Method for temperature control of a circulating fluidized bed furnace outlet

Abstract

The disclosure provides a temperature control method of a circulating fluidized bed furnace outlet, comprising: preprocessing sensor data to obtain an image of solid waste in a target area, a reflectivity matrix and a distance matrix; using the image, the reflectivity matrix and the distance matrix to obtain the weight of the solid waste in the target area and a low calorific value level; the reflectivity matrix represents the reflectivity of the surface of the solid waste; the distance matrix represents the distance from the solid waste to the sensor; using the weight of the solid waste and the low calorific value level, the heat value of the solid waste is calculated; using a pre-trained outlet temperature prediction model and an optimization algorithm, the operating parameters of the circulating fluidized bed are obtained; the operating parameters at least include one of the fan frequency and the feeding belt speed; the outlet temperature prediction model is configured to be able to output the outlet temperature according to the input operating parameters and the heat value of the solid waste.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent control technology for circulating fluidized bed combustion, and more specifically to a method for temperature control at the outlet of a circulating fluidized bed furnace. Background Technology

[0002] Circulating fluidized bed (CFB) boilers are one of the mainstream technologies for solid waste treatment. The boiler outlet temperature is a crucial parameter for assessing control effectiveness. According to regulations, the outlet temperature of a solid waste incineration boiler should be maintained above 850℃. To ensure the boiler outlet flue gas temperature meets these requirements, it is often controlled between 900℃ and 950℃. When the temperature begins to drop, manual intervention is performed to adjust it back to the ideal state before it falls below 850℃. While this prevents the temperature from falling below 850℃, the inability to predict and estimate specific feed data means the flue gas temperature often exceeds 950℃. Furthermore, when the flue gas temperature is above 900℃, the fly ash from municipal solid waste incineration, due to its low melting point, is more prone to coking and agglomerating in the cyclone separator, causing blockages and impacting production. Therefore, a method is urgently needed to control the boiler outlet flue gas temperature below 900℃ while simultaneously meeting the requirement of a temperature above 850℃—that is, effective temperature window control of the boiler outlet flue gas temperature.

[0003] Currently, most waste incineration power plants rely on manual or simple automatic control logic to adjust the combustion system, with generally limited effectiveness. The reasons for this are twofold: firstly, there is no unified adjustment rule, resulting in low automation; and secondly, there is a lack of feedforward detection methods. Summary of the Invention

[0004] In view of the above problems, this disclosure provides a method for temperature control at the outlet of a circulating fluidized bed furnace that includes feedforward detection.

[0005] This disclosure provides a method for temperature control at the outlet of a circulating fluidized bed furnace, comprising: preprocessing sensor data to obtain an image, reflectivity matrix, and distance matrix of solid waste within a target area; using the image, reflectivity matrix, and distance matrix to obtain the weight and lower heating value level of the solid waste within the target area; the reflectivity matrix characterizes the reflectivity of the solid waste surface; the distance matrix characterizes the distance from the solid waste to the sensor; using the weight and lower heating value level of the solid waste, the calorific value of the solid waste is calculated; using a pre-trained outlet temperature prediction model and optimization algorithm, the operating parameters of the circulating fluidized bed are obtained; the operating parameters include at least one of the fan frequency and the feed belt speed; the outlet temperature prediction model is configured to output the outlet temperature based on the input operating parameters and the calorific value of the solid waste.

[0006] According to embodiments of this disclosure, the weight of solid waste and the lower heating value level within a target area are obtained using an image, a reflectivity matrix, and a distance matrix, including: obtaining a stacking height matrix using the distance matrix and the distance from the sensor to the feed belt; obtaining the average stacking height of the solid waste using the stacking height matrix; calculating the weight of the solid waste using the average stacking height, the area of ​​the feed belt, and the bulk density of the solid waste; recognizing the solid waste image using a pre-trained solid waste image recognition model to obtain the proportion of solid waste of each calorific value level; the solid waste image recognition model is configured to output the area proportion of solid waste of each calorific value level in the solid waste image based on the input solid waste image; and calculating the lower heating value level using the proportion of solid waste of each calorific value level.

[0007] According to embodiments of this disclosure, calculating the lower heating value level using the proportion of solid waste of each calorific value grade includes: calculating the estimated lower heating value level within a target area using the proportion of solid waste of each calorific value grade; calculating the average moisture content within the target area using a reflectance matrix and a linear formula for moisture content with respect to reflectance; and correcting the estimated lower heating value level using the average moisture content to obtain the lower heating value level. The linear formula for moisture content with respect to reflectance is obtained by linearly fitting pre-tested sample moisture content data and sample reflectance data. The formula for correcting the average lower heating value level using the average moisture content is as follows:

[0008]

[0009] In the formula, Q 矫正 It has a low calorific value; Q 预估 To estimate the lower heating value level; This represents the average moisture content.

[0010] According to embodiments of this disclosure, the operating parameters of a circulating fluidized bed are obtained using a pre-trained outlet temperature prediction model and an optimization algorithm. This includes: constructing an outlet temperature prediction model using a long short-term memory network algorithm based on environmental conditions, operating parameters, and lower heating value levels; configuring the outlet temperature prediction model with environmental conditions, operating parameters, and lower heating value levels as inputs and outlet temperature as output; environmental conditions including at least one of temperature and pressure; obtaining preliminary operating parameters of the circulating fluidized bed using the outlet temperature prediction model and boundary conditions through an optimization algorithm; boundary conditions including the range of operating parameters and the range of outlet temperature; and adjusting the preliminary operating parameters based on the outlet temperature change trend after a preset operating time to obtain the final operating parameters of the circulating fluidized bed.

[0011] According to embodiments of this disclosure, the operating parameters of a circulating fluidized bed are obtained using a pre-trained outlet temperature prediction model and an optimization algorithm. This includes: constructing multiple outlet temperature prediction models using a long short-term memory network algorithm based on environmental conditions, operating parameters, and lower heating value levels; configuring the multiple outlet temperature prediction models so that the inputs are environmental conditions, operating parameters, and lower heating value levels, and the outputs are the outlet temperatures after different operating times; obtaining preliminary operating parameters of the circulating fluidized bed using the multiple outlet temperature prediction models and boundary conditions through an optimization algorithm; the boundary conditions include the range of operating parameters and the range of outlet temperatures after different operating times; and adjusting the preliminary operating parameters according to the outlet temperature change trend after a preset operating time to obtain the final operating parameters of the circulating fluidized bed.

