Leakage detection method and device for tubular air pre-heater and electronic equipment

Abstract

The embodiment of the invention discloses a leakage detection method and device for a tubular air pre-heater and electronic equipment. The method comprises the steps that in response to pressure information used for representing that negative pressure is generated in a smoke area of the tubular air preheater, infrared thermal imaging images of all pipelines of the tubular air preheater are obtained respectively; the method further comprises the steps of generating a first instruction in response to the fact that a temperature abnormal area exists in the infrared thermal imaging image corresponding to the target pipeline in all the pipelines and single-end plugging information used for representing one-end plugging of the target pipeline is received. In addition, the method further comprises the step of generating a first detection result of the target pipeline based on the contour shape of the flame in the flame image. In the embodiment of the invention, the leaked pipeline can be screened out progressively without manual assistance or only with a small amount of manual assistance, so that the leaked pipeline can be screened out efficiently and accurately without consuming too much manpower, the pipeline is treated in time, and it is ensured that the combustion efficiency of the boiler meets the expectation.

Description

Technical Field

[0001] The embodiments of the present specification belong to the field of tube air preheater detection, and particularly relate to a leakage detection method, device and electronic device for a tube air preheater. Background Art

[0002] A tube air preheater is a heat exchange device that uses the waste heat of the flue gas outside the pipe to heat the air used for combustion inside the pipe. It has a simple structure, high heat transfer efficiency and good sealing performance, and is widely used in power station boilers, especially circulating fluidized bed boilers. However, once the pipe is damaged and leaks, under the action of negative pressure, the air inside the pipe will flow out of the pipe, further reducing the oxygen required for combustion, deteriorating the ignition conditions and ignition process of the fuel, and affecting the combustion efficiency. At the same time, this also increases the additional auxiliary energy consumption. Therefore, it is necessary to detect and block the leakage of the tube air preheater to meet the load-carrying capacity of the unit. Currently, the existing detection methods generally rely on manual detection by listening to sounds and observing. Since there are at least hundreds, or even thousands, of pipes in the tube air preheater, such detection methods not only have low detection accuracy but also low detection efficiency. Summary of the Invention

[0003] The embodiments of the present disclosure provide a leakage detection method, device and electronic device for a tube air preheater, aiming to solve one or more of the above problems and other potential problems.

[0004] According to a first aspect of the present disclosure, a leakage detection method for a tube air preheater is provided. The method includes obtaining infrared thermal imaging images of each pipe of the tube air preheater in response to pressure information indicating that a negative pressure has been generated in the flue gas area of the tube air preheater. The method further includes generating a first instruction to control a detection object to generate a flame at the other end of the target pipe and collecting a flame image in response to the presence of a temperature anomaly area in the infrared thermal imaging image corresponding to the target pipe among the pipes and receiving single-end plugging information indicating that one end of the target pipe has been plugged. In addition, the method further includes generating a first detection result of the target pipe based on the contour shape of the flame in the flame image.

[0005] According to a second aspect of the present disclosure, there is provided a leakage detection device for a tubular air preheater. The device includes an infrared image acquisition module configured to acquire infrared thermal imaging images of each pipe of the tubular air preheater respectively in response to pressure information indicating that a negative pressure has been generated in the flue gas area of the tubular air preheater. The device further includes a flame image acquisition module configured to generate a first instruction to control a detection object to generate a flame at the other end of a target pipe and acquire a flame image in response to the presence of a temperature anomaly area in the infrared thermal imaging image corresponding to the target pipe and receipt of single-end plugging information indicating that one end of the target pipe is plugged. In addition, the device further includes a contour detection module configured to generate a first detection result of the target pipe based on the contour shape of the flame in the flame image.

[0006] According to a third aspect of the present disclosure, there is provided an electronic device including one or more processors and a memory associated with the one or more processors. The memory is used to store program instructions, and when the program instructions are read and executed by the one or more processors, the method provided according to the first solution is executed.

[0007] According to a fourth aspect of the present disclosure, there is provided a computer program product including a computer program, and when the computer program is executed by a processor, the method provided according to the first aspect is implemented.

[0008] It should be understood that the content described in the Summary of the Invention section is not intended to limit the key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In combination with the accompanying drawings and with reference to the following detailed description, the above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent. In the drawings, the same or similar reference numerals denote the same or similar elements, where: Figure 1 A schematic diagram showing an example environment in which multiple embodiments of the present disclosure can be implemented; Figure 2 A flowchart showing the process of a leakage detection method for a tubular air preheater according to some embodiments of the present disclosure; Figure 3 A flowchart showing the overall process of leakage detection of a tubular air preheater according to some embodiments of the present disclosure; Figure 4 A flowchart showing the training process of a contour recognition model according to some embodiments of the present disclosure; Figure 5 A schematic diagram showing the structure of a leakage detection device for a tubular air preheater according to some embodiments of the present disclosure; Figure 6A schematic block diagram of an electronic device according to some embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0010] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in the embodiments of this specification will be clearly and completely described below in combination with the embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0011] The terms "including" and "having" and any variations thereof in this specification and claims and the above drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices. Depending on the context, the word "if" as applied herein can be interpreted as "at..." or "when..." or "in response to determining" or "in response to detecting".

