Soot blowing method, system, electronic device, and storage medium

Abstract

The application provides a soot blowing method and system, an electronic device and a storage medium. The soot blowing method comprises the following steps: acquiring a space-time temperature field matrix of a boiler, coal quality parameters and thermal resistance parameters; generating thermal resistances of multiple heated areas according to the thermal resistance parameters and the coal quality parameters; inputting the space-time temperature field matrix and the coal quality parameters into a trained long short-term memory network model to generate coking probabilities of the heated areas; determining risk information of the heated areas according to the coking probabilities of the heated areas; determining wall temperatures of a furnace corresponding to soot blowing guns according to the space-time temperature field matrix; generating a soot blowing control strategy with steam consumption and coking risk as optimization targets according to the wall temperatures of the furnace corresponding to the soot blowing guns, the risk information of the heated areas and the thermal resistances of the multiple heated areas; and controlling the soot blowing guns to perform soot blowing on the boiler according to the soot blowing control strategy.

Description

Technical Field

[0001] This application relates to the technical field of boiler control in coal-fired power plants, and more particularly to a soot blowing method, system, electronic equipment, and storage medium. Background Technology

[0002] Soot blowing technology in coal-fired boilers aims to remove ash buildup in heated areas to maintain efficient operation. It mainly includes mechanical soot blowing, acoustic soot blowing, and shock wave soot blowing. Mechanical soot blowing is the most common method, using a high-pressure medium (such as steam or compressed air) to impact the ash buildup through a soot blower. Long telescopic and fixed rotary soot blowers are widely used. Other methods include direct scraping with wire brushes / scrapers or rapping to remove ash. Acoustic soot blowing utilizes the vibration effect of low-frequency sound waves to loosen and remove ash, offering advantages such as non-contact operation, no medium consumption, and wide coverage. Shock wave soot blowing (pulse soot blowing) uses the instantaneous ignition of combustible gas to generate high-energy shock waves to remove ash, highly efficient for stubborn ash but requiring high safety standards. Hydraulic soot blowing, while highly efficient, has a significant impact on boiler thermal stress and is usually limited to shutdown maintenance or extreme situations. In practical applications, different methods are often combined to adapt to the ash characteristics of different parts of the boiler and achieve the best cleaning effect.

[0003] Existing soot blowing methods are all based on blowing soot in a certain area, which cannot be precise to each soot blowing gun, resulting in poor blowing effect. Summary of the Invention

[0004] This application provides a soot blowing method, system, electronic device, and storage medium to solve the problems existing in related technologies. The technical solution is as follows:

[0005] In a first aspect, embodiments of this application provide a method for blowing away soot, including:

[0006] Obtain the spatiotemporal temperature field matrix, coal quality parameters, and thermal resistance parameters of the boiler;

[0007] Based on the thermal resistance parameters and the coal quality parameters, the thermal resistance of multiple heated regions is generated;

[0008] The spatiotemporal temperature field matrix and the coal quality parameters are input into a trained long short-term memory network model to generate the coking probability of each heated region.

[0009] Based on the coking probability of each heated area, the risk information of each heated area is determined;

[0010] Based on the spatiotemporal temperature field matrix, determine the furnace wall temperature corresponding to each sootblowing gun;

[0011] Based on the furnace wall temperature corresponding to each soot blowing gun, the risk information of each heated area, and the thermal resistance of the multiple heated areas, a soot blowing control strategy is generated with steam consumption and coking risk as optimization targets.

[0012] The soot blowing control strategy is used to control each soot blowing gun to blow soot onto the boiler.

[0013] In one embodiment of this application, obtaining the spatiotemporal temperature field matrix of the boiler includes:

[0014] Acquire temperature data at various points in the boiler;

[0015] The temperature data is processed by wavelet transform to remove noise, and the spatiotemporal temperature field matrix of the boiler is obtained.

[0016] In one embodiment of this application, the thermal resistance parameters include heat transfer temperature difference, heat flux density, and heat transfer area of ​​the heated region; generating the thermal resistance of multiple heated regions based on the thermal resistance parameters and the coal quality parameters includes:

[0017] Based on the coal quality parameters, determine the coal quality correction coefficient;

[0018] The thermal resistance of multiple heated regions is determined based on the heat transfer temperature difference, the heat flux density, the heat exchange area of ​​the heated region, and the coal quality correction coefficient.

[0019] In one embodiment of this application, the step of inputting the spatiotemporal temperature field matrix and the coal quality parameters into a trained long short-term memory network model to generate the coking probability of each heated region includes:

[0020] Based on the trained Long Short-Term Memory (LSTM) network model, the activation function, hidden layer weight matrix, hidden layer state vector of the LSM network at time t-1, input layer weight matrix, and bias term of the LSM network are obtained.

[0021] The coking probability of generating each heated region is determined based on the spatiotemporal temperature field matrix, the coal quality parameters, the activation function, the hidden layer weight matrix, the hidden layer state vector of the long short-term memory network at time t-1, the input layer weight matrix, and the bias term of the long short-term memory network.

[0022] In one embodiment of this application, determining the risk information of each heated area based on the coking probability of each heated area includes:

[0023] The probability of coking in each heated area is compared with the first specified threshold and the second specified threshold, respectively.

[0024] If the probability of coking in the heated area is greater than the first specified threshold, the coking risk of the corresponding heated area is high risk.

[0025] If the probability of coking in the heated area is less than or equal to the first specified threshold and the probability of coking in the heated area is greater than or equal to the second specified threshold, the coking risk of the corresponding heated area is medium risk.

[0026] If the probability of coking in the heated area is less than the second specified threshold, the coking risk of the corresponding heated area is low.

[0027] In one embodiment of this application, the step of generating a soot blowing control strategy based on the furnace wall temperature corresponding to each soot blowing gun, the risk information of each heated area, and the thermal resistance of the plurality of heated areas, with steam consumption and coking risk as optimization objectives, includes:

[0028] Based on the furnace wall temperature corresponding to each sootblowing gun and the thermal resistance of the multiple heated areas, the thermal resistance information corresponding to each sootblowing gun is obtained.

