Method and device for detecting failure of cable, storage medium and electronic equipment

Abstract

The application discloses a kind of cable fault detection method, device, storage medium and electronic equipment.It relates to power cable fault detection technical field, the method comprises: obtaining the real scene image, infrared temperature image and operation data of target cable at current time;Determine the point mapping parameter based on real scene image and infrared temperature image;Determine the high temperature pixel point coordinate in multiple first pixel point coordinates;Based on point mapping parameter, the high temperature pixel point coordinate is mapped to the corresponding target pixel point coordinate in multiple second pixel point coordinates;Determine the fault detection result of target cable at current time based on target pixel point coordinate and operation data.The present application solves the technical problems of inaccurate cable fault positioning and existing fault detection blind area caused by insufficient consideration in cable fault detection of related technology.

Description

Technical Field

[0001] This invention relates to the field of power cable fault detection technology, and more specifically, to a cable fault detection method, apparatus, storage medium, and electronic device. Background Technology

[0002] With the acceleration of urbanization and the continuous expansion of the power grid, the number of high-voltage power cables laid in underground utility tunnels, tunnels, and cable trenches has increased dramatically year by year. Cable joints, as weak points in insulation and critical load-bearing nodes in power lines, are highly susceptible to localized overheating faults due to factors such as hardware oxidation, increased contact resistance, environmental moisture corrosion, and load fluctuations. If not monitored and addressed in a timely manner, localized overheating can lead to insulation breakdown, line tripping, and even serious power safety accidents such as fires in the tunnels. Therefore, online monitoring of cable joint overheating is a core task in the operation and maintenance management of distribution network cables. Related technologies have significant shortcomings in cable fault detection, mainly in the following aspects:

[0003] The current method, which relies on maintenance personnel periodically visiting the site to collect infrared images using infrared thermal imagers and visually assessing temperature rise based on experience, while manually matching the infrared images with the joint locations in the cable ledger, has significant drawbacks. It has limited inspection frequency, strong lag, and cannot monitor sudden, short-term overheating hazards in real time. Furthermore, manual assessment is highly subjective and inefficient, posing safety risks in confined cable tunnels and harsh environments. A better approach involves collecting infrared temperature spectra of the cables from fixed locations and uploading the image data to a cloud server, relying on cloud algorithms to perform temperature monitoring. While these methods can identify and alarm, they only collect a single infrared thermal image without combining it with real-world images for feature registration. Since infrared images primarily reflect temperature distribution and lack obvious geometric structural features, while real-world images have clear physical structures, a direct correspondence between the two is impossible. Laying sensing optical fibers along the cable body and using photosensitive temperature measurement to achieve continuous temperature acquisition along the entire line can achieve full-line monitoring, but the construction cost is high, and it mainly reflects the temperature distribution of the cable body, with limited ability to distinguish local hotspots at critical connection points such as joints. Furthermore, repairs are difficult once the optical fiber is damaged. Although cable fault detection methods in related technologies can achieve a certain degree of fault detection within a certain range, insufficient consideration of factors leads to inaccurate cable fault location and the existence of fault detection blind spots.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a cable fault detection method, apparatus, storage medium, and electronic device to at least solve the technical problem that cable fault location is inaccurate and there are blind spots in fault detection due to insufficient consideration of factors in related technologies.

[0006] According to one aspect of the present invention, a cable fault detection method is provided, comprising: acquiring a real-scene image, an infrared temperature image, and operational data of a target cable at a current moment; determining point mapping parameters based on the real-scene image and the infrared temperature image, wherein the point mapping parameters are used to indicate the mapping relationship between the coordinates of a plurality of first pixel points in the infrared temperature image and the coordinates of a plurality of second pixel points in the real-scene image; determining the coordinates of a high-temperature pixel point among the plurality of first pixel point coordinates, wherein the high-temperature pixel point coordinates represent the coordinate positions corresponding to the first pixel point whose temperature value is greater than a preset safe temperature threshold among the plurality of first pixel point coordinates; mapping the high-temperature pixel point coordinates to the corresponding target pixel point coordinates among the plurality of second pixel point coordinates based on the point mapping parameters; and determining the fault detection result of the target cable at the current moment based on the target pixel point coordinates and the operational data.

[0007] According to another aspect of the present invention, a cable fault detection device is also provided, comprising: a data acquisition module, configured to acquire a real-scene image, an infrared temperature image, and operating data of a target cable at a current moment; a point mapping parameter determination module, configured to determine point mapping parameters based on the real-scene image and the infrared temperature image, wherein the point mapping parameters are used to indicate the mapping relationship between the coordinates of a plurality of first pixel points in the infrared temperature image and the coordinates of a plurality of second pixel points in the real-scene image; a high-temperature pixel point coordinate determination module, configured to determine the coordinates of a high-temperature pixel point among the plurality of first pixel point coordinates, wherein the high-temperature pixel point coordinates represent the coordinate positions corresponding to the first pixel point whose temperature value is greater than a preset safe temperature threshold among the plurality of first pixel point coordinates; a target pixel point coordinate determination module, configured to map the high-temperature pixel point coordinates to the corresponding target pixel point coordinates among the plurality of second pixel point coordinates based on the point mapping parameters; and a fault detection result determination module, configured to determine the fault detection result of the target cable at the current moment based on the target pixel point coordinates and the operating data.

