Method, system and equipment for predicting state of power transmission line after ice coating and ice melting, and medium

Abstract

The invention relates to the technical field of icing prediction, and discloses a state prediction method, system, equipment and medium after icing and ice melting of a power transmission line, and the method comprises the steps: obtaining the target data of a target power transmission line, and carrying out the preprocessing, thereby guaranteeing the accuracy and reliability of the data, and providing a solid foundation for the subsequent model building. The post-ice-melting icing state prediction model established based on the pre-processed target data can accurately predict the post-ice-melting icing state, and an important decision basis is provided for operation and maintenance personnel. The establishment of the risk assessment model enables the operation and maintenance personnel to quantitatively assess the risk level of the prediction result of the icing state after ice melting, thereby making an anti-icing operation and maintenance strategy more scientifically. According to the method, the accuracy and scientificity of state prediction after ice coating and ice melting of the power transmission line are improved, powerful technical support is provided for anti-icing operation and maintenance work, and the power transmission line fault risk caused by ice coating is effectively reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ice coating prediction, and in particular to a method, system, device and medium for predicting the state of a transmission line after ice coating melting. BACKGROUND

[0002] With the continuous expansion of the power grid scale and the in-depth promotion of power infrastructure construction in high-cold regions, the problem of transmission line ice coating is increasingly prominent, which seriously threatens the safe and stable operation of the power grid. Ice coating can lead to increased conductor load, increased mechanical tension, increased insulator flashover risk, and even cause serious accidents such as wire breakage and tower collapse. Currently, the power system uses ice melting operations to deal with the problem of transmission line ice coating, but the changes in the state of the line after ice melting and the potential risks are difficult to accurately assess, resulting in a lack of scientific basis for developing anti-icing operation and maintenance strategies, low operation and maintenance efficiency, and limited disaster prevention and mitigation capabilities.

[0003] Currently, the transmission line ice coating monitoring method based on artificial observation is a relatively common traditional solution in the industry. This method mainly relies on artificial field patrol, fixed ice observation point observation, and simple meteorological data analysis to evaluate the ice coating condition and develop an ice melting plan. This method has many shortcomings: first, artificial observation is greatly influenced by subjective factors, and the accuracy of the data is difficult to guarantee; second, the observation frequency is limited, and continuous monitoring of the ice coating state cannot be achieved; third, the prediction of the line state after ice melting relies only on experience, and lacks quantitative analysis of the relationship between changes in micro-meteorological factors and the dynamic evolution of ice coating; and finally, the anti-icing operation and maintenance strategy is a standardized and static solution, and cannot be differentiated and dynamically adjusted according to the specific conditions and risk levels of the line, resulting in unreasonable resource allocation and problems such as excessive maintenance and monitoring blind spots. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides a method, system, device and medium for predicting the state of a transmission line after ice coating melting, which can solve the problem of inaccurate line state prediction and unreasonable operation and maintenance strategy in the prior art.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a method for predicting the state of a transmission line after ice coating melting, comprising:

[0008] acquiring target data of a target transmission line and pre-processing the target data;

[0009] The target data includes transmission line ice coating state monitoring data, ice melting operation parameter data, and meteorological prediction data.

[0010] The ice-melting post-icing state prediction model is established based on the pretreated target data;

[0011] The ice-melting post-icing state prediction model is obtained according to an icing growth model and an ice-melting efficiency model;

[0012] The icing growth model is established based on ice-melting operation parameter data;

[0013] The ice-melting efficiency model is established based on meteorological prediction data;

[0014] A risk assessment model based on the ice-melting post-icing state prediction model is established, and the risk assessment model is used to assess a risk level of an ice-melting post-icing state prediction result;

[0015] An anti-icing operation and maintenance strategy is generated according to the risk level.

[0016] As a preferred scheme of the power transmission line ice-melting post-icing state prediction method, the risk assessment model based on the ice-melting post-icing state prediction model comprises:

[0017] A plurality of dimensions related to the ice-melting post-icing state prediction model are selected;

[0018] A plurality of dimension indexes representing the plurality of dimensions are established;

[0019] A comprehensive risk assessment model is established based on the plurality of dimension indexes.

[0020] As a preferred scheme of the power transmission line ice-melting post-icing state prediction method, the anti-icing operation and maintenance strategy generation according to the risk level comprises:

[0021] An operation and maintenance strategy vector is established, and the operation and maintenance strategy vector comprises a plurality of operation and maintenance key parameters;

[0022] Specific values of the operation and maintenance strategy vector are determined according to the risk level;

[0023] The anti-icing operation and maintenance strategy is generated according to the operation and maintenance strategy vector.

[0024] As a preferred scheme of the power transmission line ice-melting post-icing state prediction method, the ice-melting post-icing state prediction model comprises an icing growth model and an ice-melting efficiency model;

[0025] The icing growth model is established by obtaining a growth rate of an icing thickness under specific meteorological conditions;

[0026] The specific meteorological conditions are meteorological conditions under a numerically fixed wind speed, temperature and humidity;

[0027] The ice melting efficiency model includes efficiency functions, ice melting current or power values, ice melting duration, and correction functions related to ice melting completion time and ice thickness before ice melting under different ice melting device types and ice melting modes.

[0028] The preferred scheme can comprehensively consider the two key factors of ice growth and ice melting efficiency, and improve the accuracy and practicability of the prediction model. The ice growth model can accurately predict the ice growth under different environments by modeling the growth rate of ice thickness under specific meteorological conditions. The ice melting efficiency model can more accurately evaluate the ice melting effect and required resources by considering different ice melting device types, ice melting modes, and related efficiency functions and correction functions.

[0029] As a preferred scheme of the transmission line ice melting state prediction method, the comprehensive risk assessment model includes:

[0030] The output of the comprehensive risk assessment model is scored;

[0031] The risk level division interval is established for the scored results.

[0032] As a preferred scheme of the transmission line ice melting state prediction method, the target data of the target transmission line is obtained and preprocessed, including:

[0033] The target data of the target transmission line includes image type data, time series data, and meteorological type data related to the target transmission line; the preprocessing includes:

[0034] For image type data, image enhancement, denoising, and feature extraction algorithms are used;

[0035] For time series data, trend analysis and periodicity analysis methods are used;

[0036] For meteorological type data, spatial interpolation and time standardization processing are performed.

[0037] As a preferred scheme of the transmission line ice melting state prediction method, the preprocessing further includes:

[0038] Define the ice melting parameter vector and the micro-meteorological parameter vector;

[0039] The ice melting parameter vector includes ice melting device type, ice melting mode, ice melting current or power value, ice melting duration, and ice melting completion time;

[0040] The microclimate parameter vector comprises environmental temperature, relative humidity, wind speed, wind direction, and precipitation. In a second aspect, the present application provides a transmission line icing-melting post-state prediction system, comprising:

[0041] A data processing module is configured to acquire target data of a target transmission line and pre-process the target data.

