A method and system for on-line monitoring of power transmission line contamination

Abstract

The application discloses a kind of transmission line pollution on-line monitoring method and system, it is related to power system state monitoring technical field, including obtaining the multispectral polarization scattering data of transmission line insulator surface, and constructs the three-dimensional digital twin of corresponding insulator;Based on the multispectral polarization scattering data, the component type and deposition intensity of insulator surface pollution are identified, and local pollution feature vector is generated;The local pollution feature vector is matched with the three-dimensional digital twin in space, and the surface contamination state parameter of corresponding position in the three-dimensional digital twin is updated;Combined with the updated surface contamination state parameter and weather forecast data, the equivalent salt density evolution curve of insulator in future preset period is calculated through particle deposition dynamics model;Based on the equivalent salt density evolution curve, the pollution risk level distribution map of transmission line level is generated, and on-line monitoring is completed.The application improves the accuracy and timeliness of transmission line insulation state evaluation.

Description

Technical Field

[0001] This invention relates to the field of power system condition monitoring technology, and in particular to a method and system for online monitoring of pollution in transmission lines. Background Technology

[0002] Monitoring the pollution status of transmission line insulators is a crucial aspect of ensuring the safe operation of the power grid. Especially in areas prone to industrial pollution, coastal salt spray, and sandstorms, accumulated pollution on the insulator surface under humid conditions can easily trigger flashover accidents, causing large-scale power outages. In recent years, with the development of smart grids and the power Internet of Things (IoT), pollution monitoring technology has gradually evolved from traditional manual sampling and measurement towards automation and online monitoring. Some lines have already deployed leakage current monitoring devices or image recognition systems, achieving preliminary remote sensing of pollution levels. Simultaneously, the widespread application of drone inspections has improved the accessibility of insulator conditions in complex terrain. Combined with big data analysis and geographic information systems, preliminary assessments of pollution risks have been achieved in some areas.

[0003] However, existing technologies still have the following prominent problems: Lack of component identification capability: Existing methods mostly rely on a single indicator such as equivalent salt density (ESDD) or leakage current amplitude, failing to distinguish between different components such as salt, dust, and oil. This leads to high-density, low-conductivity pollution being misjudged as high-risk, resulting in over-maintenance or underestimation of true salt pollution risks; Unknown dynamic evolution: Monitoring is mostly "instantaneous snapshot" type, lacking physical modeling of the pollution accumulation process, unable to combine meteorological changes to predict pollution trends in the next few days, making it difficult to support proactive prevention and control decisions; Data and model disconnect: UAV inspection data is disconnected from the power grid management system, lacking a unified spatial benchmark and semantic association, making it difficult to achieve multi-source data fusion and global risk extrapolation; Limited assessment level: Existing systems mostly focus on the status of single-point insulators, unable to generate line-level or regional-level risk distribution maps, restricting the optimal allocation of operation and maintenance resources. The aforementioned problems essentially reflect that current pollution monitoring is still in the stage of "passive response and static assessment," and there is an urgent need to build an online monitoring system that integrates component identification, dynamic prediction, and digital twins in order to achieve a technological leap from "knowing the current situation" to "predicting the future." Summary of the Invention

[0004] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0005] In view of the aforementioned existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a method and system for online monitoring of pollution in power transmission lines, which can solve the problems mentioned in the background art.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0008] In a first aspect, the present invention provides a method for online monitoring of pollution in transmission lines, which includes acquiring multispectral polarization scattering data of the surface of insulators of transmission lines and constructing a three-dimensional digital twin of the corresponding insulators;

[0009] Based on the multispectral polarization scattering data, the composition type and deposition intensity of contamination on the insulator surface are identified, and a local contamination feature vector is generated.

[0010] Spatial matching is performed between the local contamination feature vector and the three-dimensional digital twin to update the surface contamination state parameters at the corresponding positions in the three-dimensional digital twin;

[0011] Combining updated surface contamination status parameters and meteorological forecast data, the equivalent salt density evolution curve of the insulator in the future preset time period is calculated using a particle deposition kinetic model;

[0012] Based on the equivalent salt density evolution curve, a pollution risk level distribution map at the transmission line level is generated to complete online monitoring.

[0013] As a preferred embodiment of the online pollution monitoring method for transmission lines according to the present invention, the step of acquiring multispectral polarization scattering data of the surface of transmission line insulators includes:

[0014] The drone is controlled to fly along the preset inspection path of the power transmission line, and a multi-band laser light source is activated simultaneously to alternately emit multiple polarized beams of specific wavelengths to scan the surface of the insulator point by point.

[0015] The system receives light signals reflected and scattered from the surface of an insulator, detects their intensity distribution and polarization state changes at multiple scattering angles, and generates a raw optical response data sequence.

