is monitored again through the three-dimensional space holographic multi-object digital twin monitoring system to realize closed-loop optimization control.

[0044] Embodiment 1

[0045] As Figure 1 shown is a flowchart of a boiler combustion optimization control method in the first embodiment of the present invention. The boiler combustion optimization control method includes the following steps S01-step S03, where:

[0046] S01. Obtain the boiler combustion conditions and key boiler combustion performance indicators, and establish a dynamically updated model based on the boiler combustion conditions.

[0047] Obtain the boiler combustion conditions and key boiler combustion performance indicators. The boiler combustion conditions include oxygen content set value, burnout air damper opening, secondary air damper opening, and coal feed bias, etc. The key boiler combustion performance indicators at least include boiler efficiency, NOx concentration, and reheat steam temperature, etc.

[0048] At the same time, set the oxygen content set value, the burnout air damper opening, the secondary air damper opening, and the coal feed bias as input variables, and set the boiler efficiency, the NOx concentration, and the reheat steam temperature as output variables to establish a dynamically updated model.

[0049] The process of establishing the dynamically updated model is as follows:

[0050] Determine the oxygen content set value of the boiler under different loads and coal qualities respectively, as well as the boiler efficiency and the NOx concentration discharged corresponding to the oxygen content set value; adjust the burnout air ratio through the burnout air damper to ensure complete combustion of the fuel, and adjust the opening of each layer of air dampers according to the burner load distribution and the flame center position to avoid local oxygen deficiency or excessive air; adjust the fuel distribution of each burner to avoid local overload or underload;

[0051] By analyzing the non-linear relationship between the input variables of oxygen content set value, burnout air damper opening, secondary air damper opening, and coal feed bias and the output variables of boiler efficiency, NOx concentration, and reheat steam temperature in the historical moment data, construct a dynamically updated model;

[0052] Establish a dynamically updated model:

[0053]

[0054] Among them, f(x) is the predicted output of the conversion model, x is the input variable, x i is the i-th input sample vector in the training data, b is the bias term, α i is the Lagrange multiplier, σ is the width parameter, and N is the number of samples;

[0055] x(t) = [Load(t), CoalQuality(t), O2(t - 1), D ofa (t

[0056] - 1), D sec (t - 1), Δm(t - 1)]

[0057] Among them, t is the current moment, t - 1 is the historical moment, x(t) is the input variable at the current moment, Load(t) is the boiler load at the current moment, CoalQuality(t) is the coal quality at the current moment, O2(t - 1) is the oxygen content set value at the historical moment, D ofa (t - 1) is the opening of the burnout air damper at the historical moment, D sec (t - 1) is the opening of the secondary air damper at the historical moment, Δm(t - 1) is the coal feed bias at the historical moment, and V(t) is the predicted output of the boiler efficiency, NOx concentration, and reheat steam temperature.

[0058] It should be noted that the input variables in this embodiment include but are not limited to the oxygen content set value, the opening of the burnout air damper, the opening of the secondary air damper, and the coal feed bias, and the output variables include but are not limited to the boiler efficiency, NOx concentration, and reheat steam temperature. By introducing historical input and output data (such as fuel quantity, air supply quantity, and furnace temperature at previous moments) as the input of the dynamic model, a state space containing delay terms is constructed to accurately describe the dynamic evolution process of the combustion state. The dynamic characteristics of the boiler are significantly different under different operating conditions such as start-stop, peak shaving, and steady-state operation. The dynamic update model can flexibly adapt to changes in operating conditions by adjusting input parameters, avoiding the limitations of traditional linear models in non-linear scenarios.

[0059] S02. According to the boundary conditions of the boiler combustion conditions, perform non-linear rolling optimization on the boundary conditions and generate control parameters corresponding to the boundary conditions.

[0060] Determine the upper limit threshold of NOx concentration and the upper and lower limit thresholds of reheat steam temperature and other output variables as the optimization objectives, and set the boundary conditions of the boiler combustion conditions. The boundary conditions at least include the upper and lower limit thresholds of the oxygen content set value, the upper and lower limit thresholds of the opening of the burnout air damper, the upper and lower limit thresholds of the opening of the secondary air damper, and other input variables.

