Power transmission line nest defect hazard level evaluation method and device and computer equipment

Abstract

The invention relates to a power transmission line nest defect hazard level evaluation method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring bird nest defect data of the power transmission line; determining hazard impact factors and weights thereof based on expert knowledge; performing feature extraction on the power transmission line nest defect data to obtain at least one defect feature; comparing the at least one defect feature with a standard defect feature, and extracting key information for identifying the bird nest defect of the power transmission line; acquiring feature description of bird nest defects of the power transmission line based on the key information; based on the feature description, the hazard impact factor and the weight thereof, determining an evaluation index and the weight thereof; based on the evaluation indexes and the weights thereof, constructing a defect hazard level evaluation model; obtaining to-be-evaluated data; and extracting features of to-be-evaluated data, and inputting the features into the defect hazard level evaluation model to obtain a hazard level. The method can evaluate the hazard level of the bird nest defect of the power transmission line.

Description

Technical Field

[0001] This application relates to the field of information identification technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for assessing the hazard level of bird nest defects on power transmission lines. Background Technology

[0002] Bird nests pose a significant threat to power transmission lines, often appearing as hidden dangers. They primarily cause two types of faults: structural short circuits, where materials like wires or damp branches used in nests can bridging conductors or towers, directly triggering arcing and tripping; and insulation damage, where bird activity and droppings contaminate insulators, potentially causing flashover and power outages under certain weather conditions. Therefore, assessing the hazard level of bird nest defects is crucial.

[0003] Traditional techniques typically rely on manual inspections to identify and record defects in bird nests. However, this method is inefficient, risky, and struggles to accurately assess defects in all nests. While a method using drones and 3D modeling exists to identify defects, its structured understanding and natural language processing of identified defects are inadequate, hindering subsequent work. Furthermore, the lack of validation, optimization, and improvement processes for the identification model results in low accuracy and an inability to automatically generate preventative measures.

[0004] Therefore, how to provide a method for assessing the hazard level of bird nest defects in transmission lines is an urgent problem to be solved. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, device, computer equipment, computer-readable storage medium, and computer program product for assessing the hazard level of bird nest defects in transmission lines, which can achieve hazard classification, in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a method for assessing the hazard level of bird nest defects in transmission lines, including:

[0007] Obtain data on bird nest defects on power transmission lines; determine the hazard impact factors and their weights based on expert knowledge;

[0008] Feature extraction is performed on the data of bird nest defects on power transmission lines to obtain at least one defect feature;

[0009] At least one defect feature is compared with standard defect features to extract key information for identifying bird nest defects in transmission lines; based on the key information, a feature description of bird nest defects in transmission lines is obtained.

[0010] Based on feature descriptions, hazard impact factors and their weights, the assessment indicators and their weights for bird nest defects in transmission lines are determined; based on the assessment indicators and their weights, a defect hazard level assessment model is constructed.

[0011] Obtain data on bird nests on the transmission lines to be evaluated; extract features from the bird nest data on the transmission lines to be evaluated, input the features into the defect hazard level assessment model, and obtain the hazard level of the bird nest defects on the transmission lines.

[0012] In one embodiment, acquiring data on bird nest defects in transmission lines includes:

[0013] Collect images of bird nests, environmental data of power transmission lines, and historical data;

[0014] Data preprocessing is performed on bird nest image data, transmission line environmental data, and historical data to obtain preprocessed bird nest image data, transmission line environmental data, and historical data; the preprocessed bird nest image data, transmission line environmental data, and historical data are used as bird nest defect data for transmission lines.

[0015] In one embodiment, a characteristic description of bird nest defects on transmission lines will be obtained based on key information, including:

[0016] Based on key information, establish a relationship model between the size of the bird's nest defect and the safety threat to the transmission line, a relationship model between the location of the bird's nest defect and the safety threat to the transmission line, and a relationship model between the bird's nest and the surrounding power equipment;

[0017] Based on the relationship model between the size of bird nest defects and the safety threat to transmission lines, the impact of the size of bird nest defects on the potential safety threat to transmission lines is assessed.

[0018] Based on the relationship model between the location of bird nest defects and the safety threat to transmission lines, the potential threat level of bird nest defects to transmission lines is assessed.

[0019] Based on the relationship model between the Bird's Nest and surrounding power equipment, the influence of each component of the transmission circuit is determined;

[0020] Based on the impact of the size of the bird nest defect on the potential safety threat of the transmission line, the potential threat of the bird nest defect to the transmission line, and the influence of various components of the transmission line circuit, a characteristic description of the bird nest defect in the transmission line is obtained.

[0021] In one embodiment, before acquiring the data on bird nests on the transmission line to be evaluated, the method further includes:

[0022] Data on bird nest defects in transmission lines were used as training samples, which were then divided into a training set and a test set.

[0023] Based on the training set, obtain a purely data-driven evaluation model;

[0024] Input the test set into the defect hazard level assessment model and the pure data-driven assessment model, and obtain the assessment accuracy and recall of the defect hazard level assessment model and the pure data-driven assessment model;

[0025] Based on the accuracy and recall of the assessment, the scores of the defect hazard level assessment model and the pure data-driven assessment model are calculated and compared; when the scores meet the preset conditions, the defect hazard level assessment model is optimized.

[0026] In one embodiment, the method further includes:

[0027] The hazard level of bird nest defects on transmission lines is transformed into a visual result, and the visual result is transmitted to the user terminal.

[0028] Receive and label misjudged defects of bird nests on power transmission lines uploaded by users;

[0029] Based on the misclassification of bird nest defects on power transmission lines, the hazard impact factors and their weights are updated.

[0030] In one embodiment, the method further includes:

[0031] Based on the hazard level of bird nest defects on transmission lines, corresponding recommended prevention and control measures and response timelines are generated.

[0032] Recommended prevention and control measures and response timelines will be pushed to users.

[0033] Secondly, this application also provides a device for assessing the hazard level of bird nest defects in transmission lines, comprising:

[0034] The acquisition module is used to acquire data on bird nest defects in transmission lines; based on expert knowledge, it determines the hazard impact factors and their weights.

[0035] The extraction module is used to extract features from the bird nest defect data of transmission lines and obtain at least one defect feature.

[0036] The comparison module is used to compare at least one defect feature with standard defect features to extract key information for identifying bird nest defects in transmission lines; based on the key information, it obtains a feature description of the bird nest defects in transmission lines.

[0037] The module is used to determine the assessment indicators and their weights for bird nest defects in transmission lines based on feature descriptions, hazard impact factors and their weights; and to construct a defect hazard level assessment model based on the assessment indicators and their weights.

