A method for inspecting and testing a boiler pressure vessel

Abstract

The present application relates to a kind of boiler pressure vessel inspection detection method, it is related to pressure detection technical field.The method mainly includes: with the image of the outer surface of the boiler pressure vessel that obtains applied magnetic powder or penetrant liquid;According to the outer surface image, determine whether the outer surface of the boiler pressure vessel appears crack;If it is determined that the outer surface of the boiler pressure vessel does not appear crack, then according to the ultrasonic data of the boiler pressure vessel, ray data determine whether the inner surface of the boiler pressure vessel appears crack;If the inner surface of the boiler pressure vessel appears crack and / or the outer surface of the boiler pressure vessel appears crack, then according to the operating data of the boiler pressure vessel and overall physical data are simulated simulation is obtained simulation simulation model, and the physical data of the region position area that appears crack is input into simulation simulation model and simulated simulation is obtained simulation simulation crack result;According to simulation simulation crack result and the crack that position area appears, determine the final crack result that the boiler pressure vessel appears.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pressure detection, in particular to a boiler pressure vessel inspection method. BACKGROUND

[0002] With the continuous development of China's industrial technology, the application of boiler pressure vessels is becoming more and more widespread, and their safe operation is attracting more and more attention. In order to ensure the safe operation of the boiler pressure vessel, it is necessary to carry out regular inspection, but in the actual inspection process, due to the complex structure of the boiler pressure vessel, various faults are prone to occur, leading to accidents. In order to effectively avoid accidents, it is necessary to strengthen the regular detection of the boiler pressure vessel, so as to ensure its safe operation.

[0003] In the production and manufacturing process of the boiler pressure vessel, a large number of materials and parts are generally used, and it operates under high temperature and high pressure conditions. Once a crack occurs, it will cause a serious accident. Therefore, crack is one of the main faults of the boiler pressure vessel.

[0004] At present, the internal and external surfaces of the boiler pressure vessel are detected by the inspection department of the boiler pressure vessel, which is completely manual. The inspector holds a flashlight and a hammer and keeps shining and knocking. For the internal surface of the boiler pressure vessel, the detection efficiency of the existing boiler pressure vessel is low. SUMMARY

[0005] The present application aims to provide a boiler pressure vessel inspection method to solve the problems existing in the prior art. The technical problems to be solved by the present application are solved by the following technical solutions.

[0006] The present application provides a boiler pressure vessel inspection method, which comprises:

[0007] Applying magnetic powder or penetrating liquid to the outer surface of the boiler pressure vessel to obtain an outer surface image of the boiler pressure vessel to which the magnetic powder or the penetrating liquid is applied;

[0008] Determining whether a crack appears on the outer surface of the boiler pressure vessel according to the outer surface image;

[0009] If it is determined that no crack appears on the outer surface of the boiler pressure vessel, obtaining ultrasonic wave data and ray data of the boiler pressure vessel;

[0010] Determining whether a crack appears on the inner surface of the boiler pressure vessel according to the ultrasonic wave data and the ray data of the boiler pressure vessel;

[0011] If the inner surface of the boiler pressure vessel has cracks and / or the outer surface of the boiler pressure vessel has cracks, area physical data of the position area of the inner surface and / or the outer surface of the boiler pressure vessel having cracks is acquired;

[0012] A simulation model is obtained by simulation according to the operation data and the overall physical data of the boiler pressure vessel, and the physical data of the position area having cracks is input into the simulation model to obtain a simulation crack result by simulation;

[0013] The final crack result of the boiler pressure vessel is determined according to the simulation crack result and the cracks in the position area.

[0014] In an optional embodiment, the determination of whether the outer surface of the boiler pressure vessel has cracks according to the outer surface image comprises:

[0015] The outer surface image is split into N sub-outer surface images of the same size, and each sub-outer surface image corresponds to an image position relationship;

[0016] M positionally non-adjacent sub-outer surface images are randomly extracted from the N sub-outer surface images;

[0017] It is determined whether cracks exist in the M positionally non-adjacent sub-outer surface images, respectively;

[0018] If cracks exist in the M extracted sub-outer surface images, it is determined whether cracks exist in the sub-outer surface images in the surrounding area of the sub-outer surface image having cracks;

[0019] If cracks do not exist in the M extracted sub-outer surface images, M positionally non-adjacent sub-outer surface images are randomly extracted again from the remaining N-M sub-outer surface images, until all the sub-outer surface images are extracted or a sub-outer surface image having cracks is extracted.

[0020] In an optional embodiment, the determination of whether cracks exist in the sub-outer surface images in the surrounding area of the sub-outer surface image having cracks comprises:

[0021] The domain outer surface images of the surrounding 8 adjacent areas of the sub-outer surface image having cracks are acquired;

[0022] It is determined whether cracks exist in the domain outer surface images of the surrounding 8 adjacent areas;

[0023] If no crack appears in the field outer surface images of the eight surrounding adjacent regions, the field outer surface images of the eight surrounding adjacent regions of the next crack-appearing sub-outer surface image are acquired, and it is determined whether cracks appear in the field outer surface images of the eight surrounding adjacent regions until the field outer surface images of the eight surrounding adjacent regions of all crack-appearing sub-outer surface images are acquired.

