A method for treating fly ash floating black of a boiler

Abstract

The application discloses a boiler fly ash floating black treatment method, which comprises the following steps: quantitatively measuring the fly ash floating black of a boiler; arranging a sensor array, constructing a two-dimensional high-resolution monitoring grid covering the whole horizontal flue cross section, and acquiring two-dimensional oxygen content distribution data and two-dimensional temperature distribution data in real time; collecting actual operation data of the boiler, and jointly constructing a comprehensive data set by using the actual operation data, the two-dimensional oxygen content distribution data and the two-dimensional temperature distribution data; calculating key characteristic indexes including a wind-coal matching index, an oxygen content balance index and a temperature balance index based on the collected operation data; establishing a fly ash floating black prediction model to predict the fly ash floating black amount; and controlling the system to perform hierarchical closed-loop optimization control according to the output prediction floating black index and the calculated characteristic indexes. Through the closed-loop adjustment, the application realizes online prediction and accurate treatment of the fly ash floating black risk, and effectively reduces the fly ash floating black phenomenon.

Description

Technical Field

[0001] This invention relates to the field of automation control technology, specifically to a method for treating blackening of boiler fly ash. Background Technology

[0002] Fly ash is a fine-grained ash residue discharged from coal-fired power plants after coal combustion. Fly ash mainly contains active silica (SiO2), active alumina (Al2O3), and iron oxide (Fe2O3), exhibiting good activity and cementitious properties. It is an excellent cement additive and is widely used in the cement industry; its quality is of paramount importance.

[0003] However, as power companies increasingly blend coal types and widely apply deep control strategies in combustion systems, fly ash quality issues have gradually become more prominent. Among these, the "floating black" phenomenon is particularly concerning, where fly ash produces a large number of floating black particles or films after being soaked in water, significantly affecting the quality of fly ash and its acceptance in external applications.

[0004] Currently, research on the causes of fly ash blackening is still in its early stages. Existing studies mainly explore the issue from the perspectives of fly ash carbon content, incomplete combustion, and coal powder fineness control, suggesting that high-volatile coal may generate dense, carbon-black-like substances under initial oxygen-deficient conditions. Furthermore, some literature suggests that the structure of blackening particles in some ash samples is similar to industrial carbon black, exhibiting strong buoyancy and low re-ignition properties, making them difficult to remove through conventional combustion adjustment methods. Overall, existing research is still relatively scattered, lacking unified evaluation standards and mechanism identification methods, and systematic research on the specific combustion pathways, particle structure characteristics, and operational causes behind "blackening." From an engineering practice perspective, fly ash blackening is mostly caused by insufficient oxygen during the volatile matter combustion stage. Therefore, combining existing research findings to provide feasible control measures has become a crucial aspect of current fly ash blackening control. Summary of the Invention

[0005] The purpose of this invention is to provide a method for treating fly ash blackening in boilers. By rationally designing and adding oxygen and temperature sensors, and using designed indicators and parameters, as well as operational data, a relevant model is constructed for fly ash blackening. Combined with optimization algorithms, the method reduces fly ash blackening to the extent possible, thereby solving the problems mentioned in the background art.

[0006] The present invention provides the following technical solution: a method for treating blackening of boiler fly ash, comprising the following operational steps:

[0007] Step S1: Quantitatively measure the fly ash and black residue from the boiler.

[0008] Preferably, a representative fly ash sample is obtained by sampling and mixing at multiple points from the ash discharge system at the tail of the boiler. The weighed fly ash sample is then placed into a beaker containing clean water. The black residue is stirred to make it float to the surface. The sample is then allowed to stand to separate the black residue from the fly ash. The black residue is filtered out, dried, and weighed. The ratio of the weight of the black residue to the weight of the fly ash sample is used as the fly ash black residue index.

[0009] Step S2: Deploy the sensor array to construct a two-dimensional high-resolution monitoring grid covering the entire horizontal flue cross section, and acquire two-dimensional oxygen distribution data and two-dimensional temperature distribution data in real time.