[0029] Based on the thermal resistance information of each sootblowing gun, a sootblowing control strategy is generated with steam consumption and coking risk as optimization objectives.

[0030] In one embodiment of this application, the step of generating a soot blowing control strategy based on the thermal resistance information corresponding to each soot blowing gun, with steam consumption and coking risk as optimization objectives, includes:

[0031] A Pareto optimal solution set was generated by using a multi-objective genetic algorithm based on the thermal resistance information of each sootblowing gun, with the optimization objective of jointly minimizing steam consumption and coking risk, and configuring constraints.

[0032] The soot blowing strategy with the highest overall utility in the Pareto optimal solution set is selected as the soot blowing control strategy through fuzzy decision-making.

[0033] Secondly, embodiments of this application provide a soot blowing system, comprising:

[0034] The first acquisition module is used to acquire the spatiotemporal temperature field matrix, coal quality parameters, and thermal resistance parameters of the boiler.

[0035] The first generation module is used to generate the thermal resistance of multiple heated regions based on the thermal resistance parameters and the coal quality parameters.

[0036] The second generation module is used to input the spatiotemporal temperature field matrix and the coal quality parameters into the trained long short-term memory network model to generate the coking probability of each heated region.

[0037] The first determining module is used to determine the risk information of each heated area based on the coking probability of each heated area;

[0038] The second determining module is used to determine the furnace wall temperature corresponding to each sootblowing gun based on the spatiotemporal temperature field matrix.

[0039] The third generation module is used to generate a soot blowing control strategy based on the furnace wall temperature corresponding to each soot blowing gun, the risk information of each heated area, and the thermal resistance of the multiple heated areas, with steam consumption and coking risk as optimization targets.

[0040] The first control module is used to control each soot blowing gun to blow soot onto the boiler according to the soot blowing control strategy.

[0041] Thirdly, embodiments of this application provide an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the above-described soot blowing method.

[0042] Fourthly, embodiments of this application provide a computer-readable storage medium that stores computer instructions, wherein when the computer instructions are executed on a computer, the methods in any of the above-described embodiments are performed.

[0043] The advantages or beneficial effects of the above technical solutions include at least the following:

[0044] In this embodiment, the soot blowing method includes: acquiring the spatiotemporal temperature field matrix, coal quality parameters, and thermal resistance parameters of the boiler; generating the thermal resistance of multiple heated regions based on the thermal resistance parameters and the coal quality parameters; inputting the spatiotemporal temperature field matrix and the coal quality parameters into a trained long short-term memory network model to generate the coking probability of each heated region; determining the risk information of each heated region based on the coking probability of each heated region; determining the furnace wall temperature corresponding to each soot blowing gun based on the spatiotemporal temperature field matrix; generating a soot blowing control strategy with steam consumption and coking risk as optimization objectives based on the furnace wall temperature corresponding to each soot blowing gun, the risk information of each heated region, and the thermal resistance of the multiple heated regions; and controlling each soot blowing gun to blow soot into the boiler according to the soot blowing control strategy. The soot blowing method in this embodiment first determines the thermal resistance of multiple heated areas on the boiler. The spatiotemporal temperature field matrix and coal quality parameters are then input into a trained long short-term memory network model to analyze and obtain risk information for each heated area. Based on the furnace wall temperature corresponding to each soot blowing gun, the risk information of each heated area, and the thermal resistance of the multiple heated areas, a soot blowing control strategy is generated with steam consumption and coking risk as optimization objectives to control the soot blowing operation of each soot blowing gun. According to the actual coking risk, thermal resistance, and furnace wall temperature, the output of the soot blowing guns corresponding to different heated areas is precisely controlled. Soot blowing is increased in areas with a higher probability of coking, and reduced in areas with a lower probability of coking, ensuring a reduction in boiler coking and achieving better soot blowing results. Furthermore, it reduces steam consumption and effectively avoids the problem of wasted steam and poor soot blowing results caused by continuous soot blowing in only a single or multiple areas.

[0045] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of this application will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0046] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments disclosed in this application and should not be construed as limiting the scope of this application.

[0047] Figure 1 This is a flowchart of a soot blowing method according to an embodiment of this application.

[0048] Figure 2 This is a block diagram of an electronic device according to an embodiment of the present application.

[0049] Figure 3This is a schematic diagram of the soot blowing control interface of a soot blowing method according to an embodiment of this application.

[0050] Figure 4 This is a schematic diagram of the heated surface condition monitoring interface of a soot blowing method according to an embodiment of this application.

[0051] Figure 5 This is a schematic diagram of a coking warning method for the heated surface in a soot blowing method according to an embodiment of this application.

[0052] Figure 6 This is a schematic diagram of the temperature field distribution of the heated surface in a soot blowing method according to an embodiment of this application. Detailed Implementation

[0053] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of this application. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0054] Traditional soot blowing systems have three core problems:

[0055] Rigid soot blowing strategies rely on fixed cycles or manual experience, failing to dynamically adjust strategies based on coal characteristics (such as alkali metal content and ash melting point) and ash accumulation in heated areas. This results in low soot blowing efficiency and significant steam waste. For example, high-alkali coal is prone to coking in the screened area during combustion, and traditional soot blowing can easily lead to localized over-blowing or under-blowing.

[0056] The monitoring methods are limited: there is a lack of refined monitoring of the furnace temperature field distribution. Relying solely on the furnace outlet flue gas temperature (heat balance method) cannot reflect the local coking status, leading to a lag in soot blowing decisions.

[0057] Delayed coal quality identification: The offline coal quality testing cycle is long (6-12 hours), making it impossible to correct the calorific value in real time, which affects the coordinated control of soot blowing and combustion optimization.

[0058] Limitations of existing technology

[0059] Temperature monitoring technology: Single-point temperature measurement cannot cover the entire furnace area, and infrared thermal imagers are expensive and have poor anti-interference capabilities.