[0061] In addition, in some application scenarios, with the operation of the boiler, disturbances such as coal quality may cause the accuracy of the initial model to decrease. When the coal type is switched from bituminous coal to lignite (the calorific value decreases and the moisture content increases), through the adaptive adjustment of the dynamic update model, the model automatically increases the coal feed bias (the total fuel quantity increases), simultaneously adjusts the opening of the secondary air damper (increases the lower secondary air to strengthen ignition), and increases the oxygen content set value (compensates for the heat absorption of moisture evaporation), avoiding unstable combustion caused by manual adjustment.

[0062] Based on each sampling moment, analyze the boundary condition data at the historical moment based on the current combustion state and optimization objective of the boiler, and generate control parameters using the least squares support vector machine dynamic model.

[0063] S03. Adjust the boiler combustion conditions based on the control parameters, and calculate the difference between the predicted output of the dynamic update model and the key performance indicators of the boiler combustion.

[0064] After obtaining the control parameters, apply the control parameters obtained at the current sampling moment to input variables such as oxygen content set value, burnout damper opening, and secondary air damper opening to update the boiler combustion conditions, record the updated boiler combustion conditions, and synchronously update the key performance indicators of the boiler combustion within a sampling moment cycle, and synchronously record the data of the updated key performance indicators of the boiler combustion.

[0065] After updating the boiler combustion conditions and the key performance indicators of the boiler combustion, use the updated boiler combustion conditions as input variables and input them into the dynamic update model to generate a predicted output, calculate the difference between the predicted output and the updated key performance indicators of the boiler combustion, and feedback the difference to the optimization process of the key performance indicators of the boiler combustion to correct the boiler combustion conditions.

[0066] By applying the dynamic update model in this embodiment to the boiler, compared with non-update and traditional update strategies, the prediction effect of the new update strategy has been greatly improved. Under the same error threshold, the new update strategy can achieve better prediction effects with fewer model update times. Use historical moment data to screen the historical best operating mode, and obtain the best secondary air damper opening, burnout damper opening, and flue gas oxygen content that take into account boiler efficiency and NOx under steady-state operating conditions to achieve preliminary combustion optimization. At the same time, on the basis of the instructions given by the preliminary optimization, within a certain range, further use economic predictive control technology for online secondary optimization to achieve closed-loop dynamic combustion optimization and better overcome the influence of uncertain factors such as coal type changes.

[0067] In summary, according to a boiler combustion optimization control method proposed by the present invention, boiler combustion conditions and key boiler combustion performance indicators are obtained, and a dynamic update model is established based on the boiler combustion conditions; according to the boundary conditions of the boiler combustion conditions, the boundary conditions are non-linearly rolled and optimized, and control parameters corresponding to the boundary conditions are generated; based on the control parameters, the boiler combustion conditions are adjusted, and the difference between the predicted output of the dynamic update model and the key boiler combustion performance indicators is calculated. By establishing a dynamic update model, the present invention uses the boiler combustion conditions as input conditions to predict the key boiler combustion performance indicators, compares the predicted results of the key boiler combustion performance indicators with the actual results, and feeds back and corrects the optimization process of the boiler combustion conditions with the comparison results to form a closed-loop control without manual intervention. At the same time, the present invention can also adaptively conform to the change of coal type through dynamic data correction. Compared with the traditional boiler combustion control method, the prediction effect in this method is greatly improved. Under the same error threshold, the new update strategy can achieve better prediction results with fewer model update times. At the same time, historical operation data is used to screen the historical best operation mode, and the best opening degrees of the secondary air damper and the burnout air damper that take into account the boiler efficiency and NOx under the steady-state operation condition are obtained to realize preliminary combustion optimization.