[0038] The assessment module is used to acquire data on bird nests on transmission lines to be assessed; extract features from the bird nest data on transmission lines to be assessed; input the features into the defect hazard level assessment model to obtain the hazard level of bird nest defects on transmission lines.

[0039] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0040] Obtain data on bird nest defects on power transmission lines; determine the hazard impact factors and their weights based on expert knowledge;

[0041] Feature extraction is performed on the data of bird nest defects on power transmission lines to obtain at least one defect feature;

[0042] At least one defect feature is compared with standard defect features to extract key information for identifying bird nest defects in transmission lines; based on the key information, a feature description of bird nest defects in transmission lines is obtained.

[0043] Based on feature descriptions, hazard impact factors and their weights, the assessment indicators and their weights for bird nest defects in transmission lines are determined; based on the assessment indicators and their weights, a defect hazard level assessment model is constructed.

[0044] Obtain data on bird nests on the transmission lines to be evaluated; extract features from the bird nest data on the transmission lines to be evaluated, input the features into the defect hazard level assessment model, and obtain the hazard level of the bird nest defects on the transmission lines.

[0045] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0046] Obtain data on bird nest defects on power transmission lines; determine the hazard impact factors and their weights based on expert knowledge;

[0047] Feature extraction is performed on the data of bird nest defects on power transmission lines to obtain at least one defect feature;

[0048] At least one defect feature is compared with standard defect features to extract key information for identifying bird nest defects in transmission lines; based on the key information, a feature description of bird nest defects in transmission lines is obtained.

[0049] Based on feature descriptions, hazard impact factors and their weights, the assessment indicators and their weights for bird nest defects in transmission lines are determined; based on the assessment indicators and their weights, a defect hazard level assessment model is constructed.

[0050] Obtain data on bird nests on the transmission lines to be evaluated; extract features from the bird nest data on the transmission lines to be evaluated, input the features into the defect hazard level assessment model, and obtain the hazard level of the bird nest defects on the transmission lines.

[0051] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0052] Obtain data on bird nest defects on power transmission lines; determine the hazard impact factors and their weights based on expert knowledge;

[0053] Feature extraction is performed on the data of bird nest defects on power transmission lines to obtain at least one defect feature;

[0054] At least one defect feature is compared with standard defect features to extract key information for identifying bird nest defects in transmission lines; based on the key information, a feature description of bird nest defects in transmission lines is obtained.

[0055] Based on feature descriptions, hazard impact factors and their weights, the assessment indicators and their weights for bird nest defects in transmission lines are determined; based on the assessment indicators and their weights, a defect hazard level assessment model is constructed.

[0056] Obtain data on bird nests on the transmission lines to be evaluated; extract features from the bird nest data on the transmission lines to be evaluated, input the features into the defect hazard level assessment model, and obtain the hazard level of the bird nest defects on the transmission lines.

[0057] The aforementioned method, device, computer equipment, computer-readable storage medium, and computer program product for assessing the hazard level of bird nest defects in transmission lines achieve the following: acquiring bird nest defect data; determining hazard influencing factors and their weights based on expert knowledge; extracting features from the bird nest defect data to obtain at least one defect feature; extracting key information for identifying bird nest defects by comparing the at least one defect feature with standard defect features; obtaining a feature description of the bird nest defect based on the key information; determining assessment indicators and their weights for the bird nest defect based on the feature description, hazard influencing factors, and their weights; constructing a defect hazard level assessment model based on the assessment indicators and their weights; acquiring bird nest data of the transmission line to be assessed; extracting features from the bird nest data of the transmission line to be assessed; inputting the features into the defect hazard level assessment model to obtain the hazard level of the bird nest defect; and achieving precise quantification and natural text description of bird nest defects. This significantly improves the accuracy and efficiency of defect detection, helps to promptly discover and handle potential safety hazards, enhances the intelligence level of inspection work, ensures the stability and reliability of the power supply system, reduces labor and time costs, and improves overall operation and maintenance efficiency. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 This is an application environment diagram of a method for assessing the hazard level of bird nest defects in transmission lines in one embodiment.

[0060] Figure 2 This is a flowchart illustrating the method for assessing the hazard level of bird nest defects in transmission lines in one embodiment;

[0061] Figure 3 This is a flowchart illustrating the method for assessing the hazard level of bird nest defects in transmission lines in another embodiment;

[0062] Figure 4 This is a structural block diagram of a power transmission line bird nest defect hazard level assessment device in one embodiment;

[0063] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0064] 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.

[0065] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0066] The method for assessing the hazard level of bird nest defects in transmission lines provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. Specifically, terminal 102 or server 104 completes a method for assessing the hazard level of bird nest defects in transmission lines. This method includes: acquiring bird nest defect data of transmission lines; determining hazard influencing factors and their weights based on expert knowledge; extracting features from the bird nest defect data of transmission lines to obtain at least one defect feature; comparing the at least one defect feature with standard defect features to extract key information for identifying bird nest defects in transmission lines; obtaining a feature description of the bird nest defect of transmission lines based on the key information; determining the assessment indicators and their weights of the bird nest defect of transmission lines based on the feature description, hazard influencing factors, and their weights; constructing a defect hazard level assessment model based on the assessment indicators and their weights; acquiring bird nest data of transmission lines to be assessed; extracting features from the bird nest data of transmission lines to be assessed, inputting the features into the defect hazard level assessment model, and obtaining the hazard level of the bird nest defect of transmission lines.

[0067] Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, and projection equipment. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0068] In one exemplary embodiment, such as Figure 2 As shown, a method for assessing the hazard level of bird nest defects in transmission lines is provided, and this method is applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps 202 to 210. Wherein:

[0069] Step 202: Obtain data on bird nest defects in transmission lines; determine the hazard impact factors and their weights based on expert knowledge.

[0070] The data on bird nest defects in transmission lines includes bird nest images, transmission line environmental data, and historical data. Expert knowledge refers to the professional knowledge used by specialists in the field to judge bird nest defects in transmission lines, such as industry standards and rules set by experts. Hazard impact factors are indicators used to determine the hazard level of bird nest defects in transmission lines. Based on these hazard impact factors, subsequent assessment standards can be obtained, and their values ​​directly affect the hazard level judgment. For example, the distance between the nest and the conductor, and the content of tree branches, are considered high-risk. When the distance between the nest and the conductor is <0.5m, the hazard level is high; when the tree branch content is >30%, it is prone to arcing.

[0071] Optionally, data preprocessing can be performed on the collected bird nest image data, power transmission line environmental data, and historical data to obtain power transmission line bird nest defect data.