[0060] Limitations of thermal resistance models: Traditional thermal resistance formulas do not consider dynamic corrections for coal quality, which may lead to increased deviations in thermal resistance calculations.

[0061] Soot blowing priority strategy: Although the existing technology is based on temperature monitoring to trigger soot blowing, it does not combine coal quality characteristics and coking trend prediction, resulting in a "one-size-fits-all" problem.

[0062] Low precision in soot blowing: Existing intelligent soot blowing strategies are mostly based on soot blowing in a certain area, and cannot be precise to each soot blowing gun, so they cannot achieve true on-demand soot blowing.

[0063] The soot blowing method provided in the embodiments of this application is applicable to the cleaning control of boiler heating areas under complex operating conditions involving multiple coal types such as high-alkali coal and low-quality coal.

[0064] Figure 1 A flowchart illustrating a soot blowing method according to an embodiment of this application is shown. Figures 1-6 As shown, a soot blowing method may include:

[0065] S110: Obtain the spatiotemporal temperature field matrix, coal quality parameters, and thermal resistance parameters of the boiler;

[0066] S120: Generate the thermal resistance of multiple heated areas based on the thermal resistance parameters and the coal quality parameters;

[0067] S130: Input the spatiotemporal temperature field matrix and the coal quality parameters into the trained long short-term memory network model to generate the coking probability of each heated region;

[0068] S140: Determine the risk information of each heated area based on the coking probability of each heated area;

[0069] S150: Determine the furnace wall temperature corresponding to each sootblowing gun based on the spatiotemporal temperature field matrix.

[0070] S160: Based on the furnace wall temperature corresponding to each soot blowing gun, the risk information of each heated area, and the thermal resistance of the multiple heated areas, a soot blowing control strategy is generated with steam consumption and coking risk as optimization targets.

[0071] S170: Control each soot blowing gun to blow soot onto the boiler according to the soot blowing control strategy.

[0072] The soot blowing method in this embodiment first determines the thermal resistance of multiple heated areas on the boiler. The spatiotemporal temperature field matrix and coal quality parameters are then input into a trained long short-term memory network model to analyze and obtain risk information for each heated area. Based on the furnace wall temperature corresponding to each soot blowing gun, the risk information of each heated area, and the thermal resistance of the multiple heated areas, a soot blowing control strategy is generated with steam consumption and coking risk as optimization objectives to control the soot blowing operation of each soot blowing gun. According to the actual coking risk, thermal resistance, and furnace wall temperature, the output of the soot blowing guns corresponding to different heated areas is precisely controlled. Soot blowing is increased in areas with a higher probability of coking, and reduced in areas with a lower probability of coking, ensuring a reduction in boiler coking and achieving better soot blowing results. Furthermore, it reduces steam consumption and effectively avoids the problem of wasted steam and poor soot blowing results caused by continuous soot blowing in only a single or multiple areas.

[0073] In step S110, the spatiotemporal temperature field matrix, coal quality parameters, and thermal resistance parameters of the boiler are obtained.

[0074] In this embodiment, distributed infrared sensors (accuracy ±5℃) are installed in areas such as the left wall, front wall, and screen of the boiler furnace. This can be achieved by deploying infrared temperature sensor arrays (3-5 sensors per square meter) in key areas, covering ≥95% of the area. Data is uploaded to edge computing nodes in real time via the OPC UA protocol. These edge computing nodes are deployed locally within the furnace to process temperature data and generate temperature field thermograms in real time, reducing cloud transmission latency. The edge computing nodes are equipped with AI acceleration chips, supporting millions of data points per second with a response latency of <50ms.

[0075] Temperature data for each heated zone in the furnace can be measured using various infrared sensors. To ensure the accuracy of the temperature data, moving averages, wavelet transforms, or Kalman filters can be used to eliminate outliers.

[0076] Temperature data is collected in real time by temperature sensors distributed at different locations in the boiler furnace. Each sensor corresponds to a specific coordinate in the furnace space (such as XYZ or other two-dimensional / three-dimensional spatial points).

[0077] Spatiotemporal matrix construction

[0078] Time dimension: Record data at a set sampling interval (e.g., every 1 second).

[0079] Spatial dimension: Data is arranged according to the spatial layout of the sensors.

[0080] Original matrix construction: Generate the temperature distribution matrix of all measuring points in the furnace at each time step.

[0081] Interpolation processing (optional): If the number of spatial measurement points is limited, interpolation algorithms (such as bilinear interpolation / Kriging) can be used to supplement the spatial temperature distribution and achieve high-precision temperature field reconstruction.

[0082] Temporal arrangement: Stack the spatial distribution matrices at different time points along the time axis to form a three-dimensional "spatiotemporal temperature field" data structure (such as Tensor: Time × Width × Height).

[0083] Visualization techniques such as heat maps and isothermal surfaces are used to display the distribution of temperature over time and space, which helps to determine the boiler's operating status.

[0084] The formula for generating a temperature field thermogram is:

[0085] in, For sensor weights, Let be the temperature value of the i-th sensor.

[0086] Thermal resistance parameters include: Represents the thermal resistance of the heated surface; Represents the heat transfer temperature difference (the temperature difference between the flue gas and the working fluid); Represents heat flux density (heat transfer per unit area); Represents the heat transfer area of ​​the heated surface; This represents the coal quality correction coefficient (dynamically adjusted based on coal quality characteristics and updated in real time via an online coal quality analyzer).

[0087] Coal quality parameters include: , , The coefficient represents the coal quality sensitivity coefficient (obtained through experimental calibration); Ash% represents the ash content of the coal; Na% represents the sodium content (mass fraction) of the coal; K% represents the potassium content (mass fraction) of the coal. It can support real-time soft measurement of ash, sulfur, and alkali metal content through an integrated online coal quality analysis interface, with a measurement error of <2%.

[0088] in:

[0089] In step S120, the thermal resistance of multiple heated regions is generated based on the thermal resistance parameters and the coal quality parameters.

[0090] In this embodiment, the result can be obtained through calculation using coal quality parameters; This represents the coal quality correction coefficient (dynamically adjusted based on coal quality characteristics and updated in real time via an online coal quality analyzer).