[0012] According to embodiments of this disclosure, adjusting the preliminary operating parameters based on the outlet temperature change trend after running the preliminary operating parameters for a preset time includes: determining whether the outlet temperature continues to decrease or increase; if so, adjusting at least one of the fan frequency and the feed belt speed within a preset range to obtain the final operating parameters; the preset range is the boundary range of the operating parameters; if not, not adjusting the preliminary operating parameters to obtain the final operating parameters; wherein, the fan frequency includes at least one of the tertiary fan frequency, the secondary fan frequency, and the return fan frequency.

[0013] According to embodiments of this disclosure, adjusting at least one of the fan frequency and the feed belt speed within a preset range includes: determining whether the outlet temperature is continuously decreasing or continuously increasing; if the outlet temperature is continuously decreasing, performing a cooling parameter adjustment step; determining whether the outlet temperature has stopped decreasing; if yes, completing the operating parameter adjustment; if no, repeating the cooling parameter adjustment step; the cooling parameter adjustment step includes at least one of reducing the tertiary fan frequency by a preset percentage, reducing the secondary fan frequency by a preset percentage, increasing the feed belt speed by a preset percentage, and increasing the return fan frequency by a preset percentage; if the outlet temperature is continuously increasing, performing a heating parameter adjustment step; determining whether the outlet temperature has stopped increasing; if yes, completing the operating parameter adjustment; if no, repeating the heating parameter adjustment step; the heating parameter adjustment step includes at least one of increasing the tertiary fan frequency by a preset percentage, increasing the secondary fan frequency by a preset percentage, decreasing the feed belt speed by a preset percentage, and decreasing the return fan frequency by a preset percentage.

[0014] According to embodiments of this disclosure, a cooling parameter adjustment step is performed; it is determined whether the outlet temperature has stopped decreasing; if yes, the operating parameter adjustment is completed; if no, the cooling parameter adjustment step is repeated, including: reducing the frequency of the tertiary fan by a preset percentage; determining whether the outlet temperature has stopped decreasing; if no, reducing the frequency of the secondary fan by a preset percentage; if yes, the operating parameter adjustment is completed; determining whether the outlet temperature has stopped decreasing; if no, reducing the feed belt speed by a preset percentage; if yes, the operating parameter adjustment is completed; determining whether the outlet temperature has stopped decreasing; if no, increasing the feed belt speed by a preset percentage; if yes, the operating parameter adjustment is completed; determining whether the outlet temperature has stopped decreasing; if no, increasing the return fan frequency by a preset percentage; if yes, the operating parameter adjustment is completed; determining whether the outlet temperature has stopped decreasing; if no, the step of reducing the frequency of the tertiary fan by a preset percentage is repeated.

[0015] According to embodiments of this disclosure, the following steps are performed: First, determine if the outlet temperature has stopped rising. If yes, the operating parameter adjustment is completed. If no, the temperature rise and parameter adjustment steps are repeated, including: increasing the frequency of the tertiary fan by a preset percentage; second, determining if the outlet temperature has stopped rising; if no, increasing the frequency of the secondary fan by a preset percentage; if yes, the operating parameter adjustment is completed; third, determining if the outlet temperature has stopped rising; if no, increasing the feed belt speed by a preset percentage; if yes, the operating parameter adjustment is completed; fourth, determining if the outlet temperature has stopped rising; if no, decreasing the feed belt speed by a preset percentage; if yes, the operating parameter adjustment is completed; fifth, determining if the outlet temperature has stopped rising; if no, decreasing the return fan frequency by a preset percentage; if yes, the operating parameter adjustment is completed; sixth, determining if the outlet temperature has stopped rising; if no, repeating the step of increasing the frequency of the tertiary fan by a preset percentage.

[0016] The second aspect of this disclosure provides a temperature control device for the outlet of a circulating fluidized bed furnace, configured to implement the aforementioned temperature control method for the outlet of a circulating fluidized bed furnace, comprising: a preprocessing module for preprocessing sensor data to obtain an image, reflectivity matrix, and distance matrix of solid waste within a target area; a calorific value calculation module for using the image, reflectivity matrix, and distance matrix to obtain the weight and lower heating value level of the solid waste within the target area; the reflectivity matrix characterizes the reflectivity of the solid waste surface; the distance matrix characterizes the distance from the solid waste to the sensor; and the calorific value of the solid waste is calculated using the weight and lower heating value level of the solid waste; and a parameter adjustment module for using a pre-trained outlet temperature prediction model and optimization algorithm to obtain the operating parameters of the circulating fluidized bed; the operating parameters include at least one of the fan frequency and the feed belt speed; and the outlet temperature prediction model is configured to output the outlet temperature based on the input operating parameters and the calorific value of the solid waste.

[0017] A third aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors perform the temperature control method described above for the outlet of a circulating fluidized bed furnace.

[0018] A fourth aspect of this disclosure also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the temperature control method for the outlet of the circulating fluidized bed furnace described above.

[0019] According to the temperature control method for the outlet of a circulating fluidized bed furnace provided in this disclosure, real-time feedforward measurement of the feed calorific value is achieved by acquiring images, reflectivity, and stacking height of the material on the feed belt; the operating parameters of the circulating fluidized bed are output through modeling prediction and optimization algorithms. By adding parameter measurement at the feed end, the accuracy and timeliness of temperature window control are increased; and by constructing an outlet temperature prediction model, advance adjustment of operating parameters is achieved. Therefore, this method at least partially solves the technical problems of untimely and inaccurate manual adjustment, realizing automated real-time adjustment of operating parameters, thereby achieving the technical effect of precisely controlling the furnace outlet temperature. Attached Figure Description

[0020] Figure 1 A flowchart illustrating a method for temperature control at the outlet of a circulating fluidized bed furnace according to an embodiment of the present disclosure is shown schematically.

[0021] Figure 2 A circulating fluidized bed according to an embodiment of the present disclosure is illustrated schematically;

[0022] Figure 3 This schematic diagram illustrates a structural block diagram of a temperature control device at the outlet of a circulating fluidized bed furnace according to an embodiment of the present disclosure;

[0023] Figure 4 A block diagram schematically illustrates an electronic device suitable for implementing a temperature control method at the outlet of a circulating fluidized bed furnace according to an embodiment of the present disclosure. Detailed Implementation

[0024] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0025] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0026] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0027] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0028] Compared to grate boilers, circulating fluidized bed boilers have a smaller time delay, and changes in fuel are quickly reflected in the combustion state. Currently, waste-to-energy plants generally face under-fueling issues, resulting in the mixing of fuels with different characteristics, such as municipal solid waste, industrial waste, and sludge. At present, material mixing in the silos relies solely on grab buckets for simple mixing, and even after crushing, uniform fuel distribution throughout the feeding process cannot be achieved. Therefore, fuel variations on the feed belt are significant, which in turn greatly affects the boiler outlet temperature.

