Whole-process multi-defect identification early warning method, system and equipment for hidden engineering of transformer substation

Abstract

The invention is suitable for the technical field of transformer substation hidden project quality monitoring, and provides a transformer substation hidden project whole process multi-defect identification early warning method, system and equipment, and the method comprises the steps: obtaining multi-source monitoring data of a transformer substation hidden project whole construction process, carrying out the preprocessing, and forming a standardized data set; therefore, parallel identification and comprehensive analysis are carried out on multiple types of anomalies, a defect early warning report is finally generated and automatically pushed to a management platform, real-time monitoring and early warning of hidden engineering defects are realized, the defect of insufficient monitoring of hidden engineering in the prior art is effectively overcome, and the hidden engineering monitoring efficiency is improved. The maintenance cost and the safety risk caused by defect discovery lag are remarkably reduced, and the intelligent quality management level of substation engineering is improved.

Description

Technical Field

[0001] This application belongs to the field of quality monitoring technology for concealed works in substations, and in particular relates to a method, system and equipment for identifying and warning of multiple defects throughout the entire process of concealed works in substations. Background Technology

[0002] With the continuous expansion of power system scale and the improvement of its intelligence level, monitoring and quality control technologies for substation projects are receiving increasing attention. During substation construction, the quality of concealed works (such as cable laying and grounding grid installation) directly affects the long-term safe and stable operation of the power system. Because these works are permanently covered after construction, any quality defects are difficult to detect in a timely manner, easily leading to serious safety hazards.

[0003] Currently, substation engineering monitoring mainly relies on manual inspections or fixed-point sensor monitoring. While these methods can control the construction quality of visible parts to some extent, they are insufficient for real-time monitoring and early warning of various types of defects in concealed works throughout the entire process. In other words, existing technologies struggle to analyze and identify multiple hidden defects in concealed works in a timely manner, leading to delayed defect detection, high maintenance costs, and difficulty in eliminating potential quality hazards at their source. Summary of the Invention

[0004] In view of this, the embodiments of this application provide a method, system and equipment for identifying and warning of multiple defects in the entire process of concealed works in substations, which can solve the problem that the existing technology is unable to analyze and identify multiple hidden defects in concealed works in a timely manner.

[0005] In a first aspect, embodiments of this application provide a method for identifying and warning of multiple defects throughout the entire process of concealed works in substations, including: Acquire multi-source monitoring data for the entire construction process of concealed works in substations; Multi-source monitoring data are preprocessed to obtain a standardized monitoring dataset; Multi-type anomaly identification processing is performed on the standardized monitoring dataset to obtain the corresponding identification results; The identification results are integrated to generate a defect early warning report and push it to the construction management platform.

[0006] Secondly, embodiments of this application provide a multi-defect identification and early warning system for the entire process of concealed works in substations, including: The acquisition module is used to acquire multi-source monitoring data of the entire construction process of concealed works in substations; The preprocessing module is used to preprocess multi-source monitoring data to obtain a standardized monitoring dataset; The identification module is used to perform multi-type anomaly identification processing on the standardized monitoring dataset and obtain the corresponding identification results; The integration module is used to integrate the identification results, generate defect early warning reports, and push them to the construction management platform.

[0007] Thirdly, this application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the above-mentioned method for identifying and warning of multiple defects throughout the entire process of concealed works in substations.

[0008] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for identifying and warning of multiple defects throughout the entire process of concealed works in substations.

[0009] Fifthly, this application provides a computer program product that, when run on a terminal device, enables the terminal device to execute the aforementioned method for identifying and warning of multiple defects throughout the entire process of concealed works in substations.

[0010] The beneficial effects of this application embodiment compared with the prior art are as follows: This application embodiment obtains multi-source monitoring data of the entire construction process of concealed works in substations, forms a standardized dataset after preprocessing, and then performs parallel identification and comprehensive analysis of multiple types of anomalies, finally generating a defect early warning report and automatically pushing it to the management platform. This realizes real-time monitoring and early warning of defects in concealed works, effectively overcomes the shortcomings of the prior art in monitoring concealed works, significantly reduces maintenance costs and safety risks caused by the lag in defect discovery, and improves the level of intelligent quality management of substation projects. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic diagram illustrating the implementation process of the multi-defect identification and early warning method for the entire process of concealed works in substations provided in this application embodiment.

[0013] Figure 2 This is a schematic diagram of the structure of the substation concealed works full-process multi-defect identification and early warning system provided in the embodiments of this application.

[0014] Figure 3 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are protected by this application.

[0016] It should be noted that the terms "comprising," "including," and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application, are intended to cover non-exclusive inclusion. For example, a process, method, terminal, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices. Terms such as "first" and "second" in the claims, specification, and accompanying drawings of this application, as well as relational terms, are used merely to distinguish one entity / operation / object from another entity / operation / object, and do not necessarily require or imply any such immediate relationship or order between these entities / operations / objects.

[0017] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0018] With the continuous expansion of power system scale and the improvement of its intelligence level, monitoring and quality control technologies for substation projects are receiving increasing attention. During substation construction, the quality of concealed works (such as cable laying and grounding grid installation) directly affects the long-term safe and stable operation of the power system. Because these works are permanently covered after construction, any quality defects are difficult to detect in a timely manner, easily leading to serious safety hazards.

[0019] Currently, substation engineering monitoring mainly relies on manual inspections or fixed-point sensor monitoring. While these methods can control the construction quality of visible parts to some extent, they are insufficient for real-time monitoring and early warning of various types of defects in concealed works throughout the entire process. In other words, existing technologies struggle to analyze and identify multiple hidden defects in concealed works in a timely manner, leading to delayed defect detection, high maintenance costs, and difficulty in eliminating potential quality hazards at their source.

[0020] In view of this, this application provides a method for identifying and warning of multiple defects throughout the entire process of concealed works in substations. By acquiring multi-source monitoring data of the entire construction process of concealed works in substations, and forming a standardized dataset after preprocessing, multiple types of anomalies are identified and comprehensively analyzed in parallel. Finally, a defect warning report is generated and automatically pushed to the management platform, realizing real-time monitoring and warning of defects in concealed works. This effectively overcomes the shortcomings of existing technologies in monitoring concealed works, significantly reduces maintenance costs and safety risks caused by delayed defect discovery, and improves the level of intelligent quality management of substation projects.

[0021] To illustrate the technical solution of this application, specific embodiments are described below.

[0022] Figure 1 This illustration shows a flowchart of a method for identifying and warning of multiple defects throughout the entire process of concealed works in substations, as provided in an embodiment of this application. This method can be applied to terminal devices. Terminal devices can be servers, service clusters, mobile phones, tablets, laptops, ultra-mobile personal computers (UMPCs), netbooks, etc.

