Methods and devices for inspecting quality defects in key stages of high-voltage cable accessory installation

Abstract

This invention discloses a method and apparatus for quality defect inspection in key stages of high-voltage cable accessory installation. The method includes: stitching together multiple cable segment images received from multiple image acquisition devices using the SIFT algorithm to generate a total cable image, wherein the multiple image acquisition devices are pre-positioned at multiple cross-linked cables within the cable accessory installation area of ​​110kV and above voltage levels; segmenting the total cable image using an RGB three-color separation edge detection method to extract multiple component images of multiple cable components; extracting defect edge point images from each component image and performing function fitting on the points in the defect edge point images to determine multiple fitting functions for multiple cable components; comparing the multiple fitting functions of multiple cable components with pre-set function range thresholds for different cable components to determine whether defects exist in the multiple cable components.

Description

Technical Field

[0001] This invention relates to the field of power cable accessory testing technology, and more specifically, to a method and apparatus for inspecting quality defects in key aspects of high-voltage cable accessory installation. Background Technology

[0002] The quality control of cable accessory manufacturing relies solely on the skills and "craftsmanship" of installation and technical supervision personnel. Although the standardization of high-voltage cable accessory manufacturing processes, quality evaluation systems, and installation skill assessments are receiving increasing attention and technical support, and standardized tools for equipment installation are being used more extensively, the focus remains on core elements such as skilled accessory manufacturers with a "craftsmanship spirit" and technical supervisors familiar with process documents. Currently, the inspection and evaluation of key aspects of high-voltage cable accessory (outdoor terminals, GIS cable terminals, intermediate joints, etc.) manufacturing and installation, such as cable pretreatment (stripping the outer semiconductive shielding layer, treating the outer shield break, and grinding the main insulation surface), prefabrication / stress cone installation, and lead-lined sealing of accessory tail tubes and cable metal sheaths, still rely on manual inspection combined with installation dimension verification. This results in significant problems such as low efficiency in on-site detection of process defects and low standardization and consistency in accessory manufacturing quality evaluation.

[0003] There is a fundamental lack of intelligent technologies and equipment for quality inspection in key aspects of cable accessory manufacturing: High-voltage cable accessory manufacturing and installation personnel are characterized by long training cycles and stringent practical quality requirements. Currently, there is a persistent shortage of skilled accessory manufacturing personnel. There are still many gaps in the research, development, improvement, configuration, and typical application of technical equipment for defect inspection and quality evaluation in cable engineering electrical construction. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method and apparatus for inspecting quality defects in key aspects of high-voltage cable accessory installation.

[0005] According to one aspect of the present invention, a method for inspecting quality defects in key stages of high-voltage cable accessory installation is provided, comprising:

[0006] The SIFT algorithm is used to stitch together multiple cable segment images received from multiple image acquisition devices to generate a total cable image. The multiple image acquisition devices are pre-set at multiple cross-linked cables in the cable accessory installation area of ​​110kV and above voltage level.

[0007] The overall cable image is segmented using an RGB three-color separation edge detection method, and multiple component images of multiple cable parts are extracted.

[0008] Defect edge point images of multiple components are extracted separately, and function fitting is performed on the points in the defect edge point images to determine multiple fitting functions for multiple cable components;

[0009] Multiple fitted functions for multiple cable components are compared with pre-set function range thresholds for different cable components to determine whether multiple cable components have defects.

[0010] Optionally, the operation of stitching together multiple cable segment images received from multiple image acquisition devices using the SIFT algorithm to generate a total cable image includes:

[0011] Denoising was performed on multiple cable segment images using adaptive filtering.

[0012] A scale space is constructed for multiple denoised cable segment images to determine the feature points to be matched among the multiple cable segment images;

[0013] Calculate the gradient magnitude and direction of multiple cable segment images respectively, and assign feature descriptors to the feature points to be matched based on the magnitude and direction;

[0014] Euclidean distance is calculated for the feature descriptors of the feature points to be matched, feature matching between the feature points is completed, and the overall cable image is generated.

[0015] Optionally, the operation of segmenting the total cable image and extracting multiple component images of multiple cable parts using an RGB three-color separation edge detection method includes:

[0016] Image enhancement of the total cable image is performed using histogram equalization.

