Boiler furnace flame temperature monitoring system and method and storage medium

Abstract

The invention relates to a boiler furnace flame temperature monitoring system and method and a storage medium, and is applied to the technical field of flame temperature monitoring. The system comprises a hyperspectral camera and a temperature monitoring module; the hyperspectral camera is used for collecting spectral data of boiler furnace flame in real time; and the temperature monitoring module is used for acquiring key parameter data during operation of the boiler and analyzing and processing the spectral data and the key parameter data to obtain the temperature of the boiler furnace flame. The accuracy of flame temperature monitoring can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of flame temperature monitoring, and particularly relates to a boiler furnace flame temperature monitoring system, method and storage medium. Background Art

[0002] For large-scale coal-fired power station boilers, real-time monitoring of the furnace flame temperature is of great significance for the reliability, safety and economy of boiler operation. In related technologies, a thermocouple-based contact point measurement technology can be used to monitor the furnace flame temperature. Since the furnace is in a high-temperature, high-dust and large-section combustion condition, the working environment of the sensor is relatively harsh, and the furnace temperature is inferred by calculation, resulting in low accuracy. Moreover, contact sensors have problems such as easy coking, frequent replacement and large maintenance workload. Summary of the Invention

[0003] In order to solve the above technical problems, the present application provides a boiler furnace flame temperature monitoring system, method, storage medium and computer program product.

[0004] According to a first aspect of the present application, there is provided a boiler furnace flame temperature monitoring system, including: a hyperspectral camera and a temperature monitoring module;

[0005] The hyperspectral camera is configured to collect spectral data of the boiler furnace flame in real time;

[0006] The temperature monitoring module is configured to obtain key parameter data during the operation of the boiler, analyze and process the spectral data and the key parameter data, and obtain the temperature of the boiler furnace flame.

[0007] Optionally, the system further includes: an angle adjustment module and a servo motor;

[0008] The angle adjustment module is configured to receive an angle control instruction;

[0009] The servo motor is configured to adjust the angle of the hyperspectral camera according to the angle control instruction;

[0010] The hyperspectral camera is specifically configured to collect spectral data of the flames at multiple positions in the boiler furnace based on the adjusted angle in real time;

[0011] The temperature monitoring module is specifically configured to analyze and process the spectral data of the flames at multiple positions in the boiler furnace and the key parameter data, and obtain the temperatures of the flames at multiple positions in the boiler furnace.

[0012] Optionally, the temperature monitoring module is specifically configured to process the spectral data of the flames at multiple positions in the boiler furnace and the key parameter data through a pre-trained flame temperature determination model to obtain the temperatures of the flames at multiple positions in the boiler furnace.

[0013] Optionally, the temperature monitoring module is specifically configured to perform denoising and normalization processing on the spectral data of the flames at multiple positions in the boiler furnace to obtain the normalized spectral data of the flames at multiple positions in the boiler furnace, extract target features from the normalized spectral data to obtain target spectral features; and process the target spectral features of the flames at multiple positions in the boiler furnace and the key parameter data through a pre-trained flame temperature determination model to obtain the temperatures of the flames at multiple positions in the boiler furnace.

[0014] Optionally, a full-spectrum glass is installed on the window of the hyperspectral camera, and the absorption rate of the full-spectrum glass is less than a preset absorption rate.

[0015] Optionally, the system further includes: a display terminal;

[0016] The display terminal is configured to generate a temperature distribution map in real time according to the temperature of the boiler furnace flame and display the temperature distribution map.

[0017] According to a second aspect of the present application, there is provided a method for monitoring the temperature of a boiler furnace flame, the method including:

[0018] Collecting the spectral data of the boiler furnace flame in real time;

[0019] Obtaining the key parameter data during the operation of the boiler;

[0020] Analyzing and processing the spectral data and the key parameter data to obtain the temperature of the boiler furnace flame.

