A system and method for identifying and optimizing boiler soot blowing effect based on slag quantity monitoring

Abstract

This invention discloses a boiler soot blowing effect identification and optimization system and method based on slag quantity monitoring, belonging to the field of boiler operation optimization in coal-fired power plants. It solves the problem that existing soot blowing operations mainly rely on the experience judgment of operators or fixed time interval control, resulting in poor control effects. The system includes an acquisition module for acquiring the baseline value and real-time mass flow rate of slag on the conveyor belt of the boiler dry slag machine; a soot blowing effect classification and judgment module generates multiple consecutive average mass flow rates based on the real-time mass flow rate within a preset time period, calculates the difference between each average mass flow rate and the baseline mass flow rate, obtains the trend of real-time mass flow rate change, and determines the category of soot blowing effect based on the trend of real-time mass flow rate change or the rate of change of real-time mass flow rate between two adjacent sampling points, combined with preset classification rules; and a soot blowing strategy dynamic optimization module is communicatively connected to the soot blowing effect classification and judgment module. This invention is applied to coal-fired power plant boilers.

Description

Technical Field

[0001] This invention relates to the field of boiler operation optimization technology in coal-fired power plants, specifically to a system and method for identifying and optimizing boiler soot blowing effects based on slag quantity monitoring. Background Technology

[0002] Soot blowing is a crucial operation in the operation of coal-fired power plant boilers, responsible for removing ash from heated surfaces and maintaining boiler heat exchange efficiency. Currently, soot blowing operations rely primarily on the experience and judgment of operators or fixed time intervals, leading to the following common problems:

[0003] 1. Lack of real-time quantitative evaluation methods for soot blowing effect: After the soot blowing operation is completed, there is no real-time and objective monitoring method to determine whether the accumulated ash has been effectively removed and whether there is a risk of ash collapse (or tower ash).

[0004] 2. The determination of soot blowing frequency and timing relies on experience: Soot blowing operations are mostly based on subjective human judgment or fixed cycle execution, which can easily lead to insufficient or excessive soot blowing, thereby impairing the economy and safety of boiler operation.

[0005] 3. Lack of linkage mechanism between soot blowing and slag: Soot blowing operation is disconnected from the actual slag state of the boiler, and the soot blowing strategy cannot be dynamically adjusted according to the real-time slag situation of the boiler.

[0006] 4. Existing monitoring methods have inherent limitations: Traditional monitoring methods use changes in parameters such as temperature and pressure to provide feedback on the soot blowing effect, which has a significant lag and makes it difficult to accurately reflect the real-time effect of soot blowing operations.

[0007] In summary, there is an urgent need to develop a method that can identify the soot blowing effect in real time and intelligently optimize the soot blowing strategy based on the identification results. Summary of the Invention

[0008] To address the technical problem that existing soot blowing operations mainly rely on the experience and judgment of operators or fixed time interval control, resulting in poor control effects, this invention proposes a boiler soot blowing effect identification and optimization system and method based on slag quantity monitoring, so as to achieve objective quantitative evaluation of soot blowing effect and dynamic closed-loop optimization of operation strategy.

[0009] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is: a boiler soot blowing effect identification and optimization system based on slag quantity monitoring, comprising:

[0010] The acquisition module is used to acquire the baseline value and real-time mass flow rate of slag on the conveyor belt of the boiler dry slag machine;

[0011] The soot blowing effect classification and judgment module is communicatively connected to the acquisition module, and the soot blowing effect classification and judgment module is configured as follows:

[0012] Obtain the rate of change of mass flow rate between two adjacent sampling points;

[0013] Based on the real-time quality flow rate within a preset time period, generate multiple consecutive average quality flow rates, calculate the difference between each average quality flow rate and the baseline quality flow rate, and obtain the trend of real-time quality flow rate changes.

[0014] Based on the changing trend of real-time mass flow rate or the rate of change of real-time mass flow rate between two adjacent sampling points, the category of soot blowing effect is determined in combination with preset classification rules; the categories of soot blowing effect include at least the good effect type, the insignificant effect type, and the risk warning type.

