A boiler furnace cleaning control system based on CCD imaging recognition

Abstract

The present application belongs to the technical field of boiler furnace cleaning control, and specifically discloses a kind of boiler furnace cleaning control system based on CCD imaging recognition, the system includes: image acquisition module, pollution identification module, grade confirmation module, cleaning control module, residual analysis module and feedback control terminal;The present application realizes the profile type determination and area calculation of the accumulated ash and coking by the thickness, color, texture and other surface texture characteristics in visual image, solves the problem of lack of visual monitoring at present, real-time acquisition of key parameters such as accumulated ash coverage and coking thickness provides quantitative data support for subsequent cleaning control, at the same time, through the analysis based on coking thickness and accumulated ash coverage, combined with the temperature characteristics of infrared thermal map, dynamically upgrade pollution grade, improve the efficiency of cleaning, and through the fusion analysis of infrared temperature data and visual features, avoid the risk of equipment over-temperature caused by pollution grade misjudgment.

Description

Technical Field

[0001] This invention belongs to the field of boiler furnace cleaning control technology, and relates to a boiler furnace cleaning control system based on CCD imaging recognition. Background Technology

[0002] The boiler furnace, as the core combustion space of a coal-fired, oil-fired, or gas-fired boiler, has water-cooled walls and other heating surfaces on its inner walls that transfer the heat released from fuel combustion to the working fluid through heat exchange. During boiler operation, ash, unburned particles, and other substances from the fuel gradually deposit on the heating surfaces, forming ash buildup or coking. Ash buildup reduces the heat transfer efficiency of the heating surfaces, leading to decreased boiler thermal efficiency and increased energy consumption. Coking, if excessive in thickness, can cause the heating surfaces to overheat and rupture, or block the flue, causing abnormal furnace pressure and seriously threatening the safe and stable operation of the boiler. Therefore, precise cleaning control of the boiler furnace is crucial to ensuring the efficient and safe operation of the equipment.

[0003] For example, Chinese invention patent CN108716690A discloses a clean industrial boiler system, whose core structure includes a rectifier unit, an inverter unit, an induced draft fan, a blower, and a PLC control unit. The system achieves furnace control through the following methods: Pressure control logic: The PLC collects furnace pressure signals in real time and adjusts the operating frequency of the induced draft fan and blower through intelligent algorithms to control the air intake and exhaust volume, thereby stabilizing the furnace negative pressure. Hardware configuration: A rectifier unit with a common DC bus and dual inverter units drive the induced draft fan and blower, and communication is achieved through a DP bus. Mechanical structure: The adjusting baffle is fixed at its maximum angle to simplify the mechanical adjustment structure.

[0004] The existing technologies mentioned above have the following shortcomings: 1. Currently, the furnace pressure is controlled only by PLC, without involving the visual monitoring of the internal pollution status of the furnace. It is impossible to obtain key parameters such as the ash thickness and coking area of ​​the furnace heating surface in real time, making it difficult to determine the type and severity of pollution. This results in a lack of data support for cleaning operations, which may lead to over-cleaning or under-cleaning.

[0005] 2. Currently, pressure is controlled only by fixing the angle of the baffle and adjusting the frequency of the fan. No differentiated cleaning strategies are developed for different pollution levels. The cleaning operation relies on preset programs and cannot dynamically adjust parameters such as blowing pressure and duration according to the actual degree of pollution. This results in low cleaning efficiency and serious energy waste. Summary of the Invention

[0006] In view of this, in order to solve the problems mentioned in the background technology, a boiler furnace cleaning control system based on CCD imaging recognition is proposed.

[0007] The objective of this invention can be achieved through the following technical solution: This invention provides a boiler furnace cleaning control system based on CCD imaging recognition, comprising: an image acquisition module, used to divide the interior of the boiler furnace into sub-regions according to the furnace structure characteristics, and to acquire visual images and infrared thermal maps of each sub-region through CCD.

[0008] The contamination identification module is used to extract surface texture features from the visual image and classify the region types of each sub-region.

