A method and system for evaluating the thermal de-icing effect of a substation post insulator

Abstract

The application provides a substation support insulator hot deicing effect evaluation method and system, and the method comprises the following steps: obtaining the temperature distribution of the deicing area based on the full aggregation infrared image of the deicing area of the substation support insulator; collecting the working parameters of the deicing robot and the environmental parameters of the substation support insulator; establishing the jet heat exchange model of the hot air deicing based on the temperature distribution, the working parameters and the environmental parameters; solving the jet heat exchange model to obtain the deicing time; constructing the hot deicing effect evaluation model based on the deicing time and the temperature distribution of the deicing area; and completing the hot deicing effect evaluation of the substation support insulator based on the hot deicing evaluation model. The application can evaluate the hot deicing effect of the substation support insulator, significantly improve the deicing efficiency and safety, and provide a strong guarantee for the stable operation of the power system.

Description

Technical Field

[0001] This invention belongs to the field of substation thermal de-icing technology, specifically relating to a method and system for evaluating the thermal de-icing effect of substation support insulators. Background Technology

[0002] In recent years, the rain, snow, and freezing weather have caused icing on power equipment, resulting in disasters for the power grid. In several substations, support insulators have been completely frozen and bridged. There have also been numerous incidents of flashovers and even explosions of coupling capacitors, current transformers (CTs), busbar support insulators, and disconnector support insulators due to icing. Furthermore, icing on substation structures can easily lead to tower deformation and collapse, causing substation outages and widespread power outages in surrounding areas. Therefore, safe and effective de-icing methods should be adopted after icing occurs at substations to prevent serious icing-related faults.

[0003] Currently, de-icing technologies for substation post insulators mainly include mechanical de-icing, coating methods, and thermal de-icing. Given the advantages of thermal de-icing in terms of efficiency and effectiveness, accurate evaluation of its performance is particularly important. However, existing technologies have some significant drawbacks that may affect the accuracy and reliability of the evaluation. These include limitations in data acquisition and processing, the complexity of model construction and solution (existing jet heat transfer models are overly simplified), the one-sidedness of evaluation indicators (single indicator evaluation makes the results insufficiently comprehensive and accurate), insufficient intelligence and automation (excessive manual intervention), and poor adaptability and scalability.

[0004] This invention proposes a method and system for evaluating the thermal de-icing effect of substation post insulators. The main focus is on detecting the surface temperature distribution of the insulators during the de-icing process. Based on real-time temperature data, the control strategy for de-icing operations and the robot's safe de-icing technology strategy are adjusted. Furthermore, the impact of factors such as hot air velocity, nozzle angle, hot air temperature, distance from the hot air outlet to the insulator surface, ice thickness, and ambient temperature on the de-icing effect is analyzed in real time. Through improvements to existing technologies, a more efficient and accurate evaluation of the thermal de-icing effect is achieved. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a method and system for evaluating the thermal de-icing effect of substation post insulators, enabling accurate evaluation and optimized control of the thermal de-icing effect, and providing strong support for the safe operation of substations.

[0006] To achieve the above objectives, the present invention provides the following solution:

[0007] A method for evaluating the thermal de-icing effect of substation post insulators includes the following steps:

[0008] The temperature distribution of the de-icing area is obtained based on the full-focus infrared image of the de-icing area of ​​the substation post insulator.

[0009] Collect operating parameters of the de-icing robot and environmental parameters of the substation support insulators;

[0010] Based on the temperature distribution, the operating parameters, and the environmental parameters, a jet heat transfer model for hot air de-icing is established; the jet heat transfer model is solved to obtain the de-icing time.

[0011] Based on the de-icing time and the temperature distribution in the de-icing area, a thermal de-icing effect evaluation model is constructed.

[0012] Based on the aforementioned thermal de-icing evaluation model, the thermal de-icing effect of substation support insulators was evaluated.

[0013] Preferably, the method for obtaining the temperature distribution of the de-icing area is as follows:

[0014] Infrared images of the de-icing area were acquired by mobile acquisition, resulting in a multi-focus infrared image sequence;

[0015] The multi-focus infrared image sequence is denoised to obtain a denoised infrared image sequence.