[0017] An edge detection algorithm based on RGB three-color separation is used to segment the enhanced overall cable image and extract multiple component images.

[0018] Optionally, before extracting defect edge points from multiple component images, the process also includes:

[0019] Perform grayscale processing on multiple component images and then perform image mean smoothing.

[0020] Histogram equalization is used to achieve grayscale equalization in images of multiple components.

[0021] Gaussian filtering is used to remove noise and interference from multiple component images.

[0022] Optionally, the operation of extracting defect edge point images from multiple component images separately includes:

[0023] The grayscale gradient amplitude and direction of multiple cable components are calculated separately to determine multiple grayscale gradient information of multiple cable components;

[0024] The local optimum method is used to determine the defect edge points of multiple gray-level gradient information to determine the initial defect edge point images of multiple cable components.

[0025] Based on pre-set high and low thresholds, the initial defect edge point images of multiple cable components are filtered to determine the defect edge point images of multiple cable components.

[0026] Optionally, the operation of performing function fitting on points in the defect edge point image to determine multiple fitting functions for multiple cable components includes:

[0027] Dilation processing was performed on the defect edge point images of multiple cable components respectively;

[0028] Function fitting is performed on the points in the defect edge point images of multiple cable components after dilation processing to determine multiple fitting functions for multiple cable components.

[0029] Optionally, the operation of comparing multiple fitted functions of multiple cable components with pre-set function range thresholds for different cable components to determine whether multiple cable components have defects includes:

[0030] Calculate the extreme values ​​or variances of multiple fitted functions separately;

[0031] The extreme values ​​or variances of multiple fitted functions are compared with the pre-set extreme value ranges and variance ranges of multiple cable components to determine whether multiple cable components have defects.

[0032] Optionally, the operation of comparing the extreme values ​​or variances of multiple fitted functions with the pre-set extreme value ranges and variance ranges of multiple cable components to determine whether the multiple cable components have defects includes:

[0033] If the extreme value or variance of the fitting function of any cable component is not within the pre-set extreme value range or variance range of that cable component, the cable component is judged to have a defect.

[0034] According to another aspect of the present invention, a quality defect inspection device for a key stage of high-voltage cable accessory installation is provided, comprising:

[0035] The stitching module is used to stitch together multiple cable segment images received from multiple image acquisition devices using the SIFT algorithm to generate a total cable image. The multiple image acquisition devices are pre-set at multiple cross-linked cables in the cable accessory installation area of ​​110kV and above voltage level.

[0036] The segmentation module is used to segment the total cable image using an edge detection method based on RGB three-color separation, and to extract multiple component images of multiple cable parts;

[0037] The fitting module is used to extract defect edge point images from multiple component images, and to perform function fitting on the points in the defect edge point images to determine multiple fitting functions for multiple cable components.

[0038] The determination module is used to compare multiple fitted functions of multiple cable components with pre-set function range thresholds for different cable components to determine whether multiple cable components have defects.

[0039] According to another aspect of the present invention, a computer-readable storage medium is provided, the storage medium storing a computer program for performing the methods described in any of the above aspects of the present invention.

[0040] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the method described in any of the preceding aspects of the present invention.

[0041] Therefore, this application identifies defects in cable components by acquiring images of cross-linked cables in segments and then processing these images. This enables automated auxiliary operations for the on-site installation of high-voltage cable accessories in electrical engineering construction, as well as intelligent inspection and evaluation of manufacturing quality defects in relevant stages. It addresses the current problem that the quality inspection and evaluation of key stages in the installation of cross-linked cable accessories still relies on manual experience and visual inspection combined with installation dimension verification, resulting in low efficiency in on-site detection of process defects and low standardization and consistency in manufacturing quality evaluation. This significantly optimizes the economy and efficiency of defect detection and quality evaluation in key stages of accessory manufacturing and installation, supporting further improvements in the inherent safety level of power cable systems. Attached Figure Description

[0042] Exemplary embodiments of the present invention can be more fully understood by referring to the following figures:

[0043] Figure 1 This is a flowchart illustrating a method for inspecting quality defects in key stages of high-voltage cable accessory installation, provided by an exemplary embodiment of the present invention.

