Intelligent operation control system and method for dry deslagging system of coal-fired boiler

Abstract

The invention discloses an intelligent operation control system and method for a coal-fired boiler dry deslagging system, and belongs to the field of thermal power generation. The problem of monitoring and control separation generally existing in an existing coal-fired boiler dry-type deslagging system is solved. According to the technical scheme, the system comprises a control cabinet, the control cabinet is in communication connection with an online monitoring system and a DCS, the online monitoring system comprises a binocular vision monitoring unit, an air volume measuring unit, a temperature measuring unit and a large slag recognition unit, and the air volume measuring unit, the temperature measuring unit and the large slag recognition unit are arranged on the dry slag extractor. The image acquisition module is in communication connection with an image processing module, the image processing module is used for processing a steel belt image acquired by the image acquisition module and obtaining the mass flow rate of slag on a steel belt through a three-dimensional reconstruction algorithm model, and the DCS system is used for providing boiler operation parameters corresponding to the dry slag extractor and displaying a monitoring result and an output result; the method is applied to thermal power generation.

Description

Technical Field

[0001] This invention provides an intelligent operation control system and method for a dry ash discharge system of a coal-fired boiler, belonging to the field of thermal power generation technology. Background Technology

[0002] Existing dry ash removal systems for coal-fired boilers generally suffer from a disconnect between monitoring and control. The ash removal volume cannot be directly, continuously, and accurately measured online, leading to reliance on experience or single ash temperature feedback for cooling airflow adjustment, resulting in lag and inefficient regulation. Simultaneously, the operating frequency of the ash removal machine does not match the real-time ash removal demand, easily causing equipment wear and increased energy consumption. Furthermore, the impact of cooling airflow on the overall boiler economy cannot be assessed and fed back in real time, making operational optimization difficult.

[0003] While existing patent documents (such as CN119860540A and CN111290447A) involve local improvements such as airflow control or leakage monitoring, they fail to address the systemic issues of multi-variable coupling and global optimization, and thus fail to form a complete intelligent operation loop. Therefore, there is an urgent need for an intelligent operation solution for dry slag discharge systems that can achieve full-domain perception, intelligent decision-making, collaborative execution, and real-time evaluation. Summary of the Invention

[0004] To address the technical problem of fragmented monitoring and control in existing dry ash discharge systems for coal-fired boilers, this invention proposes a fully closed-loop intelligent dry ash discharge operation control system and method capable of achieving full-domain perception, intelligent decision-making, collaborative execution, and real-time evaluation.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is: an intelligent operation control system for a dry ash discharge system of a coal-fired boiler, comprising: The control cabinet is connected to both an online monitoring system and a DCS system. The online monitoring system includes a binocular vision monitoring unit and an air volume measurement unit, a temperature measurement unit, and a large slag identification unit deployed on the dry slag discharge machine. The binocular vision monitoring unit includes an image acquisition module, which is communicatively connected to an image processing module; The image processing module is used to process the steel strip images acquired by the image acquisition module, and obtain the mass flow rate of slag on the steel strip through a three-dimensional reconstruction algorithm model based on the processed steel strip images. The control cabinet is configured as follows: Based on the slag temperature of the head section of the dry slag discharger collected by the slag mass flow and temperature measurement unit and the large slag identification signal output by the large slag identification unit, the opening amount of the first damper corresponding to the head section of the dry slag discharger is obtained through a multi-parameter coupling model. Based on the opening measure of the first damper corresponding to the head section of the dry slag discharge machine, the opening measure of the second damper corresponding to the horizontal section of the dry slag discharge machine is output through the correlation control model. Based on the slag mass flow rate and the current operating frequency of the dry slag discharger, the dry slag discharger operating frequency adjustment amount is output through the slag layer thickness closed-loop control model to ensure that the slag thickness on the steel strip is within the preset thickness range. The DCS system is used to provide the boiler operating parameters corresponding to the dry ash removal machine and display the monitoring results and output results.

[0006] Furthermore, the control cabinet is also configured to obtain the assessment results of the impact of the dry ash discharger operation on the boiler's economy based on the cooling air volume monitored by the air volume measurement unit and the relevant operating parameters of the boiler corresponding to the dry ash discharger through an embedded economic analysis model.

