An inner surface detection device and detection method for a nuclear reactor pressure vessel

By designing an automated inner surface detection device and detection method of nuclear reactor pressure vessel, and using deep convolutional neural network model to analyze the inner wall pictures, the existing detection methods are solved, and efficient and accurate detection is achieved, reducing costs and radiation exposure risks.

CN118762857BActive Publication Date: 2025-06-20XIAN THERMAL POWER RES INST CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202410907768.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-08
Publication Date
2025-06-20
Estimated Expiration
2044-07-08

AI Technical Summary

Technical Problem

The existing nuclear reactor pressure vessel inner surface detection method is time-consuming and labor-intensive, has safety risks, and increases economic costs. The traditional method requires a large amount of manual operation and equipment movement, resulting in insufficiency of detection.

Method used

A nuclear reactor pressure vessel inner surface detection device is designed, including the guide rail body, observation mechanism and shooting component. Automatic detection is achieved through control motor and drive components, and multi-scale features of inner wall pictures are extracted in combination with the deep convolutional neural network model, feature information pictures are analyzed, and detection reports are generated.

Benefits of technology

Automatic inspection is realized, manual operation is reduced, detection efficiency and accuracy is improved, safety hazards and economic costs are reduced, and a long-term equipment status database is established to reduce the radiation exposure risk of staff.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118762857B_ABST
    Figure CN118762857B_ABST
Patent Text Reader

Abstract

The present invention discloses an inner surface detection device and a detection method for a nuclear reactor pressure vessel, which relates to the technical field of intelligent detection of nuclear reaction cylinders, and includes the following steps: obtaining an inner wall picture of the main body of the pressure vessel through a photographing component, and transmitting the obtained inner wall picture to a control terminal; introducing a deep convolutional neural network model to extract multi-scale features of the internal picture, and obtaining detailed features of the inner wall picture through a multi-branch network structure; obtaining an inner wall feature information picture through a fusion mechanism model; analyzing the inner wall feature information picture, obtaining a detection report conclusion, and storing the detection report conclusion in a database. The digital data processing adopted by the present invention is also convenient for archiving and subsequent analysis, helps to establish a long-term equipment condition database, recycle the equipment and analyze the inspected parts, and at the same time reduces the radiation exposure risk of the staff.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent detection of nuclear reaction cylinder bodies, and particularly to an inner surface detection device and a detection method for a nuclear reactor pressure vessel. Background Art

[0002] In modern industrial production, nuclear energy is widely used as a clean energy source. During the process of ensuring the safe operation of nuclear power plants, the condition monitoring of nuclear reactor pressure vessels is particularly important because it directly affects the safety of the entire nuclear power plant. The pressure vessel of a nuclear reactor is a key component in a nuclear power plant, which undertakes multiple functions such as enclosing nuclear fuel, controlling reactivity, transferring heat, and maintaining system pressure. Under the long-term working environment of high temperature and high pressure, corrosion, cracks, or other defects may occur on the inner wall of the pressure vessel. If these defects are not discovered and processed in time, serious consequences may result. To ensure the integrity of the pressure vessel, regular inspections are required.

[0003] Traditional inspection methods are not only time-consuming and laborious, but also pose significant safety hazards and increase economic costs. Even with system remote control, the imaging device needs to be rotated back and forth, resulting in numerous operation steps. Therefore, it is particularly important to select a suitable detection device to develop an efficient and accurate detection technology. Summary of the Invention

[0004] In view of the problems existing in the above-mentioned existing inner surface detection devices and detection methods for nuclear reactor pressure vessels, the present invention is proposed.

[0005] Therefore, the object of the present invention is to provide an inner surface detection device and a detection method for a nuclear reactor pressure vessel, and its purpose is to achieve automated inspection.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides an inner surface detection device for a nuclear reactor pressure vessel, characterized in that it includes:

[0008] A pressure vessel cylinder main body;

[0009] A guide rail main body, fixedly installed above the pressure vessel cylinder main body, the guide rail main body including a fixed frame and a guide rack provided on the surface of the middle part of the fixed frame; and,

[0010] An observation mechanism, installed above the guide rail main body, the observation mechanism including a mounting frame, a control motor provided on the outer surface of the mounting frame, a driving component connected to the output end of the control motor, and a fastening belt sleeved above the driving component;

[0011] The observation mechanism further includes a connection component located on the other side of the fastening belt, a rotation component arranged on the side of the connection component, a resilience component connected to the outside of the rotation component, a driving wheel installed at the lower end of the driving component, and a photographing component arranged outside the mounting bracket.

