Boiler combustion state monitoring and early warning system and method, terminal equipment and storage medium

Abstract

The invention discloses a boiler combustion state monitoring and early warning system and method, terminal equipment and a storage medium, and relates to the technical field of boiler operation. The system comprises a server, a local control subsystem, a flame television subsystem and a distributed control subsystem, the local control subsystem comprises a local control cabinet and a plurality of hearth temperature on-line monitoring devices, and the multiple hearth temperature on-line monitoring devices are located between a main combustion area and a burnout area of a boiler and arranged in a staggered mode; the server can obtain hearth temperature data transmitted by the local control subsystem, flame video data transmitted by the flame television subsystem and combustion data transmitted by the distributed control subsystem, and input the hearth temperature data, the flame video data and the combustion data into a pre-trained neural network model; and the type corresponding to the boiler combustion state is determined, and when the type is combustion deterioration, an oil feeding instruction is sent to the distributed control subsystem. By means of the system, the boiler combustion state can be automatically monitored, and the oil feeding boundary can be accurately judged.

Description

Technical Field

[0001] The present application relates to the technical field of boiler operation, and in particular to a boiler combustion status monitoring and early warning system, method, terminal equipment and storage medium. Background Art

[0002] As the proportion of new energy continues to increase, its intermittent, random and volatile characteristics will quickly consume the flexible adjustment resources of the power system, making deep peak regulation of coal-fired power units the norm, and the risk prevention and control of boiler fire extinguishing during low-load operation has become a pain point.

[0003] At present, the relevant technology relies on manual subjective judgment of the boiler combustion status, but this method is prone to monitoring fatigue, and is also random and lagging, and cannot accurately grasp the timing of oil addition. Adding oil too early will cause fuel waste, while adding oil too late will cause the boiler to extinguish or even explode, posing a safety hazard. Summary of the invention

[0004] In view of the above-mentioned defects or deficiencies in the relevant technology, it is desired to provide a boiler combustion status monitoring and early warning system, method, terminal equipment and storage medium, which can automatically monitor the boiler combustion status and accurately determine the oil injection boundary, realize rapid early warning, and ensure the safe operation of the boiler.

[0005] In a first aspect, the present application provides a boiler combustion state monitoring and early warning system, the boiler combustion state monitoring and early warning system comprising a server, a local control subsystem connected to the server in communication, a flame television subsystem and a distributed control subsystem, the local control subsystem comprising a local control cabinet and a plurality of furnace temperature online monitoring devices connected to the local control cabinet in communication, the plurality of furnace temperature online monitoring devices being located between the main combustion zone and the burnout zone of the boiler and being staggered;

[0006] The server is configured to obtain furnace temperature data transmitted by the local control subsystem, flame video data transmitted by the flame television subsystem and combustion data transmitted by the distributed control subsystem, wherein the furnace temperature data is collected by the multiple furnace temperature online monitoring devices, the furnace temperature data includes furnace temperature and coke loss parameters, the flame video data includes flame image parameters, and the combustion data includes furnace negative pressure, fire detection intensity, furnace oxygen content, superheat / steam drum water level, coal quality parameters and coal shortage parameters; and, input the furnace temperature data, the flame video data and the combustion data into a pre-trained neural network model to determine the corresponding type of boiler combustion state, and when the type is combustion deterioration, send an oil injection instruction and a voice warning instruction to the distributed control subsystem.

[0007] Optionally, in some embodiments of the present application, the server is further configured to construct a temperature array according to the furnace temperature and generate a two-dimensional temperature field that can be displayed on an operation interface.

[0008] Optionally, the server in some embodiments of the present application is specifically used to discretize the corresponding measurement sections of the multiple furnace temperature online monitoring devices at the same height, and calculate the temperature value at the intersection of the measurement paths based on the weight value of the intersection of the measurement paths of each furnace temperature online monitoring device.