[0012] As mentioned above, in order for the tubular air preheater to produce sufficient heated air for combustion during normal operation, it is necessary to regularly check for damage and leakage of the tubular air preheater. Since the tubular air preheater has a large number of pipes for air supply, the pipes are relatively slender, and the pipes are closely distributed, the traditional process of manual inspection by listening to sounds and observing is not only labor-intensive and inefficient, but also difficult to accurately determine damage and leakage due to the structural characteristics of the pipes, which is prone to false detection and missed detection. This means that even if manual inspections are carried out regularly, air may not be delivered to the boiler in a timely and sufficient manner due to leakage problems, causing the amount of air entering the boiler to be inconsistent with the estimated amount, affecting the boiler load, and further causing the boiler's combustion efficiency to be inconsistent with expectations, requiring longer combustion time, and wasting electricity.

[0013] In view of this, an embodiment of the present disclosure proposes a leakage detection scheme for a tubular air preheater. In the embodiment of the present disclosure, firstly, a negative pressure can be drawn to the flue gas area of the tubular air preheater by an induced draft fan, and an infrared thermal imaging image of each pipe under the negative pressure state can be obtained. For pipes with abnormal temperature areas in the infrared thermal imaging image, they will be regarded as target pipes that may have leaks, and one end of the target pipe will be blocked for further detection. By generating a flame on the unblocked side of the target pipe and collecting a flame image, the leakage state of the target pipe can be judged according to the different contour shapes of the flame, and then the corresponding first detection result can be generated.

[0014] Through the above method, without manual assistance or only a small amount of manual assistance, the target pipes that are preliminarily judged to be possibly leaking can be quickly screened out from each pipe through the temperature abnormal area of the infrared thermal imaging image, and then the target pipes can be blocked unilaterally in a targeted manner to further judge whether each target pipe leaks through the contour shape of the flame image, and a first detection result is generated. In this way, the leaking pipes can be efficiently and accurately screened out without consuming too much manpower, and the pipes can be processed in time to ensure that the combustion efficiency of the boiler meets the expectations when the tubular air preheater is working normally.

[0015] Figure 1 FIG. shows a schematic diagram of an exemplary environment 100 in which multiple embodiments of the present disclosure can be implemented. As Figure 1As shown, the environment 100 may include a terminal 110, a detection object 120, and a tubular air preheater 130. The terminal 110 may be any device with computing or processing capabilities. For example, the terminal 110 may include, but is not limited to, mobile phones, tablets, desktop computers, servers, etc. The detection object 120 may include, but is not limited to, robotic arms, intelligent robots, etc. On the detection object 120, there may be at least installed an ignition unit 121 for generating flames, an infrared unit 122 for obtaining infrared thermal imaging images, and an acquisition unit 123 for collecting flame images. The detection object 120 may be set to one or multiple. The above units may be integrally installed on one detection object 120 or separately installed on different detection objects 120. After starting the induced draft fan installed in the flue gas area of the tubular air preheater 130, a negative pressure will be generated in the flue gas area, causing the terminal 110 to receive the negative pressure information 111. Then, through image recognition, each pipe 112 in the tubular air preheater 130 can be determined, and each pipe 112 can be numbered in sequence, or the coordinates corresponding to each pipe 112 can be determined. According to the differences between the detection object 120 and the infrared unit 122, the infrared unit 122 can be controlled to emit infrared signals to one or multiple pipes 112 simultaneously and collect the infrared thermal imaging images 113 of the pipes 112. After determining the target pipe 114 according to the temperature anomaly area, one end of the target pipe 114 can be temporarily blocked by using a deformable flexible plug in a robotic arm or manual manner, and after the blocking is completed, a single-end blocking information 115 (the single-end blocking information 115 may be text information including the number / coordinate area of the pipe that has completed single-end blocking and the local coordinate area corresponding to the blocked end, generated by operating on the specified app page of the mobile terminal by manual after blocking, or generated by the controller of the robotic arm after the robotic arm completes the single-end blocking operation for the specified coordinate position (i.e., the operation of grasping the flexible plug by image recognition and inserting the flexible plug into the specified coordinate position)) can be fed back to the terminal 110, causing the terminal 110 to generate a first instruction 116, controlling the detection object 120 to generate flames at the unblocked ports of each target pipe 114 in sequence, obtaining the flame images 117, and judging whether the flame deviates towards the inside of the pipe or even extinguishes under the influence of the airflow generated by the negative pressure according to the contour shape 118 of the flame in the flame images 117, so as to generate a first detection result 119 to characterize whether the target pipe 114 leaks, assisting the staff in judging whether it is necessary to process the target pipe 114. Among them, manual assistance can be used to block the target pipe instead of directly using devices such as detection objects and robotic arms to perform intelligent blocking on the pipe. In this way, while ensuring that the workload of the auxiliary detection personnel is small and does not affect the overall detection efficiency, the number of devices to be used or the functional units to be integrated on the devices can be reduced, thereby reducing the cost of the detection process.

