Full-automatic magnetic particle flaw detector for axle AI defect identification

Abstract

A full-automatic magnetic particle flaw detector for axle AI defect recognition comprises an axle conveying unit, and an axle cleaning unit and a flaw detection unit are sequentially arranged in the conveying direction of the axle conveying unit. The flaw detection unit comprises a base, and a circumferential magnetization mechanism and a longitudinal magnetization mechanism are arranged on the base; the longitudinal magnetization mechanism comprises a translation assembly capable of transversely moving along the base, and a magnetization coil, a magnetic powder liquid spraying assembly and a detection assembly are arranged on the translation assembly; wherein the magnetizing coil magnetizes the axle through an alternating current induction method; the detection assembly comprises a mounting frame connected with the translation assembly, and a plurality of first fluorescent light sources capable of ascending and descending are arranged on the mounting frame in rows in the transverse direction and used for providing illumination fluorescence with adjustable intensity for the surface of the axle; a plurality of first CCD cameras are arranged on the two sides of the fluorescent light source in an angled mode, and the shooting ends of the first CCD cameras and the lighting ends of the first fluorescent light source face the central axis of the magnetizing coil and are used for capturing magnetic mark images of a fluorescent lighting area on the surface of the axle.

Description

Technical Field

[0001] This utility model relates to the field of nondestructive testing technology, and in particular to a fully automatic magnetic particle flaw detector for axle AI defect recognition. Background Technology

[0002] As a critical component of rail transit vehicles, the quality of axles directly affects the safety of vehicle operation. Traditional axle flaw detection methods mainly rely on manual operation, which suffers from low detection efficiency, large human error, and high labor intensity. With the development of artificial intelligence technology, automated flaw detection equipment is gradually becoming an industry trend. However, existing equipment still has shortcomings in terms of magnetization uniformity, detection accuracy, and automation level, making it difficult to meet the needs of large-scale production.

[0003] Therefore, in view of the shortcomings of the existing technology, it is necessary to design a fully automatic magnetic particle flaw detector for axle AI defect recognition to solve the above problems.

[0004] It should be noted that the above introduction to the technical background is only for the purpose of providing a clear and complete explanation of the technical solution of this utility model and facilitating the understanding of those skilled in the art. It should not be assumed that the above content is known to those skilled in the art simply because it has been described in the background section of this utility model. Utility Model Content

[0005] To overcome the shortcomings of the prior art, the present invention discloses a fully automatic magnetic particle flaw detector for axle AI defect recognition. Through automated conveying, cleaning, magnetization and detection, combined with an artificial intelligence control model, it can achieve efficient and accurate identification of surface and near-surface defects of axles.

[0006] This utility model discloses a fully automatic magnetic particle inspection machine for axle AI defect recognition, including an axle conveying unit. Along the conveying direction of the axle conveying unit, an axle cleaning unit and a flaw detection unit are sequentially arranged. The axle is conveyed sequentially to the cleaning unit and the flaw detection unit by the axle conveying unit, ensuring the continuity of the inspection process. The cleaning unit is used to remove oil and iron filings from the axle surface. The axle conveying unit, the axle cleaning unit, and the flaw detection unit are all connected to an intelligent controller. The flaw detection unit includes a base with a circumferential magnetization mechanism and a longitudinal magnetization mechanism. The circumferential magnetization mechanism magnetizes the axle circumferentially; the longitudinal magnetization mechanism magnetizes the axle longitudinally. The circumferential and longitudinal magnetization mechanisms are independently controlled to avoid electromagnetic interference between them and ensure the flaw detection effect. The longitudinal magnetization mechanism includes a translation component that can move laterally along the base. The translation component is equipped with a magnetization coil, a magnetic powder spraying component, and a detection component. The magnetization coil magnetizes the axle using AC induction. The magnetic powder spraying component sprays magnetic powder onto the axle surface. The detection component includes a mounting frame connected to the translation component. Multiple liftable first fluorescent light sources are arranged on the mounting frame to provide adjustable intensity illumination fluorescence to the axle surface. Multiple first CCD cameras are angled to both sides of the fluorescent light sources. The imaging ends of the first CCD cameras and the illumination ends of the first fluorescent light sources are both oriented towards the central axis of the magnetization coil to capture magnetic trace images of the fluorescently illuminated area on the axle surface.