[0021] Optionally, the collecting the spectral data of the boiler furnace flame in real time includes:

[0022] Receiving an angle control instruction and adjusting the angle of the hyperspectral camera according to the angle control instruction;

[0023] Using the hyperspectral camera and based on the adjusted angle, collecting the spectral data of the flames at multiple positions in the boiler furnace in real time;

[0024] The analyzing and processing the spectral data and the key parameter data to obtain the temperature of the boiler furnace flame includes:

[0025] Analyze and process the spectral data of the flames at multiple positions in the boiler furnace and the key parameter data to obtain the temperatures of the flames at multiple positions in the boiler furnace.

[0026] Optionally, the analyzing and processing the spectral data of the flames at multiple positions in the boiler furnace and the key parameter data to obtain the temperatures of the flames at multiple positions in the boiler furnace includes:

[0027] Process the spectral data of the flames at multiple positions in the boiler furnace and the key parameter data through a pre-trained flame temperature determination model to obtain the temperatures of the flames at multiple positions in the boiler furnace.

[0028] Optionally, the analyzing and processing the spectral data of the flames at multiple positions in the boiler furnace and the key parameter data to obtain the temperatures of the flames at multiple positions in the boiler furnace includes:

[0029] Denoise and normalize the spectral data of the flames at multiple positions in the boiler furnace to obtain the normalized spectral data of the flames at multiple positions in the boiler furnace;

[0030] Extract target features from the normalized spectral data to obtain target spectral features;

[0031] Process the target spectral features of the flames at multiple positions in the boiler furnace and the key parameter data through a pre-trained flame temperature determination model to obtain the temperatures of the flames at multiple positions in the boiler furnace.

[0032] Optionally, a full-spectrum glass is installed on the window of the hyperspectral camera, and the absorption rate of the full-spectrum glass is less than a preset absorption rate.

[0033] Optionally, the method further includes:

[0034] Generate a temperature distribution map in real time according to the temperature of the boiler furnace flame and display the temperature distribution map.

[0035] According to the third aspect of the present application, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in the second aspect is implemented.

[0036] According to the fourth aspect of the present application, there is provided a computer program product, which when running on a computer causes the computer to execute the method described in the second aspect.

[0037] The technical solution provided by the embodiments of the present application has the following advantages compared with the prior art:

[0038] By collecting key parameter data during the operation of the boiler in real time and using a hyperspectral camera to collect spectral data of the boiler furnace flame in real time; analyzing and processing the spectral data and key parameter data to obtain the temperature of the boiler furnace flame. In the embodiments of the present application, since the spectral information emitted by the object is used to determine the temperature of the flame, compared with monitoring the temperature of the flame using the flame radiation image, the influence of factors such as image noise and uneven illumination can be eliminated, thereby improving the accuracy of temperature monitoring. The hyperspectral camera has a fast response speed and can capture the spectral information emitted by the object in real time. Therefore, it can monitor the change of the flame temperature in real time and can be applied to temperature measurement in various different occasions, applicable to various ranges from low temperature to high temperature and harsh environments, etc. In addition, the boiler furnace flame temperature monitoring system adopts non-contact measurement, is not easily affected by factors such as equipment aging and wear, is relatively stable, and avoids potential safety hazards to the measurement personnel in high-temperature environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with the present application and, together with the specification, are used to explain the principles of the present application.

[0040] To more clearly illustrate the technical solutions in the embodiments of the present application or in the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0041] Figure 1 It is a schematic structural diagram of a boiler furnace flame temperature monitoring system in the embodiments of the present application;

[0042] Figure 2 It is a schematic diagram of the marked points in the plan view of the boiler furnace looking down;

[0043] Figure 3 It is another schematic structural diagram of a boiler furnace flame temperature monitoring system in the embodiments of the present application;

[0044] Figure 4 It is a flowchart of a method for monitoring the temperature of a boiler furnace flame in the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] In order to be able to more clearly understand the above-mentioned objects, features and advantages of the present application, the following will further describe the solutions of the present application. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0046] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present application, rather than all of the embodiments.

[0047] See Figure 1 , Figure 1 FIG. 1 is a schematic structural diagram of a boiler furnace flame temperature monitoring system according to an embodiment of the present application. The boiler furnace flame temperature monitoring system 100 includes: a hyperspectral camera 101 and a temperature monitoring module 102.