[0016] Figure 2 The flowchart of the leakage detection method 200 of the tubular air preheater showing some embodiments of the present disclosure is shown. The method 200 can be executed by the terminal 110, for example. As Figure 2 shown, at block 202, the method 200 can obtain infrared thermal imaging images of each pipe of the tubular air preheater in response to the pressure information indicating that a negative pressure has been generated in the flue gas area of the tubular air preheater. In this embodiment, the induced draft fan originally provided in the flue gas area of the tubular air preheater can be controlled to operate, so that a negative pressure is generated in the flue gas area. After the induced draft fan operates, it can feedback the negative pressure information to the terminal to indicate that a negative pressure has been generated in the flue gas area. The terminal can scan each pipe separately through the infrared unit integrated on the detection object or a separately provided infrared thermal imager to obtain the infrared thermal imaging image corresponding to each pipe. Among them, the infrared thermal imaging image can indicate different temperatures through different colors and show the heat distribution inside the pipe in the image.

[0017] At block 204, the method 200 may generate a first instruction in response to the presence of a temperature anomaly region in the infrared thermal imaging image corresponding to the target pipeline in each of the pipelines and receiving the single-end plugging information used to characterize the plugging of one end of the target pipeline, so as to control the detection object to generate a flame at the other end of the target pipeline and collect a flame image. In this embodiment, if there is no leakage in the pipeline, the negative pressure generated in the flue gas region will not act on the inside of the pipeline, making the temperature distribution of the air inside the pipeline relatively uniform and all within the normal temperature range. However, if there is a leakage in the pipeline, under the action of the negative pressure, the air inside the pipeline will flow towards the leakage location, causing a local temperature anomaly due to the accumulation of cold air or hot flue gas at the leakage location. By calculating the average temperature inside the pipeline and then comparing the regional temperature of each region with the average temperature, it is possible to determine whether there is a temperature anomaly region where the regional temperature significantly deviates from the average temperature in each infrared thermal imaging image. If a certain infrared thermal imaging image has a temperature anomaly region, the pipeline corresponding to this image will be determined as the target pipeline. Considering that the thermal distribution inside the pipeline may not be balanced, and due to environmental and equipment fluctuations, it is impossible to accurately determine whether the pipeline is really leaking solely based on the infrared thermal imaging image, and there is a possibility of false detection. Therefore, after determining the target pipeline, the terminal can generate an indication message to instruct the staff or the detection object to plug one end of the target pipeline with a flexible plug (if the detection is carried out when the unit is out of service, generally the end of the pipeline far from the detection object needs to be plugged. If the detection is carried out when the unit is in operation, generally the side close to the fan needs to be plugged so that the positive pressure generated by the normal operation of the fan will not act on the pipeline for the flame test, ensuring that the air inside the pipeline is stationary under normal circumstances). After the plugging is completed, the staff can send a message through a mobile phone, or the detection object can transmit information through a communication connection to send the single-end plugging information to the terminal. The terminal will generate a first instruction to make the detection object generate a flame at the other end of the target pipeline that is not plugged and collect a flame image. Among them, the reason for first screening the target pipeline through the infrared thermal imaging image instead of directly collecting the flame image is that there are many pipelines in the tubular air preheater. If the flame images of each pipeline are directly collected, each pipeline needs to be plugged at one end. Coupled with the fact that the generation of the flame and the collection of the flame image require a certain amount of time, the overall detection efficiency will be very low. Therefore, after initially screening the pipelines according to the infrared thermal imaging image and then collecting and judging the flame images based on the selected target pipelines, the detection efficiency can be improved, and the time required to restore the tubular air preheater after the detection can also be reduced.

[0018] At block 206, method 200 may generate a first detection result of the target pipeline based on the contour shape of the flame in the flame image. In this embodiment, the contour shape of the flame corresponding in the flame image may be determined by means of a pre-trained contour recognition model or by image recognition to determine the orange-red region representing the flame in the flame image and determining the shape of the orange-red region. When there is no leakage, there is no air flow in the pipeline due to negative pressure, and thus there is no air flow interference with the flame, so that the contour shape of the flame will not show an obvious deviation. Therefore, the state of the flame (i.e., whether the flame is interfered by the air flow) can be judged by the contour shape, and then it can be determined whether the target pipeline leaks, and a corresponding first detection result is generated. As an example, corresponding result information may be set in the database in advance for different contour shapes, and the result information is used to indicate leakage or no leakage. After determining the actual contour shape of the flame, according to the result information corresponding to the contour shape that best matches the actual contour shape in the database, the leakage situation of the target pipeline can be determined, and then the first detection result is generated.

