Monitoring method for judging coking state of hearth
By calculating the heat transfer coefficient of the boiler heated surface and comparing it using a prediction model, the real-time accuracy problem of the boiler furnace coking state monitoring is solved, and efficient coking detection and combustion optimization are achieved.
Patent Information
- Application Number
- CN202411600671.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-11
- Publication Date
- 2025-02-28
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The prior art is difficult to accurately monitor the coking state inside the boiler furnace in real time and time. The traditional methods are not accurate enough and the workload is large, so it is impossible to achieve all-round real-time judgment.
By obtaining basic data on the six heating surfaces of the boiler, calculating the operating heat transfer coefficient, and comparing it using the best heat transfer coefficient prediction model to judge the drop in the heat transfer coefficient to determine whether the furnace is coking.
The accuracy of real-time monitoring of the coking state of the boiler is achieved, reducing manpower and material consumption, timely discovering coking conditions, avoiding the deterioration of problems, and improving the healthy state and operation efficiency of combustion operation.
Smart Images
Figure CN119532756A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of furnace coking monitoring, and in particular to a monitoring method for judging the furnace coking state. Background Art
[0002] Coking is a common problem in boiler operation. Generally, the ash particles moving with the flue gas are cooled together with the flue gas due to the heat absorption of the heating surface of the furnace water-cooled wall. If the liquid slag particles have solidified due to the temperature drop before approaching the water-cooled wall or the furnace wall, a loose ash layer will be formed when they adhere to the heating surface tube wall, which can be easily removed by blowing soot during operation. When the temperature in the furnace is high, some ash particles have reached a molten or semi-molten state. If these ash particles are not sufficiently cooled to a solidified state before reaching the heating surface, they have a high bonding ability and are easy to adhere to the flue gas scouring heating surface or the furnace wall, and even reach a molten state. The adhesion of molten or semi-molten ash particles and unburned coke causes coking to continue to develop and worsen.
[0003] The traditional prediction method of boiler heating surface coking encodes, classifies and models the boiler operation data according to the boiler operation principle, establishes a boiler non-coking training database in different load ranges, and establishes a boiler non-coking training model and a boiler coking training model. Based on the boiler operation mechanism and big data model, the boiler coking state is predicted. This method uses a data set for training and modeling, and the judgment mode is based on a historical data set. This prediction method is not accurate enough and cannot fully display the coking state of the boiler.
[0004] In addition, there is also a method of judging by coking thickness. By selecting any point on the other water-cooled wall of the boiler as an observation point, the coking thickness at the position corresponding to the observation point is calculated; and by analogy, by adjusting the selected fire observation hole and the position of the observation point, the coking thickness information at the corresponding positions of all the observation points measured is processed into a three-dimensional image, and the coking position and thickness of the water-cooled wall of the entire boiler can be obtained. Although it is accurate to judge the coking at the observation point of the boiler, the workload is large, the furnace volume is large, there are many fire observation points, and repeated measurements are required, which consumes a lot of manpower and material resources. And it is impossible to make a comprehensive and real-time judgment on the coking state of the furnace.
[0005] In summary, how to accurately monitor the coking state inside the furnace in real time has become a problem to be solved. Summary of the invention
[0006] The present invention provides a monitoring method for judging the coking state of a furnace, divides the entire boiler into six heating surfaces, and obtains the overall contamination rate of each heating surface by respectively calculating the heat transfer coefficients of the six surfaces, and finally uses an optimal heat transfer coefficient prediction model to judge whether adjustments or optimizations such as coking or soot blowing are needed according to the six coking surfaces. There is no need to shut down the furnace, and the coking of the boiler can be discovered in time, thereby reducing power generation losses and improving the healthy operation state and efficiency of the combustion furnace.
[0007] The present invention provides a monitoring method for determining the coking state of a furnace, comprising:
[0008] When the boiler is in operation and combustion state, basic data is obtained for each of the six heating surfaces of the boiler; wherein the basic data includes the temperature value of the flue gas before and after passing through the water-cooled wall, the heat flow passing through the heating surface, and the area size of the heating surface;
[0009] Calculate the operating heat transfer coefficients of the six heating surfaces respectively according to the basic data;
[0010] Collecting initial data of the boiler in a healthy state, and using the initial data to train an optimal heat transfer coefficient prediction model;
[0011] Obtain boiler operating parameters under boiler operation and combustion conditions, and use the trained optimal heat transfer coefficient prediction model to obtain the optimal heat transfer coefficient under boiler operation and combustion conditions;
[0012] The operating heat transfer coefficient is compared with the optimal heat transfer coefficient to determine the decrease in the heat transfer coefficient of the same heating surface, so as to determine whether the furnace of the boiler is coked.
