An intelligent detection system and method for transformer core

Abstract

The present invention discloses an intelligent detection system and method for transformer cores, which belongs to the field of transformer detection, and includes an X-axis moving module, a transfer device, a gantry and a detection module; the transport device is assembled on the X-axis moving module, the gantry is arranged on the X-axis moving module along the Y direction, and the detection module is arranged in the gantry. The intelligent detection system and method for transformer cores of the present invention have a simple overall structure and are easy to use. They can not only detect cores of different types and sizes, but also can judge whether there are defects in the appearance and stacking density of the cores through multiple cameras and control processing modules, replacing the traditional manual detection method, greatly improving the detection efficiency and detection accuracy, and have good use value and application prospects.

Description

Technical Field

[0001] The invention belongs to the field of transformer detection, and in particular relates to an intelligent detection system and method for a transformer core. Background Art

[0002] Transformers are a type of electrical energy transmission and conversion equipment that is widely used in power systems to increase or decrease voltage, and to transmit and distribute energy. The core components of transformers include windings and cores, and their performance and design have a significant impact on the efficiency, stability, and life of the transformer.

[0003] Before assembling the transformer winding, the various properties of the core need to be tested, and the most important of these are the tightness and misalignment of the core after stacking, as well as the defects on the core surface. When testing these defects, they are generally done manually or with manual handheld measuring instruments, but the overall detection efficiency is poor, the error is large, and it cannot meet the use requirements.

[0004] Therefore, we propose an intelligent detection system and method for transformer core to solve the above problems. Summary of the invention

[0005] In response to one or more of the above defects or improvement needs in the prior art, the present invention provides an intelligent detection system and method for transformer core, which carries the core to be inspected for movement through a transfer device and uses a detection module to collect external image data and internal image data of the core to determine possible defects on the surface of the core, thereby realizing high-precision and automated detection of the core.

[0006] To achieve the above-mentioned object, the present invention provides an intelligent detection system for transformer core, which includes an X-axis moving module, a transfer device, a gantry and a detection module;

[0007] Wherein, the transfer device is mounted on the X-axis moving module, the gantry is arranged on the X-axis moving module along the Y direction, and the detection module is arranged in the gantry;

[0008] The detection module includes a Z-axis moving module arranged on the inner side of the gantry, a second rotating platform is arranged on the Z-axis moving module, and a first detection camera, an infrared detection module and a telescopic member are arranged on the second rotating platform at equidistant intervals along the circumferential direction; the shooting of the first detection camera is arranged along the Y direction, and is used to collect external image data of the iron core, a micro motor is arranged at the telescopic end of the telescopic member, and a second detection camera is arranged at the rotating end of the micro motor, and a third detection camera is also arranged on the gantry, and its shooting direction is arranged along the vertical direction;

[0009] A reflective target is arranged inside the gantry and on a side opposite to the detection module, and matches the infrared detection module;

[0010] When the infrared light emitted by the infrared detection module can be reflected by the reflective target and receive a signal, the position of the second rotary platform is adjusted so that the first detection camera is located on the vertical axis of the second rotary platform, and the appearance image data of the entire iron core is collected by the first detection camera and the third detection camera; after the first detection camera completes the detection, the second detection camera is extended into the interior of the iron core to collect image data of the interior of the iron core;

[0011] The appearance image data and the internal image data of the iron core are transmitted to a control processing module, and the appearance image data and the internal image of the iron core are processed to detect defects on the surface and inside of the iron core.

[0012] As a further improvement of the present invention, the control processing module includes a first processing module and a second processing module.

[0013] The first processing module is respectively connected to the first detection camera and the third detection camera for receiving the external image data of the core captured by the first detection camera and the third detection camera, and processing the external image data to detect appearance defects on the surface of the core;

[0014] The second processing module is communicatively connected to the second detection camera, and is used to receive and process the internal image data of the iron core captured by the second detection camera to detect defects inside the iron core.

[0015] As a further improvement of the present invention, the transfer device includes a first rotating platform;

[0016] Two clamping mechanisms are arranged on the first rotating platform at intervals along the X and / or Y direction, and are used to fix the iron core to be detected on the first rotating platform and drive it to move along the X-axis direction.

