Icing experiment method and system based on portal frame icing experiment platform

Abstract

The invention discloses an icing experiment method and system based on a portal frame icing test platform, and relates to the technical field of power transmission line image recognition, and the method comprises the steps: arranging a simulation wire on a portal frame, setting an icing experiment environment condition, and starting an icing experiment; video monitoring is started, and the process from icing to complete icing of the wire is recorded; and measuring the weight change of the wire caused by icing, analyzing the weight distribution of an ice layer and the potential influence on the structure of the wire, and evaluating the physical influence of icing on the simulated wire. According to the icing experiment method based on the portal frame icing experiment platform, the icing process is analyzed through video monitoring, and multi-dimensional risk assessment is carried out in combination with finite element analysis and an assessment model. Through a contrast experiment on a standard lead, an expanded-diameter lead and a super-hydrophobic lead, the effects of different improvement measures are verified, and an optimal lead is selected.

Description

Technical Field

[0001] The present invention relates to the technical field of power transmission line image recognition, and in particular to an icing test method and system based on a portal frame icing test platform. Background Art

[0002] Power lines are often affected by ice in severe winter weather conditions. Ice increases the weight and wind load of the conductors, causing increased conductor sag, and may even cause serious accidents such as conductor breakage and tower collapse. In order to prevent these accidents, a variety of protective measures are usually adopted, such as increasing the diameter of the conductors and applying super-hydrophobic materials. However, the effects of different protective measures vary in actual applications and need to be verified and evaluated through experiments.

[0003] Traditional icing test methods mainly include natural icing test and artificial icing test. Natural icing test depends on natural weather conditions, has a long period and is difficult to control; artificial icing test can obtain experimental data in a short time by simulating the icing environment. However, traditional artificial icing test methods still have some shortcomings in the simulation of experimental environment, data collection and analysis, making it difficult to comprehensively and accurately evaluate the impact of icing on conductors. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problems solved by the present invention are: the existing icing experimental methods have the problems of difficult control of the experimental environment, insufficient accuracy of data collection and analysis, and how to scientifically evaluate and optimize the wire icing protection measures.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an icing test method based on a portal frame icing test platform, comprising:

[0007] Arrange the simulated wires on the portal frame, set the icing test environment conditions, and start the icing test;

[0008] Start video monitoring to record the process from the beginning of ice formation to complete ice coverage of the wire;

[0009] Measure the change in conductor weight caused by icing, analyze the weight distribution of ice and its potential impact on conductor structure, and evaluate the physical impact of icing on simulated conductors.

[0010] As a preferred solution of the icing test method based on the portal frame icing test platform of the present invention, wherein: the simulated wire includes a first simulated wire, a second simulated wire and a third simulated wire;

[0011] The first simulated wire is a standard comparison simulated wire;

[0012] The diameter of the second simulated wire is increased according to preset specifications compared with the first simulated wire;

[0013] Compared with the first simulated wire, the surface of the third simulated wire is coated with super-hydrophobic material.

[0014] As a preferred solution of the icing test method based on the portal frame icing test platform described in the present invention, the setting of the icing test environmental conditions includes obtaining historical meteorological data to determine typical winter meteorological conditions, determining temperature, humidity and wind speed, and using a spray device and a fan to simulate precipitation and wind.

[0015] As a preferred solution of the ice coating test method based on the portal frame ice coating test platform described in the present invention, wherein: the process of recording the wire from the beginning of icing to complete icing includes setting a camera to capture the image data of each simulated wire, performing data preprocessing on the image data, the preprocessing includes range adjustment, denoising, image sharpening and geometric correction, inputting the preprocessed image into a deep convolutional neural network CNN, configuring a multi-task learning architecture, extracting the features of ice coating shape, thickness and distribution, and processing each feature branch through a fully connected layer;

[0016] Conditional random field (CRF) is introduced to use the extracted features to model the spatial relationship between pixels in the image and mark the time nodes of the ice development stage during video monitoring, including the initial formation of the ice layer, reaching the predetermined thickness and starting to fall off.