[0024] If cracks appear in the field outer surface images of the eight surrounding adjacent regions, the field outer surface image in which cracks appear is determined as a crack-appearing sub-outer surface image, and the step of acquiring the field outer surface images of the eight surrounding adjacent regions of the crack-appearing sub-outer surface image is continued.

[0025] In an optional embodiment, the step of respectively determining whether cracks appear in the M positionally non-adjacent sub-outer surface images comprises:

[0026] The M positionally non-adjacent sub-outer surface images are preprocessed.

[0027] The preprocessed M positionally non-adjacent sub-outer surface images are respectively input into a crack recognition model to obtain a crack recognition result corresponding to each sub-outer surface image.

[0028] In an optional embodiment, the step of determining whether cracks appear on the inner surface of the boiler pressure vessel according to the ultrasonic data and the ray data of the boiler pressure vessel comprises:

[0029] A first crack result is determined according to the ultrasonic data of the boiler pressure vessel, a second crack result is determined according to the ray data of the boiler pressure vessel, and a third crack result is determined according to the ultrasonic data and the ray data of the boiler pressure vessel.

[0030] Whether cracks appear on the inner surface of the boiler pressure vessel is determined according to the first crack result, the second crack result, and the third crack result.

[0031] In an optional embodiment, the step of determining the first crack result according to the ultrasonic data of the boiler pressure vessel comprises:

[0032] Ultrasonic transverse velocity, ultrasonic longitudinal velocity, and flight time are calculated according to the ultrasonic data of the boiler pressure vessel.

[0033] The first crack result is determined according to the ultrasonic transverse velocity, the ultrasonic longitudinal velocity, and the flight time, and the first crack result includes crack positions.

[0034] In an optional embodiment, the step of determining the second crack result according to the ray data of the boiler pressure vessel comprises:

[0035] acquire ray data of the boiler pressure vessel, and obtain a projection image according to the ray data;

[0036] perform image enhancement processing, contrast enhancement processing, edge processing, and noise reduction processing on the projection image;

[0037] determine a second crack result according to the processed projection image.

[0038] In an optional embodiment, the determining a third crack result according to the ultrasonic data and the ray data of the boiler pressure vessel comprises:

[0039] converting the ultrasonic data and the ray data of the boiler pressure vessel into a feature vector;

[0040] inputting the feature vector into an internal crack identification model to obtain the third crack result of the boiler pressure vessel.

[0041] In an optional embodiment, the determining a final crack result of the boiler pressure vessel according to the simulation and emulation crack result and the cracks in the position region comprises:

[0042] performing matching and merging on the simulation and emulation crack result and the cracks in the position region to obtain the final crack result of the boiler pressure vessel.

[0043] Embodiments of the present application provide a boiler pressure vessel inspection and detection device, which comprises:

[0044] an acquisition module configured to apply magnetic powder or penetrating liquid to an outer surface of a boiler pressure vessel to acquire an outer surface image of the boiler pressure vessel to which the magnetic powder or the penetrating liquid is applied;

[0045] a determination module configured to determine whether cracks exist on the outer surface of the boiler pressure vessel according to the outer surface image;

[0046] The acquisition module is further configured to acquire ultrasonic data, ray data, and pressure data of the boiler pressure vessel if it is determined that no cracks exist on the outer surface of the boiler pressure vessel.

[0047] The determination module is further configured to determine whether cracks exist on an inner surface of the boiler pressure vessel according to the ultrasonic data, the ray data, and the pressure data of the boiler pressure vessel.

[0048] The acquisition module is further configured to acquire region physical data of a position region in which cracks exist on the inner surface and / or the outer surface of the boiler pressure vessel if cracks exist on the inner surface of the boiler pressure vessel and / or cracks exist on the outer surface of the boiler pressure vessel.

[0049] The simulation simulation module is configured to simulate and obtain a simulation simulation crack result by inputting the physical data of the position area where the crack occurs into the simulation simulation model.

[0050] The determination module is further configured to determine a final crack result of the boiler pressure vessel according to the simulation simulation crack result and the crack occurring in the position area.