[0016] By synthesizing existing multifocus infrared image datasets, paired foreground and background focused images are obtained;

[0017] Based on the paired foreground and background images, a training set is constructed, and an image fusion network is trained based on the training set to obtain a focus planning map;

[0018] Based on the aggregation planning map, the denoised infrared image sequence is guided to perform image fusion to obtain a fully focused infrared image;

[0019] Based on the DFF 3D reconstruction algorithm, a 3D surface height map of the de-icing area of ​​the substation support insulator is reconstructed from a multi-focus infrared image sequence with focus position information.

[0020] Based on the fully focused infrared image and the three-dimensional surface height map, the temperature distribution of the de-icing area is obtained.

[0021] Preferably, the method for constructing a training set based on the paired foreground and background images is as follows:

[0022] Semantic segmentation of foreground objects is performed on the original images in the existing multi-focus infrared image dataset. The mask of semantic segmentation is binarized to obtain the mask binary map.

[0023] Image segmentation is performed based on the mask binary image and the original image to obtain a first foreground image and a first background image;

[0024] Based on the diffusion function, a second foreground image and a second background image of the original image are obtained;

[0025] Add the first foreground image and the second background image to obtain a foreground-clustered image;

[0026] The second foreground image and the first background image are added together to obtain a background aggregated image;

[0027] The training set is obtained based on the foreground clustered image and the background clustered image.

[0028] Preferably, the image fusion network includes convolutional layers, residual blocks, a global perception fusion module, and a bilinear upsampling layer; the method for training the image fusion network based on the training set to obtain the focus planning map is as follows:

[0029] Based on two convolutional neural network branches with shared weights, multi-scale features of the foreground clustered image and the background clustered image are extracted respectively;

[0030] Based on the global perception fusion module, the multi-scale features extracted by the two convolutional neural network branches are concatenated to obtain a concatenated feature map.

[0031] The cascaded feature maps are subjected to average pooling to obtain multi-scale pooled feature maps;

[0032] The multi-scale pooling feature map is upsampled to the same preset spatial resolution to obtain a fused feature map;

[0033] The fused feature map is input into the decoder of the residual block to obtain the aggregation planning map.

[0034] Preferably, the operating parameters of the de-icing robot include hot air speed, nozzle angle, hot air temperature, and distance from the hot air outlet to the insulator surface.

[0035] Environmental parameters for substation support insulators include ice thickness and ambient temperature.

[0036] Preferably, the method for establishing a jet heat transfer model for hot air de-icing based on the temperature distribution, the operating parameters, and the environmental parameters is as follows:

[0037] Based on the temperature distribution, the surface temperature of the insulator is obtained;

[0038] Based on the aforementioned operating parameters, the convective heat transfer coefficient is obtained;

[0039] Based on the convective heat transfer coefficient and the surface temperature of the insulator, the heat flux density per unit area of ​​the insulator is obtained;

[0040] An energy balance equation is constructed based on the insulator surface area directly affected by hot air, the de-icing time, and the ice thickness.

[0041] Based on the energy balance equation, the jet heat transfer model is obtained.

[0042] The present invention also provides a system for evaluating the thermal de-icing effect of substation post insulators, for implementing the method, comprising:

[0043] The temperature distribution acquisition module is used to obtain the temperature distribution of the de-icing area based on the full-focus infrared image of the de-icing area of ​​the substation post insulator.

[0044] The parameter acquisition module is used to collect the working parameters of the de-icing robot and the environmental parameters of the substation support insulators.

[0045] The jet heat transfer model construction module is used to establish a jet heat transfer model for hot air de-icing based on the temperature distribution, the operating parameters, and the environmental parameters; and to solve the jet heat transfer model to obtain the de-icing time.

[0046] The evaluation model construction module is used to construct a thermal de-icing effect evaluation model based on the de-icing time and the temperature distribution of the de-icing area.

[0047] The evaluation module is used to evaluate the thermal de-icing effect of substation support insulators based on the aforementioned thermal de-icing evaluation model.

