Cable sheath fracture early warning method and system

Abstract

The embodiment of the invention discloses a cable sheath fracture early warning method and system. According to the technical scheme provided by the embodiment of the invention, the method comprises the steps: obtaining the shot image data of the corresponding target cable sheath, and determining the cable monitoring node information of the position where the target cable sheath is located; identifying the image data to obtain an image identification result, and determining a fixed type of monitoring data content in the cable monitoring node information according to the image identification result; and generating early warning information of the target cable sheath based on the monitoring data content and the image recognition result. By adopting the above technical means, cable sheath fracture analysis and early warning are performed by combining the image recognition result of the target cable sheath and the monitoring data content of the corresponding type, accurate and reliable early warning of the sheath fracture risk can be realized, multi-dimensional data support is provided for operation and maintenance decision, and the reliability and stability of cable operation and maintenance are improved.

Description

Technical Field

[0001] This application relates to the field of cable technology, and in particular to a method and system for early warning of cable sheath rupture. Background Technology

[0002] Currently, cables, as the core carriers of power transmission and signal communication, are crucial for ensuring the safety of infrastructure through their long-term stable operation. The cable sheath, as the outermost protective structure of the cable, bears multiple protective functions, including resisting mechanical stress, chemical corrosion, environmental moisture penetration, and electromagnetic interference. Once the sheath cracks due to external impact, aging, or environmental erosion, the internal conductors will be directly exposed to the harsh environment, easily leading to serious accidents such as decreased insulation performance, short circuits, grounding faults, and even fires. Therefore, early and accurate detection and warning of sheath damage is a key aspect of safe cable operation and maintenance. Currently, cable sheath condition monitoring mainly relies on two methods: one is manual periodic inspection, which involves visually inspecting the sheath surface using handheld devices; the other is online electrical parameter monitoring, which indirectly infers the insulation condition based on sensor data such as current, voltage, and partial discharge.

[0003] However, existing cable sheath condition monitoring solutions lack sensitivity to early physical damage to the sheath (such as surface cracks and scratches) that has not yet affected electrical performance, failing to directly correlate with apparent defects and resulting in delayed early warnings. This, in turn, prevents maintenance personnel from quickly locating defective sections, impacting the accuracy of risk assessments. Summary of the Invention

[0004] This application provides a cable sheath rupture early warning method and system, which can deeply integrate the sheath appearance image features with the cable's multi-dimensional operating parameters for intelligent diagnosis, realize accurate and reliable early warning of sheath rupture risk, and provide multi-dimensional data support for operation and maintenance decisions, thus solving the technical problem of delayed early warning of cable sheath rupture.

[0005] In a first aspect, embodiments of this application provide a method for early warning of cable sheath rupture, comprising: Acquire image data of the corresponding target cable sheath and determine the cable monitoring node information at the location of the target cable sheath; The image data is identified to obtain an image recognition result, and the fixed type of monitoring data content is determined in the cable monitoring node information based on the image recognition result; Early warning information for the target cable sheath is generated based on the monitoring data and image recognition results.

[0006] Further, the step of identifying the image data to obtain the image recognition result includes: The image data is input into a pre-constructed cable sheath rupture feature extraction model, and the corresponding crack features are output as the image recognition result. The crack features include the length, width and distribution density of the cable sheath cracks.

[0007] Further, determining the fixed type of monitoring data content in the cable monitoring node information based on the image recognition result includes: Based on the different values ​​of the length, width, and distribution density of the cable sheath cracks in the image recognition results, a fixed type of monitoring data content is determined in the cable monitoring node information.

[0008] Furthermore, the image recognition result includes at least one of crack features, scratch features, and damaged area.

[0009] Furthermore, after obtaining the image recognition result by recognizing the image data, the method further includes: The frequency of collecting cable monitoring node information is adjusted based on the image recognition results, and the collected cable monitoring node information is updated in real time.

[0010] Furthermore, the step of generating early warning information for the target cable sheath based on the monitoring data content and image recognition results includes: The image recognition results and the monitoring data are input into a preset risk assessment model, which outputs the corresponding rupture risk information. When the rupture risk information reaches the set conditions, an early warning message is generated that includes the location of the monitoring node, the risk level, and recommended handling measures.