[0051] The embodiment of the present application has the following advantages:

[0052] The boiler pressure vessel inspection and detection method and device provided by the embodiment of the present application first apply magnetic powder or penetrating liquid to the outer surface of the boiler pressure vessel to obtain an outer surface image of the boiler pressure vessel to which the magnetic powder or the penetrating liquid is applied, and then determine whether a crack occurs on the outer surface of the boiler pressure vessel according to the outer surface image. If it is determined that no crack occurs on the outer surface of the boiler pressure vessel, ultrasonic wave data and ray data of the boiler pressure vessel are obtained. Whether a crack occurs on the inner surface of the boiler pressure vessel is determined according to the ultrasonic wave data and the ray data of the boiler pressure vessel. If a crack occurs on the inner surface of the boiler pressure vessel and / or a crack occurs on the outer surface of the boiler pressure vessel, the physical data of a position area where a crack occurs on the inner surface and / or the outer surface of the boiler pressure vessel is obtained. A simulation simulation model is obtained by simulating and modeling according to the operation data and the overall physical data of the boiler pressure vessel, and the physical data of the position area where the crack occurs is input into the simulation simulation model to simulate and obtain a simulation simulation crack result. Finally, a final crack result of the boiler pressure vessel is determined according to the simulation simulation crack result and the crack occurring in the position area. Compared with the current detection of the boiler pressure vessel by artificial means, the outer surface of the boiler pressure vessel is detected based on the obtained outer surface image, the inner surface of the boiler pressure vessel is detected by the ultrasonic wave data and the ray data, and then the final crack result of the boiler pressure vessel is obtained based on the detection result and the simulation simulation crack result, so that the efficiency and the accuracy of the detection of the boiler pressure vessel can be improved by the present application. BRIEF DESCRIPTION OF DRAWINGS

[0053] Figure 1 FIG. 1 is a flowchart of a boiler pressure vessel inspection and detection method provided by the embodiment of the present application;

[0054] Figure 2 FIG. 2 is a flowchart of an outer surface crack detection method of a boiler pressure vessel provided by the embodiment of the present application;

[0055] Figure 3 FIG. 3 is a structural schematic diagram of a boiler pressure vessel inspection and detection device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0056] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0057] Please refer to Figure 1 A boiler pressure vessel inspection method is provided for the embodiments of the present application, and the method specifically includes S101-S107.

[0058] S101, applying magnetic powder or penetrant liquid to the outer surface of the boiler pressure vessel to obtain an outer surface image of the boiler pressure vessel to which the magnetic powder or penetrant liquid is applied.

[0059] Specifically, the magnetic powder or penetrant liquid is evenly distributed on the surface of the boiler pressure vessel. During the detection process, the flow of the carrier liquid and the attraction of the magnetic powder by the magnetic leakage field show the shape and size of the defects. The application of magnetic powder or penetrant liquid is suitable for detecting small surface defects such as fatigue cracks and grinding cracks. After applying the magnetic powder or penetrant liquid to the outer surface of the boiler pressure vessel, wait for a certain period of time, and then take a picture of the outer surface of the filter container to obtain an outer surface image of the filter pressure vessel.

[0060] In the present embodiment, the outer surface image includes multiple angles and positions, so that the photographed outer surface image covers all positions of the boiler pressure vessel, and then whether a crack appears on the outer surface of the boiler pressure vessel is determined according to the outer surface image.

[0061] S102, determining whether a crack appears on the outer surface of the boiler pressure vessel according to the outer surface image.

[0062] Specifically, the present embodiment can identify the outer surface image according to an image recognition method to determine whether a crack appears on the outer surface of the boiler pressure vessel, or determine whether a crack appears on the outer surface of the boiler pressure vessel according to a neural network model, that is, input the outer surface image into the neural network model to obtain a crack recognition result, and the present embodiment does not limit the determination method of the outer surface crack.

[0063] As shown in Figure 2 determining whether a crack appears on the outer surface of the boiler pressure vessel according to the outer surface image includes:

[0064] S201, splitting the outer surface image into N sub-outer surface images of the same unit size, and each sub-outer surface image corresponds to an image position relationship.

[0065] Wherein, the number of N can be set according to actual demand, and the specific can be determined according to the outer surface area of the boiler pressure vessel. In the embodiment, the image position relationship can be represented by 1-N, and the position relationship of the adjacent sub-outer surface images is also included, for example, for the fifth sub-outer surface image, the adjacent sub-outer surface images are eight, that is, three sub-outer surface images above and below, and one sub-outer surface image on the left and right.

[0066] S202, randomly extracting M sub-outer surface images which are not adjacent in position from N sub-outer surface images.

[0067] Wherein, the number of M is less than N, and M can be determined according to the number of N. The greater the number of N is, the greater M can be set, that is, M is proportional to N.

[0068] S203, respectively determining whether cracks appear in the M sub-outer surface images which are not adjacent in position.

[0069] In an optional embodiment provided in the application, respectively determining whether cracks appear in the M sub-outer surface images which are not adjacent in position includes: pre-processing the M sub-outer surface images which are not adjacent in position; and inputting the pre-processed M sub-outer surface images which are not adjacent in position into a crack identification model respectively to obtain a crack identification result corresponding to each sub-outer surface image respectively.

[0070] Wherein, the pre-processing includes image enhancement, image denoising, edge detection, geometric transformation, etc., which are not limited in the embodiment. In the embodiment, after pre-processing the sub-outer surface images, the pre-processed M sub-outer surface images which are not adjacent in position are input into the crack identification model respectively to obtain a crack identification result corresponding to each sub-outer surface image respectively. In the crack identification result, the corresponding crack position, crack size, and crack appearance probability are marked in the corresponding sub-outer surface image.