[0048] Preferably, it also includes a background display module, which is used to record images of insulators before and after de-icing, create a 3D map, and dynamically display the de-icing status of substation support insulators.

[0049] Compared with existing technologies, the beneficial effects of this invention are as follows: By establishing an accurate jet heat transfer model and a thermal de-icing effect evaluation model, a scientific evaluation of thermal de-icing technology is achieved. This helps to identify potential problems in the de-icing process and propose improvement measures. The evaluation results can optimize de-icing parameter settings, improving de-icing efficiency and safety. This helps to reduce energy consumption and operation and maintenance costs. The evaluation results provide important decision support for substation operation and maintenance personnel. They can select appropriate de-icing schemes and equipment configurations based on the evaluation results to ensure the stable operation of the power system. Attached Figure Description

[0050] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments are briefly introduced below. Obviously, the 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.

[0051] Figure 1This is a flowchart of the method for evaluating the thermal de-icing effect of substation post insulators according to an embodiment of the present invention;

[0052] Figure 2 This is a graph showing the relationship between hot air velocity and de-icing time at different hot air temperatures, according to an embodiment of the present invention.

[0053] Figure 3 This is a graph showing the relationship between hot air temperature and de-icing time under different hot air velocities in an embodiment of the present invention.

[0054] Figure 4 This is a flowchart illustrating the process of obtaining the jet heat transfer model in an embodiment of the present invention;

[0055] Figure 5 This is a flowchart illustrating the image denoising process according to an embodiment of the present invention;

[0056] Figure 6 This is a flowchart illustrating how a training set is constructed based on paired foreground and background images, according to an embodiment of the present invention.

[0057] Figure 7 This is a flowchart for obtaining the aggregation planning diagram in an embodiment of the present invention. Detailed Implementation

[0058] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0059] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0060] Example 1

[0061] like Figure 1 As shown, a method for evaluating the thermal de-icing effect of substation post insulators includes the following steps:

[0062] S1: Based on the full-focus infrared image of the de-icing area of ​​the substation post insulator, the temperature distribution of the de-icing area is obtained; a further implementation method is as follows:

[0063] S11: A robotic arm-infrared thermal imager is used to move and collect infrared images of the de-icing area to obtain a multi-focus infrared image sequence. In this embodiment, based on the characteristic that infrared images can accurately reflect the temperature information of the measured object under focusing conditions, multi-focus image fusion technology is used to obtain a full-focus infrared image. The infrared camera is moved in a direction perpendicular to the surface of the measured object, and a series of infrared images are collected regularly with a distance interval not exceeding one depth of field. The working principle of the infrared thermal imager is that as long as the temperature of the object is higher than absolute zero (273.15℃), it will emit infrared radiation. The energy of this radiation is proportional to the temperature of the object. The higher the temperature, the stronger the emitted infrared radiation. The core component of the infrared thermal imager is the infrared detector, which can be a detector based on different technologies, such as uncooled (e.g., microbolometer) or cooled (e.g., quantum trap detector). Uncooled detectors are characterized by low cost, small size, and low power consumption. The advantages of the infrared thermal imager used in this invention are: (1) It can work in all weather conditions and is not limited by light conditions. It can work normally even in a completely dark environment; (2) It is a non-contact measurement. It does not require direct contact with the object to measure its surface temperature. (3) Visualization can intuitively display the temperature distribution of an object, making it easy to analyze and record.

[0064] S12: As Figure 5 As shown, denoising processing is performed on the multi-focus infrared image sequence to obtain a denoised infrared image sequence; specifically, based on the characteristics of infrared images and the actual noise situation, the spatial domain standard deviation (σ) of the bilateral filter is set. d ) and intensity domain standard deviation (σ r These two parameters control the weights of spatial smoothness and intensity similarity, respectively. During the filtering process, the weight of each pixel is calculated based on spatial distance and intensity difference, and a weighted average is calculated as the output pixel value. Each denoised frame is stored in a new storage location or overwrites the original image. The quality of the denoised infrared image sequence is evaluated. In this embodiment, the signal-to-noise ratio (SNR) and peak signal-to-noise ratio (PSNR) are calculated to verify the denoising effect.