[0017] As a preferred embodiment of the icing test method based on the portal frame icing test platform described in the present invention, the measuring of the weight change of the conductor caused by icing includes measuring the weight of each simulated conductor as W1, W2, W3 and W4 at the starting time point of initial formation of the ice layer, the starting and ending time points of reaching a predetermined thickness, and the starting time point when the ice layer begins to fall off, determining the weight change ΔWi in each stage, performing finite element analysis, constructing a stress function and a displacement function based on the analysis results, and constructing a risk assessment model.

[0018] As a preferred solution of the icing test method based on the portal frame icing test platform of the present invention, the finite element analysis is expressed as:

[0019] F i =ΔW i ·g

[0020]

[0021] Where, ΔW i Indicates the weight change at each stage, F i is the force caused by the change in weight, g is the gravitational acceleration constant, and qi is the uniform load per unit length, L is the length of the wire, M i is the bending moment caused by uniformly distributed load, σ max is the maximum stress, y is the distance from the outer edge of the conductor section to the neutral axis, I is the moment of inertia of the conductor section, δ max is the maximum displacement of the conductor under the weight of ice, and E is the Young's modulus of the conductor material;

[0022] The stress function is expressed as,

[0023]

[0024] The displacement function is expressed as,

[0025]

[0026] The risk assessment model is expressed as,

[0027]

[0028] Among them, f(σ max,i ) represents the stress function, represents the exponential decay of stress, x is the integral variable, σ crit is the critical stress, g(δ max,i ) represents the displacement function, k is the number of terms to be summed, δ crit is the critical displacement, RI i represents the comprehensive risk index of each wire, γ represents the normalization factor, α and β represent the weighting factors, and n is the number of stages.

[0029] As a preferred solution of the icing test method based on the portal frame icing test platform described in the present invention, the evaluation of the physical impact of icing on the simulated conductor includes analyzing the comprehensive risk index of the first simulated conductor, the second simulated conductor and the third simulated conductor, and comprehensively evaluating and selecting the optimal conductor for application in the icing environment.

[0030] Another object of the present invention is to provide an icing test system based on a portal frame icing test platform, which can solve the problems of uncontrollable experimental environment, inaccurate data collection and analysis, and difficulty in comprehensively evaluating the performance and risk of conductors under icing conditions in existing icing test methods by constructing an icing test system based on a portal frame icing test platform.

[0031] In order to solve the above technical problems, the present invention provides the following technical solutions: an icing experiment system based on a portal frame icing test platform, comprising: an environmental simulation module, a video monitoring module and an evaluation and analysis module; the environmental simulation module is used to arrange simulated wires on the portal frame, set the icing experiment environmental conditions, and start the icing experiment; the video monitoring module is used to start video monitoring and record the process from the beginning of icing to complete icing of the wire; the evaluation and analysis module is used to measure the weight change of the wire caused by icing, analyze the weight distribution of the ice layer and the potential impact on the wire structure, and evaluate the physical impact of icing on the simulated wire.

[0032] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned icing test method based on a portal frame icing test platform when executing the computer program.

[0033] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the icing test method based on a portal frame icing test platform as described above.

[0034] Beneficial effects of the present invention: The icing test method based on the portal frame icing test platform provided by the present invention uses video monitoring to analyze the icing process, and combines finite element analysis and evaluation models to perform multi-dimensional risk assessment. Through comparative experiments on standard wires, expanded diameter wires and super-hydrophobic wires, the effects of different improvement measures are verified, and the optimal wire is selected. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use 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 ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0036] Figure 1 An overall flow chart of an icing test method based on a portal frame icing test platform provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0038] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0039] Example 1

[0040] Reference Figure 1 , which is an embodiment of the present invention, provides an icing test method based on a portal frame icing test platform, comprising:

[0041] Arrange the simulated wires on the portal frame, set the icing test environment conditions, and start the icing test;

[0042] Start video monitoring to record the process from the beginning of ice formation to complete ice coverage of the wire;

[0043] Measure the change in conductor weight caused by icing, analyze the weight distribution of ice and its potential impact on conductor structure, and evaluate the physical impact of icing on simulated conductors.