[0010] Preferably, the sensor array is arranged in the horizontal flue monitoring section between the outlet of the high-temperature superheater and the inlet of the high-temperature reheater; the two-dimensional high-resolution monitoring grid includes a two-dimensional monitoring array of "12 temperature + 6 oxygen" constructed on the monitoring section, including the arrangement of temperature measuring points and oxygen measuring points, and acquiring two-dimensional oxygen distribution data and two-dimensional temperature distribution data reflecting the difference between the A / B side wall-attached area and the central area on the same monitoring section.

[0011] Preferably, 12 K-type thermocouples are arranged at the monitoring section, forming a combined structure of "horizontal arrangement at the top + vertical arrangement on both side walls", wherein:

[0012] Upper transverse layout: Six temperature measuring points are arranged symmetrically along the width of the flue at the upper part of the monitoring section, covering the area from side A to the middle to side B, to reflect the temperature distribution and left-right deviation of the upper mainstream area.

[0013] Vertical temperature measurement points on the side walls: Three temperature measurement points are arranged along the height direction on side wall A and three temperature measurement points are arranged along the height direction on side wall B to reflect the temperature deviation and local anomalies in the wall-attached area as the height changes.

[0014] By using the arrangement of the upper transverse section + A side wall + B side wall, the temperature distribution characteristics of the two wall-attached areas and the middle area of ​​the monitoring section can be characterized simultaneously.

[0015] Step S3: Collect actual operating data of the boiler, and use the actual operating data, two-dimensional oxygen distribution data, and two-dimensional temperature distribution data to construct a comprehensive dataset.

[0016] Preferably, the actual operating data collected includes data under two typical operating conditions: with and without fly ash, and the collection period covers different load segments and coal type change cycles. The actual operating data includes: fly ash fly ash index, dry ash-free volatile matter of coal fed into the furnace, coal powder fineness, coal feed rate of each coal mill, air distribution data, and average oxygen content at the SCR inlet.

[0017] Step S4: Calculate key characteristic indicators based on the collected operational data, including air-coal matching index, oxygen balance index, and temperature balance index.

[0018] Preferably, the air-coal matching index is calculated: the ratio of the primary air volume of the pulverized coal feeding pipe corresponding to each burner to the dry ash-free volatile matter content of the coal fed into the furnace is extracted, which characterizes whether the initial oxygen provided by the primary air can meet the combustion requirements when high volatile matter coal is rapidly released in the early stage of ignition.

[0019] Calculate the oxygen balance index: Read the real-time values ​​of the 6 zirconia oxygen sensors and calculate the standard deviation of all oxygen measurement points on the cross section at that moment. The larger the standard deviation of all oxygen measurement points, the more uneven the oxygen supply distribution of the flue cross section is, and the greater the risk of local hypoxia.

[0020] Calculate the temperature uniformity index: Read the real-time values ​​of the 12 thermocouples and calculate the standard deviation of all temperature measuring points on the cross section at that moment. The standard deviation of all temperature measuring points is used to help determine whether the combustion center is skewed and the uniformity of the heat load distribution.

[0021] Step S5: Establish a fly ash and black residue prediction model to predict the amount of fly ash and black residue.

[0022] Preferably, establishing a fly ash and black residue prediction model includes:

[0023] Step S51: Select training samples from the historical running database to construct a sample dataset;

[0024] Step S52: Set the variable system for the fly ash and black powder prediction model and determine the input and output variables;

[0025] Step S53: Use data mining and machine learning algorithms to train the sample set. Through iterative learning of the algorithm, establish a high-dimensional nonlinear mapping relationship between the input and output quantities, and construct a fly ash and floating black prediction model.

[0026] Step S54: Deploy the trained fly ash blackening prediction model in the DCS control system or a separate combustion optimization workstation. The system reads the current sensor data and air-coal parameters in real time, inputs them into the fly ash blackening prediction model, and outputs the predicted blackening index at the current moment online.

[0027] Step S6: Based on the output predicted floating black index and the calculated characteristic index, the control system executes hierarchical closed-loop optimization control.