[0009] Optionally, in some embodiments of the present application, the server is further configured to determine the boiler coking location and severity based on the coking parameters, and display the boiler coking location and severity on the operation interface, the coking parameters including the slag cleaning frequency and duration of each furnace temperature online monitoring device and the coking location and coke block size detected by the array sensor integrally installed with the furnace temperature online monitoring device.

[0010] Optionally, in some embodiments of the present application, the server is further configured to extract flame image parameters including flickering frequency, brightness and color changes from the flame video data using a pre-trained convolutional variational autoencoder model.

[0011] Optionally, in some embodiments of the present application, the server is further configured to filter and denoise the frame image of the flame video data using an adaptive voting fast median filtering algorithm, and extract the flame area in the frame image using an edge detection and image segmentation algorithm.

[0012] Optionally, the server described in some embodiments of the present application is also configured to determine whether the coal mill is out of coal based on coal outage parameters including mill inlet air volume, mill inlet temperature, mill outlet temperature, mill bowl differential pressure, coal mill current, coal feeder current and coal feeder belt speed, and to issue an early warning prompt when the coal is out of coal.

[0013] In a second aspect, the present application provides a boiler combustion state monitoring and early warning method, the boiler combustion state monitoring and early warning method is used for a server of the boiler combustion state monitoring and early warning system described in any one of the first aspects, the boiler combustion state monitoring and early warning method comprising:

[0014] Obtaining furnace temperature data transmitted by the local control subsystem, flame video data transmitted by the flame television subsystem, and combustion data transmitted by the distributed control subsystem, wherein the furnace temperature data is collected by the multiple furnace temperature online monitoring devices, the furnace temperature data includes furnace temperature and coke drop parameters, the flame video data includes flame image parameters, and the combustion data includes furnace negative pressure, fire detection intensity, furnace oxygen content, superheat / steam drum water level, coal quality parameters, and coal failure parameters;

[0015] The furnace temperature data, the flame video data and the combustion data are input into a pre-trained neural network model to determine the corresponding type of the boiler combustion state, and when the type is combustion deterioration, an oil injection instruction and a voice warning instruction are sent to the distributed control subsystem.

[0016] In a third aspect, the present application provides a terminal device, comprising a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the instruction, the program, the code set or the instruction set is loaded and executed by the processor to implement the steps of the boiler combustion status monitoring and early warning method described in the second aspect.

[0017] In a fourth aspect, the present application provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the boiler combustion status monitoring and early warning method described in the second aspect.

[0018] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0019] The embodiment of the present application provides a boiler combustion state monitoring and early warning system, method, terminal equipment and storage medium. The system includes a server, an on-site control subsystem connected to the server in communication, a flame television subsystem and a distributed control subsystem. The on-site control subsystem includes an on-site control cabinet and a plurality of furnace temperature online monitoring devices connected to the on-site control cabinet in communication. The plurality of furnace temperature online monitoring devices are located between the main combustion zone and the burnout zone of the boiler and are staggered. Thus, multi-dimensional information such as furnace temperature data transmitted by the on-site control subsystem, flame video data transmitted by the flame television subsystem and combustion data transmitted by the distributed control subsystem can be obtained in real time through the server. Then, the furnace temperature data, flame video data and combustion data can be input into a pre-trained neural network model to automatically determine the corresponding type of the boiler combustion state. The system has strong reliability. When the type is deteriorating combustion, the system can quickly send oil injection instructions and broadcast voice early warning instructions to the distributed control subsystem, thereby realizing rapid early warning, avoiding boiler fire extinguishing and ensuring safe operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1A structural block diagram of a boiler combustion status monitoring and early warning system provided in an embodiment of the present application;

[0022] Figure 2 A distribution diagram of a furnace temperature online monitoring device provided in an embodiment of the present application;

[0023] Figure 3 A partial structural diagram of a furnace temperature online monitoring device provided in an embodiment of the present application;

[0024] Figure 4 A schematic diagram of the overall structure of an online furnace temperature monitoring device provided in an embodiment of the present application;