[0012] As a preferred solution of the inner surface detection device for a nuclear reactor pressure vessel according to the present invention, wherein: the driving component includes a driving rod and a driving gear installed outside the driving rod;

[0013] Wherein, one end of the fastening belt is sleeved outside the driving rod, the upper part of the driving rod is connected to a control motor, and the lower part of the driving rod is connected to the driving wheel.

[0014] As a preferred solution of the inner surface detection device for a nuclear reactor pressure vessel according to the present invention, wherein: the connection component includes a guiding seat, a guiding rod arranged inside the guiding seat, and a connection gear installed outside the guiding rod;

[0015] The rotation component includes a first rotation gear and a second rotation gear connected to the outside of the first rotation gear;

[0016] Wherein, the guiding seat is arranged in an arc shape, the upper part of the guiding rod is connected to the other end of the fastening belt, and the connection gear is meshed and connected with the driving gear.

[0017] As a preferred solution of the inner surface detection device for a nuclear reactor pressure vessel according to the present invention, wherein: the resilience component includes a vertical plate arranged inside the mounting bracket, a limiting rod installed between the vertical plates, a clamping rack sleeved outside the limiting rod, and a compression spring located at the side end of the clamping rack;

[0018] Wherein, the rack side of the clamping rack is connected to the second rotation gear, and the clamping rack slides outside the limiting rod.

[0019] As a preferred solution of the inner surface detection device for a nuclear reactor pressure vessel according to the present invention, wherein: the photographing component includes a transverse rod arranged between the two mounting brackets, two electric telescopic rods slidably connected to the transverse rod, and a camera arranged at the lower end of the electric telescopic rods;

[0020] Wherein, the camera is connected to a control terminal through a built-in signal.

[0021] Second, an embodiment of the present invention provides a method for detecting the inner surface of a nuclear reactor pressure vessel. The detection method includes the following steps.

[0022] Obtain an inner wall picture of the pressure vessel cylinder main body through the photographing component and transmit the obtained inner wall picture to the control terminal;

[0023] Introduce a deep convolutional neural network model to extract multi-scale features of the internal image, and obtain the detailed features of the inner wall image through a multi-branch network structure;

[0024] Obtain the inner wall feature information image through the fusion mechanism model;

[0025] Analyze the inner wall feature information image, obtain the conclusion of the inspection report, and store the conclusion of the inspection report in the database.

[0026] As a preferred solution of the method for inspecting the inner surface of the nuclear reactor pressure vessel described in the present invention, wherein: when the photographing component obtains the inner wall image of the main body of the pressure vessel cylinder, the moving speed of the photographing component is set to L cm / s, and the length of the inner wall image obtained by the photographing component is X cm, and the shooting interval of the photographing component is Z s, and the shooting conditions satisfy the formula:

[0027]

[0028] In the formula, L represents the moving speed, Z represents the shooting interval, and X represents the length of the shot image;

[0029] When the photographing component obtains the inner wall image of the main body of the pressure vessel cylinder, it will combine the previous inner wall image and judge whether the side ends of the two inner wall images coincide. When the judgment result is coincidence, a new inner wall image is output. When the judgment result is non-coincidence, the abnormal situation is transmitted to the control terminal, and then the control terminal issues an instruction to the control motor to make the control motor rotate in the reverse direction, and the rotation duration is set to Z / 4, and the inner wall image of the main body of the pressure vessel cylinder is obtained again until the side ends of the newly shot inner wall image and the previous inner wall image coincide, and a new inner wall image is output.

