Method, system and device for predicting icing thickness of overhead transmission line, medium and product

Abstract

The invention discloses an overhead transmission line icing thickness prediction method, system and device, a medium and a product, and relates to the field of intelligent prediction and management of a power system, and the method comprises the steps: obtaining the sensor data of a to-be-predicted overhead transmission line in a historical set time period and the sensor data of a current moment; preprocessing the sensor data to obtain processed historical sensor data and processed current sensor data; according to the processed historical sensor data and the processed current sensor data, using a freezing coefficient prediction model to determine a freezing coefficient of the overhead transmission line to be predicted; according to the wind speed, the air liquid water content and the freezing coefficient at the current moment, the icing thickness increase amount at the current moment is determined through an icing thickness increase amount calculation model; and determining the icing thickness of the to-be-predicted overhead transmission line at the prediction moment according to the icing thickness and the icing thickness increment at the current moment. According to the invention, accurate prediction of the icing thickness of the overhead transmission line is realized.

Description

Technical Field

[0001] The present application relates to the field of intelligent prediction and management of power systems, and in particular to a method, system, equipment, medium and product for predicting ice thickness of overhead transmission lines. Background Art

[0002] With the vigorous promotion and development of the construction of new power systems, the number and scale of transmission lines have increased rapidly, and the safe and stable operation of the transmission tower line system is facing severe challenges. Extreme weather has caused serious icing on transmission lines, which has a significant impact on the safe and stable operation of the power grid, while reducing the reliability of power supply, and affecting the economic and social benefits of power grid enterprises. Therefore, it is necessary to predict the ice thickness of transmission towers and lines, generate emergency plans in advance, and avoid power system failures caused by icing, which is of great significance to the safe and stable operation of the power grid. The prediction model of ice thickness of overhead transmission lines is mainly divided into physical calculation model, statistical model and machine learning model. The physical calculation model uses experimental or measured data to calculate the ice mass through mathematical description of the physical process of icing, but some parameters and environmental variables in this type of model are difficult to obtain, and the calculation process is very complicated. The statistical model contains more statistical assumptions, and it is difficult to consider the influence of micro-geographic and micro-meteorological factors. The model prediction accuracy is not high and the application scope is limited. Therefore, in recent years, machine learning models have been vigorously developed in the field of icing prediction. By studying the historical data of ice coverage on transmission lines, machine learning models can discover the nonlinear relationship between ice thickness and input variables such as the environment in which the conductor is located and the characteristics of the conductor itself. However, machine learning models require a large amount of field data and are highly dependent on the quality and quantity of data.

[0003] In summary, power grid companies are in urgent need of a method that can accurately predict the thickness of ice covering overhead transmission lines to solve the problem that existing models have difficulty in obtaining parameters and environmental variables and are highly dependent on the quality and quantity of data. Summary of the invention

[0004] The purpose of this application is to provide a method, system, device, medium and product for predicting the ice thickness of overhead transmission lines, so as to achieve accurate prediction of the ice thickness of overhead transmission lines.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for predicting ice thickness of overhead transmission lines, comprising:

[0007] Acquire sensor data of the overhead power transmission line to be predicted in a historical set period and sensor data at the current moment; the sensor data includes wind speed, wind direction, temperature, air liquid water content and ice thickness;

[0008] Preprocessing the sensor data of the historical set period and the sensor data of the current moment respectively to obtain processed historical sensor data and processed current sensor data; the preprocessing includes normalization processing and window processing; the processed sensor data is a matrix of m rows and n columns; wherein the columns are data collected by multiple sensors at a certain moment; and the rows are data collected by a certain sensor at multiple moments;

[0009] According to the processed historical sensor data and the processed current sensor data, a freezing coefficient prediction model is used to determine the freezing coefficient of the overhead transmission line to be predicted; wherein the freezing coefficient prediction model is obtained by training a Transformer-based machine learning model using a training data set;

[0010] According to the wind speed at the current moment, the liquid water content of the air at the current moment and the freezing coefficient, the ice thickness growth amount at the current moment is determined by using an ice thickness growth amount calculation model;

[0011] The ice thickness of the overhead power transmission line to be predicted at the prediction time is determined according to the ice thickness at the current time and the ice thickness growth amount.