[0025] Figure 5 A schematic diagram of a two-dimensional temperature field displayed on an operation interface provided in an embodiment of the present application;

[0026] Figure 6 A schematic diagram of a measurement cross-section discrete result provided in an embodiment of the present application;

[0027] Figure 7 A schematic diagram of a radiation energy transfer process in an air layer provided in an embodiment of the present application;

[0028] Figure 8 A schematic diagram of a convolutional variational autoencoder model training process provided in an embodiment of the present application;

[0029] Fig. 9 A flow chart of a boiler combustion state monitoring and early warning method provided in an embodiment of the present application;

[0030] Fig.10 A structural block diagram of a terminal device provided in an embodiment of the present application.

[0031] Reference numerals:

[0032] 100- boiler combustion status monitoring and early warning system, 101- server, 102- local control subsystem, 1021- local control cabinet, 1022- furnace temperature online monitoring equipment, 103- flame television subsystem, 104- distributed control subsystem, A- fire peephole, B- automatic slag cleaning mechanism, C- manual slag cleaning mechanism, 200- terminal equipment, 201- processor, 202- memory. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0034] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0035] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. Figures 1 to 10 The boiler combustion status monitoring and early warning system, method, terminal device and storage medium provided in the embodiments of the present application are explained in detail.

[0036] Please refer to Figure 1 , which is a structural block diagram of a boiler combustion state monitoring and early warning system provided in an embodiment of the present application. The boiler combustion state monitoring and early warning system 100 includes a server 101, a local control subsystem 102 connected to the server 101 in communication, a flame television subsystem 103 and a distributed control subsystem 104 (Distributed Control System, DCS), and the local control subsystem 102 includes a local control cabinet 1021 and a plurality of furnace temperature online monitoring devices 1022 connected to the local control cabinet 1021 in communication. Among them, the plurality of furnace temperature online monitoring devices 1022 are located between the main combustion zone and the burnout zone of the boiler and are staggered, such as Figure 2 As shown in the figure, two measuring points are arranged on each of the four walls of the water-cooled wall in the furnace combustion area, for a total of eight measuring points. The furnace temperature online monitoring device 1022 is a short-wave high-temperature infrared radiation temperature measuring device with a temperature measuring range of 400°C to 1600°C, a temperature measuring resolution of 0.1°C, and a measuring error of no more than ±25°C. Figure 3 As shown in the figure, each measuring point has a fire peep hole A with a diameter of 10.5 mm on the water-cooled wall fin, which is used for the sensor to receive the high-temperature flue gas radiation in the furnace for measurement. The measuring point is not installed in the form of a water-cooled wall elbow, which is cost-effective and does not require a lot of maintenance work. Figure 4 As shown, each furnace temperature online monitoring device 1022 is equipped with an electric automatic slag cleaning mechanism B. If coke slag blocks the fire peep hole A, it can automatically determine and execute the slag cleaning procedure and the timed slag cleaning function (time adjustable) to keep the measuring optical path unobstructed. In addition, a manual slag cleaning mechanism C is also configured for emergency use.