[0007] Furthermore, the multi-parameter coupling model includes: The basic feedforward control unit queries the preset load-damper opening reference curve based on the boiler load parameters and outputs the first basic damper opening value. The feedback control unit calculates the feedback correction amount of the first damper opening based on the deviation between the measured slag temperature at the head section of the dry slag discharger and the set slag temperature using a proportional-integral-derivative algorithm. The dynamic feedforward control unit outputs a feedforward correction amount for the opening of the first damper when the slag load of the steel strip changes abruptly, based on the real-time slag mass flow rate and / or large slag identification signal. The final opening value of the first damper is obtained by superimposing the opening value of the first basic damper, the feedback correction value of the first damper opening, and the feedforward correction value of the first damper opening.

[0008] Furthermore, the closed-loop control model for slag layer thickness includes: The process variable calculation unit obtains the real-time slag thickness on the steel strip based on the real-time slag mass flow rate and the current operating frequency of the dry slag discharger. The PI control unit obtains the adjustment amount of the dry slag discharger's operating frequency based on the deviation between the real-time slag layer thickness and the preset slag thickness range. The protection logic unit triggers override control when the real-time slag mass flow rate exceeds a safety threshold within a preset time, forcibly setting the operating frequency of the dry slag discharger to the maximum power frequency.

[0009] Furthermore, the embedded economic analysis model takes the total cooling air volume of the dry ash remover and the boiler load, flue gas temperature, and ambient temperature provided by the DCS system as inputs. Through a pre-established simplified thermodynamic relationship model, it calculates and outputs online the changes in boiler flue gas temperature and boiler thermal efficiency caused by changes in cooling air volume.

[0010] Furthermore, the correlation control model includes: The basic opening degree following unit is used to output the following opening degree of the second air door according to a preset ratio based on the opening degree of the first air door corresponding to the head section of the dry slag discharge machine. The large slag linkage and following unit is used to determine the maximum opening response time of the second damper based on the large slag identification signal output and the time during which the second damper remains in the maximum opening state.

[0011] Furthermore, the image acquisition module includes a cooling protection device and an image processing module. The cooling protection device is equipped with a binocular camera and a laser, and the binocular camera and laser are equipped with protective covers.

[0012] Furthermore, the image processing module uses an embedded industrial computer.

[0013] A method for intelligent operation control of a dry ash discharge system for a coal-fired boiler applied to the above-described system includes the following steps: Step S1: Through the online monitoring system deployed at the dry slag discharge machine site, collect multi-source data in real time, including steel belt images, cooling air volume, slag temperature at the head section of the dry slag discharge machine, and large slag identification signal output by the large slag identification unit, and obtain boiler load parameters. Step S2: Perform binocular vision processing on the steel strip image to obtain the slag mass flow rate on the steel strip; Step S3: Based on the real-time slag mass flow rate, slag temperature at the head section of the dry slag discharger, and large slag identification signal, the opening degree of the first damper corresponding to the head section of the dry slag discharger is obtained through a multi-parameter coupling model and transmitted to the actuator of the first damper to control the opening degree of the first damper. Step S4: Based on the real-time slag mass flow rate and the current operating frequency of the dry slag discharger, the dry slag discharger operating frequency adjustment amount is output through the slag layer thickness closed-loop control model and transmitted to the dry slag discharger frequency converter to ensure that the slag thickness on the steel strip is within the preset thickness range. Step S5: Visual feedback of the online monitoring system and the monitoring results and output of the control cabinet.

[0014] Furthermore, the binocular vision processing process includes the following steps: Step S21: Preprocess the acquired steel strip image; Step S22: For the preprocessed steel strip image, output the three-dimensional point cloud coordinates of the steel strip image based on the three-dimensional reconstruction algorithm model to obtain the depth coordinates of the slag surface points on the steel strip in the steel strip image. Step S23: Calculate the volume of the slag pile on the steel strip based on the point cloud on the surface of the steel strip in the image of the unloaded steel strip and the point cloud on the surface of the slag body. Step S24: Output mass flow rate based on slag pile volume flow rate and slag bulk density.

[0015] The advantages of this invention over the prior art are as follows: 1. Breakthrough in monitoring accuracy and scope: For the first time, direct, continuous, and high-precision online monitoring of the slag discharge volume of the dry slag discharge machine has been achieved, providing a key and reliable data source for closed-loop intelligent control.

[0016] 2. Control Optimization: By integrating the opening amount of the first basic damper, the feedback correction amount of the first damper opening, and the feedforward correction amount of the first damper opening, the inherent lag problem of traditional single temperature feedback control is effectively solved, realizing the transformation from "post-event correction" to "pre-event prevention", significantly improving response speed and control accuracy; dynamic and precise matching between the operating frequency of the ash discharger and the real-time ash discharge amount is achieved, which greatly reduces equipment power consumption and mechanical failure rate while ensuring smooth boiler ash discharge.