[0072] For example, hazard impact factors are defined based on expert knowledge; and weights are assigned to hazard impact factors based on industry standards in the expert knowledge or by using an expert scoring method (AHP).

[0073] Optionally, an expert knowledge embedding model can be obtained using knowledge embedding technology, and expert knowledge can be acquired based on the expert knowledge embedding model. Based on a large-scale computer vision model customized or optimized for power industry visual tasks (especially transmission line inspection), multi-layer convolution, attention mechanisms, and residual connection techniques are integrated to construct an expert knowledge embedding model. The optimizer uses the Adam optimizer, which can automatically adjust the learning rate. The knowledge embedding technology integrates expert knowledge into this basic model, and the specific steps include: constructing a feature set, transforming feature vectors, and knowledge embedding. The feature set is constructed based on expert knowledge and practical experience, and the features reflect the threat of bird nest defects to transmission lines, such as diameter, shape, and distance from insulators. Transforming feature vectors refers to converting all features in the feature set into numerical feature vectors, ensuring effective transmission through encoding and scaling to guarantee the model's learning effect. Knowledge embedding refers to integrating the feature vectors into the basic model. During model training, the cross-entropy loss function can be used to optimize the model, measuring the difference between the prediction and the true distribution, and improving recognition accuracy and robustness. The formula for the cross-entropy loss function is:

[0074]

[0075] Where L is the loss value, For the first One characteristic, For the first The true indicative value of each feature; For the first The model predicts the probability value of each feature.

[0076] Step 204: Extract features from the bird nest defect data of the transmission line to obtain at least one defect feature.

[0077] The defect characteristics include physical, electrical, and environmental features. Physical features include nest volume, distance from the conductor, material conductivity (twigs / metal debris), and nest humidity; electrical features include voltage levels of adjacent conductors, phase-to-phase distance, and simulation results of local field strength; environmental features include wind speed probability distribution, rainfall frequency, and seasonal patterns of bird activity.

[0078] Optionally, feature extraction utilizes image processing techniques to preprocess image data, improving the accuracy of feature extraction. It employs machine learning algorithms, such as convolutional neural networks (CNM) and support vector machines (SVM), to automatically learn key features, such as shape, texture, and color, and quantify these key features into numerical data.

[0079] Step 206: Compare at least one defect feature with standard defect features to extract key information for identifying bird nest defects in transmission lines; based on the key information, obtain a feature description of bird nest defects in transmission lines.

[0080] The key information identified is the type and severity of bird nest defects in transmission lines, including defect size, location, and component relationships. This key information is used to classify the hazard level of bird nest defects in transmission lines.

[0081] Furthermore, the classification of transmission line defects specifically includes the classification of bird nest defects, the classification of external damage hazards in transmission channels, and the classification of corrosion defects in metal equipment of transmission lines. Among them, the classification reference quantities for bird nest defects are defect size, defect location and component relationship; the classification reference quantities for external damage hazards in transmission channels are pixel coordinates, depth estimation and relative position; and the classification reference quantities for corrosion defects in metal equipment of transmission lines are equipment type, corrosion color and corrosion area.

[0082] For example, relevant defect representations are collected as standard defect features and stored in a standard absent feature database. At least one defect feature is compared with the standard defect features in the database. Defect identification is completed through cross-modal representation alignment of vision and language, and key information of the transmission line bird nest defect identification results is extracted. The key information is then transformed into a natural language text description of the transmission line bird nest defect features.

[0083] Step 208: Based on feature description, hazard impact factors and their weights, determine the assessment indicators and their weights for bird nest defects in transmission lines; based on the assessment indicators and their weights, construct a defect hazard level assessment model.

[0084] For example, based on feature descriptions, hazard impact factors, and their weights, the assessment objective for bird nest defects and hazards is confirmed to be identifying risks, determining levels, and guiding maintenance to ensure safe operation. Based on feature descriptions, hazard impact factors, and their weights, the assessment objects include different types of bird nests, and the time period covers both seasonal assessments and long-term monitoring. Based on feature descriptions, hazard impact factors, and their weights, the assessment indicators comprehensively cover physical characteristics, structural safety, and environmental factors. Expert scoring is used to determine subjective weights, the analytic hierarchy process (AHP) is used to rank the importance of indicators, and data analysis is used to set weights based on the correlation of historical data. When constructing the assessment model, the linear weighting method, fuzzy comprehensive evaluation method, or neural network model is used to determine the model parameters, the range of values ​​for the model parameter indicators, and the weight allocation, taking into account the assessment objectives and indicator characteristics.

[0085] For example, based on feature descriptions, hazard impact factors, and their weights, assessment indicators and their weights for bird nest defects in transmission lines are determined. Based on these assessment indicators and their weights, a rule engine for a defect hazard level assessment model is established to perform hard threshold judgments, such as directly classifying nests touching conductors as the highest risk. A machine learning-based defect hazard level assessment model is established, using random forest, gradient boosting tree (XG Boost), or lightweight CNN algorithms for knowledge graph assistance to construct a bird behavior-line fault association graph. Potential risks are inferred based on the bird behavior-line fault association graph. Based on the inferred potential risks, dynamic weight adjustments are made, and feature weights can be updated through online learning to adapt to regional differences, such as increasing wind speed weights in coastal areas prone to typhoons.

[0086] Step 210: Obtain the data of bird nests on the transmission line to be evaluated; extract the features of the bird nest data on the transmission line to be evaluated, input the features into the defect hazard level assessment model, and obtain the hazard level of the bird nest defect on the transmission line.

[0087] Optionally, a monocular depth prediction model can be used to identify bird nest defects on power transmission lines. Relying on a deep learning-based monocular depth estimation algorithm, the monocular depth prediction model can estimate depth information from a single image to construct a depth prediction model for identifying bird nest defects on power transmission lines. The training process includes: First, collecting stereo image pairs or video sequences covering bird nest and power transmission line scenes from different perspectives and distances, and performing detailed annotations to construct a dataset. Second, performing data preprocessing, including denoising, adjusting brightness and contrast, and format conversion, to improve image quality and ensure the monocular depth prediction model can successfully receive the preprocessed dataset. Finally, using the preprocessed dataset, the monocular depth prediction model is trained. The model learns to extract depth features and estimate pixel depth values, and accuracy is improved through iterative parameter optimization.