[0019] In this way, it is possible to first quickly screen the target pipelines that may leak in each pipeline according to the infrared thermal imaging image, and then determine the specific leakage situation of the target pipeline according to the contour shape of the flame in the flame image, so as to realize the intelligent detection of pipeline leakage without or with little human effort. Compared with pure manual detection, the detection efficiency is higher and the detection result is more accurate, so as to ensure that all pipeline leaks of the tubular air preheater can be processed in time and ensure that the combustion efficiency of the boiler meets the expectation when the tubular air preheater is working normally.

[0020] Figure 3The flowchart shows the overall process 300 of leakage detection for a tubular air preheater according to some embodiments of the present disclosure. In process 300, after detecting the negative pressure information 111, each pipe of the tubular air preheater can be scanned in turn by means of a detection object or an infrared imager to obtain an infrared thermal imaging image 113 corresponding to each pipe. For any obtained infrared thermal imaging image 113, the image generally represents different temperatures in different colors (i.e., different pixel values), and the temperature represented by a specific color can be directly obtained according to a pre-set pixel value-temperature mapping curve. Therefore, in block 321, according to the infrared thermal imaging image 113, the temperature at each position inside the pipe can be determined, and then the average temperature inside the pipe can be calculated. For a target area where the difference between the regional temperature and the average temperature is greater than the difference threshold, it is considered that the temperature of the target area is significantly abnormal compared with other areas of the pipe. Considering that the inside of the pipe is not completely in thermal equilibrium, the temperature distribution inside the pipe shows a certain degree of volatility, which does not mean that leakage must have occurred as long as there is a target area. The target area temporarily formed due to volatility generally has a small area, while the target area caused by leakage generally has a stable area with a certain size. Therefore, by comparing the area of each target area with the preset area, the interference items generated due to volatility can be excluded, the temperature abnormal area 322 in each infrared thermal imaging image can be determined, and the pipe corresponding to the infrared thermal imaging image 113 with the temperature abnormal area 322 is determined as the target pipe 114.

[0021] As an example, for the operating condition of the unit, if a leak occurs, some cold air will directly enter the flue gas passage without preheating, resulting in a decrease in the flue gas temperature. To maintain the temperature required for combustion, more fuel needs to be consumed, thereby increasing heat loss. At the same time, due to the mixing of cold air, the heat in the flue gas cannot be effectively transferred to the air entering the boiler, resulting in an increase in the flue gas discharge temperature. In addition, the leaked cold air may also reduce the air temperature at the outlet of the air preheater, lowering the temperature of the air entering the boiler and affecting the combustion efficiency and the overall performance of the boiler. Therefore, for the operating condition of the unit, depending on the pressure difference between the air passage and the flue gas passage, it may be that the leaked cold air accumulates in a local area through the leak opening, making the temperature in the area near the leak opening significantly lower than the surroundings, or it may be that the flue gas enters the air passage and accumulates in the area near the leak opening, making the temperature in this area significantly higher than the surroundings. For the condition when the unit is out of service, at this time, the primary air fan and the secondary air fan corresponding to the air passage have been stopped (i.e., the primary air and secondary air regulating dampers are in the closed state), and the leakage of the pipeline will cause the air to communicate with the flue gas side, and then cause the air in the pipeline to flow, forming an air flow from the air side to the flue gas side. Such an air flow will also make the temperature in the area near the leak opening significantly different from the surroundings. The magnitude of the air flow is related to factors such as the leakage area, the pressure difference, and the properties of the fluid. For example, the larger the leakage area and the pressure difference, the greater the air flow velocity and flow rate generated, and at the same time, there will be a certain sound, while the pipeline without leakage is in a static state, no air flow will be formed, and there will be no area with significantly abnormal temperature. Therefore, for the above two conditions, the temperature abnormal area can be determined.

