Rapid inversion method and apparatus for icing thickness of power transmission line, and related device

Abstract

Disclosed are a rapid inversion method and apparatus for icing thickness of a power transmission line, and a related device. The method comprises: acquiring meteorological data of the place where the power transmission line is located, wherein target meteorological factors in the meteorological data are determined in advance by means of association analysis, and the meteorological data includes meteorological monitoring data and / or meteorological forecast data; and inputting the meteorological data into a trained rapid inversion model to obtain an icing thickness inversion value, wherein the model is obtained by training by using the meteorological monitoring data as a training sample and icing thickness data as a sample label, and the icing thickness data comprises icing thickness monitoring data and icing thickness simulation data obtained by means of numerical simulation calculation. Abundant icing thickness simulation data is obtained by means of numerical simulation calculation, solving the problem of insufficient icing thickness data, meeting the high-precision training requirements of deep learning, and improving the generalization ability of the model; and using the trained rapid inversion model to implement rapid inversion of the icing thickness of the power transmission line achieves relatively high accuracy.

Description

A method, device and related equipment for rapid inversion of ice thickness on transmission lines Technical Field

[0001] The present invention relates to the technical field of ice thickness inversion, and more particularly to a method, device and related equipment for rapid inversion of ice thickness on a transmission line. Background Art

[0002] Maintaining safe transmission lines is crucial for providing good service and a prerequisite for the safe operation of communication systems. Icing on transmission lines is a significant factor impacting their stable operation. Icing on transmission lines can lead to overload, ice dancing, ice jumping, and ice flash on insulator strings, resulting in tower deformation, collapse, and conductor breakage. Therefore, studying the ice thickness of conductors is crucial. With the advancement of neural network technology, predicting ice thickness using deep learning models has become a potential solution. This approach can predict ice coverage on transmission lines in inclement weather, enabling real-time monitoring. It can also predict future ice thickness on transmission lines.

[0003] Transmission line ice monitoring technology was first deployed on the Shenyuan I power line in Shanxi Province in February 2006. Large-scale implementation of this technology has only begun in the past decade. Prior to this, ice data was generally missing, and ice thickness data was extremely limited. Meteorological monitoring data, on the other hand, is generally quite old. For example, the meteorological observation network was established as early as 1950, and meteorological data from 1951 to the present is available, making it a very rich source of data. Consequently, the available data far outweighs ice thickness data. Deep learning models for ice analysis require extensive data support for training, and the existing ice thickness data is far from sufficient.

[0004] Summary of the Invention

[0005] In view of this, the present invention provides a method, apparatus and related equipment for rapid inversion of ice thickness on transmission lines to overcome at least one of the technical deficiencies mentioned above.

[0006] To achieve the above objectives, the present invention provides a first aspect of a method for rapidly inverting ice thickness on a transmission line, comprising:

[0007] Acquire meteorological data at a location where the power transmission line is located, wherein each target meteorological factor in the meteorological data is determined in advance after correlation analysis, and the meteorological data includes meteorological monitoring data and / or meteorological forecast data;

[0008] Inputting the meteorological data into the trained rapid inversion model to obtain an ice thickness inversion value;

[0009] The rapid inversion model is trained using meteorological monitoring data as training samples and ice thickness data as sample labels. The ice thickness data includes ice thickness monitoring data and ice thickness simulation data obtained through numerical simulation calculations.

[0010] Preferably, the process of obtaining ice thickness simulation data through numerical simulation calculation includes:

[0011] Establish a conductor model corresponding to the transmission line, establish a fluid domain, and set the flow field boundary conditions;

[0012] Based on the wire model, the fluid domain and the flow field boundary conditions, fluid simulation software is used to perform simulation operations on the input meteorological monitoring data to obtain ice thickness simulation data.

[0013] Preferably, the process of determining each target meteorological factor after correlation analysis includes:

[0014] Based on meteorological monitoring data and ice thickness monitoring data, the correlation degree between each meteorological factor and the ice thickness monitoring value is calculated, and the meteorological factors with the highest correlation degree are determined as target meteorological factors.