[0016] The original optical response data sequence is denoised, background subtracted, and time-aligned to obtain structured multispectral polarization scattering data, which includes wavelength, incident / scattering angle, polarization direction, light intensity, and corresponding spatial coordinates.

[0017] As a preferred embodiment of the online pollution monitoring method for transmission lines according to the present invention, the construction of the three-dimensional digital twin of the corresponding insulator includes:

[0018] Based on transmission line design drawings, geographic information system data, and insulator model parameters, a three-dimensional digital model of the insulator is established, which includes geometric structure, material properties, and spatial location information.

[0019] The three-dimensional digital model of the insulator is associated with the power grid topology, and a unique equipment identifier and operating voltage level are assigned to it to form a three-dimensional digital twin with electrical context information.

[0020] As a preferred embodiment of the online pollution monitoring method for transmission lines according to the present invention, the generation of the local pollution feature vector includes:

[0021] The wavelength-scattering angle-polarization intensity four-dimensional feature matrix is ​​extracted from the multispectral polarization scattering data, and the feature matrix is ​​normalized according to spatial coordinates to obtain the standard reflectivity-polarization difference dataset.

[0022] The standard reflectivity-polarization difference dataset is input into a pre-trained lightweight neural network model, which outputs the composition type of contamination on the insulator surface.

[0023] Based on the identification results of the component types, the mass deposition density of each component is inverted by combining the multispectral scattering intensity attenuation curve to obtain the total deposition intensity;

[0024] The component type, mass deposition density of each component, total deposition intensity, corresponding spatial coordinates, and acquisition time are integrated to generate a structured local fouling feature vector. The local fouling feature vector is encapsulated in a fixed data format and marked with a timestamp.

[0025] As a preferred embodiment of the online monitoring method for pollution in transmission lines according to the present invention, updating the surface pollution status parameters includes:

[0026] The spatial coordinates of the local pollution feature vector are analyzed and converted from the geographic coordinate system to the location identifier in the local Cartesian coordinate system used by the three-dimensional digital twin.

[0027] In the three-dimensional digital twin, the insulator surface mesh nodes that match the transformed position identifiers are searched to determine the target update area;

[0028] The component types and mass deposition density of each component in the local fouling feature vector are mapped to surface fouling state parameters, which include salt content, ash density and equivalent conductivity.

[0029] The original parameters of the target update area are replaced with the surface contamination state parameters to complete the update of the corresponding position in the three-dimensional digital twin.

[0030] As a preferred embodiment of the online pollution monitoring method for transmission lines according to the present invention, the calculation of the equivalent salt density evolution curve of the insulator over a future preset time period includes:

[0031] The salt content and soluble salt mass deposition density in the updated surface contamination state parameters are obtained as the initial contamination state input for the particle deposition kinetics model.

[0032] Obtain meteorological forecast data for a future preset time period, including wind speed, wind direction, relative humidity, rainfall, atmospheric particulate matter concentration, and temperature change series;

[0033] Based on the initial pollution state input and meteorological forecast data, the net deposition rate of pollutants per unit time is calculated using a particle deposition kinetic model. The net deposition rate is determined by dry deposition flux, wet deposition loss, and wind scour term.

[0034] Integrating the net deposition rate over time yields the equivalent salinity value updated every 24 hours, generating an equivalent salinity evolution curve with a time resolution of 24 hours.

[0035] As a preferred embodiment of the online pollution monitoring method for transmission lines according to the present invention, the generation of a pollution risk level distribution map at the transmission line level includes:

[0036] Extract the predicted maximum equivalent salt density value for the next 72 hours from the equivalent salt density evolution curve corresponding to each insulator;

[0037] Based on the preset salt density-risk mapping relationship, the maximum equivalent salt density prediction value is converted into the pollution risk level of a single insulator, and the pollution risk level is divided into four levels: normal, attention, warning and alarm.

[0038] The pollution risk level of all insulators is correlated with their spatial location in a three-dimensional digital twin, and a continuous transmission line-level pollution risk distribution surface is generated using the Kriging interpolation algorithm.

[0039] The pollution risk distribution surface is overlaid onto the geographic information system layer, and a visual pollution risk level distribution map is rendered using color gradients and pushed to the operation and maintenance monitoring terminal to complete online monitoring.

[0040] Secondly, the present invention provides an online monitoring system for pollution of transmission lines, comprising: a perception modeling module for acquiring multispectral polarization scattering data of the surface of insulators of transmission lines and constructing a three-dimensional digital twin of the corresponding insulator;

[0041] The component identification module is used to identify the component type and deposition intensity of the contaminant on the insulator surface based on the multispectral polarization scattering data, and generate a local contaminant feature vector.

[0042] The status update module is used to spatially match the local contamination feature vector with the three-dimensional digital twin and update the surface contamination status parameters at the corresponding positions in the three-dimensional digital twin.