[0030] As a preferred solution of the method for inspecting the inner surface of the nuclear reactor pressure vessel described in the present invention, wherein: the method for obtaining the inner wall feature information image includes,

[0031] Cut the length of the inner wall image into a feature initial image with a length of X / 10 cm and a width of Y / 4 cm, and sequentially mark the serial numbers for all the feature initial images, respectively perform feature recognition on all the feature initial images, and then label the recognized feature information on the corresponding feature initial images. Finally, according to the fusion mechanism model, all the feature initial images are sequentially integrated together through the marked serial numbers to output an inner wall feature information image;

[0032] Wherein, Y represents the width of the shot image.

[0033] As a preferred embodiment of the method for inspecting the inner surface of the nuclear reactor pressure vessel according to the present invention, wherein: the method for obtaining the conclusion of the inspection report includes

[0034] Search for all the feature information in the picture of the inner wall feature information, set weights according to the type of feature information, and obtain the weight value of the picture of the inner wall feature information through a calculation formula. The calculation formula is expressed as:

[0035]

[0036] In the formula, Q represents the weight value. 、 、 and respectively represent different types of feature information. 、 、 and respectively represent the weights of different types of feature information.

[0037] Then, by comparing the obtained weight value with the set threshold value, when the weight value is less than the set threshold value, the conclusion of the inspection report output is no abnormality. When the weight value is not less than the set threshold value, the picture of the inner wall feature information is recognized again to obtain the abnormal area. At the same time, an instruction is sent from the control terminal to the control motor to stop the control motor.

[0038] The method for obtaining the abnormal area includes:

[0039] Judge whether there are two or more groups of feature information in the feature initial images with the same serial number. When not, query the type of feature information with the largest weight and output the serial number carrying the type of feature information. When there are, output the serial numbers corresponding to the two or more groups of feature information and generate the corresponding inspection report conclusion.

[0040] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, wherein: when the computer program is executed by a processor, any step of the method for inspecting the inner surface of the nuclear reactor pressure vessel described above is implemented.

[0041] The beneficial effects of the present invention: Through mechanical means, automated inspection is realized. When an abnormal area is found, the movement of the control motor can be stopped in time, and at the same time, it is ensured that the shooting component can be aligned with the position of the abnormal area, without the need for staff to operate the control motor to drive the shooting component to move again to re-find the abnormal area, reducing the work intensity of the operator.

[0042] The use of digital data processing also facilitates archiving and subsequent analysis, helps to establish a long-term equipment condition database, recycle the equipment and analyze the inspected parts, while reducing the radiation exposure risk of the staff. Description of the Drawings

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0044] Figure 1 It is a schematic diagram of the overall structure of the inner surface detection device of the nuclear reactor pressure vessel of the present invention.

[0045] Figure 2 It is a schematic cross-sectional structure diagram of the inner surface detection device of the nuclear reactor pressure vessel of the present invention.

[0046] Figure 3 It is a schematic diagram of the structure of the observation mechanism of the inner surface detection device of the nuclear reactor pressure vessel of the present invention.

[0047] Figure 4 It is a schematic diagram of the internal structure of the mounting frame of the inner surface detection device of the nuclear reactor pressure vessel of the present invention.

[0048] Figure 5 It is a schematic top view of the internal structure of the mounting frame of the inner surface detection device of the nuclear reactor pressure vessel of the present invention.

[0049] Figure 6 It is a schematic flow diagram of the method for detecting the inner surface of the nuclear reactor pressure vessel of the present invention.

[0050] Figure 7 It is a schematic diagram of the inner wall picture segmentation of the method for detecting the inner surface of the nuclear reactor pressure vessel of the present invention. Detailed Embodiments

[0051] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention will be made in conjunction with the drawings in the specification.

[0052] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0053] Secondly, the "one embodiment" or "embodiment" referred to herein means a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that are mutually exclusive of other embodiments.

[0054] Thirdly, the present invention is described in detail in conjunction with schematic diagrams. When detailing the embodiments of the present invention, for ease of illustration, the cross-sectional views showing the device structure will be enlarged locally in a non-general proportion, and the schematic diagrams are only examples and should not limit the scope of protection of the present invention herein. In addition, in actual production, three-dimensional spatial dimensions including length, width, and depth should be included.