[0013] Furthermore, in the step of obtaining basic data for each of the six heating surfaces of the boiler when the boiler is in operation and combustion state, the six heating surfaces include a water-cooled wall, a low-temperature superheater, a partition screen, a final superheater, a low-temperature reheater, and a final reheater. A temperature sensor is provided at the starting position of the flue gas flow direction of each heating surface, and a flow meter is installed on each heating surface.
[0014] Furthermore, in the step of respectively calculating the operating heat transfer coefficients of the six heating surfaces according to the basic data, the calculation formula is:
[0015]
[0016] Among them, Q is the heat flow, A is the heat transfer area, and Δt is the temperature difference, that is, the temperature difference measured by the flue gas flow sensor.
[0017] Furthermore, the step of collecting initial data of the boiler in a healthy state and using the initial data to train an optimal heat transfer coefficient prediction model includes:
[0018] Collect boiler operating parameters and optimal heat transfer coefficients when the boiler is in a healthy state, and store the collection time, boiler operating parameters, and heat transfer coefficients of six heating surfaces in a database as a sample set; wherein the optimal heat transfer coefficient includes the heat transfer coefficients of the six heating surfaces;
[0019] Taking the acquisition time and boiler operating parameters in the database as input and the optimal heat transfer coefficient as output, the optimal heat transfer coefficient prediction model is trained; wherein the optimal heat transfer coefficient prediction model is a relationship model between the boiler operating parameters and the optimal heat transfer coefficient of the boiler in the uncoked state;
[0020] Further, in the step of collecting boiler operating parameters and optimal heat transfer coefficients in a healthy state of the boiler, and storing the collection time, boiler operating parameters, and heat transfer coefficients of six heating surfaces in a database as a sample set, the healthy state of the boiler is the state of the first combustion operation after each boiler coking and ash cleaning treatment;
[0021] The boiler operating parameters include combustion volume, primary air volume, primary air temperature, secondary air volume, secondary air temperature, feed water volume, and the temperature and pressure of the six heating surfaces.
[0022] Furthermore, in the step of comparing the operating heat transfer coefficient with the optimal heat transfer coefficient to determine whether the heat transfer coefficient of the same heating surface decreases to determine whether the furnace of the boiler is coked,
[0023] The difference between the operating heat transfer coefficient and the optimal heat transfer coefficient is calculated to determine whether the heat transfer efficiency is attenuated and whether the furnace of the boiler is coked; if coking occurs in the furnace, the heat transfer efficiency of the heating surface will decrease, and the water-cooled wall and other heating surfaces will not be able to cool the flue gas or play a role in temperature control.
[0024] Furthermore, after the step of comparing the operating heat transfer coefficient with the optimal heat transfer coefficient to determine whether the furnace of the boiler is coked, the method further includes:
[0025] The data of the six heating surfaces are visualized in three dimensions to display the results of real-time calculations on the front end;
[0026] If coking occurs in the furnace of the boiler, the coking situation will be presented in the form of data and an alarm signal will be issued to prompt the operating personnel to perform operations such as decoking, soot blowing and combustion parameter optimization.
[0027] The present invention also provides a monitoring device for judging the coking state of a furnace, comprising:
[0028] An acquisition module is used to acquire basic data for each of the six heating surfaces of the boiler when the boiler is in operation and combustion state; wherein the basic data includes the temperature value of the flue gas before and after passing through the water-cooled wall, the heat flow passing through the heating surface, and the area size of the heating surface;
[0029] A calculation module, used to calculate the operating heat transfer coefficients of the six heating surfaces respectively according to the basic data;
[0030] A collection module, used to collect initial data of the boiler in a healthy state, and use the initial data to train an optimal heat transfer coefficient prediction model;
[0031] The prediction module is used to obtain the boiler operating parameters under the boiler operating combustion state, and use the trained optimal heat transfer coefficient prediction model to obtain the optimal heat transfer coefficient under the boiler operating combustion state;
[0032] The comparison module is used to compare the operating heat transfer coefficient with the optimal heat transfer coefficient to determine the decrease in the heat transfer coefficient of the same heating surface to determine whether the furnace of the boiler is coked.