[0088] The aforementioned method for assessing the hazard level of bird nest defects in transmission lines involves: acquiring bird nest defect data; determining hazard influencing factors and their weights based on expert knowledge; extracting features from the bird nest defect data to obtain at least one defect feature; comparing the at least one defect feature with standard defect features to extract key information for identifying bird nest defects; obtaining a feature description of the bird nest defect based on the key information; determining assessment indicators and their weights for the bird nest defect based on the feature description, hazard influencing factors, and their weights; constructing a defect hazard level assessment model based on the assessment indicators and their weights; acquiring bird nest data of the transmission line to be assessed; extracting features from the bird nest data of the transmission line to be assessed; inputting the features into the defect hazard level assessment model to obtain the hazard level of the bird nest defect. This method enables precise quantification and natural text description of bird nest defects, significantly improving the accuracy and efficiency of defect detection, helping to promptly identify and address potential safety hazards, enhancing the intelligence level of inspection work, ensuring the stability and reliability of the power supply system, reducing labor and time costs, and improving overall operation and maintenance efficiency.

[0089] In one embodiment, acquiring bird nest defect data for power transmission lines includes: collecting bird nest image data, power transmission line environmental data, and historical data; performing data preprocessing on the bird nest image data, power transmission line environmental data, and historical data to obtain preprocessed bird nest image data, power transmission line environmental data, and historical data; and using the preprocessed bird nest image data, power transmission line environmental data, and historical data as bird nest defect data for power transmission lines.

[0090] The data includes high-resolution images of the bird's nest; the power transmission line environmental data includes line voltage level, tower type, geographical location, and climate conditions; and the historical data includes fault records and maintenance logs caused by similar bird nests.

[0091] For example, high-resolution images of bird nests are collected using drones, cameras, or manual methods. Specifically, this includes: using drones for wide-area inspections and manual inspections for detailed data; collecting images of bird nests along power transmission lines and using these as bird nest image data; acquiring information such as line voltage levels, tower types, geographical locations, and climate conditions and using this as transmission line environmental data; and acquiring fault records and maintenance logs related to similar bird nests and using this as historical data.

[0092] For example, bird nest image data, power transmission line environmental data, and historical data are preprocessed. The preprocessing process includes: removing blurred and occluded images from the data; manually labeling bird nest data in the images, including bird nest location, size, type, etc., using professional tools to ensure accuracy and consistency; structuring power transmission line environmental parameters; filling missing data values ​​and removing abnormal data; correcting motion blur and enhancing image details by fusing adaptive filtering, multi-scale transformation, and deep neural network algorithms; and optimizing image performance under low light or complex lighting conditions through massive data training to achieve multi-scene adaptive enhancement of power transmission inspection images.

[0093] In this embodiment, by collecting and preprocessing multi-source data, high-quality, structured data on bird nest defects in transmission lines can be obtained, providing a solid foundation for subsequent feature extraction and model building, and further enhancing the usability and value of the data.

[0094] In one embodiment, a characteristic description of a bird's nest defect in a transmission line is obtained based on key information, including: establishing a relationship model between the size of the bird's nest defect and the safety threat to the transmission line, a relationship model between the location of the bird's nest defect and the safety threat to the transmission line, and a relationship model between the bird's nest and surrounding power equipment, based on the relationship model between the size of the bird's nest defect and the safety threat to the transmission line; assessing the degree of impact of the size of the bird's nest defect on the potential safety threat to the transmission line based on the relationship model between the location of the bird's nest defect and the safety threat to the transmission line; determining the influence of each component of the transmission line circuit based on the relationship model between the bird's nest and surrounding power equipment; and obtaining a characteristic description of the bird's nest defect in the transmission line based on the degree of impact of the size of the bird's nest defect on the potential safety threat to the transmission line, the degree of potential threat of the bird's nest defect to the transmission line, and the influence of each component of the transmission line circuit.

[0095] For example, based on the bird nest size feature extracted from at least one defect feature, the size of the bird nest defect is determined; based on the bird nest defect size, a relationship model between the bird nest defect size and the safety threat to the transmission line is established; based on the relationship model between the bird nest defect size and the safety threat to the transmission line, linear regression analysis or machine learning algorithms are used to evaluate the degree of impact of the bird nest defect size on the potential safety threat to the transmission line. Machine learning algorithms include, for example, decision trees and random forests.

[0096] Alternatively, the formula for linear regression is:

[0097]

[0098] in, For example, a predicted value, such as the Bird's Nest risk score. For the weight vector, These are the eigenvectors.

[0099] Decision trees use the information gain algorithm:

[0100]

[0101] in, Let be the empirical entropy of dataset D.

[0102] The voting mechanism for random forests is as follows:

[0103]

[0104] in, Indicates the first The prediction results of a single tree can be combined with the predictions of multiple trees.

[0105] For example, the location of the bird's nest defect is obtained; using GIS technology and statistical analysis or machine learning algorithms, a relationship model between the bird's nest defect location and the safety threat to the transmission line is established; based on the relationship model between the bird's nest defect location and the safety threat to the transmission line, and by analyzing historical data, including the bird's nest defect location, transmission line fault records and related environmental factors, the potential threat level of the bird's nest defect to the transmission line is determined.

[0106] For example, the relationships between components are analyzed to construct a relationship model between the bird's nest and the surrounding power equipment; based on the relationship model between the bird's nest and the surrounding power equipment, the impact of each component on the classification of defects and potential hazards is quantified; network analysis and machine learning methods are used to determine the importance or influence of each component.

[0107] For example, based on the impact of the size of the bird nest defect on the potential threat to the safety of the transmission line, the potential threat of the bird nest defect to the transmission line, and the influence of each component of the transmission line circuit, a characteristic description of the bird nest defect in the transmission line is obtained. The characteristic description is used to construct the evaluation system and evaluation model.

[0108] In this embodiment, by establishing relationship models based on key information—namely, the relationship between the size of bird nest defects and the safety threat to transmission lines, the relationship between the location of bird nest defects and the safety threat to transmission lines, and the relationship between bird nests and surrounding power equipment—the following models are constructed: Based on the relationship model between the size of bird nest defects and the safety threat to transmission lines, the impact of the size of bird nest defects on the potential safety threat to transmission lines is assessed; based on the relationship model between the location of bird nest defects and the safety threat to transmission lines, the potential threat level of bird nest defects on transmission lines is assessed; based on the relationship model between bird nests and surrounding power equipment, the influence of each component of the transmission line circuit is determined; and based on the impact of the size of bird nest defects on the potential safety threat to transmission lines, the potential threat level of bird nest defects on transmission lines, and the influence of each component of the transmission line circuit, a characteristic description of bird nest defects in transmission lines is obtained. This provides clear risk warnings for operation and maintenance personnel, accurately assesses the potential impact of the specific location of bird nest defects on the transmission line on its safe operation, and quickly locates and handles bird nest defects in high-risk areas. This provides solid data support for building a more accurate and reliable assessment system and assessment model, and helps to achieve intelligent management and maintenance of bird nest defects in transmission lines.