[0044] Figure 2 This is a schematic diagram of the internal structure of an image acquisition device provided in an exemplary embodiment of the present invention;

[0045] Figure 3 This is a flowchart of an image acquisition device recognition process provided in an exemplary embodiment of the present invention;

[0046] Figure 4 This is a schematic diagram of the structure of a quality defect inspection device for key aspects of high-voltage cable accessory installation provided in an exemplary embodiment of the present invention;

[0047] Figure 5 This is the structure of an electronic device provided in an exemplary embodiment of the present invention. Detailed Implementation

[0048] Hereinafter, exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0049] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of the invention.

[0050] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of the present invention are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0051] It should also be understood that in the embodiments of the present invention, "multiple" can refer to two or more, and "at least one" can refer to one, two or more.

[0052] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more unless explicitly defined or given contrary instructions in the context.

[0053] Furthermore, the term "and / or" in this invention is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this invention generally indicates that the preceding and following related objects have an "or" relationship.

[0054] It should also be understood that the description of the various embodiments in this invention emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0055] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0056] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0057] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, they should be considered part of the specification.

[0058] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0059] The embodiments of this invention can be applied to electronic devices such as terminal devices, computer systems, and servers, and can operate together with a wide range of other general-purpose or special-purpose computing system environments or configurations. Well-known examples of terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, and servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments including any of the above systems, etc.

[0060] Electronic devices such as terminal devices, computer systems, and servers can be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are executed by remote processing devices linked through communication networks. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.

[0061] Exemplary methods

[0062] Figure 1 This is a flowchart illustrating a quality defect inspection method for key stages of high-voltage cable accessory installation provided in an exemplary embodiment of the present invention. This embodiment can be applied to electronic devices, such as… Figure 1 As shown, the quality defect inspection method 100 for key aspects of high-voltage cable accessory installation includes the following steps:

[0063] Step 101: Use the SIFT algorithm to stitch together multiple cable segment images received from multiple image acquisition devices to generate a total cable image. The multiple image acquisition devices are pre-set at multiple cross-linked cables in the cable accessory installation area of ​​110kV and above voltage level.

[0064] Among them, several cable segment images are segment images of the cable body after the outer sheath and metal sleeve have been removed.

[0065] Optionally, the operation of stitching together multiple cable segment images received from multiple image acquisition devices using the SIFT algorithm to generate a total cable image includes:

[0066] Denoising was performed on multiple cable segment images using adaptive filtering.

[0067] A scale space is constructed for multiple denoised cable segment images to determine the feature points to be matched among the multiple cable segment images;

[0068] Calculate the gradient magnitude and direction of multiple cable segment images respectively, and assign feature descriptors to the feature points to be matched based on the magnitude and direction;

[0069] Euclidean distance is calculated for the feature descriptors of the feature points to be matched, feature matching between the feature points is completed, and the overall cable image is generated.

[0070] Specifically, the above operations can be implemented in the image processing unit of a computing device, using image stitching technology based on the SIFT algorithm to stitch segmented images together. First, multiple cable segment images of the cable accessory installation preprocessing area are preprocessed using adaptive filtering. Different variances are selected during adaptive filtering to obtain the optimal residual, preserving the image's detail information. Second, key points to be matched between segmented images are determined through scale space construction. Then, the gradient magnitude and direction of each segmented image are calculated, and a feature descriptor is assigned to each feature point. Finally, the Euclidean distance method is used to match feature points using the feature descriptors, stitching several segmented cable images into one, completing the segmented image stitching for all types of cross-linked cables of 110kV and above.

[0071] Step 102: Using the RGB three-color separation edge detection method, the total cable image is segmented to extract multiple component images of multiple cable parts.

[0072] Optionally, the operation of segmenting the total cable image and extracting multiple component images of multiple cable parts using an RGB three-color separation edge detection method includes:

[0073] Image enhancement of the total cable image is performed using histogram equalization.

[0074] An edge detection algorithm based on RGB three-color separation is used to segment the enhanced overall cable image and extract multiple component images.

[0075] Specifically, based on Canny's RGB three-color separation edge detection method, the spliced ​​cross-linked cable image is segmented into cable components such as the outer semiconductive layer, main insulation, and crimping tube. First, histogram equalization is used to enhance the spliced ​​cable image, making the boundaries between different parts more distinct. Second, leveraging the significant color differences between cable accessories, edge detection algorithms are employed to segment the cable accessories based on the boundaries between components of different colors. Finally, images of components at different locations, such as the main insulation, outer semiconductive layer, and crimping tube, are obtained.

