System and method for detecting internal defects of basin-type insulator based on pulse infrared thermal waves

Abstract

The invention discloses a basin-type insulator internal defect detection system and method based on pulse infrared thermal waves, and relates to the technical field of nondestructive testing and computer vision, and the basin-type insulator internal defect detection system comprises a pulse infrared thermal wave excitation module, an infrared thermal imaging module and a data processing module; the pulse infrared thermal wave excitation module is used for enabling the surface of the insulator to generate thermal response in a pulse infrared thermal wave excitation mode; the infrared thermal imaging module captures the temperature change of the surface of the insulator in real time and performs early detection; and the data processing module is used for data preprocessing, feature extraction and defect detection. According to the method for detecting the internal defect of the basin-type insulator based on the pulse infrared thermal wave, the pulse infrared thermal wave excitation and the high-precision infrared thermal imaging technology are combined, so that the bubble defect in the insulator is efficiently detected. The pulse infrared thermal wave technology generates instantaneous temperature change on the surface of the insulator, so that the bubble defect is more obvious, and the detection sensitivity and speed are improved.

Description

Technical Field

[0001] The invention relates to the fields of nondestructive testing technology and computer vision technology, and in particular to a system and method for detecting internal defects of a pot-type insulator based on pulse infrared heat waves. Background Art

[0002] The inspection of pot-type insulators is crucial for the reliable operation of power systems. By accurately identifying and locating internal defects, insulator failure can be effectively prevented, thereby reducing power outages and equipment damage, and ensuring the safety and stability of power systems. At present, the inspection of pot-type insulators mainly relies on methods such as visual inspection, ultrasonic testing, and electrical testing. Visual inspection is used to identify surface defects, but it is powerless against minor defects such as internal bubbles; ultrasonic testing detects internal cracks or bubble defects through the propagation of sound waves inside the insulator, but its sensitivity to small defects is low; electrical testing indirectly evaluates the internal condition of the insulator by detecting the overall electrical properties of the insulator, but it cannot accurately locate defects. These existing technologies have significant deficiencies in detecting internal bubbles, which limits the accuracy and non-destructiveness of the detection.

[0003] In recent years, new non-destructive testing technologies such as pulsed infrared thermal wave technology have gradually been applied to insulator inspection, which can more effectively detect defects such as internal bubbles and significantly improve the accuracy and efficiency of inspection.

[0004] In summary, in view of the shortcomings of existing detection technologies in terms of sensitivity, detection range, defect location accuracy and detection efficiency, this patent proposes a basin-type insulator internal defect detection system based on pulsed infrared thermal wave technology, and innovatively improves the YOLOv8 algorithm. The system uses pulsed infrared thermal waves to effectively identify bubble defects inside insulators, and optimizes the accuracy and speed of image processing and defect detection through the improved YOLOv8 algorithm. This solution combines highly sensitive thermal wave detection technology with advanced deep learning algorithms to achieve efficient and non-destructive bubble defect detection, significantly improving the performance and reliability of the detection system, while reducing maintenance costs and ensuring the safe and stable operation of the power system. Summary of the invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is to efficiently and accurately detect the internal defects (bubbles) of the basin insulator through non-contact thermal excitation and high-precision infrared thermal imaging technology. The system consists of a pulse infrared thermal wave excitation module, an infrared thermal imaging module, and a data processing module. Through the coordinated work of multiple modules, it realizes the accurate detection of tiny defects such as bubbles inside the insulator, which can effectively ensure the reliable operation of the insulator in the power system.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for detecting internal defects of pot-type insulators based on pulsed infrared thermal waves, comprising:

[0008] Pulse infrared thermal wave excitation module, infrared thermal imaging module and data processing module;

[0009] The pulse infrared thermal wave excitation module is used to generate a thermal response on the surface of the insulator by means of pulse infrared thermal wave excitation;

[0010] The infrared thermal imaging module captures the temperature changes on the surface of the insulator in real time for early detection;

[0011] The data processing module is used for data preprocessing, feature extraction and defect detection.