[0028] Preferably, the specific implementation includes:

[0029] Step S61: Set the trigger conditions and control objectives for starting optimization control;

[0030] Step S62: Introduce constraints including oxygen balance constraint, temperature balance constraint, air-coal matching interval constraint, and oxygen absolute value constraint, and confirm the corresponding thresholds;

[0031] Step S63: When the wind-coal matching index is detected to be less than the set threshold, the total amount of primary air system is adjusted first to achieve primary regulation;

[0032] Step S64: Based on satisfying the air-coal matching interval constraint, the stratified secondary air and burnout air are then asymmetrically distributed and adjusted to achieve secondary regulation;

[0033] Step S65: Based on satisfying the above-mentioned oxygen distribution constraints, the temperature distribution uniformity is finally adjusted to achieve three-level regulation;

[0034] Step S66: After each adjustment, the control system continuously collects new oxygen / temperature distribution and operating parameters, recalculates the air-coal matching index, oxygen balance index, and temperature balance index, and inputs the current data into the fly ash blackening prediction model to update the predicted blackening index. When the predicted blackening index is less than the set blackening warning threshold and the oxygen balance constraint, temperature balance constraint, and air-coal matching interval constraint are met for a period of time, it is determined that the optimization has achieved the goal. The control system enters the monitoring state and maintains the current parameter combination. When the warning condition is triggered again, it re-enters the hierarchical closed-loop optimization process.

[0035] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: By rationally designing and adding oxygen and temperature sensors, and using designed indicators and parameters, as well as operational data, a relevant model is constructed for fly ash blackening, and combined with optimization algorithms, the problem of fly ash blackening in boilers is solved. Furthermore, through a closed-loop path of "quantitative measurement of blackening—multi-point two-dimensional oxygen and temperature field monitoring—characteristic indicator system—predictive modeling—constrained optimization control," the measurable, assessable, predictable, and controllable blackening is achieved, enabling online prediction and precise treatment of fly ash blackening risks, effectively reducing the phenomenon of fly ash blackening. Attached Figure Description

[0036] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0037] Figure 1 This is a schematic diagram of the method steps provided in the embodiments of the present invention. Detailed Implementation

[0038] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0039] Combination Figure 1 As shown, the present invention provides a technical solution: a method for treating blackening of boiler fly ash, comprising the following operational steps:

[0040] Step S1: Metering of fly ash and black residue from boilers.

[0041] In this embodiment, the present invention quantitatively determines the content of fly ash black residue, specifically including:

[0042] Step S11: Collect approximately 5 grams of fly ash sample from the boiler tail ash discharge system (to ensure testing accuracy, multiple samples can be taken and mixed to obtain a representative sample).

[0043] Step S12: Put the weighed fly ash sample into a beaker containing clean water and stir continuously with a glass rod for about 1 minute to fully disperse the fly ash particles and make as many of the floating black carbon particles as possible float to the surface of the water.

[0044] Step S13: Then let it stand for about 5 minutes to allow the unburned carbon particles (floating black) to completely separate from the heavier ash particles. The floating black particles float on the top layer due to their low density, while the ash particles settle to the bottom of the cup.

[0045] Step S14: Gently scoop up the black floating matter on the water surface using a fine filter screen and drain as much water as possible. Place the filtered black matter in a drying oven and dry it at about 60°C for 30 minutes to remove moisture.

[0046] Step S15: Finally, use a precision electronic balance to weigh the dried surface black material. Record the original quality of fly ash. ,calculate The surface black index value of the sample was obtained;

[0047] Step S16: Measure the fly ash collected under different load conditions according to the above steps.

[0048] Step S2: Design and arrange the hardware sensors.

[0049] In this embodiment, in order to accurately grasp the spatial differences in combustion organization at the furnace outlet on the horizontal flue section and overcome the problem of insufficient representativeness of conventional single-point measurements, the present invention arranges multiple oxygen and temperature sensors at the tail end of the boiler horizontal flue to obtain two-dimensional distribution information of oxygen and temperature in the cross section.

[0050] Installation location selection: Based on site survey and demonstration, the measuring point is arranged at the horizontal flue monitoring section between the outlet of the high-temperature superheater and the inlet of the high-temperature reheater. This section can reflect the deviation and unevenness of the combustion organization at the furnace outlet on the flue section, and it is also suitable for installation and maintenance.

[0051] Two-dimensional monitoring grid construction ("12 temperature 6 oxygen"): Construct a two-dimensional monitoring array of "12 temperature + 6 oxygen" on the monitoring section, including the arrangement of temperature measuring points, the arrangement of oxygen measuring points, the installation method and sealing.