[0017] 3. Intelligent closed loop: Through the embedded economic analysis model, the real-time visualization and quantitative evaluation of the impact of the dry ash discharger's operating status on the overall energy efficiency of the boiler are realized, forming a fully closed-loop intelligent operation system of "monitoring-control-evaluation-optimization", which improves the economic efficiency of operation. Attached Figure Description

[0018] The present invention will be further described below with reference to the accompanying drawings: Figure 1 This is a schematic diagram of the system structure of the present invention; Figure 2 This is a flowchart of the method of the present invention. Detailed Implementation

[0019] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicate relative orientations or positional relationships and are used only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0020] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0021] like Figures 1 to 2 As shown, the present invention provides an intelligent operation control system for a dry ash discharge system of a coal-fired boiler, including: a control cabinet, which is communicatively connected to an online monitoring system and a DCS system; The core controller of the control cabinet adopts a high-performance industrial PLC or embedded industrial computer. The data acquisition module of the control cabinet adopts analog / digital input, the control output module adopts analog / digital output, and the network communication adopts an industrial switch.

[0022] The online monitoring system includes a binocular vision monitoring unit, as well as an air volume measurement unit, a temperature measurement unit, and a large slag identification unit deployed on the dry slag discharge machine; The binocular vision monitoring unit includes an image acquisition module, which is communicatively connected to an image processing module; The image processing module is used to process the steel strip images acquired by the image acquisition module, and obtain the mass flow rate of slag on the steel strip through a three-dimensional reconstruction algorithm model based on the processed steel strip images. The image acquisition module includes a cooling protection device and an image processing module. The cooling protection device is equipped with a binocular camera and a laser, and the binocular camera and laser are equipped with protective covers. The cooling protection device, which integrates a binocular camera and a laser, is installed 2.5-4 meters above the middle of the horizontal section of the slag discharge machine to ensure that the binocular camera's field of view covers the entire width of the steel strip and avoids direct high-temperature radiation and slag drop points.

[0023] Binocular camera intrinsic / extrinsic parameter calibration: A high-precision checkerboard calibration board was used, and the calibration was performed offline using the Zhang Zhengyou calibration method.

[0024] On-site verification of volume accuracy: When the machine is stopped, a calibration block with known geometry and volume (such as a trapezoidal wooden block) is placed at different positions on the steel belt. The binocular vision monitoring unit is run, and the calculated volume is compared with the actual volume to correct the error of the binocular vision monitoring unit.

[0025] Density verification: Periodically compare the cumulative slag volume of the binocular vision monitoring unit over 24 hours with the actual weight of the slag truck weighed on the same day, and calibrate the ρ value in reverse.

[0026] The image processing module uses an embedded industrial computer equipped with an Intel Core i7 or equivalent processor and a dedicated GPU (such as the NVIDIA Jetson series) to run visual algorithms in real time.

[0027] The stereo camera uses an industrial-grade CMOS sensor with a resolution of ≥2448×2048, a global shutter, and a frame rate of ≥15fps. The camera lens is a fixed-focus industrial lens with a focal length determined by the installation height (typically 8-16mm), and includes an infrared cutoff filter.

[0028] The laser is an 808nm line laser with adjustable power (typically 1-3W). The laser is used to form clear structured light stripes in dusty environments, enhancing image features, overcoming ambient light interference, and assisting the binocular camera in acquiring clear images of the steel strip.

[0029] The cooling and protection device integrates a semiconductor cooling chip or a circulating air cooling system to ensure that the camera core temperature is below 50℃. The protective cover uses a double-layer stainless steel shell, with the inner layer for air cooling and the outer layer for compressed air to create positive pressure and blow away dust from the observation window to prevent dust from adhering.

[0030] The air volume measurement unit is installed in the head section air duct of the dry slag discharge machine, the horizontal section air duct of the dry slag discharge machine, and the third air door inlet corresponding to each transition section of the dry slag discharge machine.

[0031] The temperature measurement unit uses thermocouples and is installed in the head section, horizontal section and transition section of the dry slag discharge machine.

[0032] The large slag identification unit uses a vibration sensor.