[0009] The pollution level confirmation module is used to analyze the coking thickness and ash coverage rate based on the area type of each sub-region, and to determine the pollution level of each sub-region by combining infrared thermograms.

[0010] The cleaning control module is used to match the cleaning method based on the pollution level and to perform cleaning control for the cleaning method.

[0011] The residual analysis module is used to trigger secondary image acquisition of each sub-region after cleaning is completed, obtain secondary visual images of each sub-region, and compare them with the baseline cleaning state image to obtain the residual regions.

[0012] The feedback control terminal is used to determine the residual pollution level based on the residual coking thickness and residual ash coverage of each residual area, and then trigger secondary cleaning by combining the location coordinates of each residual area and provide corresponding feedback.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention uses surface texture features such as thickness, color and texture in visual images to determine the contour type of ash accumulation and coking and calculate the area, which solves the current problem of lack of visual monitoring, and obtains key parameters such as ash accumulation coverage and coking thickness in real time, providing quantitative data support for subsequent cleaning control.

[0014] (2) This invention improves the accuracy of contamination identification by using contour type secondary verification and hybrid contour area allocation algorithm, and avoids the problems of over-cleaning or under-cleaning.

[0015] (3) This invention improves the cleaning efficiency by dynamically upgrading the pollution level based on the analysis of coking thickness and ash coverage rate, combined with the temperature characteristics of infrared thermograms. At the same time, the fusion analysis of infrared temperature data and visual features reduces the misjudgment rate of high-temperature coking and avoids the risk of equipment overheating due to misjudgment of pollution level.

[0016] (4) This invention locates the residual area by comparing the secondary visual image with the baseline cleaning state image, and triggers secondary cleaning based on the residual parameters, which solves the current problem of no verification of cleaning effect. Through quantitative evaluation of residual coking thickness and dust coverage, the cleaning compliance rate is improved.

[0017] (5) This invention calculates the coking and ash accumulation levels of the mixed area separately, thereby obtaining the comprehensive pollution level, and combines infrared temperature and low temperature area for level correction, effectively solving the current problem of lack of mixed pollution treatment and improving the cleaning efficiency of mixed pollution areas. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram showing the connections of the various modules in the system of the present invention.

[0020] Figure 2 This is a schematic diagram showing the connection steps of the region type division in this invention.

[0021] Figure 3 This is a schematic diagram showing the connection steps of the residual region analysis in this invention. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] Please see Figure 1 As shown, the present invention provides a boiler furnace cleaning control system based on CCD imaging recognition. The system includes: an image acquisition module, a pollution recognition module, a level confirmation module, a cleaning control module, a residual analysis module, and a feedback control terminal.

[0024] In the above, the pollution identification module is connected to the image acquisition module and the level confirmation module, respectively; the cleaning control module is connected to the level confirmation module and the residual analysis module, respectively; and the residual analysis module is also connected to the feedback control terminal.

[0025] The image acquisition module is used to divide the interior of the boiler furnace into sub-regions according to the furnace structure characteristics, and to acquire visual images and infrared thermal maps of each sub-region using a CCD.

[0026] For example, the division of the region types of each sub-region includes: dividing the furnace into upper, middle and lower three-layer regions along the vertical direction of the furnace based on the spatial distribution of each structural component in the furnace structure features.

[0027] Each layer is divided into several fan-shaped areas according to a preset circumferential angle, and these are used as sub-regions.

[0028] The pollution identification module is used to extract surface texture features from the visual image and classify the region types of each sub-region.

[0029] Please see Figure 2 As shown, exemplarily, the division of region types for each sub-region includes: Q1, determining the contour type of each contour in each sub-region based on the thickness, color, and texture of each contour in each sub-region in the surface texture features.

[0030] Furthermore, determining the contour type of each contour in each sub-region includes: Q1-1, extracting the median value from the thickness range corresponding to the ash accumulation type as the ash accumulation reference thickness.