[0055] Embodiment 1

[0056] Referring to Figures 1 to 5 , which is the first embodiment of the present invention. This embodiment provides an inner surface detection device for a nuclear reactor pressure vessel, including

[0057] The pressure vessel cylinder main body 100;

[0058] The guide rail main body 200 is fixedly installed above the pressure vessel cylinder main body 100. The guide rail main body 200 includes a fixed frame 201 and a guide rack 202 provided on the middle surface of the fixed frame 201; and

[0059] The observation mechanism 300 is installed above the guide rail main body 200. The observation mechanism 300 includes a mounting frame 301, a control motor 302 provided on the outer surface of the mounting frame 301, a driving assembly 303 connected to the output end of the control motor 302, and a fastening belt 304 sleeved above the driving assembly 303;

[0060] The observation mechanism 300 further includes a connection assembly 305 on the other side of the fastening belt 304, a rotation assembly 306 provided on the side of the connection assembly 305, a resilience assembly 307 connected to the outside of the rotation assembly 306, a driving wheel 308 installed at the lower end of the driving assembly 303, and a photographing assembly 309 provided on the outside of the mounting frame 301.

[0061] Furthermore, the driving assembly 303 includes a driving rod 303a and a driving gear 303b installed outside the driving rod 303a;

[0062] Wherein, one end of the fastening belt 304 is sleeved outside the driving rod 303a. The upper part of the driving rod 303a is connected to the control motor 302, and the lower part of the driving rod 303a is connected to the driving wheel 308;

[0063] By using the control motor 302, the rotation of the driving rod 303a can be realized, and further the position of the entire observation mechanism 300 can be moved.

[0064] Further, the connecting component 305 includes a guiding seat 305a, a guiding rod 305b disposed inside the guiding seat 305a, and a connecting gear 305c mounted outside the guiding rod 305b;

[0065] The rotating component 306 includes a first rotating gear 306a and a second rotating gear 306b connected to the outside of the first rotating gear 306a;

[0066] Among them, the guiding seat 305a is arc-shaped, the upper part of the guiding rod 305b is connected to the other end of the fastening belt 304, and the connecting gear 305c is meshed with the driving gear 303b;

[0067] By using the connecting component 305, the driving gear 303b can be connected to the first rotating gear 306a or the second rotating gear 306b respectively, and by using the fastening belt 304, the connection between the driving gear 303b and the connecting gear 305c can be made tighter.

[0068] Further, the rebounding component 307 includes a vertical plate 307a disposed inside the mounting frame 301, a limiting rod 307b mounted between the vertical plates 307a, a rack 307c sleeved outside the limiting rod 307b, and a compression spring 307d located at the side end of the rack 307c;

[0069] Among them, one side of the rack of the rack 307c is connected to the second rotating gear 306b, and the rack 307c slides outside the limiting rod 307b;

[0070] By using the rebounding component 307, when the movement stops, the second rotating gear 306b can be driven to rotate in the reverse direction, and then the reverse movement of the entire observation mechanism 300 can be realized.

[0071] Further, the photographing component 309 includes a transverse rod 309a disposed between the two mounting frames 301, two electric telescopic rods 309b slidably connected to the transverse rod 309a, and a camera 309c disposed at the lower end of the electric telescopic rod 309b;

[0072] Among them, the camera 309c is connected to the control terminal through a built-in signal;

[0073] The photographing component 309 can photograph the pressure vessel cylinder main body 100 and transmit the photographed pictures to the control terminal for convenient analysis of the pictures.