[0023] Specifically, the above-mentioned method for identifying and warning of multiple defects in the entire process of concealed works in substations may include the following steps S101 to S104.

[0024] Step S101: Obtain multi-source monitoring data of the entire construction process of the concealed works of the substation.

[0025] Among them, the concealed works of substations refer to the engineering parts that are covered or hidden after the construction of the substation is completed. They mainly include cable laying works (such as the laying and installation of cables) and grounding grid installation works (such as the welding and layout of the grounding system).

[0026] Multi-source monitoring data refers to monitoring data from multiple sources, which may include image data of cable laying site and grounding grid welding process (such as static images of cable insulation surface condition and grounding grid welding point details), video data (such as dynamic sequences of cable laying path and grounding grid welding process), as well as three-dimensional design model data imported from engineering design platform (including three-dimensional geometric information of cable laying path design and grounding grid layout design) and construction specification parameter data extracted from construction specification database (such as design values ​​of cable material specifications and grounding grid welding quality standards).

[0027] In the embodiments of this application, the terminal device can acquire image and video data through fixed image acquisition devices (such as high-definition cameras) and mobile image acquisition devices (such as inspection robots) deployed at the construction site of cable laying and grounding grid installation projects. The image data is used to capture static features of the surface condition of the cable insulation layer and the details of the grounding grid welding points, while the video data is used to record the dynamic sequence of the cable laying path and the grounding grid welding process. Simultaneously, three-dimensional design model data can be imported from an engineering design platform. This three-dimensional design model data includes three-dimensional geometric information of the cable laying path design and the grounding grid layout design. Construction specification parameter data, such as design values ​​for cable material specifications (conductor diameter, insulation layer thickness) and grounding grid welding quality standards (weld size, process parameters), can be extracted from the construction specification database, thereby obtaining multi-data covering the entire process of concealed works.

[0028] Step S102: Preprocess the multi-source monitoring data to obtain a standardized monitoring dataset.

[0029] In the embodiments of this application, the terminal device can first perform denoising processing (such as smoothing the image using a Gaussian filtering algorithm to suppress noise) and geometric correction processing (such as performing perspective transformation based on camera calibration parameters to eliminate lens distortion) on the image data to ensure consistent image quality. It can also perform keyframe extraction (such as extracting frames with significant changes through inter-frame difference calculation) and temporal synchronization processing (such as synchronizing video data with other sensor data through timestamp alignment and linear interpolation) on the video data, thereby reducing the amount of data and retaining key dynamic information. Furthermore, it can perform format conversion (such as converting CAD format to lightweight OBJ format) and lightweight processing (such as simplifying the number of mesh patches based on edge folding algorithms) on the 3D design model data, thereby improving processing efficiency and ultimately forming a standardized monitoring dataset, unifying all data in coordinates, time, and format.

[0030] Step S103: Perform multi-type anomaly identification processing on the standardized monitoring dataset to obtain the corresponding identification results.

[0031] In the embodiments of this application, the terminal device can achieve comprehensive detection by executing multiple anomaly recognition algorithms in parallel. For example, it can use image analysis techniques (such as edge detection and texture analysis) to identify cable material anomalies (such as surface damage or dimensional deviations), combine video temporal analysis and spatial matching techniques to identify grounding grid installation anomalies (such as welding point defects or positional deviations), and identify construction deviation anomalies (such as deviations between the actual path and the design path) through trajectory reconstruction and geometric deviation calculation. During the processing, the terminal device can extract key features (such as actual cable dimensions, welding point shapes, or spatial coordinates), compare them with standard parameters or design models, quantify anomaly information (such as deviation values ​​and positional coordinates), and determine the severity based on preset thresholds. Finally, it generates multiple sub-reports as recognition results to ensure coverage of hidden engineering defects.

[0032] Step S104: Integrate the identification results, generate a defect early warning report, and push it to the construction management platform.

[0033] Among them, the defect warning report refers to a structured report generated after integrating multiple identification results, which may include anomaly details, risk level and handling suggestions.

[0034] In the embodiments of this application, the terminal device can summarize multiple identification results (such as sub-reports of cable material anomalies, grounding grid installation anomalies, and construction deviation anomalies), integrate anomaly details, risk levels, and spatial location information through a structured format (such as JSON or XML), and generate a unified defect early warning report. After the report is generated, it is automatically pushed to the construction management platform, which can then provide real-time early warnings and decision support based on the report content, such as triggering rectification notices or allocating resources, thereby achieving timely defect handling and quality control.

[0035] The beneficial effects of this application embodiment compared with the prior art are as follows: This application embodiment obtains multi-source monitoring data of the entire construction process of concealed works in substations, forms a standardized dataset after preprocessing, and then performs parallel identification and comprehensive analysis of multiple types of anomalies, finally generating a defect early warning report and automatically pushing it to the management platform. This realizes real-time monitoring and early warning of defects in concealed works, effectively overcomes the shortcomings of the prior art in monitoring concealed works, significantly reduces maintenance costs and safety risks caused by the lag in defect discovery, and improves the level of intelligent quality management of substation projects.

[0036] In some specific embodiments of this application, the step of performing multi-type anomaly identification processing on the standardized monitoring dataset to obtain the corresponding identification results may specifically include steps S401 to S403.

[0037] Step S401: Perform cable material anomaly identification processing on the standardized monitoring dataset to obtain the first identification result.

[0038] In some specific embodiments of this application, the step of performing cable material anomaly identification processing on the standardized monitoring dataset to obtain a first identification result may specifically include steps S501 to S505.

[0039] Step S501: Retrieve the surface condition image data of the cable insulation layer corresponding to the cable laying project and the design value of the cable material specifications from the construction specification parameter data from the standardized monitoring dataset.

[0040] Among them, cable insulation layer surface condition image data refers to static images of the cable insulation layer surface collected by high-definition industrial cameras or mobile inspection equipment deployed at the cable laying project site, which are used to visually inspect whether the insulation layer has surface defects such as scratches, damage, and contamination.

[0041] The cable material specification design value in the construction specification parameter data refers to the standard parameters of cable materials extracted from the construction specification database. These parameters may include the design diameter of the cable conductor, the design thickness of the insulation layer, and the standard requirements for the insulation material. They are used to determine whether the actual material meets the specifications.

[0042] In the embodiments of this application, the terminal device can retrieve specific data related to the cable laying project from the preprocessed standardized monitoring dataset. The cable insulation surface condition image data is captured by fixed high-definition cameras or mobile acquisition devices (such as inspection robots) deployed on-site, providing high-resolution static images to capture details of the insulation surface. Simultaneously, cable material specification design values, including standard parameters such as conductor diameter and insulation thickness, can be retrieved from the construction specification database; these data can serve as comparison benchmarks.