[0109] In one embodiment, before obtaining the data on bird nests on the transmission line to be evaluated, the method further includes: using the data on bird nest defects on the transmission line as training samples, and dividing the training samples into a training set and a test set; obtaining a pure data-driven evaluation model based on the training set; inputting the test set into the defect hazard level evaluation model and the pure data-driven evaluation model, and obtaining the evaluation accuracy and recall of the defect hazard level evaluation model and the pure data-driven evaluation model; calculating and comparing the scores of the defect hazard level evaluation model and the pure data-driven evaluation model based on the evaluation accuracy and recall; and optimizing the defect hazard level evaluation model when the scores meet preset conditions.

[0110] The preset condition is that the scores differ significantly. Precision is the proportion of correctly predicted samples out of the total number of samples. Recall, also known as recall or sensitivity, is a metric that measures the model's ability to identify all positive samples. The score is the model's F1 score, a metric used in machine learning to comprehensively evaluate model performance; it is the harmonic mean of precision and recall.

[0111] For example, constructing a sample library based on training samples includes: integrating data on bird nest defects in transmission lines and at least one defect feature data to form complete sample data; classifying the complete sample data according to the hazard level of bird nest defects, and storing it as training samples in a database or file management system.

[0112] Optionally, an object detection model can be used to detect the score difference between the defect hazard level assessment model and the pure data-driven assessment model. The object detection model can be a deep learning algorithm-improved object detection model (YOLO) or a masked region convolutional neural network instance segmentation model (Mask R-CNN).

[0113] For example, the training set is input into the untrained evaluation model for training to obtain a pure data-driven evaluation model; the test set is simultaneously input into the defect hazard level evaluation model and the pure data-driven evaluation model to obtain the evaluation accuracy and recall of the defect hazard level evaluation model and the pure data-driven evaluation model; based on the evaluation accuracy and recall, the F1 score of the defect hazard level evaluation model and the pure data-driven evaluation model is calculated; the difference between the F1 scores of the defect hazard level evaluation model and the pure data-driven evaluation model is detected using an object detection model; when the difference in F1 scores is large, the defect hazard level evaluation model is optimized based on the difference in F1 scores.

[0114] In this embodiment, data on bird nest defects in transmission lines are used as training samples, which are then divided into a training set and a test set. A pure data-driven evaluation model is obtained based on the training set. The test set is input into both the defect hazard level assessment model and the pure data-driven evaluation model to obtain their accuracy and recall. Based on the accuracy and recall, the scores of the two models are calculated and compared. When the scores meet preset conditions, the defect hazard level assessment model is optimized. This effectively evaluates the model's performance and allows for improvements based on the evaluation results, ensuring a more accurate and reliable assessment of the hazard level of bird nest defects in transmission lines. This provides strong support for subsequent intelligent management and maintenance.

[0115] In one embodiment, the method further includes: converting the hazard level of bird nest defects on transmission lines into a visual result, transmitting the visual result to a user terminal; receiving misjudged bird nest defects on transmission lines uploaded by the user terminal; and updating the hazard impact factor and its weight based on the misjudged bird nest defects on transmission lines.

[0116] The visualization results include, for example, heat maps and risk distribution.

[0117] For example, the hazard level of bird nest defects on transmission lines is transformed into a visual result and output to the user terminal. Maintenance personnel mark misjudgment cases of the hazard level of bird nest defects on transmission lines, and the expert rule base is iteratively optimized based on the misjudgment cases. Based on the expert rule base, the iteratively optimized expert knowledge is obtained. Based on the iteratively optimized expert knowledge, the hazard impact factors and their weights are updated.

[0118] In this embodiment, the hazard level of bird nest defects in transmission lines is transformed into a visual result, which is then transmitted to the user terminal. The system receives misjudgment labels of bird nest defects in transmission lines uploaded by the user terminal. Based on the misjudgment labels of bird nest defects in transmission lines, the system updates the hazard impact factors and their weights, thus realizing a feedback loop of expert knowledge. The system continues to optimize the performance of the evaluation model based on the feedback.

[0119] In one embodiment, the method further includes: generating corresponding recommended prevention and control measures and handling timelines based on the hazard level of bird nest defects in transmission lines; and pushing the recommended prevention and control measures and handling timelines to the user terminal.

[0120] The hazard level of bird nest defects on power transmission lines can be classified into 3 to 5 levels, such as low, medium, high, and emergency. Each hazard level has corresponding different response times and recommended prevention and control measures. Recommended prevention and control measures may include installing bird spikes and relocating nests.

[0121] For example, based on preset hazard levels, different handling timelines and recommended prevention and control measures are set accordingly. The system automatically generates handling timelines and recommended prevention and control measures corresponding to the hazard levels of bird nest defects on transmission lines, and pushes these timelines and recommended prevention and control measures to the user's inspection system. Upon receiving the information, the inspection system will trigger a drone re-inspection or manual verification work order based on the handling timelines and recommended prevention and control measures.

[0122] In this embodiment, by automatically generating corresponding recommended prevention and control measures and handling timelines based on the hazard level of bird nest defects in transmission lines, clear operational guidance can be provided to maintenance personnel, realizing the automatic generation of prevention and control measures.

[0123] Next reference Figure 3 The present invention will be illustrated by a specific embodiment of the method for assessing the hazard level of bird nest defects in transmission lines.

[0124] Step 1: Collect and process the data.

[0125] Collect image data, environmental data, and historical data, and perform data preprocessing on the collected data.

[0126] Step 2: Perform expert knowledge embedding and feature extraction.

[0127] Feature extraction is performed on the preprocessed data to obtain physical, electrical, and environmental features. Expert knowledge is quantified to determine hazard impact factors and their weights.

[0128] Step 3: Perform defect identification and obtain key defect information.

[0129] The at least one defect feature is compared with the standard defect feature to extract key information for identifying bird nest defects in transmission lines; based on the key information, a feature description of bird nest defects in transmission lines is obtained.

[0130] Step 4: Construct a hazard level assessment model.

[0131] Based on the characteristic description of the defect and the defined hazard impact factors and their weights, the assessment indicators and their weights for the bird nest defects of the transmission line are determined; based on the assessment indicators and their weights, a defect hazard level assessment model is constructed.

[0132] Step 5: Perform model cross-validation and optimization.

[0133] Using data on bird nest defects in transmission lines as training samples, the training samples are divided into training and test sets. Based on the training set, a pure data-driven evaluation model is obtained. The test set is input into both the defect hazard level evaluation model and the pure data-driven evaluation model to obtain their evaluation accuracy and recall. Based on the evaluation accuracy and recall, the F1 scores of the defect hazard level evaluation model and the pure data-driven evaluation model are calculated and compared. When the F1 scores differ significantly, the defect hazard level evaluation model is optimized.