[0031] It should be added that the method for obtaining the thickness range corresponding to the ash accumulation type is as follows: extract the contour thickness during each boiler furnace cleaning from historical data, and then construct the thickness range corresponding to the ash accumulation type.

[0032] Q1-2. Calculate the similarity between the thickness of each contour and the base thickness of the ash accumulation to obtain the similarity of the ash accumulation thickness of each contour.

[0033] It should be added that the formula for calculating the similarity of the ash accumulation thickness is as follows: In the formula For the similarity of ash accumulation thickness, and These are the outline thickness and the dust accumulation reference thickness, respectively. To set a reference thickness difference, where, The acquisition method is as follows: extract the historical contour thickness difference between the contour thickness and the ash accumulation baseline thickness during each boiler furnace cleaning from historical data, and then select the maximum value as the thickness difference for setting reference.

[0034] Q1-3. Similarly, the similarity of the dust accumulation color and the similarity of the dust accumulation texture of each contour are calculated according to the same method as the calculation of the similarity of the dust accumulation thickness.

[0035] It should be added that the chromaticity value of the gray color and the gray contrast of each contour are extracted from the visual image, and then the gray color similarity and gray texture similarity of each contour are calculated in the same way as the gray thickness similarity calculation method.

[0036] Q1-4. Perform a weighted fusion calculation on the similarity of dust accumulation thickness, dust accumulation color, and dust accumulation texture of each contour to obtain the comprehensive similarity of dust accumulation for each contour.

[0037] It should be added that the analytical formula for the comprehensive similarity of the ash accumulation is as follows: In the formula For the overall similarity of ash accumulation, and These are the similarity of dust accumulation color and the similarity of dust accumulation texture, respectively. , and These represent the weights for similarity in dust accumulation thickness, color, and texture. , .

[0038] It should be added that ash thickness is the core indicator for judging the degree of contamination. A thicker ash layer will significantly affect the heat transfer efficiency of the heated surface, and the thickness is directly related to the difficulty of cleaning, so it has the highest weight. The color of the ash can reflect its composition and deposition time, and color similarity is important for distinguishing between ash and coking, but using it alone as a judgment criterion is prone to misjudgment. For example, the oxide layer on the surface of coking may appear gray, so its weight is assigned to ash thickness. The texture characteristics of ash are greatly affected by particle size and deposition method, and the texture varies significantly under different operating conditions, resulting in poor universality. Therefore, it has the lowest weight and is therefore set to... For ease of analysis, It can specifically take the value 0.5. It can specifically take the value 0.3. The specific value can be 0.2.

[0039] Q1-5. Similarly, the coking similarity of each contour is obtained by analyzing the overall similarity of ash accumulation.

[0040] Q1-6. Compare the overall similarity of ash accumulation and coking of each contour, and select the type with high similarity as the initial type of contour.

[0041] Q1-7. Using the center point of the contour as the center and the preset radius as the radius, delineate the influence range of each contour, and obtain each contour within the influence range as each influence contour. Then, perform secondary verification of the contour type based on each influence contour corresponding to each contour to obtain the contour type of each contour in each sub-region.

[0042] Furthermore, the analysis of each contour type in each sub-region includes: Q1-7-1, based on the initial type of each influencing contour, counting the number of influencing contours consistent with the contour type and the total number of influencing contours, and then using the ratio of the two as the co-validation coefficient of the contour.

[0043] Q1-7-2. Compare the collaborative verification coefficient with the preset verification threshold. When the collaborative verification coefficient is greater than or equal to the preset verification threshold, the initial type of the contour is taken as the contour type of the contour. Otherwise, the mixed type is taken as the contour type of the contour, thereby obtaining the contour type of each contour in each sub-region.