[0017] As a further improvement of the present invention, the clamping mechanism includes two guide rails spaced apart along the Y direction on the first rotating platform, at least two clamping assemblies are arranged on the guide rails, and the clamping assemblies on the two guide rails are detachably connected on their sides close to each other.

[0018] As a further improvement of the present invention, the clamping assembly includes a slide seat, a slide groove is provided at the bottom of the slide seat, and the slide seat is slidably connected to the guide rail through the slide groove at the bottom;

[0019] A rotating shaft is arranged on the top of the sliding seat, a hinge bar is sleeved on the outer circumference of the rotating shaft, and a screw is arranged at one end of the hinge bar away from the rotating shaft;

[0020] The two screw rods located on the axis of the Y direction can be connected and assembled through a double-headed nut to achieve the limitation of the Y direction and the bottom of the iron core.

[0021] As a further improvement of the present invention, the clamping mechanism further includes two clamping assemblies spaced apart on the first rotating platform along the X direction, for limiting the position of the iron core in the X direction.

[0022] As a further improvement of the present invention, the iron core is a biaxial "C" type iron core; or

[0023] The iron core is a triaxial "E" type iron core.

[0024] On this basis, the present invention also provides an intelligent detection method for a transformer core, which is implemented using the above-mentioned intelligent detection system. The method comprises the following steps:

[0025] Assemble the iron core onto the transfer device and move it into the gantry via the X-axis moving module;

[0026] When the state of the infrared detection module changes from being on, off to being on for the second time, adjusting the position of the first detection camera so that it is located on the vertical axis of the second rotary platform;

[0027] Using the transfer device to adjust the position of the iron core on the XY plane, and using the first detection camera and the third detection camera to capture external image data of the iron core;

[0028] After collecting the external image data of the iron core, the iron core is adjusted to an initial state, the second detection camera is extended into the iron core, and the shooting angle of the second detection camera on the XZ plane is adjusted to collect the image data of the inside of the iron core;

[0029] The internal image data of the iron core and the external image data of the iron core are transmitted to a control processing module for processing to detect whether the iron core has defects.

[0030] As a further improvement of the present invention, the image processing of the interior of the iron core includes the following steps:

[0031] Adjust the shooting angle of the second detection camera to rotate the second detection camera around the Y axis, collect image data of each surface inside the iron core, and splice the collected images to form complete image data of the inside of the iron core;

[0032] Preprocess the complete image data inside the core and use edge detection algorithm to extract the edge image of each silicon steel sheet;

[0033] Extracting the outline of each silicon steel sheet from the extracted edge image, and obtaining the geometric center of each layer of silicon steel sheet when stacked according to the outline;

[0034] Calculate the difference in the geometric center positions of adjacent layers to obtain the actual offset between two adjacent layers, and calculate the distance between layers based on the design parameters;

[0035] Based on the designed offset and the actual offset, determine whether the core has misalignment or uneven defects.

[0036] As a further improvement of the present invention, the process of processing the image data of the outside of the core taken by the first detection camera and the third detection camera is as follows:

[0037] The collected image data are spliced ​​to form complete external image data of the iron core;

[0038] An edge detection image is extracted from the image by using an edge detection algorithm, and contour information is extracted from the edge image;

[0039] Extracting external features of the core from the contour information of the core, the external features including area, shape and circumference data of the core;

[0040] Classify defects using rule-based algorithms or machine learning models to form recognition models;

[0041] The characteristic data of the outside of the core is imported into the recognition model to obtain the defect type of the outer surface of the core.

[0042] The above-mentioned improved technical features can be combined with each other as long as they do not conflict with each other.

[0043] In general, compared with the prior art, the above technical solution conceived by the present invention has the following beneficial effects:

[0044] (1) The intelligent detection system and method for transformer core of the present invention respectively collects external image data and internal image data of the core through the detection module, and processes the image data through the control processing module to determine the defects that may exist on the surface of the core.