[0076] Optionally, before extracting defect edge points from multiple component images, the process also includes:

[0077] Perform grayscale processing on multiple component images and then perform image mean smoothing.

[0078] Histogram equalization is used to achieve grayscale equalization in images of multiple components.

[0079] Gaussian filtering is used to remove noise and interference from multiple component images.

[0080] Specifically, in the image processing device, the segmented component image is preprocessed to remove noise and interference. First, grayscale processing is performed on different components. Then, the mean value of pixels within the template is used to replace the target center pixel of the preprocessed component image, i.e., image mean smoothing. Next, histogram equalization is used to evenly distribute a region with a relatively concentrated grayscale value in the denoised component image across the entire grayscale space to enhance the image. Finally, Gaussian filtering is used to remove noise and interference from the component image, completing the component image preprocessing.

[0081] Step 103: Extract defect edge point images from multiple component images respectively, and perform function fitting on the points in the defect edge point images to determine multiple fitting functions for multiple cable components.

[0082] Optionally, the operation of extracting defect edge point images from multiple component images separately includes:

[0083] The grayscale gradient amplitude and direction of multiple cable components are calculated separately to determine multiple grayscale gradient information of multiple cable components;

[0084] The local optimum method is used to determine the defect edge points of multiple gray-level gradient information to determine the initial defect edge point images of multiple cable components.

[0085] Based on pre-set high and low thresholds, the initial defect edge point images of multiple cable components are filtered to determine the defect edge point images of multiple cable components.

[0086] Optionally, the operation of performing function fitting on points in the defect edge point image to determine multiple fitting functions for multiple cable components includes:

[0087] Dilation processing was performed on the defect edge point images of multiple cable components respectively;

[0088] Function fitting is performed on the points in the defect edge point images of multiple cable components after dilation processing to determine multiple fitting functions for multiple cable components.

[0089] Specifically, after image preprocessing, function fitting is used to identify defects in various cable components in images of all types of cross-linked cables of 110kV and above. First, due to differences in grayscale values ​​between image boundaries and adjacent areas, different regions produce significantly different grayscale values. The grayscale gradient magnitude and direction are calculated to obtain the image's grayscale gradient information. Then, to prevent false edges, a local optimum method is used to determine whether a pixel is an edge point, suppressing non-maximum point information and highlighting edge points. Next, high and low thresholds are used to extract edge points from different components. If the threshold is set too low (high threshold set to 20), the detection intensity is too strong, detecting many unwanted features. If the threshold is set too high (high threshold set to 100), defect features will be filtered out. Next, image dilation is applied to the edge points of different components to make them easier to fit. Then, function fitting is performed on the edge points of different components. This fitting function is a quadratic function, i.e., ax² + bx + c. 2 +bx+c.

[0090] Step 104: Compare the multiple fitted functions of multiple cable components with the pre-set function range thresholds for different cable components to determine whether there are defects in the multiple cable components.

[0091] Optionally, the operation of comparing multiple fitted functions of multiple cable components with pre-set function range thresholds for different cable components to determine whether multiple cable components have defects includes:

[0092] Calculate the extreme values ​​or variances of multiple fitted functions separately;

[0093] The extreme values ​​or variances of multiple fitted functions are compared with the pre-set extreme value ranges and variance ranges of multiple cable components to determine whether multiple cable components have defects.

[0094] Optionally, the operation of comparing the extreme values ​​or variances of multiple fitted functions with the pre-set extreme value ranges and variance ranges of multiple cable components to determine whether the multiple cable components have defects includes:

[0095] If the extreme value or variance of the fitting function of any cable component is not within the pre-set extreme value range or variance range of that cable component, the cable component is judged to have a defect.

[0096] Specifically, the extreme values ​​or variances of the fitting functions of each cable component are calculated, and the presence of defects is determined by comparing them with the defect judgment threshold. For example, when the maximum value of the fitting curve of the crimped pipe does not belong to [80, 100], it is considered that there are burrs in the crimped pipe.