[0015] Preferably, the process of calculating the degree of correlation between each meteorological factor and the ice thickness monitoring value includes:

[0016] The correlation between meteorological factors and ice thickness monitoring values ​​is calculated using the following formula:

[0017] Where x0(k) represents the ice thickness monitoring value in time period k, ρ represents the resolution coefficient, and x i (k) represents the observed value of the i-th meteorological factor in time period k, Indicates the degree of correlation between the ith meteorological factor and the ice thickness monitoring value.

[0018] Preferably, each target meteorological factor includes wind direction, wind speed, relative humidity, temperature, rainfall, air pressure and / or visibility.

[0019] Preferably, the fast inversion model uses a GAP algorithm to optimize training, and the process of using the GAP algorithm to optimize training includes:

[0020] The GAP algorithm is used to perform the growth-pruning steps of each layer in both directions to obtain the number of filters in each layer;

[0021] The standard BP algorithm is used to adjust the weight of each filter.

[0022] Preferably, the process of obtaining the training set includes:

[0023] Obtain meteorological monitoring data and ice thickness data;

[0024] The meteorological monitoring data and the ice thickness data are cleaned, completed and standardized.

[0025] A second aspect of the present invention provides a device for rapidly inverting ice thickness on a transmission line, comprising:

[0026] A data acquisition unit, configured to acquire meteorological data at a location where the transmission line is located, wherein each target meteorological factor in the meteorological data is determined in advance after correlation analysis, and the meteorological data includes meteorological monitoring data and / or meteorological forecast data;

[0027] An ice inversion unit, configured to input the meteorological data into a trained rapid inversion model to obtain an ice thickness inversion value;

[0028] The rapid inversion model is trained in a semi-supervised learning manner using meteorological monitoring data and ice thickness data as training sets. The ice thickness data includes ice thickness monitoring data and ice thickness simulation data obtained through numerical simulation calculations.

[0029] A third aspect of the present invention provides a device for rapid inversion of ice thickness on a transmission line, comprising: a memory and a processor;

[0030] The memory is used to store programs;

[0031] The processor is used to execute the program to implement the various steps of the above-mentioned method for rapid inversion of ice thickness on transmission lines.

[0032] A fourth aspect of the present invention provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned method for rapid inversion of ice thickness on transmission lines are implemented.

[0033] Through the above technical solution, it can be seen that the present invention first obtains the meteorological data of the location of the transmission line, wherein each target meteorological factor in the meteorological data is determined in advance after correlation analysis, and the meteorological data includes at least one of meteorological monitoring data and meteorological forecast data. Then, the meteorological data is input into the trained rapid inversion model to obtain the ice thickness inversion value. wherein, the rapid inversion model is trained in a semi-supervised learning manner using meteorological monitoring data and ice thickness data as training sets, and the ice thickness data includes ice thickness monitoring data and ice thickness simulation data obtained by numerical simulation calculation. the rich ice thickness simulation data obtained by numerical simulation calculation solves the problem of insufficient ice thickness data, meets the high-precision training requirements of deep learning, and improves the generalization ability of the rapid inversion model. further, the trained rapid inversion model can be used to predict the icing conditions of the transmission line using meteorological monitoring data in bad weather, or to predict the ice thickness of the transmission line in the future using meteorological forecast data, both of which can achieve high accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0035] FIG1 is a schematic diagram of a method for rapidly inverting ice thickness on a transmission line disclosed in an embodiment of the present invention;

[0036] FIG2 illustrates the linear interpolation disclosed in an embodiment of the present invention;

[0037] FIG3 is a schematic diagram of a device for rapid inversion of ice thickness on a transmission line disclosed in an embodiment of the present invention;

[0038] FIG4 is a schematic diagram of a device for rapidly inverting ice thickness on a transmission line according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0040] The following describes a method for rapidly inverting ice thickness on a transmission line provided by an embodiment of the present invention. Referring to FIG1 , the method for rapidly inverting ice thickness on a transmission line provided by an embodiment of the present invention may include the following steps:

[0041] Step S101: Acquire meteorological data at the location of the transmission line.

[0042] Wherein, each target meteorological factor in the meteorological data is determined in advance after correlation analysis, and the meteorological data includes at least one of meteorological monitoring data and meteorological forecast data.

[0043] Step S102: inputting the meteorological data into the trained rapid inversion model to obtain an inversion value of ice thickness.

