Magnetic therapy coil glue filling defect detection system and method, equipment and medium

Abstract

The invention provides a glue pouring defect detection system and method for a magnetic therapy coil, and a composite excitation module of the system is used for generating near-infrared light to irradiate a detection region so as to activate non-magnetic reversible thermosensitive particles in a pouring sealant to generate heat; the multiband infrared imaging module is used for synchronously acquiring multiband thermal images; and the thermal field intelligent analysis module is used for processing the multi-band thermal image, classifying defect types and outputting three-dimensional coordinates and sizes. According to the invention, zero magnetic field interference can be realized; the magnetic susceptibility of the non-magnetic reversible thermosensitive particles is 1t; (10-5), actually measuring the center magnetic field intensity of the coil and the deviation lt when the glue is not poured when the vacuum is close; the uniformity deviation (standard deviation) of the magnetic field is basically consistent with the uniformity deviation of the magnetic field without glue pouring; the photo-thermal excitation has no electromagnetic radiation, so that the interference to a magnetic induction coil is avoided; the defect detection sensitivity reaches 0.05 mm, bubbles with the diameter being 0.08 mm and cracks with the width being 0.06 mm can be recognized, and the positioning error is + / -0.02 mm.

Description

Technical Field

[0001] The present invention relates to the technical field of nondestructive testing and medical electronic manufacturing, and in particular to a magnetic therapy coil glue filling defect detection system and method, equipment and medium. Background Art

[0002] The purpose of glue filling for magnetic therapy coils is to fix the coil structure and prevent vibration or environmental factors. If there are bubbles or cracks inside after glue filling, it may affect the performance of the coil, cause excessive noise during the treatment process, and even cause the coil to malfunction. Therefore, defect detection after glue filling is very important.

[0003] Among traditional nondestructive testing methods, ultrasonic testing requires contact with coupling agents, which can easily contaminate the product surface and may encounter material attenuation problems, especially when the acoustic impedance of the potting compound is very different from that of the coil material, which can cause ultrasonic reflection or signal attenuation problems. Conventional infrared thermal imaging is limited by the thermal conductivity of the colloid, has insufficient sensitivity to tiny defects (<0.5mm), and is greatly affected by environmental interference. In addition, high-precision industrial CT detection technology is expensive and requires professional personnel to operate, which cannot meet the full inspection needs of the production line. Traditional magnetic induction heating detection requires pre-embedded magnetic particles, which leads to distortion of the coil's working magnetic field, such as a decrease in magnetic field strength and deterioration in the uniformity of magnetic field distribution.

[0004] Therefore, it is necessary to provide a new method to solve the above technical problems. Summary of the invention

[0005] In order to achieve the above-mentioned purpose and other advantages of the present invention, the first purpose of the present invention is to provide a magnetic therapy coil glue filling defect detection system, including a composite excitation module, a multi-band infrared imaging module, and a thermal field intelligent analysis module; wherein,

[0006] The composite excitation module is used to generate near-infrared light to illuminate the detection area, so as to activate the non-magnetic reversible thermosensitive particles in the potting glue to generate heat;

[0007] The multi-band infrared imaging module is used to synchronously collect multi-band thermal images;

[0008] The thermal field intelligent analysis module is used to process the multi-band thermal images, classify defect types, and output three-dimensional coordinates and dimensions.

[0009] Furthermore, the composite excitation module includes a laser array module and an optical window. The laser array module integrates multiple near-infrared lasers. The near-infrared light generated by the near-infrared laser is uniformly irradiated to the detection area through optical fiber. The optical window is placed on the surface of the glue-filled layer to achieve near-infrared light transmission.

[0010] Further, the laser power of the laser array module adjusts the laser power according to the colloid thickness, and the formula is:

[0011] P = P0 × [1 + γ·ln(d / d0)]

[0012] where P0 is the reference power, d is the colloid thickness, and γ is the material attenuation coefficient.

[0013] Further, the multi-band infrared imaging module includes a dual-band infrared camera and a synchronization control module. The dual-band infrared camera is used to synchronously collect long-wave and mid-wave thermal images, and the synchronization control module is used to control the microsecond-level timing synchronization of the excitation signal and infrared sampling to avoid signal blurring caused by heat diffusion.