[0068] Embodiment 2

[0069] On the other hand, the present invention also provides a boiler combustion optimization control system. Please refer to Figure 2 , which shows a schematic structural diagram of the boiler combustion optimization control system in Embodiment 2 of the present invention. The boiler combustion optimization control system includes:

[0070] A model establishment module 11, configured to obtain boiler combustion conditions and key boiler combustion performance indicators, and establish a dynamic update model based on the boiler combustion conditions;

[0071] A rolling optimization module 12, configured to non-linearly roll and optimize the boundary conditions according to the boundary conditions of the boiler combustion conditions, and generate control parameters corresponding to the boundary conditions;

[0072] A difference calculation module 13, configured to adjust the boiler combustion conditions based on the control parameters, and calculate the difference between the predicted output of the dynamic update model and the key boiler combustion performance indicators.

[0073] Obtain boiler combustion conditions and key boiler combustion performance indicators. The boiler combustion conditions include oxygen content set value, burnout air damper opening degree, secondary air damper opening degree, and coal feeding amount offset, etc. The key boiler combustion performance indicators at least include boiler efficiency, NOx concentration, and reheated steam temperature, etc.

[0074] Meanwhile, taking the oxygen content set value, the burnout air damper opening, the secondary air damper opening, and the coal feed quantity offset as input variables, and taking the boiler efficiency, the NOx concentration, and the reheater steam temperature as output variables, a dynamic update model is established.

[0075] The process of establishing the dynamic update model is as follows:

[0076] Respectively determine the oxygen content set value of the boiler under different loads and coal qualities, as well as the boiler efficiency and the discharged NOx concentration corresponding to the oxygen content set value; adjust the burnout air ratio through the burnout air damper to ensure complete combustion of the fuel, and adjust the opening of each layer of air dampers according to the burner load distribution and the flame center position to avoid local oxygen deficiency or excessive air; adjust the fuel distribution of each burner to avoid local overloading or underloading;

[0077] By analyzing the non-linear relationship between the input variables of the oxygen content set value, the burnout air damper opening, the secondary air damper opening, and the coal feed quantity offset and the output variables of the boiler efficiency, the NOx concentration, and the reheater steam temperature in the historical moment data, a dynamic update model is constructed;

[0078] Establish a dynamic update model:

[0079]

[0080] Among them, f(x) is the predicted output of the conversion model, x is the input variable, x i is the i-th input sample vector in the training data, b is the bias term, α i is the Lagrange multiplier, σ is the width parameter, and N is the number of samples;

[0081] x(t) = [Load(t), CoalQuality(t), O2(t - 1), D ofa (t

[0082] - 1), D sec (t - 1), Δm(t - 1)]

[0083] Among them, t is the current moment, t - 1 is the historical moment, x(t) is the input variable at the current moment, Load(t) is the boiler load at the current moment, CoalQuality(t) is the coal quality at the current moment, O2(t - 1) is the oxygen content set value at the historical moment, D ofa (t - 1) is the burnout air damper opening at the historical moment, D sec (t - 1) is the secondary air damper opening at the historical moment, Δm(t - 1) is the coal feed quantity offset at the historical moment, and V(t) is the predicted output of the boiler efficiency, the NOx concentration, and the reheater steam temperature.

[0084] It should be noted that the input variables in this embodiment include but are not limited to the oxygen content set value, the burnout air damper opening, the secondary air damper opening, and the coal feed bias. The output variables include but are not limited to the boiler efficiency, the NOx concentration, and the reheat steam temperature. By introducing historical input and output data (such as the fuel quantity, the air supply quantity, and the furnace temperature at previous moments) as the input of the dynamic model, a state space containing delay terms is constructed to accurately describe the dynamic evolution process of the combustion state. The dynamic characteristics of the boiler are significantly different under different working conditions such as startup, peak shaving, and steady-state operation. The dynamic update model can flexibly adapt to the change of working conditions by adjusting the input parameters, avoiding the limitations of traditional linear models in non-linear scenarios.