[0071] It should be noted that the crack identification model in the embodiment is trained according to sample data and sample labels. The sample data is an image containing cracks, and the sample labels are the crack positions, crack sizes, etc. marked in the image.

[0072] S204, if cracks appear in the extracted M sub-outer surface images, determining whether cracks appear in the sub-outer surface images in the surrounding area of the sub-outer surface image in which the cracks appear.

[0073] For example, the first sub-outer surface image and the tenth sub-outer surface image appear cracks in the extracted M sub-outer surface images, and the sub-outer surface images in the surrounding area of the first sub-outer surface image and the tenth sub-outer surface image are needed to be obtained respectively, and then it is determined whether cracks appear in the sub-outer surface images in the surrounding area.

[0074] In an optional embodiment provided in the present application, determining whether the sub-outer surface images of the surrounding areas of the sub-outer surface image in which the crack appears according to the sub-outer surface image in which the crack appears comprises:

[0075] S2041, obtaining the field outer surface images of the surrounding 8 adjacent areas of the sub-outer surface image in which the crack appears.

[0076] S2042, determining whether the crack appears in the field outer surface images of the surrounding 8 adjacent areas.

[0077] S2043, if the crack does not appear in the field outer surface images of the surrounding 8 adjacent areas, obtaining the field outer surface images of the surrounding 8 adjacent areas of the next sub-outer surface image in which the crack appears, and determining whether the crack appears in the field outer surface images of the surrounding 8 adjacent areas, until the field outer surface images of the surrounding 8 adjacent areas of all the sub-outer surface images in which the crack appears are obtained.

[0078] S2044, if the crack appears in the field outer surface images of the surrounding 8 adjacent areas, determining the field outer surface image in which the crack appears as the sub-outer surface image in which the crack appears, and jumping to step S2041 to continue to execute.

[0079] S205, if the crack does not appear in the M sub-outer surface images, randomly extracting M non-adjacent sub-outer surface images from the remaining N-M sub-outer surface images, until all the sub-outer surface images are extracted or the sub-outer surface image in which the crack appears is extracted.

[0080] In the embodiment, based on the physical characteristics of the crack, it is firstly determined whether the M sub-outer surface images extracted appear cracks, if the cracks appear, the sub-outer surface image in which the crack appears is taken as the center to gradually spread around to quickly obtain the position area of the boiler pressure vessel in which the crack appears, so that the detection efficiency of the boiler pressure vessel can be improved through the embodiment.

[0081] S103, if it is determined that the outer surface of the boiler pressure vessel does not appear cracks, obtaining the ultrasonic data and the ray data of the boiler pressure vessel.

[0082] In the embodiment, the characteristics that the ultrasonic wave propagates along a straight line in the medium are used. If the medium appears uneven, the sound impedance of the ultrasonic wave in the propagation process is different, and the refraction, reflection and projection phenomena will be produced. The refraction and reflection signals are collected by the instrument, and the ultrasonic data is obtained by converting the signals into electric signals, and then the defects in the boiler pressure vessel are judged through the ultrasonic data.

[0083] The boiler pressure vessel is irradiated by X-rays or gamma rays. The rays have strong penetration and can penetrate the wall thickness of the container and be photosensitive on the film. During the detection process, the stability of the ray source and the appropriate exposure amount are ensured to obtain clear ray data.

[0084] In S104, whether the inner surface of the boiler pressure vessel has cracks is determined according to the ultrasonic data and the ray data of the boiler pressure vessel.

[0085] In an optional embodiment provided in the present application, the step of determining whether the inner surface of the boiler pressure vessel has cracks according to the ultrasonic data and the ray data of the boiler pressure vessel comprises the following steps: determining a first crack result according to the ultrasonic data of the boiler pressure vessel, determining a second crack result according to the ray data of the boiler pressure vessel, and determining a third crack result according to the ultrasonic data and the ray data of the boiler pressure vessel; and determining whether the inner surface of the boiler pressure vessel has cracks according to the first crack result, the second crack result, and the third crack result.

[0086] Optionally, the step of determining the first crack result according to the ultrasonic data of the boiler pressure vessel comprises the following steps: calculating the ultrasonic transverse velocity and the ultrasonic longitudinal velocity and the flight time according to the ultrasonic data of the boiler pressure vessel; and determining the first crack result according to the ultrasonic transverse velocity and the ultrasonic longitudinal velocity and the flight time, wherein the first crack result comprises the crack position.

[0087] Specifically, the process of determining the first crack result in the embodiment can be as follows: first, the ultrasonic transverse velocity and the ultrasonic longitudinal velocity are obtained. The ultrasonic propagation velocity of different materials is different, so the sound velocity of the detected material needs to be known. For example, the sound velocity of steel is about 5900 m / s; then, the flight time is measured. An ultrasonic flaw detector is used to emit an ultrasonic pulse to the material and receive the echo signal reflected from the crack. By measuring the time interval (round-trip time) from the emission to the reception of the ultrasonic wave, the distance traveled by the ultrasonic wave in the material can be calculated; then, according to the propagation velocity of the ultrasonic wave in the material and the measured flight time, the position of the crack from the probe can be calculated. The position is half of the propagation path of the ultrasonic wave in the material, because the ultrasonic wave needs to be reflected back at the crack.