[0043] Step S502: Feature extraction is performed on the surface condition image data of the cable insulation layer. Surface damage features are identified through edge detection and texture analysis, and the actual conductor diameter and insulation layer thickness data of the cable are extracted.

[0044] Among them, the actual conductor diameter and insulation layer thickness data of the cable refer to the physical dimension data extracted from the surface condition image of the cable insulation layer, including the actual conductor diameter and the actual insulation layer thickness.

[0045] In the embodiments of this application, the terminal device can first perform grayscale conversion and filtering preprocessing on the image data, and then apply an edge detection algorithm (such as the Sobel operator) to calculate the image gradient, highlighting cable edges and irregular surface areas, thereby identifying damage features such as cracks or scratches. It can also use texture analysis techniques (such as grayscale co-occurrence matrix) to calculate features such as contrast and energy, quantifying surface texture anomalies to distinguish damaged areas. Then, based on the edge detection results, pixel calibration and actual size conversion (using a reference calibration object such as a scale bar) can be used to extract the actual conductor diameter and insulation layer thickness data of the cable.

[0046] Step S503: Compare the actual conductor diameter and insulation layer thickness data of the cable with the design value of the cable material specifications to obtain the first comparison result.

[0047] In the embodiments of this application, the terminal device can perform a numerical subtraction operation between the actual size data (conductor diameter and insulation layer thickness) and the specified design value to calculate the absolute deviation or relative deviation percentage. Then, based on a preset tolerance threshold (such as ±5% of the design value), it determines whether the deviation exceeds the limit, thereby generating a first comparison result. The first comparison result may include the deviation value, the exceeding state, and a description of specific parameters.

[0048] Step S504: Based on the surface damage characteristics and the comparison results, the cable material anomalies are quantitatively labeled, and the first anomaly data of the anomaly location is recorded. The first anomaly data includes three-dimensional coordinates, damage area and deviation value.

[0049] In the embodiments of this application, the terminal device can integrate surface damage features (such as damage areas marked by a binary image) and the first comparison result (specification deviation data), and convert anomaly points from two-dimensional images into three-dimensional coordinates through the mapping relationship between image coordinates and spatial coordinates (based on camera calibration parameters and depth information). Simultaneously, the pixel area of ​​the damage area is calculated and converted into an actual area (such as square millimeters), and the deviation value is recorded. Finally, structured first anomaly data is generated, which may include the three-dimensional coordinates, damage area, deviation type, and value of each anomaly point, thereby achieving precise location and quantitative description of the anomaly.

[0050] Step S505: Generate the first identification result based on the first abnormal data.

[0051] In the embodiments of this application, the terminal device can integrate the first abnormal data into a cable material abnormality identification sub-report, i.e., the first identification result, according to a preset template. The report content may include an abnormality list (location, type, area, and deviation of each abnormality), severity level (based on deviation value and damage area classification), and handling suggestions (such as replacement or repair), and is output in JSON or XML format, which facilitates subsequent integration with other identification results and push to the management platform.

[0052] This application's implementation refines the entire process of cable material anomaly identification, from data retrieval, feature extraction, specification comparison to quantitative labeling and report generation, achieving automated detection of cable material defects and avoiding the subjectivity and lag of manual inspection. Simultaneously, by integrating image analysis and specification comparison, it improves the comprehensiveness and reliability of identification, providing data support for timely early warning and rectification, thereby effectively reducing the risks of hidden engineering work caused by material defects.

[0053] Step S402: Perform grounding grid installation anomaly identification processing on the standardized monitoring dataset to obtain a second identification result.

[0054] In some specific embodiments of this application, step 'a' may specifically include steps S601 to S606.

[0055] Step S601: Retrieve detailed image data of grounding grid welding points, video data of welding process, design value of grounding grid welding quality standard from construction specification parameter data, and three-dimensional geometric information of grounding grid layout design from the three-dimensional design model data corresponding to the grounding grid installation project from the standardized monitoring dataset.

[0056] Among them, the detailed image data of the grounding grid welding point refers to the static images after welding collected by high-definition industrial cameras deployed near the welding point of the grounding grid. These images are used to check the weld formation quality, including surface defects such as porosity, slag inclusion, undercut, and cracks.

[0057] Welding process video data refers to a dynamic video sequence that records the entire welding process of the grounding grid, including key operation stages such as arc initiation, welding, and arc termination, and is used to analyze the compliance of the execution of welding process parameters.

[0058] The design value of the welding quality standard for grounding grids refers to the welding process standard parameters extracted from the construction specification database, including the qualified welding current, voltage, speed range, as well as quality standards such as weld size and allowable defect range.

[0059] The three-dimensional geometric information of the grounding grid layout design refers to the grounding grid design data extracted from the three-dimensional design model, including the design coordinates of the grounding electrodes, burial depth, direction and spacing of the horizontal connection strips, and other three-dimensional geometric parameters.

[0060] In the embodiments of this application, the terminal device can retrieve multi-source data related to the grounding grid installation project from the pre-processed standardized monitoring dataset. Detailed image data of the welding points can be acquired by high-definition industrial cameras deployed near the welding points, providing high-resolution static images of the weld after formation. Video data of the welding process records the entire dynamic sequence of the welding operation. The grounding grid welding quality standard design values ​​can be extracted from the construction specification database, including standard values ​​such as weld dimensions and welding process parameters. The three-dimensional geometric information of the grounding grid layout design can be extracted from the three-dimensional design model, including design parameters such as grounding polar coordinates and the direction of the connecting strip.

[0061] Step S602: Feature extraction is performed on the detailed image data of the grounding grid welding point to obtain the extraction result.

[0062] In the embodiments of this application, the terminal device can first perform contrast enhancement and sharpening processing on the welding point image, and then use a deep learning object detection model (such as the YOLO series) or a traditional image segmentation algorithm (such as the watershed algorithm) to perform pixel-level localization and classification of welding point defects, identify typical defects such as porosity, sand holes, undercut, weld beads, and cracks, and quantify the identified defects, calculate the defect area, length, diameter and other size parameters, and finally generate an extraction result containing defect type, location and size information.

[0063] Step S603: Perform time-series frame decomposition and process analysis on the welding process video data to obtain the first analysis result.

[0064] In the embodiments of this application, the terminal device can extract key operation frames (such as arc initiation, welding, and arc termination stages) from the welding process video using the inter-frame difference method or the motion saliency-based method. Then, it can calculate the actual welding speed by tracking the movement trajectory of the welding torch or welding sparks, analyze process parameters such as welding torch angle and welding temperature, and compare them with the design value of the grounding grid welding quality standard to determine whether the welding operation process meets the specification requirements. Finally, it generates a first analysis result containing the process parameter compliance judgment.