[0134] Step 6: Conduct expert feedback closed-loop.

[0135] The hazard levels of bird nest defects on transmission lines are transformed into visual results, which are then transmitted to the user terminal. The system receives misclassified bird nest defect annotations uploaded by the user terminal and updates expert knowledge based on these annotations. Based on this updated expert knowledge, updated hazard impact factors and their weights can be obtained.

[0136] Step 7: Generate recommended prevention and control measures.

[0137] When acquiring data on bird nests on transmission lines to be evaluated, the features of this data are extracted, and the corresponding features are input into the defect hazard level assessment model to obtain the hazard level of the bird nest defect. The hazard level of the bird nest defect on the transmission lines is pre-determined to be classified into 3-5 hazard levels, and different corresponding handling timelines and recommended prevention and control measures are set for each hazard level.

[0138] Based on pre-set handling timelines and recommended prevention and control measures for each hazard level, the system automatically generates handling timelines and recommended prevention and control measures corresponding to the hazard level of bird nest defects on transmission lines and pushes them to the inspection system. Upon receiving the information, the inspection system triggers a work order for either drone re-inspection or manual verification.

[0139] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0140] Based on the same inventive concept, this application also provides a device for assessing the hazard level of bird nest defects in transmission lines, which is used to implement the aforementioned method for assessing the hazard level of bird nest defects in transmission lines. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the device for assessing the hazard level of bird nest defects in transmission lines provided below can be found in the limitations of the method for assessing the hazard level of bird nest defects in transmission lines described above, and will not be repeated here.

[0141] In one exemplary embodiment, such as Figure 4 As shown, a device 400 for assessing the hazard level of bird nest defects on power transmission lines is provided, comprising: an acquisition module 402, an extraction module 404, a comparison module 406, a construction module 408, and an assessment module 410, wherein:

[0142] The acquisition module 402 is used to acquire data on bird nest defects in transmission lines; and to determine the hazard impact factors and their weights based on expert knowledge.

[0143] The extraction module 404 is used to extract features from the bird nest defect data of the transmission line and obtain at least one defect feature.

[0144] The comparison module 406 is used to compare at least one defect feature with standard defect features to extract key information for identifying bird nest defects in transmission lines; and based on the key information, to obtain a feature description of bird nest defects in transmission lines.

[0145] Module 408 is used to determine the assessment indicators and their weights for bird nest defects in transmission lines based on feature descriptions, hazard impact factors and their weights; and to construct a defect hazard level assessment model based on the assessment indicators and their weights.

[0146] The assessment module 410 is used to acquire data on bird nests on the transmission line to be assessed; extract features from the data on bird nests on the transmission line to be assessed; input the features into the defect hazard level assessment model to obtain the hazard level of the bird nest defect on the transmission line.

[0147] In one embodiment, the acquisition module is further configured to collect bird nest image data, transmission line environmental data, and historical data; perform data preprocessing on the bird nest image data, transmission line environmental data, and historical data to obtain preprocessed bird nest image data, transmission line environmental data, and historical data; and use the preprocessed bird nest image data, transmission line environmental data, and historical data as transmission line bird nest defect data.

[0148] In one embodiment, the comparison module is further configured to establish, based on key information, a relationship model between the size of the bird's nest defect and the safety threat to the transmission line, a relationship model between the location of the bird's nest defect and the safety threat to the transmission line, and a relationship model between the bird's nest and surrounding power equipment; based on the relationship model between the size of the bird's nest defect and the safety threat to the transmission line, assess the degree of impact of the size of the bird's nest defect on the potential safety threat to the transmission line; based on the relationship model between the location of the bird's nest defect and the safety threat to the transmission line, assess the degree of potential threat posed by the bird's nest defect to the transmission line; based on the relationship model between the bird's nest and surrounding power equipment, determine the influence of each component of the transmission line circuit; and based on the degree of impact of the size of the bird's nest defect on the potential safety threat to the transmission line, the degree of potential threat posed by the bird's nest defect to the transmission line, and the influence of each component of the transmission line circuit, obtain a characteristic description of the bird's nest defect in the transmission line.

[0149] In one embodiment, the construction module is further configured to use data on bird nest defects in transmission lines as training samples, and divide the training samples into a training set and a test set; based on the training set, obtain a pure data-driven evaluation model; input the test set into the defect hazard level evaluation model and the pure data-driven evaluation model, and obtain the evaluation accuracy and recall of the defect hazard level evaluation model and the pure data-driven evaluation model; based on the evaluation accuracy and recall, calculate and compare the scores of the defect hazard level evaluation model and the pure data-driven evaluation model; when the scores meet preset conditions, optimize the defect hazard level evaluation model.

[0150] In one embodiment, the transmission line bird nest defect hazard level assessment device further includes a feedback module, which is used to convert the hazard level of the transmission line bird nest defect into a visual result, transmit the visual result to the user terminal, receive the misjudgment label of the transmission line bird nest defect uploaded by the user terminal, and update the hazard impact factor and its weight based on the misjudgment label of the transmission line bird nest defect.

[0151] In one embodiment, the feedback module is also used to generate corresponding recommended prevention and control measures and handling timelines based on the hazard level of bird nest defects in transmission lines; and push the recommended prevention and control measures and handling timelines to the user terminal.

[0152] Each module in the aforementioned power transmission line bird nest defect hazard level assessment device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0153] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for assessing the hazard level of bird nest defects on power transmission lines. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0154] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0155] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0156] Obtain data on bird nest defects on power transmission lines; determine the hazard impact factors and their weights based on expert knowledge;

[0157] Feature extraction is performed on the data of bird nest defects on power transmission lines to obtain at least one defect feature;

[0158] At least one defect feature is compared with standard defect features to extract key information for identifying bird nest defects in transmission lines; based on the key information, a feature description of bird nest defects in transmission lines is obtained.

[0159] Based on feature descriptions, hazard impact factors and their weights, the assessment indicators and their weights for bird nest defects in transmission lines are determined; based on the assessment indicators and their weights, a defect hazard level assessment model is constructed.

[0160] Obtain data on bird nests on the transmission lines to be evaluated; extract features from the bird nest data on the transmission lines to be evaluated, input the features into the defect hazard level assessment model, and obtain the hazard level of the bird nest defects on the transmission lines.

