Intelligent regulation method and system based on intelligent power plant combustion efficiency

Abstract

The application relates to the field of power plant combustion monitoring and scheduling, and provides an intelligent regulation and control method and system based on intelligent power plant combustion efficiency, which comprises the following steps: collecting burner outer wall temperature distribution data in real time through an infrared temperature measurement array, calculating the heat absorption percentage in combination with the water wall inlet and outlet working medium temperature difference, generating a temperature gradient vector by adopting a four-point central difference method and tracking an actual flame trajectory line. Then, the actual flame three-dimensional curve is reconstructed, and the actual curve is dynamically compared with a pre-stored design curve. When the flame offset amount exceeds a threshold value and the heat absorption percentage decreases, the coal supply amount is automatically increased; when the offset amount does not exceed the threshold value but the heat absorption continuously decreases, the air supply amount is gradually increased, thereby forming a double-parameter closed-loop control of the real-time flame shape and the water wall heat exchange efficiency. Through the collaborative diagnosis of the three-dimensional flame shape and the thermal efficiency, the dynamic correction of the combustion state is realized, so that the boiler combustion system is always maintained in the best thermal efficiency interval.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power plant combustion monitoring and scheduling, in particular to an intelligent regulation and control method and system based on intelligent power plant combustion efficiency. BACKGROUND

[0002] The content of this part only provides background information related to the present application, which may not constitute prior art.

[0003] In the field of thermal power generation, the industrial control system of the power plant has long been challenged by combustion optimization and safety monitoring. The supervisory control and data acquisition (SCADA) system of the traditional burner relies on manual experience to adjust the air-coal ratio, lacks real-time three-dimensional quantitative analysis of flame shape, and leads to lag in industrial monitoring and scheduling.

[0004] In the prior art, a patent with publication number CN102541036A discloses an intelligent scheduling system for coal-fired power plants. An intelligent stacking calculation module determines the optimal coal stacking position to guide the stacker unit to complete coal stacking. An intelligent coal blending and coal feeding calculation module is used to receive the coal stacking information of the online coal stacking unit and the real-time state of the boiler unit, determine the coal blending scheme based on the coal stacking information and the real-time state of the boiler unit, and then determine the coal feeding scheme based on the boiler characteristics and the coal blending scheme. The material taking decision module determines the material taking approach based on the coal stacking information and the coal feeding scheme to guide the stacker unit and the coal conveying unit to cooperate to complete material taking. The system realizes the full life cycle management and intelligent scheduling of the power plant coal, and ensures that the boiler unit has high safety, economy and environmental protection under the condition of mixed burning.

[0005] The limitation of the prior art is that it mainly relies on static coal data and boiler operating condition information in scheduling decision-making, and fails to incorporate dynamic feedback of real-time combustion state into closed-loop control, resulting in a lag in response to sudden deviations or efficiency drops during the combustion process, and unable to timely correct the deviation of fuel supply and air ratio. SUMMARY

[0006] To solve the above technical problems, the purpose of the present application is to provide an intelligent regulation and control method and system based on intelligent power plant combustion efficiency, which constructs a real-time flame three-dimensional curve through infrared temperature measurement array and water wall temperature difference monitoring, and compares it with the design curve to realize closed-loop regulation and control of fuel supply and air supply, solves the response lag problem caused by the dependence of traditional methods on static data, makes the combustion efficiency deviation automatically corrected within the threshold range, and ensures high combustion efficiency.

[0007] The purpose of the present application is achieved by the following technical solutions:

[0008] In a first aspect, the present application provides an intelligent regulation and control method based on intelligent power plant combustion efficiency, comprising:

[0009] The load demand change signal is obtained in real time by connecting the power grid dispatching system, and the power grid load is regulated, including: obtaining the corresponding design flame three-dimensional curve according to the load demand, and injecting the corresponding fuel quantity and air quantity into the burner;

[0010] The temperature distribution data of the outer wall of the burner is obtained by the infrared temperature measurement array at a preset frequency; the temperature sensors arranged at the inlet pipe and outlet pipe of the water cooling wall obtain the working medium temperature difference of the water cooling wall; the actual temperature difference and the design maximum temperature difference are calculated to obtain the heat absorption percentage;

[0011] Based on the temperature distribution data, the temperature gradient vector of each measurement point is calculated by using the adjacent four-point central difference method, and the gradient vector direction is continuously tracked on each surface to form the corresponding actual flame trajectory line;

[0012] Two adjacent and perpendicular first and second surfaces on the sidewall of the burner are selected, and positioning points are marked on the actual flame trajectory line of the first surface at a preset distance, and all the positioning points are projected onto the actual flame trajectory line of the second surface; the actual flame three-dimensional curve is established according to the positioning points on the first and second surfaces;

[0013] The actual flame three-dimensional curve is compared with the pre-stored design flame three-dimensional curve, and the flame offset is output;

[0014] If the flame offset exceeds the threshold value and the heat absorption percentage of the water cooling wall decreases to a preset amplitude, it is determined that the fuel supply is insufficient, and the coal supply is increased by the fuel supply control system according to the preset gradient until the offset returns to the threshold value range; when the flame offset does not exceed the threshold value, but the heat absorption percentage is lower than the reference value within a continuous preset time, it is determined that the air supply is insufficient, and the air supply is increased by the damper actuator in a step-by-step manner until the heat absorption percentage returns to the reference value.