[0065] Step S604: Spatial matching and comparison are performed between the spatial coordinate data of the actual installation location of the grounding grid and the three-dimensional geometric information of the grounding grid layout design to obtain the second comparison result.

[0066] Among them, the spatial coordinate data of the actual installation location of the grounding grid refers to the three-dimensional coordinates of the actual installation location of the grounding grid components collected on-site by total station, GPS-RTK equipment or visual SLAM technology.

[0067] In the embodiments of this application, the terminal device can first unify the spatial coordinate data of the actual installation location of the grounding grid collected on site with the three-dimensional design model into the same coordinate system, and then use the point cloud registration algorithm to spatially match the actual installation location model with the design model, calculate the Euclidean distance deviation between the actual coordinates and the design coordinates of each grounding electrode, as well as the offset between the actual direction of the horizontal connecting strip and the design path, and finally generate a second comparison result containing quantitative data of position deviation.

[0068] Step S605: Based on the extraction results, the first analysis results, and the second comparison results, the identified grounding grid installation anomalies are quantitatively labeled, and the second anomaly data of the anomaly location is recorded. The second anomaly data includes three-dimensional coordinates, defect type, defect size, and process non-compliance items.

[0069] In the embodiments of this application, the terminal device can integrate the image feature extraction results, video process analysis results, and spatial position comparison results to uniformly quantify and label the identified grounding grid installation anomalies. Through coordinate transformation, the abnormal positions in the two-dimensional image are mapped to three-dimensional spatial coordinates, and the three-dimensional coordinates, defect type (such as porosity, cracks, position offset, etc.), defect size (area, length, etc.), and specific process non-compliance items (such as welding speed exceeding the standard, current non-compliance, etc.) of each abnormal point are recorded to form a structured second abnormal dataset.

[0070] Step S606: Generate the second identification result based on the second abnormal data.

[0071] In the embodiments of this application, the terminal device can classify the severity of the second abnormal data according to a preset grounding grid installation abnormality level threshold, and generate a grounding grid installation abnormality identification sub-report as the second identification result. The report contains an abnormality detail list, risk level assessment, visual annotation information and processing suggestions in a structured format (such as JSON), thereby providing data support for construction quality rectification.

[0072] This application's implementation method refines the specific process for identifying and handling grounding grid installation anomalies, enabling multi-dimensional detection of welding point defects, welding process compliance, and installation location accuracy. Through multi-source data fusion analysis and automated processing, it significantly improves the comprehensiveness and accuracy of grounding grid installation quality inspection.

[0073] Step S403: Perform construction deviation anomaly identification processing on the standardized monitoring dataset to obtain a third identification result.

[0074] In some specific embodiments of this application, the step of performing construction deviation anomaly identification processing on the standardized monitoring dataset to obtain a third identification result may specifically include steps S701 to S706.

[0075] Step S701: Retrieve actual spatial monitoring data, three-dimensional design model data, and construction design threshold parameters from the standard monitoring dataset, covering the entire construction process of cable laying and grounding grid installation.

[0076] Among them, actual spatial monitoring data refers to the actual spatial information collected by on-site monitoring equipment (such as total station, GPS-RTK or visual SLAM technology) during the construction process of cable laying and grounding grid installation projects. This includes the actual laying trajectory coordinates extracted from video data of cable laying paths and the actual installation position coordinates extracted from image data of grounding grid installation process, which are used to reflect the actual spatial status of construction.

[0077] Three-dimensional design model data refers to digital models imported from engineering design platforms, which include three-dimensional coordinate information of cable laying design paths and three-dimensional geometric parameters of grounding grid installation design locations, serving as benchmark design information for construction comparison.

[0078] Construction design threshold parameters refer to the allowable deviation range standards extracted from the construction specification database, including design thresholds such as the allowable range of cable laying path deviation and the limit value of grounding grid installation position offset, which are used to determine whether the construction complies with the specifications.

[0079] In the embodiments of this application, the terminal device can retrieve specific data required for construction deviation identification from a preprocessed standardized monitoring dataset. The actual spatial monitoring data can be acquired in real time using positioning devices (such as GPS-RTK) and visual acquisition systems (such as inspection robots) deployed at the construction site, including the trajectory coordinate sequence of the cable laying path and the spatial coordinates of the grounding grid installation points. Three-dimensional design model data can be imported from an engineering design platform, providing the three-dimensional coordinates of the cable laying design path and the three-dimensional geometric parameters of the grounding grid installation design location. Construction design threshold parameters can be extracted from a construction specification database, including the allowable range of path deviation (e.g., horizontal deviation ±10cm) and the position offset limit (e.g., vertical deviation ±5cm).

[0080] Step S702: Perform coordinate calibration and trajectory reconstruction processing on the actual spatial monitoring data to generate an actual cable laying path model and an actual grounding grid installation location model.

[0081] Among them, the actual cable laying path model and the actual grounding grid installation location model refer to the three-dimensional digital representations generated after coordinate calibration and trajectory reconstruction, which respectively reflect the actual route of cable laying and the actual installation location of grounding grid components, and are used for comparison with the design model.

[0082] In the embodiments of this application, the terminal device can first use a coordinate calibration algorithm (such as least squares fitting) to unify the actual spatial monitoring data to the same coordinate system as the three-dimensional design model, eliminating coordinate errors caused by differences in measuring equipment. Then, based on the time series and spatial point data, a trajectory reconstruction algorithm (such as B-spline curve fitting) is used to generate a continuous actual cable laying path model and a discrete actual grounding grid installation location model. These models represent the actual construction state in the form of a three-dimensional point cloud or a mesh.

[0083] Step S703: Spatially overlay and compare the actual cable laying path model and the actual grounding grid installation location model with the cable laying design path model and the grounding grid installation design location model in the three-dimensional design model data. Quantitatively analyze the spatial deviation value between the actual construction and the design through geometric deviation calculation to obtain the second analysis result.

[0084] In the embodiments of this application, the terminal device can accurately overlay the actual path model and actual location model with the corresponding design model using a spatial registration algorithm (such as the iterative nearest point algorithm) to ensure alignment of key points between the models. Then, through geometric deviation calculation, the Euclidean distance between the actual point and the design point is calculated point by point to obtain the deviation value of the cable laying path and the positional offset of the grounding grid installation location, and the overall deviation distribution (such as maximum deviation and average deviation) is statistically analyzed. Finally, a second analysis result is generated, including the spatial deviation value of each detection point, the deviation type (such as horizontal or vertical offset), and the deviation area distribution map, thereby quantifying the spatial consistency between construction and design.