[0033] The control cabinet is configured as follows: Based on the slag temperature at the head section of the dry slag discharger collected by the slag mass flow and temperature measurement unit and the large slag identification signal output by the large slag identification unit, the opening amount of the first damper corresponding to the head section of the dry slag discharger is obtained through a multi-parameter coupling model.

[0034] Specifically, the multi-parameter coupling model includes: The basic feedforward control unit queries the preset load-damper opening reference curve (which can be segmented linearly or nonlinearly) based on the boiler load parameters and outputs the first basic damper opening value. In the load-damper opening reference curve, the load is the total coal feed to the boiler, which is the amount of coal fed into the boiler for combustion per unit time, representing the boiler load level; the damper opening reference is the opening amount of the first basic damper.

[0035] The feedback control unit calculates the feedback correction amount of the first damper opening based on the deviation between the measured slag temperature at the head section of the dry slag discharger and the set slag temperature using a proportional-integral-derivative algorithm. The model for calculating the feedback correction amount of the first damper opening is as follows: e(t) = Tset - Tmeas; ΔYfeedback(k)=Kp×[e(k)-e(k-1)]+Ki×e(k)+Kd×[e(k)-2e(k-1)+e(k-2)]; In the formula, Tset is the set slag temperature, for example, the head section slag temperature is set to 150°; Tmeas is the measured head section slag temperature of the dry slag discharge machine; ΔYfeedback(k) is the feedback correction amount of the first damper opening at time k, used to eliminate steady-state error; Kp, Ki, and Kd are the proportional, integral, and derivative coefficients of the proportional-integral-derivative algorithm model, respectively, used as adjustment parameters of the feedback control loop, which determine the response speed and stability of the controller.

[0036] The dynamic feedforward control unit outputs a feedforward correction amount for the opening of the first damper when the slag load of the steel strip changes abruptly, based on the real-time slag mass flow rate and / or large slag identification signal.

[0037] Specifically, the control cabinet monitors the real-time trend of mass flow rate changes and large slag identification signals to proactively adjust the opening of the first damper to cope with unexpected situations during boiler slag discharge. The specific logic is as follows: When the mass flow rate increases sharply (the rate of change exceeds the positive threshold α1) or the large slag identification unit outputs a large slag signal (the large slag identification signal Flag_slag is a Boolean value, where 1 indicates the presence of large slag, i.e., the signal is "true," and the large slag identification unit outputs a large slag signal), the control cabinet determines that a large amount of high-temperature slag is about to enter the cooling stage. To prevent the slag temperature from exceeding the preset slag temperature, the control cabinet outputs a positive first damper opening feedforward correction (+β1). This positive first damper opening feedforward correction is superimposed on the first basic damper opening, increasing the opening angle of the first damper and enhancing the cooling capacity in advance. At this time, the sum of the positive first damper opening feedforward correction and the first basic damper opening is the output first damper opening feedforward correction.

[0038] When the mass flow rate (rate of change below the negative threshold α2) decreases sharply, the control cabinet determines that the boiler ash discharge load will soon decrease significantly. To prevent overcooling and increased air leakage, the control cabinet outputs a negative first damper opening feedforward correction (-β2). This negative first damper opening feedforward correction is added to the first basic damper opening amount, reducing the opening angle of the first damper and achieving advanced energy saving. At this time, the sum of the negative first damper opening feedforward correction and the first basic damper opening amount is the output first damper opening feedforward correction.

[0039] When the mass flow rate changes smoothly (the rate of change is within the range of α2-α1) and the large slag identification unit does not output a large slag signal, the control cabinet determines that the boiler is operating stably and no feedforward compensation is required. At this time, the feedforward correction of the first damper opening is 0, and the opening amount of the first damper is determined only by the basic feedforward control unit and the feedback control unit.

[0040] The final opening value of the first damper is obtained by superimposing the opening value of the first basic damper, the feedback correction value of the first damper opening, and the feedforward correction value of the first damper opening.

[0041] The final opening measure of the first air damper is: Yfinal = Ybase + ΔYfeedback + ΔYfeedforward; In the formula, Ybase is the opening amount of the first basic damper; ΔYfeedback is the feedback correction amount of the opening of the first damper; and ΔYfeedforward is the feedforward correction amount of the opening of the first damper.

[0042] The control cabinet is also configured to output the opening amount of the second damper corresponding to the horizontal section of the dry slag discharger through the associated control model, based on the opening amount of the first damper corresponding to the head section of the dry slag discharger.