[0007] Preferred technical solution: The first fluorescent light sources are arranged at an angle, and the illumination ends of the multiple first fluorescent light sources all converge towards the same position. By controlling the rise and fall of the first fluorescent light sources, the fluorescence illumination range and intensity at the beam convergence position can be adjusted.

[0008] Preferred technical solution: The circumferential magnetization mechanism includes clamping electrodes arranged opposite to each other at both ends of the magnetization coil. The clamping electrodes are connected to a workpiece clamping drive, which is mounted on a base. The workpiece clamping drive can drive the clamping electrodes to move along the central axis of the magnetization coil, so that the clamping electrodes can be docked with both ends of the axle.

[0009] Preferred technical solution: A support roller assembly is provided below the clamping electrode. The support roller assembly consists of two parallel support rollers connected to a support roller transmission mechanism. The support roller assembly lifts the axle and drives it to rotate, facilitating automatic detection of the axle's outer circumference. The workpiece clamping drive can also drive the clamping electrode to move up and down, and the intelligent controller automatically aligns it with the end of the axle.

[0010] Preferred technical solution: A second CCD camera and a second fluorescent light source are provided at the roller assembly. The shooting end of the second CCD camera and the illumination end of the second fluorescent light source are set towards the axle end to detect defects in the axle end and the stepped area.

[0011] Preferred technical solution: The magnetic powder liquid spraying component is connected to the online detection and control device for magnetic suspension concentration to monitor the concentration in real time and adjust the amount of magnetic powder added.

[0012] Preferred technical solution: A magnetic suspension recovery pump station is installed under the base to recover the magnetic suspension, ensuring the recycling of the magnetic suspension and reducing resource waste.

[0013] Preferred technical solution: The axle cleaning unit is equipped with a water mist treatment device to treat the water mist generated during the cleaning process and maintain a clean working environment.

[0014] Preferred technical solution: The intelligent controller is equipped with an AI defect recognition model to control the timing and parameters of the conveying, cleaning, magnetizing and spraying processes, receive CCD camera image data, and dynamically identify axle defects.

[0015] Due to the application of the above technical solution, the beneficial effects of this utility model compared with the prior art are as follows:

[0016] 1) Employing a height-adjustable fluorescent light source and angled CCD cameras, the illumination range and intensity can be adjusted according to the surface shape of the axle, ensuring clear imaging of defective areas and facilitating accurate identification by the AI ​​model.

[0017] 2) It integrates functions such as axle conveying, cleaning, magnetization, spraying, and detection. The intelligent controller coordinates the working sequence of each unit, realizing fully automated operation, reducing manual intervention, and significantly improving detection efficiency.

[0018] 3) Equipped with an AI defect recognition model, it can dynamically analyze magnetic trace images captured by CCD cameras, automatically identify and classify defects on the axle surface, reduce errors in human judgment, and improve the accuracy and reliability of defect detection.

[0019] 4) The magnetic powder liquid spraying component is connected to the online detection and control device for magnetic suspension concentration, which can monitor the magnetic suspension concentration in real time and automatically adjust the amount of magnetic powder added to ensure that the magnetic powder liquid is always in the optimal concentration state.

[0020] 5) The cleaning unit is equipped with a water mist treatment device to effectively treat the water mist generated during the cleaning process. The equipment is also equipped with a magnetic suspension recovery pump station, which can recover and recycle the magnetic suspension, reducing resource waste.