[0091]

[0092] The following calculations are performed using thermal resistance parameters and coal quality parameters:

[0093] Dynamically corrected thermal resistance calculation formula based on online soft measurement model of coal quality (such as ash content and alkali metal content):

[0094] in: Represents the thermal resistance of the heated surface; Represents the heat transfer temperature difference (the temperature difference between the flue gas and the working fluid); Represents heat flux density (heat transfer per unit area); Represents the heat transfer area of ​​the heated surface; This represents the coal quality correction coefficient (dynamically adjusted based on coal quality characteristics and updated in real time via an online coal quality analyzer).

[0095] The above formula is for calculating the thermal resistance of a heated surface;

[0096] The formula for calculating the thermal resistance of any heating surface in the entire boiler is as follows:

[0097] Where: Rf,i represents the thermal resistance of the i-th heated surface, Twall,i represents the flue gas temperature of the i-th heated surface, Tfluid,i represents the working fluid temperature of the i-th heated surface, qi represents the heat flux density (heat transfer per unit area) of the i-th heated surface; Ai represents the heat exchange area of ​​the i-th heated surface. This represents the coal quality correction factor.

[0098] This allowed us to determine the thermal resistance of multiple heated surfaces.

[0099] In some embodiments, a thermal resistance-coal quality-load correlation model is trained based on historical data to predict the future trend of thermal resistance changes in the heated area. This facilitates the analysis of the thermal resistance of the entire boiler, enabling proactive measures to be taken and adjustments made to control the soot blowing guns to blow soot in areas with higher future thermal resistance.

[0100] In step S130, the spatiotemporal temperature field matrix and the coal quality parameters are input into the trained long short-term memory network model to generate the coking probability of each heated region.

[0101] In this embodiment, the spatiotemporal temperature field matrix and coal quality parameters are input into a trained Long Short-Term Memory (LSTM) network model to output the coking probability of each heated region.

[0102]

[0103] in, This represents the probability of coking on the heated surface at time t; This represents an activation function (such as the Sigmoid function, which compresses the output to the 0-1 range). This represents the weight matrix of the LSTM hidden layer; This represents the hidden state vector of the LSTM at time t-1; This represents the weight matrix of the LSTM input layer; This represents the input feature vector (such as temperature and coal quality parameters) at time t. This represents the LSTM bias term.

[0104] In step S140, risk information for each heated area is determined based on the coking probability of each heated area.

[0105] In this embodiment, the coking probability of each heated area can be determined by the above model, and the risk level is divided according to the coking probability value of the heated area, generating a three-level risk level (high risk: probability >80%; medium risk: 50%~80%; low risk: <50%).

[0106] By classifying the coking and deformation of each heated area according to the three risk levels mentioned above, we can determine which areas are high-risk, which are medium-risk, and which are low-risk, thus identifying the risk information for each heated area.

[0107] In step S150, the furnace wall temperature corresponding to each sootblowing gun is determined according to the spatiotemporal temperature field matrix.

[0108] In this embodiment, the real-time temperature of each location in the boiler furnace can be known through the spatiotemporal temperature matrix. The heated area is divided according to the position to which the soot blowing gun blows. The above division of the heated area can also be based on the position to which the soot blowing gun blows, thereby determining the furnace wall temperature corresponding to each soot blowing gun.

[0109] In step S160, a soot blowing control strategy is generated based on the furnace wall temperature corresponding to each soot blowing gun, the risk information of each heated area, and the thermal resistance of the multiple heated areas, with steam consumption and coking risk as optimization targets.

[0110] Cleaning of heat transfer surfaces in coal-fired power plant boilers is typically done by blowing soot with heated steam. However, it is difficult for operators to directly estimate the degree of soot accumulation on each heat transfer surface using thermodynamic parameters such as flue gas and steam temperature and pressure. Therefore, in most coal-fired power plants in China, soot blowers are started continuously according to a predetermined sequence and fixed schedule. Excessive operation of soot blowers leads to steam waste, while insufficient soot blowing reduces heat transfer efficiency. Therefore, providing recommendations for starting soot blowing under appropriate operating conditions is essential.

[0111] The soot blowing method in this embodiment reduces superheated steam consumption while maintaining a high-efficiency heat transfer surface, and avoids excessive soot blowing while maintaining high heat transfer efficiency. In this case, the optimization problem of soot blowing operation is "when to blow" and "for how long". Reasonable soot blowing node settings can effectively improve boiler efficiency.

[0112] The soot blowing method in this embodiment calculates the heat loss of the heating surface by adjusting the soot blowing start and end points, thereby minimizing the sum of the areas of heat loss and improving the boiler's combustion economy. Simultaneously, the soot blowing optimization strategy takes into account safety risks such as furnace wall temperature, overblowing, and coking associated with the soot blowing gun, all contributing to the intelligent soot blowing optimization strategy.

[0113] In this embodiment, the furnace wall temperature corresponding to the sootblowing gun, the risk information of each heated area, and the thermal resistance of each heated area have been determined above. The situation of each heated area is basically clear. In particular, for high-risk coking areas, heated areas with high furnace wall temperatures, and areas with high thermal resistance, corresponding weights can be assigned to the aforementioned high-risk coking areas, heated areas with high furnace wall temperatures, and areas with high thermal resistance. The final result is determined based on the weights. Through this result, multiple locations with high furnace risk and locations with relatively moderate risk can be identified. The standard deviation is calculated to obtain the standard deviation. For example, when the temperature standard deviation exceeds 50°C, local enhanced sootblowing can be triggered, and when the standard deviation is below 30°C, the system can switch to global optimization mode.

[0114] The above mainly considers the risk of coking in the heated areas, aiming to minimize the risk of coking in each heated area. At the same time, it is also necessary to consider the steam consumption, that is, to minimize the steam consumption as well. Both can be considered together to generate a soot blowing control strategy when both are minimized. This soot blowing control strategy can be generated by assigning weights to the steam consumption and coking risk of each area, adding them together, and finally determining the minimum value of the result. This value is then used to determine the control strategy of the soot blowing gun, that is, to select which soot blowing gun to start and at what working intensity to perform the soot blowing operation.