[0015] The soot blowing strategy dynamic optimization module communicates with the soot blowing effect classification and judgment module. It is used to output corresponding strategy information for adjusting subsequent soot blowing operations based on the category of soot blowing effect. The strategy information for adjusting subsequent soot blowing operations includes at least controlling the soot blowing frequency, soot blowing duration, and soot blowing intensity for the slag on the conveyor belt of the boiler dry slag machine. It also prioritizes responding to risk warning classification results and executes safety assurance strategies.

[0016] Furthermore, the preset classification rules include:

[0017] If the difference between multiple consecutive average mass flow rates and the mass flow rate baseline value within a preset time period is positive and higher than the preset significant change threshold, then the soot blowing effect is determined to be of good quality.

[0018] If the absolute value of the difference between multiple consecutive average mass flow rates and the mass flow rate benchmark value within a preset time period is lower than the preset minimum change threshold, then the dust blowing effect is determined to be of the insignificant type.

[0019] If the rate of change of real-time mass flow rate at two adjacent sampling points exceeds the preset risk threshold for a sharp increase, the dust blowing effect is determined to be of the risk warning type.

[0020] Furthermore, the dynamic optimization module for the dust removal strategy includes a rule engine and a strategy library; the rule engine calls the corresponding optimization logic in the strategy library according to the input dust removal effect category; the optimization logic includes at least: the logic for generating maintenance or optimization suggestions for the good effect type, the logic for generating reduction or inspection suggestions for the insignificant effect type, and the logic for alarm and security assurance for the risk warning type.

[0021] Furthermore, both the soot blowing effect classification and judgment module and the soot blowing strategy dynamic optimization module are communicatively connected to the DCS system. The DCS system is used to display the soot blowing effect category output by the soot blowing effect classification and judgment module and the strategy information output by the soot blowing strategy dynamic optimization module for adjusting subsequent soot blowing operations.

[0022] Furthermore, the mass flow rate benchmark value is the average mass flow rate during a preset operating period before soot blowing on the slag on the boiler dry slag conveyor belt.

[0023] Furthermore, the average mass flow rate is a flow characteristic parameter obtained through two steps: dividing the data into multiple continuous sub-windows within a preset analysis time window and independently calculating the average mass flow rate within each sub-window.

[0024] Furthermore, the preset analysis time window covers two parts: the set soot blowing time and the continuous monitoring time window after soot blowing.

[0025] Furthermore, the acquisition module adopts a binocular vision online monitoring system, including an image acquisition unit, which is communicatively connected to an image processing unit. The image acquisition unit includes a binocular camera, which is used to acquire images of slag on the conveyor belt of the boiler dry slag machine in real time. The image processing unit is used to process the slag images acquired by the image acquisition module, and obtain the mass flow rate reference value and real-time mass flow rate based on the processed slag images through a three-dimensional reconstruction model.

[0026] A method for identifying and optimizing boiler soot blowing effect based on slag quantity monitoring, employing the aforementioned boiler soot blowing effect identification and optimization system based on slag quantity monitoring, includes the following steps:

[0027] Step S1: Obtain the baseline value and real-time mass flow rate of slag on the conveyor belt of the boiler dry slag machine;

[0028] Step S2: Generate multiple consecutive average mass flow rates based on the real-time mass flow rate within a preset time period, calculate the difference between each average mass flow rate and the mass flow rate baseline value to obtain the trend of real-time mass flow rate; based on the trend of real-time mass flow rate or the rate of change of real-time mass flow rate between two adjacent sampling points, determine the category of the soot blowing effect in combination with preset classification rules; the category of soot blowing effect includes at least the following: good effect, no effect, and risk warning.

[0029] Step S3: Output the corresponding strategy information for adjusting subsequent soot blowing operations according to the category of soot blowing effect. The strategy information for adjusting subsequent soot blowing operations includes at least controlling the soot blowing frequency, soot blowing duration, and soot blowing intensity of the slag on the conveyor belt of the boiler dry slag machine, and prioritizing the response to the risk warning classification results and implementing safety assurance strategies.

[0030] Furthermore, in step S3, when the soot blowing effect of a certain area on the conveyor belt of the boiler dry slag machine is determined to be a good soot blowing operation, the generated strategy information for adjusting subsequent soot blowing operations is to maintain or moderately extend the soot blowing interval of the area.