[0012] As a preferred solution of the basin-type insulator internal defect detection system based on pulse infrared thermal wave described in the present invention, wherein: the pulse infrared thermal wave excitation module includes an infrared light source, a temperature sensor, a closed-loop control system and an infrared energy focusing system;

[0013] The infrared light source is composed of two 2500W halogen lamps, which are evenly and symmetrically arranged in the infrared energy focusing system and kept at a fixed distance of 13cm from the insulator. The peak output wavelength of the infrared light source is 1000nm.

[0014] The temperature sensor monitors the temperature of the insulator surface in real time and feeds back the temperature data to the closed-loop control system;

[0015] The closed-loop control system dynamically adjusts the power and heating time of the infrared light source according to feedback data from the temperature sensor;

[0016] The infrared energy focusing system focuses heat through a trapezoidal cover structure, and the heating time is set to 7 seconds.

[0017] As a preferred solution of the basin insulator internal defect detection system based on pulse infrared thermal waves described in the present invention, wherein: the data processing module includes a data preprocessing module, a feature extraction module, a defect detection module, a classification and evaluation module and a result output and storage module;

[0018] The data preprocessing module performs denoising, filtering and image enhancement processing on the thermal imaging data acquired from the infrared sensor;

[0019] The feature extraction module extracts temperature distribution, texture features and shape features from the preprocessed image;

[0020] The defect detection module detects defect areas in infrared images in real time through the improved YOLOv8 algorithm;

[0021] The classification and evaluation module classifies the detected defects by diameter and depth;

[0022] The result output and storage module displays the detection and evaluation results and stores the data in a database.

[0023] As a preferred solution of the basin-type insulator internal defect detection system based on pulse infrared thermal waves described in the present invention, the detected defects are classified by diameter and depth, including bubbles with a diameter less than 5 cm being classified as small bubbles, bubbles with a diameter between 5 cm and 10 cm being classified as medium bubbles, bubbles with a diameter greater than 10 cm being classified as large bubbles, bubbles with a depth less than 2 cm being classified as shallow bubbles, and bubbles with a depth greater than or equal to 2 cm being classified as deep bubbles.

[0024] As a preferred solution of the basin-type insulator internal defect detection system based on pulse infrared thermal waves described in the present invention, wherein: the data preprocessing module processes the thermal imaging data, including denoising, filtering and image enhancement;

[0025] The denoising process uses median filtering and bilateral filtering algorithms to reduce high-frequency noise in thermal imaging;

[0026] The filtering process uses a high-pass filter to remove low-frequency noise;

[0027] The image enhancement process includes contrast stretching and histogram equalization to increase the image contrast.

[0028] As a preferred solution of the basin-type insulator internal defect detection system based on pulse infrared thermal wave described in the present invention, wherein: the defect detection module performs basin-type insulator internal defect detection based on pulse infrared thermal wave technology by optimizing the YOLOv8 algorithm.

[0029] As a preferred solution of the basin insulator internal defect detection system based on pulse infrared thermal waves described in the present invention, wherein: the optimized YOLOv8 algorithm includes using the ASC2f module to replace the C2f module in the YOLOv8 backbone network;

[0030] Replace the ordinary convolutional layer in the SPPF module with a deformable convolutional layer, and add a spatial information enhancement module after the convolution operation;

[0031] The ASC2f module adjusts the receptive field at different scales and shapes through a selectable atrous convolution method, and adjusts the capture of global feature information through the dilation rate.

[0032] Another object of the present invention is to provide a method for detecting internal defects of pot-type insulators based on pulsed infrared thermal waves, which can improve the safety and reliability of power equipment, quickly and accurately detect bubbles and other defects inside pot-type insulators, and ensure the stable operation of the power system.

[0033] To solve the above technical problems, the present invention provides the following technical solutions: a method for detecting internal defects of pot-type insulators based on pulse infrared thermal waves, comprising: a pulse infrared thermal wave excitation module stimulates the temperature difference inside the insulator and highlights the defects through short-time high-energy pulses; an infrared thermal imaging module uses an infrared thermal imager to capture the temperature distribution and generate a thermal wave response image; and a data processing module detects the internal defects of the insulator by optimizing the YOLOv8 algorithm.

[0034] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for detecting internal defects of a pot-type insulator based on pulsed infrared thermal waves are implemented.