[0161] In one embodiment, when the processor executes the computer program, it further performs the following steps: collecting bird nest image data, transmission line environmental data, and historical data; performing data preprocessing on the bird nest image data, transmission line environmental data, and historical data to obtain preprocessed bird nest image data, transmission line environmental data, and historical data; and using the preprocessed bird nest image data, transmission line environmental data, and historical data as transmission line bird nest defect data.

[0162] In one embodiment, when the processor executes the computer program, it further performs the following steps: based on key information, establish a relationship model between the size of the bird's nest defect and the safety threat to the transmission line, a relationship model between the location of the bird's nest defect and the safety threat to the transmission line, and a relationship model between the bird's nest and surrounding power equipment; based on the relationship model between the size of the bird's nest defect and the safety threat to the transmission line, assess the degree of impact of the size of the bird's nest defect on the potential safety threat to the transmission line; based on the relationship model between the location of the bird's nest defect and the safety threat to the transmission line, assess the degree of potential threat posed by the bird's nest defect to the transmission line; based on the relationship model between the bird's nest and surrounding power equipment, determine the influence of each component of the transmission line circuit; based on the degree of impact of the size of the bird's nest defect on the potential safety threat to the transmission line, the degree of potential threat posed by the bird's nest defect to the transmission line, and the influence of each component of the transmission line circuit, obtain a characteristic description of the bird's nest defect in the transmission line.

[0163] In one embodiment, when the processor executes the computer program, it further performs the following steps: using data on bird nest defects in transmission lines as training samples, and dividing the training samples into a training set and a test set; obtaining a pure data-driven evaluation model based on the training set; inputting the test set into the defect hazard level evaluation model and the pure data-driven evaluation model, and obtaining the evaluation accuracy and recall of the defect hazard level evaluation model and the pure data-driven evaluation model; calculating and comparing the scores of the defect hazard level evaluation model and the pure data-driven evaluation model based on the evaluation accuracy and recall; and optimizing the defect hazard level evaluation model when the scores meet preset conditions.

[0164] In one embodiment, when the processor executes the computer program, it also performs the following steps: converting the hazard level of bird nest defects in transmission lines into a visual result, and transmitting the visual result to the user terminal; receiving misjudged bird nest defect labels uploaded by the user terminal; and updating the hazard impact factor and its weight based on the misjudged bird nest defect labels.

[0165] In one embodiment, when the processor executes the computer program, it also performs the following steps: generating corresponding recommended prevention and control measures and handling timelines based on the hazard level of bird nest defects in transmission lines; and pushing the recommended prevention and control measures and handling timelines to the user terminal.

[0166] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0167] Obtain data on bird nest defects on power transmission lines; determine the hazard impact factors and their weights based on expert knowledge;

[0168] Feature extraction is performed on the data of bird nest defects on power transmission lines to obtain at least one defect feature;

[0169] At least one defect feature is compared with standard defect features to extract key information for identifying bird nest defects in transmission lines; based on the key information, a feature description of bird nest defects in transmission lines is obtained.

[0170] Based on feature descriptions, hazard impact factors and their weights, the assessment indicators and their weights for bird nest defects in transmission lines are determined; based on the assessment indicators and their weights, a defect hazard level assessment model is constructed.

[0171] Obtain data on bird nests on the transmission lines to be evaluated; extract features from the bird nest data on the transmission lines to be evaluated, input the features into the defect hazard level assessment model, and obtain the hazard level of the bird nest defects on the transmission lines.

[0172] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: collecting bird nest image data, transmission line environmental data, and historical data; performing data preprocessing on the bird nest image data, transmission line environmental data, and historical data to obtain preprocessed bird nest image data, transmission line environmental data, and historical data; and using the preprocessed bird nest image data, transmission line environmental data, and historical data as transmission line bird nest defect data.

[0173] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: based on key information, establishing a relationship model between the size of the bird's nest defect and the safety threat to the transmission line, a relationship model between the location of the bird's nest defect and the safety threat to the transmission line, and a relationship model between the bird's nest and surrounding power equipment; based on the relationship model between the size of the bird's nest defect and the safety threat to the transmission line, assessing the degree of impact of the size of the bird's nest defect on the potential safety threat to the transmission line; based on the relationship model between the location of the bird's nest defect and the safety threat to the transmission line, assessing the degree of potential threat posed by the bird's nest defect to the transmission line; based on the relationship model between the bird's nest and surrounding power equipment, determining the influence of each component of the transmission line circuit; and based on the degree of impact of the size of the bird's nest defect on the potential safety threat to the transmission line, the degree of potential threat posed by the bird's nest defect to the transmission line, and the influence of each component of the transmission line circuit, obtaining a characteristic description of the bird's nest defect in the transmission line.

[0174] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: using data on bird nest defects in transmission lines as training samples, and dividing the training samples into a training set and a test set; obtaining a pure data-driven evaluation model based on the training set; inputting the test set into the defect hazard level evaluation model and the pure data-driven evaluation model, and obtaining the evaluation accuracy and recall of the defect hazard level evaluation model and the pure data-driven evaluation model; calculating and comparing the scores of the defect hazard level evaluation model and the pure data-driven evaluation model based on the evaluation accuracy and recall; and optimizing the defect hazard level evaluation model when the scores meet preset conditions.

[0175] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: converting the hazard level of bird nest defects in transmission lines into a visual result, and transmitting the visual result to the user terminal; receiving misjudged bird nest defect labels uploaded by the user terminal; and updating the hazard impact factor and its weight based on the misjudged bird nest defect labels.

[0176] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: generating corresponding recommended prevention and control measures and handling timelines based on the hazard level of bird nest defects in transmission lines; and pushing the recommended prevention and control measures and handling timelines to the user terminal.

[0177] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0178] Obtain data on bird nest defects on power transmission lines; determine the hazard impact factors and their weights based on expert knowledge;

[0179] Feature extraction is performed on the data of bird nest defects on power transmission lines to obtain at least one defect feature;

[0180] At least one defect feature is compared with standard defect features to extract key information for identifying bird nest defects in transmission lines; based on the key information, a feature description of bird nest defects in transmission lines is obtained.

[0181] Based on feature descriptions, hazard impact factors and their weights, the assessment indicators and their weights for bird nest defects in transmission lines are determined; based on the assessment indicators and their weights, a defect hazard level assessment model is constructed.

[0182] Obtain data on bird nests on the transmission lines to be evaluated; extract features from the bird nest data on the transmission lines to be evaluated, input the features into the defect hazard level assessment model, and obtain the hazard level of the bird nest defects on the transmission lines.

[0183] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: collecting bird nest image data, transmission line environmental data, and historical data; performing data preprocessing on the bird nest image data, transmission line environmental data, and historical data to obtain preprocessed bird nest image data, transmission line environmental data, and historical data; and using the preprocessed bird nest image data, transmission line environmental data, and historical data as transmission line bird nest defect data.

