Intelligent identification method and system for hidden project quality defects of power infrastructure construction

Abstract

The invention discloses an intelligent identification method and system for hidden project quality defects of power infrastructure construction, and relates to the technical field of intelligent defect identification, and the method comprises the steps: obtaining time sequence data and a visible light image of structure health monitoring through constructing a three-dimensional point cloud model; time sequence features are extracted based on the time sequence data, the visible light image is input into the defect segmentation model to obtain a defect probability graph, geometric features of the defect area are generated based on the defect probability graph, and the time sequence features and the geometric features are fused to obtain spatial-temporal features; obtaining an acceleration vector sequence of defect area expansion based on spatial-temporal characteristics, and performing defect mode recognition; determining an expansion direction vector of the defect area according to the geometrical characteristics, obtaining a principal stress direction vector under the action of an external load, and judging the danger degree of expansion of the defect area; and outputting the defect state according to the spatial-temporal characteristics of the pixels of the defect area, and carrying out abnormal decision-making by combining the defect mode and the danger degree of defect area expansion, so that intelligent identification of defect detection is realized.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent defect identification, and in particular to a method and system for intelligent identification of quality defects of concealed power infrastructure projects. Background Art

[0002] Transmission towers are a key component of the power transmission system, and the health of their structures is directly related to the safe and stable operation of the power grid. However, since transmission towers are exposed to the external environment all year round, various defects such as cracks, rust, and deformation emerge in an endless stream, threatening the reliability of power transmission. Traditional transmission tower structural health monitoring mainly relies on manual regular inspections, which have problems such as missed inspections and misjudgments, and it is difficult to detect early signs of defects in a timely manner, resulting in delayed maintenance decisions and passive risk prevention and control.

[0003] In recent years, with the rapid development of sensor technology and artificial intelligence, equipment health management driven by multi-source heterogeneous data has become possible. In the field of transmission tower structure monitoring, on the one hand, technologies such as lidar scanning and high-definition photography can obtain three-dimensional morphological information of the tower base; on the other hand, technologies such as optical fiber sensing and acoustic emission can collect dynamic signals such as strain and vibration of the structure in real time. At the same time, meteorological stations, line load monitoring devices, etc. can also provide external environmental parameters such as wind speed, wind direction, and conductor tension. These multi-source data from different physical fields contain rich defect feature information.

[0004] A Chinese patent application with publication number CN118133087A discloses a construction project quality monitoring method and device based on artificial intelligence and big data. The method includes: collecting data to be monitored during the construction or use of a target building structure, and fusing the data to generate a vector to be identified; inputting the vector to be identified into a pre-built feature extraction model, and extracting target features of the vector to be identified through the feature extraction model; inputting the target features into a pre-built classifier model, and outputting classification and identification results through the classifier model; the classification and identification results include the construction project quality grade corresponding to the target features; and determining the quality status of the target building structure based on the classification and identification results.

[0005] The monitoring strategies of existing methods are fixed and cannot dynamically optimize the decision logic according to the defect evolution stage, resulting in waste of resources or missed detection of key information. Summary of the invention

[0006] The present application aims to solve one of the technical problems in the related art at least to a certain extent. To this end, one purpose of the present application is to propose an intelligent identification method and system for quality defects of hidden engineering of power infrastructure, so as to realize intelligent identification of defect detection.

[0007] One aspect of the present application provides an intelligent identification method for quality defects of hidden power infrastructure projects, including:

[0008] Step S100: Construct a three-dimensional point cloud model, obtain the time-series data for structural health monitoring and visible light images of the surface texture of the transmission tower base;

[0009] Step S200: Extract time-series features based on the time-series data, input the visible light image into a defect segmentation model to obtain a defect probability map, generate geometric features of the defect region based on the defect probability map, and fuse the time-series features and geometric features to obtain spatio-temporal features;

[0010] Step S300: Obtain the acceleration vector sequence of the defect region expansion based on the spatio-temporal features, and use the acceleration vector sequence for defect pattern recognition;

[0011] Step S400: Determine the expansion direction vector of the defect region according to the geometric features, obtain the principal stress direction vector under the action of the external load, and judge the risk degree of the defect region expansion;

[0012] Step S500: Output the defect state of the defect region according to the spatio-temporal features of the defect region pixels, and make an abnormal decision in combination with the defect pattern and the risk degree of the defect region expansion;

[0013] The specific method for constructing the three-dimensional point cloud model, obtaining the time-series data for structural health monitoring and visible light images of the surface texture of the transmission tower base is as follows:

[0014] Step S110: Obtain three-dimensional point cloud data by scanning the transmission tower base and its surrounding environment with a lidar. The attributes of each point include the three-dimensional coordinates and reflection intensity of the point, and generate a three-dimensional point cloud model of the transmission tower base based on the three-dimensional point cloud data;

[0015] Step S120: Obtain visible light images of the surface texture of the transmission tower base;

[0016] Step S130: Collect strain data, vibration data and acoustic emission data through sensors in the transmission tower base, and integrate the time series of the strain data, vibration data and acoustic emission data into the time-series data for structural health monitoring;

[0017] Step S140: Take the center of the bottom surface of the transmission tower base as the origin, construct a three-dimensional space coordinate system, and synchronize the time of the time-series data for structural health monitoring and unify it into the three-dimensional space coordinate system;

[0018] The specific method for extracting time-series features based on the time-series data, inputting the visible light image into a defect segmentation model to obtain a defect probability map, generating geometric features of the defect region based on the defect probability map, and fusing the time-series features and geometric features to obtain spatio-temporal features is as follows:

[0019] Step S210: Perform time-frequency domain analysis on the time-series data of structural health monitoring, extract time-domain features and frequency-domain features, and perform feature fusion on the time-domain features and frequency-domain features to obtain time-series features;

[0020] Step S220: Align the visible light image and the three-dimensional point cloud model, and establish a three-dimensional point cloud model with texture information between the pixels of the visible light image and the three-dimensional point cloud model;

[0021] Step S230: Use a convolutional neural network incorporating prior physical knowledge for defect segmentation. The input data is the visible light image aligned with the three-dimensional point cloud model, and the output data is a defect probability map. Calculate the geometric features of the defect region based on the defect probability map; the geometric features include the main direction of the defect region;

[0022] Step S240: Align the geometric features and the time-series features according to the time stamp, and associate them with the three-dimensional spatial coordinates of the corresponding three-dimensional point cloud model to obtain spatio-temporal features; the spatio-temporal features include the three-dimensional spatial coordinates of the center of the defect region, the time stamp, and the geometric features and time-series features corresponding to the time stamp;