[0033] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.
[0034] The present invention also provides a computer-readable storage medium on which a computer program is stored, and the computer program implements the steps of the above method when executed by a processor.
[0035] The beneficial effects of the present invention are:
[0036] 1. Real-time monitoring and accuracy: By calculating the heat transfer coefficients of the six heating surfaces to obtain the overall contamination rate of each heating surface, this method can monitor the coking status of the boiler in real time. And because it is based on physical numerical calculations, it has high accuracy, which helps to detect the coking situation of the boiler in time and avoid further deterioration of the problem.
[0037] 2. Set up the optimal heat transfer coefficient prediction model. The basic data set comes from the data of the best state after each boiler cleaning or coking, and the best heat transfer coefficient is obtained according to different operating parameters, which is convenient for comparison under the same operating state. The use of equipment has efficiency decay. The heat transfer coefficient of the same boiler operating parameters in the best state after boiler cleaning and maintenance at different time nodes is different, so there is a time relationship in the database. The recurrent neural network model is good at processing time-related data and can accurately predict the optimal heat transfer coefficient under specific furnace operating parameters.
[0038] 3. The coking state of the boiler is presented intuitively through three-dimensional visualization, so that the operator can understand the operation of the boiler more intuitively, and can grasp the heat transfer coefficient of each heating surface separately, and reflect the coking state in time, so as to have an intuitive and quantitative grasp of the entire furnace. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] Figure 1 The figure is a schematic diagram of a method flow according to an embodiment of the present invention.
[0040] Figure 2 It is a schematic diagram of the operation of the process in the present invention.
[0041] Figure 3 FIG. 1 is a schematic diagram of a device structure according to an embodiment of the present invention.
[0042] Figure 4 The figure is a schematic diagram of the internal structure of a computer device according to an embodiment of the present invention.
[0043] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0044] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0045] The present invention mainly monitors the overall coking state in the combustion boiler, divides the boiler into six heating surfaces, and obtains the overall contamination rate of each heating surface by calculating the heat transfer coefficient of the six surfaces respectively, and presents it intuitively through three-dimensional visualization. Finally, a cluster analysis model is used to determine whether adjustments or optimizations such as coking or soot blowing are required based on the six coking surfaces. The online detection method is accurate and does not require shutdown. The coking of the boiler can be discovered in time, power generation losses can be reduced, and the healthy state and efficiency of the combustion furnace can be improved.
[0046] like Figure 1 , 2 As shown, the present invention provides a monitoring method for judging the coking state of a furnace, comprising:
[0047] S1. Under the boiler operation and combustion state, basic data is obtained for each of the six heating surfaces of the boiler; wherein the basic data includes the temperature value of the flue gas before and after passing through the water-cooled wall, the heat flow passing through the heating surface, and the area size of the heating surface;
[0048] Heating surface division and sensor installation: According to the boiler's operating structure and design, and according to the direction of flue gas heat exchange, the boiler is divided into six heating surfaces, namely, water-cooled wall, low-temperature superheater, partition screen, final superheater, low-temperature reheater, and final reheater. Each heating surface is a module, and a temperature sensor is installed at the starting position of the flue gas flow direction of each module to obtain the temperature value of the flue gas before and after passing through the water-cooled wall. Flow meters are installed on the six surfaces to obtain the heat flow passing through the heating surface, and the area size of the six heating surfaces is obtained according to the boiler design.
[0049] S2. Calculate the operating heat transfer coefficients of the six heating surfaces respectively according to the basic data; the calculation formula is:
[0050]
[0051] Among them, Q is the heat flow, A is the heat transfer area, and Δt is the temperature difference, that is, the temperature difference measured by the flue gas flow sensor. According to the formula, the heat transfer coefficients K of the six surfaces are calculated respectively, which are K1, K2, K3, K4, K5, and K6.