[0008] According to another aspect of the present invention, a non-volatile storage medium is also provided, which stores a plurality of instructions adapted for a cable fault detection method to be loaded by a processor and executed at any one of them.

[0009] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement any one of the cable fault detection methods.

[0010] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the steps of any one of the cable fault detection methods.

[0011] In this embodiment of the invention, the following steps are taken: First, a real-world image, an infrared temperature image, and operational data of the target cable at the current moment are acquired. Based on the real-world image and the infrared temperature image, point mapping parameters are determined. These parameters indicate the mapping relationship between the coordinates of multiple first pixels in the infrared temperature image and the coordinates of multiple second pixels in the real-world image. Second, the coordinates of high-temperature pixels among the multiple first pixels are determined. These high-temperature pixel coordinates represent the coordinate positions of the first pixels whose temperature value is greater than a preset safe temperature threshold. Finally, based on the point mapping parameters, the high-temperature pixel coordinates are mapped to the corresponding coordinates of the multiple second pixels. The target pixel coordinates are determined; based on the target pixel coordinates and operational data, the fault detection result of the target cable at the current moment is determined. This achieves the goal of determining the point mapping parameters through the real-scene image and infrared temperature image of the target cable, further mapping the extracted high-temperature pixel coordinates to the corresponding target pixel coordinates through the point mapping parameters, and finally accurately determining the fault detection result by combining the operational data. This achieves the technical effect of improving the accuracy of cable fault location and eliminating fault detection blind spots, thereby solving the technical problem of inaccurate cable fault location and the existence of fault detection blind spots caused by insufficient consideration of factors in related technologies in cable fault detection. Attached Figure Description

[0012] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0013] Figure 1 This is a flowchart of a cable fault detection method according to an embodiment of the present invention;

[0014] Figure 2 This is a flowchart of an optional cable fault detection method according to an embodiment of the present invention;

[0015] Figure 3 This is a flowchart of an optional cable fault detection system according to an embodiment of the present invention;

[0016] Figure 4 This is a schematic diagram of a cable fault detection device according to an embodiment of the present invention;

[0017] Figure 5 This is a schematic diagram of a cable fault detection electronic device according to an embodiment of the present invention. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0019] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] According to an embodiment of the present invention, a method embodiment for cable fault detection is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0021] Figure 1 This is a flowchart of a cable fault detection method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0022] Step S102: Obtain the real-world image, infrared temperature image, and operational data of the target cable at the current moment.

[0023] Optionally, real-scene images are used to provide clear geometric structure, appearance features, and spatial location information of the target cable and its joints; infrared temperature images are used to reflect the temperature and thermal distribution characteristics of the target cable; and operational data includes parameters such as load current and ambient humidity that reflect the real-time operating status and environmental conditions of the target cable. By simultaneously acquiring the above-mentioned multi-source heterogeneous data through infrared multi-source sensing devices, infrared thermal imagers, current sensors, and ambient temperature and humidity sensors, not only can the necessary visual foundation be provided for subsequent feature registration of real-scene images and infrared images to generate point mapping parameters, achieving accurate spatial correlation between the infrared temperature field and the physical entity location, but also multi-dimensional operating environment parameters are introduced. This provides data support for subsequent comprehensive risk warning based on physical location, thereby solving the technical problems in related technologies where single infrared monitoring cannot automatically correlate physical locations and the accuracy of single-dimensional data fault warnings is insufficient.

[0024] Step S104: Based on the real-scene image and the infrared temperature image, determine the point mapping parameters, wherein the point mapping parameters are used to indicate the mapping relationship between the coordinates of multiple first pixel points in the infrared temperature image and the coordinates of multiple second pixel points in the real-scene image.

[0025] Optionally, by using the acquired real-world images and infrared temperature images, point mapping parameters can be determined. These parameters are used to establish a precise geometric correspondence between the pixel space of the infrared temperature image and the pixel space of the real-world image. This allows for the automatic mapping of temperature hotspot coordinates from the abstract infrared thermal map to the coordinates of the real-world image, which has clear physical meaning. This solves the problem in related technologies where the lack of a spatial reference system in infrared monitoring leads to the knowledge that there are hotspots but not their locations. Without the need for manual comparison of images with cable ledgers, precise and automatic association between infrared heating fault points and specific target cable locations can be achieved in scenarios without GPS signals, such as tunnels and pipe corridors.

[0026] In one optional embodiment, determining point mapping parameters based on real-scene images and infrared temperature images includes: determining a first pixel located at a first position among a plurality of first pixel coordinates as a first target pixel, wherein the first position includes at least one of the following: a pixel with a sudden change in temperature gradient, a pixel with a heating inflection point; determining a second pixel located at a second position among a plurality of second pixel coordinates as a second target pixel, wherein the second position includes at least one of the following: a pixel with an edge of a metal joint, a pixel with a boundary of an insulator, a pixel with a connection of a bracket; and determining point mapping parameters based on the first target pixel and the second target pixel.