[0048] The wavelength band of the hyperspectral camera 101 is in the visible light and near-infrared range. Its core is a CMOS (Complementary Metal Oxide Semiconductor) spectral imaging chip, which can integrate more than a hundred thousand spectrometers. By taking a single photo, accurate spectral information of different positions of the furnace flame can be obtained. The hyperspectral camera 101 is used to collect spectral data of the boiler furnace flame in real time.

[0049] The temperature monitoring module 102 is connected to the hyperspectral camera 101 and the control system. It is used to receive the spectral data transmitted by the hyperspectral camera 101 and the key parameter data input from the control system, analyze and process the spectral data and the key parameter data, and obtain the temperature of the boiler furnace flame.

[0050] The control system is located outside the boiler furnace flame temperature monitoring system 100 and can collect key parameter data during the operation of the boiler in real time. Among them, the key parameter data mainly refers to the combustion conditions of the boiler, which may include: fuel type, fuel calorific value, ventilation volume, fuel flow rate, etc.

[0051] For the boiler furnace flame temperature monitoring system according to the embodiment of the present application, since the spectral information emitted by an object is used to determine the temperature of the flame, compared with monitoring the temperature of the flame by using the flame radiation image, the influence of factors such as image noise and uneven illumination can be eliminated, thereby improving the accuracy of temperature monitoring. The hyperspectral camera has a fast response speed and can capture the spectral information emitted by an object in real time. Therefore, it can monitor the change of the flame temperature in real time and can be applied to temperature measurement in various different occasions, applicable to various ranges from low temperature to high temperature and harsh environments, etc. In addition, the boiler furnace flame temperature monitoring system uses non-contact measurement, is not easily affected by factors such as equipment aging and wear, is relatively stable, and avoids potential safety hazards to measurement personnel in high-temperature environments.

[0052] Since flue gas is generated during the operation of the boiler, the hyperspectral camera 101 cannot be directly installed on the top of the boiler, but on the side of the boiler. Different ventilation volumes, fuels, etc. will affect the flame height and range. In the embodiments of the present application, in order to ensure that the hyperspectral camera 101 can capture the entire flame surface, the boiler furnace flame temperature monitoring system 100 may further include: an angle adjustment module and a servo motor. In this way, the angle of the hyperspectral camera 101 can be adjusted through the mutual cooperation of the hyperspectral camera 101, the angle adjustment module and the servo motor.

[0053] Among them, the angle adjustment module is used to receive an angle control instruction. The servo motor is used to adjust the angle of the hyperspectral camera according to the angle control instruction to ensure that the camera view completely covers the furnace flame. The hyperspectral camera 101 is specifically used to collect spectral data of flames at multiple positions in the boiler furnace in real time based on the adjusted angle.

[0054] For example, when the flame surface rises, the angle adjustment module can receive a downward rotation instruction, and the servo motor controls itself to rotate downward according to this downward rotation instruction, so that the flame surface covers the entire camera lens. On the contrary, when the flame surface drops, the angle adjustment module can receive an upward rotation instruction, and the servo motor controls itself to rotate upward according to this upward rotation instruction, so that the flame surface covers the entire camera lens. Usually, the fuel type, ventilation volume, etc. will not change for a long time, so the fluctuation of the flame surface height is very small, and the servo motor generally will not change for a long time.

[0055] In the case where the hyperspectral camera 101 collects spectral data of flames at multiple positions, the temperature monitoring module 102 can analyze and process the spectral data and key parameter data of flames at multiple positions in the boiler furnace to obtain the temperatures of flames at multiple positions in the boiler furnace.

[0056] Optionally, the temperature monitoring module 102 is specifically used to process the spectral data and key parameter data of flames at multiple positions in the boiler furnace through a pre-trained flame temperature determination model to obtain the temperatures of flames at multiple positions in the boiler furnace.