[0037] In actual use, the server 101 of the embodiment of the present application can obtain the furnace temperature data transmitted by the local control subsystem 102, the flame video data transmitted by the flame television subsystem 103, and the combustion data transmitted by the distributed control subsystem 104, wherein the furnace temperature data is collected by multiple furnace temperature online monitoring devices 1022, the furnace temperature data includes but is not limited to furnace temperature and coke loss parameters, etc., the flame video data includes flame image parameters, and the combustion data includes but is not limited to furnace negative pressure, fire detection intensity, furnace oxygen content, superheat / steam drum water level, coal quality parameters and coal shortage parameters, etc., and then the furnace temperature data, flame video data and combustion data are input into the pre-trained neural network model to determine the corresponding type of boiler combustion state, and when the type is combustion deterioration, that is, the process of various indicators from stable to unstable, the distributed control subsystem 104 is sent to send oil injection instructions and broadcast voice warning instructions, and when the type is on the verge of extinguishing or has been extinguished, the distributed control subsystem 104 is sent to prohibit the oil gun injection alarm to prevent explosion and affect the safety of the boiler. For example, the neural network model can be a back propagation (BP) neural network model. In the model training stage, firstly, the historical data of boiler operation parameters related to nine dimensions, such as furnace temperature, coke drop parameters, flame image parameters, furnace negative pressure, fire detection intensity, furnace oxygen content, superheat / drum water level, coal quality parameters and coal shortage parameters, are collected and data cleaning is performed. Secondly, the combustion state is classified by expert knowledge and 70% of the historical data is divided into a training set, 15% into a validation set and 15% into a test set. The neural network is designed again, the input layer contains 9 nodes, multiple hidden layers are set, and the output layer uses a Sigmoid activation function to obtain the judgment result of the combustion state. Finally, the cross entropy loss and Adam optimizer are selected to train the network and monitor the performance on the validation set, so as to adjust the learning rate, increase the number of iterations for stopping training, etc., to avoid overfitting, and use the test set to evaluate the model performance, pay attention to indicators such as classification accuracy, recall rate and precision, and repeatedly adjust the model parameters or redesign the network structure according to the results.

[0038] Furthermore, the server 101 of the embodiment of the present application can also construct a temperature array according to the furnace temperature and generate a two-dimensional temperature field that can be displayed on the operation interface, such as Figure 5 For example, the server may discretize the corresponding measurement sections of multiple furnace temperature online monitoring devices 1022 at the same height, and calculate the temperature value at the intersection of the measurement path based on the weight value of the intersection of the measurement path of each furnace temperature online monitoring device 1022, such as Figure 6 The temperature value at each intersection of the measurement paths shown can represent the temperature of the corresponding grid area, that is,

[0039]

[0040] In formula (1), T M represents the temperature value measured by the Mth measurement path, a i represents the temperature value at the intersection i of the measurement path, b Mi represents the weight value of the i-th measurement path intersection in the temperature data of the M-th measurement path, and N represents the number of measurement path intersections.

[0041] For M measurement paths, we have

[0042]

[0043] Expressed in vector form as

[0044] T=B·a (3)

[0045] In formula (3), T = [T1, T2, T3 ... T M ] T is an M×1 matrix, which is recorded by the furnace temperature online monitoring equipment output, B is an M×N matrix, and the weighted coefficient matrix on the entire measurement section is

[0046]

[0047] And as Figure 7 As shown, according to Bell's law, when the temperature and pressure of the gas are constant, it can be expressed as

[0048] I s =I0e -ks (5)

[0049] In formula (5), s represents the distance from the intersection of the measurement path to the measurement point, in meters; I0 represents the radiation intensity at the gas interface x = 0, I s It represents the radiation intensity at distance s, in units of W / sr.μm; k represents the radiation attenuation coefficient, which can be approximately regarded as the weight value b Mi , which is determined by the triatomic gas radiation attenuation coefficient k q , ash particle radiation attenuation coefficient k h , coke particle radiation attenuation coefficient k t , Carbon black particle radiation attenuation coefficient k th The radiation attenuation coefficient is composed of the sum of the radiation attenuation coefficients. The unit of the radiation attenuation coefficient is 1 / (m·MP). The influence of carbon black particles between the main combustion zone and the burnout zone is relatively weak. th Take 0. Furthermore, the triatomic gas radiation attenuation coefficient k q Calculated by the following formula,

[0050]

[0051] In formula (6), represents the volume fraction of water vapor in flue gas, r n represents the total volume fraction of the triatomic gas; It represents the flue gas temperature at the furnace outlet, in K; p represents the partial pressure of triatomic gas in the flue gas, approximately 0.1MPa.