[0023] The specific method of using a convolutional neural network incorporating prior physical knowledge for defect segmentation, where the input data is the visible light image aligned with the three-dimensional point cloud model, the output data is a defect probability map, and calculating the geometric features of the defect region based on the defect probability map is as follows:

[0024] Design an end-to-end convolutional neural network model for defect segmentation. Input the visible light image aligned with the three-dimensional point cloud model, label the defect labels for the visible light image to obtain a defect mask, construct a training sample based on the visible light image and the corresponding defect mask, and define minimizing the segmentation loss function as the training objective of the convolutional neural network model; Incorporate prior physical knowledge into the defect segmentation model, define a regularization term based on partial differential equations, and add the regularization term to the segmentation loss function to obtain the total segmentation loss function of the convolutional neural network incorporating prior physical knowledge; Use the training sample to train the convolutional neural network incorporating prior physical knowledge by minimizing the total segmentation loss function to obtain a defect segmentation model; Use the current visible light image aligned with the three-dimensional point cloud model as the input data, output a defect probability map through the defect segmentation model, segment the defect region based on thresholding operation, and calculate the geometric features of the defect region;

[0025] The calculation method of the main direction is as follows:

[0026] Step S231: Use the three-dimensional spatial coordinates corresponding to all pixels within a defect region as a two-dimensional point cloud to form a coordinate matrix of B×2; B is the number of pixels in the defect region;

[0027] Step S232: Decentralize the coordinate matrix to obtain the coordinate matrix after mean removal;

[0028] Step S233: Calculate the covariance matrix of the coordinate matrix after mean removal;

[0029] Step S234: Perform eigenvalue decomposition on the covariance matrix, and take the eigenvector corresponding to the largest eigenvalue as the main direction of the defect region;

[0030] The specific method for obtaining the acceleration vector sequence of defect region expansion based on spatio-temporal features and performing defect pattern recognition using the acceleration vector sequence is as follows:

[0031] Step S310: For the spatio-temporal features of the same defect region collected at consecutive tn data sampling times, form a spatio-temporal feature sequence, and calculate the displacement vector and velocity vector of the three-dimensional space coordinates of the defect region over time based on the spatio-temporal features of adjacent data sampling times;

[0032] Step S320: Based on the spatio-temporal feature sequence, obtain the displacement vector sequence and velocity vector sequence of the defect region, and calculate the acceleration vector sequence of defect region expansion according to the velocity vectors between adjacent data sampling times;

[0033] Step S330: Use a long short-term memory network to perform defect pattern recognition on the acceleration vector sequence of defect region expansion; the defect patterns include normal patterns and abnormal patterns;

[0034] The specific method for using a long short-term memory network to perform defect pattern recognition on the acceleration vector sequence of defect region expansion is as follows:

[0035] Perform defect pattern recognition using a long short-term memory network. The input is the acceleration vector sequence of defect region expansion, and the output is the defect pattern corresponding to the data sampling time. Define a binary cross-entropy loss function, and use the historical acceleration vector sequence with defect pattern labels to perform supervised learning training on the long short-term memory network; when the output for consecutive m data sampling times is an abnormal pattern, it is determined that there is a risk of structural instability.

[0036] The specific method for determining the expansion direction vector of the defect region according to geometric features, obtaining the principal stress direction vector under external load, and judging the danger degree of defect region expansion is as follows:

[0037] Step S410: For the sequence of three-dimensional space coordinates of the defect region at consecutive tn data sampling times, obtain the main direction of this defect region as the expansion direction vector;

[0038] Step S420: Obtain the principal stress direction vector under the current external load;

[0039] Step S430: Calculate the spatial angle between the expansion direction vector of the defect area and the principal stress direction vector;

[0040] Step S440: Judge the consistency between the expansion direction vector of the defect area and the principal stress direction vector according to the spatial angle threshold, and determine the danger degree of the expansion of the defect area;

[0041] The specific method for judging the consistency between the expansion direction vector of the defect area and the principal stress direction vector according to the spatial angle threshold and determining the danger degree of the expansion of the defect area is as follows: Set the spatial angle threshold. When the spatial angle is less than the spatial angle threshold, it is determined that the defect area is expanding in the high-risk direction, otherwise it is considered that the defect area is safe. The danger degree of the expansion of the defect area includes the high-risk direction and safety;

[0042] The specific method for outputting the defect state according to the spatio-temporal characteristics of the pixels in the defect area and making an anomaly decision in combination with the defect mode and the danger degree of the expansion of the defect area is as follows:

[0043] Step S510: Conduct a clustering analysis on the spatio-temporal characteristics of the defect area in the historical time, divide the defect state into three stages: the germination stage, the stable stage, and the diffusion stage, obtain the clustering model, input the spatio-temporal characteristics of the current defect area pixels, and output the corresponding defect state;

[0044] Step S520: Adaptively adjust the data adoption frequency of the defect area according to the output of the clustering model;

[0045] Step S530: Make an anomaly decision according to the defect state, defect mode, and danger degree of the expansion of the defect area.

[0046] One aspect of the present application provides an intelligent identification system for quality defects in hidden projects of power infrastructure construction, including:

[0047] A multi-modal data collection module, used to construct a three-dimensional point cloud model, obtain the time-series data of structural health monitoring and the visible light image of the surface texture of the transmission tower foundation;

[0048] A spatio-temporal feature fusion module, which extracts time-series features based on the time-series data, inputs the visible light image into the defect segmentation model to obtain a defect probability map, generates geometric features of the defect area based on the defect probability map, and fuses the time-series features and geometric features to obtain spatio-temporal features;

[0049] A defect mode recognition module, which obtains the acceleration vector sequence of the expansion of the defect area based on the spatio-temporal features, and uses the acceleration vector sequence for defect mode recognition;

[0050] A danger degree judgment module, which determines the expansion direction vector of the defect area according to the geometric features, obtains the principal stress direction vector under the action of the external load, and judges the danger degree of the expansion of the defect area;

[0051] The decision-making comprehensive judgment module outputs the defect status according to the spatiotemporal characteristics of the pixels in the defect area, and makes abnormal decisions based on the defect mode and the degree of danger of the defect area expansion.

[0052] One aspect of the present application provides a readable storage medium storing a computer program suitable for loading by a processor to execute the steps in a method for intelligently identifying quality defects of hidden projects in power infrastructure.

[0053] Compared with the prior art, the intelligent identification method and system for quality defects of hidden power infrastructure projects proposed in this application have the following advantages:

[0054] This application extracts discriminative features related to defects in multimodal sensor data and fuses them with three-dimensional spatial information to obtain a unified spatiotemporal feature representation. It uses physical prior knowledge to guide the convolutional neural network model for feature learning, realizes the organic combination of data-driven and knowledge-driven, and improves the accuracy and robustness of defect segmentation.