[0022] After determining the target pipeline 114, a processing instruction will be generated for the target pipeline 114 to instruct the staff or the detection object to block one end of the target pipeline 114, so as to avoid the formation of a small amount of air flow due to the connection of the pipelines and affect the result of flame recognition. After the blocking is completed, the single-end blocking information 115 will be received, and based on this, the pipeline with the blocking completed will be determined according to the number / coordinate area in the single-end blocking information 115, and a first instruction 116 will be generated for this pipeline. Under the command control of the first instruction 116, the detection unit will control one end with the ignition unit to move to the unblocked end port of this pipeline, so that the ignition unit generates a flame at this position, and then the flame image 117 will be collected. In the flame image 117, the contour shape 118 of the flame can be extracted, and it can be judged whether the target pipeline 114 leaks according to the contour shape 118. Among them, the extraction of the contour shape 118 can be realized by a pre-trained contour recognition model, or can be directly obtained by directly extracting the edge contour through the difference in pixel values between the flame color and the background color, etc. Exemplarily, the method for judging whether there is a leak, for example, different contour shapes can be set in the database in advance, and different result information can be pre-labeled for each contour shape according to historical test experience or manual experience, etc., to represent whether each contour shape represents a leak or no leak. For the flame without leakage, because there is no interference from the air flow, the flame will basically not show an obvious deviation in any direction. Therefore, the result information corresponding to the contour shape with the flame deviation and the contour shape with an area smaller than the preset area (corresponding to the flame becoming smaller or going out under the influence of the air flow) represents a leak, and the result information corresponding to the remaining contour shapes represents no leak. By determining the result information corresponding to the contour shape that best matches the identified contour shape in the database, it can be determined whether the target pipeline leaks. Among them, the method for determining the contour shape that best matches the identified contour shape in the database can be to calculate the area overlap rate between the contour shapes (that is, the ratio of the intersection area to the union area of the contour shapes), and the contour shape with the highest area overlap rate is the best match, or it can be to calculate the cosine similarity according to the feature vector corresponding to the contour shape, and the contour shape with the cosine similarity closest to 1 is the best match. It can also be to calculate the Hu moment of the contour shape by calling the cv2.HuMoments() function of OpenCV, and take the contour shape with the smallest Hu moment difference as the best match, etc. Another exemplary method for judging whether there is a leak, for example, during the training process of the contour recognition model, the contour shape samples can be pre-labeled to represent whether the contour shape sample represents a leak according to the labeling information. In this way, when the contour shape is obtained according to the trained contour recognition model, the corresponding labeling information indicating whether there is a leak can be directly marked on the contour shape, and it can be directly read from the labeling information on the contour shape whether there is a leak. According to the judgment result of the contour shape 118, a first detection result 343 will be generated to represent the leak detection result of the target pipeline.

[0023] To further improve the accuracy of the detection result, after obtaining the first detection result 343, a second instruction 344 can be generated to stop the negative pressure in the flue gas area. Then, manually or through the operation of the detection object, a pressure sensor is set at any position in the pipeline. To ensure the accuracy of the detection data, the pressure sensor is preferably far away from the vicinity of the unblocked port. In addition, if there is already a pressure sensor in the pipeline for daily data monitoring, the detection can be directly carried out based on this pressure sensor. Then, a positive pressure of a preset pressure is continuously introduced into the air area, that is, the interior of the target pipeline, from the unblocked end of the pipeline through a booster. When the other end of the pipeline is blocked and the pipeline does not leak, the pressure in the pipeline should tend to be stable after a preset time. If the pipeline leaks, the pressure in the pipeline cannot be well maintained near the preset pressure, and there will still be a relatively obvious pressure change after the preset time. Therefore, the pressure change ratio 345 of the target pipeline can be determined by comparing the pressures before and after the preset time, and the second detection result 346 can be generated based on the comparison between the pressure change ratio 345 and the ratio threshold to characterize whether the target pipeline leaks. When the second detection result 346 indicates that the target pipeline leaks, soap water can also be sprayed into the target pipeline manually or by controlling the spraying of the detection object. Under the action of the positive pressure, if there is a leak, the soap water will gather and flow out at the leak point, causing a change in the surface tension of the soap water, and then forming soap bubbles. If there is no leak, the surface tension of the soap water will not change significantly, that is, no soap bubbles will be formed. Therefore, the leak location can also be determined by observing the position of the soap bubbles in the internal image of the pipeline. Finally, the final leak detection result 347 of the target pipeline will be determined by comprehensively considering the first detection result 343 and the second detection result 346. As an example, if both detection results indicate no leak, it is considered that the target pipeline does not leak, and as long as at least one detection result indicates a leak, it is considered that the target pipeline leaks. Among them, to improve the accuracy of the result, for the case where only one detection result indicates a leak, a new round of detection can be carried out again to obtain a new first detection result and a new second detection result. If there is still at least one detection result indicating a leak among the two detection results, it is considered that the target pipeline leaks.

[0024] In box 350, it is also possible to determine whether the target pipeline is leaking according to the first detection result 343 or the leakage detection result 347. In box 360, if the target pipeline is leaking, the leakage position 361 of the target pipeline is determined according to the temperature abnormality area in the infrared thermal imaging image corresponding to the target pipeline. As an example, the midpoint of the area of the inner wall of the pipeline covered by the temperature abnormality area can be determined as the leakage position 361. Then, the distance 362 between the leakage position 361 and the nearest pipeline port is also determined. In addition, in box 380, the database can also pre-set the standard shape of the flame without the interference of the leakage airflow, and by calculating the similarity 381 between the contour shape 118 and the standard shape, the deviation of the actual flame relative to the flame in the standard state can be determined. As an example, the similarity 381 can be determined by obtaining the feature vectors corresponding to the contour shape and the standard shape, and then calculating the Euclidean distance and Pearson correlation coefficient of the feature vectors. The lower the similarity, the greater the deviation, which means that the gap of the leakage is larger, and a higher leakage level 382 will be assigned at this time.