[0044] The rapid inversion model is trained using semi-supervised learning, using meteorological monitoring data and ice thickness data as a training set. The ice thickness data includes ice thickness monitoring data and simulated ice thickness data obtained through numerical simulation. The inversion calculation enriches the ice thickness data, addressing its shortcomings.

[0045] It can be understood that when it is difficult to obtain ice thickness monitoring data in severe weather, meteorological monitoring data can be input into the rapid inversion model to predict the icing conditions of the transmission lines; when the meteorological forecast data is input into the rapid inversion model, the future ice thickness of the transmission lines can be predicted.

[0046] In addition, for transmission lines that have meteorological monitoring data but lack ice thickness data, the ice thickness can be inverted and calculated using the fast inversion model, thereby completing the ice thickness data.

[0047] The present invention first obtains meteorological data of the location of the transmission line, wherein each target meteorological factor in the meteorological data is determined in advance after correlation analysis, and the meteorological data includes at least one of meteorological monitoring data and meteorological forecast data. Then, the meteorological data is input into the trained rapid inversion model to obtain the ice thickness inversion value. The rapid inversion model is trained in a semi-supervised learning manner using meteorological monitoring data and ice thickness data as training sets, and the ice thickness data includes ice thickness monitoring data and ice thickness simulation data obtained by numerical simulation calculation. The rich ice thickness simulation data obtained by numerical simulation calculation solves the problem of insufficient ice thickness data, meets the high-precision training requirements of deep learning, and improves the generalization ability of the rapid inversion model. Furthermore, the trained rapid inversion model can be used to predict the icing conditions of the transmission line using meteorological monitoring data in severe weather, or to predict the ice thickness of the transmission line in the future using meteorological forecast data, both of which can achieve high accuracy.

[0048] In some embodiments of the present invention, the process of obtaining ice thickness simulation data through numerical simulation may include:

[0049] S1, establish a conductor model corresponding to the transmission line, establish a fluid domain, and set the flow field boundary conditions.

[0050] S2, based on the wire model, the fluid domain and the flow field boundary conditions, using fluid simulation software to perform simulation calculations on the input meteorological monitoring data to obtain ice thickness simulation data.

[0051] The fluid simulation software can be Ansys' Fluent or Fluent Icing. This is general computational fluid dynamics (CFD) software used to model and analyze fluid flow, heat transfer, mass exchange, and chemical reaction processes. In the application scenario of the present invention, a wire model is established, meteorological monitoring data is input, and then a simulated ice thickness value is output.

[0052] It is important to note that before using simulated ice thickness data, the simulation results must be cross-validated against the corresponding meteorological monitoring data for transmission line ice thickness. If the error between the two is within 10%, the simulation results are considered reliable. Specifically, the simulated ice thickness values ​​are compared with the monitored values ​​using the same environmental and meteorological data as the existing ice thickness monitoring data.

[0053] In some embodiments of the present invention, the process of determining each target meteorological factor after correlation analysis may include:

[0054] Based on meteorological monitoring data and ice thickness monitoring data, the correlation degree between each meteorological factor and the ice thickness monitoring value is calculated, and the meteorological factors with the highest correlation degree are determined as target meteorological factors.

[0055] In some embodiments of the present invention, the process of calculating the degree of correlation between each meteorological factor and the ice thickness monitoring value may include:

[0056] The correlation between meteorological factors and ice thickness monitoring values ​​is calculated using the following formula:

[0057] Where x0(k) represents the ice thickness monitoring value in time period k; ρ represents the resolution coefficient. The smaller the ρ value, the greater the resolution. Generally, the value of ρ is 0 to 1. i (k) represents the observed value of the i-th meteorological factor in time period k; Indicates the correlation degree between the ith meteorological factor and the ice thickness monitoring value, Larger values ​​indicate stronger correlation.

[0058] In some embodiments of the present invention, each target meteorological factor may include at least one of wind direction, wind speed, relative humidity, temperature, rainfall, air pressure, and visibility.