[0012] Optionally, the ice thickness growth calculation model is:

[0013]

[0014] Among them, ΔH is the increase in ice thickness at the current moment; t is the current moment; t+Δt is the predicted moment, ρ is the ice density; α1 is the collision coefficient; α2 is the collection coefficient; α3 is the freezing coefficient; ω is the liquid water content in the air at the current moment; v is the wind speed at the current moment.

[0015] Optionally, determining the ice thickness of the overhead transmission line to be predicted at the prediction time according to the ice thickness at the current time and the ice thickness growth amount specifically includes:

[0016] Using formula H t+Δt =H t +ΔH determines the ice thickness of the overhead transmission line to be predicted at the prediction time; where H t+Δt is the ice thickness at time t+Δt, t+Δt is the prediction time; H t is the ice thickness at time t, t is the current time; ΔH is the increase in ice thickness at time t.

[0017] Optionally, the normalization process is a Min-Max normalization method.

[0018] Optionally, the Transformer-based machine learning model includes a 3-layer encoder and a 3-layer decoder.

[0019] In a second aspect, the present application provides a system for predicting ice thickness of overhead transmission lines, comprising:

[0020] A data acquisition module is used to acquire sensor data of the overhead power transmission line to be predicted in a historical set period and sensor data at the current moment; the sensor data includes wind speed, wind direction, temperature, air liquid water content and ice thickness;

[0021] A preprocessing module is used to preprocess the sensor data of the historical set period and the sensor data of the current moment respectively to obtain processed historical sensor data and processed current sensor data; the preprocessing includes normalization processing and window processing; the processed sensor data is a matrix of m rows and n columns; wherein the columns are data collected by multiple sensors at a certain moment; and the rows are data collected by a certain sensor at multiple moments;

[0022] A freezing coefficient prediction module, used to determine the freezing coefficient of the overhead transmission line to be predicted based on the processed historical sensor data and the processed current sensor data using a freezing coefficient prediction model; wherein the freezing coefficient prediction model is obtained by training a Transformer-based machine learning model using a training data set;

[0023] An increase amount calculation module is used to determine the increase amount of ice thickness at the current moment according to the wind speed at the current moment, the liquid water content of the air at the current moment and the freezing coefficient, using an ice thickness increase amount calculation model;

[0024] The ice thickness prediction module is used to determine the ice thickness of the overhead transmission line to be predicted at the prediction time according to the ice thickness at the current time and the ice thickness growth amount.

[0025] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described methods for predicting ice thickness of overhead transmission lines.

[0026] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for predicting ice thickness of overhead transmission lines.

[0027] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for predicting ice thickness of overhead transmission lines.

[0028] According to the specific embodiments provided in this application, this application has the following technical effects:

[0029] The present application provides a method, system, device, medium and product for predicting ice thickness of overhead transmission lines, which obtain sensor data of the overhead transmission line to be predicted in a historical set time period and sensor data at the current moment; pre-process the sensor data of the historical set time period and the sensor data at the current moment respectively to obtain processed historical sensor data and processed current sensor data; determine the freezing coefficient of the overhead transmission line to be predicted by using a freezing coefficient prediction model based on the processed historical sensor data and the processed current sensor data; wherein the freezing coefficient prediction model is obtained by training a Transformer-based machine learning model using a training data set; determine the ice thickness growth at the current moment based on the wind speed at the current moment, the liquid water content in the air at the current moment and the freezing coefficient using an ice thickness growth calculation model; determine the ice thickness of the overhead transmission line to be predicted at the prediction moment based on the ice thickness at the current moment and the ice thickness growth. This application uses the advantages of the self-attention mechanism of the Transformer-based machine learning model in processing long-term historical ice sequence data to more effectively capture the nonlinear relationship between the sensor data sequence of the overhead transmission line and the freezing coefficient, and improve the prediction accuracy of the freezing coefficient. According to the physical principle of ice growth on transmission lines, the freezing coefficient is combined with the collision coefficient and collection coefficient with empirical values, as well as the easily measurable ice density, wind speed, and liquid water content, to achieve rapid and accurate prediction of the ice thickness of overhead transmission lines. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0031] Figure 1 A schematic diagram of a flow chart of a method for predicting ice thickness of an overhead transmission line provided in one embodiment of the present application;

[0032] Figure 2 This is the structural diagram of the freezing coefficient prediction model;

[0033] Figure 3 This is a performance comparison chart of the application method, the convolutional neural network CNN prediction method, and the long short-term memory network LSTM prediction method;

[0034] Figure 4 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0036] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0037] This application combines the advantages of machine learning in dealing with nonlinear problems with the advantages of high accuracy in physical calculations. It uses machine learning to mine the relationship between ice-related and easy-to-obtain data and key parameters of the physical calculation model, and predicts the key parameters. It then uses the physical calculation model to achieve ice prediction. On the one hand, it solves the problem that parameters and environmental variables in the physical calculation model are difficult to obtain and the calculation process is very complicated. On the other hand, it overcomes the limitation of the machine learning model's high data volume requirements. The method of this application has higher accuracy than the existing single machine learning method, and improves the accuracy of ice thickness prediction for overhead transmission lines.