[0085] Determine the upper limit threshold of the NOx concentration, the upper and lower limit thresholds of the reheat steam temperature and other output variables as the optimization objectives, and set the boundary conditions of the boiler combustion conditions. The boundary conditions at least include the upper and lower limit thresholds of the oxygen content set value, the upper and lower limit thresholds of the burnout air damper opening, the upper and lower limit thresholds of the secondary air damper opening and other input variables.

[0086] In addition, in some application scenarios, with the operation of the boiler, disturbances such as coal quality may cause the accuracy of the initial model to decrease. When the coal type is switched from bituminous coal to lignite (the calorific value decreases and the moisture content increases), through the adaptive adjustment of the dynamic update model, the model automatically increases the coal feed bias (the total fuel quantity increases), at the same time adjusts the secondary air damper opening (increases the lower-layer secondary air to strengthen ignition), and increases the oxygen content set value (compensates for the heat absorption of moisture evaporation), avoiding the combustion instability caused by manual adjustment.

[0087] Based on each sampling moment, based on the current combustion state and optimization objective of the boiler, analyze the boundary condition data at historical moments, and generate control parameters using the least squares support vector machine dynamic model.

[0088] After obtaining the control parameters, apply the control parameters obtained at the current sampling moment to the input variables such as the oxygen content set value, the burnout air damper opening, and the secondary air damper opening to update the boiler combustion conditions, record the updated boiler combustion conditions, and synchronously update the key performance indicators of boiler combustion within a sampling moment period, and synchronously record the data of the updated key performance indicators of boiler combustion.

[0089] After updating the boiler combustion conditions and the key performance indicators of boiler combustion, use the updated boiler combustion conditions as input variables and input them into the dynamic update model to generate a predicted output, calculate the difference between the predicted output and the updated key performance indicators of boiler combustion, and feedback the difference to the optimization process of the key performance indicators of boiler combustion to correct the boiler combustion conditions.

[0090] By applying the dynamic update model in this embodiment to a boiler, compared with non-update and traditional update strategies, the prediction effect of the new update strategy has been greatly improved. Under the same error threshold, the new update strategy can achieve better prediction effects with fewer model update times. The historical best operation mode is screened using historical moment data to obtain the optimal secondary air damper opening, burnout air damper opening, and flue gas oxygen content that take into account both boiler efficiency and NOx under steady-state operation conditions, thereby achieving preliminary combustion optimization. At the same time, based on the instructions given by the preliminary optimization, within a certain range, the economic predictive control technology is further used for online secondary optimization to achieve closed-loop dynamic combustion optimization and better overcome the influence of uncertain factors such as coal type changes.

[0091] In summary, according to a boiler combustion optimization control system proposed by the present invention, boiler combustion conditions and key boiler combustion performance indicators are obtained, and a dynamic update model is established based on the boiler combustion conditions; according to the boundary conditions of the boiler combustion conditions, the boundary conditions are non-linearly roll-optimized, and control parameters corresponding to the boundary conditions are generated; based on the control parameters, the boiler combustion conditions are adjusted, and the difference between the predicted output of the dynamic update model and the key boiler combustion performance indicators is calculated. By establishing a dynamic update model, using the boiler combustion conditions as input conditions to predict the key boiler combustion performance indicators, comparing the predicted results of the key boiler combustion performance indicators with the actual results, and using the comparison results to feedback-correct the optimization process of the boiler combustion conditions to form a closed-loop control without manual intervention. At the same time, the present invention can also adaptively conform to the change of coal type through dynamic data correction. Compared with traditional boiler combustion control methods, the prediction effect in this method has been greatly improved. Under the same error threshold, the new update strategy can achieve better prediction effects with fewer model update times. At the same time, the historical best operation mode is screened using historical operation data to obtain the optimal secondary air damper opening and burnout air damper opening that take into account both boiler efficiency and NOx under steady-state operation conditions, thereby achieving preliminary combustion optimization.

[0092] Embodiment III

[0093] On the other hand, the present invention also proposes a computer-readable storage medium, on which one or more computer programs are stored, and when the program is executed by a processor, the above-mentioned boiler combustion optimization control method is implemented.