[0074] During use, the guide rail body 200 is fixed above the pressure vessel cylinder body 100, which can guide the observation mechanism 300. And during the operation, when the control motor 302 drives the driving rod 303a to rotate counterclockwise, it can drive the driving gear 303b to rotate counterclockwise. Due to the connection of the fastening belt 304, the connecting gear 305c slides inside the guiding seat 305a, and then moves to the uppermost end, so that the connecting gear 305c is connected to the second rotating gear 306b. Finally, the counterclockwise rotation of the driving gear 303b drives the connecting gear 305c to rotate clockwise, and then drives the second rotating gear 306b to rotate counterclockwise, so that the second rotating gear 306b pushes the clamping rack 307c to the left. When the movement stops, the clamping rack 307c moves to the right under the action of the compression spring 307d. Then, the reverse rotation of the second rotating gear 306b can realize the reverse rotation of the driving gear 303b, and finally drive the driving wheel 308 to rotate reversely, realizing the reverse movement of the observation mechanism 300;

[0075] As Figure 5 shown, when one of the rightmost teeth of the clamping rack 307c is connected to the second rotating gear 306b, the continuous rotation of the second rotating gear 306b will not drive the clamping rack 307c to continue sliding, but presents a state similar to slipping of the thread;

[0076] Secondly, due to the connection of the fastening belt 304, the connection between the driving gear 303b and the connecting gear 305c will be more firm. Figure 5 shown, when the driving gear 303b rotates counterclockwise, through the connection of the fastening belt 304, it will first drive the connecting gear 305c to slide, and then be limited by the guiding seat 305a and stop sliding, and then drive the rotation of the connecting gear 305c.

[0077] Embodiment 2

[0078] Referring to Figures 1 to 7 , on the basis of the first embodiment, this embodiment further provides a method for detecting the inner surface of a nuclear reactor pressure vessel, including the following steps.

[0079] S1. Obtain the inner wall picture of the pressure vessel cylinder body 100 through the photographing component 309, and transmit the obtained inner wall picture to the control terminal.

[0080] When the photographing component 309 obtains the inner wall picture of the pressure vessel cylinder body 100, the moving speed of the photographing component 309 is set to L cm / s, and the length of the inner wall picture obtained by the photographing component 309 is X cm, and the shooting interval of the photographing component 309 is Z s. The shooting conditions satisfy the formula:

[0081]

[0082] In the formula, L represents the moving speed, Z represents the shooting interval duration, and X represents the length of the size of the captured picture.

[0083] When the shooting component 309 acquires the inner wall picture of the pressure vessel cylinder main body 100, it will combine the previous inner wall picture to judge whether the side ends of the two inner wall pictures coincide. When the judgment result is coincidence, a new inner wall picture is output. When the judgment result is non - coincidence, the abnormal situation is transmitted to the control terminal. Then the control terminal issues an instruction to the control motor 302 to rotate reversely, and the rotation duration is set to Z / 4. The inner wall picture of the pressure vessel cylinder main body 100 is acquired again until the side ends of the newly captured inner wall picture coincide with those of the previous inner wall picture, and a new inner wall picture is output.

[0084] When the moving speed of the shooting component 309 is set to 5 cm / s and the length of the size of the inner wall picture acquired by the shooting component 309 is 20 cm, the shooting interval duration needs to be less than 4 s. For example, if it is set to 3 s, after the inner wall picture of the pressure vessel cylinder main body 100 is acquired by the shooting component 309 for the first time, the second shooting is carried out after 3 s. The inner wall picture taken for the second time is compared with the side ends of the inner wall picture taken for the first time. When coincidence occurs, it means that the captured picture is complete, and a new inner wall picture is output. When there is no coincidence between the inner wall picture taken for the second time and the side ends of the inner wall picture taken for the first time, it means that the captured picture is incomplete. An instruction is issued through the control terminal to make the control motor 302 rotate reversely, and the reverse rotation duration is 3 / 4 s. The second shooting is carried out again, and after shooting, it is compared with the inner wall picture taken for the first time again until the side ends of the inner wall picture taken for the second time coincide with those of the inner wall picture taken for the first time.

[0085] S2. Introduce a deep convolutional neural network model to extract multi - scale features of the internal picture, and obtain the detailed features of the inner wall picture through a multi - branch network structure.

[0086] S3. Obtain the inner wall feature information picture through a fusion mechanism model.

[0087] The length of the inner wall picture is cut into a feature initial image with a size of X / 10 cm and the width is cut into a feature initial image with a size of Y / 4 cm, and all the feature initial images are sequentially numbered. Feature recognition is carried out on all the feature initial images respectively, and the recognized feature information is marked on the corresponding feature initial images. Finally, according to the fusion mechanism model, through the marked numbers, all the feature initial images are sequentially integrated together to output an inner wall feature information picture;

[0088] Among them, Y represents the width of the size of the captured picture.