[0031] When the soot blowing effect in a certain area of ​​the boiler dry slag machine conveyor belt is determined to be an ineffective soot blowing operation, the generated strategy information for adjusting subsequent soot blowing operations is to extend the soot blowing interval in that area or trigger the boiler dry slag machine inspection mechanism.

[0032] When the soot blowing effect in a certain area of ​​the boiler dry slag machine conveyor belt is determined to be a risk warning type soot blowing operation, the generated strategy information for adjusting subsequent soot blowing operations includes at least one of issuing an alarm, pausing subsequent automatic soot blowing programs, and reducing soot blowing intensity.

[0033] The advantages of this invention over the prior art are as follows:

[0034] 1. This invention achieves objective quantification and real-time identification of soot blowing effect by acquiring a module that monitors and reflects the mass flow rate of slag on the conveyor belt of the boiler dry slag machine in real time, and by determining the category of soot blowing effect through a preset classification rule in the soot blowing effect classification judgment module.

[0035] 2. The acquisition module, the soot blowing effect classification and judgment module, and the soot blowing strategy dynamic optimization module of this invention work together to form an intelligent control closed loop of "monitoring-identification optimization-execution feedback", and construct a data-driven soot blowing strategy dynamic optimization closed loop;

[0036] 3. The system of the present invention is based on the slag mass flow rate collected by the acquisition module and combined with the preset classification rules to determine the category of soot blowing effect. It does not require large-scale modification of the boiler body, is easy to implement, and conforms to the trend of digitalization and intelligent development of power plants. Attached Figure Description

[0037] The present invention will be further described below with reference to the accompanying drawings:

[0038] Figure 1 This is a schematic diagram of the system structure of the present invention;

[0039] Figure 2 This is a schematic diagram of the structure of an embodiment of the system of the present invention;

[0040] Figure 3 This is a flowchart of the method of the present invention. Detailed Implementation

[0041] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicate relative orientations or positional relationships and are used only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0042] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0043] like Figures 1 to 3 As shown, this invention provides a boiler soot blowing effect identification and optimization system based on slag quantity monitoring, comprising:

[0044] The acquisition module is used to acquire the baseline value and real-time mass flow rate of slag on the conveyor belt of the boiler dry slag machine.

[0045] For example, the acquisition module employs a binocular vision online monitoring system, including an image acquisition unit, which is communicatively connected to an image processing unit. The image acquisition unit includes a binocular camera for real-time acquisition of images of slag on the conveyor belt of the boiler dry slag machine; the image processing unit processes the slag images acquired by the image acquisition module and obtains the mass flow rate baseline value and real-time mass flow rate based on the processed slag images through a three-dimensional reconstruction model.

[0046] The mass flow rate baseline value is the average mass flow rate over a preset operating period before soot blowing on the slag on the boiler dry slag conveyor belt. In one embodiment, the preset operating period is 10-15 minutes.

[0047] The dust blowing effect classification and judgment module, which communicates with the acquisition module, is configured as follows:

[0048] Obtain the rate of change of mass flow rate between two adjacent sampling points;

[0049] Based on the real-time quality flow rate within a preset time period, generate multiple consecutive average quality flow rates, calculate the difference between each average quality flow rate and the baseline quality flow rate, and obtain the trend of real-time quality flow rate changes.

[0050] Based on the real-time mass flow rate change trend or the rate of change of real-time mass flow rate between two adjacent sampling points, and combined with preset classification rules, the category of the soot blowing effect is determined. The categories of soot blowing effect include at least three types: good effect, no effect, and risk warning.

[0051] The average mass flow rate is a flow characteristic parameter obtained by two steps: dividing the data into multiple continuous sub-windows within a preset analysis time window and independently calculating the average mass flow rate within each sub-window.

[0052] The preset analysis time window covers two parts: the set soot blowing time and the continuous monitoring time window after soot blowing. For example, the preset analysis time window is a continuous period of 30-60 minutes from the start of soot blowing to the end of soot blowing.

[0053] Difference between the average mass flow rate and the mass flow rate baseline within the sub-window The calculation model is as follows:

[0054] ;

[0055] in, This represents the average mass flow rate within the sub-window.