[0085] Step S704: Extract the actual operation parameters during the construction process and compare them with the construction design threshold parameters to obtain the third comparison result.

[0086] Among them, actual operation parameters refer to specific operation indicators extracted from the construction process, such as real-time recorded data on cable laying speed and grounding grid welding sequence.

[0087] In the embodiments of this application, the terminal device can extract actual operating parameters from the construction record system or sensor data, such as real-time parameters like cable laying speed and grounding grid welding time interval. These parameters are then compared numerically with construction design threshold parameters (such as the design-allowed laying speed range and welding process time requirements), calculating the difference or ratio between the actual value and the design value to determine whether the threshold range is exceeded. Finally, a third comparison result is generated, including parameter deviation values, descriptions of the exceeding condition, and the specific affected processes.

[0088] Step S705: Based on the second analysis result and the third comparison result, the identified construction deviation anomalies are quantitatively labeled, and the third anomaly data of the deviation location is recorded. The third anomaly data includes three-dimensional coordinates, deviation type, specific deviation value and corresponding design standard value.

[0089] In the embodiments of this application, the terminal device can integrate the spatial deviation value in the second analysis result and the parameter exceedance information in the third comparison result, and record each deviation anomaly through an automated annotation algorithm. First, the spatial deviation points are mapped to a three-dimensional coordinate system, and the precise three-dimensional coordinates of the anomaly points are recorded. Then, the deviation type is classified according to the deviation characteristics (such as path offset, elevation error, or process exceedance). At the same time, the specific deviation value (such as an offset distance of 5cm) and the corresponding design standard value (such as the design allowable value of 3cm) are recorded, and finally, structured third anomaly data is generated, which includes a detailed list and spatial distribution information of all deviation anomalies, thereby achieving accurate location and source tracing of anomalies.

[0090] Step S706: Generate the third identification result based on the third abnormal data.

[0091] In the embodiments of this application, the terminal device can automatically evaluate the third abnormal data according to a preset construction deviation severity grading standard (such as risk level classification based on deviation value), and generate a construction deviation anomaly identification sub-report as the third identification result. This report can integrate all deviation anomaly information in JSON or XML format, including the three-dimensional coordinates of the abnormal location, deviation type, deviation value, risk level (such as high risk, medium risk), and rectification suggestions, and supports visual annotation on the three-dimensional design model, thereby providing decision support for construction adjustments.

[0092] The implementation method of this application refines the complete process of construction deviation anomaly identification and processing, from multi-source data retrieval, coordinate calibration and model reconstruction, spatial deviation quantitative analysis to parameter compliance comparison, and realizes accurate detection and quantitative evaluation of construction path and location deviations. This effectively avoids the omission of hidden project deviations due to insufficient manual inspection and improves the automation level and accuracy of construction quality control.

[0093] In some specific embodiments of this application, after integrating the identification results, generating a defect early warning report and pushing it to the construction management platform, the above method may further include steps S801 to S804.

[0094] Step S801: Establish a real-time data update channel based on the standardized monitoring dataset to continuously receive new monitoring data generated during the construction of cable laying projects and grounding grid installation projects. The new monitoring data includes image data, video data, and environmental parameter data collected by on-site sensors.

[0095] The newly added monitoring data refers to the monitoring data collected in real time during the construction process, which may include image data (such as newly captured images of the cable insulation layer surface), video data (such as real-time video streams of the grounding grid welding process), and environmental parameter data collected by on-site sensors (such as temperature, humidity, and vibration sensor readings).

[0096] In the embodiments of this application, the terminal device can establish a persistent connection with the on-site monitoring equipment (such as high-definition cameras, video surveillance systems and IoT sensors) by configuring a real-time data interface (such as a RESTful API or message middleware), forming a real-time data update channel, continuously collecting new image data (such as static pictures of cable laying progress), video data (such as real-time video streams of grounding grid welding operations) and environmental parameter data (such as values ​​collected by temperature and humidity sensors) during the construction process, and transmitting these data to the processing system in real time to ensure that monitoring covers the entire construction process.

[0097] Step S802: Call the historical hidden engineering defect database, perform feature matching between the historical defect data and the similar engineering data in the standardized monitoring dataset, and construct a dynamic anomaly threshold model.

[0098] Among them, the historical hidden engineering defect database refers to a structured database that stores defect records in historical engineering projects. It can include data such as defect type (e.g., cable damage, welding defects), occurrence conditions (e.g., environmental parameters, construction stage), and solutions.

[0099] The dynamic anomaly threshold model is an adaptive threshold generation model whose threshold parameters (such as size deviation threshold and process parameter threshold) can be dynamically adjusted according to historical defect characteristics, current construction progress and environmental changes to improve early warning adaptability.

[0100] In the embodiments of this application, the terminal device can retrieve project data similar to the current project from the historical hidden engineering defect database, extract historical defect features (such as defect type, environmental conditions, and construction stage), and perform similarity analysis with engineering features (such as cable type, grounding grid material, and environmental parameters) in the current standardized monitoring dataset through feature matching algorithms (such as K-nearest neighbor algorithm or Euclidean distance calculation). Based on the matching results, the abnormal threshold parameters are dynamically adjusted (such as adjusting the size deviation threshold from ±5% of the design value to ±3% to adapt to a specific environment), thereby constructing a dynamic abnormal threshold model that can adapt to construction progress and environmental changes, and improving the accuracy of threshold setting.

[0101] Step S803: Input the newly added monitoring data into the dynamic anomaly threshold model and compare it with the adjusted threshold parameters in real time. If it exceeds the threshold range, trigger an immediate warning and temporarily store the warning information in a temporary database.

[0102] In the embodiments of this application, the terminal device can input the newly received monitoring data (such as cable surface features in image data or welding action sequences in video data) into the dynamic anomaly threshold model, and compare it with the current threshold parameters of the model (such as insulation layer thickness deviation threshold or welding speed allowable range) in real time. When the data exceeds the threshold, an early warning is triggered immediately, generating early warning information containing the location, type and deviation value of the anomaly point, and temporarily storing it in a temporary database (such as Redis cache).

[0103] Step S804: Based on the identification results, perform secondary verification on the warning information in the temporary database, remove false alarm information, update it to the defect warning report, obtain the first updated defect warning report, and simultaneously push the first updated defect warning report to the construction management platform.