[0065] S13: Synthesize the existing multi-focus infrared image dataset to obtain paired foreground and background focused images; construct a training set based on the paired foreground and background clustered images, and train an image fusion network based on the training set to obtain a focus planning map;

[0066] S14: Based on the aggregation planning graph, guide the image fusion of the denoised infrared image sequence to obtain a fully focused infrared image;

[0067] S15: Based on the DFF (Depth of Focus) 3D reconstruction algorithm, a 3D surface height map of the de-icing area of ​​the substation support insulator is reconstructed from a multi-focus infrared image sequence with focus position information.

[0068] S16: Based on the full-focus infrared image and the three-dimensional surface height map, the temperature distribution of the de-icing area is obtained.

[0069] A further implementation method is, such as Figure 6 As shown, in step S13, the method for constructing the training set based on paired foreground and background images is as follows:

[0070] Semantic segmentation of foreground objects is performed on the original images in the existing multi-focus infrared image dataset. The mask of semantic segmentation is binarized to obtain a mask binary map. The pixel value of the foreground is set to 1, and the pixel value of the background is set to 0.

[0071] Image segmentation is performed based on the mask binary image and the original image to obtain the first foreground image and the first background image;

[0072] Based on the diffusion function, a second foreground image and a second background image of the original image are obtained;

[0073] Add the first foreground image and the second background image to obtain the foreground clustered image;

[0074] Add the second foreground image and the first background image to obtain the background aggregated image;

[0075] The training set is obtained based on the foreground clustered image and the background clustered image.

[0076] A further implementation method is, such as Figure 7 As shown, in step S13, the image fusion network adopts a U-shaped network structure, which includes convolutional layers, residual blocks, a global perception fusion module, and a bilinear upsampling layer. The method for training the image fusion network based on the training set to obtain the focus planning map is as follows:

[0077] Based on two convolutional neural network branches (encoders) with shared weights, multi-scale features are extracted from the foreground and background clustered images, respectively. These multi-scale features include rich information ranging from low to high levels and from local to global perspectives.

[0078] Based on a global perception fusion module, multi-scale features extracted from two convolutional neural network branches are concatenated to obtain a cascaded feature map; global semantic prior constraints and multi-scale information can be preserved simultaneously. The cascaded feature map forms a hierarchical structure by chaining multiple models or algorithms together. After each model or algorithm processes the feature map, its output is used as the input to the next model, thereby progressively improving the feature representation capability and task accuracy. This method allows tasks to share more network parameters and enables mutual assistance among tasks, improving overall performance.

[0079] Average pooling is performed on the cascaded feature maps to obtain multi-scale pooled feature maps; the multi-scale pooled feature maps include useful feature information extracted from different image scales.

[0080] The multi-scale pooling feature map is upsampled to the same preset spatial resolution to obtain the fused feature map; the fused feature map contains both global semantic information and multi-scale details.

[0081] The fused feature map is input into the decoder of the residual block to obtain a clustering planning map, which represents the clustered regions of foreground and background in the image and their distribution. Specifically, based on the clustering planning map, the formula guiding image fusion of the denoised infrared image sequence is as follows:

[0082] F = I A ×M+I B ×(1-M),

[0083] F represents a fully focused infrared image, I A and I B This is the original image; M represents the focused planning map.

[0084] In step S15, the specific implementation process of the DFF (Depth of Focus) 3D reconstruction algorithm is as follows: For each pixel, the Laplacian operator is used to calculate its focus in images at different focus positions; for each pixel, the image with the highest focus is selected as the optimal focus image for that point. This indicates that the focus depth of the image at that point is closest to the actual depth. Based on the infrared camera calibration and the insulator geometric model, the optimal focus position of each pixel is mapped to the corresponding depth value to determine the correspondence between focus position and depth. Using the depth map, the two-dimensional coordinates and depth values ​​of each pixel are converted into points in three-dimensional space to construct point cloud data. Using the point cloud data, a three-dimensional surface is fitted using the triangulation method. The reconstructed three-dimensional surface is optimized and smoothed to eliminate noise and unevenness, obtaining a three-dimensional surface height map.