[0044] It should be added that the preset verification threshold is a key parameter used to determine the reliability of contour types, with a value range of [0,1]. Its core function is: when the co-verification coefficient of a contour is ≥ the threshold, it indicates that the initial type of the contour has spatial consistency, and the judgment result is reliable. If the co-verification coefficient < the threshold, it indicates that the contour type differs significantly from the surrounding influencing contours and needs to be classified as a mixed type to avoid misjudgment of a single type. The preset verification threshold is determined through training with historical clean data: a large number of contour samples of known types are collected, their co-verification coefficients are calculated, and the target misjudgment rate is <5%. The optimal threshold, such as 0.75, is determined by constructing an ROC curve.

[0045] Q2. Extract the area of ​​each contour in each sub-region from the surface texture features, and then combine the contour type to obtain the ash accumulation area and coking area of ​​each sub-region.

[0046] Furthermore, the analysis of the ash accumulation area and coking area of ​​each sub-region includes: Q2-1, extracting each contour of the mixed type from the contour type and recording them as each mixed contour.

[0047] Q2-2. Normalize the overall similarity of ash accumulation and coking of each mixed contour to obtain the proportion of ash accumulation and coking of each mixed contour.

[0048] It should be added that the calculation formulas for the normalization process are as follows: and In the formula and These are the percentages of dust accumulation and coking, respectively. and These are the overall similarity scores for ash accumulation and coking, respectively.

[0049] Q2-3. Allocate the area of ​​each mixed contour according to the proportion of ash accumulation and the proportion of coking to obtain the ash accumulation area and coking area of ​​each mixed contour.

[0050] Q2-4. Similarly, according to the method for allocating the ash accumulation area and coking area of ​​each mixed contour, allocate the area of ​​the contour type as ash accumulation and coking, and then obtain the ash accumulation area and coking area of ​​each contour.

[0051] Q2-5. Sum the ash accumulation area and coking area of ​​each contour in each sub-region to obtain the ash accumulation area and coking area of ​​each sub-region.

[0052] Q2-6. Normalize the ash accumulation area and coking area of ​​each sub-region to obtain the ash accumulation coverage rate and coking coverage rate of each sub-region.

[0053] Q3. Normalize the ash accumulation area and coking area of ​​each sub-region to obtain the ash accumulation coverage rate and coking coverage rate of each sub-region.

[0054] Q4. Determine the region type of each sub-region based on the dust accumulation coverage rate and coking coverage rate of each sub-region.

[0055] Furthermore, the determination of the region type of each sub-region includes: Q4-1, if the dust accumulation coverage rate of a certain sub-region is greater than or equal to its preset dust accumulation threshold and the coking coverage rate is less than its preset coking threshold, then the region type of the sub-region is determined to be dust accumulation.

[0056] Q4-2. If the coking coverage rate of a certain sub-region is greater than or equal to its preset coking threshold and the dust accumulation coverage rate is less than its preset dust accumulation threshold, then the region type of the sub-region is determined to be coking.

[0057] Q4-3. If the coking coverage rate of a certain sub-region is less than its preset coking threshold and the ash coverage rate is less than its preset ash threshold, then the region type of the sub-region is determined to be mixed, and the region type of each sub-region is obtained.

[0058] The embodiments of the present invention improve the accuracy of contamination identification by using secondary verification of contour types and a hybrid contour area allocation algorithm, and avoid the problems of over-cleaning or under-cleaning.

[0059] It should be added that the preset ash accumulation threshold is a critical value for determining whether a sub-region is dominated by ash accumulation, and the preset coking threshold is a critical value for determining whether a sub-region is dominated by coking. By quantifying the area ratio of ash accumulation and coking, continuous pollution states are divided into discrete types, providing a basis for decision-making on cleaning strategies. The thresholds are obtained based on historical data. Data on ash accumulation or coking coverage after cleaning is collected under different boiler loads and coal qualities to form a sample set. Based on the sample set, probability density curves of ash accumulation coverage and coking coverage are plotted, and the inflection point of the curve is taken as the threshold.

[0060] This invention uses surface texture features such as thickness, color, and texture in visual images to determine the contour type and calculate the area of ​​ash accumulation and coking, solving the current problem of lack of visual monitoring. It can obtain key parameters such as ash accumulation coverage and coking thickness in real time, providing quantitative data support for subsequent cleaning control.