[0027] Optionally, feature points with significant thermodynamic changes, such as temperature gradient abrupt change boundaries or inflection points of heating areas in infrared temperature images, are extracted as the first target pixels. Feature points with stable geometric structures, such as metal joint edges, insulator boundaries, or bracket connections in real-world images, are extracted as the second target pixels. A mathematical mapping model is established using the spatial correspondence between these two types of target pixels to determine the point-location mapping parameters. This method leverages the stable and easily identifiable structural features of real-world images and the fault sensitivity of infrared thermal features. Through multi-source feature complementarity and matching, it effectively overcomes the problems of sparse or easily interfered features in a single image modality, significantly improving the robustness and accuracy of feature matching. This ensures that the generated point-location mapping parameters accurately reflect the spatial correspondence between infrared hotspots and physical cable joints, laying a solid foundation for subsequent high-precision fault location.

[0028] In an optional embodiment, when there are multiple first target pixels and multiple second target pixels, determining point mapping parameters based on the first target pixels and the second target pixels includes: determining multiple distances based on the multiple first target pixels and the multiple second target pixels, wherein any distance among the multiple distances represents the distance between any first target pixel among the multiple first target pixels and any second target pixel among the multiple second target pixels; determining the first target pixels and second target pixels corresponding to distances less than a preset distance among the multiple distances as pixel pairs; and determining point mapping parameters based on pixel pairs.

[0029] Optionally, by calculating the spatial distance between multiple first target pixels and multiple second target pixels, target pixel pairs with a distance less than a preset threshold are selected as matching point pairs, and the point mapping parameters are determined using the target pixel pairs. This method effectively filters out mismatched feature points through distance constraints and uses multiple pairs of matching points to construct redundant data to resist noise interference. It can significantly improve the accuracy and robustness of feature matching, ensuring that the generated point mapping parameters can accurately and stably reflect the spatial geometric transformation relationship between the infrared image and the real scene image, thereby ensuring the accuracy of subsequent fault point mapping.

[0030] In an optional embodiment, when there are multiple sets of pixel pairs, determining the point mapping parameters based on the pixel pairs includes: constructing a target equation set based on the multiple sets of pixel pairs, wherein the target equation set is used to indicate the transformation relationship between the corresponding first target pixel and the corresponding second target pixel included in the multiple sets of pixel pairs; performing singular value decomposition on the target equation set to obtain a solution vector; and determining the transformation matrix corresponding to the solution vector as the point mapping parameters.

[0031] Optionally, in determining the point mapping parameters, firstly, each pair of matched pixels (i.e., the corresponding first target pixel and the corresponding second target pixel) satisfies a homogeneous mapping relationship. ,in, Represents the homogeneous coordinates of any first target pixel. Represents the homogeneous coordinates of any second target pixel. This represents the transformation matrix. For each pair of pixels, the transformation is performed using the cross product constraint. Expanding this yields a system of linear equations for the corresponding pixel pairs. Next, the linear equations corresponding to multiple sets of pixels are concatenated to construct the target equation system Ah=0, where the unknown vector... It is formed by expanding the elements of the transformation matrix H in column-major order. Furthermore, singular value decomposition is performed on the coefficient matrix A. Where U represents the left singular matrix, Let V be the singular value diagonal matrix, and let V be the right singular matrix. The last column of the right singular matrix is ​​taken as the optimal solution vector. Finally, the solution vectors are rearranged into a matrix, and constraints (such as matrix normalization) are added to eliminate scale ambiguity, thus obtaining the final transformation matrix (i.e., the transformation matrix corresponding to the solution vectors). This transformation matrix is ​​the point mapping parameter. The above calculation method, by using multiple sets of pixels to construct a system of objective equations and combining singular value decomposition to solve the least squares solution, can effectively suppress the influence of noise interference and individual feature point matching errors, improve the robustness and accuracy of the mapping relationship, and ensure high-fidelity pixel-level geometric alignment between infrared images and real-world images, providing a reliable mathematical foundation for subsequent accurate fault hotspot localization.

[0032] Step S106: Determine the coordinates of the high-temperature pixel among the multiple first pixel coordinates, wherein the high-temperature pixel coordinates represent the coordinate positions of the first pixel whose temperature value is greater than a preset safe temperature threshold among the multiple first pixel coordinates.