[0015] Further, the step of projecting all the positioning points onto the actual flame trajectory line of the second surface comprises:

[0016] The positioning points of the actual flame trajectory line of the first surface are projected onto the second surface to generate first projection points with original height characteristics;

[0017] Based on the preset elevation reference of the actual flame trajectory line of the second surface, the first projection points are linearly scaled in the vertical direction to align the projection point height with the target trajectory line;

[0018] The calibrated projection points are projected onto the actual flame trajectory line of the second surface for a second time, so that the positioning points of the second projection fall on the actual flame trajectory line on the second surface.

[0019] Further, the step of establishing the actual flame three-dimensional curve according to the positioning points on the first plane and the second plane specifically comprises:

[0020] scaling the actual flame trajectory line on the first plane and the actual flame trajectory line on the second plane to the same height in equal proportion;

[0021] drawing a first ray from the positioning point on the first plane in a direction perpendicular to the first plane, and drawing a second ray from the twice-projected positioning point on the second plane in a direction perpendicular to the second plane;

[0022] selecting all intersection points of the first ray and the second ray, sequentially connecting each intersection point, and performing smooth transition processing on the connected line segment to obtain the actual flame three-dimensional curve.

[0023] Further, the formula corresponding to the step of establishing the actual flame three-dimensional curve according to the positioning points on the first plane and the second plane is:

[0024]

[0025] In the formula, C(u) is a parameterized flame three-dimensional curve, N i,p (u) is a p-order B-spline basis function, (x B , y A ) is the original coordinate of the double-plane orthogonal projection (i.e., the x coordinate of the second plane and the y coordinate of the first plane), Z cal is the calibrated vertical coordinate, H ref is the scaling coefficient of the reference elevation, H raw is the original elevation scaling coefficient, n is the number of control points participating in B-spline curve fitting, i is the control point index, and p is the spline order.

[0026] Further, the step of increasing the air supply in a step-by-step manner by the damper actuator until the heat absorption percentage returns to the reference value specifically comprises:

[0027] Increasing the air supply in a step-by-step manner by the damper actuator, waiting for thermal inertia to stabilize after each adjustment for a preset time, and until the heat absorption percentage returns to the preset interval of the reference value.

[0028] Further, after the heat absorption percentage returns to the reference value, it further comprises:

[0029] Establishing a dynamic fluctuation database of the flame three-dimensional curve to record the flame shape change parameters before and after each compensation.

[0030] Further, it further comprises:

[0031] Traversing the temperature distribution data, when the temperature difference between any position and its adjacent position is greater than a preset value, determining that the position is a hole position, collecting all adjacent hole positions to form a hole region, marking the hole region and alarming.

[0032] In a second aspect, the present application provides an intelligent combustion efficiency control system for a smart power plant, comprising:

[0033] A power grid load dynamic response module is configured to acquire a load demand change signal in real time by connecting to a power grid dispatching system, and to control the power grid load, including: acquiring a corresponding designed flame three-dimensional curve according to the load demand, and injecting a corresponding amount of fuel and air into the burner;

[0034] A data acquisition module is configured to acquire temperature distribution data of the outer wall of the burner at a preset frequency by an infrared temperature measurement array, to acquire a working medium temperature difference of the water cooling wall by temperature sensors arranged at the inlet and outlet pipes of the water cooling wall, and to calculate a heat absorption percentage of an actual temperature difference and a designed maximum temperature difference;

[0035] A two-dimensional trajectory reconstruction module is configured to calculate a temperature gradient vector of each measurement point by using a four-point central difference method according to the temperature distribution data, and to continuously track the gradient vector direction on each surface to form a corresponding actual flame trajectory line;

[0036] A three-dimensional trajectory reconstruction module is configured to select two adjacent and perpendicular first and second surfaces on the sidewall of the burner, to mark positioning points on the actual flame trajectory line of the first surface at a preset distance, to project all the positioning points onto the actual flame trajectory line of the second surface, and to establish an actual flame three-dimensional curve according to the positioning points on the first and second surfaces;

[0037] An offset amount acquisition module is configured to compare the actual flame three-dimensional curve with a pre-stored designed flame three-dimensional curve, and to output a flame offset amount;

[0038] A control module is configured to determine that the fuel supply is insufficient when the flame offset amount exceeds a threshold value and the heat absorption percentage of the water cooling wall decreases by a preset amplitude, to increase the coal supply by a preset gradient through a fuel supply control system until the offset amount returns to a threshold range, to determine that the air supply is insufficient when the flame offset amount does not exceed the threshold value but the heat absorption percentage is lower than a reference value within a continuous preset time, and to increase the air supply in a step-by-step manner through an air door actuator until the heat absorption percentage returns to the reference value.