[0052] When the thermal radiation passes through the ash-containing gas, part of the radiation is absorbed by the ash particles, and part of the radiation is diffracted on the surface of the ash particles. The ash particle radiation attenuation coefficient k h Calculated by the following formula,

[0053]

[0054] In formula (7), ρ y represents the flue gas density, μ represents the ash particle density, the unit is kg / m 3 ; T1 * Indicates the flue gas temperature at the furnace outlet, in K; d h It represents the average diameter of ash particles in μm. It is selected according to the type of coal and coal mill. For cylindrical ball mill, 13μm is selected.

[0055] Coke particles have strong radiation ability, and their radiation attenuation coefficient is mainly related to the coke concentration. The radiation attenuation coefficient of coke particles k t Calculated by the following formula,

[0056] k t =10x1x2 (8)

[0057] In formula (8), x1 represents the influence coefficient of combustion type, which is 1 for anthracite and lean coal, and 0.5 for high-reactivity fuels such as bituminous coal and lignite; x2 represents the influence coefficient of combustion mode, which is 0.1 for pulverized coal furnace and 0.03 for grate-fired furnace.

[0058] When solving the linear equations of the temperature values ​​measured by the measurement path and the temperature values ​​at the intersection of the measurement path, each measurement path corresponds to one equation, and the change of the weighting coefficient may produce an ill-conditioned system of equations. It is necessary to determine whether the established system of equations is an ill-conditioned system of equations. Since the radiation attenuation coefficient k is a function of temperature, it will affect the solution of the equation. Therefore, when solving, the initial corresponding temperature value of the k value in the temperature weighting coefficient of each measurement path intersection is first set to the average value of the corresponding path measurement value. The condition number is one of the indicators to distinguish the ill-conditioning of the matrix. Problems with condition numbers near 1 are called well-conditioned problems, problems with high condition numbers are called ill-conditioned problems, and problems with condition numbers tending to infinity are singular problems. The condition number is improved by adding a regularization term, thereby completing an approximate estimate of the solution. In addition, the embodiment of the present application can also increase the influence of the temperature measurement lens measurement angle on the basis of the radiation attenuation coefficient k, so that the calculation of the weight value is more accurate.

[0059] Furthermore, for example, the server 101 of the embodiment of the present application can also determine the position and severity of boiler coking based on the coking parameters, and display the position and severity of boiler coking on the operation interface, wherein the coking parameters include but are not limited to the slag cleaning action frequency and slag cleaning action duration of each furnace temperature online monitoring device 1022 and the coking position and coke block size detected by the array sensor installed integrally with the furnace temperature online monitoring device 1022. For another example, the server 101 of the embodiment of the present application can also filter and denoise the frame image of the flame video data through an adaptive voting fast median filtering algorithm, and use edge detection and image segmentation algorithms to extract flame areas in the frame image and other pre-processing, and then use a pre-trained convolutional variational autoencoder (CVAE) model to extract flame image parameters including flickering frequency, brightness and color changes from the flame video data. The model training process is as follows: Figure 8 As shown. Under stable combustion conditions, the convolutional variational autoencoder model is trained on the flame image. The advantage of this setting is that it can not only use deep neural networks to mine flame image features, but also use variational inference theory to improve the model's ability to reconstruct unstable combustion images. Only stable working condition images are needed to overcome the problem of insufficient unstable combustion samples. For example, the server 101 of the embodiment of the present application can also determine whether the coal mill is out of coal based on the coal-out parameters including mill inlet air volume, mill inlet temperature, mill outlet temperature, mill bowl differential pressure, mill current, coal feeder current and coal feeder belt speed, and issue an early warning prompt when the coal is out of coal.