[0038] In an exemplary embodiment, Figure 1 As shown, a method for predicting ice thickness of overhead transmission lines is provided, comprising the following steps:

[0039] S1: Obtain sensor data of the overhead transmission line to be predicted in a historical set period and sensor data at the current moment; the sensor data includes wind speed, wind direction, temperature, liquid water content in the air and ice thickness.

[0040] In practical applications, the factors affecting the ice thickness of overhead transmission lines are analyzed, and the sensor data of the overhead transmission lines to be predicted in the historical set period and the sensor data at the current moment are collected according to the analysis results. The sampling frequency is 30 minutes / time, and a total of 600 sets of sample data are collected in this sampling, as shown in Table 1.

[0041] Table 1 Statistics of overhead transmission line data collection

[0042]

[0043] S2: Preprocess the sensor data of the historical set time period and the sensor data of the current moment respectively to obtain processed historical sensor data and processed current sensor data; the preprocessing includes normalization processing and window processing; the processed sensor data is a matrix of m rows and n columns; wherein the columns are data collected by multiple sensors at a certain moment; and the rows are data collected by a certain sensor at multiple moments.

[0044] In practical applications, the sensor data of the historical set period and the sensor data at the current moment are preprocessed respectively, including normalization processing and window processing, to generate time series data for ice thickness prediction.

[0045] The Min-Max normalization method is used to normalize the sensor data so that the data is mapped to the interval [0, 1]. The specific formula is:

[0046]

[0047] In the formula, is the normalized sensor data at time t, x kmax With x kmin are the maximum and minimum values ​​of the data collected by sensor k, is the sensor data at time t.

[0048] The sliding window is used for data segmentation. The freezing coefficient value at the corresponding moment in the last column of each sliding window is used as the sensor time series data matrix X in the window. f Corresponding output, this embodiment sets the time window T to 20, so as to divide all sample data of the data set into several time series data matrices. The sliding window at time t is expressed as follows:

[0049]

[0050] S3: Determine the freezing coefficient of the overhead transmission line to be predicted based on the processed historical sensor data and the processed current sensor data using a freezing coefficient prediction model; wherein the freezing coefficient prediction model is obtained by training a Transformer-based machine learning model using a training data set.

[0051] In practical applications, a Transformer-based machine learning model is constructed as a freezing coefficient prediction model. Figure 2As shown, in this embodiment, the number of encoder and decoder layers is set to 3, the 3-layer encoder is connected in sequence, the 3-layer decoder is connected in sequence, and the last layer of encoder is connected to the first layer of decoder; the encoder includes a first multi-head self-attention mechanism module, a first residual connection and normalization module, a first fully connected layer, and a second residual connection and normalization module; the decoder includes a second multi-head self-attention mechanism module, a third residual connection and normalization module, a third multi-head self-attention mechanism module, a fourth residual connection and normalization module, a second fully connected layer, and a fifth residual connection and normalization module. The learning rate is set to 0.0001, and the number of multi-head self-attention is 4. The processed overhead transmission line time series data (processed historical sensor data and processed current sensor data) is input into the freezing coefficient prediction model to calculate the predicted value of the freezing coefficient.

[0052] Convert the overhead transmission line time series data into the input matrix X of the encoder in the Transformer-based machine learning model f , get the encoder output matrix X f ', the column vector of the input matrix represents the historical data collected by multiple sensors at a certain moment, and the row vector of the input matrix represents the historical data collected by a sensor at multiple moments. The corresponding calculation formula is as follows:

[0053] Q=X f W Q .

[0054] K=X f W K .

[0055] V=X f W V .

[0056]

[0057] head i =Attention(QW i Q ,KW i K ,VW i V ).

[0058] MultiHead(Q,K,V)=Concat(head1,head2,…head h )W O .