[0029] Combustion requires temperatures above 850℃, and when the gas temperature exceeds 900℃, the fly ash from municipal solid waste incineration, due to its lower melting point, is more prone to coking and agglomerating in the cyclone separator, causing blockages and impacting normal production. Temporary shutdown and manual cleaning are typically required every 15 days, and in more severe cases, boiler shutdown is necessary. Based on operational experience, controlling the boiler outlet flue gas temperature below 900℃ can significantly reduce fly ash coking and agglomeration, effectively alleviating cyclone separator blockages. Within a normal shutdown and maintenance cycle, this problem will not affect production. Therefore, there is an urgent need for a circulating fluidized bed furnace outlet temperature control method to adjust operating parameters or fuel supply in real time during combustion to maintain a stable furnace outlet temperature within the [850℃, 900℃] temperature window.

[0030] First, the technical terms used in this disclosure are explained as follows:

[0031] Circulating fluidized bed: such as Figure 2As shown, the feed belt 1 is connected to the circulating fluidized bed via the discharge chute 6, and its speed is adjustable. It has no cover directly above it, allowing for direct monitoring of the material on the belt. Its width and length are determined based on site conditions. During boiler operation, material enters the discharge chute 6 via the feed belt 1 and then enters the circulating fluidized bed furnace 7 for combustion. Controlling the speed of the feed belt 1 directly controls the feeding speed. The discharge chute 6, connecting the belt and the circulating fluidized bed, is located in the dilute phase zone of the circulating fluidized bed, below the secondary air duct 4. Material enters from the feed belt 1 into the discharge chute 6, and then into the circulating fluidized bed furnace 7; primary air duct 8 connects the primary air fan 12 to the bottom of the circulating fluidized bed furnace 7; primary air fan 12 supplies primary air to the circulating fluidized bed; secondary air duct 4 connects the secondary air fan 11 to the circulating fluidized bed furnace 7, located near the boundary between the dilute phase zone and the dense phase zone of the circulating fluidized bed furnace, above the discharge chute 6; secondary air fan 11 supplies secondary air to the circulating fluidized bed; tertiary air duct 5 connects the tertiary air fan 10 to the circulating fluidized bed furnace. The furnace 7 is located above the secondary air duct 4; the tertiary air fan 10 supplies tertiary air to the circulating fluidized bed; the bottom of the circulating fluidized bed furnace 7 is connected to the primary air duct, the dense phase zone is connected to the feed chute 6 and the return pipe 17, and the boundary between the dense phase zone and the dilute phase zone is connected to the secondary air duct 4. A tertiary air duct 5 is arranged above the secondary air duct 4. A thermocouple 9 is installed at the outlet of the furnace 7, and the outlet is connected to the cyclone separator 13; the furnace 7 outlet thermocouple 9 is installed at the outlet of the circulating fluidized bed furnace 7 to detect the temperature T of the flue gas at the outlet of the furnace 7. outCyclone separator 13, with its inlet connected to the outlet of the circulating fluidized bed furnace 7 and its bottom connected to riser 14, is used to separate large particles of ash from the high-temperature flue gas. Riser 14 is connected to the bottom of cyclone separator 13, and the separated ash enters riser 14. Return feeder 16 is connected to riser 14 and return pipe 17, and is equipped with return fan 15. Return fan 15 is connected to feeder, and controlling return fan 15 can control the amount of returned ash, thereby controlling the circulation ratio. Return pipe 17 connects feeder and dilute phase zone of circulating fluidized bed furnace 7. Returned ash enters return feeder 16 through riser 14, passes through return pipe 17, and returns to the furnace 7 of circulating fluidized bed. Mounting bracket 2, spanning the feed belt 1, is used to mount image-coupled lidar sensor 3, and its installation position should be as close as possible to the discharge chute 6. Image-coupled lidar sensor 3 consists of image monitoring and lidar, and can... Simultaneously acquiring images, reflectivity, and stacking height of the material on the conveyor belt directly below it, the measurement information is directly transmitted to the industrial control computer 19 via data cable 20; the DCS system 18, i.e., the distributed control system, integrates computer, communication, display, and control technologies (4C), and can display, record, and control the parameters of various sensors and motors in real time; the industrial control computer 19 is used to install the temperature window control program at the outlet of the furnace 7 when the circulating fluidized bed is used to treat complex component solid waste, and to communicate with the DCS system 18 in real time. At the same time, it also acquires the raw detection information of the image-coupled lidar sensor 3 in real time, and outputs the final adjustment frequency of the primary fan, secondary fan, tertiary fan, return fan, and feeding belt through modeling and calculation, so as to realize the temperature window control of the circulating fluidized bed furnace outlet temperature [850℃, 900℃]; the data cable 20 connects the image-coupled lidar sensor 3 and the industrial control computer 19.

[0032] It should be noted that the circulating fluidized bed provided in this disclosure is equipped with an image-coupled lidar sensor 3, a mounting bracket 2 for mounting the sensor, and a DCS system 18, which are used to realize feedforward detection and real-time parameter adjustment, thereby improving temperature control accuracy and control efficiency.

[0033] Figure 1 A flowchart illustrating a method for temperature control at the outlet of a circulating fluidized bed furnace according to an embodiment of the present disclosure is shown, such as... Figure 1As shown, embodiments of this disclosure provide a method for temperature control at the outlet of a circulating fluidized bed furnace, comprising: preprocessing sensor data to obtain an image, reflectivity matrix, and distance matrix of solid waste within a target area; using the image, reflectivity matrix, and distance matrix to obtain the weight and lower heating value level of the solid waste within the target area; the reflectivity matrix characterizes the reflectivity of the solid waste surface; the distance matrix characterizes the distance from the solid waste to the sensor; calculating the calorific value of the solid waste using the weight and lower heating value level of the solid waste; and obtaining the operating parameters of the circulating fluidized bed using a pre-trained outlet temperature prediction model and optimization algorithm; the operating parameters include at least one of the fan frequency and the feed belt speed; the outlet temperature prediction model is configured to output the outlet temperature based on the input operating parameters and the calorific value of the solid waste.