[0042] The target data comprises transmission line icing state monitoring data, ice-melting operation parameter data, and meteorological prediction data.

[0043] A first model establishing module is configured to establish an icing-melting post-state prediction model based on the pre-processed target data.

[0044] The icing-melting post-state prediction model is obtained according to an icing growth model and an ice-melting efficiency model.

[0045] The icing growth model is established based on the ice-melting operation parameter data.

[0046] The ice-melting efficiency model is established based on the meteorological prediction data.

[0047] A second model establishing module is configured to establish a risk assessment model based on the icing-melting post-state prediction model, and the risk assessment model is configured to assess a risk level of the icing-melting post-state prediction result.

[0048] A strategy obtaining module is configured to generate an anti-icing operation and maintenance strategy according to the risk level.

[0049] In a third aspect, the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method as described above when executing the computer program.

[0050] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the method as described above when executed by a processor.

[0051] Compared with the prior art, the present application has the beneficial effects that: the present application provides a method for predicting the state of the transmission line after ice melting, by obtaining the target data of the target transmission line and preprocessing, the accuracy and reliability of the data are ensured, and a solid foundation is provided for subsequent model establishment. The ice melting state prediction model established based on the preprocessed target data can accurately predict the ice melting state, providing an important decision basis for operation and maintenance personnel. The establishment of the risk assessment model enables operation and maintenance personnel to quantitatively evaluate the risk level of the ice melting state prediction result, so as to more scientifically formulate the anti-icing operation and maintenance strategy. The present application improves the accuracy and scientificity of the state prediction of the transmission line after ice melting, provides strong technical support for anti-icing operation and maintenance work, and effectively reduces the risk of transmission line failure caused by ice. BRIEF DESCRIPTION OF DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0053] Figure 1 The method flow chart of the method for predicting the state of the transmission line after ice melting provided by an embodiment of the present application.

[0054] Figure 2 The internal structure diagram of the electronic device for predicting the state of the transmission line after ice melting provided by an embodiment of the present application. DETAILED DESCRIPTION

[0055] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings in the specification. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0056] Embodiment 1, refer to Figure 1 For the first embodiment of the present application, the embodiment provides a method for predicting the state of the transmission line after ice melting, comprising:

[0057] In the prior art, there are some problems, for example, the prediction and monitoring of power line icing usually rely on traditional meteorological data and manual inspection, which is not only inefficient, but also difficult to accurately reflect the real-time state of the power line. Especially in extreme weather conditions, manual inspection is not only dangerous, but also difficult to ensure the accuracy and timeliness of the data. In addition, the existing ice melting technology and equipment also have shortcomings in predicting the state of the line after ice melting, which cannot accurately predict the stability and safety of the line after ice melting, bringing certain risks to the stable operation of the power system.

[0058] The present application provides a method that can effectively solve the above-mentioned problems, and the following will be described in detail how to realize the power line icing after ice melting state prediction method combined with multiple embodiments;

[0059] As Figure 1 shown, the method as a specific example of the method of claim 1, the flow chart includes the following steps:

[0060] S101, obtaining the target data of the target power line, and preprocessing the target data;

[0061] It should be noted that in the prior art, whether there is still icing after ice melting is mostly dependent on manual inspection, which is not only inefficient but also has safety hazards. Some existing technologies select the method originally used for icing detection for icing detection after ice melting. It should be noted that the icing detection method generally has low accuracy and constraints on the identification of icing, such as the thickness must be greater than a certain value to accurately identify the size or state, so there is a lack of a method that can directly judge the state after ice melting.

[0062] The present application provides a method for predicting the state of a power line after ice melting, which can effectively solve the above-mentioned problems, and the following will be described in detail how to realize the power line icing after ice melting state prediction method combined with multiple embodiments;

[0063] In some specific embodiments, when predicting the state of a power line after ice melting, certain target data is needed to obtain the final regularity or model.

[0064] In the embodiments of the present application, the target data includes power line icing state monitoring data, ice melting operation parameter data and meteorological prediction data;

[0065] In some specific embodiments, terminal device data, terminal photo data, terminal running defect data, meteorological data, ice melting state table, conductor tension data, ice melting plan and ice thickness data, etc. can be obtained from the mass platform. This data fusion method breaks through the limitations of traditional single data source, and makes the ice cover state evaluation and prediction based on multi-dimensional data, significantly improving the reliability and accuracy. Real-time data acquisition can also be achieved through the Internet of Things sensor network. For ice monitoring, optical sensors, tension sensors, micro-meteorological sensors and other devices are deployed to form a comprehensive monitoring network. At the same time, the fine weather forecast data for the next 48 hours provided by the meteorological department is accessed to provide weather basis for subsequent prediction. In addition, historical ice melting operation parameters and effect evaluation results are integrated to provide rich historical samples for model training.

[0066] In the embodiments of the present application, the target data of the target power transmission line is obtained, and the target data is preprocessed, including:

[0067] The target data of the target power transmission line includes image type data, time series data and meteorological type data related to the target power transmission line; the preprocessing includes:

[0068] For image type data, image enhancement, denoising and feature extraction algorithms are used;

[0069] For time series data, trend analysis and periodicity analysis methods are used;

[0070] For meteorological type data, spatial interpolation and time standardization processing are performed.

[0071] In some specific embodiments, for image type data, the detailed steps of using image enhancement, denoising and feature extraction algorithms are, for example

[0072] First, the image is enhanced by improving the contrast, brightness and sharpness of the image, etc. so that the key information in the image is more prominent, which is convenient for subsequent processing.

[0073] Next, a denoising algorithm is used to remove noise and interference information in the image to ensure the quality of the image.

[0074] Finally, a feature extraction algorithm is used to extract key features related to the ice cover state of the target power transmission line from the enhanced and denoised image, such as ice thickness, shape, area, etc. to provide strong data support for subsequent model training and prediction.

[0075] In the image processing flow of the embodiment, for the images collected from the alpine mountainous area, there are often problems of uneven illumination and low contrast, and the adaptive histogram equalization (AHE) algorithm is selected for image enhancement. The algorithm can effectively improve the local contrast of the image, so that the edge profile of the icing is more clear and identifiable in the complex background. After enhancement processing, Gaussian filtering is used for image denoising processing to smooth the fine noise caused by weather (such as fog and snow), while the edge information of the icing is well preserved. In the feature extraction stage, the Canny edge detection algorithm is used to accurately identify the edge of the icing, and then the Hough Transform is combined to fit the conductor profile and calculate the equivalent thickness of the icing. The combined algorithm has good robustness and accuracy for the identification of irregularly shaped icing.