[0089] Such as Figure 7As shown, the obtained inner wall pictures are divided into 10 * 4 pieces of initial feature images, which are sequentially marked with serial numbers 1, 2, 3, ……, 40. The 40 pieces of initial feature images are sequentially recognized, and according to the recognition results, the recognition types are marked on different initial feature images. For example, the types of the initial feature images with serial numbers 1, 2, and 3 are cracks, and there is no recognition result in other positions. Therefore, there are only 3 pieces of feature information in the output inner wall feature information picture.

[0090] S4. Analyze the inner wall feature information picture, obtain the conclusion of the inspection report, and store the conclusion of the inspection report in the database.

[0091] The method for obtaining the conclusion of the inspection report includes

[0092] Search for all the feature information of the inner wall feature information picture, set weights according to the types of the feature information, and obtain the weight value of the inner wall feature information picture through a calculation formula. The calculation formula is expressed as:

[0093]

[0094] In the formula, Q represents the weight value 、 、 and respectively represent the types of different feature information 、 、 and respectively represent the weights of different feature information types;

[0095] Then, compare the obtained weight value with the set threshold. When the weight value is less than the set threshold, the conclusion of the inspection report output is no abnormality. When the weight value is not less than the set threshold, the inner wall feature information picture is recognized again to obtain the abnormal area. At the same time, a command is sent from the control terminal to the control motor 302 to stop the control motor 302 from running;

[0096] When recognizing the obtained inner wall feature information picture, at this time, the control motor 302 is still in the running state, so it will drive the shooting component 309 to continue moving. When the abnormal area appears in the result, even if a command is sent from the control terminal to the control motor 302 to stop the control motor 302 from running, the shooting component 309 can no longer shoot the abnormal area at this time, but a new area. Therefore, by using the rebound component 307, the shooting component 309 can be moved in the reverse direction to ensure that when it stops moving, the shooting component 309 can shoot the abnormal area, which is convenient for the operator to observe.

[0097] The method for obtaining the abnormal area includes:

[0098] Determine whether the initial feature images with the same serial number have two or more groups of feature information. When there is none, query the type of the feature information with the largest weight, and output the serial number carrying the type of the feature information. When there is, output the serial numbers corresponding to the two or more groups of feature information, and generate the corresponding detection report conclusion.

[0099] In summary, through mechanical means, automated detection is achieved. When an abnormal area is found, the movement of the control motor can be stopped in a timely manner, while ensuring that the shooting component can be aligned with the position of the abnormal area. It is not necessary for the staff to perform secondary operations to control the motor to drive the shooting component to move and re-find the abnormal area, reducing the work intensity of the operator.

[0100] The use of digital data processing is also convenient for archiving and subsequent analysis, helps to establish a long-term equipment condition database, recycle the equipment and analyze the parts to be inspected, and at the same time reduces the radiation exposure risk of the staff.

[0101] Embodiment 3

[0102] This embodiment also provides a computer device applicable to the case of the inner surface detection method of a nuclear reactor pressure vessel, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the inner surface detection method of a nuclear reactor pressure vessel as proposed in the above embodiment.

[0103] This computer device can be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be achieved through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the shell of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0104] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the inner surface detection method of a nuclear reactor pressure vessel as proposed in the above embodiment.

[0105] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. Technical details not described in detail in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0106] Embodiment 4

[0107] Based on the first three embodiments, this embodiment provides a method for detecting the inner surface of a nuclear reactor pressure vessel and a detection method. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0108] Comparative Example 1: Manual inspection is adopted;

[0109] Comparative Example 2: Search for abnormal areas by manual adjustment, and the others are the same as in Embodiment 2;

[0110] Test method: The inner walls of the same group of pressure vessel cylinders 100 are inspected by Comparative Example 1, Comparative Example 2, and Embodiment 2. Since manual inspection is adopted in Comparative Example 1, the risk is relatively high, and the cycle of each inspection is relatively long, resulting in high economic costs. In Comparative Example 2, when an abnormal area is found, the operator needs to manually issue an instruction to the control motor 302, then move the shooting component 309, and finally locate the abnormal area through the transmitted picture. This method requires manual assistance, so the monitoring device cannot be separated from the operator. Embodiment 2 can automatically locate the abnormal area, and the operator only needs to observe the pictures.