[0034] In this embodiment, the image-coupled lidar sensor acquires data such as the image of the material on the conveyor belt (size i×j, specifically determined by the sensor itself, the image is a color image in RGB color mode), reflectivity r (here, the reflectivity r is an m×n matrix, specifically determined by the sensor itself), and distance l from the sensor to the material surface (here, the distance l is an f×k matrix, specifically determined by the sensor itself), and transmits the data to the industrial control computer in real time. After receiving the data, the industrial control computer performs data preprocessing. Upon receiving the image information, it removes the portion outside the conveyor belt, leaving the effective area image with a size of i'×j'. Upon receiving the reflectivity matrix information, it leaves the reflectivity matrix R within the effective area, with a size of m'×n'. Upon receiving the distance matrix information from the sensor to the material surface, it leaves the distance matrix L within the effective area, with a size of f'×k'. The data is transmitted to the industrial control computer in real time via a data cable. After receiving the data, the industrial control computer calculates the estimated calorific value Q of the solid waste entering the furnace. sum .

[0035] In this embodiment, the formula for calculating the approximate calorific value of the solid waste within the effective area using the weight of the solid waste and the lower heating value level is as follows:

[0036] Q sum =Q 矫正 ×M

[0037] In the formula, Q sum Q represents the calorific value of solid waste. 矫正 M represents the lower heating value level, and M represents the weight of solid waste.

[0038] Through the embodiments of this disclosure, precise image, reflectivity, and distance information are obtained through sensor data preprocessing, enabling a more comprehensive understanding of the solid waste's state and a comprehensive estimation of the calorific value entering the furnace, providing a reliable foundation for subsequent calculations and demonstrating greater accuracy than conventional methods. A model for calculating the calorific value of the solid waste entering the furnace is constructed. An LSTM algorithm is used to establish a furnace outlet temperature prediction model for different future times. A particle swarm optimization algorithm is used to obtain optimization models for the primary, secondary, tertiary, return, and feeding speeds, and these models are used for coarse adjustments. A unified adjustment rule is formed through program-defined strategies and modular control logic, improving the automatic control rate. This solves the problems of insufficient feedforward measurement data, lack of unified adjustment rules, and low automation in existing temperature window control technologies. It achieves real-time feedforward measurement of the feed calorific value, a unified control strategy, high automation, and a stable furnace outlet temperature within the [850℃, 900℃] temperature window range, improving the boiler's economy and safety.

[0039] Based on the above embodiments, the weight of solid waste and the lower heating value level within the target area are obtained using images, reflectivity matrices, and distance matrices. This includes: obtaining a stacking height matrix using the distance matrix and the distance from the sensor to the feed belt; obtaining the average stacking height of the solid waste using the stacking height matrix; calculating the weight of the solid waste using the average stacking height, the area of ​​the feed belt, and the stacking density of the solid waste; recognizing the solid waste image using a pre-trained solid waste image recognition model to obtain the proportion of solid waste of each calorific value level; the solid waste image recognition model is configured to output the area proportion of solid waste of each calorific value level in the solid waste image based on the input solid waste image; and calculating the lower heating value level using the proportion of solid waste of each calorific value level.

[0040] In this embodiment, after obtaining the distance matrix, the fuel stacking height matrix H within the effective area is calculated. Since the angle of the image-coupled lidar sensor is small, the angle factor can be ignored. Each element of the distance matrix is ​​subtracted from the distance H from the image-coupled lidar sensor to the feed belt to form a new stacking height matrix H with size f'×k'.

[0041]

[0042] Calculate the average stacking height within the effective area based on the stacking height matrix H:

[0043]

[0044] Using the average stacking height, the area of ​​the feed belt, and the bulk density of the solid waste, calculate the approximate weight within the effective area:

[0045]

[0046] Where a and b represent the actual length and width of the feed conveyor belt in the image, respectively; ρ represents the bulk density of the solid waste, taken as 300 kg / m³. 3 ;

[0047] In the embodiments of this disclosure, the average stacking height, the area of ​​the feed belt, and the reflectivity are all data of the feed belt surface. The heat of the furnace is finally estimated based on this. The reason is that the fuel in the circulating fluidized bed needs to be crushed to below 50mm and mixed. Therefore, the characteristics of this part of the fuel can be characterized by surface data. Thus, the weight of solid waste can be quickly calculated by using the stacking height and area density, thereby improving the calculation efficiency. The type and proportion of solid waste are identified by the image recognition model. Combined with the calorific value data, the lower heating value level of the solid waste is accurately estimated.

[0048] Based on the above embodiments, the lower heating value level is calculated using the proportion of solid waste of each calorific value grade, including: calculating the estimated lower heating value level in the target area using the proportion of solid waste of each calorific value grade; calculating the average moisture content in the target area using the reflectance matrix and the linear formula of moisture content with respect to reflectance; and correcting the estimated lower heating value level using the average moisture content to obtain the lower heating value level. The linear formula of moisture content with respect to reflectance is obtained by linearly fitting pre-tested sample moisture content data and sample reflectance data. The formula for correcting the average lower heating value level using the average moisture content is as follows:

[0049]

[0050] In the formula, Q 矫正 It has a low calorific value; Q 预估 To estimate the lower heating value level; This represents the average moisture content.

[0051] In this embodiment, based on the YOLO algorithm, solid waste image recognition models for each calorific value level (1000 Kcal / kg, 1500 Kcal / kg, 2000 Kcal / kg, ... 7000 Kcal / kg) are established. Based on these models, solid waste images are recognized to determine the area proportion (η) of solid waste at each calorific value level. 1000Kcal / kg η 1500Kcal / kg η 2000Kcal / kg ......η 7000Kcal / kg This is used to characterize its specific gravity and calculate the approximate lower heating value level within the effective region: Q 预估 =η 1000Kcal / kg ×1000Kcal / kg+η 1500Kcal / kg ×1500Kcal / kg+η 2000Kcal / kg ×2000Kcal / kg+......+η 7000Kcal / kg×7000Kcal / kg

[0052] In this embodiment, data on the variation of reflectance of materials at different moisture contents were collected in the laboratory. A linear fitting method was used to obtain a linear formula wt = f(r) for moisture content with respect to reflectance. Using this linear formula, the average moisture content within the effective area was calculated.

[0053]

[0054] In the formula, R[i,j] represents the data in the i-th row and j-th column of the reflectivity matrix. The corresponding moisture content is obtained according to the linear formula, and the average moisture content is obtained by taking the mean value.