[0104] In the embodiments of this application, the terminal device can cross-validate the early warning information in the temporary database with the identification results generated by the main identification process (such as the abnormal details in the cable material abnormal identification sub-report), and eliminate false alarm information (such as false positive alarms caused by light interference) through a rule engine (such as filtering based on logical rules) or confidence calculation (such as setting a confidence threshold higher than 80% to be valid). Then, the real abnormal information is integrated into the defect early warning report to generate a structured first updated defect early warning report, and automatically synchronized to the construction management platform through a network interface (such as HTTP push) to achieve accurate early warning feedback.

[0105] The implementation method of this application achieves beneficial effects by establishing a real-time data update channel and a dynamic anomaly threshold model, realizing real-time monitoring and early warning of newly added data in the construction process. Furthermore, the accuracy of early warning is improved through a secondary verification mechanism, effectively reducing the rate of missed and false alarms, and enhancing the real-time performance and reliability of quality control of concealed works.

[0106] In some specific embodiments of this application, after integrating the identification results, generating a defect early warning report and pushing it to the construction management platform, the above method may further include steps S901 to S904.

[0107] Step S901: Simultaneously collect operation record data of construction personnel and operating parameter data of construction equipment.

[0108] Among them, the construction personnel operation record data refers to the data that records the on-site operation behavior of construction personnel, which may include operation time (such as the duration of welding operation), process connection time (such as the interval between each process step), operation sequence, etc.

[0109] Construction equipment operating parameter data refers to the real-time parameters of construction equipment during operation, such as equipment power (e.g., output power of a welding machine), operational accuracy (e.g., positioning error of a robotic arm), operating speed, temperature, etc.

[0110] In the embodiments of this application, after generating a defect warning report, the terminal device can collect the operation record data of construction personnel in real time from the construction management system through a data interface (such as API call), including operation time (such as process timestamps read from RFID tags) and process connection time (such as calculation of intervals between steps). At the same time, it can collect the operating parameter data of construction equipment from the equipment monitoring platform (such as SCADA system), such as equipment power (obtained through current sensors) and operation accuracy (read through encoders), and clean and format the data to ensure that the timestamps are synchronized with the identification results.

[0111] Step S902: Perform correlation analysis on the operation record data of the construction personnel and the operating parameter data of the construction equipment with the identification results to obtain the correlation analysis results.

[0112] In the embodiments of this application, the terminal device can time-align the collected operation record data (such as operation duration sequence) and equipment parameter data (such as power fluctuation value) with the abnormal details (such as defect occurrence time and location) in the identification results, and then apply the correlation analysis algorithm (such as Pearson correlation coefficient calculation or decision tree classification) to analyze the statistical relationship between operation parameters (such as process connection time) and defect types (such as weld porosity), calculate the correlation coefficient and influence weight, and generate the correlation analysis results, including a list of key factors (such as equipment power deviation being positively correlated with defect rate) and correlation quantification indicators, in order to identify the potential driving factors of defects.

[0113] Step S903: Based on the correlation analysis results, locate the root cause type of the hidden engineering defects and generate a root cause analysis report.

[0114] Among them, the root cause type refers to the category of the fundamental cause that leads to defects in concealed works, which can include pre-defined categories such as non-standard personnel operation (such as incorrect process execution), substandard equipment precision (such as equipment calibration deviation), and unqualified material batches (such as cable material problems).

[0115] In the embodiments of this application, the terminal device can locate the root cause type based on the correlation coefficient in the correlation analysis results (e.g., a coefficient exceeding 0.7 is considered significant) through preset root cause mapping rules (e.g., mapping "abnormal operation time" to "non-standard personnel operation"). Then, it can extract evidence templates from the knowledge base and generate a root cause analysis report. The report content may include root cause type classification, related data source (e.g., specific device serial number), correlation coefficient (e.g., 0.85), and root cause description (e.g., "unstable welding current leads to poor welding").

[0116] Step S904: Integrate the root cause analysis report with the defect warning report, and supplement the solutions corresponding to different root cause types to obtain a second updated defect warning report, and simultaneously push the second updated defect warning report to the construction management platform and the terminals of relevant responsible personnel.

[0117] In the embodiments of this application, the terminal device can add the content of the root cause analysis report (such as root cause type and correlation) to the defect warning report through the report integration engine to form a new chapter. Then, it retrieves preset solutions from the solution knowledge base according to the root cause type (such as recommending training courses for "non-standard personnel operation" and suggesting calibration checks for "inadequate equipment accuracy") to generate a second updated defect warning report. Finally, the report is sent in real time to the construction management platform (such as a web dashboard) and the terminals of relevant responsible personnel (such as mobile phone text messages) through a message push system (such as an email gateway or mobile APP interface), ensuring that the warning information reaches the execution level directly.

[0118] The implementation method of this application adds a root cause analysis step after defect warning, which associates personnel operation and equipment parameters with defect results, and realizes the extension from defect detection to root cause tracing. This helps to accurately locate the source of the problem and provide targeted solutions, thereby improving rectification efficiency and reducing the recurrence rate of defects.

[0119] Figure 2 This illustration shows a structural diagram of a multi-defect identification and early warning system for concealed works in a substation, provided in an embodiment of this application. The aforementioned multi-defect identification and early warning system 2 for concealed works in a substation can be configured on a terminal device. Specifically, the aforementioned multi-defect identification and early warning system 2 for concealed works in a substation includes: Module 201 is used to acquire multi-source monitoring data of the entire construction process of concealed works in substations; Preprocessing module 202 is used to preprocess the multi-source monitoring data to obtain a standardized monitoring dataset; The identification module 203 is used to perform multi-type anomaly identification processing on the standardized monitoring dataset to obtain the corresponding identification results; The integration module 204 is used to integrate the identification results, generate a defect early warning report, and push it to the construction management platform.

[0120] The beneficial effects of this application embodiment compared with the prior art are as follows: This application embodiment obtains multi-source monitoring data of the entire construction process of concealed works in substations, forms a standardized dataset after preprocessing, and then performs parallel identification and comprehensive analysis of multiple types of anomalies, finally generating a defect early warning report and automatically pushing it to the management platform. This realizes real-time monitoring and early warning of defects in concealed works, effectively overcomes the shortcomings of the prior art in monitoring concealed works, significantly reduces maintenance costs and safety risks caused by the lag in defect discovery, and improves the level of intelligent quality management of substation projects.

[0121] In some embodiments of this application, the identification module 203 is further used for: The standardized monitoring dataset is processed for cable material anomaly identification to obtain a first identification result; The standardized monitoring dataset is subjected to grounding grid installation anomaly identification processing to obtain a second identification result; The standardized monitoring dataset is subjected to construction deviation anomaly identification processing to obtain a third identification result.