[0115] In step S170, each soot blowing gun is controlled to blow soot onto the boiler according to the soot blowing control strategy.

[0116] In this embodiment, a determined soot blowing control strategy is used to activate the soot blowing gun in the corresponding area to blow soot onto the corresponding heated area.

[0117] In the embodiments of this application, control is achieved through soot blowing guns in each heated zone, which takes into account the reduction of coking risk, enabling the boiler to operate safely, stably and efficiently, while ensuring low steam consumption.

[0118] The sootblowing optimization control strategy includes sootblowing optimization start-up permission, sootblowing optimization forced shutdown, sootblowing optimization interlock, and abnormal alarms. The control strategy is configured to monitor the automatic control communication signal for sootblowing optimization. When the heartbeat signal fails, an alarm is issued on the DCS sootblowing optimization display interface, and the automatic optimization control is disconnected. Before sootblowing, the status of the power plant load, sootblowing equipment on each heating surface, auxiliary equipment, steam source conditions, pipelines, and valves is checked to determine whether the specific requirements for sootblowing operation are met. Based on meeting the sootblowing permission conditions and ensuring the safe and stable operation of the boiler, the control strategy sorts the sootblowing of the heating surface sootblowing guns and sends the sootblowing commands for each heating surface to the DCS system, realizing closed-loop control of sootblowing optimization.

[0119] The soot blowing method in this embodiment achieves precise optimization of the soot blowing strategy. Real-time analysis of coal composition and ash state on the heating surface dynamically adjusts the soot blowing frequency and range, avoiding steam waste. Taking a 660MW unit as an example, soot blowing steam consumption is reduced by 12%-18%, saving approximately 2 million yuan per unit annually (steam price 80 yuan / ton). Combined with a wide-load adaptive optimization algorithm, the excess air-coal ratio is reduced at low loads, and combustion efficiency is improved at high loads, resulting in a 1.2-1.8g / kWh reduction in coal consumption for power generation, saving over 60 million yuan in coal costs annually. The coking warning and graded soot blowing mechanism on the heating surface reduce the risk of tube rupture, extending the equipment maintenance cycle from 12 months to 18-24 months, significantly reducing operation and maintenance costs.

[0120] This invention significantly reduces pollutant emissions through a multi-objective collaborative optimization strategy. Based on an LSTM coking prediction model and online coal quality soft measurement technology, NOx emission concentration is reduced by 8%-12% (actual ≤27.6mg / m³ under a baseline of 30mg / m³), resulting in an annual emission reduction of approximately 800 tons. Improved boiler efficiency reduces fuel consumption, leading to an annual CO2 emission reduction of approximately 1000 tons (coal with 80% carbon content and 98% carbon oxidation rate). Reduced soot blowing steam consumption lowers wastewater discharge by 5000 tons / year, alleviating environmental treatment pressure. In high-alkali coal scenarios such as Zhundong coal, a dynamic thermal resistance model prevents an increase in fly ash carbon content, further reducing carbon emissions.

[0121] 3. Increased equipment reliability and lifespan

[0122] Regional thermal resistance monitoring and graded soot blowing strategies reduce the risk of damage to heated surfaces. Edge computing achieves a 50ms response time, reducing the tube burst rate by 70% compared to traditional methods (from 3 bursts per year to less than 1). Maintenance cycles are extended from 12 months to 18-24 months, and unplanned shutdowns in a power plant's affected area have been reduced to zero, saving over 3 million yuan annually. The soot blowing system adapts to coal combustion fluctuations of ±5%, reduces main steam temperature fluctuations by 40%-60%, and lowers thermal stress losses by over 50%.

[0123] In one embodiment of this application, obtaining the spatiotemporal temperature field matrix of the boiler includes:

[0124] Acquire temperature data at various points in the boiler;

[0125] The temperature data is processed by wavelet transform to remove noise, and the spatiotemporal temperature field matrix of the boiler is obtained.

[0126] In this embodiment, temperature data for each heated zone of the furnace can be measured using various infrared sensors. To ensure the accuracy of the temperature data, wavelet transform can be used to filter out noise and eliminate outliers. The spatiotemporal temperature field matrix is ​​constructed as follows:

[0127] Time dimension: Record data at a set sampling interval (e.g., every 1 second).

[0128] Spatial dimension: Data is arranged according to the spatial layout of the sensors.

[0129] Original matrix construction: Generate the temperature distribution matrix of all measuring points in the furnace at each time step.

[0130] Interpolation processing (optional): If the number of spatial measurement points is limited, interpolation algorithms (such as bilinear interpolation / Kriging) can be used to supplement the spatial temperature distribution and achieve high-precision temperature field reconstruction.

[0131] Temporal arrangement: Stack the spatial distribution matrices at different time points along the time axis to form a three-dimensional "spatiotemporal temperature field" data structure (such as Tensor: Time × Width × Height).

[0132] In one embodiment of this application, the thermal resistance parameters include heat transfer temperature difference, heat flux density, and heat transfer area of ​​the heated region; generating the thermal resistance of multiple heated regions based on the thermal resistance parameters and the coal quality parameters includes:

[0133] Based on the coal quality parameters, determine the coal quality correction coefficient;

[0134] The thermal resistance of multiple heated regions is determined based on the heat transfer temperature difference, the heat flux density, the heat exchange area of ​​the heated region, and the coal quality correction coefficient.

[0135] In this embodiment, the result can be obtained through calculation using coal quality parameters; This represents the coal quality correction coefficient (dynamically adjusted based on coal quality characteristics and updated in real time via an online coal quality analyzer).