[0076] In the embodiment of the application, the preprocessing further includes:

[0077] Defining an ice melting parameter vector and a micro-meteorological parameter vector;

[0078] The ice melting parameter vector includes an ice melting device type, an ice melting mode, an ice melting current or power value, an ice melting duration, and an ice melting completion time;

[0079] The micro-meteorological parameter vector includes an environmental temperature, a relative humidity, a wind speed, a wind direction, and a precipitation.

[0080] Specifically, for the ice melting operation parameters, an ice melting parameter vector D is defined:

[0081] D=[q1,q2,q3,q4,q5]

[0082] Wherein, q1 represents the ice melting device type (direct current ice melting, alternating current ice melting, etc.), q2 represents the ice melting mode (constant current mode, constant power mode, etc.), q3 represents the ice melting current or power value, q4 represents the ice melting duration, and q5 represents the ice melting completion time. These parameters directly affect the effect of ice melting and are key factors for predicting the icing state after ice melting.

[0083] For the meteorological prediction data, a micro-meteorological parameter vector M(t) is defined:

[0084] M(t)=[p1(t),p2(t),p3(t),p4(t),p5(t)]

[0085] Wherein, p1(t) represents the environmental temperature, p2(t) represents the relative humidity, p3(t) represents the wind speed, p4(t) represents the wind direction, and p5(t) represents the precipitation. These micro-meteorological factors jointly determine the new icing formation condition after ice melting and are crucial for predicting the future icing state.

[0086] To better illustrate the present application, the following will be described with a 500kV power transmission line located in an alpine region as a specific application scenario. An online monitoring device integrating a high-definition camera, a conductor tension sensor, and a micro-meteorological sensor is deployed on this line. Meanwhile, the system also accesses the ice-melting operation scheduling database of the power grid company and the refined weather forecasting system of the regional meteorological center.

[0087] In this scenario, the specific process of obtaining target data is as follows:

[0088] 1. Ice-coated state monitoring data of the power transmission line: Through the high-definition camera on the line, images of the conductor and insulator string are taken at regular intervals (e.g., every 30 minutes). These images directly reflect the shape and thickness of the ice coating; through the tension sensor, continuous data of the tension change of the conductor (e.g., the tension value rises from the normal 20kN to 35kN after icing) is collected. Through the inclination sensor, the offset angle of the insulator string is obtained.

[0089] 2. Ice-melting operation parameter data: Historical and planned ice-melting operation records are obtained from the power grid ice-melting operation scheduling database, which constitutes the ice-melting parameter vector, for example:

[0090] Ice-melting device type: direct current ice melting;

[0091] Ice-melting mode: constant current;

[0092] Ice-melting current: 1200A;

[0093] Ice-melting duration: 45 minutes;

[0094] Ice-melting completion time: 2023-01-10 08:00.

[0095] 3. Weather forecast data: From the regional meteorological center, obtain the refined weather forecast for the next 48 hours, including temperature, humidity, wind speed, wind direction, and precipitation, which constitutes the micro-meteorological parameter vector.

[0096] After obtaining the data, the preprocessing steps are as follows:

[0097] For image data: First, use the adaptive histogram equalization algorithm to enhance the image contrast, making the ice coating edge clearer; then use Gaussian filtering to remove image noise; finally, use feature extraction algorithms such as Canny edge detection and Hough transform to automatically calculate the equivalent thickness, unevenness, and other features of the ice coating from the image.

[0098] For time series data such as tension and inclination: Use the moving average method for smoothing and trend analysis to identify the abnormal growth rate of tension caused by icing.

[0099] For meteorological data: Kriging spatial interpolation is performed on the data obtained from different weather stations to obtain accurate meteorological parameters of the target line segment, and time standardization processing is performed.

[0100] It should be noted that obtaining the target data of the target transmission line and preprocessing the target data can improve the accuracy and availability of the data, providing strong support for subsequent establishment of a prediction model. By enhancing, denoising and feature extraction on image type data, key information can be highlighted, noise interference can be removed, and key features related to the icing state of the target transmission line can be extracted. Trend analysis and periodic analysis of time series data can reveal the change law and periodic characteristics of the data, which is helpful for predicting future icing states. Spatial interpolation and time standardization processing of meteorological type data can eliminate spatial and temporal differences, improve the comparability and consistency of the data. At the same time, the definition of the deicing parameter vector and the micro-meteorological parameter vector can quantitatively describe the key parameters of deicing operation and meteorological conditions, providing accurate input information for subsequent model training and prediction.

[0101] S102, a deicing post-icing state prediction model is established based on the preprocessed target data;

[0102] It should be noted that in order to realize the final icing state prediction, a prediction model or a prediction mapping function or other related logical framework that can obtain the final prediction state through the target data needs to be established.

[0103] In some specific embodiments, machine learning algorithms, deep learning models or traditional statistical models can be selected as the basis of the prediction model. Machine learning algorithms such as support vector machines and random forests can learn the rules in historical data to predict future icing states. Deep learning models such as convolutional neural networks and recurrent neural networks can automatically extract high-level features from data and are suitable for processing complex images and time series data. Traditional statistical models such as linear regression and time series analysis are suitable for revealing linear relationships and periodic characteristics of data. By selecting appropriate prediction models and combining preprocessed target data, accurate prediction of deicing post-icing state can be achieved.

[0104] In some specific embodiments, a prediction mapping function can also be established, which is used to map the preprocessed target data to the prediction result of the deicing post-icing state. This function has learned the complex relationship between the icing state and the deicing operation parameters and the meteorological conditions through training a large amount of historical data, so that it can quickly and accurately give the prediction result when new data is input. The establishment of the prediction mapping function not only improves the prediction accuracy, but also greatly shortens the prediction time, providing strong support for real-time scheduling and operation and maintenance of power systems.

[0105] In some specific embodiments, linear or non-linear functions can also be used for prediction.

[0106] In the embodiments of the present application, on the basis of data preprocessing, the present application constructs a prediction model of ice coating state change 48 hours after ice melting. The model considers the comprehensive influence of ice melting operation parameters and meteorological prediction data on ice coating state change. The core idea of the prediction model is to model the ice melting process and the ice coating formation process as a whole system, considering the dynamic balance relationship between the two. In practical application, ice melting operation will change the physical state of the conductor surface, including temperature distribution, surface characteristics, etc., which will affect the formation conditions and rate of subsequent ice coating. At the same time, the change of meteorological conditions after ice melting is also a key factor affecting the formation of new ice coating. Therefore, the prediction model needs to consider these complex influencing factors comprehensively.

[0107] In the embodiments of the present application, the ice coating state prediction model after ice melting is obtained according to an ice coating growth model and an ice melting efficiency model;

[0108] In the embodiments of the present application, the ice coating growth model is established based on ice melting operation parameter data;

[0109] In the embodiments of the present application, the ice melting efficiency model is established based on meteorological prediction data;

[0110] Specifically, first, an ice coating growth model is established. In the case where no ice melting operation is performed, the growth rate v g (t) of ice coating thickness under a specific meteorological condition can be represented as:

[0111]

[0112] Wherein, η is the ice collection coefficient, ρ w is the liquid water density, ρ i is the ice density, and ω(p1(t), p2(t)) is the liquid water content function under temperature and humidity conditions. The model is based on physical mechanism and considers the influence of wind speed, temperature, humidity and other factors on ice coating growth.