[0052] For example, in the temperature point arrangement, 12 K-type thermocouples are arranged in the cross section, forming a combined structure of "horizontal arrangement at the top + vertical arrangement on both side walls", which includes:

[0053] Upper transverse layout: Six temperature measuring points are arranged symmetrically along the width of the flue at the upper part of the cross section, covering the area from side A to the middle to side B, to reflect the temperature distribution and left-right deviation of the upper mainstream area.

[0054] Vertical temperature measurement points on the side walls: Three temperature measurement points are arranged along the height direction on side wall A, and three temperature measurement points are arranged along the height direction on side wall B (symmetrical left and right), to reflect the temperature deviation and local anomalies in the wall-attached area as the height changes.

[0055] By using the above arrangement of "6 (upper transverse) + 3 (A side wall) + 3 (B side wall)," the temperature distribution characteristics of the two sides of the cross-section and the middle region can be characterized simultaneously.

[0056] For example, in the oxygen measurement point arrangement, six zirconia oxygen probes are arranged in the cross section, and all measurement points are arranged in the two side wall areas: three oxygen measurement points are arranged along the height direction on side wall A, and three oxygen measurement points are arranged along the height direction on side wall B (symmetrical left and right), which are used to focus on capturing the local hypoxia risk in the wall-attached areas on both sides and its distribution characteristics as height changes.

[0057] For example, the installation method and sealing are as follows: both the thermocouple and the zirconia probe adopt the side-wall opening insertion installation method, and a reliable fixation is achieved by using a sleeve / seat tube + flange connection, and a sealing structure is adopted to avoid air leakage; the probe extends into the flue to ensure that the measurement is representative, and at the same time facilitates maintenance and replacement.

[0058] In summary, this embodiment uses a symmetrical point layout of "12 temperature points + 6 oxygen points" to obtain oxygen and temperature distribution data reflecting the differences between the A / B side wall-attached area and the central area on the same monitoring cross section, providing high-quality input data for subsequent characteristic index calculation, model training and optimized control.

[0059] Step S3: Collect runtime data.

[0060] In this embodiment, the present invention collects multiple sets of operating data during boiler operation, including data under two typical operating conditions: fly ash blackening and no fly ash blackening. The collected data includes: fly ash blackening index, dry ash-free volatile matter content of the coal fed into the boiler, coal powder fineness (R90), coal feed rate of each coal mill, primary air volume of each burner, and two-dimensional oxygen distribution data and two-dimensional temperature distribution data measured in step S2.

[0061] For example, during data collection, the sample operating conditions are ensured to be covered (based on the actual operating characteristics of the power plant). In this invention, the data collection period covers different load segments and coal type change cycles, focusing on capturing the following three types of characteristic data:

[0062] Operating Condition A (Severe Blackening Sample Set): Selected high-load periods with unit load > 530MW and burning high-volatile non-design coal with dry ash-free volatile matter > 35%. Under these conditions, the furnace heat load is high, the primary air ratio is often insufficient, obvious blackening is visible to the naked eye, and the index values ​​are significantly higher.

[0063] Condition B (Slight Blackening Sample Set): Selects transitional conditions where the blackening index is within the critical range, which usually occurs during load fluctuations or coal blending ratio adjustments, and is used to train the model's sensitivity to critical states.

[0064] Operating Condition C (No Floating Black / Benchmark Sample Set): Selects periods when the unit is operating stably at low load, or when combustion is complete and fly ash color is normal after optimization and adjustment (floating black index is extremely low or zero). This type of data is used as "low floating black sample" to help the model learn the ideal combustion state.

[0065] For example, a list of variables is collected by constructing a complete dataset containing input variables (feature values) and output variables (target values), specifically including:

[0066] Result data (label): fly ash and black residue index obtained by step S1 at the corresponding time.

[0067] Fuel and pulverizing data: Industrial analysis data of coal fed into the furnace, focusing on the dry ash-free volatile matter and the operating parameters of the pulverizing system, especially the fineness of coal powder (R90) and the coal feed rate of each coal mill (AF). The fineness of coal powder R90 is a key physical parameter affecting the carbon burnout rate and is directly related to the cause of blackening.