[0045] (2) The intelligent detection system and method for transformer core of the present invention, by setting the infrared detection module, the first detection camera and the second detection camera on the second rotating platform, enables the infrared detection module, the first detection camera and the second detection camera to be rotated to the central axis position of the second rotating platform in sequence, so that after the X-axis moving module drives the core to the position, it can detect it through the infrared detection module to determine whether the core has reached the specified position, and then adjust the first detection camera and the second detection camera to the central axis in sequence through the second rotating platform, so that the shooting range of the two cameras is in the Y direction, so that the shooting range can fully cover the core, so as to facilitate the image acquisition operation of the core.

[0046] (3) The intelligent detection system and method for transformer cores of the present invention optimizes the structural design of the transfer device so that it can not only fix the three-axis E-type cores, but also clamp and fix the two-axis C-type cores. In this way, the detection system can adapt to cores of different sizes and types, thereby improving the practicality of the system.

[0047] (4) The intelligent detection system and method for transformer cores of the present invention have a simple overall structure and are easy to use. They can not only detect cores of different types and sizes, but also determine whether there are defects in the appearance and stacking density of the cores through multiple cameras and control processing modules. They replace the traditional manual detection method, greatly improve the detection efficiency and detection accuracy, and have good use value and application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is a schematic diagram of the overall three-dimensional structure of the intelligent detection system in an embodiment of the present invention;

[0049] Figure 2 is a schematic diagram of the overall three-dimensional structure of the intelligent detection system in another perspective in an embodiment of the present invention;

[0050] Figure 3 It is a schematic diagram of the overall three-dimensional structure of the transfer device in the intelligent detection system in an embodiment of the present invention;

[0051] Figure 4 is a schematic diagram of the three-dimensional structure of a clamping component in an intelligent detection system in an embodiment of the present invention;

[0052] Figure 5 It is a schematic diagram of the overall three-dimensional structure of the detection module in the intelligent detection system in an embodiment of the present invention;

[0053] Figure 6 It is a three-dimensional structural diagram of the intelligent detection system in the embodiment of the present invention when detecting the triaxial E-type iron core;

[0054] Figure 7 is a schematic diagram of the overall side view structure of the intelligent detection system in an embodiment of the present invention;

[0055] Figure 8 is a flow chart of an intelligent detection method in an embodiment of the present invention;

[0056] In all the drawings, the same reference numerals represent the same technical features, specifically:

[0057] 100. X-axis moving module;

[0058] 200, transfer device; 201, Y-axis moving module; 202, first base; 203, first rotating platform; 204, guide rail; 205, clamping assembly; 2051, slide seat; 2052, rotating shaft; 2053, slide groove; 2054, hinge bar; 2055, screw rod; 2056, double-headed nut; 206, clamping assembly

[0059] 300, gantry; 301, reflective target; 302, third detection camera;

[0060] 400, detection module; 401, Z-axis moving module; 402, slider; 403, second base; 404, second rotary platform; 405, first detection camera; 406, telescopic member; 407, second detection camera; 408, infrared detection module;

[0061] 500. Control processing module; 600. Iron core. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0063] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. In addition, the technical features involved in each embodiment of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0064] Embodiment 1:

[0065] See also Figures 1 to 6 The intelligent detection system for transformer core in the preferred embodiment of the present invention is mainly used to detect the core formed by stacking multiple silicon steel sheets, and collect the external image data and internal image data of the core respectively through the set detection module, and then use the control processing module to process the image data to determine the possible defects on the surface of the core.

[0066] Specifically, if Figures 1 to 5 Specifically, as shown in Figures 1 to 5As shown in, the intelligent detection system in the preferred embodiment of the present invention includes an X-axis moving module 100, a transfer device 200, a gantry 300 and a detection module 400; wherein the transfer device 200 is assembled on the X-axis moving module 100, the gantry 300 is arranged on the X-axis moving module 100 along the Y direction, and the detection module 400 is arranged in the gantry 300; the detection module 400 includes a Z-axis moving module 401 arranged on the inner side of the gantry 300, and the Z-axis moving module 401 is provided with a second rotating platform 404, and the second rotating platform 404 is rotated along the circumferential direction. A first detection camera 405, an infrared detection module 408 and a telescopic member 406 are arranged at equal intervals; the shooting of the first detection camera 405 is arranged along the Y direction for collecting external image data of the iron core 600, and a micro motor is arranged at the telescopic end of the telescopic member 406, a second detection camera 407 is arranged at the rotating end of the micro motor, and a third detection camera 302 is also arranged on the gantry 300, and its shooting direction is arranged along the vertical direction; a reflective target 301 is arranged inside the gantry 300 and on the side opposite to the detection module 400, which matches the infrared detection module 408.