[0014] Further, the thermal field intelligent analysis module includes a preprocessing module, a three-dimensional heat diffusion modeling module, a defect inversion module, and a convolutional neural network module. The preprocessing module is used to perform noise filtering preprocessing on the input sequence data of the time-series thermal images. The three-dimensional heat diffusion modeling module and the defect inversion module are used to adopt a three-dimensional heat conduction inversion algorithm to locate defects according to the heat diffusion rate difference. The convolutional neural network module is used to classify the defect types and output the three-dimensional coordinates and dimensions.

[0015] The second object of the present invention is to provide a method for detecting the potting defects of a magnetic therapy coil, which is applied to the above system and includes the following steps:

[0016] Generate near-infrared light to irradiate the detection area to activate the non-magnetic reversible thermosensitive particles in the potting glue to generate heat;

[0017] Synchronously collect multi-band thermal images;

[0018] Process the multi-band thermal images, classify the defect types, and output the three-dimensional coordinates and dimensions.

[0019] Further, the multi-band thermal images are configured as long-wave and mid-wave thermal images.

[0020] Further, the step of processing the multi-band thermal images, classifying the defect types, and outputting the three-dimensional coordinates and dimensions includes:

[0021] Preprocess the input sequence data of the time-series thermal images;

[0022] Perform three-dimensional heat diffusion modeling and defect inversion on the preprocessed data;

[0023] Output parameters through the convolutional neural network, including the defect position, size, and confidence level.

[0024] Further, the step of preprocessing the input sequence data of the time-series thermal images includes:

[0025] Perform differential calculation and noise filtering on the sequential thermal image sequence data.

[0026] Furthermore, the step of performing three-dimensional heat diffusion modeling and defect inversion on the preprocessed data includes:

[0027] Perform three-dimensional heat diffusion modeling on the preprocessed data through finite element mesh generation and boundary condition setting;

[0028] Iteratively optimize through the genetic algorithm.

[0029] Furthermore, it further includes the step of:

[0030] Adjust the laser power according to the colloid thickness, and the formula is:

[0031] P = P0 × [1 + γ · ln(d / d0)]

[0032] where P0 is the reference power, d is the colloid thickness, and γ is the material attenuation coefficient.

[0033] The third object of the present invention is to provide a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the steps of the above method are implemented.

[0034] The fourth object of the present invention is to provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0035] Compared with the prior art, the beneficial effects of the present invention are:

[0036] The present invention provides a magnetic therapy coil potting defect detection system, method, device, and medium, achieving zero magnetic field interference: the magnetic susceptibility (χ < 10-5) of non-magnetic reversible thermosensitive particles is close to that of a vacuum, and the measured magnetic field intensity at the center of the coil deviates by < 0.3% from that without potting, and the magnetic field uniformity deviation (standard deviation) is basically the same as that without potting; having high safety: photo-thermal excitation has no electromagnetic radiation, avoiding interference with the magnetic induction coil; having high sensitivity: the defect detection sensitivity reaches 0.05 mm, capable of identifying Φ0.08 mm air bubbles and 0.06 mm wide cracks, with a positioning error of ±0.02 mm.

[0037] The above description is only an overview of the technical solution of the present invention. In order to be able to understand the technical means of the present invention more clearly and implement it according to the content of the specification, the following will be described in detail with reference to the preferred embodiments of the present invention and the accompanying drawings. The specific implementation manners of the present invention are given in detail by the following embodiments and their accompanying drawings. Description of the Drawings

[0038] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0039] Figure 1 This is a schematic diagram of the magnetic therapy coil glue filling defect detection system;

[0040] Figure 2 A flow chart of the method for detecting defects in the magnetic therapy coil glue filling;

[0041] Figure 3 Multi-band thermal image processing flow Figure 1 ;

[0042] Figure 4 Multi-band thermal image processing flow Figure 2 ;

[0043] Figure 5 It is a schematic diagram of computer equipment;

[0044] Figure 6 A schematic diagram of a computer-readable storage medium. DETAILED DESCRIPTION

[0045] The present invention is further described below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. It should be noted that, under the premise of no conflict, the embodiments or technical features described below can be arbitrarily combined to form a new embodiment.