[0088] The specific calculation formula is: crack distance = (sound velocity x flight time) / 2. The flight time refers to the total time of the ultrasonic wave from the probe to the crack and then to the probe.

[0089] In an optional embodiment provided by the application, the calculation amount can be reduced while ensuring the accuracy of the defect position, that is, the information with the same characteristics is divided into two components by using the region information division technology. On the basis of the region information division, assuming that the weak signal of the first half of the position information feature is a and the second half of the signal is b, the mapping of the global complete defect position signal echo feature is:

[0090]

[0091] In the formula, r ab is the mapping of the global complete defect position signal echo feature, n is the total amount of crack position feedback signals, i and j are the number of weak signals of the first half and the second half of the position information feature respectively. When the total amount of feedback signals corresponds to a coefficient value less than 0, it indicates that there is a crack on the surface in the detection area. At this time, combined with the uniqueness of the distribution position in the range of the area, the specific position of the defect is determined by the following calculation formula:

[0092]

[0093] In the formula, d is the specific position of the defect; D is the total length of the defect detection surface of the boiler pressure vessel; v is the transmission speed (that is, the wave transverse speed and the ultrasonic longitudinal speed); and Δt is the crack information distribution position parameter. These parameters jointly determine the specific position of the crack in the pipeline. By accurately calculating these parameters, the defect is accurately positioned, which provides strong support for the subsequent repair work. In summary, the region information division technology is used to realize efficient and accurate pressure vessel defect positioning.

[0094] The wave transverse speed and the ultrasonic longitudinal speed are calculated by the following formula:

[0095]

[0096] In the formula, V S is the ultrasonic transverse wave speed, V L is the ultrasonic longitudinal wave speed, unit: km / s; E is the elastic modulus; ρ is the density; and μ is the Poisson's ratio.

[0097] Optionally, the second crack result is determined according to the ray data of the boiler pressure vessel, including: obtaining the ray data of the boiler pressure vessel, and obtaining a projection image according to the ray data; performing image enhancement processing, contrast enhancement processing, edge processing and noise reduction processing on the projection image; and determining the second crack result according to the processed projection image.

[0098] Optionally, the determining the third crack result according to the ultrasonic data and the ray data of the boiler pressure vessel comprises: converting the ultrasonic data and the ray data of the boiler pressure vessel into a feature vector; inputting the feature vector into an internal crack identification model to obtain the third crack result of the boiler pressure vessel. The internal crack identification model is a neural network model for identifying cracks through ultrasonic data and ray data, i.e., the sample data is a sample feature vector converted from the ultrasonic data and the ray data, and the sample label is a labeled crack position, crack size, etc.

[0099] In S105, if cracks appear on the inner surface of the boiler pressure vessel and / or cracks appear on the outer surface of the boiler pressure vessel, the area physical data of the position area where the cracks appear on the inner surface and / or the outer surface of the boiler pressure vessel is obtained.

[0100] The area physical data can be the density, elastic modulus, Poisson's ratio, yield strength, tensile strength, corrosion resistance, etc. of the material, and the basic dimensions of the corresponding area, such as length, width, height, wall thickness, diameter, volume, etc. The embodiment does not make specific limitations on this.

[0101] In S106, a simulation model is obtained by simulating according to the operation data and the overall physical data of the boiler pressure vessel, and the physical data of the area position where the cracks appear is input into the simulation model for simulation to obtain a simulation crack result.

[0102] The operation data includes pressure data, temperature data, and medium data. The pressure data includes working pressure, design pressure, maximum working pressure, etc. The change of pressure will directly affect the stress state and deformation of the equipment, so the pressure parameter needs to be accurately set in the simulation. For example, when simulating the overpressure working condition, it is necessary to ensure that the simulation model can truly reflect the stress distribution and deformation trend of the equipment under overpressure.

[0103] The temperature data includes normal working temperature range, maximum working temperature, temperature change rate, etc. The change of temperature will cause thermal expansion and thermal stress of the material, and also affect the mechanical properties of the material. In the simulation, the influence of temperature on the structure and performance of the equipment needs to be considered, such as simulating the change of temperature field and the thermal stress generated thereby through a thermal analysis module.

[0104] For the boiler pressure vessel, the internal medium can be water, steam, air, gas mixture or other chemical substances. The physical properties (such as density, viscosity, specific heat capacity, thermal conductivity, etc.) and chemical properties (such as corrosiveness, reactivity, etc.) of the medium will affect the internal surface stress, heat transfer and corrosion of the equipment. In the simulation, the corresponding boundary conditions and loads need to be set according to the characteristics of the medium.