[0085] S2: Collect the working parameters of the de-icing robot and the environmental parameters of the substation support insulators; a further implementation method is that the working parameters of the de-icing robot include hot air velocity, nozzle angle, hot air temperature and the distance from the hot air outlet to the surface of the insulator.

[0086] Environmental parameters for substation support insulators include ice thickness and ambient temperature.

[0087] S3: As Figure 4As shown, a jet heat transfer model for hot air de-icing is established based on temperature distribution, operating parameters, and environmental parameters; the de-icing time is obtained by solving the jet heat transfer model; a further implementation method is as follows:

[0088] The surface temperature of the insulator is obtained based on the temperature distribution;

[0089] Based on the operating parameters, the convective heat transfer coefficient is obtained;

[0090] Based on the convective heat transfer coefficient and the insulator surface temperature, the heat flux density per unit area of ​​the insulator is obtained; the specific calculation formula is as follows:

[0091] q = h(T) h -T s ),

[0092] Where q represents the heat flux density per unit area of ​​the insulator, h represents the convective heat transfer coefficient (affected by factors such as wind speed, distance, and angle), and T s This represents the surface temperature of the insulator (close to the temperature of ice).

[0093] Based on the insulator surface area directly affected by hot air, de-icing time, and ice thickness, an energy balance equation is constructed:

[0094]

[0095] Where A is the surface area of ​​the insulator directly affected by the hot air, t is time, and ρ is the surface area of ​​the insulator. i It is the density of ice, L f L is the latent heat of melting of ice, L0 is the initial ice thickness, and L(t) is the remaining ice thickness as time changes.

[0096] Based on the energy balance equation, a jet heat transfer model is obtained. Specifically, substituting the heat flux density q into the energy balance equation yields the expression for the jet heat transfer model:

[0097]

[0098] S4: Based on the de-icing time and the temperature distribution in the de-icing area, construct a thermal de-icing effect evaluation model; such as... Figure 2 , Figure 3 As shown.

[0099] In this embodiment, the formula for the thermal de-icing effect evaluation model is as follows:

[0100]

[0101] In the formula, Q NThe heat required to de-ice each section of the post insulator is represented in J; m0 represents the mass of ice melted in each section, in kg; T ice Represents the initial temperature of the ice layer, in °C; m fall c represents the mass of ice that did not melt into water and detach; ice γ represents the specific heat of ice, J (kg·℃); γ represents the latent heat of phase transition between ice and water, J / kg.

[0102] Specifically, in this embodiment, based on the jet heat transfer model and the thermal de-icing effect evaluation model, the effects of hot air velocity, nozzle angle, hot air temperature, distance from the hot air outlet to the insulator surface, ice thickness, and ambient temperature on the de-icing effect were analyzed. In this embodiment, an insulator sample library with different degrees of icing was also constructed, and the thermal de-icing effect evaluation model was used to obtain the de-icing effect of different influencing factors on insulator samples with different degrees of icing. The degree of icing was obtained by measuring the thickness and density of the ice.

[0103] Hot air velocity: Increasing the air velocity can improve the convective heat transfer coefficient, thereby accelerating the de-icing speed, but it may also reduce the residence time of hot air on the insulator surface, affecting the heat exchange efficiency.

[0104] Nozzle angle: Optimizing the angle ensures that the hot air jet better covers the insulator surface, improving de-icing efficiency.

[0105] Hot air temperature: Increasing the hot air temperature can increase the heat transferred to the ice layer, but care must be taken to avoid overheating the insulator.

[0106] Distance from hot air outlet to insulator surface: Reducing the distance can enhance the concentration of the jet and the heat exchange efficiency, but too close a distance may lead to local overheating.

[0107] Ice thickness: Thicker ice layers require more heat to melt, so de-icing takes longer.

[0108] Ambient temperature: Although ambient temperature has little effect on the direct de-icing effect, it affects the temperature difference driving force of the heat exchange process, thus affecting the heat exchange efficiency.

[0109] S5: Based on the thermal de-icing evaluation model, complete the evaluation of the thermal de-icing effect of substation support insulators.