[0061] The level confirmation module is used to analyze the coking thickness and ash coverage rate based on the area type of each sub-region, and at the same time determine the pollution level of each sub-region by combining infrared thermal images.

[0062] For example, determining the pollution level of each sub-region includes: if the region type of a certain sub-region is coking, then extracting the maximum coking thickness from the surface texture features as the reference coking thickness of the sub-region, and matching it with the coking thickness range corresponding to each coking level to obtain the coking pollution level of the sub-region.

[0063] It should be added that the coking thickness range corresponding to the coking grade is obtained based on historical data. Data on coking thickness of boilers under different operating conditions is collected, and a probability density curve of coking thickness is plotted. The inflection point or quantile of the curve is taken as the interval boundary. For example, in the historical data of a certain boiler, the proportion of coking thickness ≤1mm is 60%, 1-3mm accounts for 30%, and >3mm accounts for 10%. Then the interval is set as follows: low grade is 0-1mm, medium grade is 1-3mm, and high grade is >3mm.

[0064] The highest temperature of the sub-region is obtained from the infrared thermal image and compared with a preset temperature threshold. When the highest temperature is greater than the preset temperature threshold, the coking contamination level is upgraded.

[0065] It should be added that the preset temperature threshold is the critical temperature value for determining the severity of coking in the infrared thermogram. When the temperature of the coking area exceeds the threshold, it indicates that the coking may melt or that the thermal resistance is significant, requiring an upgrade in the contamination level. The method for setting the preset temperature threshold is as follows: obtain historical coking thickness and corresponding infrared temperature data from historical data, establish a "thickness-temperature" mapping relationship, such as a 5°C decrease in wall temperature for every 1mm increase in coking thickness, and then extract the temperature corresponding to moderate coking thickness in the historical data as the threshold.

[0066] It should be added that upgrading the coking contamination level means that when the highest temperature is greater than the preset temperature threshold, the coking contamination level is increased by one level, such as from medium level to high level.

[0067] If the region type of a certain sub-region is dust accumulation, the dust accumulation coverage rate of the sub-region is extracted from the surface texture features, and it is matched with the dust accumulation coverage rate interval corresponding to each dust accumulation level to obtain the dust accumulation pollution level of the sub-region.

[0068] It should be added that the dust accumulation coverage range is the proportion of the dust accumulation area to the total area of ​​the sub-region. This quantifies the degree of dust accumulation and pollution, and matches different purging intensities. For example, heavy dust accumulation requires high-frequency purging. The method for setting the dust accumulation coverage range corresponding to each dust accumulation level is similar to the method for setting the coking thickness range corresponding to the coking level mentioned above, and will not be repeated here.

[0069] The low-temperature coverage area of ​​the sub-region is obtained from the infrared thermal image and compared with a preset low-temperature coverage area threshold. When the low-temperature coverage area is greater than the preset low-temperature coverage area threshold, the dust pollution level is upgraded.

[0070] It should be added that the preset low-temperature coverage area threshold is the critical value of the coverage rate of the low-temperature area in the sub-region of the infrared thermogram. The degree of dust accumulation coverage is verified by the proportion of the low-temperature area, avoiding misjudgment based on a single coverage rate, such as a large area of ​​loose dust but a thin thickness. The method of obtaining it is similar to the method of obtaining the preset temperature threshold mentioned above, and will not be repeated here.

[0071] If a sub-region is classified as mixed, the coking pollution level and ash pollution level of that sub-region are analyzed in the same way as the coking level and ash accumulation level, and the two are taken as the mixed pollution level of that sub-region.

[0072] The highest temperature and low-temperature coverage area of ​​the sub-region are obtained from the infrared thermal map and compared with preset values. When the highest temperature is greater than the preset temperature threshold or the low-temperature coverage area is greater than the preset low-temperature coverage area threshold, the mixed pollution level is upgraded to obtain the pollution level of each sub-region.