[0043] The trend prediction module is used to combine updated surface contamination status parameters and meteorological forecast data to calculate the equivalent salt density evolution curve of the insulator in the future preset time period through a particle deposition dynamics model.

[0044] The risk visualization module is used to generate a pollution risk level distribution map at the transmission line level based on the equivalent salt density evolution curve, and to complete online monitoring.

[0045] Thirdly, the present invention 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 implement the steps of an online monitoring method for pollution of power transmission lines.

[0046] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements the steps of a method for online monitoring of pollution in power transmission lines.

[0047] Compared with existing technologies, the advantages of this invention are as follows: by acquiring multispectral polarization scattering data and constructing a three-dimensional digital twin, it achieves the simultaneous establishment of physical perception and virtual modeling, providing a unified spatiotemporal benchmark for subsequent analysis; by identifying components and generating local pollution feature vectors, it breaks through the limitation of traditional methods that only assess the total amount, achieving accurate analysis of pollutant types and significantly improving the accuracy of salinity calculation; by spatial matching and updating state parameters, it completes the dynamic alignment of virtual and real integration, ensuring that the digital twin reflects the real pollution state in real time; by combining meteorological data and particle deposition dynamics models to deduce equivalent salinity evolution curves, it achieves a leap from current state monitoring to future trend prediction, supporting the prediction of risk windows; finally, by generating a risk level distribution map at the transmission line level, it transforms scattered data into a global visual decision-making view, helping operation and maintenance shift from passive response to proactive prevention and control. Overall, this invention constructs a closed-loop system encompassing "perception-identification-fusion-prediction-decision," achieving for the first time high-precision online monitoring of pollution with identifiable components, measurable evolution, and visible risks. This significantly improves the accuracy, timeliness, and intelligence of transmission line insulation condition assessment, effectively supporting the safe operation and predictive maintenance of the power grid. Attached Figure Description

[0048] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 A flowchart illustrating an online monitoring method and system for pollution in power transmission lines, provided in one embodiment of the present invention;

[0050] Figure 2 This is a schematic diagram of an online monitoring method and system for pollution in power transmission lines according to an embodiment of the present invention;

[0051] Figure 3 This is an internal structural diagram of a computer device for an online monitoring method and system for pollution of power transmission lines, provided in one embodiment of the present invention. Detailed Implementation

[0052] To make the above-mentioned objects, features, and advantages of the present invention more readily understood, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0053] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0054] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0055] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not necessarily drawn according to actual scale.

[0056] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0057] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0058] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0059] Furthermore, in the description of this disclosure, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or order. Similarly, although operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring such operations to be performed in the specific order shown or in sequential order, or requiring the execution of all illustrated operations to achieve the desired result. In some cases, multitasking and parallel processing can be advantageous.

[0060] Example 1, referring to Figure 1 This is the first embodiment of the present invention, which provides a method for online monitoring of pollution in power transmission lines, including:

[0061] Figure 1 A flowchart of a method and system for online monitoring of pollution in power transmission lines is shown, including:

[0062] S1: Acquire multispectral polarization scattering data of the surface of transmission line insulators and construct a three-dimensional digital twin of the corresponding insulator;

[0063] S2: Based on the multispectral polarization scattering data, identify the composition type and deposition intensity of the contaminant on the insulator surface, and generate a local contaminant feature vector;

[0064] S3: Spatial matching of the local contamination feature vector with the three-dimensional digital twin, and updating the surface contamination state parameters at the corresponding positions in the three-dimensional digital twin;

[0065] S4: Combining the updated surface contamination status parameters and meteorological forecast data, calculate the equivalent salt density evolution curve of the insulator in the future preset time period using the particle deposition dynamics model;

[0066] S5: Based on the equivalent salt density evolution curve, generate a pollution risk level distribution map at the transmission line level to complete online monitoring.

[0067] It should be noted that transmission line insulators are exposed to a complex atmospheric environment for extended periods, and their surfaces are prone to accumulating pollutants such as industrial dust, salt, coal ash, and oil. Under conditions of humidity changes (such as fog, dew, and rainfall), these pollutants dissolve to form a conductive film, significantly reducing the surface resistance of the insulators and increasing leakage current. In severe cases, this can lead to flashover accidents, threatening the safe operation of the power grid. Current pollution monitoring methods largely rely on manual sampling to measure equivalent salt density (ESDD) or indirect assessment through leakage current. These methods suffer from problems such as response lag, inability to identify pollutant components, and difficulty in reflecting spatial distribution differences. Furthermore, the accumulation of insulator pollution is dynamically affected by meteorological and environmental factors such as wind speed, temperature, humidity, rainfall, and aerosol concentration. Measurements taken at a single moment are insufficient to characterize its evolution trend, leading to untimely risk warnings and blind cleaning and maintenance strategies.