[0067] In actual use, the operator first limits the core 600 vertically to the transfer device 200, and then moves it along the X-axis moving module 100. When the core 600 has not moved to the bottom of the gantry 300, the detection light emitted by the infrared detection module 408 can be reflected by the reflective target 301, so that the infrared detection module 408 can receive the light emitted by it, so that the X-axis moving module 100 continues to drive the transfer device 200 and the core 600 to move. When the column of the core 600 blocks the light of the infrared detection module 408 for the first time, One end of the core 600 has moved to the gantry 300; when the infrared detection module 408 is able to receive the light emitted by itself for the second time, it means that the core 600 has been completely moved under the gantry 300, and the X-axis moving module 100 will stop operating after a period of time (it is worth noting that the period of time here refers to the time calculated by the operator based on the length of the core 600 and the speed of the X-axis moving module 100), so that the center of the core 600 can be aligned with the detection module 400 in the Y direction, so as to facilitate subsequent detection operations.

[0068] Meanwhile, it is worth noting that when the infrared detection module 408 detects the light reflected by the emission target for the second time, the second rotating platform 404 is controlled to rotate so that the first detection camera 405 rotates 90 degrees, ensuring that the first detection camera 405 is located on the vertical center line of the second rotating platform 404. Then, the first detection camera 405 and the third detection camera 302 respectively shoot a side surface and a top surface of the iron core 600, and at the same time, the transfer device 200 drives the iron core 600 to rotate around the XY plane, so that the first detection camera 405 can sequentially shoot the four sides of the iron core 600; after the iron core 600 rotates one circle, the detection of the outer surface of the iron core 600 is completed; then the second detection camera 407 is extended into the interior of the iron core 600 to collect the image data of the interior of the iron core 600, and the appearance image data and the internal image data of the iron core 600 are transmitted to the control processing module 500, and the appearance image data and the internal image data of the iron core 600 are processed to detect the defects on the surface and inside of the iron core 600.

[0069] In more detail, Figure 5 As shown in FIG. 4 , a second base 403 is disposed on the slider 402 of the Z-axis moving module 401 , and a second rotating platform 404 is disposed on the second base 403 .

[0070] More specifically, the control processing module 500 in the preferred embodiment of the present invention includes a first processing module and a second processing module. The first processing module is communicatively connected to the first detection camera 405 and the third detection camera 302, respectively, and is used to receive external image data of the iron core 600 captured by the first detection camera 405 and the third detection camera 302, and process the external image data to detect appearance defects on the surface of the iron core 600; the second processing module is communicatively connected to the second detection camera 407, and is used to receive and process internal image data of the iron core 600 captured by the second detection camera 407 to detect defects inside the iron core 600.

[0071] Furthermore, the transfer device 200 in the preferred embodiment of the present invention includes a first rotating platform 203, and two clamping mechanisms are arranged on the first rotating platform 203 at intervals along the X and / or Y direction, which are used to fix the iron core 600 to be tested on the first rotating platform 203 and drive it to move along the X-axis direction. At the same time, a Y-axis moving module 201 is provided at the bottom of the first rotating platform 203, which is used to adjust the position of the iron core 600 in the Y direction, and a first base 202 is provided on the Y-axis moving module 201, and the first rotating platform 203 is assembled on the first base 202.