[0094] Those skilled in the art can understand that the logic or steps represented in the flowchart or described in other ways herein, for example, can be considered as a fixed sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable storage medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable storage medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in combination with an instruction execution system, apparatus, or device.

[0095] More specific examples (non-exhaustive list) of computer-readable storage media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable storage medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or, if necessary, other suitable processing, and then stored in a computer memory.

[0096] Embodiment 4

[0097] Figure 3 A structural block diagram of an electronic device provided for Embodiment 4. The electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the boiler combustion optimization control method in the above embodiments. Figure 3 The shown electronic device 30 is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present invention.

[0098] As Figure 3 shown, the electronic device 30 can be presented in the form of a general computing device, for example, it can be a server device. The components of the electronic device 30 can include, but are not limited to: at least one of the above-mentioned processors 31, at least one of the above-mentioned memories 32, and a bus 33 connecting different system components (including the memory 32 and the processor 31).

[0099] The bus 33 includes a data bus, an address bus, and a control bus.

[0100] The memory 32 may include volatile memory, such as RAM 321 (Random Access Memory), and / or cache memory 322, and may further include ROM 323 (Read-Only Memory).

[0101] The memory 32 may also include a program tool 325 having a set (at least one) of program modules 324. Such program modules 324 include but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0102] The processor 31 executes various functional applications and data processing by running computer programs stored in the memory 32, such as the boiler combustion optimization control method described above in the present invention.

[0103] The electronic device 30 may also communicate with one or more external devices 34 (such as a keyboard, a pointing device, etc.). Such communication may be carried out through the I / O interface 35 (Input / Output Interface). Moreover, the electronic device 30 for model generation may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 36. As Figure 3 shown, the network adapter 36 communicates with other modules of the electronic device 30 for model generation through the bus 33. It should be understood that although not shown in the figure, other hardware and / or software modules may be used in combination with the electronic device 30 for model generation, including but not limited to: microcode, device drivers, redundant processors, disk drive arrays, RAID (Redundant Array of Independent Disks) systems, tape drives, and data backup storage systems, etc.

[0104] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present invention, the features and functions of two or more of the above-described units / modules may be embodied in one unit / module. Conversely, the features and functions of one unit / module described above may be further divided and embodied by multiple units / modules.

[0105] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations 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 one or more embodiments or examples in a suitable manner.

[0106] The embodiments described above merely represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation to the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the appended claims.

Claims

1. A boiler combustion optimization control method, characterized in that, The boiler combustion optimization control method includes: Obtaining the boiler combustion conditions and the key performance indicators of boiler combustion, and establishing a dynamically updated model based on the boiler combustion conditions; According to the boundary conditions of the boiler combustion conditions, performing non-linear rolling optimization on the boundary conditions, and generating control parameters corresponding to the boundary conditions; Adjusting the boiler combustion conditions based on the control parameters, and calculating the difference between the predicted output of the dynamically updated model and the key performance indicators of boiler combustion.

2. The boiler combustion optimization control method according to claim 1, characterized in that The steps of obtaining the boiler combustion conditions and the key performance indicators of boiler combustion, and establishing a dynamically updated model based on the boiler combustion conditions include: The boiler combustion conditions at least include the oxygen content set value, the burnout air damper opening, the secondary air damper opening, and the coal feeding amount offset, and the key performance indicators of boiler combustion at least include the boiler efficiency, the NOx concentration, and the reheat steam temperature; Setting the oxygen content set value, the burnout air damper opening, the secondary air damper opening, and the coal feeding amount offset as input variables, and setting the boiler efficiency, the NOx concentration, and the reheat steam temperature as output variables to establish a dynamically updated model.