[0059] In some embodiments of the present invention, the rapid inversion model may include an input layer, a hidden layer, and an output layer. The hidden layer is composed of a convolutional layer and a fully connected layer. The number of neurons in the input layer is the number of extracted meteorological monitoring data types. The number of neurons in the hidden layer is initially determined by the relationship: 2 * number of neurons in the input layer + 1, and is subsequently increased or decreased based on the training effect of the neural network. The number of neurons in the output layer is determined by the number of engineering requirements parameters.

[0060] In some embodiments of the present invention, the fast inversion model uses a GAP algorithm to optimize training. The process of using the GAP algorithm to optimize training may include:

[0061] S1, use the GAP algorithm to perform the growth-pruning steps of each layer in both directions to obtain the number of filters in each layer.

[0062] S2, use the standard BP algorithm to adjust the weights of each filter.

[0063] Specifically, to avoid falling into local optimality, the GAP (Grow-And-Prune) algorithm is used to determine the number of filters in each layer, where the growth operation increases the complexity of each layer and promotes more functions; where the pruning operation removes each layer to produce a complete filter bank, starting from an over-complete filter combination and an empty filter bank. When the number of filters is constant, the growth-pruning steps of each layer are performed bidirectionally, and finally converge to the optimal configuration.

[0064] The data obtained by numerical simulation in the training set creation module is used as the training set. During the training process, the standard BP algorithm is used to adjust all the filter weights of the neural network. In this stage, the recognition loss function of the top layer of the neural network will be propagated to the lower layer along with the reconstruction loss of each layer to update each parameter.

[0065] Finally, the monitoring data processed by the data preprocessing module is used as a validation set to test the training results of the neural network. When the linear correlation coefficient between the neural network calculation results and the transmission line ice coverage monitoring values ​​reaches or exceeds 0.9, it is considered to meet the accuracy requirements.

[0066] In some embodiments of the present invention, the process of obtaining a training set may include:

[0067] S1, obtain meteorological monitoring data and ice thickness data.

[0068] S2, performing data cleaning, data completion, and standardization on the meteorological monitoring data and the ice thickness data.

[0069] Specifically, Min-Max normalization can be adopted, and the formula is as follows:

[0070] Where n is the length of the data set, x1, x2, ..., x n The data collected by the data acquisition module, y1, y2, ..., y n The data are processed after standardization.

[0071] Regarding data completion, offline interpolation can be used to estimate missing values. Specifically, as shown in Figure 2, the coordinates (x0, y0) and (x1, y1) are known coordinates. If the y value at the coordinate x is required, the following formula can be used:

[0072] You can get:

[0073] Furthermore, significant fluctuations in external meteorological conditions can affect some monitoring equipment, leading to abnormal values. Industry experts generally agree that the probability of icing is higher when the conductor temperature is between -5°C and -1°C, wind speeds are between 2 and 10 m / s, and the angle between the wind direction and the conductor is greater than 45 degrees. Therefore, data outside these ranges should be discarded and interpolated.

[0074] The following describes a rapid inversion device for ice thickness of a transmission line provided by an embodiment of the present invention. The rapid inversion device for ice thickness of a transmission line described below and the rapid inversion method for ice thickness of a transmission line described above can refer to each other.

[0075] Referring to FIG3 , the apparatus for rapidly inverting ice thickness on a transmission line provided by an embodiment of the present invention may include:

[0076] A data acquisition unit 21 is configured to acquire meteorological data at a location where the transmission line is located. Each target meteorological factor in the meteorological data is determined in advance after correlation analysis. The meteorological data includes meteorological monitoring data and / or meteorological forecast data.

[0077] An ice inversion unit 22 is configured to input the meteorological data into a trained rapid inversion model to obtain an ice thickness inversion value;

[0078] The rapid inversion model is trained in a semi-supervised learning manner using meteorological monitoring data and ice thickness data as training sets. The ice thickness data includes ice thickness monitoring data and ice thickness simulation data obtained through numerical simulation calculations.

[0079] In some embodiments of the present invention, the transmission line ice thickness rapid inversion device may further include a simulation calculation unit. The process of the simulation calculation unit obtaining ice thickness simulation data through numerical simulation calculation may include:

[0080] Establish a conductor model corresponding to the transmission line, establish a fluid domain, and set the flow field boundary conditions;

[0081] Based on the wire model, the fluid domain and the flow field boundary conditions, fluid simulation software is used to perform simulation operations on the input meteorological monitoring data to obtain ice thickness simulation data.