[0011] Furthermore, after generating the early warning information for the target cable sheath based on the monitoring data content and image recognition results, the method further includes: A location map is generated based on the monitoring node locations in the early warning information, and the early warning location and the retrieved historical curves of monitoring data are marked on the location map.

[0012] In a second aspect, embodiments of this application provide a cable sheath rupture early warning system, comprising: The acquisition module is used to acquire image data captured by the corresponding target cable sheath and determine the cable monitoring node information at the location of the target cable sheath; The identification module is used to identify the image data to obtain the image identification result, and to determine the fixed type of monitoring data content in the cable monitoring node information based on the image identification result; The early warning module is used to generate early warning information for the target cable sheath based on the monitoring data content and image recognition results.

[0013] In a third aspect, embodiments of this application provide an electronic device, including: Memory and one or more processors; The memory is used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the cable sheath rupture early warning method as described in the first aspect.

[0014] In a fourth aspect, embodiments of this application provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the cable sheath rupture early warning method as described in the first aspect.

[0015] This application embodiment acquires image data of the target cable sheath and determines the cable monitoring node information at the location of the target cable sheath; it then identifies the image data to obtain image recognition results, and determines fixed-type monitoring data content in the cable monitoring node information based on the image recognition results; finally, it generates early warning information for the target cable sheath based on the monitoring data content and the image recognition results. By employing the above technical means, and combining the image recognition results of the target cable sheath with the corresponding type of monitoring data content for cable sheath rupture analysis and early warning, accurate and reliable early warning of sheath rupture risk can be achieved, providing multi-dimensional data support for operation and maintenance decisions, and improving the reliability and stability of cable operation and maintenance. Attached Figure Description

[0016] Figure 1 This is a flowchart of a cable sheath rupture early warning method provided in Embodiment 1 of this application; Figure 2 This is a schematic diagram of the cable sheath rupture early warning frame in Embodiment 1 of this application; Figure 3 This is a flowchart illustrating the generation of early warning information in Embodiment 1 of this application; Figure 4 This is a schematic diagram of the structure of a cable sheath rupture early warning system provided in Embodiment 1 of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 1 of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, specific embodiments of this application will be described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. It should also be noted that, for ease of description, only the parts relevant to this application are shown in the drawings, not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0018] Example 1: Figure 1 A flowchart of a cable sheath rupture early warning method according to Embodiment 1 of this application is provided. The cable sheath rupture early warning method provided in this embodiment can be executed by a cable sheath rupture early warning device. This device can be implemented by software and / or hardware, and can consist of two or more physical entities, or a single physical entity. Generally, the cable sheath rupture early warning device can be a computing device such as a backend server host of a cable sheath rupture early warning framework.

[0019] The following description uses a backend server as the main body for implementing the cable sheath rupture early warning method. (Refer to...) Figure 1 The cable sheath rupture early warning method specifically includes: S110. Acquire image data of the corresponding target cable sheath and determine the cable monitoring node information at the location of the target cable sheath.

[0020] The cable sheath rupture early warning method proposed in this application constructs a complete closed loop from apparent defect detection to risk warning. Its core lies in breaking down information silos in traditional monitoring methods, achieving deep integration of physical state visualization and electrical parameter analysis. Specifically, in the data acquisition phase, the system uses high-definition image acquisition devices or drone inspection systems deployed along the cable line to acquire real-time image data of the sheath surface at fixed intervals or dynamic paths. This image data, after being labeled with timestamps and spatial coordinates, is bound to the monitoring node codes in the cable network topology. For example, in underground utility tunnel scenarios, weather-resistant industrial cameras can be used in conjunction with track-mounted inspection robots to achieve all-weather image acquisition; in overhead line scenarios, drones equipped with multispectral imaging equipment can perform periodic scanning along preset routes. Simultaneously, a multi-dimensional sensor array configured at each cable monitoring node continuously collects operating parameters such as temperature, humidity, vibration acceleration, and partial discharge. All data is aggregated to the backend server via power line carrier communication or a dedicated wireless network. This completes the acquisition of cable sheath surface image data and cable monitoring node information.