[0039] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements steps corresponding to the method of the first aspect when executing the computer program.

[0040] In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the program is executable by a processor to implement steps corresponding to the method of the first aspect.

[0041] In summary, the technical scheme of the embodiment of the application has at least the following advantages and beneficial effects:

[0042] The application obtains the real-time heat absorption percentage by scanning the temperature field of the outer wall of the burner at a preset frequency through the infrared temperature measurement array, synchronously collecting the temperature sensor data of the inlet and outlet pipelines of the water cooling wall to calculate the actual temperature difference of the working medium, and combining the designed maximum temperature difference. The system adopts the four-point central difference algorithm to process the temperature distribution data, point-by-point calculates the temperature gradient vector, and traces along the vector direction to form the actual flame trajectory line of each monitoring surface. By selecting two orthogonal planes of the side wall of the burner, the equidistant positioning points of the trajectory line of the first plane are projected to the trajectory line of the second plane, and the actual flame three-dimensional curve under the spatial coordinate system is established. The curve is compared with the pre-stored design curve to obtain the flame offset, and when the offset exceeds the limit and the heat absorption percentage decreases, the gradient compensation mechanism of the fuel supply control system is triggered, the coal quantity is adjusted through closed loop to make the flame shape return to the design value; when the heat absorption percentage continuously decreases below the reference value but the flame offset does not exceed the limit, the step-by-step air supply optimization of the air door actuator is started. Through the dual-dimension monitoring of the infrared temperature measurement and the temperature difference of the water cooling wall, the real-time three-dimensional modeling of the flame shape and the heat exchange efficiency of the burner is realized, the dynamic compensation system of the fuel-air linkage is constructed, the response lag problem of the traditional single-parameter control is solved, and the boiler combustion system is always maintained in the best heat efficiency interval. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 A flowchart of an intelligent control method based on the combustion efficiency of a smart power plant is provided in the application.

[0044] Figure 2 A schematic diagram of the actual flame trajectory line of the first plane is provided in the application.

[0045] Figure 3 A schematic diagram of the actual flame trajectory line of the second plane is provided in the application.

[0046] Figure 4 A schematic diagram of the projection of the first plane to the second plane is provided in the application.

[0047] Figure 5 A structural schematic diagram of an intelligent control system based on the combustion efficiency of a smart power plant is provided in the application.

[0048] Figure 6 A structural schematic diagram of an electronic device is provided in the application. DETAILED DESCRIPTION

[0049] To make the purposes, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0050] As shown in Figure 1 The intelligent regulation and control method based on the combustion efficiency of a smart power plant according to the embodiments of the present application comprises the following steps.

[0051] S101, a load demand change signal is acquired in real time by connecting a power grid dispatching system, and regulation and control is performed according to the power grid load, which comprises the following steps: a corresponding design flame three-dimensional curve is acquired according to the load demand, and a corresponding fuel quantity and air quantity are injected into the burner.

[0052] Specifically, a real-time data channel of the combustion control system and the power grid dispatching system is established by an industrial communication protocol (such as IEC 61850), and when the power grid load demand signal fluctuates, the dispatching system sends a digital instruction containing the load change amplitude, duration, and other parameters. After the combustion control system analyzes the instruction, a design flame three-dimensional curve matched with the current load is retrieved from a pre-stored flame shape database, the curve defines the spatial distribution characteristics of the flame in the burner under ideal working conditions, including the flame height, radial expansion angle, core zone temperature gradient, and other key parameters.

[0053] S102, temperature distribution data of the outer wall of the burner is acquired at a preset frequency by an infrared temperature measurement array; the temperature difference of the working medium entering and exiting the water cooling wall is acquired by temperature sensors arranged at the inlet pipe and outlet pipe of the water cooling wall; and the heat absorption percentage of the actual temperature difference and the design maximum temperature difference is calculated.