[0073] This invention calculates the coking and ash accumulation levels of the mixed area separately to obtain the comprehensive pollution level, and then corrects the level by combining infrared temperature and low temperature area. This effectively solves the current problem of missing mixed pollution treatment and improves the cleaning efficiency of mixed pollution areas.

[0074] This invention improves cleaning efficiency by dynamically upgrading the pollution level based on the analysis of coking thickness and ash coverage, combined with the temperature characteristics of infrared thermograms. At the same time, the fusion analysis of infrared temperature data and visual features reduces the misjudgment rate of high-temperature coking and avoids the risk of equipment overheating due to misjudgment of pollution level.

[0075] The cleaning control module is used to match a cleaning method based on the pollution level and to perform cleaning control for the cleaning method.

[0076] For example, the cleaning control module includes: when the pollution level is a coking pollution level, matching the coking pollution level with the coking cleaning method corresponding to each pollution level to obtain a coking cleaning method.

[0077] Similarly, the matching method for coking cleaning methods is used to obtain the ash accumulation cleaning method and the mixed cleaning method.

[0078] In one specific embodiment, the coking cleaning methods corresponding to the coking contamination levels are as follows: For low levels, pulsed steam purging is used, with a purging pressure set at 0.5-0.8 MPa and a purging time of 10-15 seconds to avoid over-purging and damaging the furnace wall. For medium levels, continuous steam purging is used, with the pressure increased to 0.8-1.2 MPa, combined with alternating operation of a mechanical rapping device, and the purging time extended to 20-30 seconds. For high levels, high-pressure water jet cleaning is used, combined with manual assisted coking removal, while simultaneously lowering the furnace temperature to a safe threshold beforehand.

[0079] The cleaning methods corresponding to different levels of dust accumulation are as follows: Low level: Regular, timed blowing using compressed air at a pressure of 0.3-0.5 MPa, covering the dust-accumulated area. Medium level: Adjusting the blowing angle according to the dust accumulation location, using a rotary sootblower, shortening the blowing cycle to 4 hours, and a pressure of 0.5-0.7 MPa. High level: Synchronous blowing with multiple sootblowers, combined with an acoustic cleaning device, at a frequency of 20-40 kHz and a blowing pressure of 0.7-1.0 MPa; if necessary, increasing the blowing frequency to once every 2 hours.

[0080] Mixed contamination levels: Combining the levels of coking and ash accumulation, prioritize treating the higher level of contamination. For example, if the coking level is higher than the ash level, perform the coking cleaning method first, and then perform the ash cleaning method.

[0081] The residual analysis module is used to trigger secondary image acquisition of each sub-region after cleaning is completed, obtain secondary visual images of each sub-region, and compare them with the baseline cleaning state image to obtain each residual region.

[0082] Please see Figure 3 As shown, exemplarily, the residual region analysis includes: W1, extracting the maximum contour thickness and contour area from the secondary visual image of each sub-region.

[0083] W2. Compare the maximum contour thickness and contour area with the reference thickness threshold and reference contour area threshold corresponding to the reference clean state image, respectively.

[0084] W3. When the maximum contour thickness is greater than the reference thickness threshold or the contour area is greater than the reference contour area threshold, the sub-region is determined to be a residual region, and then each residual region is obtained.

[0085] This invention addresses the current lack of verification of cleaning effectiveness by comparing secondary visual images with baseline clean state images, locating residual areas, and triggering secondary cleaning based on residual parameters. It also improves the cleaning compliance rate through quantitative evaluation of residual coking thickness and dust coverage.

[0086] The feedback control terminal is used to determine the residual pollution level based on the residual coking thickness and residual ash coverage of each residual area, and then trigger secondary cleaning by combining the location coordinates of each residual area and provide corresponding feedback.

[0087] It should be added that the method for determining the residual pollution level is the same as the method for determining the pollution level described above, and will not be repeated here.