[0021] For example, refer to Figure 2 Image acquisition devices 111 (or dynamic acquisition via drone inspection, etc.) and sensors 112 for collecting cable monitoring node information are installed at intervals along the cable 11. The cable monitoring node information and sensor 112 at each location respectively collect image data and cable monitoring node information captured by the target cable sheath, and then aggregate the collected data to the backend server 113, thereby completing the basic data collection for cable sheath rupture early warning.

[0022] By spatially aligning the images with the node parameters, the initial correlation between the physical state of the sheath and the electrical operating state was achieved. This solves the problems of low coverage, strong subjectivity, and inability to quantify defect locations in traditional manual inspections, and provides a high-fidelity raw dataset for subsequent analysis.

[0023] S120. The image data is identified to obtain the image recognition result. Based on the image recognition result, the fixed type of monitoring data content is determined in the cable monitoring node information.

[0024] Furthermore, based on the aforementioned image data and monitoring node information, a deep learning-driven image recognition engine is first employed to automatically detect defects in the acquired images. This engine, based on an improved YOLOv7 or EfficientDet architecture, can be pre-trained on a dataset containing hundreds of thousands of cable sheath defect samples using transfer learning techniques. This allows for accurate identification of typical defect types in cable sheaths, such as minute surface cracks, wear grooves, and chemical corrosion marks. Depending on the specific requirements, the recognition results can include various cable defect feature types. The recognition results not only include the geometric feature parameters of the defects but also generate defect region masks using semantic segmentation techniques, providing spatial guidance for subsequent parameter association.

[0025] Furthermore, based on the image recognition results determined above, this application further selects fixed types of information from the cable monitoring node information according to different image recognition results as monitoring data content for subsequent cable sheath rupture early warning analysis.

[0026] Based on the established association rules, the system filters corresponding cable monitoring node information according to the defect type characteristics determined by image recognition results. For example, when mechanical damage characteristics are detected in the cable (such as surface cracks, wear grooves, etc.), triaxial vibration acceleration data and strain sensor data are retrieved first; when corrosive damage is identified, environmental parameters such as temperature and humidity gradients and chemical gas concentrations are analyzed in detail. The on-demand retrieval mechanism avoids the bandwidth pressure caused by full data transmission while ensuring that the analysis model always focuses on physical quantities strongly correlated with the current defect mode. For example, for longitudinal cracks on the sheath surface, the system automatically associates historical bending stress data and diurnal temperature cycle records for that section, thereby constructing a stress-damage evolution model analysis.

[0027] Optionally, the image data is processed to obtain image recognition results, including: Image data is input into a pre-built cable sheath rupture feature extraction model, and the corresponding crack features are output as image recognition results. Crack features include the length, width and distribution density of cable sheath cracks.

[0028] Furthermore, in the image recognition stage, accurate quantification and characterization of crack features can be achieved through multi-level technology fusion. The pre-built cable sheath crack feature extraction model adopts a collaborative mechanism of deep learning and computer vision. Its core architecture consists of a feature encoding network, a multi-scale decoder, and a geometric measurement module. The feature encoding network typically uses models with strong feature extraction capabilities, such as DenseNet-121 or Vision Transformer (ViT), as the backbone, and is fine-tuned on a dedicated dataset containing hundreds of thousands of labeled samples through transfer learning. This dataset covers different sheath materials, various damage morphologies, and complex environmental interference scenarios. Each sample uses the actual crack size obtained by a high-precision 3D scanner or laser profilometer as the annotation benchmark to ensure that the model learns the mapping relationship from pixel distribution to physical size. A contrastive learning strategy is introduced during model training to enhance the distinction between crack edges and background textures through positive and negative sample pairs. At the same time, knowledge distillation technology is used to transfer the feature representation capabilities of the large teacher network to the lightweight student model to adapt to the deployment requirements of edge computing devices.