[0184] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: based on key information, establishing a relationship model between the size of the bird's nest defect and the safety threat to the transmission line, a relationship model between the location of the bird's nest defect and the safety threat to the transmission line, and a relationship model between the bird's nest and surrounding power equipment; based on the relationship model between the size of the bird's nest defect and the safety threat to the transmission line, assessing the degree of impact of the size of the bird's nest defect on the potential safety threat to the transmission line; based on the relationship model between the location of the bird's nest defect and the safety threat to the transmission line, assessing the degree of potential threat posed by the bird's nest defect to the transmission line; based on the relationship model between the bird's nest and surrounding power equipment, determining the influence of each component of the transmission line circuit; and based on the degree of impact of the size of the bird's nest defect on the potential safety threat to the transmission line, the degree of potential threat posed by the bird's nest defect to the transmission line, and the influence of each component of the transmission line circuit, obtaining a characteristic description of the bird's nest defect in the transmission line.

[0185] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: using data on bird nest defects in transmission lines as training samples, and dividing the training samples into a training set and a test set; obtaining a pure data-driven evaluation model based on the training set; inputting the test set into the defect hazard level evaluation model and the pure data-driven evaluation model, and obtaining the evaluation accuracy and recall of the defect hazard level evaluation model and the pure data-driven evaluation model; calculating and comparing the scores of the defect hazard level evaluation model and the pure data-driven evaluation model based on the evaluation accuracy and recall; and optimizing the defect hazard level evaluation model when the scores meet preset conditions.

[0186] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: converting the hazard level of bird nest defects in transmission lines into a visual result, and transmitting the visual result to the user terminal; receiving misjudged bird nest defect labels uploaded by the user terminal; and updating the hazard impact factor and its weight based on the misjudged bird nest defect labels.

[0187] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: generating corresponding recommended prevention and control measures and handling timelines based on the hazard level of bird nest defects in transmission lines; and pushing the recommended prevention and control measures and handling timelines to the user terminal.

[0188] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0189] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0190] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0191] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for assessing the hazard level of a bird nest defect of a power transmission line, characterized by, The method includes: Obtain data on bird nest defects on power transmission lines; determine the hazard impact factors and their weights based on expert knowledge; Feature extraction is performed on the bird nest defect data of the transmission line to obtain at least one defect feature; The at least one defect feature is compared with the standard defect feature to extract key information for identifying bird nest defects in transmission lines; based on the key information, a feature description of the bird nest defects in transmission lines is obtained. Based on the feature description, the hazard impact factors and their weights, the assessment indicators and their weights for the bird nest defects of the transmission line are determined; based on the assessment indicators and their weights, a defect hazard level assessment model is constructed. Obtain data on bird nests on the transmission line to be evaluated; extract features from the bird nest data on the transmission line to be evaluated, input the features into the defect hazard level assessment model, and obtain the hazard level of the bird nest defect on the transmission line.

2. The method of claim 1, wherein, The acquisition of data on bird nest defects in transmission lines includes: Collect images of bird nests, environmental data of power transmission lines, and historical data; The bird nest image data, power transmission line environmental data, and historical data are preprocessed to obtain preprocessed bird nest image data, power transmission line environmental data, and historical data; the preprocessed bird nest image data, power transmission line environmental data, and historical data are used as bird nest defect data for power transmission lines.

3. The method of claim 1, wherein, The process of obtaining a characteristic description of bird nest defects on transmission lines based on the aforementioned key information includes: Based on the aforementioned key information, establish a relationship model between the size of the bird's nest defect and the safety threat to the transmission line, a relationship model between the location of the bird's nest defect and the safety threat to the transmission line, and a relationship model between the bird's nest and surrounding power equipment; Based on the relationship model between the size of bird nest defects and the safety threat to transmission lines, the impact of the size of bird nest defects on the potential safety threat to transmission lines is assessed. Based on the relationship model between the location of the bird's nest defect and the safety threat to the transmission line, the potential threat level of the bird's nest defect to the transmission line is assessed. Based on the relationship model between the bird's nest and the surrounding power equipment, the influence of each component of the transmission circuit is determined. Based on the impact of the size of the bird nest defect on the potential safety threat of the transmission line, the potential threat of the bird nest defect to the transmission line, and the influence of various components of the transmission line circuit, a characteristic description of the bird nest defect in the transmission line is obtained.

4. The method of claim 1, wherein, Before obtaining the bird nest data for the transmission line to be evaluated, the process also includes: The data on bird nest defects in the transmission lines were used as training samples, and the training samples were divided into a training set and a test set. Based on the training set, a pure data-driven evaluation model is obtained; The test set is input into the defect hazard level assessment model and the pure data-driven assessment model to obtain the assessment accuracy and recall of the defect hazard level assessment model and the pure data-driven assessment model. Based on the accuracy and recall of the assessment, the scores of the defect hazard level assessment model and the pure data-driven assessment model are calculated and compared; when the scores meet the preset conditions, the defect hazard level assessment model is optimized.

5. The method of claim 1, wherein, The method further includes: The hazard level of the bird nest defect in the transmission line is converted into a visual result, and the visual result is transmitted to the user terminal. Receive and label misjudged defects of bird nests on power transmission lines uploaded by users; Based on the misjudgment labeling of bird nest defects on the transmission line, the hazard impact factor and its weight are updated.

6. The method of claim 1, wherein, The method further includes: Based on the hazard level of the bird nest defects in the transmission lines, corresponding recommended prevention and control measures and response timelines are generated. The recommended prevention and control measures and their response timelines will be pushed to the user's device.

7. A device for assessing the hazard level of a bird nest defect of a power transmission line, characterized by The device includes: The acquisition module is used to acquire data on bird nest defects in transmission lines; based on expert knowledge, it determines the hazard impact factors and their weights. The extraction module is used to extract features from the bird nest defect data of the transmission line to obtain at least one defect feature; The comparison module is used to compare the at least one defect feature with standard defect features to extract key information for identifying bird nest defects in transmission lines; and to obtain a feature description of bird nest defects in transmission lines based on the key information. A construction module is used to determine the assessment indicators and their weights for the bird nest defects of the transmission line based on the feature description, the hazard impact factors and their weights; and to construct a defect hazard level assessment model based on the assessment indicators and their weights. The assessment module is used to acquire data on bird nests on the transmission line to be assessed; extract features from the bird nest data on the transmission line to be assessed; input the features into the defect hazard level assessment model to obtain the hazard level of the bird nest defect on the transmission line.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images