[0113] Based on ice melting operation parameters, the present application establishes an ice melting efficiency model. Through analysis of a large amount of historical ice melting operation data, the model summarizes the influence law of different ice melting device types, ice melting modes, ice melting parameters on ice coating thickness reduction. Research shows that the ice melting effect is not only related to the ice melting current or power, but also closely related to the ice melting duration, ice coating thickness before ice melting, environmental temperature and other factors. Therefore, the present application adopts a multi-factor comprehensive evaluation method to establish a quantitative calculation model of ice melting efficiency. The ice coating thickness reduction Δh m caused by ice melting operation can be represented as:

[0114] Δhm = f d (q1, q2) · q3 · q4 · g(q5, h b )

[0115] where f d (q1, q2) is the performance function under different de-icing device types and de-icing modes, and g(q5, h b ) is the correction function related to the de-icing completion time and the ice thickness h b before de-icing. This model fully considers the complex influencing factors of de-icing effect in actual engineering, and can accurately evaluate the actual effect of de-icing operation.

[0116] In some specific embodiments, during the model training process, historical de-icing operation data and ice monitoring data are used to optimize the model parameters through machine learning methods. Gradient boosting decision tree (GBDT), random forest and other algorithms are used to improve the generalization ability and prediction accuracy of the model. At the same time, a model verification mechanism is designed to evaluate the model performance through cross-validation and independent test set, ensuring the reliability of the model in actual application.

[0117] In the embodiments of the present application, the post-de-icing ice state prediction model includes an ice growth model and a de-icing performance model.

[0118] The ice growth model is established by obtaining the growth rate of ice thickness under specific meteorological conditions.

[0119] The specific meteorological conditions are meteorological conditions under fixed numerical wind speed, temperature and humidity.

[0120] The de-icing performance model includes performance functions under different de-icing device types and de-icing modes, de-icing current or power values, de-icing duration, and correction functions related to de-icing completion time and ice thickness before de-icing.

[0121] In combination with de-icing performance and subsequent meteorological conditions, the present application constructs a post-de-icing ice state prediction model. The model uses time series analysis method, considers the ice accumulation and natural shedding balance, and the differences in ice formation mechanism under different meteorological conditions, and has strong adaptability and robustness.

[0122] In some specific embodiments, for any time t+τ (τ∈[0, 45h]) after de-icing is completed, the predicted ice thickness h p (t+τ) is:

[0123]

[0124] This model represents the ice thickness after melting as the thickness before melting minus the melting reduction, plus the newly formed ice thickness, fully reflecting the dynamic change process of ice. Among them, the integral term represents the newly formed ice thickness from the completion of melting to the prediction time, which is solved by numerical integration method.

[0125] In order to improve the prediction accuracy, the present application also introduces an online learning and adaptive adjustment mechanism. By continuously collecting actual ice monitoring data and comparing it with the prediction results, the distribution characteristics and variation law of the prediction error are analyzed, and the model parameters and prediction strategy are adjusted in time, so that the prediction result is more accurate. This closed-loop feedback mechanism enables the model to have self-learning and optimization capabilities, and can adapt to the ice prediction needs of different lines and different weather conditions.

[0126] In some specific embodiments, the operation of introducing online learning and adaptive adjustment mechanism for optimization can be as follows:

[0127] First, set an initial set of prediction model parameters, including but not limited to ice growth rate, melting rate, and new ice formation condition threshold, etc. At the beginning of the prediction period, according to the current line state, weather conditions and historical data, the initial parameter set is used to make the first ice thickness prediction.

[0128] Subsequently, real-time or periodic collection of actual ice monitoring data of the transmission line, which may come from sensors installed on the line, such as weight sensors, image recognition sensors, etc. The collected data will be compared with the prediction results to generate prediction errors.

[0129] Next, these prediction errors are analyzed in depth to identify the distribution characteristics of the errors, such as whether they show some regularity, whether they are affected by certain factors, etc. At the same time, monitor the error trend to determine whether the error is gradually decreasing or increasing, and how fast the change is.

[0130] Based on these analysis results, the parameters of the prediction model are adaptively adjusted. If the error analysis shows that the prediction result is generally low, increase the parameter value of the ice growth rate; if the error shows that the prediction result is high, then the corresponding parameter value may be reduced. This adjustment is dynamic, aiming to make the prediction result closer to the actual ice situation.

[0131] In addition, according to the results of error analysis, the prediction strategy is optimized. For example, if it is found that the prediction error is large under certain weather conditions, a more detailed prediction model or an increased data collection frequency can be used under that condition.

[0132] Through the above online learning and adaptive adjustment mechanism, the prediction accuracy can be continuously improved, and the icing prediction demand under different lines and different weather conditions can be better adapted. The ability of continuous optimization makes the method have higher reliability and practicality in actual application.

[0133] In the application scenario, the establishment of the prediction model is divided into two parts:

[0134] Firstly, an icing growth model is established. By analyzing historical monitoring data, the present invention finds that in the mountainous environment where the line is located, under the specific weather conditions of wind speed of 5 m / s, temperature of-3℃ and humidity of 95%, the average growth rate of icing thickness is about 2 mm / h. Based on such data, a functional relationship between the icing growth rate and the micro-meteorological parameter vector is established.

[0135] Secondly, an ice melting efficiency model is established. By analyzing historical ice melting operation data, the present invention obtains the ice melting effect under different ice melting parameters. For example, for 15 mm thick icing, in a-5℃ environment, using 1200A direct current ice melting for 45 minutes, the icing can be basically eliminated. The model takes into account factors such as ice melting device type, current, duration and icing thickness before ice melting, and forms an efficiency function. According to the newly added icing thickness predicted by the weather forecast data.

[0136] It should be noted that the establishment of the post-icing icing state prediction model based on the preprocessed target data can significantly improve the accuracy and reliability of the prediction results. By preprocessing the target data, noise and outliers in the data can be eliminated, improving the quality of the data. At the same time, preprocessing can also standardize and normalize the data, so that data of different sources and different scales can be compared and analyzed under the same framework. These preprocessing steps provide more accurate and reliable input information for subsequent prediction model establishment, helping the model to learn the true rules and characteristics in the data, thereby improving the prediction accuracy. In addition, preprocessed data is easier to process and analyze, which can shorten the model training time and improve the prediction efficiency.