[0029] In the feature extraction stage, the input image is first enhanced with a super-resolution reconstruction network to improve detail. For the detection of tiny cracks (width < 0.1 mm), a residual dense network (RDN) combined with sub-pixel convolutional layers is used to recover high-frequency details through multi-path feature fusion and layer-by-layer upsampling. Subsequently, an improved DeepLabv3+ network performs pixel-level semantic segmentation, generating crack region masks while focusing on high-risk morphological features through a spatial channel attention module. To quantify crack geometric parameters, the system implements a post-processing procedure for the segmentation results: a phase consistency model is used to replace the traditional edge detection operator, and frequency domain analysis is used to accurately locate the crack skeleton, avoiding edge breaks caused by uneven illumination; a stochastic Hough transform is used to detect the crack's principal axis direction, and the average width perpendicular to the principal axis direction is measured using the minimum bounding rectangle method and dynamic programming algorithm. A graph-based width-weighted algorithm is specifically developed for branch cracks; for complex morphologies such as mesh cracks, superpixel segmentation and a Markov random field model are applied to statistically analyze the density of crack intersections and the number of branches per unit area as distribution density indicators, and morphological reconstruction is used to eliminate noise interference. Using the above method, the crack features corresponding to the length, width, and distribution density of the cable sheath cracks can be obtained as image recognition results.

[0030] Furthermore, based on the image recognition results, fixed types of monitoring data content are determined in the cable monitoring node information, including: Based on the different values ​​of the length, width, and distribution density of the cable sheath cracks in the image recognition results, the fixed type of monitoring data content is determined in the cable monitoring node information.

[0031] The process of dynamically determining monitoring data content based on image recognition results essentially involves constructing a causal relationship network between physical defect morphology features and cable operating status parameters. This step achieves intelligent data retrieval through a pre-defined defect-parameter mapping rule base. Its core logic lies in transforming the geometric attributes of cracks into quantitative diagnostic criteria for specific failure mechanisms. When the image recognition module outputs parameters such as crack length, width, and distribution density, the system can perform preliminary failure mode judgment based on a material mechanics model. For example, when the crack length exceeds 30% of the sheath circumference or the width reaches 0.5 mm, the retrieval of mechanical stress-related parameters is triggered, including data streams such as triaxial vibration acceleration, bending strain, and joint displacement. If the cracks exhibit a network distribution and the density exceeds 5 cracks / cm², environmental corrosion monitoring indicators, such as historical sequences of temperature and humidity cycles, chemical gas concentration, and ultraviolet exposure dose, are activated first. This dynamic correlation mechanism is implemented through a rule engine deployed on edge computing nodes. This engine has a built-in knowledge base based on fault tree analysis (FTA), containing multiple defect-parameter mapping rules covering various typical failure scenarios such as mechanical damage, chemical corrosion, and thermal aging. By establishing a causal relationship network between the physical defect morphology features and cable operating status parameters, the corresponding type of monitoring node information can be selected from the cable monitoring node information as monitoring data content based on the different values ​​of the length, width, and distribution density of the cable sheath cracks in the image recognition results.

[0032] Optionally, the image recognition results include at least one of crack features, scratch features, and damaged area.

[0033] Depending on the actual monitoring needs, the image recognition results in the image recognition process may include at least one of crack features, scratch features, and damaged area. Different image recognition results can be identified based on a pre-built feature extraction model. This application does not impose fixed limitations on the image recognition results collected by the feature extraction model, and will not elaborate further here. Similarly, for different image recognition results, the monitoring data content can also be determined through the causal relationship network between the aforementioned physical defect morphology features and cable operating status parameters, thereby providing accurate analytical data for cable sheath rupture early warning.

[0034] After obtaining image recognition results by recognizing image data, the process also includes: The frequency of cable monitoring node information collection is adjusted based on the image recognition results, and the collected cable monitoring node information is updated in real time.

[0035] Based on the image recognition results, this application further optimizes the dynamic monitoring of cable monitoring node information. An adaptive sampling strategy is used to achieve intelligent matching of monitoring resources and risk levels. The core of this strategy lies in constructing a closed-loop feedback mechanism between defect severity and data acquisition frequency. For example, after completing image recognition and acquiring characteristic parameters such as crack length, width, and distribution density, a mapping relationship between crack geometric parameters and remaining lifespan is established, and a real-time risk index is calculated based on cable operating conditions (such as load fluctuations and ambient temperature and humidity). When the risk index exceeds a preset threshold, the acquisition frequency adjustment module is triggered. An optimized sampling interval is determined through a nonlinear mapping function, for example, shortening the high-frequency partial discharge monitoring cycle from 1 hour to 5 minutes, while simultaneously increasing the bandwidth of the vibration acceleration sensor from 1 kHz to 10 kHz to capture weak impact signals.