[0105] S107, determining the final crack result of the boiler pressure vessel according to the simulation crack result and the crack in the position area.

[0106] Specifically, the determining the final crack result of the boiler pressure vessel according to the simulation crack result and the crack in the position area comprises: matching the simulation crack result and the crack in the position area to obtain the final crack result of the boiler pressure vessel.

[0107] It should be noted that, since the very small crack cannot be determined through the outer surface image, the ultrasonic data and the ray data, that is, the end of a certain crack cannot be identified, in order to solve the above problem, the embodiment is based on the physical characteristics of the crack, that is, the continuous and uninterrupted characteristics, the simulation model is obtained according to the operation data and the overall physical data of the boiler pressure vessel, the physical data of the position area where the crack occurs is input into the simulation model to obtain the simulation crack result, that is, whether there is a smaller crack in the position area where the crack occurs is further determined through the simulation, if there is, the simulation crack result and the crack in the position area are matched to obtain the final crack result of the boiler pressure vessel, so that the crack recognition accuracy can be improved through the embodiment.

[0108] This embodiment provides a method for inspecting and testing boiler pressure vessels. First, magnetic powder or penetrating liquid is applied to the outer surface of the boiler pressure vessel to obtain an image of the outer surface. Then, based on the outer surface image, it is determined whether cracks appear on the outer surface of the boiler pressure vessel. If no cracks are found on the outer surface, ultrasonic and radiographic data of the boiler pressure vessel are acquired. Based on the ultrasonic and radiographic data, it is determined whether cracks appear on the inner surface of the boiler pressure vessel. If cracks appear on the inner surface and / or the outer surface, the physical data of the location of the cracks on the inner and / or outer surfaces are acquired. A simulation model is obtained based on the boiler pressure vessel's operating data and overall physical data. The physical data of the location of the cracked area is input into the simulation model to obtain the simulated crack result. Finally, the final crack result of the boiler pressure vessel is determined based on the simulated crack result and the cracks appearing in the location area. Compared with the current method of manually inspecting boiler pressure vessels, this application inspects the outer surface of the boiler pressure vessel based on acquired external surface images, and inspects the inner surface of the boiler pressure vessel using ultrasonic and X-ray data. Then, based on the inspection results and simulated crack results, the final crack result of the boiler pressure vessel is obtained. Thus, this application can improve the efficiency and accuracy of pressure vessel inspection.

[0109] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0110] In one embodiment, a boiler pressure vessel inspection and testing device is provided. For example... Figure 3 As shown, the functional modules of this boiler and pressure vessel inspection and testing device are described in detail below:

[0111] The acquisition module 31 is used to apply magnetic powder or penetrating liquid to the outer surface of the boiler pressure vessel in order to obtain an image of the outer surface of the boiler pressure vessel with applied magnetic powder or penetrating liquid.

[0112] The determination module 32 is used to determine whether cracks appear on the outer surface of the boiler pressure vessel based on the outer surface image;

[0113] The acquisition module 31 is further configured to acquire ultrasonic data, X-ray data and pressure data of the boiler pressure vessel if it is determined that no cracks appear on the outer surface of the boiler pressure vessel.

[0114] The determining module 32 is further configured to determine whether a crack occurs on the inner surface of the boiler pressure vessel according to the ultrasonic data, the ray data and the pressure data of the boiler pressure vessel.

[0115] The obtaining module 31 is further configured to obtain regional physical data of a position area where a crack occurs on the inner surface and / or the outer surface of the boiler pressure vessel if the crack occurs on the inner surface of the boiler pressure vessel and / or the crack occurs on the outer surface of the boiler pressure vessel.

[0116] The simulation module 33 is configured to perform simulation simulation according to the operation data and the overall physical data of the boiler pressure vessel to obtain a simulation simulation model, and input the physical data of the position area where the crack occurs into the simulation simulation model to perform simulation simulation and obtain a simulation simulation crack result.

[0117] The determining module 32 is further configured to determine a final crack result of the boiler pressure vessel according to the simulation simulation crack result and the crack occurring on the position area.

[0118] In an optional embodiment, the determining module 32 is specifically configured to:

[0119] Split the outer surface image into N sub-outer surface images of the same size, and each sub-outer surface image corresponds to an image position relationship;

[0120] Randomly extract M positionally non-adjacent sub-outer surface images from the N sub-outer surface images;

[0121] Determine whether a crack occurs in each of the M positionally non-adjacent sub-outer surface images;

[0122] If a crack occurs in the extracted M sub-outer surface images, determine whether a crack occurs in the sub-outer surface images of the surrounding area of the sub-outer surface image where the crack occurs;

[0123] If no crack occurs in the extracted M sub-outer surface images, randomly extract M positionally non-adjacent sub-outer surface images from the remaining N-M sub-outer surface images again, until all the sub-outer surface images are extracted or a sub-outer surface image with a crack is extracted.