[0056] This is the baseline value for mass flow rate.

[0057] The preset classification rules include:

[0058] If the difference between multiple consecutive average mass flow rates and the mass flow rate benchmark value within a preset time period If all values ​​are positive and exceed a preset significant change threshold, the soot blowing effect is determined to be of good quality; in one embodiment, the preset significant change threshold is 15%-30% of the mass flow rate baseline value.

[0059] If the difference between multiple consecutive average mass flow rates and the mass flow rate benchmark value within a preset time period If the absolute values ​​are all lower than the preset minimum change threshold, the blowing effect is determined to be of the insignificant type; in one embodiment, the preset minimum change threshold is within ±5% of the mass flow rate reference value;

[0060] If the rate of change of real-time mass flow rate at two adjacent sampling points exceeds a preset steep increase risk threshold, the dust blowing effect is determined to be a risk warning type. In one embodiment, the normal fluctuation range of the steep increase risk threshold (mass flow rate baseline value) is defined as follows: of More than 3 to 5 times that of 5%.

[0061] Rate of change of real-time mass flow rate between two adjacent sampling points The model for obtaining this model is:

[0062] ;

[0063] in, and These represent the real-time mass flow rates at two sampling points;

[0064] For example, to collect the time interval of real-time mass flow rate at two sampling points, The value range is 1-2 minutes.

[0065] The soot blowing strategy dynamic optimization module communicates with the soot blowing effect classification and judgment module. It is used to output corresponding strategy information for adjusting subsequent soot blowing operations based on the category of soot blowing effect. The strategy information for adjusting subsequent soot blowing operations includes at least controlling the soot blowing frequency, soot blowing duration, and soot blowing intensity for the slag on the conveyor belt of the boiler dry slag machine. It also prioritizes responding to risk warning classification results and executes safety assurance strategies.

[0066] The dynamic optimization module for the dust removal strategy includes a rule engine and a strategy library. The rule engine calls the corresponding optimization logic in the strategy library based on the input dust removal effect category. The optimization logic includes at least: logic for generating maintenance or optimization suggestions for the good effect type, logic for generating reduction or inspection suggestions for the insignificant effect type, and alarm and security protection logic for the risk warning type.

[0067] Both the soot blowing effect classification and judgment module and the soot blowing strategy dynamic optimization module are communicatively connected to the DCS system. The DCS system is used to display the soot blowing effect category output by the soot blowing effect classification and judgment module and the strategy information output by the soot blowing strategy dynamic optimization module for adjusting subsequent soot blowing operations.

[0068] This invention provides a method for identifying and optimizing boiler soot blowing effect based on slag quantity monitoring. The method employs the aforementioned system for identifying and optimizing boiler soot blowing effect based on slag quantity monitoring, and includes the following steps:

[0069] Step S1: Obtain the baseline value and real-time mass flow rate of the slag on the conveyor belt of the boiler dry slag machine.

[0070] To obtain the real-time mass flow rate of slag on the conveyor belt of the boiler dry slag machine, the following steps are taken: visual imaging of the conveyor belt area of ​​the boiler dry slag machine; obtaining the volume information of the slag on the conveyor belt through a 3D reconstruction model; converting the volume information of the slag into mass information by combining the preset density parameters of the slag; and calculating the real-time mass flow rate based on continuously collected time series data.

[0071] The process of obtaining the reference value of the mass flow rate of slag on the conveyor belt of the boiler dry slag machine is as follows: before performing soot blowing operation on the slag on the conveyor belt of the boiler dry slag machine, the average value of multiple real-time mass flow rates within a preset operating time period is obtained. In one embodiment, the preset operating time period is 10-15 minutes.

[0072] Step S2: Generate multiple consecutive average mass flow rates based on the real-time mass flow rate within a preset time period. Calculate the difference between each average mass flow rate and the baseline mass flow rate to obtain the trend of real-time mass flow rate changes. Based on the trend of real-time mass flow rate changes or the rate of change of real-time mass flow rate between two adjacent sampling points, determine the category of the soot blowing effect according to preset classification rules. The categories of soot blowing effect include at least three types: good effect, no effect, and risk warning.