[0043] The associated control model includes: The basic opening degree following unit is used to output the following opening degree of the second air door according to a preset ratio based on the opening degree of the first air door corresponding to the head section of the dry slag discharge machine. The large slag linkage following unit is used to determine the response time of the second damper to its maximum opening based on the large slag identification signal output, as well as the time the second damper remains at its maximum opening. Specifically, when the large slag identification unit outputs a large slag signal, the second damper in the horizontal section of the corresponding area of ​​the steel strip rapidly opens to Y_max (e.g., 80%) within t1 seconds, holds for t2 seconds, and then slowly returns to its original following opening. Here, t1 is the response time of the second damper opening to its maximum opening; t2 is the time the second damper remains at its maximum opening.

[0044] The control cabinet is also configured to output the operating frequency adjustment of the dry slag discharger based on the slag mass flow rate and the current operating frequency of the dry slag discharger through a closed-loop control model of slag layer thickness, so as to ensure that the slag thickness on the steel strip is within the preset thickness range.

[0045] Specifically, the closed-loop control model for slag layer thickness includes: The process variable calculation unit obtains the real-time slag thickness on the steel strip based on the real-time slag mass flow rate and the current operating frequency of the dry slag discharger. The current running speed of the steel belt in the dry slag discharge machine is: S = k × f; Real-time slag thickness on the steel strip: H_actual=(M / ρ) / (S×W); In the formula, M is the mass flow rate, W is the effective width of the steel strip (m); ρ is the bulk density; S is the running speed of the steel strip; f is the output frequency of the steel strip inverter; k is the mechanical transmission coefficient; and H_actual is the real-time slag thickness on the steel strip, that is, the actual average thickness of the slag accumulation on the steel strip.

[0046] The PI control unit obtains the adjustment amount of the dry slag discharger's operating frequency based on the deviation between the real-time slag layer thickness and the preset slag thickness range. Specifically, the median value of the preset thickness range [Hmin, Hmax] is taken as the set thickness H_set, and the PI control unit is used to obtain the adjustment amount Δf(k) of the dry slag discharger operating frequency: Δf(k) = Kp_h × [H_set - H_actual(k)] + Ki_h × Σ [H_set - H_actual(j)]; Final adjustment of the dry slag discharger operating frequency: f_cmd = f_base + Δf; In the formula, H_set is the slag layer thickness setting value; Kp_h and Ki_h are the proportional and integral coefficients of the PI control unit, respectively, which are adjustment parameters used for the slag layer thickness control loop; f_cmd is the adjustment amount of the dry slag discharger's operating frequency; and f_base is the base operating frequency, which is the initial operating frequency of the dry slag discharger set according to the boiler load.

[0047] The protection logic unit triggers override control when the real-time slag mass flow rate exceeds the safety threshold within a preset time (e.g., 5 seconds), forcing the dry slag discharger's operating frequency to the maximum power frequency (50Hz).

[0048] The DCS system is used to provide boiler operating parameters and display monitoring results and outputs.

[0049] The control cabinet is also configured to obtain the assessment results of the impact of the dry ash discharger operation on the boiler's economy based on the cooling air volume monitored by the air volume measurement unit and the relevant operating parameters of the boiler corresponding to the dry ash discharger through an embedded economic analysis model. Specifically, the embedded economic analysis model takes the total cooling air volume of the dry ash remover and the boiler load, flue gas temperature and ambient temperature provided by the DCS system as inputs. Through a pre-established simplified thermodynamic relationship model, it calculates and outputs the changes in boiler flue gas temperature and boiler thermal efficiency caused by changes in cooling air volume online. The simplified thermodynamic model focuses on the impact of cooling air as additional leakage on flue gas heat loss.

[0050] The embedded economic analysis model is configured as follows: The additional heat brought in by the cooling air input through all dampers on the output dry slag discharge machine: Q_in=Q_cool×ρ_air×c_p×(T_exh-T_cool_in).

[0051] The change in boiler flue gas temperature, ΔT_exh_model, caused by the additional heat brought in by the cooling air from all dampers on the dry ash remover is estimated using empirical formulas or a pre-trained linear regression model.

[0052] Based on the influence coefficient k_η of flue gas temperature on boiler efficiency (typically, efficiency decreases by about 0.5% for every 10-15℃ increase), calculate the change in boiler thermal efficiency: Δη=-k_η×(ΔT_exh_model / 10); The embedded economic analysis model performs rolling calculations every 1-5 minutes, and the results are displayed in real time on the DCS system screen.