[0054] Specifically, this step realizes accurate diagnosis of the combustion state through a double temperature monitoring mechanism. First, an infrared temperature measurement array scans the outer wall of the burner at a preset frequency of no less than 10 Hz to obtain a temperature distribution data matrix composed of 256 temperature measurement points. The working principle is based on the Stefan-Boltzmann law, which reverses the surface temperature by detecting the infrared wavelength of the metal wall radiation. For example, a certain 600 MW unit adopts an 8x32 annular array layout, which can capture the temperature change every 11.25° interval in the circumferential direction of the burner, and the temperature measurement accuracy is ±2℃. Simultaneously, PT100 temperature sensors arranged in the inlet and outlet pipes of the water wall transmit the working medium temperature through 4-20 mA current signals, and the actual temperature difference is obtained by calculating the difference between the output temperature and the input temperature. The maximum temperature difference is taken from the thermal calculation under the rated load of the boiler, for example, the maximum temperature difference of a certain supercritical unit is 85℃, and when the measured temperature difference is 68℃, the heat absorption percentage is (68 / 85) x 100% = 80%. The infrared data reflect the spatial distribution characteristics of the flame, which can identify abnormalities such as flame deflection and wall sticking; the water wall temperature difference directly represents the heat transfer efficiency, and the combination of the two can eliminate false judgments of a single signal.

[0055] S103, based on the temperature distribution data, the temperature gradient vector of each measurement point is calculated by using the adjacent four-point central difference method, and the gradient vector direction is continuously tracked on each surface to form a corresponding actual flame trajectory line.

[0056] Specifically, the core of this step is to accurately reconstruct the spatial form of the flame through temperature gradient vector calculation. First, based on the 256-point temperature distribution data matrix obtained by the infrared temperature measurement array, the temperature gradient vector of each measurement point is calculated by using the adjacent four-point central difference method. This method selects the temperature values of the target point and its four adjacent points (i.e. above, below, left and right) to calculate the horizontal and vertical temperature change rates, and synthesizes a two-dimensional gradient vector. For example, the temperatures of the four adjacent points of the burner outer wall temperature measurement point of a certain 600 MW unit are 62℃, 58℃, 65℃ and 60℃ at an interval of 11.25° in the circumferential direction, and the gradient vector direction is northeast by east 15°, indicating that there is obvious oblique heat flow distribution in this area. This gradient calculation method can effectively eliminate single-point temperature fluctuation interference and accurately reflect the heat flow direction characteristics of the flame. Subsequently, the gradient vector directions of the measurement points are continuously tracked to form actual flame trajectory lines on each measurement surface. In specific implementation, the measurement points with consistent gradient directions are connected in sequence along the circumferential direction to form a continuous curve reflecting the position of the flame front. The specific calculation process is as follows:

[0057] The adjacent four-point central difference method is used to calculate the temperature gradient vector of each measurement point as follows:

[0058]

[0059] In the formula, Δx is the temperature gradient vector at point (i,j); i and j represent the horizontal and vertical coordinate indices of the discrete grid points, respectively; Δx is the horizontal spacing between the temperature measurement points, and Δy is the vertical spacing between the temperature measurement points.

[0060] The gradient direction is:

[0061]

[0062] In the formula, θ is the radian of the direction of flame heat flow. Let be the gradient component of the temperature field in the y-direction. Let be the gradient component of the temperature field in the x-direction.

[0063] S104, Select two adjacent and mutually perpendicular first and second surfaces on the burner sidewall, mark positioning points at preset distances on the actual flame trajectory line of the first surface, and project all positioning points onto the actual flame trajectory line of the second surface; establish the actual flame three-dimensional curve based on the positioning points on the first and second surfaces.

[0064] Specifically, the core of this step lies in achieving spatial positioning of the flame trajectory using dual-plane projection technology. In practice, two adjacent and mutually perpendicular surfaces, a first and a second, on the burner sidewall are first selected as reference measurement planes. These two planes are typically arranged at 90° intervals around the burner to form an orthogonal observation system. Positioning points are marked at predetermined intervals along the actual flame trajectory line on the first surface, such as... Figure 2 The black dots shown represent the two-dimensional coordinates of different positions of the flame. During projection, the positioning points of the actual flame trajectory line on the first surface are projected onto the second surface, generating a first projection point with original height characteristics. The continuity of spatial coordinates is maintained using the geometric constraints between orthogonal planes. Due to elevation differences caused by installation tolerances on different measurement surfaces, the first projection point needs to be linearly scaled vertically based on the preset elevation reference of the second surface. Therefore, based on the preset elevation reference of the actual flame trajectory line on the second surface, the first projection point is linearly scaled vertically to align its height with the target trajectory line. Figure 4 As shown, the left line segment represents the actual flame trajectory line of the first surface, and the black dots on this trajectory line are the positioning points of the first surface. The right line represents the actual flame trajectory line of the second surface, and the black dots on this trajectory line are the projected points of the second surface. The dashed line is a schematic diagram of the relationship between the positioning point projections and has no practical significance. For example, a 1000MW unit uses the burner centerline as the reference elevation and corrects installation deviations using a scaling factor of 0.98. After calibration, the calibrated projection points are projected a second time onto the actual flame trajectory line of the second surface, so that the positioning points of the second projection fall on the actual flame trajectory line of the second surface. This process uses a minimum distance projection algorithm to ensure spatial consistency.