[0136]

[0137] The following calculations are performed using thermal resistance parameters and coal quality parameters:

[0138] Dynamically corrected thermal resistance calculation formula based on online soft measurement model of coal quality (such as ash content and alkali metal content):

[0139] in: Represents the thermal resistance of the heated surface; Represents the heat transfer temperature difference (the temperature difference between the flue gas and the working fluid); Represents heat flux density (heat transfer per unit area); Represents the heat transfer area of ​​the heated surface; This represents the coal quality correction coefficient (dynamically adjusted based on coal quality characteristics and updated in real time via an online coal quality analyzer).

[0140] In one embodiment of this application, the step of inputting the spatiotemporal temperature field matrix and the coal quality parameters into a trained long short-term memory network model to generate the coking probability of each heated region includes:

[0141] Based on the trained Long Short-Term Memory (LSTM) network model, the activation function, hidden layer weight matrix, hidden layer state vector of the LSM network at time t-1, input layer weight matrix, and bias term of the LSM network are obtained.

[0142] The coking probability of generating each heated region is determined based on the spatiotemporal temperature field matrix, the coal quality parameters, the activation function, the hidden layer weight matrix, the hidden layer state vector of the long short-term memory network at time t-1, the input layer weight matrix, and the bias term of the long short-term memory network.

[0143] In this embodiment, the spatiotemporal temperature field matrix and coal quality parameters are input into a trained Long Short-Term Memory (LSTM) network model to output the coking probability of each heated region.

[0144]

[0145] in, This represents the probability of coking on the heated surface at time t; This represents an activation function (such as the Sigmoid function, which compresses the output to the 0-1 range). The hidden layer weight matrix represents the Long Short-Term Memory network; This represents the hidden state vector of the Long Short-Term Memory network at time t-1. The input layer weight matrix represents the Long Short-Term Memory (LSTM) network. This represents the input feature vector (such as temperature and coal quality parameters) at time t. This represents the bias term of the Long Short-Term Memory network.

[0146] In one embodiment of this application, determining the risk information of each heated area based on the coking probability of each heated area includes:

[0147] The probability of coking in each heated area is compared with the first specified threshold and the second specified threshold, respectively.

[0148] If the probability of coking in the heated area is greater than the first specified threshold, the coking risk of the corresponding heated area is high risk.

[0149] If the probability of coking in the heated area is less than or equal to the first specified threshold and the probability of coking in the heated area is greater than or equal to the second specified threshold, the coking risk of the corresponding heated area is medium risk.

[0150] If the probability of coking in the heated area is less than the second specified threshold, the coking risk of the corresponding heated area is low.

[0151] In the embodiments of this application, risk levels are divided according to the coking probability value of the heated area, and a three-level risk level is generated.

[0152] Wherein, the first specified threshold can be 80%, and the second specified threshold can be 50%, that is:

[0153] When the probability of coking in the heated area is greater than 80%, the corresponding risk of coking in the heated area is high.

[0154] When the probability of coking in the heated area is less than or equal to 80% and the probability of coking in the heated area is greater than or equal to 50%, the coking risk of the corresponding heated area is medium risk.

[0155] If the probability of coking in the heated area is less than 50%, the corresponding risk of coking in the heated area is low.

[0156] In one embodiment of this application, the step of generating a soot blowing control strategy based on the furnace wall temperature corresponding to each soot blowing gun, the risk information of each heated area, and the thermal resistance of the plurality of heated areas, with steam consumption and coking risk as optimization objectives, includes:

[0157] Based on the furnace wall temperature corresponding to each sootblowing gun and the thermal resistance of the multiple heated areas, the thermal resistance information corresponding to each sootblowing gun is obtained.

[0158] Based on the thermal resistance information of each sootblowing gun, a sootblowing control strategy is generated with steam consumption and coking risk as optimization objectives.

[0159] In this embodiment, the furnace wall temperature corresponding to the sootblowing gun, the risk information of each heated area, and the thermal resistance of each heated area have been determined above. The situation of each heated area is basically clear. In particular, for high-risk coking areas, heated areas with high furnace wall temperatures, and areas with high thermal resistance, corresponding weights can be assigned to the aforementioned high-risk coking areas, heated areas with high furnace wall temperatures, and areas with high thermal resistance. The final result is determined based on the weights. Through this result, multiple locations with high furnace risk and locations with relatively moderate risk can be identified. The standard deviation is calculated to obtain the standard deviation. For example, when the temperature standard deviation exceeds 50°C, local enhanced sootblowing can be triggered, and when the standard deviation is below 30°C, the system can switch to global optimization mode.

[0160] The above mainly considers the risk of coking in the heated areas, aiming to minimize the risk of coking in each heated area. At the same time, it is also necessary to consider the steam consumption, that is, to minimize the steam consumption as well. Both can be considered together to generate a soot blowing control strategy when both are minimized. This soot blowing control strategy can be generated by assigning weights to the steam consumption and coking risk of each area, adding them together, and finally determining the minimum value of the result. This value is then used to determine the control strategy of the soot blowing gun, that is, to select which soot blowing gun to start and at what working intensity to perform the soot blowing operation.

[0161] In one embodiment of this application, the step of generating a soot blowing control strategy based on the thermal resistance information corresponding to each soot blowing gun, with steam consumption and coking risk as optimization objectives, includes:

[0162] Using a multi-objective genetic algorithm, based on the thermal resistance information of each sootblower, and with the joint minimization of steam consumption (Esteam) and coking risk (Trisk) as the optimization objective and with configured constraints, a Pareto optimal solution set is generated.

[0163] The soot blowing strategy with the highest overall utility in the Pareto optimal solution set is selected as the soot blowing control strategy through fuzzy decision-making.

[0164] In this embodiment, the optimization targets are steam consumption (Esteam) and coking risk (Trisk), and the constraints include wall temperature safety threshold, soot blowing frequency, steam pressure, and water supply temperature.

[0165] The Pareto optimal solution set is generated using the multi-objective genetic algorithm MOGA, and the blowing strategy with the highest comprehensive utility is selected through fuzzy decision-making.

[0166] The optimization objective is to jointly minimize steam consumption (Esteam) and coking risk (Trisk):

[0167] This allows us to determine the soot blowing control strategy for controlling the soot blowing gun.