[0053] Where, Q_in is the extra heat brought in by the cooling air input from all dampers on the dry ash remover, and the extra heat carried away by the excessive cooling air (considered as leakage) being heated to the flue gas temperature; ρ_air is the air density, representing the dry air density under standard conditions; c_p is the specific heat capacity of air at constant pressure, representing the heat absorbed by the air temperature to increase by 1°C; k_η is the influence coefficient of flue gas temperature on boiler thermal efficiency, representing the percentage point decrease in boiler efficiency caused by each increase in flue gas temperature by a certain value (e.g., 10°C); Δη: the change in boiler thermal efficiency (percentage points, %).

[0054] This invention utilizes the rate of change in slag discharge as a feedforward signal, combined with a large slag identification signal, to adjust the cooling airflow in advance before the slag temperature changes significantly. This effectively solves the inherent lag problem of traditional single temperature feedback control, realizing a shift from "post-event correction" to "pre-event prevention," thereby improving regulation quality and operational economy while ensuring equipment safety. It also addresses sudden changes in slag discharge (such as coke collapse) by acting proactively before the slag temperature rises significantly, thus resolving the lag problem. The positive first damper opening feedforward correction β1, the negative first damper opening feedforward correction β2, and the duration are adjustable.

[0055] A method for intelligent operation control of a dry ash discharge system for a coal-fired boiler applied to the above-described system includes the following steps: Step S1: Through the online monitoring system deployed at the dry slag discharge machine site, collect multi-source data in real time, including steel belt images, cooling air volume, slag temperature at the head section of the dry slag discharge machine, and vibration signals output by the large slag identification unit, and obtain boiler load parameters. Step S2: Perform binocular vision processing on the steel strip image to obtain the slag mass flow rate on the steel strip, analyze the vibration signal, and generate a large slag identification signal. The process of binocular vision processing includes: Step S21, Steel strip image preprocessing: The acquired steel strip image is subjected to grayscale conversion, median filtering (to remove salt and pepper noise), Gaussian filtering (smoothing), and laser line enhancement (using ROI and threshold segmentation to extract the center line of the laser stripe) to obtain the preprocessed steel strip image. Step S22, Stereo Matching and 3D Reconstruction: Based on the 3D reconstruction algorithm model, output the 3D point cloud coordinates of the steel strip image after preprocessing to obtain the depth coordinates of the slag surface points on the steel strip in the steel strip image. Specifically, for the preprocessed steel strip image, the disparity map is calculated using the SGBM (semi-global block matching) algorithm. Based on the binocular camera calibration parameters (intrinsic parameters, extrinsic parameters, distortion coefficients) in the image acquisition module, the disparity map is converted into three-dimensional point cloud coordinates.

[0056] The depth coordinates of the points on the slag surface of the steel strip in the steel strip image are: z = (f × B) / d; In the formula, f is the focal length of the binocular camera in the image acquisition module, which is the distance from the optical center of the camera lens to the imaging sensor, and determines the field of view; B is the baseline distance, which is the horizontal distance between the optical centers of the two lenses of the binocular camera in the image acquisition module, and affects the depth measurement accuracy; d is the parallax, which is the pixel difference between the horizontal positions of the same object point in the left and right camera images in the image acquisition module, and is used to calculate the depth; z is the slag depth, which is the vertical distance from the slag on the steel strip to the plane of the binocular camera in the image acquisition module, and is calculated from the parallax.

[0057] Step S23: Calculate the slag pile volume on the steel strip: When the steel strip is running unloaded, the point cloud on the surface of the steel strip is fitted using the RANSAC algorithm to obtain the reference plane coordinates (the three-dimensional point cloud coordinates of the unloaded steel strip image); when the steel strip is running under load, the height hi of the point cloud on the surface of the slag body on the steel strip in the collected steel strip image to the reference plane is calculated. In the pixel coordinate system of the steel strip image, the small area ΔS (the physical area represented by a pixel in the steel strip image on the actual steel strip plane) corresponding to each pixel is integrated with hi (the height of each point on the slag surface to the reference plane) to approximately obtain the slag pile volume V=Σ(hi×ΔS) on the steel strip.