[0044] The simulated wires include a first simulated wire, a second simulated wire and a third simulated wire;

[0045] The first simulated wire is a standard comparison simulated wire;

[0046] The diameter of the second simulated wire is increased according to preset specifications compared with the first simulated wire;

[0047] Compared with the first simulated wire, the surface of the third simulated wire is coated with super-hydrophobic material.

[0048] The setting of the icing experiment environmental conditions includes obtaining historical meteorological data to determine typical winter meteorological conditions, determining temperature, humidity and wind speed, and using a spray device and a fan to simulate precipitation and wind.

[0049] The process of recording the wire from the beginning of ice formation to complete ice coverage includes setting a camera to capture image data of each simulated wire, performing data preprocessing on the image data, wherein the preprocessing includes range adjustment, denoising, image sharpening and geometric correction, inputting the preprocessed image into a deep convolutional neural network CNN, configuring a multi-task learning architecture, extracting features of ice shape, thickness and distribution, and processing each feature branch through a fully connected layer;

[0050] Conditional random field (CRF) is introduced to use the extracted features to model the spatial relationship between pixels in the image and mark the time nodes of the ice development stage during video monitoring, including the initial formation of the ice layer, reaching the predetermined thickness and starting to fall off.

[0051] The range adjustment is expressed as,

[0052]

[0053] Where I represents the original image data, min(I) represents the minimum value of the image data, max(I) represents the maximum value of the image data, and I adj Represents the adjusted image data, normalizing the pixel values ​​to the [0,1] interval.

[0054] Denoising is expressed as,

[0055] I dn =median_filter(I adj ,k)

[0056] Among them, I dn represents the denoised image, median_filter represents the median filter function, and k represents the filter window size.

[0057] Image sharpening is expressed as,

[0058] I sh =I dn +(I dn -Gaussian_blur(I dn ,σ))

[0059] Among them, I sh It represents the result after image sharpening, Gaussian_blur represents the Gaussian blur function, and σ represents the standard deviation of Gaussian blur.

[0060] Geometric Correction Representation

[0061] I cor =geometric_correction(I sh ,H

[0062] Among them, I cor Represents the image after geometric correction, geometric_correction represents the geometric correction function, and H represents the geometric transformation matrix.

[0063] Feature extraction

[0064] The preprocessed image is input into a deep convolutional neural network (CNN) and a multi-task learning architecture is configured to extract the features of ice shape, thickness and distribution. Each feature branch is processed through a fully connected layer.

[0065] The feature extraction formula is expressed as:

[0066] S p =W s·flatten(A)+b s

[0067] T p =W t ·flatten(A)+b t

[0068] D p =W d flatten(A)+b d

[0069] Where A represents the output feature map of CNN, which represents the feature representation of the image in the deep learning model. Flatten(A) means flattening the output feature map of CNN into a one-dimensional vector. s ,W t ,W d The weight matrix representing the features is used to map the flattened features to shape, thickness, and distribution features, b s ,b t ,b d Represents the bias term, adjusting the result of feature mapping, S p represents the shape feature of pixel p, T p represents the thickness feature of pixel p, D p Represents the distribution characteristics of pixel p.

[0070] The conditional random field (CRF) model is used to integrate features and consider the spatial relationship between pixels to label the ice-covered stage.

[0071] The unit potential function is expressed as

[0072] φ(s)=-logP(s|S,T,D)

[0073] Among them, φ(s) represents the unit potential energy of state s, and P(s|S,T,D) represents the probability of state s given features S,T,D.

[0074] The pairwise potential function is expressed as

[0075] ψ(s t ,s t+1 )=w·exp(-β||[S t ,T t ,D t ]-[S t+1 ,T t+1 ,D t+1 ]|| 2 )·[s t ≠s t+1 ]

[0076] Among them, ψ(s t,s t+1 ) represents the pairwise potential energy at time points t and t+1, w represents the weight parameter of the pairwise potential function, β represents the parameter of the pairwise potential function, which is used to adjust the influence of similarity, [S t ,T t ,D t ] represents the feature vector at time point t, [S t+1 ,T t+1 ,D t+1 ] represents the feature vector at time point t+1, ||·|| 2 represents the square of the Euclidean distance, [s t ≠s t+1 ] represents the indicator function, when s t Not equal to s t+1 1 if the value is 0, otherwise it is 0.