[0068] More critically, traditional monitoring methods lack the ability to identify differences in pollution composition, mistakenly equating high-density, low-conductivity pollution with high-salt-density, high-risk conditions, leading to misjudgments. Furthermore, due to the lack of long-term dynamic prediction mechanisms, maintenance units struggle to anticipate pollution trends over the next few days, hindering proactive prevention and control. While drone inspections can improve coverage, they typically only collect image data, lacking onboard real-time analysis and model feedback, resulting in low data utilization and no integration with power grid-level condition assessment systems.

[0069] Therefore, to address the aforementioned issues such as component misjudgment, unknowable dynamic evolution, lack of predictive capability, and fragmented multi-source data, an online monitoring framework integrating multispectral polarization scattering sensing and a three-dimensional digital twin is constructed through steps S1-S5. This framework enables accurate identification of the type and intensity of pollution components on the insulator surface. A virtual-real matching mechanism driven by geographic coordinates and timestamps is used to dynamically inject monitoring data into the digital twin and update its status. Combining particle deposition dynamics models and meteorological forecast data, the future evolution trend of the equivalent salt density of insulators is quantitatively calculated. Finally, a pollution risk level distribution map at the transmission line level is generated, completing the leap from "point detection" to "comprehensive prediction," providing a scientific basis for power grid operation and maintenance, and improving the accuracy and timeliness of pollution flashover early warning.

[0070] Example 2, refer to Figures 1-2 This is a second embodiment of the present invention. This embodiment also provides a method for online monitoring of pollution in power transmission lines, comprising:

[0071] In this embodiment of the application, step S1 involves obtaining multispectral polarization scattering data of the transmission line insulator surface through the following steps, and constructing a three-dimensional digital twin of the corresponding insulator, including:

[0072] S11: Control the drone to fly along the preset inspection path of the power transmission line, and simultaneously start a multi-band laser light source to alternately emit multiple polarized beams of specific wavelengths to scan the surface of the insulator point by point.

[0073] S12: Receives the light signals reflected and scattered from the surface of the insulator, detects the intensity distribution and polarization state changes at multiple scattering angles, and generates the original optical response data sequence;

[0074] S13: The original optical response data sequence is denoised, background subtracted and time-aligned to obtain structured multispectral polarization scattering data, which includes wavelength, incident / scattering angle, polarization direction, light intensity and corresponding spatial coordinates.

[0075] S14: Based on transmission line design drawings, geographic information system data and insulator model parameters, establish a three-dimensional digital model of the insulator that includes geometric structure, material properties and spatial location information.

[0076] S15: Associate the three-dimensional digital model of the insulator with the power grid topology, assign a unique equipment identifier and operating voltage level, and form a three-dimensional digital twin with electrical context information.

[0077] In an optional embodiment, the wavelength range of the multispectral polarization scattering data includes 450 nm, 532 nm, 635 nm, 850 nm and 1064 nm, and the incident light at each wavelength adopts a linear polarization state with polarization directions of 0° and 90° respectively. The scattered light signal is simultaneously acquired at three angles: forward 30°, side 90° and backward 135°, to cover the scattering characteristic responses of different particle types.

[0078] In an optional embodiment, for power transmission lines in coastal areas, during the acquisition of multispectral polarization scattering data, the sampling density of 532nm and 1064nm wavelengths is enhanced, and under meteorological conditions with humidity above 75%, the polarization differential gain of the scattering angle is automatically increased by 90° to improve the sensitivity of NaCl crystal particles. The spatial coordinates are obtained by fusing differential GPS and inertial navigation system carried by the UAV, with a positioning accuracy better than 0.3 meters.

[0079] In an optional embodiment, during the construction of the three-dimensional digital twin, the insulator model parameters include the height of the shed structure, the creepage distance, and the dielectric constant of the material. The geometric structure is generated by matching laser point cloud scanning data with a standard model. The surface roughness parameter in the material properties is degraded according to the years of operation, and the correction coefficient increases by 0.15 μm for every 5 years of operation. The power grid topology relationship includes the tower number to which the insulator belongs, the line name, and the electrical connection relationship of adjacent equipment.

[0080] In an optional embodiment, when applied in high-altitude, low-pressure areas, the background subtraction process of the multispectral polarization scattering data employs a dynamic baseline correction algorithm. This algorithm establishes a local optical background template based on continuous sampling data of the clean insulator area 30 minutes before the inspection and automatically updates the template after each tower scan is completed.

[0081] In this embodiment of the application, step S2 generates a local contamination feature vector through the following steps:

[0082] S21: Extract the four-dimensional feature matrix of wavelength-scattering angle-polarization intensity from the multispectral polarization scattering data, and normalize the feature matrix according to spatial coordinates to obtain the standard reflectivity-polarization difference dataset.