[0057] Among them, the training method of the flame temperature determination model can be:

[0058] First, obtain a training data set. The training data set includes: sample flame spectral data, sample key parameter data, and the sample flame temperature corresponding to each group of sample flame spectral data and sample key parameter data. The sample flame spectral data and sample key parameter data are input data, and the sample flame temperature corresponding to the sample flame spectral data and sample key parameter data is label data. The training data set can be divided into a training set, a validation set, and a test set. The proportion of the training set, the validation set, and the test set can be, for example, 6:2:2, etc.

[0059] Among them, the sample flame spectral data can be collected by the hyperspectral camera 101, and the sample key parameter data can be collected by using different types of devices according to the type of data. The sample flame temperature can be measured by using an ultra-high temperature thermocouple.

[0060] Secondly, construct a network structure according to the input data and label data. For example, a CNN (Convolutional Neural Network) structure suitable for flame temperature prediction can be constructed. The CNN structure can include an input layer, a convolutional layer, a pooling layer, a fully connected layer, etc. The number of nodes in the input layer is the dimension of the input data (i.e., the sample flame spectral data and the sample key parameter data); the convolutional layer can extract the features of the input data; the pooling layer can reduce the size of the feature map, thereby reducing the amount of calculation; the fully connected layer can classify or regress the features of the previous layer.

[0061] Initialize the model parameters, send the training data set into the model in batches for forward propagation to obtain the predicted values, substitute the predicted values and the actual values (i.e., the label data) into the loss function to calculate the error between the predicted values and the actual values, that is, the loss value, update the model parameters according to the backpropagation error, and verify on the validation set to ensure that the model does not overfit or underfit. If the stop condition is met (such as reaching the preset maximum number of iterations or the performance on the validation set no longer improves), the training ends. During this process, an appropriate loss function (such as mean square error or mean absolute error, etc.) and an optimizer (such as Adam or RMSprop) can be selected to guide the model training.

[0062] After the training is completed, the test set can be used to evaluate the model performance. Specifically, according to the key evaluation metrics (such as mean square error, mean absolute error, and R 2 score, etc.), the performance of the model can be evaluated. If the performance of the model is poor, the model structure and parameters can be adjusted according to the evaluation results to improve the performance of the model, so as to achieve higher prediction accuracy.

[0063] Optionally, the temperature monitoring module 102 can perform denoising and normalization processing on the spectral data of the flames at multiple positions in the boiler furnace to obtain the normalized spectral data of the flames at multiple positions in the boiler furnace, extract the target spectral features from the normalized spectral data, and obtain the target spectral features; through a pre-trained flame temperature determination model, process the target spectral features and key parameter data of the flames at multiple positions in the boiler furnace to obtain the temperatures of the flames at multiple positions in the boiler furnace.

[0064] Spectral data may be subject to noise interference. Therefore, denoising processing can be performed before modeling. For example, smoothing method and median filtering method can be used for denoising. In addition, for spectral data, the numerical range differences between different channels are relatively large, which may affect the convergence speed and performance of the model. Therefore, the denoised spectral data can also be normalized so that the numerical ranges of each channel are the same, enabling the model to converge quickly and improving the performance of the model. For example, maximum-minimum normalization and standardization can be used to normalize the spectral data.

[0065] In the embodiments of the present application, useful features (i.e., target spectral features) can also be extracted from the normalized spectral data as the model input to improve the accuracy and robustness of the model. For example, principal component analysis method can be used to extract target spectral features, etc.

[0066] Optionally, the boiler furnace flame temperature monitoring system 100 may further include: a display terminal. The display terminal is used to generate a temperature distribution map in real time according to the temperature of the boiler furnace flame and display the temperature distribution map.