[0077] The total energy formula is expressed as

[0078]

[0079] Among them, TotalEnergy represents the total energy of the entire wire in the entire time period, T represents the set of all time points in the time period, φ(s t ) means that time point t is in state s t The unit energy under represents the set of all pairs of consecutive time points in the time period, ψ(s t ,s t+1 ) indicates that time points t and t+1 are in state s t and t+1 The pair energy under .

[0080] The minimized total energy is expressed as

[0081]

[0082] Among them, s * represents the optimal state configuration, which represents the optimal state sequence of the entire wire in the entire time period, argmin s It means finding the state configuration s that minimizes the total energy.

[0083] The method of measuring the weight change of the conductor caused by ice coating includes measuring the weight of each simulated conductor as W1, W2, W3 and W4 at the starting time point of initial formation of the ice layer, the starting and ending time points of reaching a predetermined thickness, and the starting time point of ice layer falling off, determining the weight change ΔWi in each stage, performing finite element analysis, constructing stress function and displacement function based on the analysis results, and constructing a risk assessment model.

[0084] The finite element analysis is expressed as,

[0085] F i =ΔW i ·g

[0086]

[0087] Where, ΔW i Indicates the weight change at each stage, F i is the force caused by the change in weight, g is the gravitational acceleration constant, and q i is the uniform load per unit length, L is the length of the wire, M i is the bending moment caused by uniformly distributed load, σ max is the maximum stress, y is the distance from the outer edge of the conductor section to the neutral axis, I is the moment of inertia of the conductor section, δ max is the maximum displacement of the conductor under the weight of ice, and E is the Young's modulus of the conductor material;

[0088] The stress function is expressed as,

[0089]

[0090] The displacement function is expressed as,

[0091]

[0092] The risk assessment model is expressed as,

[0093]

[0094] Among them, f(σ max,i ) represents the stress function, represents the exponential decay of stress, x is the integral variable, σ crit is the critical stress, g(δ max,i ) represents the displacement function, k is the number of terms to be summed, δ crit is the critical displacement, RI i represents the comprehensive risk index of each wire, γ represents the normalization factor, α and β represent the weighting factors, and n is the number of stages.

[0095] The evaluation of the physical impact of ice coating on the simulated conductor includes analyzing the comprehensive risk index of the first simulated conductor, the second simulated conductor and the third simulated conductor, and comprehensively evaluating and selecting the optimal conductor for application in an ice coating environment.

[0096] Example 2

[0097] According to an embodiment of the present invention, an icing test system based on a portal frame icing test platform is provided, comprising:

[0098] Environmental simulation module, video monitoring module and evaluation and analysis module;

[0099] The environmental simulation module is used to arrange simulated wires on the portal frame, set the environmental conditions of the icing experiment, and start the icing experiment;

[0100] The video monitoring module is used to start video monitoring and record the process from the beginning of icing to the complete icing of the wire;

[0101] The evaluation and analysis module is used to measure the weight change of the conductor caused by ice coating, analyze the weight distribution of the ice layer and the potential impact on the conductor structure, and evaluate the physical impact of ice coating on the simulated conductor.

[0102] Example 3

[0103] An embodiment of the present invention is different from the first two embodiments in that:

[0104] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0105] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0106] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0107] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0108] Example 4

[0109] As an embodiment of the present invention, an icing test method based on a portal frame icing test platform is provided. In order to verify the beneficial effects of the present invention, a scientific demonstration is carried out through simulation experiments.

[0110] The experiment was conducted under simulated winter weather conditions, including a temperature of -10°C, a humidity of 80%, and a wind speed of 5m / s. Three types of wires were used, namely standard comparison wires, expanded diameter wires, and super-hydrophobic material wires. The experimental period was 48 hours, and the entire process of wire icing from the initial stage to complete icing was recorded.

[0111] The traditional method is to conduct icing experiments in a natural environment, selecting a typical severe winter weather condition. Manual inspection and recording of conductor icing conditions are performed regularly, recording conductor weight changes and ice thickness. The impact of icing on the conductor is analyzed by visual inspection and simple measuring tools, and the stress and displacement of the conductor are mainly calculated by manual experience and conventional formulas.