[0055] This application extracts the geometric features of the defect area, characterizes the spatial morphology of the defect, takes the main direction of the defect area as its expansion direction vector, reveals the local expansion trend of the defect, introduces the main stress direction vector under the action of external load, combines the defect analysis with the structural force analysis, explains the evolution behavior of the defect from the perspective of physical mechanism, and provides a quantitative indicator for evaluating the degree of danger of the defect.

[0056] This application calculates the displacement vector and velocity vector of the defect area based on the spatiotemporal feature sequence, characterizes the dynamic evolution process of the defect, further calculates the acceleration vector sequence, introduces high-order physical quantities to describe the dynamic behavior of the defect, and uses the LSTM network to perform defect pattern recognition on the acceleration vector sequence, thereby realizing abnormal detection and early warning of defect evolution. Through modeling and pattern recognition of the dynamic evolution of defects, early warning of the risk of structural instability is achieved.

[0057] This application clusters the temporal and spatial characteristics of historical defects, adaptively divides the defect status, reveals the inherent stages of defect evolution, dynamically adjusts the data sampling frequency according to the defect status, realizes self-optimization of the monitoring strategy, comprehensively considers the defect status, defect mode and degree of danger, and constructs an abnormal decision-making mechanism that integrates multiple factors. Through hierarchical and classified state modeling and abnormal decision-making, a global evaluation from local to overall, from state to trend is realized, which solves the problem of dynamically optimizing the decision-making logic of defect maintenance according to the defect evolution stage, and improves the sensitivity and reliability of defect detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1Flowchart of the intelligent identification method for quality defects of hidden projects in power infrastructure construction provided by this application;

[0059] Figure 2 Flowchart of the fusion method for spatio-temporal features provided by this application;

[0060] Figure 3 Flowchart of the defect pattern recognition method provided by this application;

[0061] Figure 4 Schematic diagram of the extended direction vector and the principal stress direction vector provided by this application;

[0062] Figure 5 Functional module diagram of the intelligent identification system for quality defects of hidden projects in power infrastructure construction provided by this application. Detailed implementation manners

[0063] To better understand this application, more detailed descriptions of various aspects of this application will be made with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of the exemplary embodiments of this application and do not limit the scope of this application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0064] In the accompanying drawings, for ease of illustration, the sizes, dimensions, and shapes of the elements have been slightly adjusted. The drawings are only examples and are not drawn strictly to scale. As used herein, terms such as "substantially", "about", and similar terms are used as terms indicating approximation and not as terms indicating degree, and are intended to illustrate the inherent deviations in measured or calculated values that would be recognized by those of ordinary skill in the art. Additionally, in this application, the order of description of the processing steps does not necessarily represent the order in which these processes occur in actual operation, unless there are clear other limitations or can be deduced from the context.

[0065] It should also be understood that expressions such as "including", "including having", "having", "containing", and / or "containing having" in this specification are open-ended rather than closed-ended expressions, which mean that there are the stated features, elements, and / or components, but do not exclude the existence of one or more other features, elements, components, and / or their combinations. In addition, when an expression such as "at least one of..." appears after the list of listed features, it modifies the entire list of features rather than just the individual elements in the list. In addition, when describing the embodiments of this application, the use of "may" means "one or more embodiments of this application". And the term "exemplary" is intended to refer to an example or illustration.

[0066] Unless otherwise defined, all terms used herein (including engineering and scientific terms) shall have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. It should also be understood that, unless explicitly stated otherwise in this application, words defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and should not be interpreted in an idealized or overly formal sense.

[0067] It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other. The following will describe this application in detail with reference to the drawings and in combination with the embodiments.

[0068] Embodiment 1

[0069] As Figure 1 shown, the intelligent identification method for quality defects of hidden works in power infrastructure provided by this application includes:

[0070] Step S100: Construct a three-dimensional point cloud model, and obtain the time-series data of structural health monitoring and the visible light image of the surface texture of the transmission tower foundation;

[0071] The specific method for constructing the three-dimensional point cloud model and obtaining the time-series data of structural health monitoring and the visible light image of the surface texture of the transmission tower foundation is as follows:

[0072] Step S110: Obtain three-dimensional point cloud data by lidar scanning the transmission tower foundation and its surrounding environment. The attributes of each point include the three-dimensional coordinates and reflection intensity of the point, and generate a three-dimensional point cloud model of the transmission tower foundation based on the three-dimensional point cloud data;

[0073] The three-dimensional point cloud data is used to reconstruct the three-dimensional geometric model of the transmission tower foundation, providing a data basis for subsequent defect location.

[0074] Step S120: Obtain the visible light image of the surface texture of the transmission tower foundation;

[0075] The visible light image of the surface texture of the transmission tower foundation is obtained by taking pictures of the surface texture of the transmission tower foundation with a high-resolution camera or a drone;

[0076] The three-dimensional point cloud data and the visible light image are synchronously collected and matched, so that in subsequent defect analysis, the defect information in the image space can be accurately mapped to the three-dimensional physical space, so that the position, size and shape of the defect can be intuitively displayed on the three-dimensional point cloud model and correlated with the time-series data of subsequent structural health monitoring.

[0077] Step S130: Collect strain data, vibration data, and acoustic emission data through sensors in the transmission tower foundation, and integrate the time series of strain data, vibration data, and acoustic emission data into the time series data for structural health monitoring;

[0078] The strain data can be expressed as: ; is the strain data collected at the th data sampling time;

[0079] The vibration data can be expressed as:

[0080] ; is the vibration data collected at the th data sampling time;

[0081] The acoustic emission data can be expressed as:

[0082] ; is the acoustic emission data collected at the th data sampling time;

[0083] wherein, represents the sensor number, is the data sampling time;

[0084] The time series data for structural health monitoring are the time series signal data such as strain data, vibration data, and acoustic emission data obtained through sensors such as strain gauges, accelerometers, and ultrasonic flaw detectors, and are used to reflect the dynamic response of the structure under external loads to analyze the damage and deterioration state of the structure.

[0085] Furthermore, the acquisition frequencies and sampling times of the multi-modal time series data need to be synchronized. Time synchronization is achieved by embedding a high-precision clock module in the sensor nodes to ensure that the data collected by different sensors are aligned in the time dimension for multi-modal information fusion and time series analysis.

[0086] Step S140: Taking the center of the bottom surface of the transmission tower foundation as the origin, construct a three-dimensional space coordinate system, and synchronize the time series data for structural health monitoring and unify them into the three-dimensional space coordinate system;

[0087] The three-dimensional space coordinates in the three-dimensional space coordinate system can be expressed as (x, y, z).