[0097] In addition, refer to Figure 2 As shown, the image acquisition device 3 can be a CCD camera, 1 is a cross-linked cable accessory, and 2 is an LED light strip. The CCD camera 3 and the LED light strip 2 are arranged in a triangular pattern around the inner wall of the supporting structure, with the CCD camera 3 located on the inner wall at the axial center of the supporting structure. The LED light strip 2 is arranged on both sides of the CCD camera 3, forming a 45-degree angle with the CCD camera 3. The segmented images acquired by the CCD camera 3 are transmitted to a computing device via a wireless transmission module for image processing and recognition operations.

[0098] also, Figure 3 The flowchart illustrates the defect identification process, specifically: initializing the image acquisition device and checking for faults; establishing wireless communication with the computing device if no faults are found; turning on LED strip 2 to begin capturing segmented images; transmitting these segmented images to the computing device via the wireless transmission module; and having the computing device perform defect identification based on the received segmented images, obtaining and storing the detection results for any defects.

[0099] This invention proposes a method for inspecting quality defects in key stages of high-voltage cable accessory installation. Based on machine vision and intelligent image recognition technology, it proposes an intelligent image recognition technology method for installation quality defects such as non-standard stripping length, uneven breaks, stains on the insulation surface, and sharp corners and burrs in the crimping of conductor connecting pipes during key stages of accessory installation, including the removal of the outer semiconductive shielding layer, insulation grinding, surface cleaning, and crimping of conductor connecting pipes. An innovative automatic detection device for cable accessory installation quality defects is also designed.

[0100] Therefore, the quality defect inspection method for key links in the installation of high-voltage cable accessories proposed in this invention can automate the on-site installation of high-voltage cable accessories in engineering electrical construction, as well as intelligently inspect and evaluate the manufacturing quality defects of corresponding links. It can also provide practical training in accessory installation skills and intelligent quality inspection and evaluation for core teams in the operation and maintenance of high-voltage cable equipment, addressing the current problem that the quality inspection and evaluation of key links in the installation of cross-linked cable accessories still relies on manual experience-based visual inspection combined with installation dimension verification. This results in low efficiency in on-site detection of process defects and low standardization and consistency in manufacturing quality evaluation. The method significantly optimizes the economy and execution efficiency of defect detection and quality evaluation in key links of accessory manufacturing and installation, supporting further improvement in the inherent safety level of power cable systems.

[0101] Exemplary device

[0102] Figure 4 This is a schematic diagram of a quality defect inspection device for a key stage of high-voltage cable accessory installation provided in an exemplary embodiment of the present invention. Figure 4 As shown, the device 400 includes:

[0103] The splicing module 410 is used to splice multiple cable segment images received from multiple image acquisition devices using the SIFT algorithm to generate a total cable image, wherein the multiple image acquisition devices are pre-set at multiple cross-linked cables in the cable accessory installation area of ​​110kV and above voltage level.

[0104] The segmentation module 420 is used to segment the total cable image using the RGB three-color separation edge detection method and extract multiple component images of multiple cable components;

[0105] The fitting module 430 is used to extract defect edge point images from multiple component images respectively, and to perform function fitting on the points in the defect edge point images to determine multiple fitting functions for multiple cable components.

[0106] The determination module 440 is used to compare multiple fitted functions of multiple cable components with pre-set function range thresholds for different cable components to determine whether the multiple cable components have defects.

[0107] Optionally, the splicing module 410 includes:

[0108] The denoising submodule is used to denoise multiple cable segment images separately using adaptive filtering;

[0109] A submodule is constructed to build a scale space for multiple denoised cable segment images and determine the feature points to be matched between multiple cable segment images;

[0110] The first calculation submodule is used to calculate the gradient magnitude and direction of multiple cable segment images respectively, and assign feature descriptors to the feature points to be matched according to the magnitude and direction.

[0111] The generation submodule is used to calculate the Euclidean distance between the feature descriptors of the feature points to be matched, complete the feature matching between the feature points to be matched, and generate the total cable image.

[0112] Optionally, the segmentation module 420 includes:

[0113] The enhancement submodule is used to enhance the overall cable image using histogram equalization.

[0114] The extraction submodule is used to segment the enhanced total cable image using an edge detection algorithm based on RGB three-color separation, and extract multiple component images.