3. The boiler combustion optimization control method according to claim 2, characterized in that The establishment process of the dynamically updated model is: Respectively determining the oxygen content set value of the boiler under different loads and coal qualities, and the boiler efficiency and the NOx concentration discharged corresponding to the oxygen content set value; adjusting the burnout air ratio through the burnout air damper to ensure complete combustion of the fuel, and adjusting the opening of each layer of air damper according to the burner load distribution and the flame center position to avoid local oxygen deficiency or excessive air; adjusting the fuel distribution of each burner to avoid local overload or underload; By analyzing the non-linear relationship between the input variables of the oxygen content set value, the burnout air damper opening, the secondary air damper opening, and the coal feeding amount offset and the output variables of the boiler efficiency, the NOx concentration, and the reheat steam temperature in the historical moment data, constructing a dynamically updated model; Establishing a dynamically updated model: where f(x) is the predicted output of the conversion model, x is the input variable, and x i is the i-th input sample vector in the training data, b is the bias term, and α i is the Lagrange multiplier, σ is the width parameter, and N is the number of samples; x(t) = [Load(t), CoalQuality(t), O2(t - 1), D ofa (t -1), D sec (t - 1), Δm(t - 1)] Among them, t is the current moment, t - 1 is the historical moment, x(t) is the input variable at the current moment, Load(t) is the boiler load at the current moment, CoalQuality(t) is the coal quality at the current moment, O2(t - 1) is the oxygen content set value at the historical moment, D ofa (t - 1) is the opening of the burnout air damper at the historical moment, D sec (t - 1) is the opening of the secondary air damper at the historical moment, Δm(t - 1) is the coal feed bias at the historical moment, and V(t) is the predicted output of the boiler efficiency, NOx concentration, and reheat steam temperature.

4. The boiler combustion optimization control method according to claim 1, characterized in that, The steps of performing non-linear rolling optimization on the boundary conditions according to the boundary conditions of the boiler combustion conditions and generating control parameters corresponding to the boundary conditions include: Determining the upper limit threshold of the NOx concentration and the upper and lower limit thresholds of the reheat steam temperature as the optimization objectives, and setting the boundary conditions of the boiler combustion conditions, where the boundary conditions at least include the upper and lower limit thresholds of the oxygen content set value, the upper and lower limit thresholds of the burnout air damper opening, and the upper and lower limit thresholds of the secondary air damper opening; Based on each sampling moment, based on the current combustion state of the boiler and the optimization objective, analyzing the boundary condition data of the historical moment, and generating control parameters using the least squares support vector machine dynamic model.

5. The boiler combustion optimization control method according to claim 1, characterized in that The steps of adjusting the boiler combustion conditions based on the control parameters and calculating the difference between the predicted output of the dynamically updated model and the key performance indicators of boiler combustion include: After obtaining the control parameters, applying the control parameters obtained at the current sampling moment to the oxygen content set value, the burnout air damper opening, and the secondary air damper opening to update the boiler combustion conditions, and synchronously updating the key performance indicators of boiler combustion within a sampling moment period.

6. The boiler combustion optimization control method according to claim 5, characterized in that, The steps after updating the boiler combustion conditions and the key performance indicators of boiler combustion are: The updated boiler combustion conditions are used as input variables and input into the dynamic update model to generate a predicted output, and the difference between the predicted output and the updated key boiler combustion performance indicators is calculated. The difference is fed back into the optimization process of the key boiler combustion performance indicators to correct the boiler combustion conditions.

7. A boiler combustion optimization control system, characterized in that, The boiler combustion optimization control system is used to implement the boiler combustion optimization control method according to any one of claims 1-6. The system includes: a model establishment module, configured to obtain boiler combustion conditions and key boiler combustion performance indicators, and establish a dynamic update model based on the boiler combustion conditions; a rolling optimization module, configured to perform non-linear rolling optimization on the boundary conditions according to the boundary conditions of the boiler combustion conditions, and generate control parameters corresponding to the boundary conditions; a difference calculation module, configured to adjust the boiler combustion conditions based on the control parameters, and calculate the difference between the predicted output of the dynamic update model and the key boiler combustion performance indicators.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the boiler combustion optimization control method according to any one of claims 1-6.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the boiler combustion optimization control method according to any one of claims 1-6.

Images