[0036] In addition, a threshold triggering mechanism based on a sliding window can be adopted. The system presets multiple risk thresholds. When the crack characteristic parameters exceed a certain threshold for N consecutive samples, the sampling frequency of the corresponding monitoring channel is automatically increased to the next preset value. For example, the initial frequency is 1 time / hour, which is increased to 1 time / 10 minutes when the crack width is detected to be >0.3mm, and further increased to 1 time / minute when it exceeds 0.5mm. By dynamically adjusting the sampling frequency of cable monitoring node information, the timeliness of cable sheath rupture early warning can be improved.

[0037] S130. Generate early warning information for the target cable sheath based on monitoring data and image recognition results.

[0038] Subsequently, in the risk warning stage, this application generates warning information with spatiotemporal continuity and causal interpretability through multimodal data fusion and dynamic risk assessment. Its core lies in constructing a quantitative mapping mechanism from apparent defects to failure probability. This process first aligns the image recognition results (morphological features such as crack length, width, and distribution density) with the synchronously acquired monitoring data (time-series parameters such as temperature, vibration, partial discharge, and strain). A clock correction technique based on phase synchronization is used to ensure that the timestamp error of the multi-source data is less than 1 μs. Then, the image pixel coordinates are mapped to the geographic information system (GIS) coordinate system of the cable line through three-dimensional coordinate transformation.

[0039] Furthermore, at the data fusion level, a dual-stream convolutional recurrent neural network (DCRNN) is employed. The image feature stream uses an improved ResNeXt-101 architecture to extract multi-scale crack morphology encoding, while the temporal data stream (i.e., monitoring data content) captures the dynamic evolution patterns of monitoring parameters through a Long Short-Term Memory (LSTM) network. The two streams are fused at a higher level through a cross-attention mechanism, enabling the model to learn the potential correlation between morphological features and physical parameters, such as the exponential correlation between crack width variation and partial discharge amplitude. To enhance the model's adaptability to complex defect scenarios, a graph attention network (GAT) is introduced to construct a risk propagation model between cable segments. Monitoring data from adjacent segments are incorporated as contextual information into the risk assessment of the current node, and a message passing mechanism simulates the diffusion effect of stress waves or corrosive media in the cable network.

[0040] The risk assessment module employs a Monte Carlo-Markov chain hybrid model, generating a risk probability distribution based on fused features. First, a variational autoencoder (VAE) probabilistically models the defect evolution path, generating 1000 possible extension trajectories. Then, a physics engine-driven digital twin simulates the cable stress-strain response under each trajectory, and the failure probability density function is calculated by combining the material fatigue curve (SN curve). This process specifically considers the time-varying influence of environmental factors, introducing a Weibull distribution to describe the stochastic process of covariates such as temperature and humidity, enabling the risk assessment to be environmentally adaptive. For example, when a sheath crack width of 0.4 mm is detected in a certain section, the model automatically loads the historical temperature and humidity data for that location over the past six months, correcting the risk prediction value through covariance analysis to avoid false alarms or missed warnings under extreme weather conditions. Through this method, quantified risk indicators are obtained. Then, by comparing different values ​​of the risk indicators with corresponding threshold information, a risk warning for cable sheath rupture can be issued based on the comparison results, and corresponding warning information can be output.

[0041] Optionally, refer to Figure 3 Based on monitoring data and image recognition results, early warning information for the target cable sheath is generated, including: S1301. Input the image recognition results and monitoring data into the preset risk assessment model, and output the corresponding rupture risk information; S1302. When the rupture risk information reaches the set conditions, generate early warning information including the location of the monitoring node, the risk level, and recommended treatment measures.