[0068] Air distribution and combustion parameters: primary air volume (or primary air pressure) of each burner, secondary air box damper opening, horizontal and vertical swing angle of burnout air (SOFA), and average oxygen content at the SCR inlet;

[0069] Two-dimensional flow field distribution data (key features): Two-dimensional temperature distribution data and two-dimensional oxygen distribution data obtained by the sensor arrays on the A / B sides in step S2. These data are no longer single average values, but spatial distribution fields that can reflect the left / right deviation of the flue section and the deep / shallow gradient.

[0070] Step S4: Calculate the characteristic index.

[0071] In this embodiment, based on the real-time operating data collected in step S3, the calculation module of the DCS system is used to calculate the key characteristic indicators affecting fly ash blackening according to the following logic:

[0072] Calculate the wind-coal matching index Extract the primary air volume of the pulverized coal feeding pipes corresponding to each burner. Ash-free volatile matter in dried coal fed into the furnace ratio This indicator is used to characterize whether the initial oxygen provided by the primary air is sufficient to meet the combustion requirements when high volatile coal is rapidly released during the initial stage of ignition.

[0073] Calculate the oxygen balance index Read the real-time values ​​of the six zirconia oxygen sensors arranged in step S2, and calculate the standard deviation of all oxygen measurement points on the cross section at that moment. The larger the value of this index, the more uneven the oxygen supply distribution of the flue section is, and the greater the risk of local oxygen deficiency.

[0074] Calculate temperature uniformity index Read the real-time values ​​of the 12 thermocouples arranged in step S2, and calculate the standard deviation of all temperature measuring points on the cross section at that moment. This index is used to help determine whether the combustion center is skewed and the uniformity of the heat load distribution.

[0075] Step S5: Build a prediction model.

[0076] In this embodiment, the specific implementation process includes:

[0077] Step S51: Select high-quality training samples from the power plant's historical operation database to construct a sample dataset.

[0078] For example, in order to ensure that the model can both identify high-float black conditions and learn low-float black baseline conditions, the sample set preferably includes the following three types of typical data:

[0079] Severe blackening sample: Corresponds to operating condition A, used to learn the severe combustion modes that lead to blackening;

[0080] Slightly dark sample: corresponding to working condition B, used to learn the weak features when the system is in a critical state;

[0081] No floating black (baseline) sample: corresponding to operating condition C, used to learn the parameter combination under ideal combustion conditions. The above data is cleaned and normalized to remove outliers caused by sensor malfunctions, forming a standardized training set.

[0082] Step S52: Establishing input and output variables.

[0083] In this embodiment, to ensure that the model accurately reflects the combined impact of "coal-air-field" on the surface black, the variable system of the model is set as follows:

[0084] Input variables (feature variables): Select the calculated wind-coal matching index. Oxygen balance index Temperature uniformity index The collected coal powder fineness (R90) and volatile matter content of the coal entering the furnace were measured. , as well as the two-dimensional oxygen distribution matrix and the two-dimensional temperature distribution matrix obtained based on the monitoring grid.

[0085] Output (target variable): The fly ash blackening index obtained by actual measurement according to the measurement method under the corresponding working conditions.

[0086] Step S53: Perform algorithm selection and model training.

[0087] For example, data mining and machine learning algorithms (those skilled in the art can choose modeling algorithms such as SVR, neural networks, or ensemble learning according to the amount of data and deployment requirements) are used to train the above sample set. Through iterative learning of the algorithm, a high-dimensional nonlinear mapping relationship between the input (combustion process parameters and distribution characteristics) and the output (final degree of blackening) is established, thereby constructing a "fly ash blackening prediction model".

[0088] Step S54: Perform online prediction.

[0089] For example, the trained model can be deployed in a DCS control system or a standalone combustion optimization workstation. The system reads the current sensor data and air-coal parameters in real time, inputs them into the model, and can output the "predicted black spore index" at the current moment online, providing feedforward signals for subsequent optimization control and solving the problem of strong lag in traditional offline testing.

[0090] Step S6: Optimization control based on distributed constraints.

[0091] In this embodiment, the predicted floating black index is output based on the established prediction model. Based on the calculated characteristic indicators, the control system (which can be a DCS or an independent combustion optimization workstation) performs hierarchical closed-loop optimization control to reduce the level of fly ash black while meeting operational constraints.

[0092] For example, the specific implementation process includes:

[0093] Step S61: Set the trigger and control target.