[0124] In an optional embodiment, the determining module 32 is specifically configured to:

[0125] Obtain the domain outer surface images of the surrounding 8 adjacent areas of the sub-outer surface image where the crack occurs;

[0126] Determine whether a crack occurs in the domain outer surface images of the surrounding 8 adjacent areas;

[0127] If no crack appears in the field outer surface images of the eight surrounding adjacent regions, the field outer surface images of the eight surrounding adjacent regions of the next sub-outer surface image with cracks are acquired, and it is determined whether cracks appear in the field outer surface images of the eight surrounding adjacent regions until the field outer surface images of the eight surrounding adjacent regions of all sub-outer surface images with cracks are acquired.

[0128] If cracks appear in the field outer surface images of the eight surrounding adjacent regions, the field outer surface image with cracks is determined as the sub-outer surface image with cracks, and the step of acquiring the field outer surface images of the eight surrounding adjacent regions of the sub-outer surface image with cracks is executed.

[0129] In an optional embodiment, the determining module 32 is specifically configured to:

[0130] The M sub-outer surface images with non-adjacent positions are preprocessed.

[0131] The preprocessed M sub-outer surface images with non-adjacent positions are respectively input into the crack recognition model to obtain the crack recognition result corresponding to each sub-outer surface image.

[0132] In an optional embodiment, the determining module 32 is specifically configured to:

[0133] The first crack result is determined according to the ultrasonic data of the boiler pressure vessel, the second crack result is determined according to the ray data of the boiler pressure vessel, and the third crack result is determined according to the ultrasonic data and the ray data of the boiler pressure vessel.

[0134] It is determined whether cracks appear on the inner surface of the boiler pressure vessel according to the first crack result, the second crack result, and the third crack result.

[0135] In an optional embodiment, the determining module 32 is specifically configured to:

[0136] The ultrasonic transverse velocity, the ultrasonic longitudinal velocity, and the flight time are calculated according to the ultrasonic data of the boiler pressure vessel.

[0137] The first crack result is determined according to the ultrasonic transverse velocity, the ultrasonic longitudinal velocity, and the flight time, and the first crack result includes the crack position.

[0138] In an optional embodiment, the determining module 32 is specifically configured to:

[0139] The ray data of the boiler pressure vessel are acquired, and the projection image is obtained according to the ray data.

[0140] performing image enhancement processing, contrast processing, edge processing and noise reduction processing on the projection image;

[0141] determining a second crack result according to the processed projection image.

[0142] In an optional embodiment, the determining module 32 is specifically configured to:

[0143] convert the ultrasonic data and the ray data of the boiler pressure vessel into a feature vector;

[0144] input the feature vector into the internal crack identification model to obtain a third crack result of the boiler pressure vessel.

[0145] In an optional embodiment, the determining module 32 is specifically configured to:

[0146] match the simulation simulation crack result and the crack appearing in the position area to obtain a final crack result appearing in the boiler pressure vessel.

[0147] It should be noted that the above detailed description is exemplary and is intended to provide further description of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present application belongs.

[0148] For specific limitations of the boiler pressure vessel inspection and detection device, refer to the limitations of the boiler pressure vessel inspection and detection method described above, which will not be repeated here. Each module in the above device can be realized by software, hardware and their combination in whole or in part. The above modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0149] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the system is divided into different functional units or modules to complete all or part of the functions described above.

[0150] The above examples are only used to illustrate the technical solutions of the present application, but not limit the present application; although the present application has been described in detail with reference to the foregoing examples, those ordinarily skilled in the art should understand: the technical solutions recorded in the foregoing examples can still be modified, or some technical features can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for inspecting and testing boilers and pressure vessels, characterized in that, The method includes: Apply magnetic powder or penetrant to the outer surface of the boiler pressure vessel to obtain an image of the outer surface of the boiler pressure vessel to which the magnetic powder or penetrant has been applied; Determine whether cracks appear on the outer surface of the boiler pressure vessel based on the outer surface image; If it is determined that no cracks appear on the outer surface of the boiler pressure vessel, then the ultrasonic data and X-ray data of the boiler pressure vessel are acquired. Determine whether cracks appear on the inner surface of the boiler pressure vessel based on the ultrasonic and radiographic data of the boiler pressure vessel. If cracks appear on the inner surface of the boiler pressure vessel and / or on the outer surface of the boiler pressure vessel, then obtain the regional physical data of the location area of ​​the cracks on the inner and / or outer surfaces of the boiler pressure vessel. The simulation model is obtained by simulating the operating data and overall physical data of the boiler pressure vessel. The physical data of the location of the cracked area is then input into the simulation model to obtain the simulation crack result. The final crack result of the boiler pressure vessel is determined based on the simulated crack results and the cracks appearing in the specified location area. The step of determining whether cracks appear on the outer surface of the boiler pressure vessel based on the outer surface image includes: The outer surface image is divided into N sub-outer surface images of the same unit size, and each sub-outer surface image corresponds to an image position relationship; M non-adjacent sub-outer surface images are randomly selected from the N sub-outer surface images; Determine whether cracks appear in M ​​non-adjacent sub-exterior surface images; If cracks appear in the M extracted sub-external surface images, then determine whether cracks appear in the sub-external surface images of the surrounding area based on the sub-external surface image with cracks. If no cracks are found in the M extracted sub-exterior surface images, then M non-adjacent sub-exterior surface images are randomly selected from the remaining NM sub-exterior surface images, until all sub-exterior surface images are extracted or a sub-exterior surface image with cracks is extracted.