[0083] S22: Input the standard reflectivity-polarization difference dataset into a pre-trained lightweight neural network model and output the composition type of the contaminant on the insulator surface, wherein the composition type includes one or more of NaCl, CaSO4, SiO2 and carbon black;

[0084] S23: Based on the identification results of the component types, the mass deposition density of each component is inverted by combining the multispectral scattering intensity attenuation curve to obtain the total deposition intensity;

[0085] S24: Integrate the component type, mass deposition density of each component, total deposition intensity, corresponding spatial coordinates and acquisition time to generate a structured local fouling feature vector. The local fouling feature vector is encapsulated in a fixed data format and marked with a timestamp.

[0086] In an optional embodiment, the lightweight neural network model is a hybrid structure of MobileNetV2 and a one-dimensional convolutional neural network. The input layer receives a three-dimensional tensor combining wavelength, scattering angle, and polarization direction, and the output layer provides the confidence level of each type of contaminant through the Softmax function. During the training phase, the model uses a dataset containing 100,000 sets of mixed simulated and measured data, with each set of data labeled with the proportion of the real components and the corresponding environmental conditions.

[0087] In an optional embodiment, when inverting the mass deposition density of each component, a weighted least squares method is used to fit the multispectral scattering intensity decay curve. The initial weights are set according to the imaginary part of the refractive index corresponding to the component type, where NaCl is 0.025, SiO2 is 0.008, and carbon black is 0.18. The weight coefficients are dynamically adjusted according to the residual distribution after each inversion, and the iteration continues until convergence. The sum of the mass deposition densities of each component is taken as the total deposition intensity, with the unit being mg / cm².

[0088] In an optional embodiment, the data format of the local contamination feature vector is defined as: {list of component types, [NaCl:x1, CaSO4:x2, SiO2:x3, carbon black:x4], total deposition intensity, longitude, latitude, altitude, acquisition time (UTC)}, where the acquisition time is accurate to the second, the spatial coordinates are retained to 6 decimal places, and when the confidence level of a certain component is less than 60%, the mass deposition density of that component is marked as 0, to ensure the reliability and consistency of the output data.

[0089] In an optional embodiment, during continuous inspection, if the spatial coordinate distance between two adjacent insulators is less than 50 meters and the environmental conditions are similar, the component identification result of the previous position is used as the prior input for the current identification to initialize the intermediate layer feature distribution of the lightweight neural network model, realize cross-point knowledge transfer, and improve the identification stability and response speed of the model under low signal-to-noise ratio conditions in the edge computing environment.

[0090] In this embodiment of the application, step S3 involves spatial matching and updating the surface contamination state parameters through the following steps:

[0091] S31: Analyze the spatial coordinates in the local filth feature vector and convert them from the geographic coordinate system to the location identifier in the local Cartesian coordinate system used by the three-dimensional digital twin;

[0092] S32: In the three-dimensional digital twin, search for insulator surface mesh nodes that match the transformed position identifiers to determine the target update area;

[0093] S33: Map the component types and mass deposition density of each component in the local fouling feature vector to surface fouling state parameters, the surface fouling state parameters including salt content, ash density value and equivalent conductivity;

[0094] S34: Replace the original parameters of the target update area with the surface contamination state parameters to complete the dynamic update of the corresponding position in the three-dimensional digital twin.

[0095] In an optional embodiment, the geographic coordinate system transformation adopts a seven-parameter Bursa model, combined with the reference transformation parameters from local WGS84 to the local coordinate system, to convert the longitude, latitude, and altitude in the local pollution feature vector into X, Y, and Z coordinates in the local Cartesian coordinate system used by the three-dimensional digital twin. During the transformation process, the insulator installation offset angle in the tower design drawings is introduced for attitude compensation to ensure that the matching accuracy is better than 10cm.

[0096] In an optional embodiment, when searching for matching insulator surface grid nodes, a KD tree spatial index structure is used to accelerate the search. The matching threshold is set to 15cm. If the distance of the nearest neighbor node exceeds the threshold, it is determined to be a new monitoring point. The system automatically generates virtual monitoring points in the three-dimensional digital twin based on the geometric continuity of the adjacent umbrella skirts and incorporates them into the subsequent update process. At the same time, they are marked as "interpolation nodes" for traceability.

[0097] In an optional embodiment, the equivalent conductivity is calculated as follows: based on the mass deposition density of NaCl and CaSO4 in the component type, combined with their solubility and ion mobility coefficient, the surface liquid film conductivity is calculated using the following formula:

[0098] ;

[0099] in, Let be the equivalent ion concentration of the i-th soluble salt. The mobility is F, and F is the Faraday constant. The obtained equivalent conductivity is written into the three-dimensional digital twin as one of the surface contamination state parameters.

[0100] In an optional embodiment, when the same insulator receives multiple local pollution feature vectors at different times, the system retains the latest data in chronological order of timestamps. Before updating, it determines the time interval between adjacent updates. If the time interval is less than 48 hours and the environmental conditions do not change significantly, a weighted moving average method is used to fuse the old and new parameters, with the weights calculated according to a time decay factor e. −Δt / τ The calculation is performed, where Δt is the time difference and τ = 24 hours, to suppress the abrupt impact of short-term measurement fluctuations on the state of the 3D digital twin.