[0137] S103, a risk assessment model based on the post-icing icing state prediction model is established, and the risk assessment model is used to assess the risk level of the post-icing icing state prediction result;

[0138] It should be noted that when the post-icing icing state prediction model is established, how to make specific judgments based on the results of this model is also a problem to be solved. At present, designing some logical judgments or manually re-judging are ways to solve the problem. In the present invention, a corresponding risk assessment model is established for the post-icing icing state prediction model, so as to realize automatic discrimination of risk.

[0139] In some specific embodiments, the establishment of the risk assessment model can be based on the output of the post-icing ice coating state prediction model, combined with the pre-set risk level classification standard, to evaluate the risk level of the prediction results. The risk assessment model can comprehensively consider multiple dimensions such as predicted ice coating thickness, ice coating growth rate, and prediction uncertainty to determine the risk level. For example, when the predicted ice coating thickness exceeds a certain threshold, or the ice coating growth rate is too fast, or the uncertainty of the prediction result is high, the risk level can be classified as high risk; otherwise, it is low risk or medium risk. Through the risk assessment model, the risk that the post-icing ice coating state may bring can be intuitively understood, providing a basis for the safe operation of the power system and timely measures. At the same time, the risk assessment model can also be flexibly adjusted according to actual needs to adapt to the risk assessment needs of different lines and different weather conditions.

[0140] In some specific embodiments, the risk assessment model can use various algorithms and techniques to achieve automatic classification of risk levels. For example, a decision tree algorithm can be used to construct a decision path according to the predicted ice coating state characteristics, and each path corresponds to a risk level. Alternatively, a fuzzy logic method can be used to match the predicted ice coating state with a pre-set fuzzy set of risk levels, and the final risk level can be determined by calculating the membership degree. In addition, expert systems can be combined to introduce the knowledge and experience of domain experts and establish more accurate risk assessment models. The choice of these methods and techniques depends on the specific application scenario, data characteristics, and precision requirements. By reasonably designing and optimizing the risk assessment model, the application value of the ice coating state prediction result can be further improved, providing stronger protection for the safe and stable operation of the power system.

[0141] When the decision tree algorithm is selected, considering the use background of the present application, factors such as the geographical location of the transmission line, weather conditions, line type, and historical ice coating records need to be considered. The construction process of the decision tree includes steps such as feature selection, node splitting, and pruning.

[0142] First, select key features from the output of the ice coating state prediction model, such as predicted ice coating thickness, ice coating growth rate, and prediction uncertainty.

[0143] Then, according to these features, node splitting is performed to form different decision paths.

[0144] Finally, through pruning operation, remove redundancy and noise to make the decision tree more concise and effective. At each leaf node of the decision tree, a risk level can be corresponded, thereby achieving automatic classification of risk levels. This method has the advantages of intuitive understanding, high computational efficiency, and is suitable for real-time risk assessment and decision support.

[0145] In the embodiments of the present application, the risk assessment model based on the ice-melted ice-covered state prediction model comprises:

[0146] Several dimensions related to the ice-melted ice-covered state prediction model are selected;

[0147] Several dimension indexes representing the several dimensions are established;

[0148] A comprehensive risk assessment model is established based on the several dimension indexes.

[0149] It should be noted that the several dimensions related to the ice-melted ice-covered state prediction model can include ice physical risk, line importance and historical failure risk dimensions. The ice physical risk dimension mainly focuses on the predicted ice thickness, ice growth rate and ice shape and other physical characteristics. These characteristics directly reflect the severity of the ice on the transmission line and the possible impact on the safe operation of the line. By comparing these physical characteristics with the preset risk threshold, the high and low of the ice physical risk can be preliminarily judged.

[0150] It should be noted that the line importance dimension considers the position and role of the transmission line in the power grid. For example, the ice risk of a key transmission line may be higher because its failure may cause a larger range of power outage and power grid instability. This dimension combines the power grid topology and the operation data of the line to evaluate the importance of each line and determine its weight in risk assessment.

[0151] It should be noted that the historical failure risk dimension is based on historical ice data and failure records to analyze the performance of a specific line in past ice events, including failure frequency, failure type and recovery time. Through the mining and analysis of historical data, the line sections prone to failure and high-risk periods under certain weather conditions can be identified, providing historical basis for risk assessment.

[0152] In some specific embodiments, after the establishment of these dimension indexes, the comprehensive risk assessment model combines these indexes, adopts weighted average, fuzzy comprehensive evaluation or analytic hierarchy process method, etc., to calculate the final risk level. The design of the risk assessment model considers the mutual influence and weight distribution between different dimensions to ensure the accuracy and reliability of the evaluation results. Through the comprehensive risk assessment model, the risks that may be brought by the ice-melted ice-covered state can be more comprehensively understood, and more scientific basis can be provided for the safe dispatching and operation and maintenance of the power system.

[0153] Specifically, risk assessment is the key link of anti-icing operation and maintenance decision. The traditional risk assessment mainly relies on single index and experience judgment, which cannot comprehensively reflect the complexity of the icing risk of the power transmission line. The multi-dimensional risk assessment model proposed by the application constructs a risk assessment system from three dimensions: icing physical risk, line importance and historical failure risk, forming a comprehensive risk assessment framework.

[0154] Firstly, the icing ratio r is defined i (t+τ) is the ratio of the predicted icing thickness to the design icing thickness:

[0155]

[0156] Where, h d is the design icing thickness of the line. The icing ratio is the most direct index for evaluating the icing risk, which reflects the relationship between the actual icing thickness and the design carrying capacity of the line. When the icing ratio exceeds 1, it means that the icing thickness has exceeded the design value, and the line has a high safety risk.

[0157] Based on the icing ratio, the icing risk index R1(t+τ) is defined, which converts the icing ratio into a risk score through a nonlinear mapping function, and more accurately reflects the nonlinear relationship between the icing thickness and the risk. In practical application, even if the icing thickness does not reach the design value, the risk may still increase due to uneven icing distribution, excessive local load, etc. Therefore, the risk mapping function adopts a segmented design, and different risk assessment strategies are adopted in different icing ratio intervals.

[0158]

[0159] Where, w i is the weight coefficient of the monitoring point i, is the risk mapping function, which is defined as a piecewise function, and different risk levels are given according to different icing ratio intervals. This design considers the threshold characteristics of icing risk and is more consistent with engineering practice.

[0160] Line importance is the second dimension of risk assessment. Different power transmission lines have different positions and roles in the power grid, so the risk level of important lines should be higher under the same icing conditions. The application introduces the line importance index R2 to evaluate the line importance from three aspects of voltage level, load condition and network topology position:

[0161] R2=σ1·I1+σ2·I2+σ3·I3

[0162] wherein, I1 is a voltage level index, I2 is a load importance index, I3 is a network connection importance index, σ1, σ2, σ3 are weight coefficients, and satisfy σ1+σ2+σ3=1. The three indexes reflect the importance of the line in the power grid from different angles: the voltage level reflects the technical level of the line, the load importance reflects the power supply task undertaken by the line, and the network connection importance reflects the position of the line in the power grid topology.