[0088] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0089] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0090] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0091] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0092] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0093] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A boiler furnace cleaning control system based on CCD imaging recognition, characterized in that: include: The interior of the boiler furnace is divided into sub-regions according to the structural characteristics of the furnace, and visual images and infrared thermal maps of each sub-region are acquired by CCD. Surface texture features are extracted from the visual image, and the region types of each sub-region are divided. Based on the regional type of each sub-region, the coking thickness and ash coverage rate were analyzed, and the pollution level of each sub-region was determined by combining infrared thermograms. The cleaning method is matched based on the pollution level, and cleaning control is performed for the cleaning method. After cleaning is completed, secondary image acquisition of each sub-region is triggered to obtain secondary visual images of each sub-region, and these images are compared with the baseline clean state image to obtain the residual regions. Based on the residual coking thickness and residual ash coverage of each residual area, the residual pollution level is determined, and then secondary cleaning is triggered in combination with the location coordinates of each residual area, and corresponding feedback is given. Determining the pollution level of each sub-region includes: If the region type of a certain sub-region is coking, the maximum coking thickness is extracted from the surface texture features as the reference coking thickness of the sub-region, and it is matched with the coking thickness range corresponding to each coking level to obtain the coking contamination level of the sub-region. The highest temperature of the sub-region is obtained from the infrared thermal image and compared with a preset temperature threshold. When the highest temperature is greater than the preset temperature threshold, the coking contamination level is upgraded. If the region type of a certain sub-region is dust accumulation, the dust accumulation coverage rate of the sub-region is extracted from the surface texture features and matched with the dust accumulation coverage rate interval corresponding to each dust accumulation level to obtain the dust accumulation pollution level of the sub-region. The low-temperature coverage area of ​​the sub-region is obtained from the infrared thermal image and compared with a preset low-temperature coverage area threshold. When the low-temperature coverage area is greater than the preset low-temperature coverage area threshold, the dust pollution level is upgraded. If the region type of a certain sub-region is mixed, the coking pollution level and ash pollution level of the sub-region are obtained by analogy according to the analysis method of the coking level and ash accumulation level, and the two are taken as the mixed pollution level of the sub-region. The highest temperature and low-temperature coverage area of ​​the sub-region are obtained from the infrared thermal map and compared with preset values. When the highest temperature is greater than the preset temperature threshold or the low-temperature coverage area is greater than the preset low-temperature coverage area threshold, the mixed pollution level is upgraded to obtain the pollution level of each sub-region.

2. The boiler furnace cleaning control system based on CCD imaging recognition according to claim 1, characterized in that: The process of classifying the region types of each sub-region includes: Based on the spatial distribution of structural components in the furnace structure, the furnace is divided into three layers along the vertical direction: upper, middle and lower. Each layer is divided into several fan-shaped areas according to a preset circumferential angle, and these are used as sub-regions.

3. A boiler furnace cleaning control system based on CCD imaging recognition according to claim 1, characterized in that: The process of classifying the region types of each sub-region includes: Q1. Based on the thickness, color, and texture of each contour in each sub-region of the surface texture features, determine the contour type of each contour in each sub-region. Q2. Extract the area of ​​each contour in each sub-region from the surface texture features, and then combine the contour type to obtain the dust accumulation area and coking area of ​​each sub-region. Q3. Normalize the ash accumulation area and coking area of ​​each sub-region to obtain the ash accumulation coverage rate and coking coverage rate of each sub-region. Q4. Determine the region type of each sub-region based on the dust accumulation coverage rate and coking coverage rate of each sub-region.