[0088] Synchronizing the time series data for structural health monitoring and unifying them into the three-dimensional space coordinate system is to achieve the spatio-temporal consistency of the data, which is convenient for subsequent multi-modal data fusion and defect location.

[0089] The data acquisition process in the above steps is designed for the synchronous acquisition and spatio-temporal alignment of multi-source heterogeneous data, which is the basis for subsequent defect analysis and prediction. Among them, the 3D point cloud data provides an accurate geometric model of the transmission tower base, the visible light image provides visual features of surface defects, and the time-series data of structural health monitoring reflects the physical quantity indicators of the structural health state. These data complement each other and jointly constitute comprehensive health monitoring information of the transmission tower base.

[0090] Step S200: Extract time-series features based on the time-series data, input the visible light image into the defect segmentation model to obtain the defect probability map, generate geometric features of the defect region based on the defect probability map, and fuse the time-series features and geometric features to obtain spatio-temporal features;

[0091] As Figure 2 shown, the specific method for extracting time-series features based on the time-series data, inputting the visible light image into the defect segmentation model to obtain the defect probability map, generating geometric features of the defect region based on the defect probability map, and fusing the time-series features and geometric features to obtain spatio-temporal features is as follows:

[0092] Step S210: Perform time-frequency domain analysis on the time-series data of structural health monitoring, extract time-domain features and frequency-domain features, and fuse the time-domain features and frequency-domain features to obtain time-series features;

[0093] The time-domain features include the mean and variance of the time-series data, which respectively reflect the average amplitude and fluctuation degree of the time-series data. The frequency-domain features include the Fourier transform coefficients of the time-series data and the power spectral density of the time-series data, which are respectively used to transform the time-domain signal to the frequency domain and reflect the energy distribution of the time-series data on different frequency components;

[0094] The calculation formula for the mean of the time-series data is:

[0095] ; where represents the time-series data at the data sampling time ti, tn is the last data sampling time, represents the mean of the time-series data sx;

[0096] The calculation formula for the variance of the time-series data is: ; where represents the variance of the time-series data sx;

[0097] The calculation formula for the Fourier transform coefficients of the time-series data is: ; where represents the Fourier transform coefficients of the time-series data sx, t represents the data sampling time variable of the time-domain signal, f represents the frequency variable of the frequency-domain signal, and j is the imaginary unit, satisfying , Timing data representing the data sampling time t

[0098] The calculation formula for the power spectral density of the timing data is as follows: ; where represents the power spectral density of the timing data sx, and TS is the total duration of the time-domain signal;

[0099] The timing feature is represented as and is obtained by combining multiple time-frequency domain features;

[0100] Step S220: Align the visible light image and the 3D point cloud model, and establish a 3D point cloud model with texture information between the pixels of the visible light image and the 3D point cloud model;

[0101] The specific method for aligning the visible light image and the 3D point cloud model and establishing a 3D point cloud model with texture information between the pixels of the visible light image and the 3D point cloud model is as follows:

[0102] Step S221: Input the visible light image and the 3D point cloud model, and extract image features and point cloud features from the visible light image and the 3D point cloud model;

[0103] The feature descriptor used for the extraction of local feature points is SIFT. The process of extracting image features of the visible light image I is represented as and the process of extracting point cloud features of the 3D point cloud model P is represented as ; where and respectively represent the SIFT feature vectors of the visible light image and the 3D point cloud model, is the image feature, is the point cloud feature;

[0104] Step S222: Perform feature matching on the image features and the point cloud features to obtain an initial feature matching set;

[0105] Step S223: Remove outliers from the initial feature matching set to obtain an inlier matching set. According to the inlier matching set, solve the optimal transformation matrix from the image features to the point cloud features through the least squares optimization algorithm ;

[0106] The RANSAC method is used for outlier removal, and the transformation matrix is ; where T is the transformation model from the image features to the point cloud features, and respectively represent the coordinates of the image feature points and the three-dimensional coordinates of the point cloud feature points, is the indicator function, is the threshold for inlier determination; the argmax function represents searching for the one that makes The transformation matrix with the largest value represents the Euclidean distance represents the Euclidean distance between the image feature points and the point cloud feature points obtained by projecting through the transformation model T indicates that the mi-th image feature and the mk-th point cloud feature are a pair of matching pairs is the feature matching set between the image features and the point cloud features

[0107] Step S224: Map each pixel point in the visible light image to the coordinates of the corresponding point in the three-dimensional point cloud model according to the transformation matrix, and obtain a three-dimensional point cloud model with texture information ;

[0108] Step S230: Perform defect segmentation using a convolutional neural network incorporating prior physical knowledge. The input data is the visible light image aligned with the three-dimensional point cloud model, and the output data is the defect probability map. Calculate the geometric features of the defect region based on the defect probability map; the geometric features include the main direction of the defect region

[0109] Preferably, the convolutional neural network model selects the U-Net model

[0110] The specific method of performing defect segmentation using a convolutional neural network incorporating prior physical knowledge, where the input data is the visible light image aligned with the three-dimensional point cloud model, the output data is the defect probability map, and calculating the geometric features of the defect region based on the defect probability map is as follows

[0111] Design an end-to-end convolutional neural network model for defect segmentation. Input the visible light image I aligned with the three-dimensional point cloud model, and label the defect labels for the visible light image to obtain a defect mask , construct training samples based on the visible light image and the corresponding defect mask, define the minimization of the segmentation loss function as the training objective of the convolutional neural network model; incorporate prior physical knowledge into the defect segmentation model, define a regularization term based on partial differential equations, add the regularization term to the segmentation loss function to obtain the total segmentation loss function of the convolutional neural network incorporating prior physical knowledge; use the training samples to train the convolutional neural network incorporating prior physical knowledge by minimizing the total segmentation loss function to obtain a defect segmentation model; use the current visible light image aligned with the three-dimensional point cloud model as the input data, output the defect probability map through the defect segmentation model, segment the defect region based on thresholding operations, and calculate the geometric features of the defect region

[0112] The segmentation loss function The calculation formula of is ; where N is the number of training samples and are the height and width of the visible light image respectively, n ≤ N, i ≤ H, k ≤ W, and represent the pixel row and column indices in the visible light image, represent the pixel in the visible light image is predicted to be the probability of a defect, are the parameters of the convolutional neural network model; the segmentation loss function is the pixel-level binary cross-entropy loss. is the pixel of the defect mask of the visible light image in the nth training sample;