[0073] The process of generating multiple consecutive average mass flow rates is as follows:

[0074] The preset analysis time window is divided into multiple consecutive sub-windows (e.g., every 5 minutes). The average mass flow rate within each sub-window is obtained. The average mass flow rate within each sub-window is then used to calculate the worst-case scenario of the mass flow rate baseline value, resulting in the difference between the average mass flow rate and the mass flow rate baseline value. .

[0075] The preset analysis time window covers two parts: the set soot blowing time and the continuous monitoring time window after soot blowing. For example, the preset analysis time window is a continuous period of 30-60 minutes from the start of soot blowing to the end of soot blowing.

[0076] Difference between the average mass flow rate and the mass flow rate baseline within the sub-window The calculation model is as follows:

[0077] ;

[0078] in, This represents the average mass flow rate within the sub-window.

[0079] This is the baseline value for mass flow rate.

[0080] Rate of change of real-time mass flow rate between two adjacent sampling points The model for obtaining this model is:

[0081] ;

[0082] in, and These represent the real-time mass flow rates at two sampling points;

[0083] This is the time interval for collecting real-time mass flow rates at two sampling points; for example, The value range is 1-2 minutes.

[0084] The preset classification rules include:

[0085] If the difference between multiple consecutive average mass flow rates and the mass flow rate benchmark value within a preset time period If all values ​​are positive and exceed the preset significant change threshold, the soot blowing effect is determined to be of the good type. In one embodiment, the preset significant change threshold is 15%-30% of the mass flow rate baseline value. The trend of real-time mass flow rate change corresponding to the good soot blowing effect is that after the soot blowing operation is completed on the slag on the conveyor belt of the boiler dry slag machine, the real-time mass flow rate shows a continuous and stable increase or a high and stable level within the preset analysis time window, and there is no situation where the slag flow rate drops.

[0086] If the difference between multiple consecutive average mass flow rates and the mass flow rate benchmark value within a preset time period If the absolute values ​​are all lower than the preset minimum change threshold, the soot blowing effect is determined to be of the insignificant type. In one embodiment, the preset minimum change threshold is within ±5% of the mass flow rate benchmark value. The change trend of the real-time mass flow rate corresponding to the insignificant soot blowing effect is that the real-time mass flow rate fluctuates slightly and randomly around the mass flow rate benchmark value, without a clear trend. Specifically, the amount of slag does not change significantly before and after performing soot blowing operation on the slag on the conveyor belt of the boiler dry slag machine.

[0087] If the rate of change of real-time mass flow rate between two adjacent sampling points exceeds a preset steep increase risk threshold, the dust blowing effect is determined to be of a risk warning type. In one embodiment, the steep increase risk threshold is the normal fluctuation range (mass flow rate baseline value). of The change trend of real-time quality flow rate corresponding to the risk warning type dust blowing effect is characterized by a single point or continuous sharp peak in real-time quality flow rate within a very short time window (1-2 minutes). After the peak appears, the quality flow rate will then show a rapid decline or a large and violent fluctuation.

[0088] Step S3: Output the corresponding strategy information for adjusting subsequent soot blowing operations according to the category of soot blowing effect. The strategy information for adjusting subsequent soot blowing operations includes at least controlling the soot blowing frequency, soot blowing duration, and soot blowing intensity of the slag on the conveyor belt of the boiler dry slag machine, and prioritizing the response to the risk warning classification results and implementing safety assurance strategies.

[0089] In step S3, when the soot blowing effect of a certain area on the conveyor belt of the boiler dry slag machine is determined to be a good soot blowing operation, the generated strategy information for adjusting subsequent soot blowing operations is to maintain or moderately extend the soot blowing interval of the area (e.g., increase the cycle by 10%-20%), which can save costs while maintaining the cleanliness of the conveyor belt.