[0115] Optionally, prior to the operation of extracting defect edge points from multiple component images, the apparatus 400 further includes:

[0116] The grayscale processing submodule is used to perform grayscale processing on multiple component images and to perform image mean smoothing.

[0117] The balanced distribution submodule is used to perform grayscale balanced distribution on multiple component images using the histogram equalization method.

[0118] The removal submodule is used to remove noise and interference from multiple component images using Gaussian filtering.

[0119] Optionally, the fitting module 430 includes:

[0120] The first determination submodule is used to calculate the grayscale gradient amplitude and direction of multiple cable components respectively, and determine multiple grayscale gradient information of multiple cable components.

[0121] The second determination submodule is used to determine the defect edge points of multiple gray-level gradient information by using the local optimum method, and to determine the initial defect edge point images of multiple cable components.

[0122] The third determination submodule is used to filter the initial defect edge point images of multiple cable components according to the pre-set high and low dual thresholds, and determine the defect edge point images of multiple cable components.

[0123] Optionally, the fitting module 430 includes:

[0124] The dilation submodule is used to perform dilation processing on defect edge point images of multiple cable components respectively;

[0125] The function fitting submodule is used to perform function fitting on the points in the defect edge point images of multiple cable components after dilation processing, and to determine multiple fitting functions for multiple cable components.

[0126] Optionally, module 440 is defined, including:

[0127] The second calculation submodule is used to calculate the extreme values ​​or variances of multiple fitted functions respectively;

[0128] The fourth determination submodule is used to compare the extreme values ​​or variances of multiple fitted functions with the pre-set extreme value ranges and variance ranges of multiple cable components to determine whether multiple cable components have defects.

[0129] Optionally, the fourth determining submodule includes:

[0130] The judgment unit is used to determine that a cable component has a defect if the extreme value or variance of the fitting function of any cable component is not within the preset extreme value range or variance range of the cable component.

[0131] Exemplary electronic devices

[0132] Figure 5 This is the structure of an electronic device provided in an exemplary embodiment of the present invention. For example... Figure 5 As shown, the electronic device 50 includes one or more processors 51 and memory 52.

[0133] The processor 51 may be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0134] The memory 52 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 51 may execute the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above, and / or other desired functions. In one example, the electronic device may also include an input device 53 and an output device 54, these components being interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0135] In addition, the input device 53 may also include, for example, a keyboard, a mouse, etc.

[0136] The output device 54 can output various information to the outside. The output device 54 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0137] Of course, for the sake of simplicity, Figure 5 Only some of the components of the electronic device relevant to the present invention are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device may include any other suitable components depending on the specific application.

[0138] Exemplary computer program products and computer-readable storage media

[0139] In addition to the methods and apparatus described above, embodiments of the present invention may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of the present invention described in the "Exemplary Methods" section above.

[0140] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of the present invention. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0141] Furthermore, embodiments of the present invention may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps of the methods for information mining of historical change records according to various embodiments of the present invention as described in the "Exemplary Methods" section above.

[0142] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0143] The basic principles of the present invention have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in the present invention are merely examples and not limitations, and should not be considered as essential features of each embodiment of the present invention. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the present invention to the necessity of employing the aforementioned specific details.

[0144] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0145] The block diagrams of devices, systems, devices, and systems involved in this invention are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, systems, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0146] The methods and systems of the present invention may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of the present invention are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, the present invention may also be implemented as a program recorded on a recording medium, the program comprising machine-readable instructions for implementing the methods according to the present invention. Thus, the present invention also covers recording media storing programs for performing the methods according to the present invention.

[0147] It should also be noted that in the systems, apparatus, and methods of the present invention, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered equivalents of the present invention. The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the invention. Therefore, the invention is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0148] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the invention to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A method for inspecting quality defects in key stages of high-voltage cable accessory installation, characterized in that, include: The SIFT algorithm is used to stitch together multiple cable segment images received from multiple image acquisition devices to generate a total cable image. The multiple image acquisition devices are pre-set at multiple cross-linked cables in the cable accessory installation area of ​​110kV and above voltage level. The total cable image is segmented using Canny's RGB three-color separation edge detection method, and multiple component images of multiple cable parts are extracted. Defect edge point images of the multiple component images are extracted respectively, and function fitting is performed on the points in the defect edge point images to determine multiple fitting functions for the multiple cable components; The fitting functions of the multiple cable components are compared with the function range thresholds of different cable components that are preset to determine whether the multiple cable components have defects. The operation of segmenting the total cable image and extracting multiple component images of multiple cable parts using Canny's RGB three-color separation edge detection method includes: The total cable image is enhanced using a histogram equalization method. The enhanced total cable image is segmented using the Canny RGB three-color separation edge detection algorithm to extract the images of the multiple components.