[0101] In this embodiment of the application, step S4 involves calculating the equivalent salt density evolution curve of the insulator over a predetermined future time period using the following steps:

[0102] S41: Obtain the salt content and soluble salt mass deposition density in the updated surface contamination state parameters as the initial contamination state input for the particle deposition kinetics model;

[0103] S42: Obtain meteorological forecast data for a future preset time period, including wind speed, wind direction, relative humidity, rainfall, atmospheric particulate matter concentration, and temperature change sequence;

[0104] S43: Based on the initial pollution state input and meteorological forecast data, the net deposition rate of pollutants per unit time is calculated using a particle deposition kinetics model. The net deposition rate is determined by dry deposition flux, wet deposition loss, and wind scour term.

[0105] S44: Integrate the net deposition rate over time to obtain the equivalent salinity value updated every 24 hours, and generate an equivalent salinity evolution curve with a time resolution of 24 hours.

[0106] In an optional embodiment, the dry deposition flux is calculated using the sedimentation velocity method, wherein the deposition velocity of particles of different sizes is determined according to Stokes' law, and the atmospheric particulate matter concentration is calculated according to PM2.5. 10 PM2.5 is input in stages. The deposition process takes into account the adsorption enhancement effect of the electric field on the insulator surface on charged particles. The adsorption coefficient is obtained from the table according to the operating voltage level: 1.15 for 110kV, 1.28 for 220kV, and 1.42 for 500kV and above.

[0107] In an optional embodiment, the wet deposition loss term is activated during the rainfall period, and the loss rate is positively correlated with the cumulative rainfall, using an empirical attenuation model, as shown in the formula:

[0108] ;

[0109] in, This represents the mass of soluble salts remaining after rainfall. R is the initial value before rainfall, R is the cumulative rainfall, and Kr is the regional cleaning coefficient, which is 0.035 for coastal industrial areas, 0.025 for inland arid areas, and 0.018 for plateau areas. This coefficient is calibrated based on historical cleaning effects and is built into the model.

[0110] In an optional embodiment, the wind scouring term uses a wind speed threshold as the criterion. When the instantaneous wind speed exceeds 12 m / s, the scouring model is activated. The scouring rate is directly proportional to the cube of the wind speed and inversely proportional to the surface dirt adhesion strength. The adhesion strength is dynamically set according to the ratio of ash density to salt density. When NSDD / ESDD≤2, a low adhesion strength of 0.15 N / m² is taken, and when the ratio>4, a high adhesion strength of 0.45 N / m² is taken. The pollutant loss caused by scouring is included in the negative component of the net deposition rate.

[0111] In an optional embodiment, the time integration process employs a piecewise linear discretization method, updating the meteorological input hourly and dynamically adjusting the weights of deposition and loss terms. For meteorological forecast data within the next 72 hours, numerical weather prediction (NWP) outputs are used; for data beyond 72 hours, climatic averages are used to supplement the results, generating an equivalent salinity evolution curve for the next 7 days. The curve output format is a time series pair: {(t1,ESDD1),(t2,ESDD2),...,(t...} n ,ESDD n The time interval is 24 hours, and the start time is the current update time.

[0112] In this embodiment of the application, step S5 generates a pollution risk level distribution map at the transmission line level through the following steps:

[0113] S51: Extract the predicted maximum equivalent salt density value for the next 72 hours from the equivalent salt density evolution curve corresponding to each insulator;

[0114] S52: Based on the preset salt density-risk mapping relationship, the maximum equivalent salt density prediction value is converted into the pollution risk level of a single insulator, and the risk level is divided into four levels: normal, attention, warning and alarm.

[0115] S53: Associate the risk level of all insulators with their spatial location in a three-dimensional digital twin, and use the Kriging interpolation algorithm to generate a continuous transmission line-level pollution risk distribution surface;

[0116] S54: Overlay the pollution risk distribution surface onto the geographic information system layer, render a visualized pollution risk level distribution map using color gradient, and push it to the operation and maintenance monitoring terminal to complete online monitoring.

[0117] In an optional embodiment, in the salt density-risk mapping relationship, the normal level corresponds to an equivalent salt density of less than 0.03 mg / cm², the attention level is 0.03 to 0.06 mg / cm², the warning level is 0.06 to 0.10 mg / cm², and the alarm level is greater than 0.10 mg / cm². The thresholds for each level are dynamically corrected based on the creepage distance of the insulator. When the creepage distance is less than 25 mm / kV, the thresholds for each level are reduced by 15%, and when the creepage distance is greater than 31 mm / kV, the thresholds for each level are increased by 10% to reflect the differences in the pollution resistance of the equipment.