[0055] Since some energy is used to evaporate moisture during combustion, the higher the moisture content of solid waste, the lower its lower heating value (i.e., the energy available during combustion). Therefore, the lower heating value level of solid waste in the effective area can be corrected by adjusting the moisture content.

[0056] The embodiments of this disclosure utilize the linear relationship between reflectivity and moisture content for correction, thereby improving the accuracy of calorific value estimation.

[0057] Based on the above embodiments, the operating parameters of the circulating fluidized bed are obtained using a pre-trained outlet temperature prediction model and optimization algorithm. This includes: constructing an outlet temperature prediction model using a long short-term memory network algorithm based on environmental conditions, operating parameters, and lower heating value level; configuring the outlet temperature prediction model with environmental conditions, operating parameters, and lower heating value level as inputs and outlet temperature as output; environmental conditions include at least one of temperature and pressure; obtaining preliminary operating parameters of the circulating fluidized bed using the outlet temperature prediction model and boundary conditions through an optimization algorithm; boundary conditions include the range of operating parameters and the range of outlet temperature; and adjusting the preliminary operating parameters according to the outlet temperature change trend after a preset operating time to obtain the final operating parameters of the circulating fluidized bed.

[0058] Through the embodiments of this disclosure, the Long Short-Term Memory (LSTM) network algorithm can be used to capture long-term dependencies in time series data, thereby improving the prediction accuracy of outlet temperature. The optimization algorithm finds the optimal operating parameters under given boundary conditions, thereby achieving optimal control of outlet temperature. The automated optimization process reduces manual intervention and improves the operating efficiency and stability of the system.

[0059] Based on the above embodiments, the operating parameters of the circulating fluidized bed are obtained using a pre-trained outlet temperature prediction model and optimization algorithm. This includes: constructing multiple outlet temperature prediction models using a long short-term memory network algorithm based on environmental conditions, operating parameters, and lower heating value levels; configuring the multiple outlet temperature prediction models so that the inputs are environmental conditions, operating parameters, and lower heating value levels, and the outputs are the outlet temperatures after different running times; using the multiple outlet temperature prediction models and boundary conditions, the preliminary operating parameters of the circulating fluidized bed are obtained through an optimization algorithm; the boundary conditions include the range of operating parameters and the range of outlet temperatures after different running times; adjusting the preliminary operating parameters according to the outlet temperature change trend after running for a preset time based on the preliminary operating parameters to obtain the final operating parameters of the circulating fluidized bed.

[0060] In this embodiment, the operating data of the circulating fluidized bed (including motor frequency, temperature, pressure, and approximate calorific value Q of the feed involved in the process) is used. sum Using the LSTM algorithm, prediction models for the furnace outlet temperature of a circulating fluidized bed boiler were constructed after 1 minute, 2 minutes, 3 minutes, 4 minutes, and 5 minutes, respectively.

[0061] T out,time =MOD LSTM (x1,x2......Q sum )

[0062] The primary fan frequency, secondary fan frequency, tertiary fan frequency, return fan frequency, and feed belt speed are used as control variables, and these variables are limited to 0-50Hz as boundary condition 1. The furnace outlet temperature of the circulating fluidized bed boiler is limited to 850-900℃ after 1 minute, 2 minutes, 3 minutes, 4 minutes, and 5 minutes as boundary condition 2. The primary fan frequency, secondary fan frequency, tertiary fan frequency, return fan frequency, and feed belt speed that meet the above boundary conditions at each time point are obtained using a particle swarm optimization algorithm. These results are used as the basis for coarse adjustment, and the data is transmitted to the DCS system. The DCS system is then used to adjust the relevant equipment, with a coarse adjustment frequency of once every 3 minutes.

[0063] Through the embodiments of this disclosure, a predictive model for the furnace outlet temperature of a circulating fluidized bed boiler at different future times is constructed using the LSTM algorithm, which has the ability to remember long and short-term information. This increases the reliability of the results, reduces the workload of fine-tuning, and improves the adjustment efficiency.

[0064] Based on the above embodiments, the preliminary operating parameters are adjusted according to the trend of outlet temperature change after the preliminary operating parameters have been running for a preset time. This includes: determining whether the outlet temperature continues to decrease or increase; if so, adjusting at least one of the fan frequency and the feed belt speed within a preset range to obtain the final operating parameters; the preset range is the boundary range of the operating parameters; if not, the preliminary operating parameters are not adjusted to obtain the final operating parameters; wherein, the fan frequency includes at least one of the tertiary fan frequency, the secondary fan frequency, and the return fan frequency.

[0065] In this embodiment, the industrial control computer acquires the operating data of the DCS system in real time, and transmits the adjustment values ​​of the primary fan, secondary fan, tertiary fan, return fan and feed belt to the DCS system according to the rules to complete the fine adjustment.

[0066] Through embodiments of this disclosure, based on the temperature T of the flue gas at the furnace outlet... out The temperature T of the flue gas at the furnace outlet is fine-tuned according to the changing trend (equipment control is completed by the DCS system, and the adjustment data is calculated by the industrial control computer; the two data are interconnected). out If the temperature remains relatively stable, no fine-tuning is required. The results obtained from the model are used only as the basis for coarse-tuning, and fine-tuning is performed according to the rules. This increases the applicability and robustness of the control method and enables precise temperature control.

[0067] Based on the above embodiments, adjusting at least one of the fan frequency and the feed belt speed within a preset range includes: determining whether the outlet temperature is continuously decreasing or continuously increasing; if the outlet temperature is continuously decreasing, performing a cooling parameter adjustment step; determining whether the outlet temperature has stopped decreasing; if yes, completing the operating parameter adjustment; if no, repeating the cooling parameter adjustment step; the cooling parameter adjustment step includes at least one of reducing the tertiary fan frequency by a preset percentage, reducing the secondary fan frequency by a preset percentage, increasing the feed belt speed by a preset percentage, and increasing the return fan frequency by a preset percentage; if the outlet temperature is continuously increasing, performing a heating parameter adjustment step; determining whether the outlet temperature has stopped increasing; if yes, completing the operating parameter adjustment; if no, repeating the heating parameter adjustment step; the heating parameter adjustment step includes at least one of increasing the tertiary fan frequency by a preset percentage, increasing the secondary fan frequency by a preset percentage, decreasing the feed belt speed by a preset percentage, and decreasing the return fan frequency by a preset percentage.