[0111] Importantly, it should be noted that the construction and arrangement of the present application shown in multiple different exemplary embodiments are merely illustrative. Although only a few embodiments are described in detail in this disclosure, those who refer to this disclosure should easily understand that many modifications are possible without materially departing from the novel teachings and advantages of the subject matter described in this application (for example, the dimensions, scales, structures, shapes and proportions of various elements, and parameter values (such as temperature, pressure, etc.), installation arrangements, use of materials, color, orientation changes, etc.). For example, an element shown as integrally formed may be composed of multiple parts or elements, the position of the element may be inverted or otherwise changed, and the nature, number or position of discrete elements may be altered or changed. Accordingly, all such modifications are intended to be included within the scope of the present invention. The order or sequence of any process or method steps may be altered or reordered according to alternative embodiments. In the claims, any clause of "means-plus-function" is intended to cover the structures that perform the recited function herein, and not only structural equivalents but also equivalent structures. Other substitutions, modifications, changes and omissions may be made in the design, operating conditions and arrangement of the exemplary embodiments without departing from the scope of the present invention. Therefore, the present invention is not limited to the specific embodiments, but extends to various modifications that still fall within the scope of the appended claims. In addition, in order to provide a concise description of the exemplary embodiments, not all features of the actual embodiments may be described (i.e., those features that are not relevant to the currently contemplated best mode of carrying out the present invention, or those features that are not relevant to the implementation of the present invention).

[0112] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A nuclear reactor pressure vessel inner surface detection device, characterized in that: include, A pressure vessel barrel body (100); A guide rail body (200) is fixedly mounted above the pressure vessel barrel body (100), the guide rail body (200) comprising a fixing frame (201) and a guide rack (202) arranged on the middle surface of the fixing frame (201); and, An observation mechanism (300) is installed above the guide rail body (200), and the observation mechanism (300) comprises a mounting frame (301), a control motor (302) arranged on the outer surface of the mounting frame (301), a driving component (303) connected to the output end of the control motor (302), and a fastening belt (304) sleeved above the driving component (303); The observation mechanism (300) further comprises a connection assembly (305) located at the other side of the fastening belt (304), a rotation assembly (306) arranged at the side of the connection assembly (305), a rebound assembly (307) connected to the outside of the rotation assembly (306), a driving wheel (308) installed at the lower end of the driving assembly (303), and a shooting assembly (309) arranged outside the mounting frame (301); The driving assembly (303) comprises a driving rod (303a) and a driving gear (303b) installed outside the driving rod (303a); One end of the fastening belt (304) is sleeved on the outside of the driving rod (303a), the upper part of the driving rod (303a) is connected to the control motor (302), and the lower part of the driving rod (303a) is connected to the driving wheel (308); The connecting assembly (305) comprises a guide seat (305a), a guide rod (305b) arranged inside the guide seat (305a), and a connecting gear (305c) installed outside the guide rod (305b); The rotating assembly (306) comprises a first rotating gear (306a) and a second rotating gear (306b) connected to the outside of the first rotating gear (306a); The guide seat (305a) is arranged in an arc shape, the upper part of the guide rod (305b) is connected to the other end of the fastening belt (304), and the connecting gear (305c) is meshedly connected with the driving gear (303b); The rebound assembly (307) comprises a vertical plate (307a) arranged inside the mounting frame (301), a limiting rod (307b) installed between the vertical plates (307a), a clamping rack (307c) sleeved on the outside of the limiting rod (307b), and a compression spring (307d) located at a side end of the clamping rack (307c); Wherein, one side of the rack of the latching rack (307c) is connected to the second rotating gear (306b), and the latching rack (307c) slides outside the limiting rod (307b); The shooting assembly (309) comprises a transverse rod (309a) arranged between the two mounting frames (301), two electric telescopic rods (309b) slidably connected to the transverse rod (309a), and a camera (309c) arranged at the lower end of the electric telescopic rod (309b); Wherein, the camera (309c) is connected to the control terminal via a built-in signal.