[0042] Based on this risk assessment model, the image recognition results (geometric parameters such as crack length, width, and distribution density) are first mapped to the Geographic Information System (GIS) coordinate system of the cable line via a three-dimensional coordinate transformation. Simultaneously, the monitoring data (time-series signals such as temperature, vibration, partial discharge, and strain) are time-aligned using phase synchronization technology. Then, feature fusion is performed on the image recognition results and monitoring data. This fusion can be achieved using a weighted average method, with the weights dynamically adjusted based on sensor confidence levels. Finally, the fused features yield the corresponding rupture risk information by querying the pre-built mapping relationship between rupture risk and the fused features.

[0043] Based on this rupture risk information, early warnings can be issued by comparing it with a pre-constructed multi-level risk rating system. Each level's threshold is learned by using a support vector machine (SVM) to classify the morphology-parameter joint distribution of historical failure cases. When the real-time risk value of the rupture risk information exceeds the current level's threshold, the system triggers an early warning generation process, thereby generating early warning information that includes the location of the monitoring node, the risk level, and recommended handling measures. For example, for high-risk crack defects, the system will generate the following warning: "[Risk Level - Severe] A longitudinal crack has been detected in cable segment #C-372 (116.3912°E, 39.9067°N, burial depth 1.2m), with a current width of 0.42mm (daily growth rate of 0.08mm) and an estimated remaining life of 72 hours (±12 hours). According to Clause 5.3.2 of DL / T1636-2016, it is recommended to immediately initiate the live-line repair process (priority P1) and deploy a temporary stress relief device (model SR-3000)." To enhance decision support capabilities, an interactive risk heat map can also be provided, which uses WebGL technology to render the three-dimensional stress field of the cable network, allowing maintenance personnel to zoom in and out to view the failure probability distribution and historical maintenance trajectory of any segment.

[0044] Optionally, after generating early warning information about the target cable sheath based on monitoring data and image recognition results, the system may also include: A location map is generated based on the location of the monitoring nodes in the early warning information, and the early warning location and the historical curve of the retrieved monitoring data are marked on the location map.

[0045] Building upon the aforementioned embodiments, this application further enhances the visualization of cable sheath rupture early warning. Specifically, based on the location coordinates of monitoring nodes (such as latitude and longitude or local coordinate systems) in the early warning information, standardized address resolution and spatial positioning are achieved through geocoding services. Furthermore, dynamic layer overlay technology is employed to generate a risk heat map layer on the base map (satellite imagery / road network / pipeline network). The risk level of each monitoring node is visualized through color gradient encoding (such as red-yellow-green three-color scale). Simultaneously, three-dimensional symbolization technology is used to map parameters such as crack width and damaged area into the height / radius of bar charts or pie charts, forming a three-dimensional perception of spatial distribution.

[0046] Furthermore, the marking of warning locations can utilize mixed reality technology, which blends augmented reality (AR) with 2D maps. In mobile terminal scenarios, the 3D model of the cable line is registered in the real environment. When maintenance personnel use tablet devices to scan the ground, they can intuitively see the virtual cable route, monitoring node locations, and risk markers floating above the actual physical space. For fixed terminals, the system provides a 3D earth visualization component, enabling smooth browsing of the global cable network based on WebGL technology. It supports multi-scale zooming (from the national power grid level to individual cable joints) and multi-view switching (bird's-eye view / section / first-person roaming). The risk information of each monitoring node is displayed in real time through information bubbles, and clicking on them allows users to access the historical monitoring data curves for that node.

[0047] The above-described process involves acquiring image data of the target cable sheath and determining the cable monitoring node information at the location of the target cable sheath; identifying the image data to obtain image recognition results; determining fixed-type monitoring data content in the cable monitoring node information based on the image recognition results; and generating early warning information for the target cable sheath based on the monitoring data content and the image recognition results. By employing the above techniques, combining the image recognition results of the target cable sheath with the corresponding type of monitoring data content for cable sheath rupture analysis and early warning, accurate and reliable early warning of sheath rupture risks can be achieved, providing multi-dimensional data support for operation and maintenance decisions and improving the reliability and stability of cable operation and maintenance.

[0048] Example 2: Based on the above embodiments, Figure 4 This is a schematic diagram of a cable sheath rupture early warning system provided in Embodiment 2 of this application. (Reference) Figure 4 The cable sheath rupture early warning system provided in this embodiment specifically includes: an acquisition module 21, an identification module 22, and an early warning module 23.