[0090] When the soot blowing effect in a certain area of ​​the boiler dry slag machine conveyor belt is determined to be an ineffective soot blowing operation, the generated strategy information for adjusting subsequent soot blowing operations is to extend the soot blowing interval of that area or trigger the boiler dry slag machine inspection mechanism; in one embodiment, when the soot blowing effect in a certain area of ​​the boiler dry slag machine conveyor belt is determined to be an ineffective soot blowing operation, the strategy information for adjusting subsequent soot blowing operations is:

[0091] Level 1 adjustment: Extend the soot blowing interval in areas where the effect is not obvious (e.g., increase by 30%-50%) to reduce ineffective soot blowing;

[0092] Secondary adjustment: If the soot blowing effect in this area is still judged as having an insignificant extended effect after the primary adjustment, the boiler dry slag machine inspection mechanism will be triggered, and the soot blower angle, soot blowing medium pressure, or soot blowing time corresponding to this area will be adjusted.

[0093] The boiler dry slag machine inspection mechanism includes checking parameters such as the temperature of the corresponding heating surface and flue gas resistance in that area to determine whether it is an instrument malfunction or a special type of ash accumulation.

[0094] When the soot blowing effect in a certain area of ​​the boiler dry slag machine conveyor belt is determined to be a risk warning type soot blowing operation, the generated strategy information for adjusting subsequent soot blowing operations includes at least one of issuing an alarm, pausing subsequent automatic soot blowing programs, and reducing soot blowing intensity.

[0095] The strategy information generated in step S3 for adjusting subsequent soot blowing operations is also comprehensively optimized by combining historical soot blowing effect data of the identified area and the current operating parameters of the boiler.

[0096] Regarding the specific structure of this invention, it should be noted that the connection relationships between the various component modules used in this invention are definite and achievable. Except as specifically described in the embodiments, their specific connection relationships can bring about corresponding technical effects and solve the technical problems proposed by this invention without relying on the execution of corresponding software programs. The models of the components, modules, and specific components appearing in this invention, the connection methods between them, and the conventional usage methods and expected technical effects brought about by the above technical features, unless specifically described, are all publicly disclosed content in patents, journal articles, technical manuals, technical dictionaries, and textbooks that can be obtained by those skilled in the art before the application date, or belong to conventional technology, common knowledge, and other existing technologies in this field. There is no need to elaborate, which makes the technical solution provided in this case clear, complete, and achievable, and can reproduce or obtain corresponding physical products based on this technical means.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A boiler soot blowing effect identification and optimization system based on slag quantity monitoring, characterized in that, include: The acquisition module is used to acquire the baseline value and real-time mass flow rate of slag on the conveyor belt of the boiler dry slag machine; The soot blowing effect classification and judgment module is communicatively connected to the acquisition module, and the soot blowing effect classification and judgment module is configured as follows: Obtain the rate of change of mass flow rate between two adjacent sampling points; Multiple consecutive average mass flows are generated based on the real-time mass flow within a preset time period. The difference between each average mass flow and the baseline mass flow is calculated to obtain the trend of real-time mass flow. The mass flow rate baseline value is the average mass flow rate during a preset operating time period before soot blowing is performed on the slag conveyor belt of the boiler dry slag machine. Based on the changing trend of real-time mass flow rate or the rate of change of real-time mass flow rate between two adjacent sampling points, the category of the soot blowing effect is determined in combination with the preset classification rules. The categories of dust removal effects include at least three types: good effect, no effect, and risk warning. The soot blowing strategy dynamic optimization module communicates with the soot blowing effect classification and judgment module. It is used to output corresponding strategy information for adjusting subsequent soot blowing operations according to the category of soot blowing effect. The strategy information for adjusting subsequent soot blowing operations includes at least controlling the soot blowing frequency, soot blowing duration, and soot blowing intensity of the slag on the conveyor belt of the boiler dry slag machine, and prioritizes responding to risk warning classification results and executing safety assurance strategies. The preset classification rules include: If the difference between multiple consecutive average mass flow rates and the mass flow rate baseline value within a preset time period is positive and higher than the preset significant change threshold, then the soot blowing effect is determined to be of good quality. If the absolute value of the difference between multiple consecutive average mass flow rates and the mass flow rate benchmark value within a preset time period is lower than the preset minimum change threshold, then the dust blowing effect is determined to be of the insignificant type. If the rate of change of real-time mass flow rate at two adjacent sampling points exceeds the preset risk threshold for a sharp increase, the dust blowing effect is determined to be of the risk warning type.