[0067] As mentioned above, since the hyperspectral camera integrates hundreds of thousands of spectrometers, the spectral data of the flames at multiple positions in the boiler furnace can be accurately obtained in one photo. Assuming 9 positions are selected to monitor the temperatures of the flames at these 9 positions, then during model training, the temperatures of the flames at these 9 positions can be labeled. Of course, the more labeled points during training, the more positions can be monitored after the model training is completed. The model can train data in different regions, thereby improving the accuracy of the temperatures at all positions on the entire flame plane. Refer to Figure 2 , Figure 2 which is a schematic diagram of the labeled points in the top view plan of the furnace. It can be seen that the temperatures of the flames at 81 positions are selected for labeling, and these 81 positions form a 9×9 two-dimensional plane. During real-time monitoring, the temperatures of the flames at these 81 positions can be monitored.

[0068] It can be understood that the more positions are selected, the larger the amount of data used for model training, resulting in a larger computational amount and a slower training speed. Therefore, an appropriate number of positions can be selected for labeling and monitoring according to the actual scenario.

[0069] The temperature of the flame in the coal-fired power plant furnace is generally between 900°C and 1200°C. The temperature distribution map can set color mapping to represent different temperature values, and add legends, titles, and other annotations for easy viewing and understanding.

[0070] The steps to construct the temperature distribution map are as follows:

[0071] (1) Organize the output of hundreds of thousands of temperature values into a structured format to ensure that each data point has its corresponding X and Y coordinates;

[0072] (2) Preprocess the data to eliminate outliers and missing values, and use interpolation techniques to complete the data;

[0073] (3) Create a grid according to the measurement range, and divide the X-axis and Y-axis into a certain number of equally spaced intervals;

[0074] (4) Select a suitable plotting tool and the preprocessed temperature data to generate a two-dimensional temperature distribution map;

[0075] (5) After the temperature data is updated, repeat steps (1) and (2), and use the updated data and the determined grid to regenerate the two-dimensional temperature distribution map. The animation function in the plotting library can be used to achieve dynamic update of the distribution map.

[0076] In the embodiments of the present application, the appropriate refresh frequency can be determined according to the actual application scenario and the change speed of the temperature value, so that the program runs continuously and the latest two-dimensional temperature distribution map is displayed after each update.

[0077] See Figure 3 , Figure 3 FIG. is another structural schematic diagram of the boiler furnace flame temperature monitoring system in the embodiments of the present application. The boiler furnace flame temperature monitoring system 300 includes: a hyperspectral camera 301, a servo 302, a temperature monitoring module 303, a heat dissipation device 304, a heat dissipation device 305, a heat dissipation device 306, a window 307 of the hyperspectral camera 301, and a chassis 308.

[0078] The hyperspectral camera 301 can collect the spectral data of the flame and transmit the spectral data to the temperature monitoring module 303.

[0079] The servo 302 can adjust the angle of the hyperspectral camera 301 to ensure that the viewing angle of the hyperspectral camera 301 fully covers the furnace flame.

[0080] The key parameter data is transmitted to the temperature monitoring module 303 via a twisted pair. The key parameter data mainly refers to the combustion conditions of the boiler, which can include: fuel type, fuel calorific value, ventilation volume, fuel flow rate, etc.

[0081] The temperature monitoring module 303 stores a pre-trained model, can receive the spectral data transmitted by the hyperspectral camera 301, receive the key parameter data transmitted in real time by the external control system, perform data processing and calculation, output temperature data, store data, etc. The output temperature data can be transmitted to the display terminal via a twisted pair and the temperature data is displayed on the display terminal.

[0082] The heat dissipation devices 304, 305, and 306 can be small refrigerators to ensure that the boiler furnace flame temperature monitoring system 300 is within the operating temperature.

[0083] The window 307 of the hyperspectral camera is installed with a full-spectrum glass, and the absorption rate of the full-spectrum glass is less than the preset absorption rate. Full-spectrum means that the absorption rate of this glass for the spectra of all bands is almost the same, and low loss means that its absorption rate is low, generally less than 10%. Assuming the absorption rate is 10%, when the hyperspectral camera 301 receives the light intensity of 100 Lux from the boiler flame (the light intensities of different bands are different), after adding the glass, the hyperspectral camera 301 receives the light intensity of 90 Lux. Since the glass is full-spectrum, the loss of each band is fixed, so it will not have a great impact on the spectral data and subsequent data analysis. Therefore, by installing the full-spectrum glass, it can hardly affect the acquisition of the flame spectral information, and can prevent dust from entering the device, avoiding affecting the service life of the device.