[0082] In some embodiments of the present invention, 3. The method according to claim 1 is characterized in that the process of determining each target meteorological factor after correlation analysis may include:

[0083] Based on meteorological monitoring data and ice thickness monitoring data, the correlation degree between each meteorological factor and the ice thickness monitoring value is calculated, and the meteorological factors with the highest correlation degree are determined as target meteorological factors.

[0084] In some embodiments of the present invention, the transmission line ice thickness rapid inversion device may further include a correlation analysis unit. The process of the correlation analysis unit calculating the correlation degree between each meteorological factor and the ice thickness monitoring value may include:

[0085] The correlation between meteorological factors and ice thickness monitoring values ​​is calculated using the following formula:

[0086] Where x0(k) represents the ice thickness monitoring value in time period k, ρ represents the resolution coefficient, and xi (k) represents the observed value of the i-th meteorological factor in time period k, Indicates the degree of correlation between the ith meteorological factor and the ice thickness monitoring value.

[0087] In some embodiments of the present invention, the apparatus for rapid inversion of ice thickness on transmission lines may further include a model training unit. The rapid inversion model uses a GAP algorithm for optimization training. The process of optimizing training using the GAP algorithm by the model training unit includes:

[0088] The GAP algorithm is used to perform the growth-pruning steps of each layer in both directions to obtain the number of filters in each layer;

[0089] The standard BP algorithm is used to adjust the weight of each filter.

[0090] In some embodiments of the present invention, the apparatus for rapid inversion of ice thickness on transmission lines may further include a training set construction unit. The process of obtaining the training set by the training set construction unit may include:

[0091] Obtain meteorological monitoring data and ice thickness data;

[0092] The meteorological monitoring data and the ice thickness data are cleaned, completed and standardized.

[0093] The apparatus for rapid inversion of ice thickness on transmission lines provided in an embodiment of the present invention can be applied to a device for rapid inversion of ice thickness on transmission lines, such as a computer. Optionally, FIG4 shows a block diagram of the hardware structure of the rapid inversion device for ice thickness on transmission lines. Referring to FIG4 , the hardware structure of the rapid inversion device for ice thickness on transmission lines may include: at least one processor 31, at least one communication interface 32, at least one memory 33, and at least one communication bus 34.

[0094] In the embodiment of the present invention, the number of the processor 31, the communication interface 32, the memory 33, and the communication bus 34 is at least one, and the processor 31, the communication interface 32, and the memory 33 communicate with each other through the communication bus 34;

[0095] The processor 31 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention;

[0096] The memory 33 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory;

[0097] The memory 33 stores a program, and the processor 31 can call the program stored in the memory 33, wherein the program is used to:

[0098] Acquire meteorological data at a location where the power transmission line is located, wherein each target meteorological factor in the meteorological data is determined in advance after correlation analysis, and the meteorological data includes meteorological monitoring data and / or meteorological forecast data;

[0099] Inputting the meteorological data into the trained rapid inversion model to obtain an ice thickness inversion value;

[0100] The rapid inversion model is trained using meteorological monitoring data as training samples and ice thickness data as sample labels. The ice thickness data includes ice thickness monitoring data and ice thickness simulation data obtained through numerical simulation calculations.

[0101] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0102] An embodiment of the present invention further provides a storage medium, which may store a program suitable for execution by a processor, wherein the program is used to:

[0103] Acquire meteorological data at a location where the power transmission line is located, wherein each target meteorological factor in the meteorological data is determined in advance after correlation analysis, and the meteorological data includes meteorological monitoring data and / or meteorological forecast data;

[0104] Inputting the meteorological data into the trained rapid inversion model to obtain an ice thickness inversion value;

[0105] The rapid inversion model is trained using meteorological monitoring data as training samples and ice thickness data as sample labels. The ice thickness data includes ice thickness monitoring data and ice thickness simulation data obtained through numerical simulation calculations.