[0046] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0047] The figure numbers in this application are only used to distinguish the various steps in the scheme, and are not used to limit the execution order of the various steps. The specific execution order is subject to the description in the specification.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0049] Example 1

[0050] A magnetic therapy coil glue filling defect detection system combines enhanced thermal excitation strategy and multi-modal infrared thermal imaging analysis technology to detect internal bubbles / cracks after glue filling of magnetic therapy coils and other precision electronic devices. Figure 1As shown, the system includes a composite excitation module, a multi-band infrared imaging module, and a thermal field intelligent analysis module; among them,

[0051] The composite excitation module is used to generate near-infrared light to irradiate the detection area, so as to activate the non-magnetic reversible thermosensitive particles in the potting glue to generate heat;

[0052] The multi-band infrared imaging module is used to synchronously collect multi-band thermal images;

[0053] The thermal field intelligent analysis module is used to process the multi-band thermal images, classify the defect types, and output the three-dimensional coordinates and dimensions.

[0054] In some embodiments, the composite excitation module includes a laser array module and an optical window. The laser array module integrates multiple near-infrared lasers. For example, it integrates multiple near-infrared lasers with a wavelength of 800 nm and adjustable power density, and can emit 800 nm laser pulses. The near-infrared light generated by the near-infrared lasers is uniformly irradiated to the detection area through optical fibers. The optical window is placed on the surface of the potting layer. For example, a transparent quartz glass window is embedded on the surface of the potting layer to achieve near-infrared light transmission. For example, ensure that the laser transmittance > 90%.

[0055] Among them, non-magnetic reversible thermosensitive particles (carbon-coated boron nitride nanosheets) are added to the potting glue. This material has the advantages of non-magnetism and good thermal response effect.

[0056] Optionally, the near-infrared laser array module emits 800 nm laser pulses to irradiate the optical window optical fiber to achieve uniform irradiation of the detection area, activate the non-magnetic reversible thermosensitive particles to generate heat, and the non-magnetic reversible thermosensitive particles do not generate heat after the light is stopped. Further, the laser power of the laser array module adjusts the laser power according to the colloid thickness, and the formula is:

[0057] P = P0 × [1 + γ·ln(d / d0)]

[0058] Wherein, P0 is the reference power, d is the colloid thickness, and γ is the material attenuation coefficient.

[0059] In some embodiments, the multi-band infrared imaging module includes a dual-band infrared camera and a synchronous control module. The dual-band infrared camera is used to synchronously collect long-wave (LWIR 7-14 μm) and mid-wave (MWIR 3-5 μm) thermal images. The synchronous control module (timing controller) is used to control the microsecond (μs)-level timing synchronization of the excitation signal and infrared sampling to avoid signal blurring caused by thermal diffusion.

[0060] Specifically, after the non-magnetic reversible thermosensitive particles generate heat, an infrared camera synchronously acquires the thermal image sequences during the heating period (0 - 500 ms) and the cooling period (500 ms - 1000 ms). The synchronization control module (timing controller) displays the synchronization relationship between the laser pulse and the infrared camera with a timing waveform diagram.

[0061] In some embodiments, the intelligent thermal field analysis module includes a thermal diffusion inversion algorithm for estimating the defect size and depth based on a finite element model, and a deep learning network for dynamically suppressing noise and classifying defects in the temporal thermal images. Specifically, this module includes a preprocessing module, a three-dimensional thermal diffusion modeling module, a defect inversion module, and a convolutional neural network module. The preprocessing module is used to perform noise filtering preprocessing on the input temporal thermal image sequence data. The three-dimensional thermal diffusion modeling module and the defect inversion module are used to adopt a three-dimensional heat conduction inversion algorithm to locate defects according to the difference in thermal diffusion rates. The convolutional neural network (CNN) module is used to classify the defect types (bubbles / cracks) and output the three-dimensional coordinates and sizes.