[0060] The boiler combustion state monitoring and early warning system provided in the embodiment of the present application includes a server, an on-site control subsystem connected to the server in communication, a flame television subsystem and a distributed control subsystem. The on-site control subsystem includes an on-site control cabinet and a plurality of furnace temperature online monitoring devices connected to the on-site control cabinet in communication. The plurality of furnace temperature online monitoring devices are located between the main combustion zone and the burnout zone of the boiler and are staggered. Thus, multi-dimensional information such as furnace temperature data transmitted by the on-site control subsystem, flame video data transmitted by the flame television subsystem and combustion data transmitted by the distributed control subsystem can be obtained in real time through the server. Then, the furnace temperature data, flame video data and combustion data can be input into a pre-trained neural network model to automatically determine the corresponding type of the boiler combustion state. The system has strong reliability, and when the type is deteriorating combustion, it can quickly send oil injection instructions and broadcast voice early warning instructions to the distributed control subsystem, thereby realizing rapid early warning, avoiding boiler fire extinguishing and ensuring safe operation.

[0061] Based on the above embodiments, the present application provides a boiler combustion state monitoring and early warning method, which can be used for Figures 1 to 8The server 101 of the boiler combustion state monitoring and early warning system 100 in the corresponding embodiment. Fig. 9 , which is a flow chart of a boiler combustion state monitoring and early warning method provided in an embodiment of the present application, the method specifically comprises the following steps:

[0062] S101, acquiring furnace temperature data transmitted by the local control subsystem, flame video data transmitted by the flame television subsystem and combustion data transmitted by the distributed control subsystem, wherein the furnace temperature data is collected by multiple furnace temperature online monitoring devices.

[0063] Exemplarily, the furnace temperature data in the embodiment of the present application includes but is not limited to furnace temperature and coke drop parameters, the flame video data includes flame image parameters, and the combustion data includes but is not limited to furnace negative pressure, fire detection intensity, furnace oxygen content, superheat / steam drum water level, coal quality parameters and coal outage parameters, etc.

[0064] S102, input the furnace temperature data, flame video data and combustion data into the pre-trained neural network model to determine the corresponding type of the boiler combustion state, and when the type is combustion deterioration, send an oil injection instruction and a voice warning instruction to the distributed control subsystem.

[0065] For example, in the embodiment of the present application, when the type is imminent fire extinguishing or has been extinguished, an alarm prohibiting the use of oil guns can also be sent to the distributed control subsystem, thereby preventing explosions and affecting boiler safety.

[0066] It should be noted that, for the description of the same steps and the same contents in this embodiment as those in other embodiments, reference can be made to the description in other embodiments and will not be repeated here.

[0067] The boiler combustion status monitoring and early warning method provided in the embodiment of the present application obtains multi-dimensional information such as furnace temperature data transmitted by the local control subsystem, flame video data transmitted by the flame television subsystem and combustion data transmitted by the distributed control subsystem in real time through the server, and then the furnace temperature data, flame video data and combustion data can be input into a pre-trained neural network model to automatically determine the corresponding type of the boiler combustion status, with strong reliability, and when the type is combustion deterioration, it can quickly send oil injection instructions and broadcast voice warning instructions to the distributed control subsystem, thereby realizing rapid warning, avoiding boiler fire extinguishing and ensuring safe operation.

[0068] Based on the above embodiments, the present application provides a terminal device. Fig.10 The terminal device 200 may include a processor 201 and a memory 202. The memory 202 stores at least one instruction, at least one program, code set or instruction set, which is loaded and executed by the processor 201 to implement Fig. 9 The steps of the boiler combustion state monitoring and early warning method in the corresponding embodiment.

[0069] As another aspect, the present application provides a computer-readable storage medium for storing program code, the program code for executing the aforementioned Fig. 9 The steps of the boiler combustion state monitoring and early warning method in the corresponding embodiment.

[0070] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0071] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms. The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0072] In addition, each functional module in each embodiment of the present application may be integrated into a processing unit, or each module may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium.