[0072] In a specific embodiment, Figure 3As shown in , the clamping mechanism includes two guide rails 204 arranged on the first rotary platform 203 at intervals along the Y direction, and at least two clamping assemblies 205 are arranged on the guide rails 204, and the clamping assemblies 205 on the two guide rails 204 are detachably connected on the sides close to each other. The clamping assembly 205 includes a slide 2051, a slide groove 2053 is provided at the bottom of the slide 2051, and the slide 2051 is slidably connected to the guide rail 204 through the slide groove 2053 at the bottom, and a rotating shaft 2052 is arranged on the top of the slide 2051, and a hinge bar 2054 is sleeved on the outer periphery of the rotating shaft 2052, and a screw rod 2055 is arranged at one end of the hinge bar 2054 away from the rotating shaft 2052; and the two screw rods 2055 located on the Y axis can be connected and assembled through a double-headed nut 2056 to achieve the limitation of the iron core 600 in the Y direction and at the bottom.

[0073] In actual use, the iron core 600 can be clamped and fixed by the clamping assembly 205 designed on the guide rail 204, and the sliding design can adapt to iron cores 600 of different sizes and types, such as Figure 3 and Figure 7 The states shown in the figure respectively represent the states when the clamping assembly 205 clamps the "C" type iron core 600 and the "E" type iron core 600.

[0074] In another specific embodiment, Figure 3 As shown in FIG. 1 , the clamping mechanism further includes two clamping assemblies 206 spaced apart along the X direction on the first rotary platform 203 for limiting the position of the iron core 600 in the X direction.

[0075] In a specific application scenario, the core 600 detection device in the preferred embodiment of the present invention is adapted to a biaxial "C" type core 600. When the detected object is a "C" type core 600, its fixing method and image detection and acquisition method can refer to the description in the above embodiment 1.

[0076] Embodiment 2:

[0077] In this embodiment, what is different from Embodiment 1 is that the object detected by this system is a three-axis "E"-type iron core 600. When detecting the iron core 600, the infrared detection module 408 will detect the two gaps between the three columns of the "E"-type iron core 600 through the second detection camera 407 after receiving the light emitted by itself for the third time. In Embodiment 1, the two-axis "C"-type iron core 600 only needs to detect the gap between the two axes once.

[0078] In general, the present invention is an intelligent detection system and method for transformer subsidization, which drives the movement of the iron core through the X-axis moving module and detects the position of the iron core through the infrared detection module. At the same time, the design of the control logic of the infrared detection module 408 is used to make it fully fit the structural shape of the iron core itself, and multiple detection cameras are integrated with the infrared detection module 408. The positional relationship of the three functional modules is coordinated by rotation to ensure that the three functional modules can be aligned with the central position of the iron core at all times, avoiding secondary positioning in the subsequent image shooting process, greatly improving the detection efficiency, and making it applicable to a wider range of types.

[0079] On this basis, see Figure 8 The invention also provides an intelligent detection method for transformer core, which is implemented by using the intelligent detection system in the above preferred embodiment, and the method comprises the following steps:

[0080] S100: Assemble the core to the transfer device and move it into the gantry via the X-axis moving module.

[0081] S200: When the state of the infrared detection module changes from being on, off, to being on for the second time, adjusting the position of the first detection camera so that it is located on the vertical axis of the second rotary platform;

[0082] S300: Using the transfer device to adjust the position of the iron core on the XY plane, and using the first detection camera and the third detection camera to capture external image data of the iron core.

[0083] S400: After collecting the external image data of the iron core, adjust the iron core to an initial state, extend the second detection camera into the iron core, and adjust the shooting angle of the second detection camera on the XZ plane to collect image data inside the iron core;

[0084] S500: The internal image data of the iron core and the external image data of the iron core are transmitted to the control processing module for processing to detect whether the iron core has defects.

[0085] More specifically, in step S500, the image processing of the interior of the iron core includes the following steps:

[0086] S501: adjusting the shooting angle of the second detection camera, rotating the second detection camera around the Y axis, collecting image data of each surface inside the iron core, and splicing the collected images to form complete image data of the inside of the iron core.

[0087] S502: Then, the complete image data inside the iron core is preprocessed, and the edge detection algorithm is used to extract the edge image of each silicon steel sheet; and the contour is extracted from the edge image of each silicon steel sheet. Each contour is represented by a point set, and these point sets form the contour boundary of each layer of the iron core.