[0062] This embodiment provides a non-contact, highly sensitive, and low-cost magnetic therapy coil potting defect detection system, which realizes the rapid identification and location of micro-bubbles and cracks through enhanced thermal excitation and multimodal analysis.

[0063] Embodiment 2

[0064] A method for detecting potting defects of a magnetic therapy coil is applied to the above system. For a detailed description of the system, reference can be made to the corresponding description in the above system embodiment, which will not be elaborated here. Combining the enhanced thermal excitation strategy and multimodal infrared thermography analysis technology to detect internal bubbles / cracks in the potted magnetic therapy coils and other precision electronic devices, as Figure 2 、 Figure 4 shown. This method includes the following steps:

[0065] S100: Generate near-infrared light to irradiate the detection area to activate the non-magnetic reversible thermosensitive particles in the potting adhesive to generate heat;

[0066] Specifically, the composite excitation module generates near-infrared light to irradiate the detection area to activate the non-magnetic reversible thermosensitive particles in the potting adhesive to generate heat.

[0067] In some embodiments, the composite excitation module includes a laser array module and an optical window. The laser array module integrates multiple near-infrared lasers. For example, it integrates multiple near-infrared lasers with a wavelength of 800 nm and adjustable power density, and can emit 800-nm laser pulses. The near-infrared light generated by the near-infrared lasers is uniformly irradiated onto the detection area through optical fibers. The optical window is placed on the surface of the potting layer. For example, a transparent quartz glass window is embedded in the surface of the potting layer to achieve near-infrared light transmission. For example, it is ensured that the laser transmittance > 90%.

[0068] Among them, non-magnetic reversible thermosensitive particles (carbon-coated boron nitride nanosheets) are added to the potting adhesive. This material has the advantages of being non-magnetic and having good thermal response effects.

[0069] Optionally, the near-infrared laser array module emits 800-nm laser pulses to irradiate the optical window optical fiber, achieving uniform irradiation of the detection area and activating the non-magnetic reversible thermosensitive particles to generate heat. After the light is stopped, the non-magnetic reversible thermosensitive particles do not generate heat. Further, it also includes the steps of:

[0070] Adjust the laser power according to the colloid thickness. The formula is:

[0071] P = P0 × [1 + γ·ln(d / d0)]

[0072] Where, P0 is the reference power, d is the colloid thickness, and γ is the material attenuation coefficient.

[0073] S110. Synchronously collect multi-band thermal images;

[0074] Specifically, multi-band thermal images are synchronously collected through a multi-band infrared imaging module.

[0075] In some embodiments, the multi-band infrared imaging module includes a dual-band infrared camera and a synchronous control module. The dual-band infrared camera is used to synchronously collect long-wave (LW IR 7-14 μm) and mid-wave (MW IR 3-5 μm) thermal images. The synchronous control module (timing controller) is used to control the microsecond (μs)-level timing synchronization of the excitation signal and infrared sampling to avoid signal blurring caused by thermal diffusion.

[0076] Specifically, after the non-magnetic reversible thermosensitive particles generate heat, the infrared camera synchronously collects a sequence of thermal images during the heating period (0-500 ms) and the cooling period (500 ms-1000 ms). The synchronous control module (timing controller) displays the synchronous relationship between the laser pulse and the infrared camera with a timing waveform diagram.

[0077] S120. Process the multi-band thermal images, classify the defect types, and output the three-dimensional coordinates and dimensions.

[0078] Specifically, the thermal field intelligent analysis module is used to process the multi-band thermal images, classify the defect types, and output the three-dimensional coordinates and dimensions.

[0079] In some embodiments, the thermal field intelligent analysis module includes a thermal diffusion inversion algorithm for estimating the defect size and depth based on a finite element model, and a deep learning network for dynamically suppressing noise and classifying defects in the time-series thermal images. Further, as Figure 3 shown, the steps of processing the multi-band thermal images, classifying the defect types, and outputting the three-dimensional coordinates and dimensions include:

[0080] S121. Preprocess the input time-series thermal image sequence data;

[0081] Further, the step of preprocessing the input time-series thermal image sequence data includes:

[0082] Perform differential calculation and noise filtering on the time-series thermal image sequence data.