[0068] Through the embodiments of this disclosure, dynamic adjustments are made based on the actual changing trend of the outlet temperature to ensure that the system can respond quickly and stabilize the temperature; after coarse adjustment, fine adjustment is performed according to the established unified control strategy, realizing real-time feedforward measurement of the feed calorific value, unified control strategy, and high degree of control automation.

[0069] Based on the above embodiments, a cooling parameter adjustment step is performed; it is determined whether the outlet temperature has stopped decreasing; if yes, the operating parameter adjustment is completed; if no, the cooling parameter adjustment step is repeated, including: reducing the frequency of the tertiary fan by a preset percentage; determining whether the outlet temperature has stopped decreasing; if no, reducing the frequency of the secondary fan by a preset percentage; if yes, the operating parameter adjustment is completed; determining whether the outlet temperature has stopped decreasing; if no, reducing the feed belt speed by a preset percentage; if yes, the operating parameter adjustment is completed; determining whether the outlet temperature has stopped decreasing; if no, increasing the feed belt speed by a preset percentage; if yes, the operating parameter adjustment is completed; determining whether the outlet temperature has stopped decreasing; if no, increasing the return fan frequency by a preset percentage; if yes, the operating parameter adjustment is completed; determining whether the outlet temperature has stopped decreasing; if no, the step of reducing the frequency of the tertiary fan by a preset percentage is repeated.

[0070] In this embodiment, if the temperature T of the flue gas at the furnace outlet out Continuous reduction: Reduce the frequency of the tertiary air blower (V3) by 5%, reduce the frequency of the secondary air blower (V2) by 5%, and increase the feed belt speed (V) by 5%. 给料 Increase the frequency of the return material fan by 5% V 返料 The above four steps are performed in sequence, with a 20-second wait after each step, and a determination of T is made. out Has the temperature stopped decreasing, such as the temperature T of the flue gas at the furnace outlet? out If the descent has stopped, then stop adjusting. If, during the above adjustments, a parameter reaches its limit of 0Hz or 50Hz, skip this step and proceed to the next step.

[0071] Through the embodiments of this disclosure, precise temperature adjustment is achieved by gradually reducing the frequency of different fans and the feeding speed, reducing the possibility of over-adjustment. Multiple possible adjustment schemes are considered to ensure effective temperature regulation under different conditions. First, the tertiary and secondary fans are adjusted to ensure the stability of the temperature and position of the calcination zone within the kiln. Then, the feeding belt speed is adjusted to match material supply with production needs, ensuring the stability and efficiency of the production process. Finally, the return fan frequency is adjusted to optimize the return system, improve resource utilization and product quality, while simultaneously reducing energy consumption and optimizing auxiliary systems.

[0072] Based on the above embodiments, the following steps are performed: determining whether the outlet temperature has stopped rising; if yes, the operating parameter adjustment is completed; if no, the heating and parameter adjustment steps are repeated, including: increasing the frequency of the tertiary fan by a preset percentage; determining whether the outlet temperature has stopped rising; if no, increasing the frequency of the secondary fan by a preset percentage; if yes, the operating parameter adjustment is completed; determining whether the outlet temperature has stopped rising; if no, increasing the feed belt speed by a preset percentage; if yes, the operating parameter adjustment is completed; determining whether the outlet temperature has stopped rising; if no, decreasing the feed belt speed by a preset percentage; if yes, the operating parameter adjustment is completed; determining whether the outlet temperature has stopped rising; if no, decreasing the return fan frequency by a preset percentage; if yes, the operating parameter adjustment is completed; determining whether the outlet temperature has stopped rising; if no, the step of increasing the frequency of the tertiary fan by a preset percentage is repeated.

[0073] In this embodiment, when the temperature T of the flue gas at the furnace outlet out Continuous increase: Increase the frequency of the tertiary air blower (V3) by 5%, increase the frequency of the secondary air blower (V2) by 5%, and decrease the feed belt speed (V) by 5%. 给料 Reduce the frequency of the return material fan by 5% V 返料 The above four steps are performed in sequence, with a 20-second wait after each step, and a determination of T is made. out Has the temperature stopped rising, such as the temperature T of the flue gas at the furnace outlet? out If the increase has stopped, then stop adjusting. If, during the above adjustments, a parameter reaches its limit of 0Hz or 50Hz, skip this step and proceed to the next step.

[0074] Through the embodiments of this disclosure, similar to temperature adjustment, precise temperature control is achieved by gradually increasing the fan frequency and feeding speed.

[0075] Based on the above-described temperature control method for the outlet of a circulating fluidized bed furnace, this disclosure also provides a temperature control device for the outlet of a circulating fluidized bed furnace, configured to implement the above-described temperature control method for the outlet of a circulating fluidized bed furnace. The following will be combined with... Figure 3 The device is described in detail.

[0076] like Figure 3 As shown, the temperature control device 300 at the outlet of the circulating fluidized bed furnace in this embodiment includes a pretreatment module 301, a calorific value calculation module 302, and a parameter adjustment module 303.

[0077] The preprocessing module is used to preprocess the sensor data to obtain the image, reflectance matrix, and distance matrix of the solid waste within the target area. In one embodiment, the preprocessing module can be used to perform the operation S1 described above, which will not be repeated here.

[0078] The calorific value calculation module is used to obtain the solid waste weight and lower heating value level within the target area using an image, a reflectance matrix, and a distance matrix. The reflectance matrix represents the reflectance of the solid waste surface; the distance matrix represents the distance from the solid waste to the sensor; and the calorific value of the solid waste is calculated using the solid waste weight and lower heating value level. In one embodiment, the calorific value calculation module can be used to perform the operation S2 described above, which will not be repeated here.

[0079] The parameter adjustment module is used to obtain the operating parameters of the circulating fluidized bed using a pre-trained outlet temperature prediction model and optimization algorithm. The operating parameters include at least one of the following: fan frequency and feed belt speed. The outlet temperature prediction model is configured to output the outlet temperature based on the input operating parameters and the calorific value of the solid waste. In one embodiment, the parameter adjustment module can be used to perform the operation S3 described above, which will not be repeated here.

[0080] Figure 4 A block diagram schematically illustrates an electronic device suitable for implementing a temperature control method at the outlet of a circulating fluidized bed furnace according to an embodiment of the present disclosure.