[0035] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for detecting internal defects of a pot-type insulator based on pulsed infrared thermal waves as described above.

[0036] Beneficial effects of the invention: The method for detecting internal defects of pot-type insulators based on pulsed infrared thermal waves provided by the invention realizes efficient detection of bubble defects inside insulators by combining pulsed infrared thermal wave excitation and high-precision infrared thermal imaging technology. The pulsed infrared thermal wave technology produces instantaneous temperature changes on the surface of the insulator, making the bubble defects more obvious, thereby improving the sensitivity and speed of detection.

[0037] The present invention adopts non-contact infrared pulse heating technology to avoid damage to the surface of the insulator and ensure the safety and reliability of the detection. The FLIR A655sc scientific research thermal imager provides high resolution and high temperature sensitivity, supporting real-time monitoring.

[0038] In terms of data processing, the system integrates the improved YOLOv8 algorithm and automated analysis module to achieve efficient defect detection and classification. The improved YOLOv8 algorithm enhances the detection capability of bubble defects of different scales and shapes by introducing optional dilated convolution and deformable convolution layers. At the same time, automated data analysis reduces manual intervention and improves detection accuracy and efficiency.

[0039] In summary, the present invention combines pulsed infrared thermal wave excitation, infrared thermal imaging and advanced data processing technology to provide an efficient and accurate bubble detection system for pot-type insulators, which can effectively ensure the quality and safety of insulators in power systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0041] Figure 1 The overall structure diagram of a basin-type insulator internal defect detection system based on pulsed infrared thermal waves provided by one embodiment of the present invention.

[0042] Figure 2 A detection flow chart of a basin-type insulator internal defect detection system based on pulsed infrared thermal waves provided in one embodiment of the present invention.

[0043] Figure 3 A flowchart of algorithm optimization design for a method for detecting internal defects of pot-type insulators based on pulsed infrared thermal waves provided in one embodiment of the present invention.

[0044] Figure 4 A method for detecting internal defects of pot-type insulators based on pulse infrared thermal waves provided in one embodiment of the present invention is a structural diagram of an algorithm optimization model of a system for detecting internal defects of pot-type insulators based on pulse infrared thermal wave technology.

[0045] Figure 5 A diagram of a selectable void convolution structure in algorithm optimization in a method for detecting internal defects of pot-type insulators based on pulsed infrared thermal waves provided in one embodiment of the present invention.

[0046] Figure 6 A schematic diagram of an improved SPPF module in the algorithm optimization of a method for detecting internal defects of pot-type insulators based on pulsed infrared thermal waves provided in one embodiment of the present invention.

[0047] Figure 7 A diagram showing the detection and evaluation results of a method for detecting internal defects of pot-type insulators based on pulsed infrared thermal waves provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0049] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0050] Example 1

[0051] Reference Figure 1 , which is an embodiment of the present invention, provides a basin insulator internal defect detection system based on pulse infrared thermal waves, comprising:

[0052] Pulse infrared heat wave excitation module 100, infrared thermal imaging module 200 and data processing module 300;

[0053] The pulse infrared heat wave excitation module 100 adopts an optimized pulse infrared heat wave excitation method, uses two 2500W halogen lamps, evenly distributes and accurately controls the heating time to 7 seconds, to ensure a uniform and controllable thermal response on the surface of the insulator, and enhance the temperature difference contrast in the defect area;

[0054] The infrared thermal imaging module 200 uses a high-resolution, low-temperature-sensitivity infrared thermal imaging device that can capture subtle temperature changes on the surface of the insulator in real time, and is suitable for early detection of minor defects;

[0055] The data processing module 300 integrates data preprocessing, feature extraction and defect detection functions. The defect detection module is based on the improved YOLOv8 algorithm. By introducing the ASC2f module, deformable convolution layer and spatial information enhancement module, the detection accuracy and speed of defects of different scales are significantly improved;

[0056] Through the innovative design of this system, internal defects (bubbles) of insulators can be detected quickly and accurately without affecting the performance of insulators, which greatly improves the efficiency and accuracy of detection and solves the problems of insufficient detection accuracy and slow speed in existing technologies.