[0033] Optionally, the coordinates of high-temperature pixels can be determined as follows: First, the acquired infrared temperature images are processed using a local lightweight convolutional neural network model to determine the coordinates of high-temperature pixels. This convolutional neural network model strictly adheres to standardized sample library construction specifications during the training phase. The sample library covers normal state samples under different voltage levels, laying methods (e.g., underground, overhead, tunnel), and environmental conditions (e.g., day and night, seasons, sunny and rainy), as well as samples of six typical defects such as overheating of cover joints, insulation degradation, and mechanical damage, and rare defects simulated in the laboratory, ensuring that the convolutional neural network model has broad generalization capabilities. During data acquisition and annotation, an infrared thermal imager with a resolution no lower than the preset pixel count and thermal sensitivity within the preset range is used. Emissivity is uniformly set, and environmental parameters are strictly recorded. Defect boundaries and temperature difference information are accurately labeled using polygons. A high-quality dataset is constructed using JSON metadata format containing equipment parameters, environmental data, and defect descriptions. The convolutional neural network... The network model training adopts a phased and progressive optimization strategy. First, global parameter optimization is performed through large-scale labeled samples to establish preliminary recognition capabilities. Then, transfer learning is introduced to reuse the feature extraction capabilities of the pre-trained model, and an attention mechanism is incorporated into the convolutional neural network architecture to enhance the ability to focus on key abnormal regions, thereby significantly improving the inference efficiency and accuracy of the convolutional neural network model at the edge terminal. In actual operation, the trained model is used to quickly extract high-temperature pixels in the image and identify the first pixel with a temperature value greater than the preset safe temperature threshold, i.e., the coordinates of the high-temperature pixel. This process can achieve high-speed and accurate fault detection under low computing power requirements at the edge without uploading massive amounts of original images to the cloud, effectively reducing data transmission bandwidth consumption and response latency. At the same time, through standardized data governance and model optimization, high sensitivity can be ensured for capturing weak heating signals and rare defects under complex working conditions, thereby improving the overall accuracy and real-time performance of cable fault detection.

[0034] Step S108: Based on the point mapping parameters, map the coordinates of the high-temperature pixel to the corresponding target pixel coordinates among multiple second pixel coordinates.

[0035] Optionally, using the obtained point mapping parameters, geometric transformation operations are performed on the extracted high-temperature pixel coordinates to accurately map the high-temperature hot spot pixel coordinates in the infrared temperature image to the corresponding target pixel coordinates in the real-world image. This enables the spatial coordinate transformation from an abstract thermal distribution space to a concrete physical entity space. As a result, high-temperature pixels that originally only appear as temperature anomalies in the infrared thermal image can be accurately located and superimposed on a real-world image with clear physical structural features. This allows for a direct indication of the specific cable location where the fault occurs (such as a specific hardware or stress cone). This solves the technical problem of knowing the heat but not the location in infrared monitoring, achieving pixel-level precise location and visual identification of the fault point, thereby greatly improving the efficiency and accuracy of maintenance personnel in troubleshooting.

[0036] In one optional embodiment, mapping the coordinates of a high-temperature pixel to the corresponding target pixel coordinates among a plurality of second pixel coordinates based on the point mapping parameters includes: mapping the coordinates of a high-temperature pixel to the corresponding initial pixel coordinates among a plurality of second pixel coordinates based on the point mapping parameters; and normalizing the initial pixel coordinates to obtain the target pixel coordinates.

[0037] Optionally, in determining the target pixel coordinates, firstly, using the point mapping parameters, the high-temperature pixel coordinates are transformed into homogeneous coordinates to calculate the initial pixel coordinates in the real-world image coordinate system. This is achieved by obtaining the homogeneous representation of the new coordinates through matrix multiplication. Subsequently, these initial pixel coordinates are normalized to obtain the final target pixel coordinates, thereby eliminating the bias introduced by the homogeneous coordinate scale and obtaining the precise physical pixel position in the real-world image. The target pixel coordinates can be obtained in the following way. ,in, This represents the x-coordinate of the target pixel. This represents the ordinate of the target pixel. This represents the x-coordinate of the initial pixel coordinates. This represents the y-coordinate in the initial pixel coordinates. This represents the vertical coordinate in the initial pixel coordinates. The above normalization process ensures the geometric accuracy of the mapping results, solves the scale inconsistency problem caused by the calculation of point mapping parameters, and enables the mapped target pixel coordinates to perfectly fit the actual pixel grid of the real scene image. This achieves precise spatial alignment between the infrared thermal anomaly area and the target cable entity in the real scene image, providing a reliable coordinate basis for intuitively identifying fault locations and issuing accurate work orders in the real scene image.

[0038] In an optional embodiment, mapping the coordinates of high-temperature pixels to the corresponding initial pixel coordinates among a plurality of second pixel coordinates based on the point-to-point mapping parameters includes: mapping the coordinates of high-temperature pixels to the initial pixel coordinates based on the point-to-point mapping parameters in the following manner:

[0039] ;

[0040] in, This represents the x-coordinate of the initial pixel coordinates. This represents the y-coordinate in the initial pixel coordinates. This represents the vertical coordinate in the initial pixel coordinate system. This represents the x-coordinate of the high-temperature pixel coordinates. This represents the ordinate of the high-temperature pixel coordinates. This represents the vertical coordinate of the high-temperature pixel. This represents the point mapping parameters.