[0122] In some embodiments of this application, the identification module 203 is further used for: The standardized monitoring dataset retrieves the surface condition image data of the cable insulation layer corresponding to the cable laying project, as well as the cable material specification design value from the construction specification parameter data; Feature extraction is performed on the surface condition image data of the cable insulation layer. Surface damage features are identified through edge detection and texture analysis. The actual conductor diameter and insulation layer thickness data of the cable are also extracted. The difference between the actual conductor diameter and insulation layer thickness of the cable and the design value of the cable material specifications is compared to obtain the first comparison result. Based on the surface damage characteristics and the comparison results, the cable material anomalies are quantitatively labeled, and the first anomaly data of the anomaly location is recorded. The first anomaly data includes three-dimensional coordinates, damage area and deviation value. The first identification result is generated based on the first abnormal data.

[0123] In some embodiments of this application, the identification module 203 is further used for: The system retrieves detailed image data of the welding points of the grounding grid, video data of the welding process, design values ​​of the grounding grid welding quality standard from the construction specification parameter data, and three-dimensional geometric information of the grounding grid layout design from the three-dimensional design model data corresponding to the grounding grid installation project from the standardized monitoring dataset. Feature extraction is performed on the detailed image data of the grounding grid welding points to obtain the extraction results; The welding process video data is subjected to time-series frame decomposition and process analysis to obtain the first analysis result; The spatial coordinate data of the actual installation location of the grounding grid are spatially matched and compared with the three-dimensional geometric information of the grounding grid layout design to obtain a second comparison result. Based on the extraction results, the first analysis results, and the second comparison results, the identified grounding grid installation anomalies are quantitatively labeled, and the second anomaly data of the anomaly location is recorded. The second anomaly data includes three-dimensional coordinates, defect type, defect size, and process non-compliance items. The second identification result is generated based on the second abnormal data.

[0124] In some embodiments of this application, the identification module 203 is further used for: The system retrieves actual spatial monitoring data, three-dimensional design model data, and construction design threshold parameters from the construction specification parameter data of the entire construction process of cable laying and grounding grid installation projects from the standardized monitoring dataset. The actual spatial monitoring data is subjected to coordinate calibration and trajectory reconstruction to generate an actual cable laying path model and an actual grounding grid installation location model. The actual cable laying path model and the actual grounding grid installation location model are spatially superimposed and compared with the cable laying design path model and the grounding grid installation design location model in the three-dimensional design model data. The spatial deviation value between the actual construction and the design is quantitatively analyzed by geometric deviation calculation to obtain the second analysis result. Extract the actual operational parameters during the construction process and compare them with the construction design threshold parameters to obtain a third comparison result. Based on the second analysis result and the third comparison result, the identified construction deviation anomalies are quantitatively labeled, and the third anomaly data of the deviation location is recorded. The third anomaly data includes three-dimensional coordinates, deviation type, specific deviation value and corresponding design standard value. The third identification result is generated based on the third abnormal data.

[0125] In some embodiments of this application, the substation concealed works full-process multi-defect identification and early warning system 2 further includes a first update module, used for: A real-time data update channel is established based on the standardized monitoring dataset to continuously receive new monitoring data generated during the construction of cable laying projects and grounding grid installation projects. The new monitoring data includes image data, video data, and environmental parameter data collected by on-site sensors. The historical hidden engineering defect database is invoked, and the historical defect data is matched with the similar engineering data in the standardized monitoring dataset to construct a dynamic anomaly threshold model. The newly added monitoring data is input into the dynamic anomaly threshold model and compared in real time with the adjusted threshold parameters. If the data exceeds the threshold range, an immediate warning is triggered and the warning information is temporarily stored in a temporary database. Based on the identification results, the warning information in the temporary database is verified a second time. After removing false alarms, the information is updated to the defect warning report to obtain the first updated defect warning report. The first updated defect warning report is then pushed to the construction management platform simultaneously.

[0126] In some embodiments of this application, the substation concealed works full-process multi-defect identification and early warning system 2 further includes a second update module, used for: Simultaneously collect data from construction personnel's operation records and construction equipment's operating parameters; The operation record data of the construction personnel and the operating parameter data of the construction equipment are correlated with the identification results to obtain the correlation analysis results; Based on the correlation analysis results, the root cause type leading to the defects in the concealed works is identified, and a root cause analysis report is generated. The root cause analysis report and the defect warning report are integrated, and solutions corresponding to different root cause types are added to obtain a second updated defect warning report. The second updated defect warning report is then pushed to the construction management platform and the terminals of relevant responsible personnel.

[0127] like Figure 3 The diagram shown is a schematic of a terminal device provided in an embodiment of this application. The terminal device 3 may include: a processor 301, a memory 302, and a computer program 303 stored in the memory 302 and executable on the processor 301, such as a multi-defect identification and early warning program for the entire process of concealed works in substations. When the processor 301 executes the computer program 303, it implements the steps in the aforementioned embodiments of multi-defect identification and early warning for the entire process of concealed works in substations, for example... Figure 1 Steps S101 to S104 are shown.

[0128] A computer program can be divided into one or more modules / units. One or more modules / units are stored in memory 302 and executed by processor 301 to complete this application. One or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in a terminal device.

[0129] The terminal device may include, but is not limited to, processor 301 and memory 302. Those skilled in the art will understand that... Figure 3This is merely an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, a terminal device may also include input / output devices, network access devices, buses, etc.

[0130] The processor 301 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0131] The memory 302 can be an internal storage unit of the terminal device, such as the hard drive or RAM of the terminal device. The memory 302 can also be an external storage device of the terminal device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 302 can include both internal and external storage units of the terminal device. The memory 302 is used to store computer programs and other programs and data required by the terminal device. The memory 302 can also be used to temporarily store data that has been output or will be output.

[0132] It should be noted that, for the sake of convenience and brevity, the structure of the terminal device described above can also be referred to the specific description of the structure in the method embodiment, which will not be repeated here.

[0133] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0134] This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it can implement the steps in the above-mentioned method for identifying and warning of multiple defects in the entire process of concealed works in substations.

[0135] This application provides a computer program product that, when run on a mobile terminal, enables the mobile terminal to implement the steps in the above-mentioned method for identifying and warning of multiple defects throughout the entire process of concealed works in substations.

[0136] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0137] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for various specific applications, but such implementations should not be considered beyond the scope of this application.

[0138] In the embodiments provided in this application, it should be understood that the disclosed systems / terminal devices and methods can be implemented in other ways. For example, the system / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of systems or units may be electrical, mechanical, or other forms.