[0083] Among them, the differential calculation process is as follows:

[0084] ΔT = T excitation - T baseline

[0085] The defect area increases significantly.

[0086] Optionally, wavelet decomposition Daubechies4 is used for noise filtering.

[0087] S122. Perform three-dimensional thermal diffusion modeling and defect inversion on the preprocessed data;

[0088] Further, the steps of performing three-dimensional thermal diffusion modeling and defect inversion on the preprocessed data include:

[0089] Perform three-dimensional thermal diffusion modeling on the preprocessed data through finite element mesh generation and boundary condition setting;

[0090] Among them, finite element mesh generation (three-dimensional heat conduction formula):

[0091]

[0092] Boundary condition setting: The laser power is 50 mW / cm 2 , the ambient temperature is 25 °C, and the thermal conductivity of the colloid is 0.15 W / m·K.

[0093] Iteratively optimize through the genetic algorithm (GA):

[0094] Generate the initial population (random defect parameters);

[0095] Fitness calculation: The mean square error (MSE) between the measured ΔT and the simulated ΔT;

[0096] Selection, crossover, mutation;

[0097] Convergence condition: MSE < 0.1 °C 2 .

[0098] S123. Output parameters through a convolutional neural network (CNN), including the defect location, size, and confidence level.

[0099] This embodiment provides a non-contact, highly sensitive, and low-cost method for detecting defects in the potting of a magnetic therapy coil. Through enhanced thermal excitation and multimodal analysis, rapid identification and localization of microbubbles and cracks are achieved.

[0100] Embodiment 3

[0101] A computer device 200, as Figure 5 shown, includes a memory 210, a processor 220, and a computer program 230 stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of a method for detecting defects in the potting of a magnetic therapy coil. For a detailed description of the method, reference can be made to the corresponding description in the above method embodiments and will not be elaborated here.

[0102] Embodiment 4

[0103] A computer-readable storage medium, as Figure 6 shown, stores a computer program thereon. When the computer program is executed by a processor, it implements the steps of a method for detecting defects in the potting of a magnetic therapy coil. For a detailed description of the method, reference can be made to the corresponding description in the above method embodiments and will not be elaborated here.

[0104] The number of devices and the scale of processing described here are used to simplify the description of the present invention. Applications, modifications, and variations of the present invention will be apparent to those skilled in the art.

[0105] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and embodiments. It can be fully applied to various fields suitable for the present invention. For those skilled in the art, additional modifications can be easily made. Therefore, without departing from the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details and the illustrated and described examples here.

[0106] The device, computer device, non-volatile computer storage medium, and method provided in the embodiments of this specification are corresponding. Therefore, the device, computer device, and non-volatile computer storage medium also have beneficial technical effects similar to those of the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding device, computer device, and non-volatile computer storage medium will not be elaborated here.

[0107] Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, the method steps can be logically programmed to enable the controller to be implemented in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. to achieve the same function. Therefore, such a controller can be regarded as a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software units for implementing the method or structures within the hardware component.

[0108] The systems, devices, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. For the convenience of description, when describing the above devices, they are described as various units according to their functions. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0109] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, system, or computer program product. Therefore, the embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0110] This specification is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0111] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to work in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one or more of the flows Figure 1 one or more of the flows and / or boxes Figure 1 specified in one or more of the boxes or boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or boxes Figure 1 specified in one or more of the boxes or boxes.

[0113] It should also be noted that the term "comprising", "including" or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or apparatus comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or apparatus. Without further limitation, an element qualified by the statement "comprising an …" does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising the element.

[0114] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program units. Generally, program units include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program units may be located in both local and remote computer storage media including storage devices.

[0115] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, they are described relatively simply, and the relevant parts can be referred to the partial description of the method embodiments.

[0116] The above is only for the embodiments of this specification and is not intended to limit one or more embodiments of this specification. For those skilled in the art, there can be various modifications and variations to one or more embodiments of this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included within the scope of the claims of one or more embodiments of this specification.