[0163] The historical failure risk is the third dimension of risk assessment. The historical failure records and operation performance of the transmission line can reflect the inherent vulnerability and potential risk points of the line. The present application establishes a historical failure risk assessment model R3 by analyzing historical failure data, which considers factors such as failure frequency, failure type, and failure cause, forming a comprehensive historical risk profile. Combining the risk assessment results of the above three dimensions, the present application defines a comprehensive risk score R t (t+τ):

[0164] R t (t+τ)=μ1·R1(t+τ)+μ2·R2+μ3·R3

[0165] wherein, μ1, μ2, μ3 are weight coefficients, and satisfy μ1+μ2+μ3=1. The three weight coefficients are set according to the experience of power grid operation and risk management strategy, and can be adjusted according to actual needs. In actual application, the weights can be dynamically adjusted according to the characteristics of different seasons and different regions, so that the risk assessment results are more in line with the actual situation.

[0166] In an embodiment of the present application, the comprehensive risk assessment model includes:

[0167] The output of the comprehensive risk assessment model is scored;

[0168] Establish risk level division interval for the scored results.

[0169] In some specific embodiments, the scoring operation can be performed in different ways and by setting rules, for example, linear functions, exponential functions, logarithmic functions, etc. can be used for scoring, and the selection of each function can be determined according to the specific risk assessment needs and data characteristics. At the same time, the setting rules are also an important part of the scoring operation, and the rules can be based on historical data, expert experience or industry standards, etc. to ensure the accuracy and reasonableness of the scoring results. Through these ways and rules, the output of the comprehensive risk assessment model can be more intuitive and easy to understand, providing stronger support for subsequent decision-making.

[0170] Specifically, when a linear function is used for scoring, the original numerical value of the risk factor can be linearly transformed by a certain proportion to obtain the corresponding score. This method is simple and intuitive, and is suitable for the case where the risk factor and the risk level are in a linear relationship. When an exponential function is used for scoring, the extreme values in the risk factor can be highlighted, so that high-risk factors are given greater weight in the scoring result, which is suitable for the case where the risk factor and the risk level are in a nonlinear relationship and extreme risks need to be emphasized. The logarithmic function is suitable for the case where the numerical range of the risk factor is large and needs to be compressed. Through logarithmic transformation, the numerical range can be reduced to a suitable interval, facilitating subsequent risk level division.

[0171] It should be noted that after determining the scoring operation and performing the scoring operation, the risk level division interval needs to be performed. The setting of the risk level division interval is based on the understanding of the risk assessment result and the actual needs. Generally, the risk assessment score range can be divided into different levels, such as high risk, medium risk, and low risk. Each level corresponds to a different score interval, reflecting different risk levels and possible impacts.

[0172] Specifically, according to the comprehensive risk score, the risk level is divided into four levels:

[0173] I level (low risk): R t <1.0

[0174] II level (medium risk): 1.0≤R t <2.0

[0175] III level (high risk): 2.0≤R t <3.0

[0176] IV level (extremely high risk): R t ≥3.0

[0177] This grading method is consistent with the risk management system of the power industry, facilitating the integration with existing operation and maintenance processes and plans, and improving the practicality and effectiveness of risk management.

[0178] In some specific embodiments, the risk assessment result is displayed in a visual manner, including risk heat maps, risk trend charts, risk level distribution charts, and other forms, helping operation and maintenance personnel to intuitively understand the icing risk situation. At the same time, the system also provides a risk detail query function, which can display the risk composition and main risk factors of a specific line segment, providing accurate information for operation and maintenance decision-making.

[0179] Continuing with the above scenario, let's assume the predictive model concludes that 24 hours after the de-icing operation is completed, the ice thickness on the power line will reach 10mm again due to continuous freezing rain. At this point, the risk assessment model is activated.

[0180] Calculating the physical risk of icing: The designed icing thickness of this line is 20mm. The predicted 10mm icing corresponds to an icing ratio of 0.5. According to the risk mapping function, this ratio corresponds to an icing risk index of 40 points (medium risk).

[0181] Assessing the importance of the line: This 500kV line is a main line connecting two major cities. It belongs to the highest voltage level and has been operating under high load for a long time. Its importance index score is 90 points (very important).

[0182] Analysis of historical fault risk: Historical data shows that the line has experienced two tripping incidents due to icing in the past 5 years, and its historical fault risk index score is 75 points (higher risk).

[0183] With weights of 0.4, 0.4, and 0.2, the overall score is 16 + 36 + 15 = 67 points. Based on the risk level classification, 67 points falls into Level III (high risk).

[0184] It should be noted that establishing a risk assessment model based on a post-melting icing state prediction model enables a quantitative assessment of the risks associated with the icing state of transmission lines after melting, thereby more accurately identifying potential safety hazards. This risk assessment model comprehensively considers multiple factors, such as weather conditions, line parameters, and historical icing data, providing maintenance personnel with a more comprehensive and detailed risk analysis. Furthermore, through this risk assessment model, maintenance personnel can develop corresponding maintenance strategies and emergency plans for line sections with different risk levels, ensuring the safe and stable operation of the lines.

[0185] S104 generates anti-icing operation and maintenance strategies based on risk levels.

[0186] It is important to note that risk management should begin immediately upon obtaining the risk level. Relying solely on manual processing at this stage will lead to low efficiency and may result in delays or improper handling due to human error. Therefore, upon obtaining the risk level, the system should automatically trigger the corresponding risk management process, such as sending warning messages to relevant personnel and activating emergency plans, to ensure that the risk is handled promptly and effectively.

[0187] Therefore, the application establishes different anti-icing operation and maintenance strategies corresponding to risk levels, and through the self-adaptive design method, the most suitable operation and maintenance measures can be automatically selected according to the current risk level. For example, for the low risk level (I level), the routine inspection and maintenance measures can be taken to ensure that the basic operation state of the line is good; for the medium risk level (II level), the monitoring frequency needs to be strengthened, and the necessary emergency supplies and equipment are prepared so as to respond quickly when the risk is upgraded; for the high risk level (III level), the emergency plan needs to be started immediately, and the professional team needs to be organized to carry out on-site disposal to ensure the line safety; for the very high risk level (IV level), more stringent measures need to be taken, such as temporary power outage maintenance, strengthening line protection, etc., to minimize the impact of icing on line operation. The self-adaptive anti-icing operation and maintenance strategy design not only improves the efficiency of risk processing, but also ensures the effectiveness and pertinence of operation and maintenance measures, and provides a strong guarantee for the safe and stable operation of the power system.