[0049] The acquisition module 21 is used to acquire image data captured by the corresponding target cable sheath and determine the cable monitoring node information at the location of the target cable sheath. The identification module 22 is used to identify the image data to obtain an image identification result, and to determine the fixed type of monitoring data content in the cable monitoring node information based on the image identification result; The early warning module 23 is used to generate early warning information for the target cable sheath based on the monitoring data content and image recognition results.

[0050] Specifically, the image recognition results obtained by identifying image data include: Image data is input into a pre-built cable sheath rupture feature extraction model, and the corresponding crack features are output as image recognition results. Crack features include the length, width and distribution density of cable sheath cracks.

[0051] Based on the image recognition results, the fixed type of monitoring data content is determined in the cable monitoring node information, including: Based on the different values ​​of the length, width, and distribution density of the cable sheath cracks in the image recognition results, the fixed type of monitoring data content is determined in the cable monitoring node information.

[0052] The image recognition results include at least one of the following: crack features, scratch features, and damaged area.

[0053] After obtaining image recognition results by recognizing image data, the process also includes: The frequency of cable monitoring node information collection is adjusted based on the image recognition results, and the collected cable monitoring node information is updated in real time.

[0054] Specifically, early warning information for the target cable sheath is generated based on monitoring data and image recognition results, including: Input the image recognition results and monitoring data into the preset risk assessment model, and output the corresponding rupture risk information; When the rupture risk information reaches the set conditions, an early warning message is generated, which includes the location of the monitoring node, the risk level, and recommended handling measures.

[0055] After generating early warning information about the target cable sheath based on monitoring data and image recognition results, the process also includes: A location map is generated based on the location of the monitoring nodes in the early warning information, and the early warning location and the historical curve of the retrieved monitoring data are marked on the location map.

[0056] The above-described process involves acquiring image data of the target cable sheath and determining the cable monitoring node information at the location of the target cable sheath; identifying the image data to obtain image recognition results; determining fixed-type monitoring data content in the cable monitoring node information based on the image recognition results; and generating early warning information for the target cable sheath based on the monitoring data content and the image recognition results. By employing the above techniques, combining the image recognition results of the target cable sheath with the corresponding type of monitoring data content for cable sheath rupture analysis and early warning, accurate and reliable early warning of sheath rupture risks can be achieved, providing multi-dimensional data support for operation and maintenance decisions and improving the reliability and stability of cable operation and maintenance.

[0057] The cable sheath rupture early warning system provided in Embodiment 2 of this application can be used to execute the cable sheath rupture early warning method provided in Embodiment 1 above, and has the corresponding functions and beneficial effects.

[0058] Example 3: This application provides an electronic device in embodiment three, referring to... Figure 5 The electronic device includes a processor 31, a memory 32, a communication module 33, an input device 34, and an output device 35. The electronic device may have one or more processors and one or more memories. The processor, memory, communication module, input device, and output device of the electronic device can be connected via a bus or other means.

[0059] Memory, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the cable sheath rupture early warning method described in any embodiment of this application (e.g., the acquisition module, identification module, and early warning module in a cable sheath rupture early warning system). Memory may primarily include a program storage area and a data storage area, wherein the program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on the use of the device, etc. Furthermore, memory may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0060] The communication module is used for data transmission.

[0061] The processor executes various functional applications and data processing of the device by running software programs, instructions, and modules stored in memory, thereby realizing the aforementioned cable sheath rupture early warning method.

[0062] Input devices can be used to receive input numerical or character information, and to generate key signal inputs related to user settings and function control of the device. Output devices may include display devices such as displays.

[0063] The electronic device provided above can be used to execute the cable sheath rupture early warning method provided in Embodiment 1 above, and has the corresponding functions and beneficial effects.

[0064] Example 4: This application embodiment also provides a storage medium containing computer-executable instructions. When executed by a computer processor, the computer-executable instructions are used to perform a cable sheath rupture early warning method. The cable sheath rupture early warning method includes: acquiring image data captured by a corresponding target cable sheath and determining cable monitoring node information at the location of the target cable sheath; recognizing the image data to obtain an image recognition result; determining fixed-type monitoring data content in the cable monitoring node information based on the image recognition result; and generating early warning information for the target cable sheath based on the monitoring data content and the image recognition result.