[0118] In an optional embodiment, the Kriging interpolation algorithm adopts a spherical variogram model with a range of 3 km. The nugget value is set according to the regional pollution source density, with 0.015 for densely industrial areas, 0.008 for agricultural areas, and 0.012 for marine impact areas. The line orientation is introduced as anisotropy weight during the interpolation process, and the correlation along the line direction is enhanced by 1.3 times, ensuring that the risk distribution surface maintains spatial continuity and physical rationality in long-distance power transmission corridors.

[0119] In an optional embodiment, the pollution risk level distribution map uses a four-color gradient rendering: green (normal), yellow (caution), orange (warning), and red (alarm). The transparency of each color increases as the risk duration increases. If a location is at the warning level or above for 24 consecutive hours, the transparency increases to 80%. If it is in this state for 48 consecutive hours, it is automatically marked as a "high-risk continuous area" and indicated with a flashing border on the map.

[0120] In an optional embodiment, the information pushed to the operation and maintenance monitoring terminal includes not only a static risk distribution map, but also a dynamic alarm list. The alarm list is arranged in descending order of alarm level. Each item includes the tower number, the line to which it belongs, the maximum predicted salt density value, the alarm time, the surrounding weather trend, and the suggested handling measures. When a new alarm occurs, the system automatically triggers a dual-channel notification via SMS and the platform, and simultaneously generates a work order to the power production management system.

[0121] Example 3, referring to Figure 3 This is the third embodiment of the present invention. This embodiment also provides an online monitoring system for pollution of transmission lines, including: a perception modeling module, used to acquire multispectral polarization scattering data of the surface of transmission line insulators and construct a three-dimensional digital twin of the corresponding insulator;

[0122] The component identification module is used to identify the component type and deposition intensity of the contaminant on the insulator surface based on the multispectral polarization scattering data, and generate a local contaminant feature vector.

[0123] The status update module is used to spatially match the local contamination feature vector with the three-dimensional digital twin and update the surface contamination status parameters at the corresponding positions in the three-dimensional digital twin.

[0124] The trend prediction module is used to combine updated surface contamination status parameters and meteorological forecast data to calculate the equivalent salt density evolution curve of the insulator in the future preset time period through a particle deposition dynamics model.

[0125] The risk visualization module is used to generate a pollution risk level distribution map at the transmission line level based on the equivalent salt density evolution curve, and to complete online monitoring.

[0126] This embodiment also provides a computer device, which may be a terminal, and its internal structure diagram may be as follows. Figure 3As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing 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 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 the computer program is executed by the processor, it implements a method for online monitoring of pollution in power transmission lines. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0127] This embodiment also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it performs the following steps: acquiring multispectral polarization scattering data of the surface of a transmission line insulator and constructing a three-dimensional digital twin of the corresponding insulator.

[0128] Based on the multispectral polarization scattering data, the composition type and deposition intensity of contamination on the insulator surface are identified, and a local contamination feature vector is generated.

[0129] Spatial matching is performed between the local contamination feature vector and the three-dimensional digital twin to update the surface contamination state parameters at the corresponding positions in the three-dimensional digital twin;

[0130] Combining updated surface contamination status parameters and meteorological forecast data, the equivalent salt density evolution curve of the insulator in the future preset time period is calculated using a particle deposition kinetic model;

[0131] Based on the equivalent salt density evolution curve, a pollution risk level distribution map at the transmission line level is generated to complete online monitoring.

[0132] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

[0133] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of this application can be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0134] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0135] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0136] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0137] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0138] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for online monitoring of pollution in power transmission lines, characterized in that: include, Acquire multispectral polarization scattering data of the surface of transmission line insulators and construct a three-dimensional digital twin of the corresponding insulator; Based on the multispectral polarization scattering data, the composition type and deposition intensity of contamination on the insulator surface are identified, and a local contamination feature vector is generated. Spatial matching is performed between the local contamination feature vector and the three-dimensional digital twin to update the surface contamination state parameters at the corresponding positions in the three-dimensional digital twin; Combining updated surface contamination status parameters and meteorological forecast data, the equivalent salt density evolution curve of the insulator in the future preset time period is calculated using a particle deposition kinetic model; Based on the equivalent salt density evolution curve, a pollution risk level distribution map at the transmission line level is generated to complete online monitoring; The generation of the local soil feature vector includes: The wavelength-scattering angle-polarization intensity four-dimensional feature matrix is ​​extracted from the multispectral polarization scattering data, and the feature matrix is ​​normalized according to spatial coordinates to obtain the standard reflectivity-polarization difference dataset. The standard reflectivity-polarization difference dataset is input into a pre-trained lightweight neural network model, which outputs the composition type of contamination on the insulator surface. Based on the identification results of the component types, the mass deposition density of each component is inverted by combining the multispectral scattering intensity attenuation curve to obtain the total deposition intensity; The component type, mass deposition density of each component, total deposition intensity, corresponding spatial coordinates and acquisition time are integrated to generate a structured local fouling feature vector. The local fouling feature vector is encapsulated in a fixed data format and marked with a timestamp. Updating surface contamination status parameters includes: The spatial coordinates of the local pollution feature vector are analyzed and converted from the geographic coordinate system to the location identifier in the local Cartesian coordinate system used by the three-dimensional digital twin. In the three-dimensional digital twin, the insulator surface mesh nodes that match the transformed position identifiers are searched to determine the target update area; The component types and mass deposition density of each component in the local fouling feature vector are mapped to surface fouling state parameters, which include salt content, ash density and equivalent conductivity. The original parameters of the target update area are replaced with the surface contamination state parameters to complete the update of the corresponding position in the three-dimensional digital twin.