[0025] In frame 370, it is determined whether the distance 362 is less than the preset distance and whether the leakage level is lower than the preset level. Considering that the pipeline cannot be removed from the tubular air preheater alone and the pipeline is long, if the distance 362 is less than the preset distance, it is considered that the leakage position 361 is close to the port, which is convenient for the staff to handle. If the leakage level is also lower than the preset level, it is considered that the leakage gap is not large and can be directly repaired. Therefore, a repair reminder message 371 can be generated to remind the staff to go to the target pipeline to directly repair the leakage position so that the repaired target pipeline can continue to be used normally. If the distance 362 is not less than the preset distance, it is considered that the leakage position 361 is far from the port. Under the structural characteristics of the pipeline, the staff cannot repair the pipeline, or the leakage level is not lower than the preset level, indicating that the leakage gap is large and can no longer be repaired. At this time, a blocking reminder message 372 will be generated to remind the staff to directly block the target pipeline by plugging flexible plugs at both ends of the target pipeline, so that air will not flow into the target pipeline during normal operation. Among them, although the method of blocking the pipes will reduce the amount of air entering the boiler, the specific number of blocked pipes is fixed, and the reduction in air volume can be estimated according to the equipment parameters of the tubular air preheater, and then the combustion volume of the combustibles in the boiler can be adjusted accordingly to ensure that the combustibles in the boiler can be fully burned, the combustion efficiency meets expectations, and avoid additional energy waste. In addition, if the proportion of the number of blocked pipes to the total number of pipes exceeds the preset ratio threshold, the staff can be directly reminded to replace the tubular air preheater.

[0026] After obtaining the repair reminder message 371 or the plugging reminder message 372, according to the different leakage levels 382, the recipients of the repair reminder message or the plugging reminder message will be adjusted. For example, when the leakage level is lower than the preset level, it is considered that the leakage situation is not very serious at this time, and it can be sent to the system used by the staff, so that the system generates a to-do task and waits for the staff to handle it according to the to-do task. If the leakage level is high, it is considered that the leakage situation is relatively serious and needs to be dealt with in a timely manner. It can be directly sent to the mobile phones of the corresponding managers stored in advance, so that the managers can understand the situation in a timely manner and arrange the corresponding personnel to go to handle it.

[0027] Figure 4 The flowchart shows the training process 400 of the contour recognition model for some embodiments of the present disclosure. In process 400, by extracting the flame features from the historical flame images, the flame feature samples 420-1 can be determined. The flame features can include color features, shape features, and texture features. Among them, the color features can be obtained by converting the color space from RGB to HSV or segmenting the pixel region of the flame by color threshold. The shape features can be obtained by identifying the flame boundary through an edge detection algorithm or a Canny edge detector. The texture features can be obtained by means of a gray-level co-occurrence matrix, local binary pattern, etc. In addition, for the historical flame images used for training, the contour shapes can be manually marked on each image in advance, which is used as the contour that is expected to be obtained after contour recognition of the image, and then the contour shape samples 420-2 can be obtained. Among them, the contour shapes in the contour shape samples need to be manually marked to distinguish them from the shape features directly extracted by the edge detection algorithm, and reduce the problem of the decrease in the prediction accuracy of the model caused by the error of the edge detection algorithm. According to the flame feature samples 420-1 and the contour shape samples 420-2, the training samples 420 can be constructed. The initial contour recognition model used for training can be a support vector machine, U-Net, fully convolutional network, or other models. During the process of training the contour recognition model 430 using the training samples 420, the generator 431 of the model can generate a predicted contour shape 432 based on the flame feature samples 420-1. According to the comparison between the contour shape samples 420-2 and the predicted contour shape 432, the generator loss 433 can be obtained. The generator loss 433 can be used to judge the loss of the predicted contour shape 432, and the loss judgment can be made using a comparison loss function. The generator loss 433 can be a larger value, and then the generator loss 433 can be backpropagated to the generator 431 to guide the optimization of the parameters of the generator 431, realizing one round of supervised training of the generator 431. Such a training process can be iteratively executed round by round until the generator 431 can generate a more accurate predicted contour shape 432, that is, until the loss value calculated by the loss function is smaller. After the training is completed, the contour recognition model 430 can output the contour shape 118.