2. A method for detecting the inner surface of a nuclear reactor pressure vessel, applied to the detection device according to claim 1, the detection method comprising the following steps: Acquiring an image of the inner wall of the pressure vessel barrel body (100) through a photographing component (309), and transmitting the acquired inner wall image to a control terminal; A deep convolutional neural network model is introduced to extract multi-scale features of the internal image, and the detailed features of the inner wall image are obtained through a multi-branch network structure; The inner wall feature information picture is obtained by fusion mechanism model; Analyze the inner wall feature information image, obtain the test report conclusion, and store the test report conclusion in the database.

3. The method for detecting the inner surface of a nuclear reactor pressure vessel according to claim 2, characterized in that: When the photographing component (309) acquires the inner wall image of the pressure vessel barrel body (100), the moving speed of the photographing component (309) is set to Lcm / s, and the size length of the inner wall image acquired by the photographing component (309) is Xcm, the interval length of the photographing by the photographing component (309) is Zs, and the photographing condition satisfies the formula: L*Z<X In the formula, L represents the moving speed, Z represents the shooting interval, and X represents the length of the captured image size; When acquiring the inner wall image of the pressure vessel barrel body (100), the shooting component (309) combines the inner wall image of the previous time to determine whether the side ends of the two inner wall images overlap. When the judgment result is overlap, a new inner wall image is output. When the judgment result is not overlap, the abnormal situation is transmitted to the control terminal. Then the control terminal issues a command to the control motor (302) to make the control motor (302) rotate in the opposite direction. The rotation time is set to Z / 4, and the inner wall image of the pressure vessel barrel body (100) is acquired again until the newly captured inner wall image overlaps with the side end of the previous inner wall image, and a new inner wall image is output.

4. The method for detecting the inner surface of a nuclear reactor pressure vessel according to claim 3, characterized in that: The method for obtaining the inner wall characteristic information picture includes: The inner wall image is cut into feature initial images with a length of X / 10cm and a width of Y / 4cm, and all feature initial images are marked with serial numbers in sequence. Feature recognition is performed on all feature initial images respectively, and the recognized feature information is marked on the corresponding feature initial images. Finally, according to the fusion mechanism model, all feature initial images are integrated together in sequence by marking serial numbers and output as an inner wall feature information image; Wherein, Y represents the width of the captured image size.

5. The method for detecting the inner surface of a nuclear reactor pressure vessel according to claim 4, characterized in that: The method for obtaining the conclusion of the test report includes: Search for all feature information of the inner wall feature information picture, set a weight according to the type of feature information, and obtain the weight value of the inner wall feature information picture through a calculation formula, which is expressed as: Q=λ1*β1+λ2*β2+λ3*β3+…+λ n *b n In the formula, Q is the weight value, λ1, λ2, λ3 and λ n They are represented by different types of feature information, β1, β2, β3 and β n They are respectively expressed as weights of different feature information types; Then, the obtained weight value is compared with a set threshold value. When the weight value is less than the set threshold value, the output detection report concludes that there is no abnormality. When the weight value is not less than the set threshold value, the inner wall feature information image is re-identified to obtain the abnormal area, and at the same time, a command is issued to the control motor (302) through the control terminal to stop the control motor (302) from running. Methods for obtaining abnormal areas include: Determine whether the feature initial image with the same serial number has 2 or more sets of feature information. If not, query the type of feature information with the largest weight and output the serial number of the type carrying the feature information. If it exists, output the serial number corresponding to 2 or more sets of feature information and generate the corresponding detection report conclusion.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for detecting the inner surface of a nuclear reactor pressure vessel according to any one of claims 2 to 5 are implemented.

Citation Information

Patent Citations

  • Automatic detection device and positioning method for weld joint at safe end of nuclear reactor pressure vessel

    CN101916597A

  • Nuclear rector pressure vessel nozzle safe end welding joint automatic ray inspection device

    CN102509566A