[0041] Optionally, the above formula utilizes the linear transformation properties of matrix algebra to establish a strict geometric mapping relationship between the pixel space of the infrared image and the pixel space of the real-world image. This can accurately handle image perspective distortion caused by differences in camera viewpoint, distance, and installation angle, ensuring that any temperature anomaly point in the infrared thermal image can be accurately projected onto the corresponding physical location in the real-world image. This achieves spatial registration of cross-modal images, transforming invisible temperature distribution information into visible physical location information. This allows maintenance personnel to directly locate the specific source of the fault on the real-world image without manual comparison, thereby greatly improving the automation level and positioning accuracy of fault identification.

[0042] Step S110: Based on the target pixel coordinates and running data, determine the fault detection result of the target cable at the current moment.

[0043] Optionally, the target pixel coordinates and the real-time operational data of the target cable connection are fused and analyzed to generate a fault detection result. This process, through deep fusion of spatial positioning data and time-series operational data, can achieve a leap from single temperature alarms to multi-dimensional situational awareness, clearly identifying the specific physical location of the fault. It also combines electrical load and environmental factors to assess the urgency and causes of the fault, effectively reducing the false alarm rate caused by fluctuations in a single indicator, improving the confidence of fault diagnosis, and thus enhancing the intelligence level of cable operation and maintenance and the timeliness of fault handling.

[0044] In one optional embodiment, when the operating data includes the load current of the target pixel corresponding to the target pixel coordinates and the ambient humidity of the area where the target pixel is located, the fault detection result of the target cable at the current moment is determined based on the target pixel coordinates and the operating data. This includes: if the load current is within a preset current range and the ambient humidity is within a preset humidity range, determining that the fault detection result is that the target pixel is at a warning risk level at the current moment; if the load current is within a preset current range and the ambient humidity is not within a preset humidity range, determining that the fault detection result is that the target pixel is at a warning risk level at the current moment; or if the load current is not within a preset current range and the ambient humidity is within a preset humidity range, determining that the fault detection result is that the target pixel is at a warning risk level at the current moment; and if the load current is not within a preset current range and the ambient humidity is not within a preset humidity range, determining that the fault detection result is that the target pixel is at an emergency risk level at the current moment.

[0045] Optionally, firstly, obtain the real-time load current value and the ambient humidity value of the area corresponding to the target pixel coordinates, and compare these two parameters with preset current threshold ranges and humidity threshold ranges respectively: if the load current is within the preset current range and the ambient humidity is also within the preset humidity range, it is judged as a prompt-level risk warning, indicating that the target cable has local heating but the overall operating environment is stable and the risk is low; if the load current is within the preset current range but the ambient humidity exceeds the preset humidity range, or the load current exceeds the preset current range but the ambient humidity is within the preset humidity range, that is, only one indicator is abnormal, it is judged as a warning-level risk warning, indicating that the target cable has a single-dimensional potential hazard or environmental interference that needs attention; if the load current exceeds the preset current range and the ambient humidity also exceeds the preset humidity range, that is, both indicators are abnormal at the same time, it is judged as an emergency-level risk warning, indicating that the target cable is under the dual unfavorable conditions of high load overheating and harsh environment, and the probability of failure is high. The aforementioned multi-dimensional dynamic early warning mechanism can effectively distinguish between real fault heating caused by overload and false heating caused by high environmental humidity or external heat sources, thereby achieving graded and accurate early warning, avoiding false alarms and missed alarms caused by single temperature threshold alarms, improving the accuracy of fault detection and the pertinence of early warning, enabling maintenance personnel to rationally allocate emergency repair resources according to the early warning level, prioritize handling emergency risks, and improve the safety and efficiency of power grid operation and maintenance.

[0046] Through the above steps S102 to S110, the point mapping parameters can be determined by the real-scene image and infrared temperature image of the target cable. The extracted high-temperature pixel coordinates are then mapped to the corresponding target pixel coordinates through the point mapping parameters. Finally, the fault detection results are accurately determined by combining the operational data. This achieves the technical effect of improving the accuracy of cable fault location and eliminating fault detection blind spots. In turn, it solves the technical problem of inaccurate cable fault location and the existence of fault detection blind spots caused by insufficient consideration of factors in related technologies in cable fault detection.

[0047] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation method. Figure 2 This is a flowchart of an optional cable fault detection method according to an embodiment of the present invention, such as... Figure 2 As shown, the method includes:

[0048] S01: Equipped with an infrared multi-source sensing device to continuously collect infrared temperature spectrum, real-scene image, load current, and ambient humidity of the cable. Specifically, it includes: acquiring infrared temperature spectrum of the cable through an infrared thermal imager to obtain temperature distribution data, acquiring real-scene image of the cable through a visible light camera to obtain visual feature data, and simultaneously acquiring real-time load current of the cable and ambient humidity of the environment through a current sensor and an ambient temperature and humidity sensor, and storing the multi-source data synchronously.

[0049] S02: Complete the feature registration of the infrared image and the cable joint location, generate the location mapping parameters and send them to the edge terminal. Specifically, this includes: extracting thermal feature points such as temperature gradient abrupt boundary in the infrared temperature spectrum as the first target pixel point, extracting geometric feature points such as metal joint corners and insulator boundaries in the real scene image as the second target pixel point, constructing a target equation system based on the determined multiple sets of pixel point pairs, and solving the transformation matrix by singular value decomposition. The transformation matrix is ​​stored as the location mapping parameters and sent to the edge terminal. The specific implementation process is the same as the aforementioned embodiment and will not be repeated here.