[0113] The partial differential equation is a defect propagation partial differential equation derived based on Paris' law, and the equation expression is: , where represents the characteristic function of the defect region, represents the gradient of the characteristic function u of the defect region, and are constants related to material properties;

[0114] The total segmentation loss function The calculation formula is: ; where is the regularization coefficient, is the visible light image domain;

[0115] The defect region segmented based on the thresholding operation means setting a probability threshold. For the output defect probability map , where the pixels with a probability greater than the probability threshold are determined as the defect region, the defect mask of the defect region is 1, and the defect mask of the non-defect region is 0, obtaining a binary defect mask ;

[0116] The calculation method of the main direction is:

[0117] Step S231: Use the three-dimensional space coordinates corresponding to all pixels in a defect region as a two-dimensional point cloud to form a coordinate matrix of B×2;

[0118] The coordinate matrix is expressed as:

[0119] , where B is the number of pixels in the defect region; is the row index of the pixel in the defect region, is the column index of the pixel in the defect region;

[0120] Step S232: Decentralize the coordinate matrix to obtain the coordinate matrix after removing the mean;

[0121] The coordinate matrix after mean removal is as follows:

[0122] ; where and are the means of each column of the coordinate matrix respectively;

[0123] Step S233: Calculate the covariance matrix of the coordinate matrix after mean removal;

[0124] The covariance matrix of the coordinate matrix after mean removal has the following calculation formula:

[0125] ; where and represent the variances of the row index ' and column index of the coordinate matrix after mean removal respectively, represents the covariance of the row index ' and column index of the coordinate matrix after mean removal; is 's transpose;

[0126] Step S234: Perform eigenvalue decomposition on the covariance matrix, and take the eigenvector corresponding to the largest eigenvalue as the main direction of the defect area;

[0127] The calculation formula for performing eigenvalue decomposition on the covariance matrix is: , where is a diagonal matrix, and the elements on its diagonal are the eigenvalues and of the covariance matrix, is an orthogonal matrix, and its column vectors and are the eigenvectors corresponding to and respectively, and they satisfy the relationship ;

[0128] The process of taking the eigenvector corresponding to the largest eigenvalue as the main direction of the defect area includes: taking the largest eigenvalue and among the eigenvalues on the diagonal of the diagonal matrix and taking the corresponding eigenvector as the main direction of the defect area.

[0129] The main direction of the defect area can be expressed as:

[0130] ; where Represents the angle between the main direction and the horizontal direction;

[0131] The main direction captures the direction of the maximum variance in the pixel distribution of the defect area, reflecting the overall extension trend of the defect. The other eigenvector orthogonal to it represents the secondary extension direction of the defect.

[0132] By solving the main direction through the principal component analysis method, a quantitative direction feature can be extracted from the segmented defect area, providing a data basis for subsequent defect classification, recognition, and evolution analysis. For example, for crack-like defects, its main direction can indicate the trend of crack propagation. For corrosion-like defects, the main direction may be related to the direction of stress concentration. Combining the direction feature with geometric features such as area, perimeter, and major axis length results in a comprehensive description of the defect morphology, providing more abundant information for automated defect analysis.

[0133] The geometric features also include the area, perimeter, and major axis perimeter of the defect area;

[0134] The area of the defect area The calculation formula is: ;

[0135] The calculation formula for the perimeter of the defect area is: ;

[0136] Among them,

[0137] Represents the difference between the defect mask of the current pixel and its left pixel, Represents the difference between the defect mask of the current pixel and its upper pixel; Represents the pixel Predicted defect mask;

[0138] If the defect mask values of two pixels are different, it means there is a vertical boundary, and the corresponding side length is 1, otherwise the side length is 0; similarly, the difference between the defect mask of the current pixel and its upper pixel is used to determine whether there is a horizontal boundary between two pixels;

[0139] The major axis length The calculation formula is: ;

[0140] Step S240: Align the geometric features and the temporal features according to the timestamp and associate them with the three-dimensional spatial coordinates of the corresponding three-dimensional point cloud model to obtain spatio-temporal features;

[0141] The spatio-temporal features include the three-dimensional spatial coordinates of the center of the defect area, the timestamp, and the geometric features and temporal features corresponding to the timestamp.

[0142] Exemplarily, assume that a crack image is captured on the concrete surface of a certain transmission tower foundation. The traditional CNN model may only be able to segment the general outline of the crack, while the CNN model with a physical regularization term can estimate the crack propagation direction and morphology according to Paris' law, making the segmentation result more refined and accurate. At the same time, the physical regularization term can also make up for the problem of insufficient training data, enabling the CNN model to learn reasonable defect features even in small-sample scenarios.

[0143] Step S300: Obtain the acceleration vector sequence of the defect area expansion based on spatio-temporal features, and use the acceleration vector sequence for defect pattern recognition;

[0144] As Figure 3 shown, the specific method for obtaining the acceleration vector sequence of the defect area expansion based on spatio-temporal features and using the acceleration vector sequence for defect pattern recognition is as follows:

[0145] Step S310: For the spatio-temporal features of the same defect area collected at continuous tn data sampling times, form a spatio-temporal feature sequence, and calculate the displacement vector and velocity vector of the three-dimensional spatial coordinates of the defect area over time according to the spatio-temporal features at adjacent data sampling times;

[0146] The spatio-temporal features extracted at the ti-th data sampling time can be expressed as , where is the three-dimensional spatial coordinate of the center of the defect area, and are the geometric feature and temporal feature at the ti-th data sampling time respectively;

[0147] The calculation methods for the displacement vector and velocity vector are as follows:

[0148] For the time between the ti-th data sampling time and the ti + 1-th data sampling time, calculate the displacement vector and velocity vector of the defect area. The calculation formula for the displacement vector is:

[0149] ; The calculation formula for the velocity vector is: ; where is the three-dimensional spatial coordinate of the center of the defect area at the ti + 1-th data sampling time, is the time difference between adjacent data sampling times;

[0150] Step S320: Obtain the displacement vector sequence and velocity vector sequence of the defect area based on the spatio-temporal feature sequence, and calculate the acceleration vector sequence of the defect area expansion according to the velocity vectors between adjacent data sampling times;

[0151] The acceleration vector The calculation formula is: ; where is the velocity vector at the (ti + 1)-th data sampling time;

[0152] Step S330: Use a long short-term memory network to perform defect pattern recognition on the acceleration vector sequence of the defect area expansion; the defect patterns include a normal pattern and an abnormal pattern;

[0153] The specific method for using a long short-term memory network to perform defect pattern recognition on the acceleration vector sequence of the defect area expansion is as follows:

[0154] Use a long short-term memory network for defect pattern recognition. The input is the acceleration vector sequence of the defect area expansion, and the output is the defect pattern corresponding to the data sampling time. Define a binary cross-entropy loss function, and use the historical acceleration vector sequence with defect pattern labels to perform supervised learning training on the long short-term memory network. When the output for m consecutive data sampling times is the abnormal pattern, it is determined that there is a risk of structural instability.