[0057] The pulse infrared heat wave excitation module 100 includes: an infrared light source 101, a temperature sensor 102, a closed-loop control system 103 and an infrared energy focusing system 104;

[0058] The infrared light source 101 is composed of two 2500W halogen lamps, which are evenly and symmetrically arranged in the infrared focusing system 104, and keep a fixed distance of 13cm from the insulator. The peak output wavelength of the light source is 1000nm, which optimizes the infrared radiation efficiency and meets the heating requirements of the insulator material.

[0059] The temperature sensor 102 monitors the surface temperature of the insulator in real time and feeds the data back to the closed-loop control system 103. The system dynamically adjusts the power and heating time of the infrared light source according to the temperature feedback to prevent local overheating and ensure safe operation. At the same time, the infrared energy focusing system 104 composed of a trapezoidal cover effectively focuses heat to improve the efficiency of heat wave transmission. The heating time is set to 7 seconds to achieve uniform and sufficient heat wave excitation, thereby improving the accuracy and reliability of bubble defect detection inside the insulator.

[0060] The modules work together to enable the system to efficiently and accurately detect bubble defects inside pot-type insulators. Through pulsed infrared thermal wave technology, the system achieves rapid heating and high-precision imaging, significantly improving the accuracy and reliability of defect detection and providing a strong guarantee for the safe operation of power equipment.

[0061] The data processing module 300 includes: a data preprocessing module 301, a feature extraction module 302, a defect detection module 303, a classification and evaluation module 304 and a result output and storage module 305;

[0062] The data preprocessing module 301 performs denoising, filtering and image enhancement after acquiring thermal imaging data from the infrared sensor. These processing steps can effectively reduce noise interference, improve image clarity and contrast, ensure that the data for subsequent analysis is more accurate and reliable, and provide high-quality data support for subsequent defect detection;

[0063] A feature extraction module 302 extracts key information from the preprocessed image, including temperature distribution, texture features, shape features, etc., so as to further analyze possible defects inside the insulator;

[0064] The defect detection module 303 detects defect areas in infrared images in real time through the improved YOLOv8 algorithm. Compared with the traditional defect detection method, YOLOv8 has significantly improved speed and accuracy and can quickly locate bubble defects.

[0065] The classification and evaluation module 304 is responsible for accurately classifying and evaluating the detected bubble defects. By calculating the diameter and depth of each bubble and classifying the bubble defects into different levels according to preset standards, it provides a basis for subsequent quality control and decision-making.

[0066] First, in a controlled environment, ensure that the bubbles are in a stable state to avoid external interference, and use an infrared thermal imager to capture and obtain its thermal image. Due to the temperature difference between the bubble and the surrounding medium, the image processing software can accurately identify the bubble area and extract its edge, thereby calculating the diameter of the bubble; then, establish a relationship model between the bubble diameter and depth to achieve accurate depth estimation. The construction of this model relies on the calibration of experimental data to ensure that it is suitable for a variety of application scenarios and conditions;

[0067] Finally, bubbles are classified according to their diameter and depth, with two diameter thresholds set: 5 cm and 10 cm. Bubbles with a diameter less than 5 cm are classified as "small bubbles", bubbles with a diameter between 5 cm and 10 cm are classified as "medium bubbles", and bubbles with a diameter greater than 10 cm are classified as "large bubbles". At the same time, a threshold is set based on the depth: bubbles with a depth less than 2 cm are classified as "shallow bubbles", and bubbles with a depth greater than or equal to 2 cm are classified as "deep bubbles". This classification method can effectively classify each bubble into the corresponding category according to its size and depth, facilitating subsequent analysis and processing.

[0068] The result output and storage module 305 is responsible for presenting the detection and evaluation results in a visual manner and storing the data in a database, ensuring the reliability and accessibility of the data, and facilitating subsequent fault analysis and management;

[0069] These modules work together, from data preprocessing to improve image quality, to feature extraction to extract key information, to the defect detection module to accurately locate defects, the classification and evaluation module to grade defects, and finally to the result output and storage module to display and save data. The integration of the entire system ensures the comprehensiveness and accuracy of detection.