[0088] Specifically, in step S502, preprocessing the complete image data inside the iron core includes the following steps: converting the captured image into a grayscale image, smoothing it using a Gaussian filter, and finally enhancing the image to improve the contrast of the image.

[0089] S503: Obtain the geometric center of each layer of silicon steel sheets when stacked according to the contour. The geometric center can be obtained by the following formula:

[0090]

[0091] in, is the number of contour points, ( , ) is The coordinates of the points;

[0092] S504: Calculate the difference in the geometric center positions of adjacent layers to obtain the actual offset between two adjacent layers; the actual offset can be achieved by the following formula:

[0093]

[0094] in,( , ) is The geometric center point of the layer, ( , ) is The geometric center point of the layer.

[0095] S505: Based on the design parameters, calculate the distance between layers in an ideal situation, and determine whether the core has a problem of excessive interlayer spacing or tightness according to the designed offset and the actual offset.

[0096] Furthermore, the process of processing the image data of the outside of the iron core taken by the first detection camera and the third detection camera is as follows: splicing the collected image data to form a complete external image data of the iron core; extracting the edge detection image in the image through the edge detection algorithm, and extracting the contour information from the edge image; extracting the external features of the iron core from the contour information of the iron core, and the external features include the area, shape and circumference data of the iron core; using a rule-based algorithm or machine learning model to classify the defects to form a recognition model; importing the feature data of the outside of the iron core into the recognition model to obtain the defect type of the outer surface of the iron core. The above-mentioned recognition process for appearance defects is a conventional technical means of the prior art and will not be repeated here.

[0097] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent detection system for transformer core, characterized in that: It comprises an X-axis moving module (100), a transfer device (200), a gantry (300) and a detection module (400); The transfer device (200) is mounted on the X-axis moving module (100), the gantry (300) is arranged on the X-axis moving module (100) along the Y direction, and the detection module (400) is arranged in the gantry (300); The detection module (400) comprises a Z-axis moving module (401) arranged on the inner side of the gantry (300); a second rotating platform (404) is arranged on the Z-axis moving module (401); a first detection camera (405), an infrared detection module (408) and a telescopic member (406) are arranged on the second rotating platform (404) at equidistant intervals in a circumferential direction; the shooting direction of the first detection camera (405) is arranged along the Y direction, and is used to collect external image data of the iron core (600); a micro motor is arranged at the telescopic end of the telescopic member (406); a second detection camera (407) is arranged at the rotating end of the micro motor; and a third detection camera (302) is also arranged on the gantry (300), and its shooting direction is arranged along the vertical direction; A reflective target (301) is arranged inside the gantry (300) and on a side opposite to the detection module (400), and matches the infrared detection module (408); When the state of the infrared detection module (408) changes from being on, off, to being on for the second time, the second rotating platform (404) is adjusted so that the first detection camera (405) is located on the vertical axis of the second rotating platform (404), and the appearance image data of the entire iron core (600) is collected by the first detection camera (405) and the third detection camera (302); after the first detection camera (405) and the third detection camera (302) complete the detection, the second detection camera (407) is extended into the interior of the iron core (600) to collect image data of the interior of the iron core (600); The appearance image data and the internal image data of the iron core (600) are transmitted to a control processing module (500), and the appearance image data and the internal image of the iron core (600) are processed to detect defects on the surface and inside of the iron core (600).

2. The intelligent detection system for transformer core according to claim 1, characterized in that: The control processing module (500) comprises a first processing module and a second processing module. The first processing module is respectively connected to the first detection camera (405) and the third detection camera (302) for communication, and is used to receive external image data of the iron core (600) captured by the first detection camera (405) and the third detection camera (302), and process the external image data to detect appearance defects on the surface of the iron core (600); The second processing module is communicatively connected to the second detection camera (407) and is used to receive and process internal image data of the iron core (600) captured by the second detection camera (407) to detect defects inside the iron core (600).

3. The intelligent detection system for transformer core according to claim 1, characterized in that: The transfer device (200) comprises a first rotating platform (203); Two clamping mechanisms are arranged at intervals on the first rotating platform (203) along the X and / or Y direction, and are used to fix the iron core (600) to be tested on the first rotating platform (203) and drive it to move along the X-axis direction.