[0112] The method of the present invention arranges three wires on a gantry, namely a standard comparison wire, an expanded diameter wire and a super-hydrophobic material wire, and sets environmental conditions for a simulated icing experiment. A camera is used to record the process of the wire from the beginning of icing to complete icing. The image data is processed by a deep convolutional neural network (CNN) and a conditional random field (CRF), and the time nodes of icing development are marked. The weight of each wire is measured at the beginning and end time points of the ice layer, when it is initially formed, when it reaches a predetermined thickness, and when the ice layer begins to fall off. Finite element analysis is performed based on the measured data, stress and displacement functions are calculated, and a comprehensive risk index (RI) model is constructed to perform risk assessment on different wires. The experimental results are shown in Table 1.

[0113] Table 1 Comparison of experimental results

[0114]

[0115]

[0116] Traditional methods rely on manual experience and simple measuring tools, with low data acquisition accuracy, and it is difficult to fully reflect the icing condition of the conductors. Traditional methods can only be performed through regular inspections and manual recording of weight changes and ice thickness, with low accuracy, prone to human errors, and difficult to fully assess the physical state and risks of the conductors. The method of the present invention accurately records and analyzes the icing process through video monitoring and deep learning technology (CNN and CRF), making the calculation of stress and displacement more accurate, thereby providing a detailed risk assessment. The method of the present invention uses a camera to record the entire process of conductor icing, and processes and analyzes the image data through CNN and CRF technology to ensure high accuracy and high reliability of data acquisition, and can fully reflect the physical state of the conductor at different stages of icing.

[0117] Traditional methods rely on natural weather conditions, the experimental environment is difficult to control, and the experimental repeatability is poor. Traditional methods rely on actual weather conditions in the natural environment to conduct icing experiments. The experimental environment is uncontrollable, the experimental results are greatly affected by natural conditions, and the repeatability and reliability of the experiment are low. The method of the present invention ensures the controllability and repeatability of the experimental environment by artificially simulating winter meteorological conditions, making the experimental results more reliable. The method of the present invention uses artificial simulation of typical winter meteorological conditions, including temperature, humidity and wind speed, to ensure the controllability and stability of the experimental environment, and can efficiently conduct icing experiments under laboratory conditions and obtain highly reliable data.

[0118] Traditional methods cannot provide accurate risk assessments. They only rely on simple formula calculations and manual experience, making it difficult to accurately assess the risk level of conductors. Traditional methods mainly rely on simple formulas to calculate the stress and displacement of conductors. They lack in-depth analysis of data and cannot provide accurate risk assessment results, making it difficult to provide a scientific basis for conductor design and protective measures. The method of the present invention uses finite element analysis and risk assessment models to comprehensively evaluate the physical properties and risk levels of different types of conductors under icing conditions, and provide scientific decision-making support. The method of the present invention combines finite element analysis and a comprehensive risk index model (RI) to comprehensively evaluate the stress, displacement and risk levels of different types of conductors under icing conditions, providing detailed risk assessment results that can provide a scientific basis for conductor design and protective measures.

[0119] Traditional methods lack scientific verification of different improvement measures and cannot systematically evaluate the advantages and disadvantages of different wire designs. Traditional methods find it difficult to systematically verify and compare improvement measures for different wire designs, such as increasing the diameter and applying super-hydrophobic materials, and lack scientific evaluation of different wire designs. The method of the present invention scientifically verifies the effects of different improvement measures through comparative experiments on standard wires, expanded diameter wires, and super-hydrophobic material wires, providing a reliable basis for practical applications. The method of the present invention systematically evaluates the performance of different improvement measures under icing conditions through comparative experiments on three different wires, and can scientifically verify the effect of expanding the diameter and applying super-hydrophobic materials on the physical properties of the wire, providing a reliable scientific basis for practical engineering applications.

[0120] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An icing test method based on a portal frame icing test platform, characterized in that: include: Arrange the simulated wires on the portal frame, set the icing test environment conditions, and start the icing test; Start video monitoring to record the process from the beginning of ice formation to complete ice coverage of the wire; Measure the weight change of the conductor caused by ice coating, analyze the weight distribution of the ice layer and its potential impact on the conductor structure, and evaluate the physical impact of ice coating on the simulated conductor.