2. The method according to claim 1, characterized in that, The operation of stitching together multiple cable segment images received from multiple image acquisition devices to generate a total cable image using the SIFT algorithm includes: The multiple cable segment images are denoised using adaptive filtering. A scale space is constructed for the denoised multiple cable segment images to determine the feature points to be matched among the multiple cable segment images; The gradient magnitude and direction of the multiple cable segment images are calculated respectively, and feature descriptors are assigned to the feature points to be matched based on the magnitude and direction. Euclidean distance is calculated for the feature descriptors of the feature points to be matched, feature matching between the feature points to be matched is completed, and the total cable image is generated.

3. The method according to claim 1, characterized in that, Before the operation of extracting defect edge points from the multiple component images, the method further includes: The images of the multiple components are processed in grayscale and then smoothed by mean value. The grayscale distribution of the multiple component images is balanced using a histogram equalization method. The Gaussian filtering method is used to remove noise and interference from the images of the multiple components.

4. The method according to claim 1, characterized in that, The operation of extracting defect edge point images from the multiple component images includes: The grayscale gradient amplitude and direction of the plurality of cable components are calculated respectively to determine the grayscale gradient information of the plurality of cable components; The local optimum method is used to determine the defect edge points of the multiple gray-level gradient information to determine the initial defect edge point images of the multiple cable components. The initial defect edge point images of the multiple cable components are filtered according to the pre-set high and low dual thresholds to determine the defect edge point images of the multiple cable components.

5. The method according to claim 1, characterized in that, The operation of performing function fitting on points in the defect edge point image to determine multiple fitting functions for the multiple cable components includes: The defect edge point images of the multiple cable components are subjected to dilation processing respectively; The points in the defect edge point images of the multiple cable components after dilation processing are fitted with functions to determine the multiple fitting functions of the multiple cable components.

6. The method according to claim 1, characterized in that, The operation of comparing multiple fitted functions of the multiple cable components with pre-set function range thresholds for different cable components to determine whether the multiple cable components have defects includes: Calculate the extreme values ​​or variances of the multiple fitted functions respectively; The extreme values ​​or variances of the multiple fitted functions are compared with the preset extreme value ranges and variance ranges of the multiple cable components to determine whether the multiple cable components have defects.

7. The method according to claim 6, characterized in that, The operation of comparing the extreme values ​​or variances of the multiple fitted functions with the preset extreme value ranges and variance ranges of the multiple cable components to determine whether the multiple cable components have defects includes: If the extreme value or variance of the fitting function of any cable component is not within the preset extreme value range or variance range of the cable component, the cable component is judged to have a defect.

8. A quality defect inspection device for key stages of high-voltage cable accessory installation, characterized in that, include: The stitching module is used to stitch together multiple cable segment images received from multiple image acquisition devices using the SIFT algorithm to generate a total cable image, wherein the multiple image acquisition devices are pre-set at multiple cross-linked cables in the cable accessory installation area of ​​110kV and above voltage level. The segmentation module is used to segment the total cable image using Canny's RGB three-color separation edge detection method and extract multiple component images of multiple cable components. The fitting module is used to extract defect edge point images from the multiple component images respectively, and to perform function fitting on the points in the defect edge point images to determine multiple fitting functions for the multiple cable components; The determination module is used to compare the multiple fitting functions of the multiple cable components with the function range thresholds of different cable components that are preset, and to determine whether the multiple cable components have defects; The segmentation module includes: The total cable image is enhanced using a histogram equalization method. The enhanced total cable image is segmented using the Canny RGB three-color separation edge detection algorithm to extract the images of the multiple components.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for performing the method described in any one of claims 1-7.

10. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1-7.

Images