[0070] The data preprocessing module 301 is intended to improve the quality of thermal imaging data acquired from the infrared sensor;

[0071] The raw data usually contains noise and image quality issues, and multiple processing is required. First, through denoising, the median filter and bilateral filter algorithms are applied to reduce the high-frequency noise in the thermal imaging and eliminate the interference caused by environmental factors and sensor errors. Then, through filtering, a high-pass filter is used to highlight the useful frequency components and remove the useless low-frequency noise, thereby enhancing the signal in the key area. Finally, image enhancement techniques such as contrast stretching and histogram equalization are used to improve the visual effect of the image and make the bubble defect area more obvious. These preprocessing steps ensure that the image remains clear under high contrast, laying a solid foundation for subsequent feature extraction and detection.

[0072] The defect detection module 303 uses an optimized YOLOv8 algorithm to improve the performance of the internal defect detection system of the pot insulator based on the pulse infrared thermal wave technology. The optimization measures include the following aspects:

[0073] Firstly, for the C2f module in the YOLOv8 backbone network, an improved design of optional dilated convolution is proposed, and a new module ASC2f is introduced to replace the original C2f module. This module can expand the receptive field and enhance the feature fusion capability, effectively improving the detection accuracy of bubble defects of different scales.

[0074] Secondly, the ordinary convolution layer in the SPPF (Spatial Pyramid Pooling-Fast) module is replaced with a deformable convolution layer. The deformable convolution layer dynamically adjusts the shape of the receptive field to enhance the adaptability to the shape and size of bubble defects. At the same time, a spatial information enhancement module is added after the convolution operation to further optimize the spatial information of the feature map, which significantly improves the detection performance.

[0075] In addition, the selective dilated convolution is introduced to dynamically adjust the expansion rate in the convolution operation according to the different scales and shapes of bubble defects, thereby improving the ability to capture global feature information. This design not only improves the detection accuracy, but also effectively reduces the amount of model calculation and network parameters.

[0076] Through these optimizations, the defect detection module can more accurately identify and analyze bubble defects inside pot insulators, ensuring efficient and accurate defect detection and positioning.

[0077] Example 2

[0078] Refer to the figure-- Figure 3 , which is an embodiment of the present invention, provides a method for detecting internal defects of a pot-type insulator based on pulsed infrared thermal waves, comprising:

[0079] Reference Figure 2 ,The pulse infrared thermal wave excitation module stimulates the temperature difference inside the insulator and highlights the defects through short-term high-energy pulses;

[0080] The infrared thermal imaging module uses an infrared thermal imager to capture temperature distribution and generate thermal wave response images;

[0081] The data processing module detects the internal defects of the insulator by optimizing the YOLOv8 algorithm.

[0082] Pulse infrared thermal wave excitation adopts an optimized pulse infrared thermal wave excitation method, which mainly includes the following components: infrared light source, temperature sensor, closed-loop control system and infrared energy focusing system. The infrared light source consists of two 2500W halogen lamps, which are fixed at 13cm from the surface of the insulator, and its peak output wavelength is 1000nm to optimize the infrared radiation efficiency; the temperature sensor monitors the surface temperature of the insulator in real time, and transmits feedback information to the closed-loop control system, dynamically adjusts the power and heating time of the infrared light source, ensures that the surface of the insulator is evenly heated and avoids local overheating; the infrared energy focusing system is composed of a trapezoidal cover, which effectively focuses heat and improves the efficiency of heat wave transmission, thereby ensuring a uniform and controllable temperature difference contrast in the defect area to improve the accuracy and reliability of internal bubble defect detection.

[0083] The infrared thermal imaging module uses the FLIRA655sc scientific infrared thermal imager produced by FLIR. The thermal imager has a high-resolution sensor of 640×480 pixels and a temperature sensitivity of less than 30mK. It can capture the temperature distribution on the surface of the insulator in real time and generate high-quality thermal images. The distance between the sample and the thermal imager is set to 13cm to ensure the best image resolution and temperature change data.

[0084] The data processing module is responsible for processing and analyzing the thermal images collected by the infrared thermal imager. This module includes a data preprocessing module, a feature extraction module, a defect detection module, a classification and evaluation module, and a result output and storage module. Through the preprocessing step, the noise in the image is removed, and the image contrast is enhanced through filtering technology. The feature extraction module extracts the temperature distribution, shape and texture characteristics of the bubble defect from the image. Subsequently, the defect detection module uses the improved YOLOv8 algorithm to locate and detect defects in the infrared image in real time.