[0065] When establishing the actual flame three-dimensional curve, the actual flame trajectory line on the first plane and the actual flame trajectory line on the second plane are scaled to the same height in equal proportion; that is, the scale difference is eliminated through height normalization processing, for example, the first plane trajectory line is scaled to the same maximum height value as the second plane. Then the first plane positioning point is introduced to the first ray in the direction perpendicular to the plane, and the second plane positioning point is introduced to the second ray in the normal direction, and the two sets of rays form a cross network in the three-dimensional space. Select all the intersection points of the rays to form a set of space points, for example, a 660 MW supercritical unit obtains 172 effective intersection points during implementation, and through the B-spline curve algorithm, these points are connected in turn and smooth constraint is applied, and finally a continuous actual flame three-dimensional curve is generated. The spatial accuracy of the curve depends on the density of the positioning points, and in a typical implementation case, the positioning points are set every 10 mm of axial spacing, which can control the reconstruction error within ±3 mm. The specific calculation process is as follows:

[0066] Double-plane orthogonal projection coordinate system definition: let the coordinate system of the first plane be (x A ,y A ), and the coordinate system of the second plane be (x B ,z B ), the two planes are arranged orthogonally and share the z axis. The geometric constraint is that the y axis of the first plane is parallel to the z axis of the second plane, which ensures the consistency of the projection direction.

[0067] Positioning point projection and calibration: take point P A (x A ,y A ) from the flame trajectory line of plane A, and eliminate the installation deviation through height calibration:

[0068]

[0069] In the formula, Z cal is the calibrated vertical coordinate, H A is the maximum measurement height of the first plane, and H B is the reference elevation of the second plane.

[0070] The ray equation of the first plane is (in the y axis direction):

[0071]

[0072] The ray equation of the second plane (in the x axis direction):

[0073]

[0074] According to formulas (4) and (5):

[0075] x=x B (6)

[0076] y=y A(7)

[0077] z = z B (8)

[0078] Based on formulas (3), (6), (7) and (8), the points are sequentially connected by a B-spline curve algorithm and a smooth constraint is applied to obtain:

[0079]

[0080] In the formula, C(u) is a parameterized three-dimensional flame curve, N i,p (u) is a p-th B-spline basis function, (x B ,y A ) is the original coordinate of the double plane orthogonal projection (i.e., the x coordinate of the second plane and the y coordinate of the first plane), Z cal is the calibrated vertical coordinate, H ref is the scaling coefficient of the reference elevation, H raw is the original elevation scaling coefficient, n is the number of control points participating in the B-spline curve fitting, i is the control point index, and p is the spline order.

[0081] S105, comparing the actual three-dimensional flame curve with the pre-stored design three-dimensional flame curve, and outputting a flame offset.

[0082] In specific implementation, the actual three-dimensional flame curve generated in S104 is imported into a three-dimensional coordinate system for spatial registration, the coordinate system takes the burner center line as the Z-axis reference, and the XYZ space reference system is established using the right-hand rule. The comparison process first performs a reference alignment operation, that is, the root positioning points of the two curves are made to coincide by least square fitting to eliminate systematic errors caused by installation deviation. Subsequently, a point-by-point scanning method is used to calculate the spatial offset, which specifically includes three key parameters: radial offset, axial offset and circumferential offset. The radial offset refers to the deviation distance of the actual flame profile from the design profile in the horizontal direction, reflecting whether the flame center deviates from the geometric center of the burner; the axial offset represents the advance or lag of the flame front position along the burner axis, directly affecting the fuel burnout; and the circumferential deflection is obtained by calculating the inverse tangent of the tangential angle between the two curves, and is used to diagnose abnormal flame rotation.

[0083] S106, if the flame offset exceeds the threshold value and the heat absorption percentage of the water-cooled wall decreases by a preset amplitude, it is determined that the fuel supply is insufficient, and the fuel supply control system is used to increase the coal supply by a preset gradient until the offset returns to the threshold value range; when the flame offset does not exceed the threshold value but the heat absorption percentage is lower than the reference value for a continuous preset time, it is determined that the air supply is insufficient, and the air door actuator is used to increase the air supply in a step-by-step manner until the heat absorption percentage returns to the reference value.