[0050] S03: Extract the hot spots in the infrared image, output the hot spot pixel coordinates, and call the point mapping parameters to complete the automatic mapping of the hot spot pixel coordinates to the cable joint point. Specifically, this includes: using a lightweight convolutional neural network model to identify the coordinates of high-temperature pixels (i.e., hot spot pixel coordinates) in the infrared temperature spectrum with a temperature greater than a preset safety threshold; calling the point mapping parameters to map the high-temperature pixel coordinates to the real-scene image coordinate system through matrix multiplication to obtain the initial pixel coordinates; and normalizing the initial coordinates to obtain the target pixel coordinates, thereby determining the specific location of the hot spot in the real-scene image. The specific implementation process is the same as in the aforementioned embodiment and will not be repeated here.

[0051] S04: Integrating load current and ambient humidity to provide risk warning for cable joint locations, specifically including: comparing the real-time load current and ambient humidity corresponding to the target pixel with preset current thresholds and humidity thresholds respectively; and determining the fault detection result as a prompt risk warning level, a warning risk warning level, or an emergency risk warning level based on different combinations of whether the load current and ambient humidity exceed the preset range. The specific implementation process is the same as in the aforementioned embodiments and will not be repeated here.

[0052] S05: Receive the mapped cable joint location, issue fault location work orders and early warning information, specifically including: receiving the coordinates of the target pixel point located by mapping and the corresponding risk warning level information, generating a fault location work order containing the specific location of the fault, the defect type and the handling suggestions based on the early warning level, and pushing the corresponding early warning information to the operation and maintenance terminal.

[0053] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation method. Figure 3 This is a flowchart of an optional cable fault detection system according to an embodiment of the present invention, such as... Figure 3 As shown, the system includes: an infrared data sensing and acquisition module, a feature extraction and intelligent processing module, a pixel-level fault location module, a multi-dimensional dynamic early warning module, and a cloud-based integrated management module. Specifically:

[0054] The infrared data sensing and acquisition module is used to continuously acquire infrared temperature spectra, real-scene images, load current, and ambient humidity of the cable using infrared multi-source sensing equipment. The feature extraction and intelligent processing module is used to complete feature registration between the infrared image and the cable joint location, generating point mapping parameters and sending them to the edge terminal. The edge terminal is equipped with a network monitoring mode switching function, automatically switching between online and offline autonomous modes to ensure secure data transmission. The pixel-level fault location module uses a local lightweight convolutional neural network model to extract heat spots from the infrared image, outputting the hotspot pixel coordinates and calling the point mapping parameters to automatically map the hotspot pixel coordinates to the cable joint location. The multi-dimensional dynamic early warning module integrates load current and ambient humidity to provide risk warnings for cable joint locations. The cloud-based integrated management module receives the mapped cable joint locations and issues fault location work orders and early warning information.

[0055] This embodiment also provides a cable fault detection device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the terms "module" and "device" can refer to a combination of software and / or hardware that performs a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0056] According to an embodiment of the present invention, an apparatus embodiment for implementing the above-described cable fault detection method is also provided. Figure 4 This is a schematic diagram of the structure of a cable fault detection device according to an embodiment of the present invention, as shown below. Figure 4 As shown, the above-mentioned cable fault detection device includes: a data acquisition module 400, a point mapping parameter determination module 402, a high-temperature pixel coordinate determination module 404, a target pixel coordinate determination module 406, and a fault detection result determination module 408, wherein:

[0057] The data acquisition module 400 is used to acquire real-time images, infrared temperature images, and operational data of the target cable at the current moment.

[0058] The point mapping parameter determination module 402 is connected to the data acquisition module 400 and is used to determine the point mapping parameters based on the real scene image and the infrared temperature image. The point mapping parameters are used to indicate the mapping relationship between the coordinates of multiple first pixel points in the infrared temperature image and the coordinates of multiple second pixel points in the real scene image.

[0059] The high-temperature pixel coordinate determination module 404 is connected to the point mapping parameter determination module 402 and is used to determine the coordinates of the high-temperature pixel among multiple first pixel coordinates. The high-temperature pixel coordinates represent the coordinate positions of the first pixel whose temperature value is greater than a preset safe temperature threshold among multiple first pixel coordinates.

[0060] The target pixel coordinate determination module 406 is connected to the high temperature pixel coordinate determination module 404 and is used to map the high temperature pixel coordinates to the corresponding target pixel coordinates among multiple second pixel coordinates based on the point mapping parameters.

[0061] The fault detection result determination module 408 is connected to the target pixel coordinate determination module 406 and is used to determine the fault detection result of the target cable at the current moment based on the target pixel coordinates and running data.

[0062] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0063] It should be noted that the data acquisition module 400, the point mapping parameter determination module 402, the high-temperature pixel coordinate determination module 404, the target pixel coordinate determination module 406, and the fault detection result determination module 408 correspond to steps S102 to S110 in the embodiments. The instances and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run in a computer terminal.