4. The intelligent detection system for transformer core according to claim 3, characterized in that: The clamping mechanism comprises two guide rails (204) arranged on the first rotary platform (203) at intervals along the Y direction, at least two clamping assemblies (205) are arranged on the guide rails (204), and the clamping assemblies (205) on the two guide rails (204) are detachably connected at their mutually adjacent sides.

5. The intelligent detection system for transformer core according to claim 4, characterized in that: The clamping assembly (205) comprises a slide seat (2051), a slide groove (2053) is provided at the bottom of the slide seat (2051), and the slide seat (2051) is slidably connected to the guide rail (204) via the slide groove (2053) at the bottom; A rotating shaft (2052) is arranged on the top of the sliding seat (2051), a hinge bar (2054) is sleeved on the outer circumference of the rotating shaft (2052), and a screw rod (2055) is arranged at one end of the hinge bar (2054) away from the rotating shaft (2052); Furthermore, the two screw rods (2055) located on the axis in the Y direction can be connected and assembled via a double-headed nut (2056) to achieve the limitation of the Y direction and the bottom of the iron core (600).

6. The intelligent detection system for transformer core according to claim 3, characterized in that: The clamping mechanism further comprises two clamping assemblies (206) arranged on the first rotating platform (203) at intervals along the X direction, and used for limiting the position of the iron core (600) in the X direction.

7. The intelligent detection system for transformer core according to any one of claims 1 to 6, characterized in that: The iron core (600) is a biaxial "C" type iron core; or The iron core (600) is a triaxial "E" type iron core.

8. An intelligent detection method for transformer core, characterized in that: The method is implemented by using the intelligent detection system according to any one of claims 1 to 7, and comprises the following steps: Assembling the iron core (600) onto the transfer device (200), and moving it into the gantry (300) via the X-axis moving module (100); When the state of the infrared detection module (408) changes from being on, off, to being on for the second time, adjusting the position of the first detection camera (405) so that it is located on the vertical axis of the second rotating platform (404); Using the transfer device (200) to adjust the position of the iron core (600) on the XY plane, and using the first detection camera (405) and the third detection camera (302) to capture external image data of the iron core (600); After collecting external image data of the iron core (600), the iron core (600) is adjusted to an initial state, the second detection camera (407) is extended into the iron core (600), and the shooting angle of the second detection camera (407) on the XZ plane is adjusted to collect image data of the interior of the iron core (600); The internal image data of the iron core (600) and the external image data of the iron core (600) are transmitted to the control processing module (500) for processing to detect whether the iron core (600) has defects.

9. The intelligent detection method for transformer core according to claim 8, characterized in that: The image processing of the interior of the iron core (600) comprises the following steps: Adjusting the shooting angle of the second detection camera (407) so that the second detection camera (407) rotates around the Y axis, collecting image data of each surface inside the iron core (600), and splicing the collected images to form complete image data of the inside of the iron core (600); Preprocessing the complete image data inside the iron core (600), and extracting the edge image of each silicon steel sheet using an edge detection algorithm; Extracting the outline of each silicon steel sheet from the extracted edge image, and obtaining the geometric center of each layer of silicon steel sheet when stacked according to the outline; Calculate the difference in the geometric center positions of adjacent layers to obtain the actual offset between two adjacent layers, and calculate the distance between layers based on the design parameters; According to the designed offset and the actual offset, it is determined whether the iron core (600) has a misalignment or uneven defect.

10. The intelligent detection method for transformer core according to claim 8, characterized in that: The process of processing the image data of the outside of the iron core (600) photographed by the first detection camera (405) and the third detection camera (302) is as follows: splicing the collected image data to form complete external image data of the iron core (600); An edge detection image is extracted from the image by using an edge detection algorithm, and contour information is extracted from the edge image; Extracting external features of the iron core (600) from the contour information of the iron core (600), the external features including area, shape and perimeter data of the iron core (600); Classify defects using rule-based algorithms or machine learning models to form recognition models; The characteristic data of the outside of the iron core (600) is imported into the recognition model to obtain the defect type of the outer surface of the iron core (600).

Images