[0139] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0140] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0141] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or system capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0142] The embodiments described above are merely illustrative of the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for identifying and warning of multiple defects throughout the entire process of concealed works in substations, characterized in that, include: Acquire multi-source monitoring data for the entire construction process of concealed works in substations; The multi-source monitoring data is preprocessed to obtain a standardized monitoring dataset; The standardized monitoring dataset is subjected to multi-type anomaly identification processing to obtain the corresponding identification results; The identification results are integrated to generate a defect early warning report and push it to the construction management platform.

2. The method for identifying and warning of multiple defects throughout the entire process of concealed works in substations as described in claim 1, characterized in that, The process of performing multi-type anomaly identification on the standardized monitoring dataset to obtain the corresponding identification results includes: The standardized monitoring dataset is processed for cable material anomaly identification to obtain a first identification result; The standardized monitoring dataset is subjected to grounding grid installation anomaly identification processing to obtain a second identification result; The standardized monitoring dataset is subjected to construction deviation anomaly identification processing to obtain a third identification result.

3. The method for identifying and warning of multiple defects throughout the entire process of concealed works in substations as described in claim 2, characterized in that, The process of performing cable material anomaly identification on the standardized monitoring dataset to obtain a first identification result includes: The standardized monitoring dataset retrieves the surface condition image data of the cable insulation layer corresponding to the cable laying project, as well as the cable material specification design value from the construction specification parameter data; Feature extraction is performed on the surface condition image data of the cable insulation layer. Surface damage features are identified through edge detection and texture analysis. The actual conductor diameter and insulation layer thickness data of the cable are also extracted. The difference between the actual conductor diameter and insulation layer thickness of the cable and the design value of the cable material specifications is compared to obtain the first comparison result. Based on the surface damage characteristics and the comparison results, the cable material anomalies are quantitatively labeled, and the first anomaly data of the anomaly location is recorded. The first anomaly data includes three-dimensional coordinates, damage area and deviation value. The first identification result is generated based on the first abnormal data.

4. The method for identifying and warning of multiple defects throughout the entire process of concealed works in substations as described in claim 2, characterized in that, The step of performing grounding grid installation anomaly identification processing on the standardized monitoring dataset to obtain a second identification result includes: The system retrieves detailed image data of the welding points of the grounding grid, video data of the welding process, design values ​​of the grounding grid welding quality standard from the construction specification parameter data, and three-dimensional geometric information of the grounding grid layout design from the three-dimensional design model data corresponding to the grounding grid installation project from the standardized monitoring dataset. Feature extraction is performed on the detailed image data of the grounding grid welding points to obtain the extraction results; The welding process video data is subjected to time-series frame decomposition and process analysis to obtain the first analysis result; The spatial coordinate data of the actual installation location of the grounding grid are spatially matched and compared with the three-dimensional geometric information of the grounding grid layout design to obtain a second comparison result. Based on the extraction results, the first analysis results, and the second comparison results, the identified grounding grid installation anomalies are quantitatively labeled, and the second anomaly data of the anomaly location is recorded. The second anomaly data includes three-dimensional coordinates, defect type, defect size, and process non-compliance items. The second identification result is generated based on the second abnormal data.

5. The method for identifying and warning of multiple defects throughout the entire process of concealed works in substations as described in claim 2, characterized in that, The process of identifying construction deviation anomalies in the standardized monitoring dataset to obtain a third identification result includes: The system retrieves actual spatial monitoring data, three-dimensional design model data, and construction design threshold parameters from the construction specification parameter data of the entire construction process of cable laying and grounding grid installation projects from the standardized monitoring dataset. The actual spatial monitoring data is subjected to coordinate calibration and trajectory reconstruction to generate an actual cable laying path model and an actual grounding grid installation location model. The actual cable laying path model and the actual grounding grid installation location model are spatially superimposed and compared with the cable laying design path model and the grounding grid installation design location model in the three-dimensional design model data. The spatial deviation value between the actual construction and the design is quantitatively analyzed by geometric deviation calculation to obtain the second analysis result. Extract the actual operational parameters during the construction process and compare them with the construction design threshold parameters to obtain a third comparison result. Based on the second analysis result and the third comparison result, the identified construction deviation anomalies are quantitatively labeled, and the third anomaly data of the deviation location is recorded. The third anomaly data includes three-dimensional coordinates, deviation type, specific deviation value and corresponding design standard value. The third identification result is generated based on the third abnormal data.

6. The method for identifying and warning of multiple defects throughout the entire process of concealed works in substations as described in claim 1, characterized in that, After integrating the identification results, generating a defect early warning report, and pushing it to the construction management platform, the method further includes: A real-time data update channel is established based on the standardized monitoring dataset to continuously receive new monitoring data generated during the construction of cable laying projects and grounding grid installation projects. The new monitoring data includes image data, video data, and environmental parameter data collected by on-site sensors. The historical hidden engineering defect database is invoked, and the historical defect data is matched with the similar engineering data in the standardized monitoring dataset to construct a dynamic anomaly threshold model. The newly added monitoring data is input into the dynamic anomaly threshold model and compared in real time with the adjusted threshold parameters. If the data exceeds the threshold range, an immediate warning is triggered and the warning information is temporarily stored in a temporary database. Based on the identification results, the warning information in the temporary database is verified a second time. After removing false alarms, the information is updated to the defect warning report to obtain the first updated defect warning report. The first updated defect warning report is then pushed to the construction management platform simultaneously.

7. The method for identifying and warning of multiple defects throughout the entire process of concealed works in substations as described in claim 1, characterized in that, After integrating the identification results, generating a defect early warning report, and pushing it to the construction management platform, the method further includes: Simultaneously collect data from construction personnel's operation records and construction equipment's operating parameters; The operation record data of the construction personnel and the operating parameter data of the construction equipment are correlated with the identification results to obtain the correlation analysis results; Based on the correlation analysis results, the root cause type leading to the defects in the concealed works is identified, and a root cause analysis report is generated. The root cause analysis report and the defect warning report are integrated, and solutions corresponding to different root cause types are added to obtain a second updated defect warning report. The second updated defect warning report is then pushed to the construction management platform and the terminals of relevant responsible personnel.

8. A multi-defect identification and early warning system for concealed works in substations throughout the entire process, characterized in that, The system includes: The acquisition module is used to acquire multi-source monitoring data of the entire construction process of concealed works in substations; The preprocessing module is used to preprocess the multi-source monitoring data to obtain a standardized monitoring dataset; The identification module is used to perform multi-type anomaly identification processing on the standardized monitoring dataset to obtain the corresponding identification results; The integration module is used to integrate the identification results, generate a defect early warning report, and push it to the construction management platform.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the substation concealed works full-process multi-defect identification and early warning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the substation concealed works full-process multi-defect identification and early warning method as described in any one of claims 1 to 7.

Images