[0110] In this embodiment, response surface methodology based on the Box-Behnken Designs central composite design model is used to fit the factors influencing thermal de-icing effect and de-icing time.

[0111] The method for obtaining the significant relationship between influencing factors and de-icing time is as follows:

[0112] Based on response surface methodology, the response values ​​of influencing factors and regression equations were obtained.

[0113] Based on the regression analysis equation, a one-way ANOVA was performed on the influencing factors and their response values ​​to obtain the F-value of the F-statistic and the probability P-value.

[0114] Based on the magnitude of the F-value and the probability P-value, the significant relationship between de-icing time and influencing factors is determined.

[0115] This invention employs a response surface model constructed through regression analysis for experimentation. This effectively estimates the model parameters and assesses the interactions between various factors, recording the input variables (such as hot air velocity and temperature) and output responses (such as de-icing time) for each experiment. This ensures the stability and repeatability of the experimental conditions. By plotting response surface diagrams and contour maps, the impact of each factor on the de-icing effect and the interactions between factors can be visually observed. Simultaneously, a genetic algorithm is used to search for the optimal combination of influencing factors under model constraints. Through the optimal combination of influencing factors, the operating parameters of the de-icing robot are optimized, achieving efficient de-icing.

[0116] Example 2

[0117] This invention also provides a system for evaluating the thermal de-icing effect of substation post insulators, and a method for implementing this system, comprising:

[0118] The temperature distribution acquisition module is used to obtain the temperature distribution of the de-icing area based on the full-focus infrared image of the de-icing area of ​​the substation post insulator.

[0119] The parameter acquisition module is used to collect the working parameters of the de-icing robot and the environmental parameters of the substation support insulators.

[0120] The jet heat transfer model building module is used to establish a jet heat transfer model for hot air de-icing based on temperature distribution, operating parameters, and environmental parameters; and to solve the jet heat transfer model to obtain the de-icing time.

[0121] The evaluation model building module is used to build a thermal de-icing effect evaluation model based on de-icing time and temperature distribution in the de-icing area;

[0122] The evaluation module is used to evaluate the thermal de-icing effect of substation post insulators based on the thermal de-icing evaluation model.

[0123] A further implementation method includes a background display module for recording images of insulators before and after de-icing, creating a 3D map, and dynamically displaying the de-icing status of substation support insulators.

[0124] The evaluation system provided by this invention can be seamlessly integrated with the de-icing robot system, enabling the de-icing robot to evaluate its work performance while operating, thus achieving automated control and optimization of the de-icing process.

[0125] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made to the technical solutions of the present invention by those skilled in the art without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A method for evaluating the thermal de-icing effect of substation post insulators, characterized in that, Includes the following steps: The temperature distribution of the de-icing area is obtained based on the full-focus infrared image of the de-icing area of ​​the substation post insulator. Collect operating parameters of the de-icing robot and environmental parameters of the substation support insulators; Based on the temperature distribution, the operating parameters, and the environmental parameters, a jet heat transfer model for hot air de-icing is established; the jet heat transfer model is solved to obtain the de-icing time. Based on the de-icing time and the temperature distribution in the de-icing area, a thermal de-icing effect evaluation model is constructed; the formula for the thermal de-icing effect evaluation model is as follows: ， In the formula, Q N The heat required to de-ice each section of the post insulator is represented in J; m0 represents the mass of ice melted in each section, in kg; T ice Represents the initial temperature of the ice layer, in °C; m fall c represents the mass of ice that did not melt into water and detach; ice γ represents the specific heat of ice, J (kg·℃); γ represents the latent heat of phase transition between ice and water, J / kg; Based on the aforementioned thermal de-icing effect evaluation model, the thermal de-icing effect evaluation of substation support insulators was completed.