[0094] For example, the threshold for the blackout warning is set to... When online predicted values If the predicted blackening index shows an upward trend for a continuous period of time, it is determined that there is a risk of blackening generation under the current operating condition, and optimization control is initiated; the control objective is to reduce the predicted blackening index under the constraint conditions. The oxygen content and temperature distribution uniformity are reduced and tend to stabilize, while ensuring that the oxygen content and temperature distribution uniformity are not inferior to the target conditions for low float black.

[0095] Step S62: Determine the constraints and thresholds.

[0096] For example, to avoid introducing combustion safety and efficiency risks by reducing the predicted value through "extreme air distribution / extreme air-coal ratio", the following constraints are set:

[0097] Oxygen balance constraints: ;

[0098] Temperature uniformity constraint: ;

[0099] Wind-coal matching interval constraints: ;

[0100] Absolute oxygen content constraint: based on the arrangement of oxygen measurement points Maintain the combustion within a preset reasonable range (e.g., 2.5% to 4.5%, which can be set according to the characteristics of the unit).

[0101] Among them, threshold , as well as , Determined through statistical analysis of historical operating samples, specifically based on the obtained floating black index. Select a low-floating black target sample set (e.g.) (for the working condition samples), statistical analysis was performed on each sample set. , and The distribution characteristics will , Upper limit statistical values ​​(e.g., upper quantile or mean) (multiple standard deviations) was determined as , and will The lower limit and upper limit of statistical values ​​(e.g., upper quantile or mean) (multiple standard deviations) were determined as follows: , This ensures that the real-time distribution uniformity and the degree of air-coal matching are not inferior to the target conditions for low-floating black.

[0102] Step S63: Perform primary regulation, prioritizing the regulation of wind and coal matching (total amount).

[0103] For example, when monitored When (indicating a relative shortage of primary air supply and a tendency for localized oxygen deficiency during volatile matter release), priority should be given to adjusting the total volume of the primary air system. Under the premise of meeting furnace pressure and unit safety constraints, increase the primary air volume or primary air damper opening of the relevant coal mill / burner branches, or adjust the coal feed rate and primary air volume in a coordinated manner. Return to the preset matching range; when At this time, the primary air volume can be appropriately reduced or the air and coal distribution can be optimized to bring it back to the matching range and avoid efficiency loss and deviation from combustion organization caused by excessive air.

[0104] Step S64: Perform secondary adjustment.

[0105] For example, based on satisfying the wind-coal matching interval constraint, if If significant deviations are observed at the oxygen measurement points on both sides of the wall, the relative oxygen-deficient or oxygen-enriched trend on sides A and B is determined based on the feedback from the oxygen measurement points (3 points on side A and 3 points on side B). Asymmetrical distribution adjustments are then made to the stratified secondary air and burnout air (OFA): increasing the opening or airflow ratio of the corresponding damper / OFA on the relatively oxygen-deficient side and decreasing the corresponding opening or airflow ratio on the relatively oxygen-enriched side, thereby reducing the oxygen supply difference between the two sides of the wall and promoting oxygen production. The oxygen content should fall back to the threshold range; at the same time, the absolute value constraint of oxygen content should be continuously checked to avoid unstable combustion due to excessively low oxygen content or decreased efficiency due to excessively high oxygen content.

[0106] Step S65: Perform three-level adjustment, namely, temperature distribution uniformity adjustment (correcting combustion center offset and uneven heat load).

[0107] For example, based on satisfying the above-mentioned oxygen distribution constraints, if If the temperature measuring points show a trend of lateral burning / high temperature adhering to the wall, then based on the temperature distribution information constructed from the temperature measuring points (upper horizontal measuring points and measuring points on both side walls), it is determined whether the combustion center is biased towards side A or side B and whether there are local high / low temperature areas. By fine-tuning the secondary air ratio on the corresponding side and the opening of the relevant burner dampers (and, if necessary, linking the primary air or coal feed distribution), the combustion center is pushed back, reducing the temperature dispersion and... Control it within a preset range (for example, make the standard deviation not exceed a certain threshold, such as within 30℃, which can be determined by the statistics of historical low floating black samples).

[0108] Step S66: Setting closed-loop iteration and exit conditions.