[0052] S3, collecting initial data of the boiler in a healthy state, and using the initial data to train an optimal heat transfer coefficient prediction model;
[0053] Step S3 specifically includes:
[0054] S31, collecting boiler operating parameters and optimal heat transfer coefficients in a healthy state of the boiler, and storing the collection time, boiler operating parameters, and heat transfer coefficients of six heating surfaces in a database as a sample set; wherein the optimal heat transfer coefficient includes the heat transfer coefficients of the six heating surfaces; the healthy state of the boiler is the state of the first combustion operation after each boiler coking and ash cleaning treatment;
[0055] Establish a data acquisition system: It is used to collect data from temperature sensors, flow meters, and other relevant parameters of boiler operation (such as combustion volume, primary air volume, primary air temperature, secondary air volume, secondary air temperature, feed water volume, etc.) in real time. Only collect boiler operating parameters and heat transfer coefficients when the furnace is in a healthy state. The data on the healthy state of the boiler refers to the first use of the boiler, as well as the first use of the boiler after each inspection, cleaning, soot blowing, and coking of the furnace. This data is the optimal heat transfer coefficient when the furnace is not coked. The collected time, corresponding boiler operating parameters, corresponding heat transfer coefficients of the six heating surfaces, and other data are stored in the database as a sample set to prepare data for model training.
[0056] S32, using the acquisition time and boiler operating parameters in the database as input and the optimal heat transfer coefficient as output, training an optimal heat transfer coefficient prediction model; wherein the optimal heat transfer coefficient prediction model is a relationship model between the boiler operating parameters and the optimal heat transfer coefficient of the boiler in an uncoked state;
[0057] The optimal heat transfer coefficient prediction model is trained by a recurrent neural network algorithm. The sample set of the model comes from the boiler operating status and heat transfer parameter database sample set in step S31. With time and the combustion parameters of boiler operation as input and the optimal heat transfer coefficient as output, the model is trained to obtain a relationship model between the boiler operating parameters and the optimal heat transfer coefficient of the boiler in the uncoked state. Furthermore, the recurrent neural network model is regularly updated and optimized to improve the prediction accuracy and robustness. The implementation method is that the combustion data and heat transfer coefficient when the boiler is operated in the uncoked state after overhaul, soot blowing, and coking are updated to the database each time, and the recurrent neural network model is retrained each time the database is updated to ensure continuous learning and improvement of the model.
[0058] S4, obtaining boiler operating parameters under the boiler operating combustion state, and using the trained optimal heat transfer coefficient prediction model to obtain the optimal heat transfer coefficient under the boiler operating combustion state;
[0059] When the boiler is running and burning, the heat transfer coefficients of the six heating surfaces are calculated in real time through the sensors of the six heating surfaces. The heat transfer coefficients calculated as described above are K1, K2, K3, K4, K5, and K6. At the same time, according to the trained recurrent neural network model, the current boiler operating parameters are input to obtain the optimal heat transfer coefficients K10, K20, K30, K40, K50, and K60 under the current situation, and the heat transfer coefficients of the two are compared. By comparing the difference, the decrease in the heat transfer coefficient of the same heating surface can be calculated separately to determine the coking state of the furnace. Furthermore, the total difference of the six heating surfaces can also be calculated to obtain the overall coking situation of the boiler.
[0060] S5. Compare the operating heat transfer coefficient with the optimal heat transfer coefficient to determine the decrease in the heat transfer coefficient of the same heating surface to determine whether the furnace of the boiler is coked.
[0061] Calculating the difference between the operating heat transfer coefficient and the optimal heat transfer coefficient to determine whether the heat transfer efficiency is attenuated and whether the furnace of the boiler is coked;
[0062] If coking occurs in the furnace, the heat transfer efficiency of the heating surface will decrease, and the water-cooled wall and other heating surfaces will not be able to cool the flue gas or play a role in temperature control. The attenuation of heat transfer efficiency is determined by the difference between the heat transfer coefficient calculated in real time under the current working conditions and the optimal heat transfer coefficient under the same combustion parameters.
[0063] S6, three-dimensionally visualize the data of the six heating surfaces to display the results of the real-time calculation on the front end;
[0064] If coking occurs in the furnace of the boiler, the coking situation will be presented in the form of data and an alarm signal will be issued to prompt the operating personnel to perform operations such as decoking, soot blowing and combustion parameter optimization.
[0065] like Figure 3 As shown, the present invention also provides a monitoring device for judging the coking state of a furnace, comprising:
[0066] Acquisition module 1, used for acquiring basic data for each of the six heating surfaces of the boiler when the boiler is in operation and combustion state; wherein the basic data includes the temperature value of the flue gas before and after passing through the water-cooled wall, the heat flow passing through the heating surface, and the area size of the heating surface;
[0067] Calculation module 2, used to calculate the operating heat transfer coefficients of the six heating surfaces respectively according to the basic data;
[0068] The acquisition module 3 is used to acquire the initial data of the boiler in a healthy state, and use the initial data to train the optimal heat transfer coefficient prediction model;
[0069] Prediction module 4 is used to obtain boiler operating parameters under the boiler operating combustion state, and use the trained optimal heat transfer coefficient prediction model to obtain the optimal heat transfer coefficient under the boiler operating combustion state;
[0070] The comparison module 5 is used to compare the operating heat transfer coefficient with the optimal heat transfer coefficient to determine the decrease in the heat transfer coefficient of the same heating surface to determine whether the furnace of the boiler is coked.