[0064] It should be noted that the optional or preferred implementation methods of this embodiment can be found in the relevant descriptions in the embodiments, and will not be repeated here.

[0065] The aforementioned cable fault detection device may further include a processor and a memory. The aforementioned data acquisition module 400, point mapping parameter determination module 402, high temperature pixel coordinate determination module 404, target pixel coordinate determination module 406, fault detection result determination module 408, etc., are all stored in the memory as program modules, and the processor executes the aforementioned program modules stored in the memory to realize the corresponding functions.

[0066] The processor contains a core that retrieves the corresponding program modules from memory. One or more cores may be configured. Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip.

[0067] According to an embodiment of this application, an embodiment of a non-volatile storage medium is also provided. Optionally, in this embodiment, the non-volatile storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the non-volatile storage medium to perform any of the cable fault detection methods described above.

[0068] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals, and the non-volatile storage medium includes stored programs.

[0069] Optionally, during program execution, the device containing the non-volatile storage medium may be controlled to perform the following functions: acquire the real-world image, infrared temperature image, and operational data of the target cable at the current moment; determine the point mapping parameters based on the real-world image and infrared temperature image, wherein the point mapping parameters are used to indicate the mapping relationship between the coordinates of multiple first pixels in the infrared temperature image and the coordinates of multiple second pixels in the real-world image; determine the coordinates of high-temperature pixels among the multiple first pixels, wherein the high-temperature pixel coordinates represent the coordinate positions of the first pixels whose temperature values ​​are greater than a preset safe temperature threshold; map the high-temperature pixel coordinates to the corresponding target pixel coordinates among the multiple second pixel coordinates based on the point mapping parameters; and determine the fault detection result of the target cable at the current moment based on the target pixel coordinates and operational data.

[0070] According to an embodiment of this application, an embodiment of a processor is also provided. Optionally, in this embodiment, the processor is used to run a program, wherein the program executes any of the above-described cable fault detection methods.

[0071] According to an embodiment of this application, an embodiment of a computer program product is also provided. Optionally, in this embodiment, the computer program product includes a computer program that, when executed by a processor, implements the cable fault detection method steps described above.

[0072] Optionally, when the aforementioned computer program product is executed on a data processing device, it is suitable to execute an initialization program with the following method steps: acquiring a real-world image, an infrared temperature image, and operational data of the target cable at the current moment; determining point mapping parameters based on the real-world image and the infrared temperature image, wherein the point mapping parameters are used to indicate the mapping relationship between the coordinates of multiple first pixel points in the infrared temperature image and the coordinates of multiple second pixel points in the real-world image; determining the coordinates of high-temperature pixel points among the multiple first pixel point coordinates, wherein the high-temperature pixel point coordinates represent the coordinate positions of the first pixel point whose temperature value is greater than a preset safe temperature threshold among the multiple first pixel point coordinates; mapping the high-temperature pixel point coordinates to the corresponding target pixel point coordinates among the multiple second pixel point coordinates based on the point mapping parameters; and determining the fault detection result of the target cable at the current moment based on the target pixel point coordinates and the operational data.

[0073] like Figure 5As shown, this embodiment of the invention provides an electronic device 10, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: acquiring a real-world image, an infrared temperature image, and operational data of the target cable at the current moment; determining point mapping parameters based on the real-world image and the infrared temperature image, wherein the point mapping parameters are used to indicate the mapping relationship between the coordinates of multiple first pixels in the infrared temperature image and the coordinates of multiple second pixels in the real-world image; determining the coordinates of high-temperature pixels among the multiple first pixels, wherein the high-temperature pixel coordinates represent the coordinate positions of the first pixels whose temperature values ​​are greater than a preset safe temperature threshold; mapping the high-temperature pixel coordinates to the corresponding target pixel coordinates among the multiple second pixel coordinates based on the point mapping parameters; and determining the fault detection result of the target cable at the current moment based on the target pixel coordinates and the operational data.

[0074] The order of the above embodiments of the present invention is merely for description and does not represent the superiority or inferiority of the embodiments.

[0075] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of modules described above can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between modules, and may be electrical or other forms.

[0077] The modules described above as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple modules. Some or all of the modules can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0078] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0079] If the aforementioned integrated modules are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a non-volatile storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned non-volatile storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0080] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for detecting cable faults, characterized in that, include: Acquire real-time images, infrared temperature images, and operational data of the target cable; Based on the real-scene image and the infrared temperature image, point mapping parameters are determined, wherein the point mapping parameters are used to indicate the mapping relationship between the coordinates of multiple first pixel points in the infrared temperature image and the coordinates of multiple second pixel points in the real-scene image; Determine the coordinates of the high-temperature pixel among the plurality of first pixel coordinates, wherein the high-temperature pixel coordinates represent the coordinate positions of the first pixel whose temperature value is greater than a preset safe temperature threshold among the plurality of first pixel coordinates; Based on the point mapping parameters, the coordinates of the high-temperature pixel point are mapped to the corresponding target pixel point coordinates among the plurality of second pixel point coordinates; Based on the target pixel coordinates and the running data, the fault detection result of the target cable at the current moment is determined.