2. The online monitoring method for pollution in transmission lines as described in claim 1, characterized in that: The acquisition of multispectral polarization scattering data from the surface of transmission line insulators includes: The drone is controlled to fly along the preset inspection path of the power transmission line, and a multi-band laser light source is activated simultaneously to alternately emit multiple polarized beams of specific wavelengths to scan the surface of the insulator point by point. The system receives light signals reflected and scattered from the surface of an insulator, detects their intensity distribution and polarization state changes at multiple scattering angles, and generates a raw optical response data sequence. The original optical response data sequence is denoised, background subtracted, and time-aligned to obtain structured multispectral polarization scattering data, which includes wavelength, incident / scattering angle, polarization direction, light intensity, and corresponding spatial coordinates.

3. The online monitoring method for pollution in transmission lines as described in claim 2, characterized in that: The construction of the three-dimensional digital twin of the corresponding insulator includes: Based on transmission line design drawings, geographic information system data, and insulator model parameters, a three-dimensional digital model of the insulator is established, which includes geometric structure, material properties, and spatial location information. The three-dimensional digital model of the insulator is associated with the power grid topology, and a unique equipment identifier and operating voltage level are assigned to it to form a three-dimensional digital twin with electrical context information.

4. The online monitoring method for pollution in transmission lines as described in claim 3, characterized in that: The calculated equivalent salt density evolution curve of the insulator over a predetermined future time period includes: The salt content and soluble salt mass deposition density in the updated surface contamination state parameters are obtained as the initial contamination state input for the particle deposition kinetics model. Obtain meteorological forecast data for a future preset time period, including wind speed, wind direction, relative humidity, rainfall, atmospheric particulate matter concentration, and temperature change series; Based on the initial pollution state input and meteorological forecast data, the net deposition rate of pollutants per unit time is calculated using a particle deposition kinetic model. The net deposition rate is determined by dry deposition flux, wet deposition loss, and wind scour term. Integrating the net deposition rate over time yields the equivalent salinity value updated every 24 hours, generating an equivalent salinity evolution curve with a time resolution of 24 hours.

5. The online monitoring method for pollution in transmission lines as described in claim 4, characterized in that: The pollution risk level distribution map generated at the transmission line level includes: Extract the predicted maximum equivalent salt density value for the next 72 hours from the equivalent salt density evolution curve corresponding to each insulator; Based on the preset salt density-risk mapping relationship, the maximum equivalent salt density prediction value is converted into the pollution risk level of a single insulator, and the pollution risk level is divided into four levels: normal, attention, warning and alarm. The pollution risk level of all insulators is correlated with their spatial location in a three-dimensional digital twin, and a continuous transmission line-level pollution risk distribution surface is generated using the Kriging interpolation algorithm. The pollution risk distribution surface is overlaid onto the geographic information system layer, and a visual pollution risk level distribution map is rendered using color gradients and pushed to the operation and maintenance monitoring terminal to complete online monitoring.

6. A transmission line pollution online monitoring system, based on the transmission line pollution online monitoring method according to any one of claims 1 to 5, characterized in that: include, The perception modeling module is used to acquire multispectral polarization scattering data of the surface of transmission line insulators and construct a three-dimensional digital twin of the corresponding insulator; The component identification module is used to identify the component type and deposition intensity of the contaminant on the insulator surface based on the multispectral polarization scattering data, and generate a local contaminant feature vector. The status update module is used to spatially match the local contamination feature vector with the three-dimensional digital twin and update the surface contamination status parameters at the corresponding positions in the three-dimensional digital twin. The trend prediction module is used to combine updated surface contamination status parameters and meteorological forecast data to calculate the equivalent salt density evolution curve of the insulator in the future preset time period through a particle deposition dynamics model. The risk visualization module is used to generate a pollution risk level distribution map at the transmission line level based on the equivalent salt density evolution curve, and to complete online monitoring.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the online monitoring method for pollution of transmission lines according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the online monitoring method for pollution of transmission lines according to any one of claims 1 to 5.

Images