[0058] The 3D point cloud coordinates of the image of the unloaded steel strip are the reference plane coordinates. The reference plane coordinate model is as follows: Ax + By + Cz + D = 0; In the formula, z is the depth coordinate of a point on the surface of the steel strip slag (distance from the binocular camera in the image acquisition module); x and y are the horizontal coordinates of a point on the surface of the steel strip slag. Step S24, Mass Flow Calculation and Output: The mass flow calculation model is as follows: M(t) = V(t) × ρ; In the formula, ρ is the slag bulk density (configurable parameter, typically 900-1100 kg / m³); M(t) is the mass flow rate (instantaneous slag discharge), which is the mass of slag passing through the dry slag discharger per unit time, calculated by the binocular vision monitoring unit; V(t) is the slag pile volumetric flow rate, the volume of slag occupied on the steel belt per unit time.

[0059] Cumulative slag volume M1 = ∫M(t) dt; The DCS system uses Modbus TCP or OPC UA protocols to exchange key data such as mass flow rate M(t), slag pile volume flow rate V(t), and average slag layer height with the control cabinet at a fixed frequency (e.g., 1Hz).

[0060] Step S3: Based on the real-time slag mass flow rate, slag temperature at the head section of the dry slag discharger, and large slag identification signal, the opening degree of the first damper corresponding to the head section of the dry slag discharger is obtained through a multi-parameter coupling model and transmitted to the actuator of the first damper to control the opening degree of the first damper. Step S4: Based on the real-time slag mass flow rate and the current operating frequency of the dry slag discharger, the dry slag discharger operating frequency adjustment amount is output through the slag layer thickness closed-loop control model and transmitted to the dry slag discharger frequency converter to ensure that the slag thickness on the steel strip is within the preset thickness range. Step S5: Visual feedback of the online monitoring system and the monitoring results and output results of the control system.

[0061] Regarding the specific structure of this invention, it should be noted that the connection relationships between the various component modules used in this invention are definite and achievable. Except as specifically described in the embodiments, their specific connection relationships can bring about corresponding technical effects and solve the technical problems proposed by this invention without relying on the execution of corresponding software programs. The models of the components, modules, and specific components appearing in this invention, the connection methods between them, and the conventional usage methods and expected technical effects brought about by the above technical features, unless specifically described, are all publicly disclosed content in patents, journal articles, technical manuals, technical dictionaries, and textbooks that can be obtained by those skilled in the art before the application date, or belong to conventional technology, common knowledge, and other existing technologies in this field. There is no need to elaborate, which makes the technical solution provided in this case clear, complete, and achievable, and can reproduce or obtain corresponding physical products based on this technical means.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent operation control system for a dry ash discharge system of a coal-fired boiler, characterized in that, include: The control cabinet is connected to both an online monitoring system and a DCS system. The online monitoring system includes a binocular vision monitoring unit and an air volume measurement unit, a temperature measurement unit, and a large slag identification unit deployed on the dry slag discharge machine. The binocular vision monitoring unit includes an image acquisition module, which is communicatively connected to an image processing module; The image processing module is used to process the steel strip images acquired by the image acquisition module, and obtain the mass flow rate of slag on the steel strip through a three-dimensional reconstruction algorithm model based on the processed steel strip images. The control cabinet is configured as follows: Based on the slag temperature of the head section of the dry slag discharger collected by the slag mass flow and temperature measurement unit and the large slag identification signal output by the large slag identification unit, the opening amount of the first damper corresponding to the head section of the dry slag discharger is obtained through a multi-parameter coupling model. Based on the opening measure of the first damper corresponding to the head section of the dry slag discharge machine, the opening measure of the second damper corresponding to the horizontal section of the dry slag discharge machine is output through the correlation control model. Based on the slag mass flow rate and the current operating frequency of the dry slag discharger, the dry slag discharger operating frequency adjustment amount is output through the slag layer thickness closed-loop control model to ensure that the slag thickness on the steel strip is within the preset thickness range. The DCS system is used to provide the boiler operating parameters corresponding to the dry ash discharge machine and display the monitoring results and output results.

2. The intelligent operation control system for a dry ash removal system of a coal-fired boiler according to claim 1, characterized in that, The control cabinet is also configured to obtain the assessment results of the impact of the dry ash discharger operation on the boiler's economy based on the cooling air volume monitored by the air volume measurement unit and the relevant operating parameters of the boiler corresponding to the dry ash discharger through an embedded economic analysis model.