Claims

1. A magnetic therapy coil potting defect detection system, characterized in that: It includes a composite excitation module, a multi-band infrared imaging module, and a thermal field intelligent analysis module. Among them, the composite excitation module is used to generate near-infrared light to irradiate the detection area, so as to activate the non-magnetic reversible thermosensitive particles in the potting glue to generate heat; the multi-band infrared imaging module is used to synchronously collect multi-band thermal images; the thermal field intelligent analysis module is used to process the multi-band thermal images, classify the defect types, and output the three-dimensional coordinates and dimensions.

2. The magnetic therapy coil potting defect detection system according to claim 1, characterized in that: The composite excitation module includes a laser array module and an optical window. The laser array module integrates multiple near-infrared lasers. The near-infrared light generated by the near-infrared lasers is uniformly irradiated to the detection area through optical fibers. The optical window is placed on the surface of the potting layer to achieve the transmission of near-infrared light.

3. The magnetic therapy coil potting defect detection system according to claim 2, wherein: The laser power of the laser array module adjusts the laser power according to the colloid thickness, and the formula is: P = P0 × [1 + γ · ln(d / d0)] where P0 is the reference power, d is the colloid thickness, and γ is the material attenuation coefficient.

4. A magnetic therapy coil potting defect detection system according to claim 1, characterized in that: The multi-band infrared imaging module includes a dual-band infrared camera and a synchronous control module. The dual-band infrared camera is used to synchronously collect long-wave and mid-wave thermal images. The synchronous control module is used to control the microsecond-level timing synchronization of the excitation signal and the infrared sampling to avoid signal blurring caused by thermal diffusion.

5. A magnetic therapy coil potting defect detection system according to claim 1, characterized in that: The thermal field intelligent analysis module includes a preprocessing module, a three-dimensional thermal diffusion modeling module, a defect inversion module, and a convolutional neural network module. The preprocessing module is used to perform noise filtering preprocessing on the input sequence data of the timing thermal images. The three-dimensional thermal diffusion modeling module and the defect inversion module are used to adopt a three-dimensional heat conduction inversion algorithm to locate defects according to the difference in the thermal diffusion rate. The convolutional neural network module is used to classify the defect types and output the three-dimensional coordinates and dimensions.

6. A method for detecting potting defects of a magnetic therapy coil, which is applied to the system according to any one of claims 1 to 5, characterized in that, It includes the following steps: Generate near-infrared light to irradiate the detection area to activate the non-magnetic reversible thermosensitive particles in the potting glue to generate heat; Synchronously collect multi-band thermal images; Process the multi-band thermal images, classify the defect types, and output the three-dimensional coordinates and dimensions.

7. A method for detecting potting defects of a magnetic therapy coil according to claim 6, characterized in that: The multi-band thermal images are configured as long-wave and mid-wave thermal images.

8. The magnetic therapy coil potting defect detection method according to claim 7, characterized in that, The step of processing the multi-band thermal images, classifying the defect types, and outputting the three-dimensional coordinates and dimensions includes: Perform preprocessing on the input sequence data of the timing thermal images; Perform three-dimensional thermal diffusion modeling and defect inversion on the preprocessed data; Output parameters through the convolutional neural network, including defect position, size, and confidence.

9. A method for detecting the potting defects of a magnetic therapy coil as described in claim 8, characterized in that, The step of performing preprocessing on the input sequence data of the timing thermal images includes: Perform differential calculation and noise filtering on the sequence data of the timing thermal images.

10. A method for detecting potting defects of a magnetic therapy coil according to claim 9, characterized in that, The step of performing three-dimensional thermal diffusion modeling and defect inversion on the preprocessed data includes: Perform three-dimensional thermal diffusion modeling on the preprocessed data through finite element mesh generation and boundary condition setting; Iteratively optimize through the genetic algorithm.

11. A method for detecting the potting defects of a magnetic therapy coil according to claim 6, characterized in that, It also includes the steps: Adjust the laser power according to the colloid thickness, and the formula is: P = P0 × [1 + γ · ln(d / d0)] where P0 is the reference power, d is the colloid thickness, and γ is the material attenuation coefficient.

12. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 6 to 11 are implemented.

13. 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 according to any one of claims 6 to 11 are implemented.

Images