[0155] The acceleration vector sequence can be expressed as , representing the data sampling time corresponding acceleration vector;

[0156] The above steps introduce the concept of defect acceleration, construct a physical quantity describing the dynamic evolution of defects, and use an LSTM network to learn its normal and abnormal patterns to achieve early warning of structural instability.

[0157] Exemplarily, a crack defect was found in the foundation of a transmission tower during continuous monitoring. Through the analysis in step S300, it was found that the crack had a significant accelerating expansion trend in the past week, and its acceleration vector continuously increased in a certain direction. The LSTM network recognized its acceleration sequence, so the instability risk of the crack was timely warned. Compared with the traditional static evaluation method based on defect size, the present application identified the instability sign of the crack earlier by analyzing the dynamic evolution trend of the defect, and gained a valuable time window for subsequent maintenance decisions. This reflects the innovative role of step S300 in the early warning of defects.

[0158] Step S400: Determine the expansion direction vector of the defect area according to the geometric features, obtain the principal stress direction vector under the action of the external load, and judge the danger degree of the defect area expansion;

[0159] The specific method for determining the expansion direction vector of the defect area according to the geometric features, obtaining the principal stress direction vector under the action of the external load, and judging the danger degree of the defect area expansion is as follows:

[0160] Step S410: For the sequence of three-dimensional spatial coordinates of the defect area at consecutive tn data sampling times, obtain the main direction of the defect area as the expansion direction vector. ;

[0161] Step S420: Obtain the principal stress direction vector under the current external load.

[0162] The method for obtaining the principal stress direction vector under the current external load is as follows: Use finite element analysis software to perform stress calculations on the transmission tower foundation structure, obtain the stress distribution nephogram under the actual external load, and take the stress direction of the element with the maximum stress as the principal stress direction vector of the structure. .

[0163] Step S430: Calculate the expansion direction vector of the defect area. and the principal stress direction vector to obtain the spatial angle between them.

[0164] The expansion direction vector of the defect area and the principal stress direction vector The formula for the spatial angle between them is: ;

[0165] where represents the vector norm, represents the inverse cosine function, and the spatial angle .

[0166] Step S440: Determine the consistency between the expansion direction vector of the defect area and the principal stress direction vector according to the spatial angle threshold, and determine the risk degree of the expansion of the defect area.

[0167] The specific method for determining the consistency between the expansion direction vector of the defect area and the principal stress direction vector according to the spatial angle threshold and determining the risk degree of the expansion of the defect area is as follows: Set the spatial angle threshold . When the spatial angle is less than the spatial angle threshold, it is determined that the defect area is expanding in the high-risk direction; otherwise, the defect area is considered safe. The risk degree of the expansion of the defect area includes the high-risk direction and safety.

[0168] Furthermore, for the defect area determined to be expanding in the high-risk direction, the maintenance priority of this defect area needs to be improved.

[0169] Preferably, the spatial angle threshold is 30°.

[0170] The above steps explore the spatial correlation between the defect expansion direction and the structural stress direction, combine defect monitoring with load analysis, explain the evolution behavior of defects from the physical mechanism, and guide the formulation of maintenance decisions.

[0171] As shown Figure 4 in the figure, it is a schematic diagram of the extended direction vector and the principal stress direction vector provided by this application. The gray cube in the figure represents the transmission tower foundation. The center of the bottom surface of the transmission tower foundation is the origin, and a three-dimensional space coordinate system is constructed. There is a black crack on the transmission tower foundation, which is a simple schematic diagram of the defect area. There are two arrows with an included angle of 15° on the right side of the figure. The red arrow represents the extended direction vector of the defect area, and the blue arrow represents the principal stress direction vector under the action of the external load. The spatial included angle between the extended direction vector of the defect area and the principal stress direction vector under the action of the external load is 15°. When the spatial included angle threshold is 30°, compare the size of the spatial included angle with the spatial included angle threshold. At this time, it is determined that the defect area is expanding in the high-risk direction, and the maintenance priority of this defect area needs to be improved.

[0172] Step S500: Output the defect status according to the spatio-temporal characteristics of the pixels in the defect area, and make an abnormal decision by combining the defect mode and the risk degree of the expansion of the defect area;

[0173] The specific method for outputting the defect status according to the spatio-temporal characteristics of the pixels in the defect area and making an abnormal decision by combining the defect mode and the risk degree of the expansion of the defect area is as follows:

[0174] Step S510: Perform clustering analysis on the spatio-temporal characteristics of the defect area in the historical time to divide the defect status into three stages: the germination stage, the stable stage, and the diffusion stage, obtain a clustering model, input the spatio-temporal characteristics of the pixels in the current defect area, and output the corresponding defect status; and represent the geometric feature and the temporal feature respectively;

[0175] The clustering analysis uses the K-means clustering algorithm to determine that the number of clustering clusters is 3, corresponding to three defect statuses. The spatio-temporal characteristics of all defect areas in the historical time period are used as the training set. Each data point corresponds to a spatio-temporal feature. Randomly select K data points as the initial clustering centers. For each data point, calculate its distance from the K clustering centers and assign it to the category of the nearest clustering center. Update the clustering center of each category to the geometric center of all data points in this category; repeat the above steps until the clustering centers no longer change, and obtain the final clustering model;

[0176] Exemplarily, according to the trained clustering model, when inputting the spatio-temporal characteristics of the pixels in the current defect area, the clustering model calculates the distance between this spatio-temporal feature and each clustering center, and divides this spatio-temporal feature into the category of the nearest clustering center. This category is the defect status corresponding to the spatio-temporal characteristics of the pixels in the current defect area.

[0177] Step S520: According to the output of the clustering model, adaptively adjust the data sampling frequency of the defect area;

[0178] Specifically, the method for adaptively adjusting the data sampling frequency of the defect area according to the output of the clustering model is as follows: when the output of the clustering model determines that the defect area is in the budding stage or the stable stage, maintain the data sampling frequency of the defect area at the default slow detection frequency; when the output of the clustering model determines that the defect area enters the diffusion stage, increase the data sampling frequency of the defect area to the high-speed detection rate.

[0179] Preferably, the slow detection frequency is once per hour, and the high-speed detection rate is once per minute.