2. The method for evaluating the thermal de-icing effect of substation post insulators according to claim 1, characterized in that, The method for obtaining the temperature distribution of the de-icing area is as follows: Infrared images of the de-icing area were acquired by mobile acquisition, resulting in a multi-focus infrared image sequence; The multi-focus infrared image sequence is denoised to obtain a denoised infrared image sequence. By synthesizing existing multifocus infrared image datasets, paired foreground and background focused images are obtained; Based on the paired foreground and background focused images, a training set is constructed, and an image fusion network is trained based on the training set to obtain a focus planning map; Based on the focusing planning map, the denoised infrared image sequence is guided to perform image fusion to obtain a fully focused infrared image; Based on the DFF 3D reconstruction algorithm, a 3D surface height map of the de-icing area of ​​the substation support insulator is reconstructed from a multi-focus infrared image sequence with focus position information. Based on the fully focused infrared image and the three-dimensional surface height map, the temperature distribution of the de-icing area is obtained.

3. The method for evaluating the thermal de-icing effect of substation post insulators according to claim 2, characterized in that, The method for constructing a training set based on the paired foreground and background focused images is as follows: Semantic segmentation of foreground objects is performed on the original images in the existing multi-focus infrared image dataset. The mask of semantic segmentation is binarized to obtain the mask binary map. Image segmentation is performed based on the mask binary image and the original image to obtain a first foreground image and a first background image; Based on the diffusion function, a second foreground image and a second background image of the original image are obtained; Add the first foreground image and the second background image to obtain a foreground focused image; The second foreground image and the first background image are added together to obtain a background focused image; The training set is obtained based on the foreground focused image and the background focused image.

4. The method for evaluating the thermal de-icing effect of substation post insulators according to claim 3, characterized in that, The image fusion network includes convolutional layers, residual blocks, a global perception fusion module, and a bilinear upsampling layer; the method for training the image fusion network based on the training set to obtain the focus planning map is as follows: Based on two convolutional neural network branches with shared weights, multi-scale features of the foreground focused image and the background focused image are extracted respectively; Based on the global perception fusion module, the multi-scale features extracted by the two convolutional neural network branches are concatenated to obtain a concatenated feature map. The cascaded feature maps are subjected to average pooling to obtain multi-scale pooled feature maps; The multi-scale pooling feature map is upsampled to the same preset spatial resolution to obtain a fused feature map; The fused feature map is input into the decoder of the residual block to obtain the focusing planning map.

5. The method for evaluating the thermal de-icing effect of substation post insulators according to claim 1, characterized in that, The operating parameters of the de-icing robot include hot air speed, nozzle angle, hot air temperature, and the distance from the hot air outlet to the insulator surface; Environmental parameters for substation support insulators include ice thickness and ambient temperature.

6. The method for evaluating the thermal de-icing effect of substation post insulators according to claim 5, characterized in that, Based on the temperature distribution, the operating parameters, and the environmental parameters, the method for establishing a jet heat transfer model for hot air de-icing is as follows: Based on the temperature distribution, the surface temperature of the insulator is obtained; Based on the aforementioned operating parameters, the convective heat transfer coefficient is obtained; Based on the convective heat transfer coefficient and the surface temperature of the insulator, the heat flux density per unit area of ​​the insulator is obtained; An energy balance equation is constructed based on the insulator surface area directly affected by hot air, the de-icing time, and the ice thickness. Based on the energy balance equation, the jet heat transfer model is obtained.

7. A system for evaluating the thermal de-icing effect of substation post insulators, used to implement the method described in any one of claims 1-6, characterized in that, include: The temperature distribution acquisition module is used to obtain the temperature distribution of the de-icing area based on the full-focus infrared image of the de-icing area of ​​the substation post insulator; The parameter acquisition module is used to collect the working parameters of the de-icing robot and the environmental parameters of the substation support insulators. The jet heat transfer model construction module is used to establish a jet heat transfer model for hot air de-icing based on the temperature distribution, the operating parameters, and the environmental parameters; and to solve the jet heat transfer model to obtain the de-icing time. The evaluation model construction module is used to construct a thermal de-icing effect evaluation model based on the de-icing time and the temperature distribution of the de-icing area. The evaluation module is used to evaluate the thermal de-icing effect of substation support insulators based on the aforementioned thermal de-icing effect evaluation model.

8. The substation post insulator thermal de-icing effect evaluation system according to claim 7, characterized in that, It also includes a background display module, which records images of insulators before and after de-icing, creates a 3D map, and dynamically displays the de-icing status of substation support insulators.

Images