[0073] Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the whole or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the boiler combustion state monitoring and early warning method of each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0074] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0075] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A boiler combustion status monitoring and early warning system, characterized in that: The boiler combustion state monitoring and early warning system comprises a server, a local control subsystem connected to the server in communication, a flame television subsystem and a distributed control subsystem, wherein the local control subsystem comprises a local control cabinet and a plurality of furnace temperature online monitoring devices connected to the local control cabinet in communication, wherein the plurality of furnace temperature online monitoring devices are located between the main combustion zone and the burnout zone of the boiler and are staggered; The server is configured to obtain furnace temperature data transmitted by the local control subsystem, flame video data transmitted by the flame television subsystem and combustion data transmitted by the distributed control subsystem, wherein the furnace temperature data is collected by the multiple furnace temperature online monitoring devices, the furnace temperature data includes furnace temperature and coke loss parameters, the flame video data includes flame image parameters, and the combustion data includes furnace negative pressure, fire detection intensity, furnace oxygen content, superheat / steam drum water level, coal quality parameters and coal shortage parameters; and, input the furnace temperature data, the flame video data and the combustion data into a pre-trained neural network model to determine the corresponding type of boiler combustion state, and when the type is combustion deterioration, send an oil injection instruction and a voice warning instruction to the distributed control subsystem.

2. The boiler combustion status monitoring and early warning system according to claim 1 is characterized in that: The server is also configured to construct a temperature array according to the furnace temperature and generate a two-dimensional temperature field that can be displayed on an operation interface.

3. The boiler combustion status monitoring and early warning system according to claim 2 is characterized in that: The server is specifically used to discretize the corresponding measurement sections of the multiple furnace temperature online monitoring devices at the same height, and calculate the temperature value at the intersection of the measurement path based on the weight value of the intersection of the measurement path of each furnace temperature online monitoring device.

4. The boiler combustion status monitoring and early warning system according to claim 2 is characterized in that: The server is also configured to determine the boiler coking location and severity based on the coking parameters, and display the boiler coking location and severity on the operation interface, wherein the coking parameters include the slag cleaning frequency and duration of each furnace temperature online monitoring device and the coking location and coke block size detected by the array sensor integrated with the furnace temperature online monitoring device.

5. The boiler combustion status monitoring and early warning system according to any one of claims 1 to 4, characterized in that: The server is also configured to extract flame image parameters including flickering frequency, brightness and color changes from the flame video data using a pre-trained convolutional variational autoencoder model.

6. The boiler combustion status monitoring and early warning system according to claim 5 is characterized in that: The server is also configured to filter and denoise the frame image of the flame video data using an adaptive voting fast median filtering algorithm, and extract the flame area in the frame image using an edge detection and image segmentation algorithm.

7. The boiler combustion status monitoring and early warning system according to claim 5 is characterized in that: The server is also configured to determine whether the coal mill is out of coal based on coal outage parameters including mill inlet air volume, mill inlet temperature, mill outlet temperature, mill bowl differential pressure, mill current, coal feeder current and coal feeder belt speed, and issue an early warning prompt when the coal is out of coal.

8. A boiler combustion status monitoring and early warning method, characterized in that: The boiler combustion state monitoring and early warning method is used for a server of the boiler combustion state monitoring and early warning system according to any one of claims 1 to 7, and the boiler combustion state monitoring and early warning method comprises: Obtaining furnace temperature data transmitted by the local control subsystem, flame video data transmitted by the flame television subsystem, and combustion data transmitted by the distributed control subsystem, wherein the furnace temperature data is collected by the multiple furnace temperature online monitoring devices, the furnace temperature data includes furnace temperature and coke drop parameters, the flame video data includes flame image parameters, and the combustion data includes furnace negative pressure, fire detection intensity, furnace oxygen content, superheat / steam drum water level, coal quality parameters, and coal failure parameters; The furnace temperature data, the flame video data and the combustion data are input into a pre-trained neural network model to determine the corresponding type of the boiler combustion state, and when the type is combustion deterioration, an oil injection instruction and a voice warning instruction are sent to the distributed control subsystem.

9. A terminal device, characterized in that: The terminal device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set or instruction set, and the instruction, the program, the code set or the instruction set is loaded and executed by the processor to implement the steps of the boiler combustion status monitoring and early warning method according to claim 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the boiler combustion state monitoring and early warning method according to claim 8.

Images