[0168] Secondly, embodiments of this application provide a soot blowing system, comprising:

[0169] The first acquisition module is used to acquire the spatiotemporal temperature field matrix, coal quality parameters, and thermal resistance parameters of the boiler.

[0170] The first generation module is used to generate the thermal resistance of multiple heated regions based on the thermal resistance parameters and the coal quality parameters.

[0171] The second generation module is used to input the spatiotemporal temperature field matrix and the coal quality parameters into the trained long short-term memory network model to generate the coking probability of each heated region.

[0172] The first determining module is used to determine the risk information of each heated area based on the coking probability of each heated area;

[0173] The second determining module is used to determine the furnace wall temperature corresponding to each sootblowing gun based on the spatiotemporal temperature field matrix.

[0174] The third generation module is used to generate a soot blowing control strategy based on the furnace wall temperature corresponding to each soot blowing gun, the risk information of each heated area, and the thermal resistance of the multiple heated areas, with steam consumption and coking risk as optimization targets.

[0175] The first control module is used to control each soot blowing gun to blow soot onto the boiler according to the soot blowing control strategy.

[0176] The soot blowing system in this embodiment first determines the thermal resistance of multiple heated areas on the boiler. The spatiotemporal temperature field matrix and coal quality parameters are then input into a trained long short-term memory network model to analyze and obtain risk information for each heated area. Based on the furnace wall temperature corresponding to each soot blowing gun, the risk information of each heated area, and the thermal resistance of the multiple heated areas, a soot blowing control strategy is generated with steam consumption and coking risk as optimization objectives to control the soot blowing operation of each soot blowing gun. According to the actual coking risk, thermal resistance, and furnace wall temperature, the output of the soot blowing guns corresponding to different heated areas is precisely controlled. Soot blowing is increased in areas with a higher probability of coking, and reduced in areas with a lower probability of coking, ensuring a reduction in boiler coking and achieving better soot blowing results. Furthermore, it reduces steam consumption and effectively avoids the problem of wasted steam and poor soot blowing results caused by continuous soot blowing in only a single or multiple areas.

[0177] In one embodiment of this application, obtaining the spatiotemporal temperature field matrix of the boiler includes:

[0178] Acquire temperature data at various points in the boiler;

[0179] The temperature data is processed by wavelet transform to remove noise, and the spatiotemporal temperature field matrix of the boiler is obtained.

[0180] In one embodiment of this application, the thermal resistance parameters include heat transfer temperature difference, heat flux density, and heat transfer area of ​​the heated region; generating the thermal resistance of multiple heated regions based on the thermal resistance parameters and the coal quality parameters includes:

[0181] Based on the coal quality parameters, determine the coal quality correction coefficient;

[0182] The thermal resistance of multiple heated regions is determined based on the heat transfer temperature difference, the heat flux density, the heat exchange area of ​​the heated region, and the coal quality correction coefficient.

[0183] In one embodiment of this application, the step of inputting the spatiotemporal temperature field matrix and the coal quality parameters into a trained long short-term memory network model to generate the coking probability of each heated region includes:

[0184] Based on the trained Long Short-Term Memory (LSTM) network model, the activation function, hidden layer weight matrix, hidden layer state vector of the LSM network at time t-1, input layer weight matrix, and bias term of the LSM network are obtained.

[0185] The coking probability of generating each heated region is determined based on the spatiotemporal temperature field matrix, the coal quality parameters, the activation function, the hidden layer weight matrix, the hidden layer state vector of the long short-term memory network at time t-1, the input layer weight matrix, and the bias term of the long short-term memory network.

[0186] In one embodiment of this application, determining the risk information of each heated area based on the coking probability of each heated area includes:

[0187] The probability of coking in each heated area is compared with the first specified threshold and the second specified threshold, respectively.

[0188] If the probability of coking in the heated area is greater than the first specified threshold, the coking risk of the corresponding heated area is high risk.

[0189] If the probability of coking in the heated area is less than or equal to the first specified threshold and the probability of coking in the heated area is greater than or equal to the second specified threshold, the coking risk of the corresponding heated area is medium risk.

[0190] If the probability of coking in the heated area is less than the second specified threshold, the coking risk of the corresponding heated area is low.

[0191] In one embodiment of this application, the step of generating a soot blowing control strategy based on the furnace wall temperature corresponding to each soot blowing gun, the risk information of each heated area, and the thermal resistance of the multiple heated areas, with steam consumption and coking risk as optimization objectives, includes:

[0192] Based on the furnace wall temperature corresponding to each sootblowing gun and the thermal resistance of the multiple heated areas, the thermal resistance information corresponding to each sootblowing gun is obtained.

[0193] Based on the thermal resistance information of each sootblowing gun, a sootblowing control strategy is generated with steam consumption and coking risk as optimization objectives.

[0194] In one embodiment of this application, the step of generating a soot blowing control strategy based on the thermal resistance information corresponding to each soot blowing gun, with steam consumption and coking risk as optimization objectives, includes:

[0195] Using a multi-objective genetic algorithm, based on the thermal resistance information of each sootblowing gun, and with the joint minimization of steam consumption Esteam and coking risk Trisk as the optimization objective and with configured constraints, a Pareto optimal solution set is generated.

[0196] The soot blowing strategy with the highest overall utility in the Pareto optimal solution set is selected as the soot blowing control strategy through fuzzy decision-making.

[0197] The functions of each module in each device in the embodiments of this application can be found in the corresponding descriptions in the above methods, and will not be repeated here.

[0198] Figure 2 A structural block diagram of an electronic device according to an embodiment of this application is shown. Figure 2 As shown, the electronic device includes a memory 410 and a processor 420, wherein the memory 410 stores instructions executable on the processor 420. When the processor 420 executes these instructions, it implements the soot blowing method described in the above embodiments. The number of memories 410 and processors 420 can be one or more. This electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described and / or claimed herein.