2. The method according to claim 1, characterized in that, The step of determining whether a crack appears in the sub-outer surface image of the region surrounding the cracked sub-outer surface image includes: Obtain the outer surface images of the surrounding 8 adjacent regions of the sub-outer surface image where the crack appears; Determine whether cracks appear in the outer surface images of the eight surrounding adjacent regions; If no cracks appear in the outer surface images of the surrounding 8 adjacent regions, then the outer surface images of the surrounding 8 adjacent regions of the next cracked sub-outer surface image are obtained, and it is determined whether cracks appear in the outer surface images of the surrounding 8 adjacent regions, until the outer surface images of the surrounding 8 adjacent regions of all cracked sub-outer surface images are obtained. If cracks appear in the outer surface images of the eight surrounding adjacent regions, the outer surface image with cracks is determined as the sub-outer surface image with cracks, and the process jumps to the step of obtaining the outer surface images of the eight surrounding adjacent regions of the sub-outer surface image with cracks to continue execution.

3. The method according to claim 1, characterized in that, The step of determining whether cracks appear in M ​​non-adjacent sub-exterior surface images includes: Preprocess the images of M non-adjacent sub-outer surfaces; The preprocessed M non-adjacent sub-exterior surface images are input into the crack recognition model to obtain the crack recognition result corresponding to each sub-exterior surface image.

4. The method according to claim 1, characterized in that, The step of determining whether cracks appear on the inner surface of the boiler pressure vessel based on ultrasonic and radiographic data includes: The first crack result is determined based on the ultrasonic data of the boiler pressure vessel; the second crack result is determined based on the X-ray data of the boiler pressure vessel; and the third crack result is determined based on the ultrasonic data and X-ray data of the boiler pressure vessel. Based on the first crack result, the second crack result, and the third crack result, determine whether cracks have appeared on the inner surface of the boiler pressure vessel.

5. The method according to claim 4, characterized in that, The step of determining the first crack result based on the ultrasonic data of the boiler pressure vessel includes: The ultrasonic transverse velocity, ultrasonic longitudinal velocity, and flight time are calculated based on the ultrasonic data of the boiler pressure vessel. The first crack result is determined by the transverse velocity of the wave, the longitudinal velocity of the ultrasonic wave, and the flight time. The first crack result includes the crack location.

6. The method according to claim 4, characterized in that, The determination of the second crack result based on the X-ray data of the boiler pressure vessel includes: Acquire the X-ray data of the boiler pressure vessel and obtain a projection image based on the X-ray data; The projected image is subjected to image enhancement processing, contrast enhancement processing, edge processing, and noise reduction processing; The result of the second crack was determined based on the processed projection image.

7. The method according to claim 6, characterized in that, The determination of the third crack result based on the ultrasonic and radiographic data of the boiler pressure vessel includes: The ultrasonic and X-ray data of the boiler pressure vessel are converted into feature vectors; The feature vector is input into the internal crack identification model to obtain the third crack result of the boiler pressure vessel.

8. The method according to claim 1, characterized in that, The step of determining the final crack result of the boiler pressure vessel based on the simulated crack results and the cracks appearing in the location region includes: The simulated crack results and the cracks appearing in the location area are matched and merged to obtain the final crack results of the boiler pressure vessel.

9. A boiler pressure vessel inspection and testing device, the device implementing the method as described in claim 1, characterized in that, The device includes: The acquisition module is used to apply magnetic powder or penetrating liquid to the outer surface of the boiler pressure vessel in order to obtain an image of the outer surface of the boiler pressure vessel with applied magnetic powder or penetrating liquid. A determination module is used to determine whether cracks appear on the outer surface of the boiler pressure vessel based on the outer surface image. The acquisition module is further configured to acquire ultrasonic data, X-ray data, and pressure data of the boiler pressure vessel if it is determined that no cracks have appeared on the outer surface of the boiler pressure vessel. The determining module is also used to determine whether cracks appear on the inner surface of the boiler pressure vessel based on the ultrasonic data, X-ray data and pressure data of the boiler pressure vessel. The acquisition module is further configured to acquire regional physical data of the location area of ​​the crack on the inner surface and / or outer surface of the boiler pressure vessel if a crack appears on the inner surface and / or the outer surface of the boiler pressure vessel. The simulation module is used to perform simulation based on the operating data and overall physical data of the boiler pressure vessel to obtain a simulation model, and input the physical data of the location of the cracked area into the simulation model to obtain the simulation crack result. The determining module is further configured to determine the final crack result of the boiler pressure vessel based on the simulated crack result and the cracks appearing in the location area.

Images