[0109] In this embodiment, the control system continuously collects new oxygen / temperature distribution and operating parameters after each adjustment and recalculates. , , The current data is then input into the prediction model in step S5 to update the predicted floating black index. When satisfied and , , After a period of time (which can be set to several sampling periods), it is determined that the optimization has reached the target, and the control system enters the monitoring state and maintains the current parameter combination; if the warning condition is triggered again, the above hierarchical closed-loop optimization process will be re-entered.

[0110] This invention achieves measurability, evaluability, predictability, and controllability of floating black matter through a closed-loop path of "quantitative measurement of floating black matter - multi-point two-dimensional oxygen and temperature field monitoring - characteristic index system - predictive modeling - constrained optimization control".

[0111] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0112] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for treating blackening in boiler fly ash, characterized in that: The following steps are included: Step S1: Quantitatively measure the fly ash and black residue from the boiler; Step S2: Deploy the sensor array to construct a two-dimensional high-resolution monitoring grid covering the entire horizontal flue cross section, and acquire two-dimensional oxygen distribution data and two-dimensional temperature distribution data in real time; Step S3: Collect actual operating data of the boiler, and use the actual operating data, two-dimensional oxygen distribution data, and two-dimensional temperature distribution data to construct a comprehensive dataset; Step S4: Calculate key characteristic indicators based on the collected operational data, including air-coal matching index, oxygen balance index, and temperature balance index. Step S5: Establish a fly ash and black residue prediction model to predict the amount of fly ash and black residue; Step S6: Based on the output predicted floating black index and the calculated characteristic index, the control system executes hierarchical closed-loop optimization control.

2. The method for treating blackening of boiler fly ash according to claim 1, characterized in that: The quantitative measurement of fly ash black in step S1 includes: obtaining a representative fly ash sample by sampling and mixing at multiple points from the ash discharge system at the tail of the boiler; then putting the weighed fly ash sample into a beaker containing clean water; stirring to make all the black float to the surface; then letting it stand to separate the black from the fly ash; filtering out the black and drying it before weighing it; and using the ratio of the weight of the black to the weight of the fly ash sample as the fly ash black index.

3. The method for treating blackening of boiler fly ash according to claim 2, characterized in that: Step S2 includes: The sensor array is arranged in the horizontal flue monitoring section between the outlet of the high-temperature superheater and the inlet of the high-temperature reheater. The two-dimensional high-resolution monitoring grid includes constructing a two-dimensional monitoring array on the monitoring cross section, including the arrangement of temperature measuring points and oxygen measuring points, and acquiring two-dimensional oxygen distribution data and two-dimensional temperature distribution data reflecting the differences between the A / B side wall-attached area and the central area on the same monitoring cross section.

4. The method for treating blackening of boiler fly ash according to claim 3, characterized in that: The temperature point arrangement includes: K-type thermocouples are arranged at the monitoring section, forming an overall structure of "horizontal points at the top + vertical points on both side walls," wherein: Upper transverse layout: Temperature measuring points are arranged symmetrically along the width of the flue at the upper part of the monitoring section, covering the area from side A to the middle to side B, to reflect the temperature distribution and left-right deviation of the upper mainstream area. Vertical temperature measurement points on the side walls: Temperature measurement points are arranged along the height direction on side wall A and on side wall B to reflect the temperature deviation and local anomalies in the wall-attached area as the height changes. By using the arrangement of the upper transverse section + A side wall + B side wall, the temperature distribution characteristics of the two wall-attached areas and the middle area of ​​the monitoring section can be characterized simultaneously.

5. The method for treating blackening of boiler fly ash according to claim 4, characterized in that: The oxygen measurement point layout includes: arranging zirconia oxygen probes on the monitoring section, with all measurement points located in the areas of both side walls. Oxygen measurement points are arranged along the height direction on side wall A and side wall B, to capture the local hypoxia risk in the wall-adhering areas on both sides and its distribution characteristics as a function of height.

6. The method for treating blackening of boiler fly ash according to claim 5, characterized in that: Step S3 includes: The actual operating data collected includes data under two typical operating conditions: with and without floating black, and the collection period covers different load segments and coal type change cycles. Actual operating data includes: fly ash blackening index, dry ash-free volatile matter of coal fed into the furnace, coal powder fineness, coal feed rate of each coal mill, air distribution data, and average oxygen content at the SCR inlet.