2. The method according to claim 1, characterized in that, The step of determining the point mapping parameters based on the real-scene image and the infrared temperature image includes: The first pixel located at a first position among the plurality of first pixel coordinates is determined as the first target pixel, wherein the first position includes at least one of the following: a pixel with a sudden change in temperature gradient, or a pixel with a heating inflection point; The second pixel point located at the second position among the plurality of second pixel point coordinates is determined as the second target pixel point, wherein the second position includes at least one of the following: the corner pixel point of the metal joint, the boundary pixel point of the insulator, and the connection pixel point of the bracket; The point mapping parameters are determined based on the first target pixel and the second target pixel.

3. The method according to claim 2, characterized in that, When there are multiple first target pixels and multiple second target pixels, determining the point mapping parameters based on the first target pixels and the second target pixels includes: Based on multiple first target pixels and multiple second target pixels, multiple distances are determined, wherein any one of the multiple distances represents the distance between any one of the multiple first target pixels and any one of the multiple second target pixels; Among the plurality of distances, the first target pixel and the second target pixel corresponding to the distance that is less than the preset distance are determined as pixel pairs; Based on the pixel pairs, the point mapping parameters are determined.

4. The method according to claim 3, characterized in that, When there are multiple sets of pixel pairs, determining the point mapping parameters based on the pixel pairs includes: Based on multiple sets of pixel pairs, a set of target equations is constructed, wherein the set of target equations is used to indicate the transformation relationship between the corresponding first target pixel and the corresponding second target pixel included in the multiple sets of pixel pairs; Singular value decomposition is performed on the objective equation system to obtain the solution vector; The transformation matrix corresponding to the solution vector is determined as the point mapping parameter.

5. The method according to claim 1, characterized in that, The step of mapping the coordinates of the high-temperature pixel to the corresponding target pixel coordinates among the plurality of second pixel coordinates based on the point mapping parameters includes: Based on the point mapping parameters, the coordinates of the high-temperature pixel point are mapped to the corresponding initial pixel point coordinates among the plurality of second pixel point coordinates; The initial pixel coordinates are normalized to obtain the target pixel coordinates.

6. The method according to claim 5, characterized in that, The step of mapping the coordinates of the high-temperature pixel point to the corresponding initial pixel point coordinates among the plurality of second pixel point coordinates based on the point mapping parameters includes: Based on the point mapping parameters, the coordinates of the high-temperature pixel are mapped to the coordinates of the initial pixel in the following manner: ； in, This represents the x-coordinate in the initial pixel coordinates. This represents the ordinate in the initial pixel coordinates. This represents the vertical coordinate in the initial pixel coordinates. This represents the x-coordinate in the coordinates of the high-temperature pixel. This represents the ordinate in the coordinates of the high-temperature pixel. This represents the vertical coordinate in the coordinates of the high-temperature pixel. This represents the point mapping parameters.

7. The method according to any one of claims 1 to 6, characterized in that, When the operating data includes the load current of the target pixel corresponding to the target pixel coordinates and the ambient humidity of the area where the target pixel is located, determining the fault detection result of the target cable at the current moment based on the target pixel coordinates and the operating data includes: If the load current is within a preset current range and the ambient humidity is within a preset humidity range, the fault detection result is determined to be that the target pixel is at a warning risk level at the current moment; or If the load current is within the preset current range and the ambient humidity is not within the preset humidity range, the fault detection result is determined to be that the target pixel is at a warning risk level at the current moment; or If the load current is not within the preset current range and the ambient humidity is within the preset humidity range, the fault detection result is determined to be that the target pixel is at the warning risk level at the current moment; or If the load current is not within the preset current range and the ambient humidity is not within the preset humidity range, the fault detection result is determined to be that the target pixel is at an emergency risk warning level at the current moment.

8. A cable fault detection device, characterized in that, include: The data acquisition module is used to acquire real-time images, infrared temperature images, and operational data of the target cable at the current moment. The point mapping parameter determination module is used to determine point mapping parameters based on the real scene image and the infrared temperature image, wherein the point mapping parameters are used to indicate the mapping relationship between the coordinates of multiple first pixel points in the infrared temperature image and the coordinates of multiple second pixel points in the real scene image; The high-temperature pixel coordinate determination module is used to determine the coordinates of high-temperature pixels among the plurality of first pixel coordinates, wherein the high-temperature pixel coordinates represent the coordinate positions of the first pixel whose temperature value is greater than a preset safe temperature threshold among the plurality of first pixel coordinates. The target pixel coordinate determination module is used to map the high-temperature pixel coordinates to the corresponding target pixel coordinates among the plurality of second pixel coordinates based on the point mapping parameters. The fault detection result determination module is used to determine the fault detection result of the target cable at the current moment based on the target pixel coordinates and the running data.

9. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores multiple instructions adapted for loading by a processor and executing the cable fault detection method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the cable fault detection method according to any one of claims 1 to 7.

Images