[0081] like Figure 4 As shown, an electronic device 400 according to an embodiment of the present disclosure includes a processor 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage portion 408 into a random access memory (RAM) 403. The processor 401 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 401 may also include onboard memory for caching purposes. The processor 401 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0082] RAM 403 stores various programs and data required for the operation of electronic device 400. Processor 401, ROM 402, and RAM 403 are interconnected via bus 404. Processor 401 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 402 and / or RAM 403. It should be noted that the programs may also be stored in one or more memories other than ROM 402 and RAM 403. Processor 401 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0083] According to embodiments of this disclosure, the electronic device 400 may further include an input / output (I / O) interface 405, which is also connected to a bus 404. The electronic device 400 may also include one or more of the following components connected to the I / O interface 405: an input section 406 including a keyboard, mouse, etc.; an output section 407 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 410 as needed so that computer programs read from it can be installed into the storage section 408 as needed.

[0084] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0085] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the methods provided in the embodiments of this disclosure.

[0086] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0087] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0088] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0089] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A method of temperature control of a circulating fluidized bed furnace outlet, characterized in that, The method comprises: preprocessing sensor data to obtain an image, a reflectivity matrix and a distance matrix of solid waste in a target area; using the image, the reflectivity matrix and the distance matrix to obtain a weight and a low calorific value level of the solid waste in the target area; the reflectivity matrix represents reflectivity of a surface of the solid waste; the distance matrix represents a distance from the solid waste to the sensor; using the weight and the low calorific value level, a calorific value of the solid waste is calculated; using a pre-trained outlet temperature prediction model and an optimization algorithm, operation parameters of a circulating fluidized bed are obtained; the operation parameters at least include one of a fan frequency and a feeding belt speed; the outlet temperature prediction model is configured to output an outlet temperature according to input operation parameters and the calorific value of the solid waste; wherein, using the pre-trained outlet temperature prediction model and the optimization algorithm, the operation parameters of the circulating fluidized bed are obtained, comprising: using environmental conditions, the operation parameters and the low calorific value level, a plurality of outlet temperature prediction models are constructed by a long short-term memory network algorithm; the plurality of outlet temperature prediction models are configured to input environmental conditions, operation parameters and low calorific value levels, and output outlet temperatures after different operation durations; using the plurality of outlet temperature prediction models and boundary conditions, preliminary operation parameters of the circulating fluidized bed are obtained by an optimization algorithm; the boundary conditions include a range of operation parameters and a range of outlet temperatures after different operation durations; according to a change trend of the outlet temperature after a preset time of operation of the preliminary operation parameters, the preliminary operation parameters are adjusted to obtain final operation parameters of the circulating fluidized bed; wherein, according to the change trend of the outlet temperature after a preset time of operation of the preliminary operation parameters, the preliminary operation parameters are adjusted, comprising: judging whether the outlet temperature is continuously decreasing or continuously increasing; if yes, at least one of the fan frequency and the feeding belt speed is adjusted within a preset range to obtain the final operation parameters; the preset range is a boundary range of the operation parameters; if not, the preliminary operation parameters are not adjusted to obtain the final operation parameters; wherein, the fan frequency at least includes one of a tertiary fan frequency, a secondary fan frequency and a return material fan frequency; wherein, at least one of the fan frequency and the feeding belt speed is adjusted within a preset range, comprising: judging whether the outlet temperature is continuously decreasing or continuously increasing; If the outlet temperature is continuously decreasing, a temperature-lowering parameter adjustment step is performed; it is determined whether the outlet temperature stops decreasing; if yes, the operation parameter adjustment is completed; if no, the temperature-lowering parameter adjustment step is repeatedly performed; the temperature-lowering parameter adjustment step at least includes one of decreasing a tertiary air fan frequency by a preset percentage, decreasing a secondary air fan frequency by a preset percentage, increasing a feeding belt speed by a preset percentage, and increasing a return material fan frequency by a preset percentage; if the outlet temperature is continuously increasing, a temperature-raising parameter adjustment step is performed; it is determined whether the outlet temperature stops increasing; if yes, the operation parameter adjustment is completed; if no, the temperature-raising parameter adjustment step is repeatedly performed; the temperature-raising parameter adjustment step at least includes one of increasing a tertiary air fan frequency by a preset percentage, increasing a secondary air fan frequency by a preset percentage, decreasing a feeding belt speed by a preset percentage, and decreasing a return material fan frequency by a preset percentage; If the outlet temperature is continuously decreasing, a temperature-lowering parameter adjustment step is performed; it is determined whether the outlet temperature stops decreasing; if yes, the operation parameter adjustment is completed; if no, the temperature-lowering parameter adjustment step is repeatedly performed; the temperature-lowering parameter adjustment step at least includes one of decreasing a tertiary air fan frequency by a preset percentage, decreasing a secondary air fan frequency by a preset percentage, increasing a feeding belt speed by a preset percentage, and increasing a return material fan frequency by a preset percentage; if the outlet temperature is continuously increasing, a temperature-raising parameter adjustment step is performed; it is determined whether the outlet temperature stops increasing; if yes, the operation parameter adjustment is completed; if no, the temperature-raising parameter adjustment step is repeatedly performed; the temperature-raising parameter adjustment step at least includes one of increasing a tertiary air fan frequency by a preset percentage, increasing a secondary air fan frequency by a preset percentage, decreasing a feeding belt speed by a preset percentage, and decreasing a return material fan frequency by a preset percentage; 2. The method of claim 1, wherein, The weight and low calorific value level of the solid waste in the target region are obtained by using the image, reflectivity matrix and distance matrix, including: A stacking height matrix is obtained by using the distance matrix and the distance from the sensor to the feeding belt; The average stacking height of the solid waste is obtained by using the stacking height matrix; The weight of the solid waste is calculated by using the average stacking height, the area of the feeding belt and the stacking density of the solid waste; The proportion of each calorific value grade solid waste is obtained by using the pre-trained solid waste image recognition model to recognize the solid waste image; the solid waste image recognition model is configured to output the area proportion of each calorific value grade solid waste in the solid waste image according to the input solid waste image; The low calorific value level is calculated by using the proportion of each calorific value grade solid waste.

3. The method of claim 2, wherein, The low calorific value level is calculated by using the proportion of each calorific value grade solid waste, including: The estimated low calorific value level in the target region is calculated by using the proportion of each calorific value grade solid waste; The average moisture content in the target region is calculated by using the reflectivity matrix and the linear formula of moisture content with respect to reflectivity; The low calorific value level is obtained by correcting the estimated low calorific value level by using the average moisture content; The linear formula of the moisture content with respect to the reflectivity is obtained by linear fitting of the pre-tested sample moisture content data and sample reflectivity data; The formula for correcting the estimated low calorific value level using the average moisture content is as follows: ； wherein is a low heating value level; is a predicted low heating value level; is an average moisture content.