[0084] In specific implementation, this step realizes accurate regulation of the combustion state through a multi-parameter coupling diagnosis mechanism. When the flame offset exceeds the preset threshold and the water-cooled wall heat absorption percentage synchronously decreases by a preset amplitude, the system determines that it is a fuel supply insufficient condition. The diagnosis principle is based on the correlation between flame morphology and heat transfer efficiency: a significant increase in the radial offset indicates that the flame core area deviates from the geometric center of the burner, resulting in a decrease in the effective flame radiation area; abnormal axial offset reflects insufficient residence time of the fuel in the furnace; excessive circumferential deflection shows that the combustion dynamic field is unbalanced. These offset characteristics are consistent with the typical symptoms of flame contraction and temperature field distortion when the fuel supply is insufficient, and the decrease in the water-cooled wall heat absorption percentage further verifies the decrease in the effective flame heat radiation intensity. At this time, the fuel supply control system increases the coal supply by a preset gradient, which needs to consider the thermal inertia characteristics of the unit, and usually uses a coal supply incremental amplitude of 2% to 5% per minute to avoid sharp adjustment and cause steam temperature fluctuations. During the regulation process, the dynamic change of the flame offset is continuously monitored, and when the offset returns to the threshold range, the compensation is immediately stopped, forming a closed-loop control.

[0085] When the flame offset does not exceed the threshold but the heat absorption percentage is lower than the reference value for three consecutive sampling periods, the system determines that it is a insufficient air supply condition. The diagnosis is based on the fact that under insufficient air supply, although the flame spatial form has not been significantly distorted, insufficient oxygen supply will lead to a decrease in the combustion reaction rate, which is specifically manifested by a decrease in the water-cooled wall working medium temperature difference and a continuous decrease in the heat absorption percentage. At this time, the air door actuator increases the air supply in a step-by-step manner, with each adjustment amplitude controlled within 1% to 2% of the total air volume, and a delay of ninety to one hundred and twenty seconds is waited after adjustment for thermal inertia stability. This delay time is pre-calibrated according to the volumetric heat load characteristics of the boiler. During the regulation process, it is necessary to ensure that the heat absorption percentage returns to the reference value within ±3%, to avoid excessive air supply increasing the exhaust gas loss, and to prevent insufficient air supply causing incomplete combustion.

[0086] In addition, after the heat absorption percentage returns to the reference value, the step further includes: establishing a dynamic fluctuation database of the flame three-dimensional curve to record the flame form change parameters before and after each compensation.

[0087] Specifically, after completing the regulation operation of returning the heat absorption percentage to the reference value, the system automatically starts the construction process of the dynamic fluctuation database of the flame three-dimensional curve. This database stores the key parameters of the flame form before and after each compensation intervention in a time sequence manner, including the spatial coordinate point set of the actual flame three-dimensional curve, the gradient vector direction matrix, and the three-dimensional component values of the flame offset (radial offset, axial offset, circumferential deflection). Through the accumulation of historical operation data, a dynamic response characteristic library of the combustion system is established, providing data support for intelligent prediction of subsequent similar conditions.

[0088] Further, the method further comprises: traversing the temperature distribution data, when a temperature difference between any position and its adjacent position is greater than a preset value, judging the position as a hole position, collecting all adjacent hole positions to form a hole region, marking the hole region and alarming.

[0089] Specifically, the system first traverses the temperature distribution data matrix composed of 256 temperature measuring points, for each temperature measuring point in the matrix, calculates the temperature difference with the adjacent four directions (i.e. up, down, left and right) temperature measuring points, when the temperature difference of any direction exceeds the preset threshold value (for example, 100℃), it is determined that there is a hole defect at the position of the temperature measuring point. The determination principle is based on the change of heat conduction characteristics of the damaged refractory material: when the burner lining appears a hole, the high-temperature flue gas directly washes the metal wall surface, causing the local temperature to rise sharply, while the adjacent intact area of the refractory material still maintains normal heat insulation performance, thereby forming a significant temperature difference gradient. For example, in the implementation case of a 1000MW ultra-supercritical unit, the temperature of the center point of the hole region can reach 280℃, while the temperature of the surrounding intact area is only 120℃, forming a temperature difference mutation of 160℃. The aggregation processing of the hole region adopts a region growing algorithm to automatically connect all hole positions with a spatial distance less than a preset value (usually 1.5 times the distance between two adjacent temperature measuring points) to form a continuous hole region contour. The system marks the hole region boundary with red contour lines through the man-machine interface, triggers sound and light alarms, and generates an alarm log containing the hole position coordinates, region area (converted to actual size) and maximum temperature value

[0090] Based on the same inventive concept, the present application provides an intelligent control system based on the combustion efficiency of a smart power plant, comprising:

[0091] The power grid load dynamic response module 201 is used to acquire the load demand change signal in real time by connecting the power grid dispatching system, and to control according to the power grid load, including: acquiring the corresponding design flame three-dimensional curve according to the load demand, and injecting the corresponding fuel quantity and air quantity into the burner;

[0092] The data acquisition module 202 is used to acquire the temperature distribution data of the outer wall of the burner at a preset frequency through an infrared temperature measuring array; the temperature sensors arranged at the inlet pipe and outlet pipe of the water wall are used to acquire the working medium temperature difference of the inlet and outlet of the water wall; and the heat absorption percentage of the actual temperature difference and the design maximum temperature difference is calculated;

[0093] The two-dimensional trajectory reconstruction module 203 is used to calculate the temperature gradient vector of each measuring point by using the adjacent four-point central difference method according to the temperature distribution data, and to continuously track the gradient vector direction on each surface to form the corresponding actual flame trajectory line;

[0094] The three-dimensional trajectory reconstruction module 204 selects two adjacent and perpendicular first and second faces on the sidewall of the burner, marks positioning points on the actual flame trajectory line of the first face at preset intervals, projects all the positioning points onto the actual flame trajectory line of the second face, and establishes an actual three-dimensional flame curve according to the positioning points on the first and second faces;

[0095] The offset amount acquisition module 205 is configured to compare the actual three-dimensional flame curve with a pre-stored design three-dimensional flame curve, and output a flame offset amount.

[0096] The control module 206 is configured to determine that the fuel supply is insufficient when the flame offset amount exceeds a threshold value and the heat absorption percentage of the water wall decreases by a preset amplitude, increase the coal supply by a preset gradient through a fuel supply control system until the offset amount returns to the threshold value range, stop compensation, determine that the air supply is insufficient when the flame offset amount does not exceed the threshold value but the heat absorption percentage is lower than a reference value within a continuous preset time, and increase the air supply in a step-by-step manner through an air door actuator until the heat absorption percentage returns to the reference value.

[0097] Based on the same inventive concept, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to realize an intelligent control method based on the combustion efficiency of a smart power plant.

[0098] Based on the same inventive concept, the present application provides a computer readable storage medium having a computer program stored thereon, and the program is executed by a processor to realize an intelligent control method based on the combustion efficiency of a smart power plant.

[0099] The above is only a preferred embodiment of the present application and is not used to limit the present application, and the present application can have various changes and variations for those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A smart control method based on combustion efficiency in smart power plants, characterized in that, include: By connecting to the power grid dispatching system, load demand change signals are obtained in real time, and regulation is carried out according to the power grid load. The regulation includes: obtaining the corresponding three-dimensional curve of the design flame according to the load demand, and injecting the corresponding amount of fuel and air into the burner. The temperature distribution data of the burner outer wall is acquired by an infrared temperature measurement array at a preset frequency; the temperature difference of the working fluid entering and leaving the water-cooled wall is acquired by temperature sensors installed in the inlet and outlet pipes of the water-cooled wall; and the percentage of heat absorption between the actual temperature difference and the design maximum temperature difference is calculated. Based on the temperature distribution data, the temperature gradient vector of each measurement point is calculated using the central difference method of adjacent four points, and the gradient vector direction is continuously tracked on each surface to form the corresponding actual flame trajectory line. Select two adjacent and mutually perpendicular first and second surfaces on the burner sidewall. Mark positioning points at preset distances on the actual flame trajectory line of the first surface. Project all the positioning points onto the actual flame trajectory line of the second surface. Establish the actual flame three-dimensional curve based on the positioning points on the first and second surfaces. The actual flame 3D curve is compared with the pre-stored design flame 3D curve, and the flame offset is output. If the flame deviation exceeds the threshold and the heat absorption percentage of the water-cooled wall drops to the preset range, it is determined that the fuel supply is insufficient. The fuel supply control system increases the coal feed rate according to the preset gradient until the deviation returns to the threshold range and the compensation stops. If the flame deviation does not exceed the threshold but the heat absorption percentage is lower than the benchmark value for a continuous preset time, it is determined that the air supply is insufficient. The air supply is increased in a stepwise manner through the damper actuator until the heat absorption percentage returns to the benchmark value.

2. The intelligent control method based on combustion efficiency of a smart power plant according to claim 1, characterized in that, The step of projecting all the positioning points onto the actual flame trajectory line of the second surface specifically includes: Project the positioning point of the actual flame trajectory line on the first surface onto the second surface to generate a first projection point with the original height characteristics. Based on the preset elevation reference of the actual flame trajectory line on the second side, the first projection point is linearly scaled in the vertical direction so that the height of the projection point is aligned with the target trajectory line. The calibrated projection point is then projected onto the actual flame trajectory line on the second surface, so that the positioning point of the secondary projection falls on the actual flame trajectory line on the second surface.