4. A boiler furnace cleaning control system based on CCD imaging recognition according to claim 3, characterized in that: The determination of the contour type of each contour in each sub-region includes: Extract the median value from the thickness range corresponding to the ash accumulation type as the ash accumulation reference thickness; The similarity between the thickness of each contour and the base thickness of the ash accumulation is calculated to obtain the similarity of the ash accumulation thickness of each contour. Similarly, the similarity of dust accumulation color and dust accumulation texture for each contour is calculated using the same method as the calculation of dust accumulation thickness similarity. The similarity of dust accumulation thickness, dust accumulation color, and dust accumulation texture of each contour is weighted and fused to obtain the comprehensive similarity of dust accumulation for each contour. Similarly, the coking similarity of each contour is obtained by analyzing the comprehensive similarity of ash accumulation. The overall similarity of ash accumulation and coking of each contour are compared, and the type with high similarity is selected as the initial type of contour. Using the center point of the contour as the center and a preset radius as the radius, the influence range of each contour is delineated, and each contour within the influence range is obtained as an influence contour. Then, based on each influence contour corresponding to each contour, the contour type is verified a second time to obtain the contour type of each contour in each sub-region.

5. A boiler furnace cleaning control system based on CCD imaging recognition according to claim 4, characterized in that: The analysis of each contour type in each sub-region includes: Based on the initial type of each influence profile, the number of influence profiles consistent with the profile type and the total number of influence profiles are counted, and then the ratio of the two is used as the co-validation coefficient of the profile. The collaborative verification coefficient is compared with a preset verification threshold. When the collaborative verification coefficient is greater than or equal to the preset verification threshold, the initial type of the contour is taken as the contour type of the contour. Otherwise, the mixed type is taken as the contour type of the contour, thereby obtaining the contour type of each contour in each sub-region.

6. A boiler furnace cleaning control system based on CCD imaging recognition according to claim 3, characterized in that: The analysis of the ash accumulation area and coking area of ​​each sub-region includes: Extract each contour of type mixed from the contour type and record them as each mixed contour; The overall similarity of ash accumulation and coking of each mixed contour are normalized to obtain the proportion of ash accumulation and coking of each mixed contour. The area of ​​each mixed contour is allocated according to the proportion of ash accumulation and the proportion of coking to obtain the ash accumulation area and coking area of ​​each mixed contour. Similarly, the areas of contours with ash accumulation and coking areas are allocated according to the allocation method of each mixed contour, thereby obtaining the ash accumulation area and coking area of ​​each contour. The ash accumulation area and coking area of ​​each contour in each sub-region are summed to obtain the ash accumulation area and coking area of ​​each sub-region. The ash accumulation area and coking area of ​​each sub-region are normalized to obtain the ash accumulation coverage rate and coking coverage rate of each sub-region.

7. A boiler furnace cleaning control system based on CCD imaging recognition according to claim 3, characterized in that: The determination of the region type of each sub-region includes: If the dust accumulation coverage rate of a certain sub-region is greater than or equal to its preset dust accumulation threshold and the coking coverage rate is less than its preset coking threshold, then the region type of the sub-region is determined to be dust accumulation. If the coking coverage rate of a certain sub-region is greater than or equal to its preset coking threshold and the dust accumulation coverage rate is less than its preset dust accumulation threshold, then the region type of the sub-region is determined to be coking. If the coking coverage rate of a certain sub-region is less than its preset coking threshold and the ash coverage rate is less than its preset ash threshold, then the region type of the sub-region is determined to be mixed, and the region type of each sub-region is obtained.

8. A boiler furnace cleaning control system based on CCD imaging recognition according to claim 1, characterized in that: The cleaning control includes: When the pollution level is the coking pollution level, the coking pollution level is matched with the coking cleaning method corresponding to each pollution level to obtain the coking cleaning method. Similarly, the matching method for coking cleaning methods is used to obtain the ash accumulation cleaning method and the mixed cleaning method.

9. A boiler furnace cleaning control system based on CCD imaging recognition according to claim 1, characterized in that: The analysis of each residual region includes: W1. Extract the maximum contour thickness and contour area from the secondary visual images of each sub-region; W2. Compare the maximum contour thickness and contour area with the reference thickness threshold and reference contour area threshold corresponding to the reference clean state image, respectively. W3. When the maximum contour thickness is greater than the reference thickness threshold or the contour area is greater than the reference contour area threshold, the sub-region is determined to be a residual region, and then each residual region is obtained.

Images