[0085] The overall process of this system refers to Figure 3 ,like Figure 3 As shown in the figure, the basin insulator is first heated non-contactly using a pulse infrared thermal wave excitation module, and then the infrared thermal imager collects the temperature change image of the insulator surface in real time, and transmits the data to the data processing module for analysis and processing. Through the optimized YOLOv8 algorithm, the bubble defect can be quickly identified and located, and the final result is visualized through the output module and stored in the database.

[0086] Example 3

[0087] An embodiment of the present invention is different from the first two embodiments in that:

[0088] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0089] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0090] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0091] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0092] Example 4

[0093] Reference Figure 4-Figure 7 , which is an embodiment of the present invention, provides a method for detecting internal defects of pot-type insulators based on pulse infrared thermal waves. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0094] like Figure 4 The improved YOLOv8 model structure of the basin insulator bubble detection system based on pulse infrared thermal wave technology includes four parts: input end 4, backbone network 5, feature fusion 6 and detection head 7.

[0095] The improved YOLOv8 model structure of this patent is to optimize the backbone network 5 of YOLOv8. In the backbone network, optional dilated convolution is introduced to improve the C2f module, and a new module ASC2f is designed to replace the C2f in the backbone network. Figure 5 As shown in Figure 2, the ASC2f module improves the detection accuracy of bubbles of different scales by expanding the receptive field and enhancing feature fusion.

[0096] The SPPF module enhances the feature extraction capability by performing pooling at different scales. In this embodiment, the ordinary convolution layer in the SPPF module is replaced with a deformable convolution layer, and a spatial information enhancement module is added. The deformable convolution layer can dynamically adjust the receptive field to adapt to bubble defects of different shapes and sizes, while the spatial information enhancement module enhances the spatial information of the feature map by aggregating contextual information, such as Figure 6 These improvements not only reduce the amount of computation, but also accelerate the inference speed, ensuring the real-time detection performance of the system.

[0097] The improved YOLOv8 algorithm can achieve accurate detection and location of bubble defects through efficient feature fusion and feature extraction. The detected bubble defects are then analyzed by the classification and evaluation module and graded according to their diameter and depth to facilitate subsequent quality control and processing decisions.

[0098] In summary, the system in this embodiment can achieve high-precision detection of bubble defects in basin insulators by combining pulsed infrared thermal wave technology with the improved YOLOv8 algorithm. The data processing and analysis module in the system ensures the reliability and accuracy of the detection results through multi-step optimization.

[0099] refer to Figure 7 In this paper, PyCharm was used to identify and evaluate bubble defects on the surface of pot insulators. First, the bubble area can be accurately identified and its edge can be extracted through image processing software to calculate the diameter of the bubble. Then, a relationship model between bubble diameter and depth is established to achieve accurate depth estimation. The test results are shown in Figure 2. Figure 7 As shown in the figure, bubbles are classified and colored according to diameter and depth. The diameter is shown in red and classified into small bubbles (S, diameter less than 5mm), medium bubbles (M, diameter 5-10mm) and large bubbles (L, diameter greater than 10mm); the depth is shown in blue and classified into shallow bubbles (Sh, depth less than 2mm) and deep bubbles (D, depth greater than 2mm).

[0100] The results show that the diameter calculation error ranges from 1.73% to 4.31%; the depth error is as high as 11.59%. Most bubbles are classified as small bubbles (S) and shallow bubbles (Sh), which have little impact on the insulator surface. However, medium bubbles (M), large bubbles (L) and deep bubbles (D) may pose potential risks to the mechanical strength and dielectric properties of the insulator, and relevant information is presented through green labels.

[0101] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. The internal defect detection system of pot-type insulator based on pulse infrared thermal wave is characterized by: include: A pulse infrared heat wave excitation module (100), an infrared thermal imaging module (200) and a data processing module (300); The pulse infrared heat wave excitation module (100) is used to generate a thermal response on the surface of the insulator by means of pulse infrared heat wave excitation; The infrared thermal imaging module (200) captures temperature changes on the surface of the insulator in real time to perform early detection; The data processing module (300) is used for data preprocessing, feature extraction and defect detection.