3. The intelligent control method based on combustion efficiency of a smart power plant according to claim 2, characterized in that, The step of establishing the actual three-dimensional curve of the flame based on the positioning points on the first and second surfaces specifically includes: The actual flame trajectory lines on the first surface and the actual flame trajectory lines on the second surface are scaled proportionally to the same height. Draw a first ray from the positioning point on the first surface in a direction perpendicular to the first surface, and draw a second ray from the positioning point of the secondary projection on the second surface in a direction perpendicular to the second surface. Select all intersection points of the first and second rays, connect each intersection point in sequence, and perform a smooth transition process on the connected line segments to obtain the actual three-dimensional curve of the flame.

4. The intelligent control method based on combustion efficiency of a smart power plant according to claim 3, characterized in that, The formula for establishing the actual three-dimensional curve of the flame based on the positioning points on the first and second surfaces is as follows: In the formula, C(u) is the parameterized three-dimensional flame curve, and N i,p (u) is a p-th degree B-spline basis function, (x) B ,y A Z represents the original coordinates of the biplane orthogonal projection (i.e., the x-coordinate of the second plane and the y-coordinate of the first plane), and Z represents the original coordinates of the biplane orthogonal projection. cal H is the calibrated vertical coordinate. ref H is the scaling factor for the reference elevation. raw is the scaling factor for the original elevation, n is the number of control points participating in the B-spline curve fitting, i is the control point index, and p is the spline degree.

5. The intelligent control method based on combustion efficiency of a smart power plant according to claim 1, characterized in that, The step of increasing the air supply volume in a stepwise manner through the damper actuator until the heat absorption percentage returns to the baseline value specifically includes: The air volume is increased in a stepwise manner by means of damper actuator. After each adjustment, a preset time is delayed to wait for the thermal inertia to stabilize until the heat absorption percentage returns to the preset range of the benchmark value.

6. The intelligent control method based on combustion efficiency of a smart power plant according to claim 1, characterized in that, The process of continuing until the heat absorption percentage returns to the baseline value also includes: Establish a dynamic fluctuation database of three-dimensional flame curves to record the flame morphology change parameters before and after each compensation.

7. The intelligent control method based on combustion efficiency of a smart power plant according to claim 1, characterized in that, Also includes: The temperature distribution data is traversed. When the temperature difference between any location and its adjacent locations is greater than a preset value, the location is determined to be a hole location. All adjacent hole locations are aggregated to form a hole area. The hole area is marked and an alarm is triggered.

8. An intelligent control system based on the combustion efficiency of a smart power plant, characterized in that, include: The power grid load dynamic response module is used to obtain load demand change signals in real time by connecting to the power grid dispatching system and to regulate the power grid load. The regulation includes: obtaining the corresponding three-dimensional curve of the design flame according to the load demand and injecting the corresponding amount of fuel and air into the burner. The data acquisition module is used to acquire temperature distribution data of the burner outer wall at a preset frequency through an infrared temperature measurement array; to acquire the working fluid temperature difference between the inlet and outlet pipes of the water-cooled wall through temperature sensors installed in the inlet and outlet pipes of the water-cooled wall; and to calculate the percentage of heat absorption between the actual temperature difference and the design maximum temperature difference. The two-dimensional trajectory reconstruction module is used to calculate the temperature gradient vector of each measurement point based on the temperature distribution data using the central difference method of adjacent four points, and continuously track the gradient vector direction on each surface to form the corresponding actual flame trajectory line. The three-dimensional trajectory reconstruction module selects two adjacent and mutually perpendicular first and second surfaces on the burner sidewall, marks positioning points at preset distances on the actual flame trajectory line of the first surface, and projects all the positioning points onto the actual flame trajectory line of the second surface; and establishes the actual flame three-dimensional curve based on the positioning points on the first and second surfaces. The offset acquisition module is used to compare the actual flame 3D curve with the pre-stored design flame 3D curve and output the flame offset. The control module is used to determine that if the flame deviation exceeds the threshold and the heat absorption percentage of the water-cooled wall decreases by a preset amount, the fuel supply is insufficient. The fuel supply control system increases the coal feed rate according to a preset gradient until the deviation returns to the threshold range and then stops compensation. If the flame deviation does not exceed the threshold but the heat absorption percentage is lower than the benchmark value for a continuous preset time, the air supply is insufficient. The damper actuator increases the air supply rate in a stepwise manner until the heat absorption percentage returns to the benchmark value.

9. An electronic device, characterized in that, The electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements an intelligent control method based on the combustion efficiency of a smart power plant as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements an intelligent control method based on the combustion efficiency of a smart power plant as described in any one of claims 1 to 7.

Images