[0199] The electronic device may also include a communication interface 430 for communicating with external devices and exchanging data. The devices are interconnected using different buses and can be mounted on a common motherboard or otherwise as needed. The processor 420 can process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple electronic devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). The bus can be divided into address buses, data buses, control buses, etc. For ease of illustration, Figure 2 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0200] Optionally, in a specific implementation, if the memory 410, processor 420 and communication interface 430 are integrated on a single chip, the memory 410, processor 420 and communication interface 430 can communicate with each other through an internal interface.

[0201] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that the processor can be a processor supporting Advanced Reduced Instruction Set Machines (ARM) architecture.

[0202] This application provides a computer-readable storage medium (such as the memory 410 described above) that stores computer instructions, which, when executed by a processor, implement the method provided in this application.

[0203] Optionally, memory 410 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device, etc. Furthermore, memory 410 may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 410 may optionally include memory remotely located relative to processor 420, and these remote memories can be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0204] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0205] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0206] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more (two or more) executable instructions for implementing a particular logical function or process. Furthermore, the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functionality involved.

[0207] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a processor-included system or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0208] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. All or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware, the program being stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiments.

[0209] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. This storage medium can be a read-only memory, a disk, or an optical disk, etc.

[0210] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in this application, and these should all be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for blowing soot, characterized in that, include: Obtain the spatiotemporal temperature field matrix, coal quality parameters, and thermal resistance parameters of the boiler; Based on the thermal resistance parameters and the coal quality parameters, the thermal resistance of multiple heated regions is generated; The spatiotemporal temperature field matrix and the coal quality parameters are input into a trained long short-term memory network model to generate the coking probability of each heated region. Based on the coking probability of each heated area, the risk information of each heated area is determined; Based on the spatiotemporal temperature field matrix, determine the furnace wall temperature corresponding to each sootblowing gun; Based on the furnace wall temperature corresponding to each soot blowing gun, the risk information of each heated area, and the thermal resistance of the multiple heated areas, a soot blowing control strategy is generated with steam consumption and coking risk as optimization targets. The soot blowing control strategy is used to control each soot blowing gun to blow soot onto the boiler. The acquisition of the spatiotemporal temperature field matrix of the boiler includes: Acquire temperature data at various points in the boiler; The temperature data is processed by wavelet transform to remove noise, and the spatiotemporal temperature field matrix of the boiler is obtained. The thermal resistance parameters include heat transfer temperature difference, heat flux density, and heat transfer area of ​​the heated region; the generation of the thermal resistance of multiple heated regions based on the thermal resistance parameters and the coal quality parameters includes: Based on the coal quality parameters, determine the coal quality correction coefficient; The thermal resistance of multiple heating zones is determined based on the heat transfer temperature difference, the heat flux density, the heat exchange area of ​​the heated zone, and the coal quality correction coefficient. The step of inputting the spatiotemporal temperature field matrix and the coal quality parameters into a trained long short-term memory network model to generate the coking probability of each heated region includes: Based on the trained Long Short-Term Memory (LSTM) network model, the activation function, hidden layer weight matrix, hidden layer state vector of the LSM network at time t-1, input layer weight matrix, and bias term of the LSM network are obtained. Based on the spatiotemporal temperature field matrix, the coal quality parameters, the activation function, the hidden layer weight matrix, the hidden layer state vector of the long short-term memory network at time t-1, the input layer weight matrix, and the bias term of the long short-term memory network, the coking probability of generating each heated region is determined. The determination of risk information for each heated area based on the coking probability of each heated area includes: The probability of coking in each heated area is compared with the first specified threshold and the second specified threshold, respectively. If the probability of coking in the heated area is greater than the first specified threshold, the coking risk of the corresponding heated area is high risk. If the probability of coking in the heated area is less than or equal to the first specified threshold and the probability of coking in the heated area is greater than or equal to the second specified threshold, the coking risk of the corresponding heated area is medium risk. If the probability of coking in the heated area is less than the second specified threshold, the coking risk of the corresponding heated area is low risk. The step of generating a soot blowing control strategy based on the furnace wall temperature corresponding to each soot blowing gun, the risk information of each heated area, and the thermal resistance of the multiple heated areas, with steam consumption and coking risk as optimization objectives, includes: Based on the furnace wall temperature corresponding to each sootblowing gun and the thermal resistance of the multiple heated areas, the thermal resistance information corresponding to each sootblowing gun is obtained. Based on the thermal resistance information of each sootblowing gun, a sootblowing control strategy is generated with steam consumption and coking risk as optimization objectives. The process of generating a soot blowing control strategy based on the thermal resistance information of each soot blowing gun, with steam consumption and coking risk as optimization objectives, includes: A Pareto optimal solution set was generated by using a multi-objective genetic algorithm based on the thermal resistance information of each sootblowing gun, with the optimization objective of jointly minimizing steam consumption and coking risk, and configuring constraints. The soot blowing strategy with the highest overall utility in the Pareto optimal solution set is selected as the soot blowing control strategy through fuzzy decision-making.

2. A soot blowing system, employing the method of claim 1, characterized in that, include: The first acquisition module is used to acquire the spatiotemporal temperature field matrix, coal quality parameters, and thermal resistance parameters of the boiler. The first generation module is used to generate the thermal resistance of multiple heated regions based on the thermal resistance parameters and the coal quality parameters. The second generation module is used to input the spatiotemporal temperature field matrix and the coal quality parameters into the trained long short-term memory network model to generate the coking probability of each heated region. The first determining module is used to determine the risk information of each heated area based on the coking probability of each heated area; The second determining module is used to determine the furnace wall temperature corresponding to each sootblowing gun based on the spatiotemporal temperature field matrix. The third generation module is used to generate a soot blowing control strategy based on the furnace wall temperature corresponding to each soot blowing gun, the risk information of each heated area, and the thermal resistance of the multiple heated areas, with steam consumption and coking risk as optimization targets. The first control module is used to control each soot blowing gun to blow soot onto the boiler according to the soot blowing control strategy.

3. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of claim 1.

4. A computer-readable storage medium storing computer instructions that, when executed by a processor, implement the method of claim 1.

Images