4. The method of claim 1, wherein, Using the pre-trained outlet temperature prediction model and the optimization algorithm, the operating parameters of the circulating fluidized bed are obtained, including: Using the environmental conditions, the operating parameters and the low calorific value level, an outlet temperature prediction model is constructed by a long short-term memory network algorithm; the outlet temperature prediction model is configured to input environmental conditions, operating parameters and low calorific value level, and output outlet temperature; the environmental conditions at least include one of temperature and pressure; Using the outlet temperature prediction model and the boundary conditions, the preliminary operating parameters of the circulating fluidized bed are obtained by an optimization algorithm; the boundary conditions include the range of operating parameters and the range of outlet temperature; According to the outlet temperature change trend after the preliminary operating parameters are operated for a preset time, the preliminary operating parameters are adjusted to obtain the final operating parameters of the circulating fluidized bed.

5. The method of claim 1, wherein, A temperature rising parameter adjusting step is performed; it is judged whether the outlet temperature stops rising; if yes, the operating parameter adjustment is completed; if no, the temperature rising parameter adjusting step is repeatedly performed, including: The frequency of the tertiary air fan is increased by a preset percentage; It is judged whether the outlet temperature stops rising; if no, the frequency of the secondary air fan is increased by a preset percentage; if yes, the operating parameter adjustment is completed; It is judged whether the outlet temperature stops rising; if no, the speed of the feeding belt is increased by a preset percentage; if yes, the operating parameter adjustment is completed; It is judged whether the outlet temperature stops rising; if no, the speed of the feeding belt is reduced by a preset percentage; if yes, the operating parameter adjustment is completed; It is judged whether the outlet temperature stops rising; if no, the frequency of the return air fan is reduced by a preset percentage; if yes, the operating parameter adjustment is completed; It is judged whether the outlet temperature stops rising; if no, the step of increasing the frequency of the tertiary air fan by a preset percentage is repeatedly performed.

6. A temperature control device for the outlet of a circulating fluidized bed furnace, characterized in that It is configured to be capable of realizing the temperature control method of the circulating fluidized bed furnace outlet according to any one of claims 1-5, including: A preprocessing module for preprocessing sensor data to obtain images, reflectivity matrices and distance matrices of solid wastes in a target area; A calorific value calculation module for obtaining the weight of solid wastes and the low calorific value level in the target area using the images, reflectivity matrices and distance matrices; the reflectivity matrix represents the reflectivity of the surface of the solid waste; the distance matrix represents the distance from the solid waste to the sensor; the solid waste calorific value is calculated using the weight of the solid waste and the low calorific value level; A parameter adjustment module for obtaining the operating parameters of the circulating fluidized bed using a pre-trained outlet temperature prediction model and an optimization algorithm; the operating parameters at least include one of fan frequency and feeding belt speed; the outlet temperature prediction model is configured to output the outlet temperature according to the input operating parameters and the solid waste calorific value; The process involves obtaining the operating parameters of the circulating fluidized bed using a pre-trained outlet temperature prediction model and optimization algorithm. This includes: constructing multiple outlet temperature prediction models using a Long Short-Term Memory (LSTM) network algorithm based on environmental conditions, the operating parameters, and the lower heating value level; configuring these multiple outlet temperature prediction models so that the inputs are environmental conditions, operating parameters, and the lower heating value level, and the output is the outlet temperature after different operating times; using these multiple outlet temperature prediction models and boundary conditions, obtaining the preliminary operating parameters of the circulating fluidized bed through an optimization algorithm; the boundary conditions include the range of operating parameters and the range of outlet temperatures after different operating times; and adjusting the preliminary operating parameters based on the outlet temperature change trend after a preset operating time to obtain the final operating parameters of the circulating fluidized bed. The step of adjusting the preliminary operating parameters based on the outlet temperature change trend after running for a preset time according to the preliminary operating parameters includes: determining whether the outlet temperature continues to decrease or increase; if so, adjusting at least one of the fan frequency and the feed belt speed within a preset range to obtain the final operating parameters; the preset range is the boundary range of the operating parameters; if not, not adjusting the preliminary operating parameters to obtain the final operating parameters; wherein the fan frequency includes at least one of the tertiary fan frequency, the secondary fan frequency, and the return fan frequency; The step of adjusting at least one of the fan frequency and the feed belt speed within a preset range includes: determining whether the outlet temperature is continuously decreasing or continuously increasing; if the outlet temperature is continuously decreasing, performing a cooling parameter adjustment step; determining whether the outlet temperature has stopped decreasing; if yes, completing the operating parameter adjustment; if no, repeating the cooling parameter adjustment step; the cooling parameter adjustment step includes at least one of reducing the tertiary fan frequency by a preset percentage, reducing the secondary fan frequency by a preset percentage, increasing the feed belt speed by a preset percentage, and increasing the return fan frequency by a preset percentage; if the outlet temperature is continuously increasing, performing a heating parameter adjustment step; determining whether the outlet temperature has stopped increasing; if yes, completing the operating parameter adjustment; if no, repeating the heating parameter adjustment step; the heating parameter adjustment step includes at least one of increasing the tertiary fan frequency by a preset percentage, increasing the secondary fan frequency by a preset percentage, decreasing the feed belt speed by a preset percentage, and decreasing the return fan frequency by a preset percentage. If the outlet temperature stops decreasing, the operation parameter adjustment is completed; if not, the temperature adjustment step is repeated, including: reducing the frequency of the tertiary air fan by a preset percentage; determining whether the outlet temperature stops decreasing; if not, reducing the frequency of the secondary air fan by a preset percentage; if so, completing the operation parameter adjustment; determining whether the outlet temperature stops decreasing; if not, reducing the speed of the feeding belt by a preset percentage; if so, completing the operation parameter adjustment; determining whether the outlet temperature stops decreasing; if not, increasing the speed of the feeding belt by a preset percentage; if so, completing the operation parameter adjustment; determining whether the outlet temperature stops decreasing; if not, increasing the frequency of the return material fan by a preset percentage; if so, completing the operation parameter adjustment; determining whether the outlet temperature stops decreasing; if not, repeating the step of reducing the frequency of the tertiary air fan by a preset percentage.

Images