[0084] The chassis 308 can be made of aluminum alloy or steel.

[0085] In the boiler furnace flame temperature monitoring system according to the embodiment of the present application, a hyperspectral camera is used to collect the spectral data of the boiler furnace flame in real time, and the temperature of the boiler furnace flame is monitored according to the spectral data. Since the spectral data is not affected by other factors such as light, the accuracy of temperature monitoring can be improved. The hyperspectral camera has a fast response speed and can capture the spectral information emitted by an object in real time. Therefore, it can monitor the change of the flame temperature in real time and can be applied to temperature measurement in various different occasions, applicable to various ranges from low temperature to high temperature and harsh environments, etc. In addition, the boiler furnace flame temperature monitoring system adopts non-contact measurement and is not easily affected by factors such as equipment aging, wear, and coking, and is relatively stable. And a full-spectrum glass is installed on the window of the hyperspectral camera. Therefore, while not affecting the spectral data, the service life of the hyperspectral camera is extended.

[0086] Corresponding to the above system embodiment, the embodiment of the present application also provides a method for monitoring the temperature of the boiler furnace flame, see Figure 4 , the method for monitoring the temperature of the boiler furnace flame may include the following steps:

[0087] Step S402, collect the spectral data of the boiler furnace flame in real time.

[0088] Step S404, obtain the key parameter data during boiler operation.

[0089] Step S406, analyze and process the spectral data and the key parameter data to obtain the temperature of the boiler furnace flame.

[0090] Optionally, using a hyperspectral camera to collect the spectral data of the boiler furnace flame in real time includes:

[0091] Receive an angle control instruction, and adjust the angle of the hyperspectral camera according to the angle control instruction;

[0092] Using a hyperspectral camera and based on the adjusted angles, spectral data of flames at multiple positions in the boiler furnace are collected in real time;

[0093] Analyze and process the spectral data and key parameter data to obtain the temperature of the boiler furnace flame, including:

[0094] Analyze and process the spectral data and key parameter data of flames at multiple positions in the boiler furnace to obtain the temperatures of flames at multiple positions in the boiler furnace.

[0095] Optionally, analyze and process the spectral data and key parameter data of flames at multiple positions in the boiler furnace to obtain the temperatures of flames at multiple positions in the boiler furnace, including:

[0096] Process the spectral data and key parameter data of flames at multiple positions in the boiler furnace through a pre-trained flame temperature determination model to obtain the temperatures of flames at multiple positions in the boiler furnace.

[0097] Optionally, process the spectral data and key parameter data of flames at multiple positions in the boiler furnace to obtain the temperatures of flames at multiple positions in the boiler furnace, including:

[0098] Denoise and normalize the spectral data of flames at multiple positions in the boiler furnace to obtain the normalized spectral data of flames at multiple positions in the boiler furnace;

[0099] Extract target features from the normalized spectral data to obtain target spectral features;

[0100] Process the target spectral features and key parameter data of flames at multiple positions in the boiler furnace through a pre-trained flame temperature determination model to obtain the temperatures of flames at multiple positions in the boiler furnace.

[0101] Optionally, a full-spectrum glass is installed on the window of the hyperspectral camera, and the absorption rate of the full-spectrum glass is less than a preset absorption rate.

[0102] Optionally, the above method for monitoring the temperature of the boiler furnace flame further includes:

[0103] According to the temperature of the boiler furnace flame, generate a temperature distribution map in real time and display the temperature distribution map.

[0104] The specific details of each step in the above method have been described in detail in the corresponding system, so they will not be elaborated here.

[0105] In an embodiment of the present application, there is also provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned method for monitoring the flame temperature in a boiler furnace is implemented.

[0106] It should be noted that the computer-readable storage medium shown in the present application may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable storage medium may be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable storage medium can be transmitted by any appropriate medium, including but not limited to: wireless, wire, optical cable, radio frequency, etc., or any suitable combination of the above.