[0071] In one embodiment, in the acquisition module 1, the six heating surfaces include a water-cooled wall, a low-temperature superheater, a partition screen, a final superheater, a low-temperature reheater, and a final reheater. A temperature sensor is provided at the starting position of the flue gas flow direction of each heating surface, and a flow meter is installed on each heating surface.
[0072] In one embodiment, in the calculation module 2, the calculation formula is:
[0073]
[0074] Among them, Q is the heat flow, A is the heat transfer area, and Δt is the temperature difference, that is, the temperature difference measured by the flue gas flow sensor.
[0075] In one embodiment, the acquisition module 3 includes:
[0076] A collection unit, used to collect boiler operating parameters and optimal heat transfer coefficients in a healthy state of the boiler, and store the collection time, boiler operating parameters, and heat transfer coefficients of six heating surfaces in a database as a sample set; wherein the optimal heat transfer coefficient includes the heat transfer coefficients of the six heating surfaces;
[0077] A training unit, used to train an optimal heat transfer coefficient prediction model using the acquisition time and boiler operating parameters in the database as input and the optimal heat transfer coefficient as output; wherein the optimal heat transfer coefficient prediction model is a relationship model between the boiler operating parameters and the optimal heat transfer coefficient of the boiler in an uncoked state;
[0078] In one embodiment, in the collection unit, the boiler health status is the status of the first combustion operation after each boiler coking and ash cleaning process;
[0079] The boiler operating parameters include combustion volume, primary air volume, primary air temperature, secondary air volume, secondary air temperature, feed water volume, and the temperature and pressure of the six heating surfaces.
[0080] In one embodiment, in the comparison module 5, the difference between the operating heat transfer coefficient and the optimal heat transfer coefficient is calculated to determine whether the heat transfer efficiency is attenuated and whether the furnace of the boiler is coked; if coking occurs in the furnace, the heat transfer efficiency of the heating surface will decrease, and the water-cooled wall and other heating surfaces will not be able to cool the flue gas or play a role in temperature control.
[0081] In one embodiment, it further includes:
[0082] The display module visualizes the data of the six heating surfaces in three dimensions to display the results of real-time calculations on the front end;
[0083] If coking occurs in the furnace of the boiler, the coking situation will be presented in the form of data and an alarm signal will be issued to prompt the operating personnel to perform operations such as decoking, soot blowing and combustion parameter optimization.
[0084] The above modules and units are used to execute the corresponding steps in the above monitoring method for determining the coking state of the furnace. The specific implementation method thereof is described in the above method embodiment and will not be repeated here.
[0085] like Figure 4 As shown, the present invention also provides a computer device, which can be a server, and its internal structure can be as shown in Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store all data required for the process of the monitoring method for determining the coking state of the furnace. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the monitoring method for determining the coking state of the furnace is implemented.
[0086] Those skilled in the art will understand that Figure 4 The structure shown in is merely a block diagram of a portion of the structure related to the present application solution and does not constitute a limitation on the computer device to which the present application solution is applied.
[0087] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, any one of the above-mentioned monitoring methods for determining the coking state of a furnace is implemented.
[0088] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0089] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.
[0090] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.
Claims
1. A monitoring method for judging the coking state of a furnace, characterized in that: include: When the boiler is in operation and combustion state, basic data is obtained for each of the six heating surfaces of the boiler; wherein the basic data includes the temperature value of the flue gas before and after passing through the water-cooled wall, the heat flow passing through the heating surface, and the area size of the heating surface; Calculate the operating heat transfer coefficients of the six heating surfaces respectively according to the basic data; Collecting initial data of the boiler in a healthy state, and using the initial data to train an optimal heat transfer coefficient prediction model; Obtain boiler operating parameters under boiler operation and combustion conditions, and use the trained optimal heat transfer coefficient prediction model to obtain the optimal heat transfer coefficient under boiler operation and combustion conditions; The operating heat transfer coefficient is compared with the optimal heat transfer coefficient to determine the decrease in the heat transfer coefficient of the same heating surface, so as to determine whether the furnace of the boiler is coked.