[0106] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0107] In summary:

[0108] The present invention first obtains meteorological data of the location of the transmission line, wherein each target meteorological factor in the meteorological data is determined in advance after correlation analysis, and the meteorological data includes at least one of meteorological monitoring data and meteorological forecast data. Then, the meteorological data is input into the trained rapid inversion model to obtain the ice thickness inversion value. The rapid inversion model is trained in a semi-supervised learning manner using meteorological monitoring data and ice thickness data as training sets, and the ice thickness data includes ice thickness monitoring data and ice thickness simulation data obtained by numerical simulation calculation. The rich ice thickness simulation data obtained by numerical simulation calculation solves the problem of insufficient ice thickness data, meets the high-precision training requirements of deep learning, and improves the generalization ability of the rapid inversion model. Furthermore, the trained rapid inversion model can be used to predict the icing conditions of the transmission line using meteorological monitoring data in severe weather, or to predict the ice thickness of the transmission line in the future using meteorological forecast data, both of which can achieve high accuracy.

[0109] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0110] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referenced to each other.

[0111] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A fast inversion method for ice thickness of transmission lines, characterized in that: include: Acquire meteorological data of the location of the transmission line, wherein each target meteorological factor in the meteorological data is determined in advance after correlation analysis, and the meteorological data includes meteorological monitoring data and / or meteorological forecast data; Inputting the meteorological data into the trained rapid inversion model to obtain an inversion value of ice thickness; The rapid inversion model is trained using meteorological monitoring data as training samples and ice thickness data as sample labels. The ice thickness data includes ice thickness monitoring data and ice thickness simulation data obtained through numerical simulation calculations.

2. The method according to claim 1, characterized in that The process of obtaining ice thickness simulation data through numerical simulation includes: Establish a conductor model corresponding to the transmission line, establish a fluid domain, and set the flow field boundary conditions; Based on the wire model, the fluid domain and the flow field boundary conditions, fluid simulation software is used to perform simulation operations on the input meteorological monitoring data to obtain ice thickness simulation data.

3. The method according to claim 1, characterized in that The process of determining each target meteorological factor after correlation analysis includes: Based on the meteorological monitoring data and ice thickness monitoring data, the correlation degree between each meteorological factor and the ice thickness monitoring value is calculated, and the meteorological factors with the highest correlation degree are determined as target meteorological factors.

4. The method according to claim 3, characterized in that The process of calculating the correlation between each meteorological factor and the ice thickness monitoring value includes: The correlation between meteorological factors and ice thickness monitoring values ​​is calculated using the following formula: Where x0(k) represents the ice thickness monitoring value in time period k, ρ represents the resolution coefficient, and x i (k) represents the observed value of the i-th meteorological factor in time period k, It indicates the correlation degree between the ith meteorological factor and the ice thickness monitoring value.

5. The method according to claim 1, characterized in that Target meteorological factors include wind direction, wind speed, relative humidity, temperature, rainfall, air pressure and / or visibility.

6. The method according to claim 1, characterized in that The fast inversion model uses the GAP algorithm to optimize training. The process of using the GAP algorithm to optimize training includes: The GAP algorithm is used to perform the growth-pruning steps of each layer in both directions to obtain the number of filters in each layer; The standard BP algorithm is used to adjust the weight of each filter.

7. The method according to claim 1, characterized in that The process of obtaining the training set includes: Obtain meteorological monitoring data and ice thickness data; The meteorological monitoring data and the ice thickness data are cleaned, completed and standardized.

8. A fast inversion device for ice thickness of power transmission lines, characterized in that: include: A data acquisition unit, used to acquire meteorological data of a location where a power transmission line is located, wherein each target meteorological factor in the meteorological data is determined in advance after correlation analysis, and the meteorological data includes meteorological monitoring data and / or meteorological forecast data; An ice inversion unit, used for inputting the meteorological data into a trained rapid inversion model to obtain an ice thickness inversion value; The rapid inversion model is trained in a semi-supervised learning manner using meteorological monitoring data and ice thickness data as training sets. The ice thickness data includes ice thickness monitoring data and ice thickness simulation data obtained through numerical simulation calculations.

9. A fast inversion device for ice thickness of power transmission lines, characterized in that: include: Memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the method for rapid inversion of ice thickness on a transmission line according to any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the method for rapid inversion of ice thickness on a power transmission line according to any one of claims 1 to 7 is implemented.

Images