[0028] Figure 5 The structural schematic diagram of the leakage detection device 500 of the tubular air preheater according to some embodiments of the present disclosure is shown. Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments. As Figure 5 shown, the device 500 includes an infrared image acquisition module 501, which is configured to acquire infrared thermal imaging images of each pipe of the tubular air preheater respectively in response to the pressure information indicating that a negative pressure has been generated in the flue gas area of the tubular air preheater. The device further includes a flame image acquisition module 502, which is configured to generate a first instruction to control the detection object to generate a flame at the other end of the target pipe and acquire the flame image in response to the presence of a temperature anomaly area in the infrared thermal imaging image corresponding to the target pipe and the receipt of the single-end plugging information indicating that one end of the target pipe is plugged. In addition, the device further includes a contour detection module 503, which is configured to generate a first detection result of the target pipe based on the contour shape of the flame in the flame image.

[0029] The infrared image acquisition module 501 is further configured to determine, for any infrared thermal imaging image, a target area where the temperature difference between the area temperature and the average temperature inside the pipe is greater than a difference threshold; and determine the target area with an area greater than a preset area as the temperature anomaly area.

[0030] The contour detection module 503 is further configured to generate a second instruction to control the flue gas area to stop generating negative pressure and continuously introduce a positive pressure with a preset pressure into the target pipe; generate a second detection result of the target pipe based on the pressure change ratio of the target pipe within a preset time period; and determine the leakage detection result of the target pipe based on the first detection result and the second detection result.

[0031] The device 500 further includes a leakage location determination module, which is configured to determine the leakage location of the target pipe based on the temperature anomaly area in response to the first detection result indicating the presence of leakage. The device 500 further includes a first information generation module, which is configured to generate a repair reminder information for the leakage location in response to the distance between the leakage location and the nearest port of the target pipe being less than a preset distance. In addition, the device 500 further includes a second information generation module, which is configured to generate a plugging reminder information for the target pipe in response to the distance between the leakage location and the nearest port of the target pipe being not less than a preset distance.

[0032] The device 500 further includes a leakage level calculation module configured to determine the leakage level of the target pipeline based on the similarity between the profile shape and a preset standard shape, where the leakage level is inversely proportional to the similarity. The device 500 further includes a sending object determination module configured to determine the sending object of the repair reminder message or the plugging reminder message based on the leakage level.

[0033] In the device 500, the profile shape is obtained based on a profile recognition model. The device 500 further includes a training sample generation module configured to determine training samples based on historical flame images, where the training samples include flame feature samples and profile shape samples. The device 500 further includes a sample prediction module configured to generate a predicted profile shape from an initial profile recognition model based on the flame feature samples. In addition, the device 500 further includes a model training module configured to perform at least one round of model training on the initial profile recognition model using the profile shape samples as supervision signals to obtain the profile recognition model.

[0034] The training sample generation module includes a sample acquisition unit configured to acquire flame feature samples based on historical flame images. The training sample generation module further includes a profile annotation unit configured to annotate the profile shape in the historical flame images to obtain profile shape samples. In addition, the training sample generation module further includes a training sample construction unit configured to construct training samples based on the flame feature samples and the profile shape samples.

[0035] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this specification are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., Digital Versatile Disc (DVD)), or a semiconductor medium (e.g., Solid State Disk (SSD)), etc.

[0036] Figure 6 A block diagram of an electronic device 600 in which multiple embodiments of the present disclosure can be implemented is shown. As Figure 6 shown, the electronic device 600 includes a processor 610, a disk drive 620, an input / output interface 630, a network interface 640, and a memory 650. The above-mentioned processor 610, disk drive 620, input / output interface 630, network interface 640, and the memory 650 can be communicatively connected through a communication bus 660.

[0037] Among them, the processor 610 can be implemented in ways such as a general-purpose CPU, a microprocessor, an Application-Specific Integrated Circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in this application.

[0038] The memory 650 can be implemented in the form of ROM (Read Only Memory), RAM (Read Access Memory), static memory, dynamic storage devices, etc. The memory 650 can store the operating system 651 for controlling the operation of the electronic device 600, and the basic input / output system (BIOS) 652 for controlling the low-level operations of the electronic device 600. Additionally, it can also store a web browser 653, a data storage management system 654, etc. In short, when implementing the technical solution provided in this application through software or firmware, the relevant program code is stored in the memory 650 and is called and executed by the processor 610.

[0039] The input / output interface 630 is used to connect to the input / output module to achieve information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, a warning light, etc.

[0040] The network interface 640 is used to connect to a communication module (not shown in the figure) to achieve communication and interaction between the device and other devices. Among them, the communication module can achieve communication through wired means (such as USB, network cable, etc.) or through wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0041] The bus 660 includes a path for transmitting information between various components of the device (such as the processor 610, the disk drive 620, the input / input interface 630, the network interface 640, and the memory 650).

[0042] It should be noted that although the above device only shows the processor 610, the disk drive 620, the input / input interface 630, the network interface 640, the memory 650, the bus 660, etc., in the specific implementation process, the device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may only include the components necessary to implement the method of this application and does not necessarily include all the components shown in the figure.