[0180] Step S530: Make an anomaly decision based on the defect status, defect mode, and the risk level of the expansion of the defect area;

[0181] Exemplarily, the method for making an anomaly decision based on the defect status, defect mode, and the risk level of the expansion of the defect area is as follows: design a rule-based three-color decision system: green indicates safety, the defect status of each pixel in the defect area is in the budding stage or the stable stage, and the defect mode and the risk level of the expansion of the defect area are normal and safe; yellow indicates warning, no more than 30% of the pixels enter the diffusion stage, or the defect mode and the risk level of the expansion of the defect area are in the abnormal mode and the high-risk direction, but have not reached the red standard; red indicates alarm and maintenance, more than 30% of the pixels enter the diffusion stage, and the defect mode and the risk level of the expansion of the defect area are in the abnormal mode and the high-risk direction;

[0182] When the red alarm is output for 3 consecutive decision cycles, start the emergency maintenance plan; when the yellow warning is output for 3 consecutive decision cycles, start the daily maintenance plan and pay close attention; when the green safety status is continuously output, perform regular periodic inspections. Through the coordination of the hierarchical state machine, the false alarm rate can be reduced while the overall defect detection sensitivity is improved.

[0183] The above steps design a micro-macro hierarchical state machine framework, taking the defect status of the pixels in the defect area as the micro basis for anomaly decision-making, and taking the defect mode of the defect area and the risk level of the expansion of the defect area as the macro basis for anomaly decision-making. It fuses multi-source heterogeneous monitoring data at different scales, and proposes an adaptive multi-sensor collaborative optimization method, which balances the real-time performance and reliability of detection.

[0184] Through the analysis of the evolution trend of spatio-temporal features, load correlation analysis, and hierarchical decision fusion, this application has formed a complete closed-loop solution from the local to the whole, from a single point to a sequence, and from detection to early warning, jointly constituting a "physics + data"-driven, hierarchical distributed defect analysis and early warning system, which can play an important role in the online structural health monitoring under complex working conditions.

[0185] Embodiment 2

[0186] As Figure 5 shown, the intelligent identification system for the quality defects of hidden projects in power infrastructure provided by this application includes:

[0187] A multi-modal data collection module for constructing a three-dimensional point cloud model, obtaining the time-series data of structural health monitoring, and visible light images of the surface texture of transmission tower bases;

[0188] A spatio-temporal feature fusion module that extracts time-series features based on the time-series data, inputs the visible light image into a defect segmentation model to obtain a defect probability map, generates geometric features of the defect area based on the defect probability map, and fuses the time-series features and geometric features to obtain spatio-temporal features;

[0189] A defect pattern recognition module that obtains the acceleration vector sequence of the defect area expansion based on the spatio-temporal features, and uses the acceleration vector sequence for defect pattern recognition;

[0190] A danger degree judgment module that determines the expansion direction vector of the defect area according to the geometric features, obtains the principal stress direction vector under the action of the external load, and judges the danger degree of the defect area expansion;

[0191] A decision comprehensive judgment module that outputs the defect state of the defect area according to the spatio-temporal features of the pixels in the defect area, and makes an abnormal decision in combination with the defect pattern and the danger degree of the defect area expansion.

[0192] Embodiment 3

[0193] This application also provides a readable storage medium. Computer-readable instructions are stored on the readable storage medium. When the computer-readable instructions are run by a processor, the intelligent identification method for the quality defects of hidden projects in power infrastructure according to the embodiments of this application described with reference to the above drawings can be executed.

[0194] In addition, the parts of the above technical solutions provided in the embodiments of this application that are consistent with the corresponding technical solutions in the prior art in terms of implementation principles are not described in detail to avoid excessive elaboration.

[0195] The specific embodiments described above further elaborate in detail the objectives, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only the specific embodiments of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent identification method for quality defects of hidden power infrastructure projects, characterized in that: include: Construct a 3D point cloud model to obtain time series data for structural health monitoring and visible light images of the surface texture of the transmission tower foundation; Extract time series features based on time series data, input the visible light image into the defect segmentation model to obtain a defect probability map, generate geometric features of the defect area based on the defect probability map, and fuse the time series features with the geometric features to obtain spatiotemporal features; Based on the spatiotemporal characteristics, the acceleration vector sequence of the defect area expansion is obtained, and the defect pattern recognition is performed using the acceleration vector sequence; Determine the expansion direction vector of the defect area based on the geometric characteristics, obtain the principal stress direction vector under the external load, and judge the degree of danger of the defect area expansion; The defect status is output according to the spatiotemporal characteristics of the pixels in the defect area, and abnormal decisions are made based on the defect mode and the degree of danger of the defect area expansion.

2. The method for intelligently identifying quality defects of hidden power infrastructure projects according to claim 1, characterized in that: The specific method of constructing a three-dimensional point cloud model and obtaining time series data of structural health monitoring and a visible light image of the surface texture of the transmission tower base is as follows: The three-dimensional point cloud data is obtained by scanning the transmission tower base and its surrounding environment through laser radar. The attributes of each point include the three-dimensional coordinates and reflection intensity of the point. A three-dimensional point cloud model of the transmission tower base is generated based on the three-dimensional point cloud data. Obtain visible light images of the surface texture of the transmission tower base; The strain data, vibration data and acoustic emission data are collected through sensors in the transmission tower foundation, and the time series of the strain data, vibration data and acoustic emission data are integrated into time series data for structural health monitoring; A three-dimensional space coordinate system is constructed with the center of the transmission tower base surface as the origin, and the time series data of structural health monitoring are synchronized and unified into the three-dimensional space coordinate system.

3. The intelligent identification method for quality defects of hidden power infrastructure projects according to claim 2 is characterized in that: The specific method of extracting time series features based on time series data, inputting the visible light image into the defect segmentation model to obtain a defect probability map, generating geometric features of the defect area based on the defect probability map, and fusing the time series features with the geometric features to obtain the spatiotemporal features is as follows: Perform time-frequency domain analysis on the time series data of structural health monitoring, extract time domain features and frequency domain features, and fuse the time domain features and frequency domain features to obtain time series features; Align the visible light image and the three-dimensional point cloud model, and establish a three-dimensional point cloud model with texture information between the visible light image pixels and the three-dimensional point cloud model; A convolutional neural network with prior physical knowledge is used for defect segmentation. The input data is a visible light image aligned with a 3D point cloud model, and the output data is a defect probability map. The geometric features of the defect area are calculated based on the defect probability map. Geometric features include the main direction of the defect area; The geometric features and the timing features are aligned according to the timestamps and associated with the three-dimensional spatial coordinates of the corresponding three-dimensional point cloud model to obtain the spatiotemporal features; the spatiotemporal features include the three-dimensional spatial coordinates of the defect area center, the timestamp, and the geometric features and timing features corresponding to the timestamp.