[0021] 6) The equipment can not only detect the outer peripheral surface of the axle, but also detect defects in the axle end and stepped area through a second CCD camera and a second fluorescent light source, realizing full-surface coverage detection of the axle. Attached Figure Description

[0022] To more clearly illustrate the specific embodiments of this utility model or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this utility model. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram of the structure of a fully automatic magnetic particle flaw detector for axle AI defect recognition according to this utility model;

[0024] Figure 2 This is a schematic diagram of the flaw detection unit in this utility model;

[0025] Figure 3 This is a schematic diagram of the circumferential magnetization mechanism in this utility model;

[0026] Figure 4 This is a schematic diagram of the longitudinal magnetization mechanism in this utility model;

[0027] Figure 5 for Figure 4 A magnified view of a portion of point A in the middle.

[0028] In the attached figures above, 1. Axle conveying unit; 2. Axle cleaning unit; 21. Water mist treatment device; 3. Flaw detection unit; 31. Base; 32. Circumferential magnetization mechanism; 321. Clamping electrode; 322. Workpiece clamping drive; 323. Roller assembly; 323a. Roller; 323b. Roller transmission mechanism; 323c. Second CCD camera; 323d. Second fluorescent light source; 33. Longitudinal magnetization mechanism; 331. Translation assembly; 332. Magnetization coil; 333. Magnetic powder liquid spraying assembly; 334. Detection assembly; 334a. Mounting frame; 334b. First fluorescent light source; 334c. First CCD camera; 335. Online detection and control device for magnetic suspension concentration; 34. Magnetic suspension recovery pump station; 4. Intelligent controller; 5. Axle. Detailed Implementation

[0029] The following specific embodiments illustrate the implementation of this utility model. Those skilled in the art can easily understand other advantages and effects of this utility model from the content disclosed in this specification.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate for the description of embodiments of this application herein. Furthermore, the terms "comprising" and "having," and their synonyms, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] In this application, the terms "upper," "lower," "left," "right," "front," "rear," "top," "bottom," "inner," "outer," "middle," "vertical," "horizontal," "lateral," and "longitudinal" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are primarily for the purpose of better describing the present invention and its embodiments, and are not intended to limit the indicated device, element, or component to having a specific orientation, or to be constructed and operated in a specific orientation.

[0032] Furthermore, in addition to indicating direction or positional relationship, some of the aforementioned terms may also have other meanings. For example, the term "above" may also be used in some cases to indicate a certain dependency or connection relationship. Those skilled in the art can understand the specific meaning of these terms in this utility model according to the specific circumstances.

[0033] Furthermore, the terms "installation," "setting," "equipped with," "connection," "linking," "fitting," and "fitting" should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or an internal connection between two devices, components, or parts. Similarly, "fitting" can mean completely or partially fitted. Those skilled in the art can understand the specific meaning of the above terms in this utility model based on the specific circumstances.

[0034] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0035] Example:

[0036] like Figure 1As shown, this utility model discloses a fully automatic magnetic particle flaw detector for axle AI defect recognition, including an axle conveying unit 1, an axle cleaning unit 2, a flaw detection unit 3, and an intelligent controller 4. The main components of this utility model will be described in detail below:

[0037] like Figure 1 As shown, the axle conveying unit 1 is used to convey the axle 5 sequentially to the cleaning unit 2 and the flaw detection unit 3 along the conveying direction.

[0038] like Figure 1 As shown, the axle cleaning unit 2 is located in the conveying direction of the conveying unit 1 and is used to clean the surface of the axle 5. The cleaning unit 2 is equipped with a water mist treatment device 21 to treat the water mist generated during the cleaning process.

[0039] like Figure 1 , Figure 2 , Figure 3 , Figure 4 and Figure 5 As shown, the flaw detection unit 3 is located in the conveying direction of the conveying unit 1, and includes a base 31 that supports the entire flaw detection unit. The base 31 integrates:

[0040] The circumferential magnetization mechanism 32 is used to circumferentially magnetize the axle 5. It includes a clamping electrode 321 arranged opposite to both ends of the magnetization coil 332. The clamping electrode 321 is connected to the workpiece clamping drive 322, which is mounted on the base 31. The workpiece clamping drive 322 can drive the clamping electrode 321 to move along the central axis of the magnetization coil 332, and is used to control the connection between the clamping electrode 321 and both ends of the axle 5.