[0043] The program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, a special purpose computer, or other programmable data processing device, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.

[0044] In the context of the present disclosure, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. Additionally, although the operations are depicted in a particular order, this should be understood to require that the operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed to achieve the desired result. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although a number of specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation may also be implemented separately or in any suitable sub-combination in multiple implementations.

[0045] Although the subject matter has been described in language specific to structural features and / or methodological acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A leakage detection method for a tubular air preheater, characterized in that, The method includes: In response to pressure information indicating that a negative pressure has been generated in the flue gas area of the tubular air preheater, obtaining infrared thermal imaging images of each pipeline of the tubular air preheater respectively; In response to the presence of a temperature anomaly area in the infrared thermal imaging image corresponding to a target pipeline among each pipeline, and receiving single-end plugging information indicating that one end of the target pipeline is plugged, generating a first instruction to control a detection object to generate a flame at the other end of the target pipeline and collecting a flame image; and Generating a first detection result of the target pipeline based on the contour shape of the flame in the flame image.

2. The leakage detection method of a tubular air preheater according to claim 1, wherein After respectively obtaining the infrared thermal imaging images of each pipeline of the tubular air preheater, it further includes: For any one of the infrared thermal imaging images, determining a target area where the temperature difference between the area temperature and the average temperature inside the pipeline is greater than a difference threshold; and Determining the target area with an area greater than a preset area as the temperature anomaly area.

3. A leakage detection method for a tubular air preheater according to claim 1 or 2, characterized in that After generating the first detection result of the target pipeline, it further includes: Generating a second instruction to control the flue gas area to stop generating negative pressure and continuously introduce a positive pressure with a preset pressure into the target pipeline; Generating a second detection result of the target pipeline based on the pressure change ratio of the target pipeline within a preset time period; and Determining a leakage detection result of the target pipeline based on the first detection result and the second detection result.

4. A leakage detection method for a tubular air preheater according to claim 1, characterized in that, The method further includes: In response to the first detection result indicating the existence of leakage, determining the leakage location of the target pipeline based on the temperature anomaly area; In response to the distance between the leakage location and the nearest port of the target pipeline being less than a preset distance, generating a repair reminder message for the leakage location; and In response to the distance between the leakage location and the nearest port of the target pipeline being not less than a preset distance, generating a plugging reminder message for the target pipeline.

5. The leak detection method for a tubular air preheater according to claim 4, characterized in that, The method further includes: In response to the first detection result indicating leakage, determining the leakage level of the target pipeline based on the similarity between the contour shape and a preset standard shape, and the leakage level is inversely proportional to the similarity; In response to the distance between the leakage location and the nearest port of the target pipeline being less than a preset distance and the leakage level being lower than a preset level, generating a repair reminder message for the leakage location; In response to the distance between the leakage location and the nearest port of the target pipeline being not less than a preset distance, or the leakage level being not less than the preset level, generating a plugging reminder message for the target pipeline; and Determining the recipient of the repair reminder message or the plugging reminder message based on the leakage level.

6. The leak detection method for a tubular air preheater according to claim 1, characterized in that, The contour shape is obtained based on a contour recognition model; The method further includes: Based on historical flame images, determining training samples, where the training samples include flame feature samples and contour shape samples; Generating a predicted contour shape from an initial contour recognition model based on the flame feature samples; and Using the contour shape samples as a supervision signal to perform at least one round of model training on the initial contour recognition model to obtain a contour recognition model.

7. A leakage detection method for a tubular air preheater according to claim 6, characterized in that, Determining training samples based on historical flame images includes: Obtaining flame feature samples based on historical flame images; Obtaining contour shape samples based on the contour shapes annotated on the historical flame images; and Constructing training samples based on the flame feature samples and the contour shape samples.

8. A leakage detection device for a tubular air preheater, characterized in that, The device includes: An infrared image acquisition module configured to acquire infrared thermal imaging images of respective pipes of the tubular air preheater in response to pressure information indicating that a negative pressure has been generated in the flue gas region of the tubular air preheater; A flame image acquisition module configured to generate a first instruction to control a detection object to generate a flame at the other end of the target pipe and acquire a flame image in response to the presence of a temperature anomaly region in the infrared thermal imaging image corresponding to the target pipe among the respective pipes and receipt of single-end plugging information indicating that one end of the target pipe is plugged; and A contour detection module configured to generate a first detection result of the target pipe based on the contour shape of the flame in the flame image.

9. An electronic device, comprising: One or more processors, and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method for detecting leakage of a tubular air preheater according to any one of claims 1-7.

10. A computer program product, comprising a computer program that, when executed by a processor, implements a method for detecting leakage of a tubular air preheater according to any one of claims 1-7.

Images