3. The intelligent operation control system for a dry ash removal system of a coal-fired boiler according to claim 1, characterized in that, Multi-parameter coupling models include: The basic feedforward control unit queries the preset load-damper opening reference curve based on the boiler load parameters and outputs the first basic damper opening value. The feedback control unit calculates the feedback correction amount of the first damper opening based on the deviation between the measured slag temperature at the head section of the dry slag discharger and the set slag temperature using a proportional-integral-derivative algorithm. The dynamic feedforward control unit outputs a feedforward correction amount for the opening of the first damper when the slag load of the steel strip changes abruptly, based on the real-time slag mass flow rate and / or large slag identification signal. The final opening value of the first damper is obtained by superimposing the opening value of the first basic damper, the feedback correction value of the first damper opening, and the feedforward correction value of the first damper opening.

4. The intelligent operation control system for a dry ash removal system of a coal-fired boiler according to claim 1, characterized in that, The closed-loop control model for slag layer thickness includes: The process variable calculation unit obtains the real-time slag thickness on the steel strip based on the real-time slag mass flow rate and the current operating frequency of the dry slag discharger. The PI control unit obtains the adjustment amount of the dry slag discharger's operating frequency based on the deviation between the real-time slag layer thickness and the preset slag thickness range. The protection logic unit triggers override control when the real-time slag mass flow rate exceeds a safety threshold within a preset time, forcibly setting the operating frequency of the dry slag discharger to the maximum power frequency.

5. The intelligent operation control system for a dry ash removal system of a coal-fired boiler according to claim 1, characterized in that, The embedded economic analysis model takes the total cooling air volume of the dry ash remover and the boiler load, flue gas temperature and ambient temperature provided by the DCS system as inputs. Through a pre-established simplified thermodynamic relationship model, it calculates and outputs online the changes in boiler flue gas temperature and boiler thermal efficiency caused by changes in cooling air volume.

6. The intelligent operation control system for a dry ash removal system of a coal-fired boiler according to claim 1, characterized in that, The associated control model includes: The basic opening degree following unit is used to output the following opening degree of the second air door according to a preset ratio based on the opening degree of the first air door corresponding to the head section of the dry slag discharge machine. The large slag linkage and following unit is used to determine the maximum opening response time of the second damper based on the large slag identification signal output and the time during which the second damper remains in the maximum opening state.

7. The intelligent operation control system for a dry ash removal system of a coal-fired boiler according to claim 1, characterized in that, The image acquisition module includes a cooling protection device and an image processing module. The cooling protection device is equipped with a binocular camera and a laser, and the binocular camera and laser are equipped with protective covers.

8. The intelligent operation control system for a dry ash removal system of a coal-fired boiler according to claim 1, characterized in that, The image processing module uses an embedded industrial computer.

9. A method for intelligent operation control of a dry ash discharge system for a coal-fired boiler applied to any one of the systems described in claims 1-8, characterized in that, Includes the following steps: Step S1: Through the online monitoring system deployed at the dry slag discharge machine site, collect multi-source data in real time, including steel belt images, cooling air volume, slag temperature at the head section of the dry slag discharge machine, and large slag identification signal output by the large slag identification unit, and obtain boiler load parameters. Step S2: Perform binocular vision processing on the steel strip image to obtain the slag mass flow rate on the steel strip; Step S3: Based on the real-time slag mass flow rate, slag temperature at the head section of the dry slag discharger, and large slag identification signal, the opening degree of the first damper corresponding to the head section of the dry slag discharger is obtained through a multi-parameter coupling model and transmitted to the actuator of the first damper to control the opening degree of the first damper. Step S4: Based on the real-time slag mass flow rate and the current operating frequency of the dry slag discharger, the dry slag discharger operating frequency adjustment amount is output through the slag layer thickness closed-loop control model and transmitted to the dry slag discharger frequency converter to ensure that the slag thickness on the steel strip is within the preset thickness range. Step S5: Visual feedback of the online monitoring system and the monitoring results and output of the control cabinet.

10. The intelligent operation control method for a dry ash discharge system of a coal-fired boiler according to claim 9, characterized in that, The binocular vision processing process includes the following steps: Step S21: Preprocess the acquired steel strip image; Step S22: For the preprocessed steel strip image, output the three-dimensional point cloud coordinates of the steel strip image based on the three-dimensional reconstruction algorithm model to obtain the depth coordinates of the slag surface points on the steel strip in the steel strip image. Step S23: Calculate the volume of the slag pile on the steel strip based on the point cloud on the surface of the steel strip in the image of the unloaded steel strip and the point cloud on the surface of the slag body. Step S24: Output mass flow rate based on slag pile volume flow rate and slag bulk density.

Images