[0188] In the embodiment of the application, the self-adaptive anti-icing operation and maintenance strategy selection is realized by designing the operation and maintenance strategy vector. The anti-icing operation and maintenance strategy is generated according to the risk level, which includes:

[0189] The operation and maintenance strategy vector is established, and the operation and maintenance strategy vector includes several operation and maintenance key parameters;

[0190] The specific value of the operation and maintenance strategy vector is determined according to the risk level;

[0191] The anti-icing operation and maintenance strategy is generated according to the operation and maintenance strategy vector.

[0192] It should be noted that the traditional anti-icing operation and maintenance strategy is mostly a standardized and static scheme, which cannot be differentiated and dynamically adjusted according to the specific situation of the line and the risk level, resulting in unreasonable resource allocation and problems such as excessive maintenance and monitoring blind area.

[0193] The self-adaptive generation method proposed in the application overcomes these shortcomings and realizes the precise allocation and efficient use of operation and maintenance resources. The intelligent generation of the anti-icing operation and maintenance strategy is based on the risk assessment results, and considers various factors such as line characteristics, geographical environment, historical operation and maintenance experience, etc. The system first determines the overall direction and focus of the operation and maintenance strategy according to the risk assessment results, then makes individualized adjustment according to the specific line situation, and finally forms a complete operation and maintenance strategy.

[0194] The operation and maintenance strategy vector S is defined, which contains the key parameters of the anti-icing operation and maintenance:

[0195] S=[z1,z2,z3,z4,z5]

[0196] wherein z1 represents the number of inspection rounds, z2 represents the proportion of key monitoring sections, z3 represents the level of emergency resource allocation, z4 represents the advance of warning time, and z5 represents the number of special operation measures. These parameters together constitute the framework of the anti-icing operation strategy, covering multiple aspects such as inspection monitoring, emergency preparation, and early warning management.

[0197] It should be noted that adaptive operation strategy generation functions are designed for different risk levels. These functions automatically calculate the values of each operation parameter based on the risk assessment results, combined with the physical characteristics of the line and historical operation effects.

[0198] It should also be noted that by converting the operation strategy into a quantitative operation strategy vector, the formulation of the operation strategy becomes more accurate and measurable. Each parameter in the operation strategy vector corresponds to a specific operation action and resource allocation, such as increasing the number of inspection rounds, determining key monitoring sections, and deploying emergency supplies, which can be dynamically adjusted according to changes in risk levels.

[0199] For the above-mentioned III level (high risk) evaluation, the system automatically generates the following anti-icing operation strategy and issues it to the operation team.

[0200] Inspection rounds: from the regular once every 24 hours to once every 4 hours.

[0201] Proportion of key monitoring sections: 80% of the line is listed as the key monitoring object.

[0202] Emergency resource allocation level: immediately deploy a set of mobile DC ice melting devices to the nearby substation on standby.

[0203] Advance of warning time: set the warning threshold to 13mm of predicted ice thickness and issue an orange warning 6 hours in advance.

[0204] Number of special operation measures: generate 2 special measures: 1) arrange a drone to conduct infrared temperature measurement inspection to check for hardware heating points; 2) notify the dispatch department to prepare a backup power supply scheme.

[0205] In summary, the present application proposes a method for predicting the state of an icing transmission line after ice melting. By obtaining target data of the target transmission line and preprocessing, the accuracy and reliability of the data are ensured, providing a solid foundation for subsequent model establishment. The ice melting state prediction model established based on the preprocessed target data can accurately predict the ice melting state, providing an important decision basis for operation and maintenance personnel. The establishment of the risk assessment model enables operation and maintenance personnel to quantitatively assess the risk level of the ice melting state prediction result, thereby more scientifically formulating the anti-icing operation and maintenance strategy. The present application improves the accuracy and scientificity of the state prediction of the icing transmission line after ice melting, provides strong technical support for anti-icing operation and maintenance work, and effectively reduces the risk of transmission line failure caused by icing.

[0206] In a preferred embodiment of embodiment 2, the anti-icing operation and maintenance strategy not only considers the risk level, but also considers the physical characteristics and historical operation and maintenance effects of the line. For example, for lines located in special geographical environments (such as mountainous areas, valleys, etc.), the system will adjust the patrol route and monitoring focus according to the topographic characteristics; for lines that have historically had frequent icing problems, the system will increase the monitoring frequency and early warning sensitivity. This personalized adjustment makes the operation and maintenance strategy more in line with actual needs, improving the pertinence and effectiveness of anti-icing operation and maintenance.

[0207] In some specific embodiments, in order to optimize resource allocation, an operation and maintenance resource allocation model is constructed. Based on the risk assessment results, the model reasonably allocates limited operation and maintenance resources to each line section according to the principle of "risk-oriented, resource-optimized". For the total available resources C t , the resources c i allocated to the i-th line section are:

[0208]

[0209] where R i is the risk score of the i-th line section, θ is the resource allocation sensitivity parameter, and m is the total number of line sections. This allocation ensures that high-risk sections receive more operation and maintenance resources, while also ensuring the basic operation and maintenance needs of low-risk sections, achieving rational allocation of resources.

[0210] It should be noted that the generation process of the anti-icing operation and maintenance strategy is dynamic, and the system will automatically adjust the operation and maintenance strategy according to changes in the risk prediction results. For example, when it is predicted that the icing risk of a certain line section will sharply rise within the next 48 hours, the system will automatically adjust the operation and maintenance strategy for that section, increasing the number of patrols, deploying emergency resources in advance, and ensuring that effective prevention and control measures are taken before the risk intensifies. This dynamic adjustment mechanism ensures that anti-icing operation and maintenance always keeps pace with risk conditions, improving the timeliness and foresight of anti-icing operation and maintenance.

[0211] In some specific embodiments, a policy execution feedback mechanism can be introduced to continuously optimize operation and maintenance decisions through evaluation of policy execution effects. The system will collect actual data and effect evaluation during policy execution, analyze the effectiveness of policy execution, find out the deficiencies and improvement points, and provide optimization basis for subsequent policy generation. This closed-loop feedback mechanism enables continuous improvement of anti-icing operation and maintenance strategies and continuous improvement of operation and maintenance effects.

[0212] The comparison between the present application and the conventional technology (transmission line icing monitoring method based on manual observation) is shown in Table 1. As can be clearly seen from the table, the present application has significant advantages in data sources, prediction ability, risk assessment, operation and maintenance strategies, decision-making mode and resource utilization, and represents the development direction of transmission line anti-icing operation and maintenance technology.

[0213] Table 1 Comparison between the present application and the conventional technology

[0214]

[0215] Example 3, with reference to Figure 2 In this embodiment, a transmission line icing post-melting state prediction system is also provided, comprising:

[0216] A data processing module is configured to acquire target data of a target transmission line and pre-process the target data.

[0217] The target data includes transmission line icing state monitoring data, ice-melting operation parameter data and weather prediction data.

[0218] A first model establishing module is configured to establish an icing post-melting state prediction model based on the pre-processed target data.

[0219] The icing post-melting state prediction model is obtained according to an icing growth model and an ice-melting efficiency model.