2. The icing test method based on the portal frame icing test platform according to claim 1, characterized in that: The simulated wires include a first simulated wire, a second simulated wire and a third simulated wire; The first simulated wire is a standard comparison simulated wire; The diameter of the second simulated wire is increased according to preset specifications compared with the first simulated wire; Compared with the first simulated wire, the surface of the third simulated wire is coated with super-hydrophobic material.

3. The icing test method based on the portal frame icing test platform according to claim 2 is characterized in that: The setting of the icing experiment environmental conditions includes obtaining historical meteorological data to determine typical winter meteorological conditions, determining temperature, humidity and wind speed, and using a spray device and a fan to simulate precipitation and wind.

4. The icing test method based on the portal frame icing test platform according to claim 3 is characterized in that: The process of recording the wire from the beginning of ice formation to complete ice coverage includes setting a camera to capture image data of each simulated wire, performing data preprocessing on the image data, wherein the preprocessing includes range adjustment, denoising, image sharpening and geometric correction, inputting the preprocessed image into a deep convolutional neural network CNN, configuring a multi-task learning architecture, extracting features of ice shape, thickness and distribution, and processing each feature branch through a fully connected layer; Conditional random field (CRF) is introduced to use the extracted features to model the spatial relationship between pixels in the image and mark the time nodes of the ice development stage during video monitoring, including the initial formation of the ice layer, reaching the predetermined thickness and starting to fall off.

5. The icing test method based on the portal frame icing test platform according to claim 4 is characterized in that: The method of measuring the weight change of the conductor caused by ice coating includes measuring the weight of each simulated conductor as W1, W2, W3 and W4 at the starting time point of initial formation of the ice layer, the starting and ending time points of reaching a predetermined thickness, and the starting time point of ice layer falling off, determining the weight change ΔWi in each stage, performing finite element analysis, constructing stress function and displacement function based on the analysis results, and constructing a risk assessment model.

6. The icing test method based on the portal frame icing test platform according to claim 5 is characterized in that: The finite element analysis is expressed as, F i =ΔW i ·g Where, ΔW i Indicates the weight change at each stage, F i is the force caused by the change in weight, g is the gravitational acceleration constant, and q i is the uniform load per unit length, L is the length of the wire, M i is the bending moment caused by uniformly distributed load, σ max is the maximum stress, y is the distance from the outer edge of the conductor section to the neutral axis, I is the moment of inertia of the conductor section, δ max is the maximum displacement of the conductor under the weight of ice, and E is the Young's modulus of the conductor material; The stress function is expressed as, The displacement function is expressed as, The risk assessment model is expressed as, Among them, f(σ max,i ) represents the stress function, represents the exponential decay of stress, x is the integral variable, σ crit is the critical stress, g(δ max,i ) represents the displacement function, k is the number of terms to be summed, δ crit is the critical displacement, RI i represents the comprehensive risk index of each wire, γ represents the normalization factor, α and β represent the weighting factors, and n is the number of stages.

7. The icing test method based on the portal frame icing test platform according to claim 6 is characterized in that: The evaluation of the physical impact of ice coating on the simulated conductor includes analyzing the comprehensive risk index of the first simulated conductor, the second simulated conductor and the third simulated conductor, and comprehensively evaluating and selecting the optimal conductor for application in an ice coating environment.

8. A system using an icing test method based on a portal frame icing test platform as claimed in any one of claims 1 to 7, characterized in that: include: Environmental simulation module, video monitoring module and evaluation and analysis module; The environmental simulation module is used to arrange simulated wires on the portal frame, set the icing experiment environmental conditions, and start the icing experiment; The video monitoring module is used to start video monitoring and record the process from the beginning of icing to the complete icing of the wire; The evaluation and analysis module is used to measure the weight change of the conductor caused by ice coating, analyze the weight distribution of the ice layer and the potential impact on the conductor structure, and evaluate the physical impact of ice coating on the simulated conductor.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the icing test method based on the portal frame icing test platform according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the icing test method based on a portal frame icing test platform according to any one of claims 1 to 7 are implemented.

Images