2. The basin insulator internal defect detection system based on pulse infrared thermal waves according to claim 1 is characterized in that: The pulse infrared thermal wave excitation module (100) comprises an infrared light source (101), a temperature sensor (102), a closed-loop control system (103) and an infrared energy focusing system (104); The infrared light source (101) is composed of two halogen lamps with a power of 2500 W, which are evenly and symmetrically arranged in the infrared energy focusing system (104) and maintained at a fixed distance of 13 cm from the insulator. The peak output wavelength of the infrared light source (101) is 1000 nm; The temperature sensor (102) monitors the temperature of the surface of the insulator in real time and feeds back the temperature data to the closed-loop control system (103); The closed-loop control system (103) dynamically adjusts the power and heating time of the infrared light source (101) according to feedback data from the temperature sensor (102); The infrared energy focusing system (104) focuses heat through a trapezoidal cover structure, and the heating time is set to 7 seconds.

3. The basin insulator internal defect detection system based on pulse infrared thermal waves according to claim 2, characterized in that: The data processing module (300) comprises a data preprocessing module (301), a feature extraction module (302), a defect detection module (303), a classification and evaluation module (304) and a result output and storage module (305); The data preprocessing module (301) performs denoising, filtering and image enhancement processing on the thermal imaging data acquired from the infrared sensor; The feature extraction module (302) extracts temperature distribution, texture features and shape features from the preprocessed image; The defect detection module (303) detects defect areas in the infrared image in real time using an improved YOLOv8 algorithm; The classification and evaluation module (304) classifies the detected defects by diameter and depth; The result output and storage module (305) displays the detection and evaluation results and stores the data in a database.

4. The basin insulator internal defect detection system based on pulse infrared thermal waves according to claim 3 is characterized in that: The classification of the detected defects by diameter and depth includes classifying bubbles with a diameter less than 5 cm as small bubbles, bubbles with a diameter between 5 cm and 10 cm as medium bubbles, bubbles with a diameter greater than 10 cm as large bubbles, bubbles with a depth less than 2 cm as shallow bubbles, and bubbles with a depth greater than or equal to 2 cm as deep bubbles.

5. The basin insulator internal defect detection system based on pulse infrared thermal waves according to claim 4, characterized in that: The data preprocessing module (301) processes the thermal imaging data, including denoising, filtering and image enhancement. The denoising process uses median filtering and bilateral filtering algorithms to reduce high-frequency noise in thermal imaging; The filtering process uses a high-pass filter to remove low-frequency noise; The image enhancement process includes contrast stretching and histogram equalization to increase the image contrast.

6. The basin insulator internal defect detection system based on pulse infrared thermal waves according to claim 5, characterized in that: The defect detection module (303) performs internal defect detection of pot-type insulators based on pulse infrared thermal wave technology by optimizing the YOLOv8 algorithm.

7. The basin insulator internal defect detection system based on pulse infrared thermal waves according to claim 6, characterized in that: The optimization of the YOLOv8 algorithm includes replacing the C2f module in the YOLOv8 backbone network with the ASC2f module; Replace the ordinary convolutional layer in the SPPF module with a deformable convolutional layer, and add a spatial information enhancement module after the convolution operation; The ASC2f module adjusts the receptive field at different scales and shapes through a selectable atrous convolution method, and adjusts the capture of global feature information through the dilation rate.

8. A method for detecting internal defects of pot-type insulators using the pulse infrared thermal wave-based system as claimed in any one of claims 1 to 7, characterized in that: include: The pulse infrared thermal wave excitation module stimulates the temperature difference inside the insulator and highlights defects through short-term high-energy pulses; The infrared thermal imaging module uses an infrared thermal imager to capture temperature distribution and generate thermal wave response images; The data processing module detects the internal defects of the insulator by optimizing the YOLOv8 algorithm.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for detecting internal defects of pot-type insulators based on pulsed infrared thermal waves according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for detecting internal defects of pot-type insulators based on pulsed infrared thermal waves according to any one of claims 1 to 7 are implemented.

Images