[0220] The icing growth model is established based on the ice-melting operation parameter data.

[0221] The ice-melting efficiency model is established based on the weather prediction data.

[0222] A second model establishing module is configured to establish a risk assessment model based on the icing post-melting state prediction model, and the risk assessment model is configured to evaluate the risk level of the icing post-melting state prediction result.

[0223] A strategy obtaining module is configured to generate an anti-icing operation and maintenance strategy according to the risk level.

[0224] The above-mentioned various modules can be embedded in or independent of the processor in the electronic device in hardware form, or can be stored in the memory in the electronic device in software form, so as to be called and executed by the processor to perform the operations corresponding to the above-mentioned various modules.

[0225] This embodiment also provides an electronic device, which can be a terminal, and its internal structure diagram can be as follows: Figure 2 As shown, the electronic device includes a processor, memory, communication interface, display screen, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium 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 medium. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for predicting the post-icing state of transmission lines. The display screen can be an LCD screen or an e-ink screen. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the device's casing, or an external keyboard, touchpad, or mouse.

[0226] This embodiment also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, it performs the following steps:

[0227] Acquire target data for the target transmission line and preprocess the target data;

[0228] The target data includes transmission line icing status monitoring data, de-icing operation parameter data, and meteorological forecast data;

[0229] A prediction model for the icing state after melting is established based on the preprocessed target data.

[0230] The prediction model for the icing state after melting is obtained based on the icing growth model and the melting efficiency model.

[0231] The ice growth model is established based on ice melting operation parameter data;

[0232] The ice-melting efficiency model is established based on meteorological forecast data;

[0233] Establish a risk assessment model based on the prediction model of the icing state after melting ice. The risk assessment model is used to evaluate the risk level of the prediction results of the icing state after melting ice.

[0234] Anti-icing operation and maintenance strategies are generated based on risk levels.

[0235] It should be noted that the above-mentioned embodiments are only used to explain the technical solutions of the present application, not to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalent replaced without departing from the spirit and scope of the present application, and they should be covered in the scope of claims of the present application.

[0236] Although the preferred embodiments of the application have been described, those skilled in the art will appreciate that other modifications and variations to the preferred embodiments are possible without departing from the spirit and scope of the application. Accordingly, it is intended that the appended claims encompass all such modifications and variations as fall within the scope of the application.

[0237] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and variations.

Claims

1. A method of predicting a state of a transmission line after ice melting, characterized by, The method comprises: acquiring target data of a target power transmission line, and preprocessing the target data; the target data comprises icing state monitoring data of the power transmission line, de-icing operation parameter data, and meteorological prediction data; a post-de-icing icing state prediction model is established based on the preprocessed target data; the post-de-icing icing state prediction model is obtained according to an icing growth model and a de-icing efficiency model; the icing growth model is established based on the de-icing operation parameter data; the de-icing efficiency model is established based on the meteorological prediction data; a risk assessment model based on the post-de-icing icing state prediction model is established, and the risk assessment model is used to assess a risk level of a post-de-icing icing state prediction result; an anti-icing operation and maintenance strategy is generated according to the risk level.

2. The method of claim 1, wherein the method further comprises: The establishment of the risk assessment model based on the post-de-icing icing state prediction model comprises: selecting a plurality of dimensions related to the post-de-icing icing state prediction model; establishing a plurality of dimension indexes representing the plurality of dimensions; establishing a comprehensive risk assessment model based on the plurality of dimension indexes.

3. The method for predicting the post-icing state of transmission lines as described in claim 2, characterized in that, The generation of the anti-icing operation and maintenance strategy according to the risk level comprises: establishing an operation and maintenance strategy vector, the operation and maintenance strategy vector comprising a plurality of operation and maintenance key parameters; the specific values of the operation and maintenance strategy vector are determined according to the risk level; an anti-icing operation and maintenance strategy is generated according to the operation and maintenance strategy vector.

4. The method for predicting the post-icing state of transmission lines as described in claim 3, characterized in that, The post-de-icing icing state prediction model comprises an icing growth model and a de-icing efficiency model; the icing growth model is established by acquiring the growth rate of the icing thickness under specific meteorological conditions; the specific meteorological conditions are meteorological conditions under fixed numerical wind speed, temperature, and humidity; the de-icing efficiency model comprises efficiency functions under different de-icing device types and de-icing modes, de-icing current or power values, de-icing duration, and correction functions related to de-icing completion time and pre-de-icing icing thickness.

5. The method for predicting the post-icing state of transmission lines as described in claim 4, characterized in that, The comprehensive risk assessment model comprises: score the output of the comprehensive risk assessment model; establish a risk level division interval for the scored result.

6. The method of claim 5, wherein the step of predicting the post-icing state of the power transmission line is performed by using the following equation: ###0002### where, A is a constant, and B is a constant. The acquisition of the target data of the target power transmission line and the preprocessing of the target data comprise: the target data of the target power transmission line comprises image type data, time series data, and meteorological type data related to the target power transmission line; and the preprocessing comprises: for the image type data, image enhancement, denoising, and feature extraction algorithms are adopted; for the time series data, trend analysis and periodicity analysis methods are adopted; for the meteorological type data, spatial interpolation and time standardization processing are performed.

7. The method for predicting the post-icing state of transmission lines as described in claim 6, characterized in that, The preprocessing further comprises: defining a de-icing parameter vector and a micro-meteorological parameter vector; the de-icing parameter vector comprises a de-icing device type, a de-icing mode, a de-icing current or power value, a de-icing duration, and a de-icing completion time; the micro-meteorological parameter vector comprises an environmental temperature, a relative humidity, a wind speed, a wind direction, and a precipitation.

8. A system for predicting the state of a power transmission line after de-icing of ice accretion, applying the method according to any one of claims 1 to 7, characterized in that The method comprises: a data processing module, configured to acquire target data of a target power transmission line, and preprocess the target data; the target data comprises icing state monitoring data of the power transmission line, de-icing operation parameter data, and meteorological prediction data; The first model establishing module is configured to establish an ice-melted icing state prediction model based on the preprocessed target data; The ice-melted icing state prediction model is obtained according to an icing growth model and an ice-melt efficiency model; The icing growth model is established based on ice-melt operation parameter data; The ice-melt efficiency model is established based on meteorological prediction data; The second model establishing module is configured to establish a risk assessment model based on the ice-melted icing state prediction model, and the risk assessment model is configured to assess a risk level of the ice-melted icing state prediction result; The strategy obtaining module is configured to generate an anti-icing operation and maintenance strategy according to the risk level. 9.An electronic device comprising a memory and a processor, the memory storing a computer program, wherein, The processor executes the computer program to implement the steps of the power transmission line ice-melted icing state prediction method in any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the power transmission line ice-melted icing state prediction method in any one of claims 1-7.

Images