7. The method for treating blackening of boiler fly ash according to claim 6, characterized in that: Step S4 includes: Calculate the air-coal matching index: extract the ratio of the primary air volume of the pulverized coal feeding pipeline corresponding to each burner to the dry ash-free volatile matter of the coal fed into the furnace, which characterizes whether the initial oxygen provided by the primary air can meet the combustion requirements when high volatile coal is rapidly released in the early stage of ignition. Calculate the oxygen balance index: Read the real-time values ​​of the deployed zirconia oxygen sensors and calculate the standard deviation of all oxygen measurement points on the cross section at that moment. The larger the standard deviation of all oxygen measurement points, the more uneven the oxygen supply distribution of the flue section is, and the greater the risk of local oxygen deficiency. Calculate the temperature uniformity index: Read the real-time values ​​of the arranged thermocouples, calculate the standard deviation of all temperature measuring points on the cross section at that moment, and use the standard deviation of all temperature measuring points to help determine whether the combustion center is skewed and the uniformity of the heat load distribution.

8. The method for treating blackening of boiler fly ash according to claim 7, characterized in that: Step S5, establishing the fly ash and black residue prediction model, includes: Step S51: Select training samples from the historical running database to construct a sample dataset; Step S52: Set the variable system for the fly ash and black powder prediction model and determine the input and output variables; Step S53: Use data mining and machine learning algorithms to train the sample set. Through iterative learning of the algorithm, establish a high-dimensional nonlinear mapping relationship between the input and output quantities, and construct a fly ash and floating black prediction model. Step S54: Deploy the trained fly ash blackening prediction model in the DCS control system or a separate combustion optimization workstation. The system reads the current sensor data and air-coal parameters in real time, inputs them into the fly ash blackening prediction model, and outputs the predicted blackening index at the current moment online.

9. A method for treating blackening of boiler fly ash according to claim 8, characterized in that: The implementation of step S6 includes: Step S61: Set the trigger conditions and control objectives for starting optimization control; Step S62: Introduce constraints including oxygen balance constraint, temperature balance constraint, air-coal matching interval constraint, and oxygen absolute value constraint, and confirm the corresponding thresholds; Step S63: When the wind-coal matching index is detected to be less than the set threshold, the total amount of primary air system is adjusted first to achieve primary regulation; Step S64: Based on satisfying the air-coal matching interval constraint, the stratified secondary air and burnout air are then asymmetrically distributed and adjusted to achieve secondary regulation; Step S65: Based on satisfying the above-mentioned oxygen distribution constraints, the temperature distribution uniformity is finally adjusted to achieve three-level regulation; Step S66: After each adjustment, the control system continuously collects new oxygen / temperature distribution and operating parameters, recalculates the air-coal matching index, oxygen balance index, and temperature balance index, and inputs the current data into the fly ash blackening prediction model to update the predicted blackening index. When the predicted blackening index is less than the set blackening warning threshold and the oxygen balance constraint, temperature balance constraint, and air-coal matching interval constraint are met for a period of time, it is determined that the optimization has achieved the goal. The control system enters the monitoring state and maintains the current parameter combination. When the warning condition is triggered again, it re-enters the hierarchical closed-loop optimization process.

10. A method for treating blackening of boiler fly ash according to claim 9, characterized in that: Achieving secondary regulation includes: Based on the constraint of the air-coal matching range, when the oxygen balance index is greater than the set threshold or there is a significant deviation in the oxygen measurement points on both sides of the wall, the relative oxygen-deficient or oxygen-rich trend of the A / B side is determined according to the feedback from the oxygen measurement points, and the stratified secondary air and burnout air are asymmetrically distributed and adjusted. The three-level adjustment includes: on the basis of meeting the oxygen distribution constraints, if the temperature uniformity index is greater than the set threshold and the temperature measuring points show a trend of left-right bias / high temperature adhering to the wall, based on the temperature distribution information constructed by the temperature measuring points, it is determined whether the combustion center is biased towards side A or side B and whether there are local high / low temperature areas. By fine-tuning the secondary air ratio on the corresponding side and the opening of the relevant burner damper, the combustion center is pushed back, so as to reduce the temperature dispersion and control the temperature uniformity index within the preset range.

Images