2. The boiler soot blowing effect identification and optimization system based on slag quantity monitoring according to claim 1, characterized in that, The dynamic optimization module for the dust removal strategy includes a rule engine and a strategy library. The rule engine calls the corresponding optimization logic in the strategy library based on the input dust removal effect category. The optimization logic includes at least: logic for generating maintenance or optimization suggestions for the good effect type, logic for generating reduction or inspection suggestions for the insignificant effect type, and alarm and security protection logic for the risk warning type.

3. The boiler soot blowing effect identification and optimization system based on slag quantity monitoring according to claim 1, characterized in that, Both the soot blowing effect classification and judgment module and the soot blowing strategy dynamic optimization module are communicatively connected to the DCS system. The DCS system is used to display the soot blowing effect category output by the soot blowing effect classification and judgment module and the strategy information output by the soot blowing strategy dynamic optimization module for adjusting subsequent soot blowing operations.

4. The boiler soot blowing effect identification and optimization system based on slag quantity monitoring according to claim 1, characterized in that, The average mass flow rate is a flow characteristic parameter obtained through two steps: dividing the data into multiple continuous sub-windows within a preset analysis time window and independently calculating the average mass flow rate within each sub-window.

5. The boiler soot blowing effect identification and optimization system based on slag quantity monitoring according to claim 4, characterized in that, The preset analysis time window covers two parts: the set soot blowing time and the continuous monitoring time window after soot blowing.

6. The boiler soot blowing effect identification and optimization system based on slag quantity monitoring according to claim 1, characterized in that, The acquisition module adopts a binocular vision online monitoring system, including an image acquisition unit, which is communicatively connected to an image processing unit. The image acquisition unit includes a binocular camera, which is used to acquire images of slag on the conveyor belt of the boiler dry slag machine in real time. The image processing unit is used to process the slag images acquired by the image acquisition module, and obtain the mass flow rate baseline value and real-time mass flow rate based on the processed slag images through a three-dimensional reconstruction model.

7. A method for identifying and optimizing boiler soot blowing effect based on slag quantity monitoring, comprising the boiler soot blowing effect identification and optimization system based on slag quantity monitoring as described in any one of claims 1-6, characterized in that, Includes the following steps: Step S1: Obtain the baseline value and real-time mass flow rate of slag on the conveyor belt of the boiler dry slag machine; Step S2: Generate multiple consecutive average mass flow rates based on the real-time mass flow rate within a preset time period, and calculate the difference between each average mass flow rate and the mass flow rate baseline value to obtain the trend of real-time mass flow rate changes. Based on the changing trend of real-time mass flow rate or the rate of change of real-time mass flow rate between two adjacent sampling points, the category of the soot blowing effect is determined in combination with the preset classification rules. The categories of dust removal effects include at least three types: good effect, no effect, and risk warning. Step S3: Output the corresponding strategy information for adjusting subsequent soot blowing operations according to the category of soot blowing effect. The strategy information for adjusting subsequent soot blowing operations includes at least controlling the soot blowing frequency, soot blowing duration, and soot blowing intensity of the slag on the conveyor belt of the boiler dry slag machine, and prioritizing the response to the risk warning classification results and implementing safety assurance strategies.

8. The method for identifying and optimizing boiler soot blowing effect based on slag quantity monitoring according to claim 7, characterized in that, In step S3, when the soot blowing effect of a certain area on the conveyor belt of the boiler dry slag machine is determined to be a good soot blowing operation, the generated strategy information for adjusting subsequent soot blowing operations is to maintain or moderately extend the soot blowing interval of the area. When the soot blowing effect in a certain area of ​​the boiler dry slag machine conveyor belt is determined to be an ineffective soot blowing operation, the generated strategy information for adjusting subsequent soot blowing operations is to extend the soot blowing interval in that area or trigger the boiler dry slag machine inspection mechanism. When the soot blowing effect in a certain area of ​​the boiler dry slag machine conveyor belt is determined to be a risk warning type soot blowing operation, the generated strategy information for adjusting subsequent soot blowing operations includes at least one of issuing an alarm, pausing subsequent automatic soot blowing programs, and reducing soot blowing intensity.

Images