[0041] Below the clamping electrode 321 is a support roller assembly 323, which consists of two parallel support rollers 323a. The support rollers 323a are connected to the support roller transmission mechanism 323b, so that the support roller assembly 323 can support the axle 5 and control its rotation. The workpiece clamping drive 322 can also drive the clamping electrode 321 to move up and down, and can automatically position according to the outer diameter of the axle 5, so that the clamping electrode 321 is concentrically aligned with the axle 5.

[0042] The roller assembly 323 is equipped with a second CCD camera 323c and a second fluorescent light source 323d. The shooting end of the second CCD camera 323c and the illumination end of the second fluorescent light source 323d are set towards the end of the axle 5 to detect defects at the end of the axle 5.

[0043] The longitudinal magnetization mechanism 33 is used to longitudinally magnetize the axle 5. It includes a translation component 331 that can move laterally along the base 31. The translation component 331 is equipped with a magnetization coil 332 for generating a longitudinal magnetic field, a magnetic powder spraying component 333 for spraying magnetic powder liquid onto the surface of the axle 5, and a detection component 334. The detection component 334 includes a mounting frame 334a connected to the translation component 331. Multiple liftable first fluorescent light sources 334b ​​are arranged in a row laterally on the mounting frame 334a. The brightness and coverage of the fluorescent illuminated area on the axle 5 are adjusted by controlling the lifting and lowering of the first fluorescent light sources 334b. Multiple first CCD cameras 334c are arranged at an angle on both sides of the fluorescent light sources 334b. The shooting end of the first CCD camera 334c and the illumination end of the first fluorescent light source 334b ​​are both set towards the central axis of the magnetization coil 332, so as to capture magnetic trace images of the fluorescent illuminated area on the surface of the axle 5 from multiple angles.

[0044] like Figure 1 , Figure 2 , Figure 3 and Figure 4 As shown, the axle conveying unit 1, the axle cleaning unit 2, and the flaw detection unit 3 are all connected to the intelligent controller 4, which is equipped with an AI defect recognition model.

[0045] refer to Figure 1 , Figure 2 , Figure 3 , Figure 4 and Figure 5 As shown, the usage method and principle of this utility model are as follows: The axle 5 enters the cleaning unit 2 through the conveying unit 1. The cleaning unit 2 cleans the surface of the axle 5, and the water mist treatment device 21 treats the water mist generated during the cleaning process. After cleaning, the axle 5 enters the flaw detection unit 3. The workpiece clamping drive 322 of the circumferential magnetization mechanism 32 drives the clamping electrode 321 to align with the axis of the axle 5 and clamp the axle 5. Simultaneously, the support roller assembly 323 supports and rotates the axle 5. The translation component 331 of the longitudinal magnetization mechanism 33 drives the magnetization coil 332 to move laterally, longitudinally magnetizing the axle 5. The magnetic powder spraying component 333 sprays magnetic powder liquid onto the surface of the axle 5. The first fluorescent light source 334b ​​of the detection component 334 irradiates the surface of the axle 5, and the first CCD camera 334c captures defect images of the axle 5 surface. The second fluorescent light source 323d at the support roller assembly 323 irradiates the axle end, and the second CCD camera 323c captures defect images of the axle end. The intelligent controller 4 receives the inspection images and automatically analyzes and identifies defects on the surface and end of the axle 5 through the AI ​​defect recognition model. At the same time, it controls the axle conveying unit 1, the axle cleaning unit 2, and the flaw detection unit 3 to improve inspection efficiency and accuracy.

[0046] like Figure 1 , Figure 4 and Figure 5As shown, the first fluorescent light sources 334b ​​are arranged at an angle, and the illumination ends of the multiple first fluorescent light sources 334b ​​converge towards the same position, thereby enhancing the light intensity and uniformity of the surface fluorescent illuminated area.

[0047] like Figure 1 , Figure 2 , Figure 3 , Figure 4 and Figure 5 As shown, the magnetic powder liquid spraying assembly 333 is further connected to the magnetic suspension concentration online detection and control device 335 to monitor and control the magnetic suspension concentration in real time.