4. The method for intelligently identifying quality defects of hidden power infrastructure projects as claimed in claim 3, characterized in that: The convolutional neural network that introduces prior physical knowledge is used to perform defect segmentation. The input data is a visible light image aligned with the three-dimensional point cloud model, and the output data is a defect probability map. The specific method for calculating the geometric features of the defect area according to the defect probability map is: An end-to-end convolutional neural network model is designed for defect segmentation. The visible light image aligned with the three-dimensional point cloud model is input, and the defect labels are annotated on the visible light image to obtain the defect mask. Training samples are constructed based on the visible light image and the corresponding defect mask, and the minimization of the segmentation loss function is defined as the training objective of the convolutional neural network model. Prior physical knowledge is integrated into the defect segmentation model, and a regularization term based on partial differential equations is defined. The regularization term is added to the segmentation loss function to obtain the total segmentation loss function of the convolutional neural network with prior physical knowledge. The convolutional neural network with prior physical knowledge is trained by minimizing the total segmentation loss function using the training samples to obtain the defect segmentation model. The current visible light image aligned with the three-dimensional point cloud model is used as input data, and the defect probability map is output through the defect segmentation model. The defect area is obtained by segmentation based on the thresholding operation, and the geometric features of the defect area are calculated.

5. The method for intelligently identifying quality defects of hidden power infrastructure projects as claimed in claim 4, characterized in that: The main direction is calculated as follows: The three-dimensional spatial coordinates corresponding to all pixels in a defect area are taken as a two-dimensional point cloud to form a B×2 coordinate matrix; B is the number of pixels in the defect area; Decentralize the coordinate matrix to obtain the coordinate matrix after removing the mean; Calculate the covariance matrix of the coordinate matrix after removing the mean; Perform eigenvalue decomposition on the covariance matrix and take the eigenvector corresponding to the maximum eigenvalue as the main direction of the defect area.

6. The method for intelligently identifying quality defects of hidden power infrastructure projects according to claim 5, characterized in that: The specific method of obtaining the acceleration vector sequence of defect area expansion based on the spatiotemporal characteristics and using the acceleration vector sequence to identify the defect pattern is as follows: The spatiotemporal features of the same defect area collected at tn consecutive data sampling times constitute a spatiotemporal feature sequence, and the displacement vector and velocity vector of the three-dimensional spatial coordinates of the defect area over time are calculated according to the spatiotemporal features of adjacent data sampling times; Based on the spatiotemporal feature sequence, the displacement vector sequence and velocity vector sequence of the defect area are obtained, and according to the velocity vector between adjacent data sampling times, the acceleration vector sequence of the defect area expansion is calculated; Defect pattern recognition is performed on the acceleration vector sequence of defect area extension using long short-term memory network; The defect mode includes a normal mode and an abnormal mode.

7. The method for intelligently identifying quality defects of hidden power infrastructure projects according to claim 6, characterized in that: The specific method of using the long short-term memory network to perform defect pattern recognition on the acceleration vector sequence of defect area expansion is: Long short-term memory network is used for defect pattern recognition. The input is the acceleration vector sequence of the defect area extension, and the output is the defect pattern corresponding to the data sampling time. A binary cross entropy loss function is defined, and the long short-term memory network is trained for supervised learning using the historical acceleration vector sequence with defect pattern labels. When the output of m consecutive data sampling times is an abnormal pattern, it is determined that there is a risk of structural instability.

8. The method for intelligently identifying quality defects of hidden power infrastructure projects according to claim 7, characterized in that: The specific method of determining the expansion direction vector of the defect area according to the geometric characteristics, obtaining the principal stress direction vector under the external load, and judging the danger level of the defect area expansion is: For a sequence of three-dimensional spatial coordinates of a defect area at consecutive tn data sampling times, obtaining the main direction of the defect area as an expansion direction vector; Get the principal stress direction vector under the current external load; Calculate the spatial angle between the expansion direction vector of the defect area and the principal stress direction vector; The consistency between the expansion direction vector of the defect area and the principal stress direction vector is judged according to the spatial angle threshold, and the danger level of the defect area expansion is determined; The specific method for determining the consistency between the expansion direction vector of the defect area and the principal stress direction vector based on the spatial angle threshold and the danger level of the defect area expansion is as follows: setting the spatial angle threshold, when the spatial angle is less than the spatial angle threshold, it is determined that the defect area is expanding in a high-risk direction, otherwise the defect area is considered safe, and the danger level of the defect area expansion includes high-risk direction and safety.

9. The method for intelligently identifying quality defects of concealed power infrastructure projects according to claim 8, characterized in that: The specific method of outputting the defect state according to the spatiotemporal characteristics of the pixels in the defect area and making an abnormal decision in combination with the defect mode and the degree of danger of the defect area expansion is as follows: Cluster analysis is performed on the spatiotemporal characteristics of defect areas in historical time, and the defect state is divided into three stages: the germination stage, the stable stage, and the diffusion stage. A clustering model is obtained, and the spatiotemporal characteristics of the pixels in the current defect area are input to output the corresponding defect state. Adaptively adjust the data sampling frequency of the defect area according to the output of the clustering model; Make abnormal decisions based on the defect status, defect mode and dangerous degree of defect area expansion.

10. An intelligent identification system for quality defects of hidden power infrastructure projects, used to implement the intelligent identification method for quality defects of hidden power infrastructure projects according to any one of claims 1 to 9, characterized in that: include: Multimodal data collection module, used to build a 3D point cloud model, obtain time series data for structural health monitoring and visible light images of the surface texture of the transmission tower foundation; The spatiotemporal feature fusion module extracts the time series features based on the time series data, inputs the visible light image into the defect segmentation model to obtain the defect probability map, generates the geometric features of the defect area based on the defect probability map, and fuses the time series features with the geometric features to obtain the spatiotemporal features; The defect pattern recognition module obtains the acceleration vector sequence of the defect area expansion based on the spatiotemporal characteristics, and uses the acceleration vector sequence to perform defect pattern recognition; The danger level judgment module determines the expansion direction vector of the defect area according to the geometric characteristics, obtains the principal stress direction vector under the external load, and judges the danger level of the defect area expansion; The decision-making comprehensive judgment module outputs the defect status according to the spatiotemporal characteristics of the pixels in the defect area, and makes abnormal decisions based on the defect mode and the degree of danger of the defect area expansion.

11. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps in the method for intelligently identifying quality defects of hidden projects in power infrastructure as described in any one of claims 1-9.

Images