2. The monitoring method for judging the coking state of a furnace according to claim 1, characterized in that: In the step of obtaining basic data for each of the six heating surfaces of the boiler when the boiler is in operation and combustion state, the six heating surfaces include a water-cooled wall, a low-temperature superheater, a partition screen, a final superheater, a low-temperature reheater, and a final reheater. A temperature sensor is provided at the starting position of the flue gas flow direction of each heating surface, and a flow meter is installed on each heating surface.
3. The monitoring method for judging the coking state of a furnace according to claim 1, characterized in that: In the step of respectively calculating the operating heat transfer coefficients of the six heating surfaces according to the basic data, the calculation formula is: Among them, Q is the heat flow, A is the heat transfer area, and Δt is the temperature difference, that is, the temperature difference measured by the flue gas flow sensor.
4. The monitoring method for judging the coking state of a furnace according to claim 1, characterized in that: The step of collecting initial data of the boiler in a healthy state and using the initial data to train an optimal heat transfer coefficient prediction model comprises: Collect boiler operating parameters and optimal heat transfer coefficients when the boiler is in a healthy state, and store the collection time, boiler operating parameters, and heat transfer coefficients of six heating surfaces in a database as a sample set; wherein the optimal heat transfer coefficient includes the heat transfer coefficients of the six heating surfaces; The optimal heat transfer coefficient prediction model is trained with the collection time and boiler operating parameters in the database as input and the optimal heat transfer coefficient as output; wherein the optimal heat transfer coefficient prediction model is a relationship model between the boiler operating parameters and the optimal heat transfer coefficient of the boiler in the uncoked state.
5. The monitoring method for judging the coking state of a furnace according to claim 4, characterized in that: The step of collecting boiler operating parameters and optimal heat transfer coefficients in a healthy state of the boiler, and storing the collection time, boiler operating parameters, and heat transfer coefficients of six heating surfaces in a database as a sample set, wherein the healthy state of the boiler is the state of the first combustion operation after each boiler coking and ash cleaning treatment; The boiler operating parameters include combustion volume, primary air volume, primary air temperature, secondary air volume, secondary air temperature, feed water volume, and the temperature and pressure of the six heating surfaces.
6. The monitoring method for judging the coking state of a furnace according to claim 1, characterized in that: In the step of comparing the operating heat transfer coefficient with the optimal heat transfer coefficient to determine whether the furnace of the boiler is coked, The difference between the operating heat transfer coefficient and the optimal heat transfer coefficient is calculated to determine whether the heat transfer efficiency is attenuated and whether the furnace of the boiler is coked; if coking occurs in the furnace, the heat transfer efficiency of the heating surface will decrease, and the water-cooled wall and other heating surfaces will not be able to cool the flue gas or play a role in temperature control.
7. The monitoring method for judging the coking state of a furnace according to claim 1, characterized in that: After the step of comparing the operating heat transfer coefficient with the optimal heat transfer coefficient to determine whether the furnace of the boiler is coked, the method further includes: The data of the six heating surfaces are visualized in three dimensions to display the results of real-time calculations on the front end; If coking occurs in the furnace of the boiler, the coking situation will be presented in the form of data and an alarm signal will be issued to prompt the operating personnel to perform operations such as decoking, soot blowing and combustion parameter optimization.
8. A monitoring device for judging the coking state of a furnace, characterized in that: include: An acquisition module, used for acquiring basic data for each of the six heating surfaces of the boiler when the boiler is in operation and combustion state; The basic data include the temperature of the flue gas before and after passing through the water-cooled wall, the heat flow through the heating surface, and the area of the heating surface; A calculation module, used to calculate the operating heat transfer coefficients of the six heating surfaces respectively according to the basic data; A collection module, used to collect initial data of the boiler in a healthy state, and use the initial data to train an optimal heat transfer coefficient prediction model; The prediction module is used to obtain the boiler operating parameters under the boiler operating combustion state, and use the trained optimal heat transfer coefficient prediction model to obtain the optimal heat transfer coefficient under the boiler operating combustion state; The comparison module is used to compare the operating heat transfer coefficient with the optimal heat transfer coefficient to determine the decrease in the heat transfer coefficient of the same heating surface to determine whether the furnace of the boiler is coked.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.