[0107] In an embodiment of the present application, there is also provided a computer program product. When the computer program product runs on a computer, the computer is enabled to execute the above-mentioned method for monitoring the flame temperature in a boiler furnace.

[0108] It should be noted that in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

[0109] The above are only specific embodiments of the present application, enabling those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A boiler furnace flame temperature monitoring system, characterized in that, it includes: a hyperspectral camera and a temperature monitoring module; the hyperspectral camera is used to collect spectral data of the boiler furnace flame in real time; the temperature monitoring module is used to obtain key parameter data during the operation of the boiler, analyze and process the spectral data and the key parameter data, and obtain the temperature of the boiler furnace flame.

2. The system according to claim 1, characterized in that, the system further includes: an angle adjustment module and a servo motor; the angle adjustment module is used to receive an angle control instruction; the servo motor is used to adjust the angle of the hyperspectral camera according to the angle control instruction; the hyperspectral camera is specifically used to collect spectral data of the flames at multiple positions in the boiler furnace based on the adjusted angle in real time; the temperature monitoring module is specifically used to analyze and process the spectral data of the flames at multiple positions in the boiler furnace and the key parameter data, and obtain the temperatures of the flames at multiple positions in the boiler furnace.

3. The system according to claim 2, characterized in that, the temperature monitoring module is specifically used to process the spectral data of the flames at multiple positions in the boiler furnace and the key parameter data through a pre-trained flame temperature determination model, and obtain the temperatures of the flames at multiple positions in the boiler furnace.

4. The system according to claim 2, characterized in that, the temperature monitoring module is specifically used to denoise and normalize the spectral data of the flames at multiple positions in the boiler furnace, obtain the normalized spectral data of the flames at multiple positions in the boiler furnace, extract target features from the normalized spectral data, and obtain target spectral features; through a pre-trained flame temperature determination model, process the target spectral features of the flames at multiple positions in the boiler furnace and the key parameter data, and obtain the temperatures of the flames at multiple positions in the boiler furnace.

5. The system according to claim 1, characterized in that, a full-spectrum glass is installed on the window of the hyperspectral camera, and the absorption rate of the full-spectrum glass is less than a preset absorption rate.

6. The system according to claim 1, characterized in that, the system further includes: a display terminal; the display terminal is used to generate a temperature distribution map in real time according to the temperature of the boiler furnace flame and display the temperature distribution map.

7. A method for monitoring the temperature of a boiler furnace flame, characterized in that, the method includes: collecting spectral data of the boiler furnace flame in real time; obtaining key parameter data during the operation of the boiler; analyzing and processing the spectral data and the key parameter data to obtain the temperature of the boiler furnace flame.

8. The method according to claim 7, characterized in that, the step of collecting spectral data of the boiler furnace flame in real time includes: receiving an angle control instruction and adjusting the angle of the hyperspectral camera according to the angle control instruction; using the hyperspectral camera and collecting spectral data of the flames at multiple positions in the boiler furnace in real time based on the adjusted angle. Analyzing and processing the spectral data and the key parameter data to obtain the temperature of the boiler furnace flame includes: Analyzing and processing the spectral data and the key parameter data of the flames at multiple positions in the boiler furnace to obtain the temperatures of the flames at multiple positions in the boiler furnace.

9. The method according to claim 8, characterized in that the analyzing and processing the spectral data and the key parameter data of the flames at multiple positions in the boiler furnace to obtain the temperatures of the flames at multiple positions in the boiler furnace includes: denoising and normalizing the spectral data of the flames at multiple positions in the boiler furnace to obtain the normalized spectral data of the flames at multiple positions in the boiler furnace; extracting target features from the normalized spectral data to obtain target spectral features; processing the target spectral features and the key parameter data of the flames at multiple positions in the boiler furnace through a pre-trained flame temperature determination model to obtain the temperatures of the flames at multiple positions in the boiler furnace.

10. A computer-readable storage medium, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the method according to any one of claims 7 to 9 is implemented.

Images