[0065] Storage medium – any type of memory device or storage device. The term “storage medium” is intended to include: mounting media, such as CD-ROM, floppy disk, or magnetic tape devices; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. Storage medium may also include other types of memory or combinations thereof. Furthermore, storage medium may reside in a first computer system in which the program is executed, or it may reside in a different second computer system connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term “storage medium” can include two or more storage media residing in different locations (e.g., in different computer systems connected via a network). Storage medium may store program instructions (e.g., specifically implemented as a computer program) executable by one or more processors.

[0066] Of course, the computer-executable instructions provided in the embodiments of this application are not limited to the cable sheath rupture early warning method described above, but can also perform related operations in the cable sheath rupture early warning method provided in any embodiment of this application.

[0067] The cable sheath rupture early warning system, storage medium, and electronic device provided in the above embodiments can execute the cable sheath rupture early warning method provided in any embodiment of this application. For technical details not described in detail in the above embodiments, please refer to the cable sheath rupture early warning method provided in any embodiment of this application.

[0068] The above description is merely a preferred embodiment and the technical principles employed in this application. This application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that can be made by those skilled in the art will not depart from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the claims.

Claims

1. A method for early warning of cable sheath rupture, characterized in that, include: Acquire image data of the corresponding target cable sheath and determine the cable monitoring node information at the location of the target cable sheath; The image data is identified to obtain an image recognition result, and the fixed type of monitoring data content is determined in the cable monitoring node information based on the image recognition result; Early warning information for the target cable sheath is generated based on the monitoring data and image recognition results.

2. The cable sheath rupture early warning method according to claim 1, characterized in that, The process of identifying the image data to obtain the image recognition result includes: The image data is input into a pre-constructed cable sheath rupture feature extraction model, and the corresponding crack features are output as the image recognition result. The crack features include the length, width and distribution density of the cable sheath cracks.

3. The cable sheath rupture early warning method according to claim 2, characterized in that, The step of determining the fixed type of monitoring data content in the cable monitoring node information based on the image recognition result includes: Based on the different values ​​of the length, width, and distribution density of the cable sheath cracks in the image recognition results, a fixed type of monitoring data content is determined in the cable monitoring node information.

4. The cable sheath rupture early warning method according to claim 1, characterized in that, The image recognition results include at least one of crack features, scratch features, and damaged area.

5. The cable sheath rupture early warning method according to claim 4, characterized in that, After obtaining the image recognition result by recognizing the image data, the process further includes: The frequency of collecting cable monitoring node information is adjusted based on the image recognition results, and the collected cable monitoring node information is updated in real time.

6. The cable sheath rupture early warning method according to any one of claims 1-5, characterized in that, The generation of early warning information for the target cable sheath based on the monitoring data content and image recognition results includes: The image recognition results and the monitoring data are input into a preset risk assessment model, which outputs the corresponding rupture risk information. When the rupture risk information reaches the set conditions, an early warning message is generated that includes the location of the monitoring node, the risk level, and recommended handling measures.

7. The cable sheath rupture early warning method according to claim 6, characterized in that, After generating the early warning information for the target cable sheath based on the monitoring data content and image recognition results, the method further includes: A location map is generated based on the monitoring node locations in the early warning information, and the early warning location and the retrieved historical curves of monitoring data are marked on the location map.

8. A cable sheath rupture early warning system, characterized in that, include: The acquisition module is used to acquire image data captured by the corresponding target cable sheath and determine the cable monitoring node information at the location of the target cable sheath; The identification module is used to identify the image data to obtain the image identification result, and to determine the fixed type of monitoring data content in the cable monitoring node information based on the image identification result; The early warning module is used to generate early warning information for the target cable sheath based on the monitoring data content and image recognition results.

9. An electronic device, characterized in that, include: Memory and one or more processors; The memory is used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the cable sheath rupture early warning method as described in any one of claims 1-7.

10. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the cable sheath rupture early warning method as described in any one of claims 1-7.

Images