[0048] like Figure 1 and Figure 2 As shown, a magnetic suspension recovery pump station 34 is further provided below the base 31 to recover the magnetic suspension and achieve recycling.

[0049] This utility model discloses a fully automated magnetic particle inspection machine for axle AI defect recognition. Through a highly integrated automation system and advanced AI technology, it achieves efficient and accurate detection of axle surface defects. Its entire process utilizes AI intelligent control, giving it significant advantages in the industrial inspection field. It can greatly improve inspection efficiency and accuracy while reducing resource waste and labor costs.

[0050] Finally, it should be noted that the above are merely preferred embodiments of the present utility model and are not intended to limit the present utility model. Although the present utility model has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present utility model should be included within the protection scope of the present utility model.

Claims

1. A fully automated magnetic particle inspection machine for axle AI defect recognition, comprising an axle conveying unit (1), characterized in that: Along the conveying direction of the axle conveying unit (1), an axle cleaning unit (2) and a flaw detection unit (3) are sequentially arranged. The axle conveying unit (1), the axle cleaning unit (2), and the flaw detection unit (3) are all connected to the intelligent controller (4). The flaw detection unit (3) includes a base (31), on which a circumferential magnetization mechanism (32) and a longitudinal magnetization mechanism (33) are provided. The longitudinal magnetization mechanism (33) includes a translation component (331) that can move laterally along the base (31), and a magnetization coil is provided on the translation component (331). (332), magnetic powder liquid spraying assembly (333) and detection assembly (334); the detection assembly (334) includes a mounting frame (334a) connected to the translation assembly (331), and a plurality of liftable first fluorescent light sources (334b) are arranged on the mounting frame (334a); a plurality of first CCD cameras (334c) are arranged at an angle on both sides of the fluorescent light sources (334b); the shooting end of the first CCD camera (334c) and the illumination end of the first fluorescent light source (334b) are both arranged towards the central axis of the magnetization coil (332).

2. The fully automatic magnetic particle flaw detector for axle AI defect recognition as described in claim 1, characterized in that: The first fluorescent light sources (334b) are arranged at an angle to each other, and the illumination ends of the multiple first fluorescent light sources (334b) all converge towards the same position.

3. The fully automatic magnetic particle flaw detector for axle AI defect recognition as described in claim 1, characterized in that: The circumferential magnetization mechanism (32) includes clamping electrodes (321) arranged opposite to each other at both ends of the magnetization coil (332). The clamping electrodes (321) are connected to a workpiece clamping drive (322). The workpiece clamping drive (322) is mounted on the base (31). The workpiece clamping drive (322) can drive the clamping electrodes (321) to move along the central axis of the magnetization coil (332).

4. The fully automatic magnetic particle inspection machine for axle AI defect recognition according to claim 3, characterized in that: Below the clamping electrode (321) is a roller assembly (323), which consists of two parallel rollers (323a) connected to a roller transmission mechanism (323b). The workpiece clamping drive (322) can also drive the clamping electrode (321) to move up and down.

5. The fully automatic magnetic particle flaw detector for axle AI defect recognition according to claim 4, characterized in that: The roller assembly (323) is provided with a second CCD camera (323c) and a second fluorescent light source (323d), with the shooting end of the second CCD camera (323c) and the illumination end of the second fluorescent light source (323d) facing the axle end.

6. The fully automatic magnetic particle flaw detector for axle AI defect recognition according to claim 1, characterized in that: The magnetic powder liquid spraying assembly (333) is connected to the magnetic suspension liquid concentration online detection and control device (335).

7. The fully automatic magnetic particle inspection machine for axle AI defect recognition according to claim 1, characterized in that: A magnetic suspension recovery pump station (34) is provided below the base (31).

8. The fully automatic magnetic particle flaw detector for axle AI defect recognition according to claim 1, characterized in that: The axle cleaning unit (2) is equipped with a water mist treatment device (21).

9. The fully automatic magnetic particle flaw detector for axle AI defect recognition according to claim 1, characterized in that: The intelligent controller (4) is equipped with an AI defect recognition model.

Images