[0059] Where Q is the query matrix; W Q is the query weight matrix; K is the key matrix; W K is the key weight matrix; V is the value matrix; WV is the value weight matrix; T is the transpose; d is the sensor dimension; Attention() is the self-attention operation; head i is a multi-head self-attention operation; MultiHead() is a multi-head self-attention matrix; Concat() is a concatenation operation; W O is the multi-head self-attention weight matrix.

[0060] In the Transformer-based machine learning model, the decoder receives X f 'The sensor data collection sequence at the freezing coefficient prediction moment (the processed current sensor data) outputs the prediction result of the freezing coefficient.

[0061] S4: According to the wind speed at the current moment, the liquid water content of the air at the current moment and the freezing coefficient, the ice thickness growth amount at the current moment is determined by using an ice thickness growth amount calculation model.

[0062] The predicted freezing coefficient is substituted into the ice thickness growth calculation model to calculate the ice thickness growth, and then the ice thickness of the overhead transmission line is predicted.

[0063] The calculation model of ice thickness growth is:

[0064]

[0065] Among them, ΔH is the increase in ice thickness at the current moment; t is the current moment; t+Δt is the predicted moment, ρ is the ice density; α1 is the collision coefficient; α2 is the collection coefficient; α3 is the freezing coefficient; ω is the liquid water content in the air at the current moment; v is the wind speed at the current moment.

[0066] The calculation formula of collision coefficient α1 is:

[0067] α1=A-0.028-C(B-0.0454).

[0068] Among them, A, B, and C are empirical parameters.

[0069]

[0070] Where K = ρ W d 2 v / 9μD,φ=Re 2 / K,Re=ρ a dv / μ,ρ w is the water density, take 1.0×10 3 kg / m 3 ρ a is the air density, take 1.293kg / m 3; v is wind speed, μ is the absolute viscosity of air, which is 1.7984×10 -5 kg / ; D is the diameter of the overhead transmission line conductor, which is 23.94 mm; d is the median diameter of supercooled water droplets in the air, which is 26 μm.

[0071] S5: Determine the ice thickness of the overhead transmission line to be predicted at the prediction time according to the ice thickness at the current time and the ice thickness growth amount.

[0072] As an optional implementation, S5 specifically includes:

[0073] Using formula H t+Δt =H t +ΔH determines the ice thickness of the overhead transmission line to be predicted at the prediction time; where H t+Δt is the ice thickness at time t+Δt, t+Δt is the prediction time; H t is the ice thickness at time t, t is the current time; ΔH is the increase in ice thickness at time t.

[0074] This application uses the mean absolute error EMA and the root mean square error ERMS as evaluation indicators to quantify the accuracy of ice thickness prediction for transmission lines. The corresponding calculation formula is:

[0075]

[0076] Where n is the number of samples, Y i is the true value of ice thickness, is the predicted value of ice thickness. In this embodiment, EMA=0.1028, ERMS=0.1076.

[0077] The performance comparison of the present application method with the convolutional neural network (CNN) prediction method and the long short-term memory network (LSTM) prediction method is shown in the figure below: Figure 3 As shown in the figure, the CNN model is good at processing image data, but it is difficult to capture long-term dependencies in time series prediction. The LSTM model can only capture short-term dependencies and is less effective in processing long time series. MT-ITP directly calculates the dependency between any two time steps in the historical data of the transmission line through the self-attention mechanism. When processing long-term data, the previous and subsequent information can be directly associated, and all the information of the input data is comprehensively considered, further improving the prediction accuracy of the ice thickness of the transmission line. The above experiments show that MT-ITP has higher prediction accuracy than other neural network models.

[0078] This application utilizes the advantages of the self-attention mechanism of the Transformer-based machine learning model in processing long-term historical ice sequence data, which can more effectively capture the nonlinear relationship between the sensor data sequence of the overhead transmission line and the freezing coefficient, and improve the prediction accuracy of the freezing coefficient. According to the physical principle of ice growth on the transmission line, the freezing coefficient is combined with the collision coefficient and collection coefficient with empirical values, as well as the easily measurable ice density, wind speed, and liquid water content to achieve rapid and accurate prediction of the ice thickness of the overhead transmission line. This method combines the advantages of physical computing and machine learning, can more accurately analyze the ice formation process, improve the prediction accuracy of ice thickness on the transmission line, and has the characteristics of high calculation accuracy and fast speed.

[0079] Based on the same inventive concept, the embodiment of the present application also provides a system for realizing the above-mentioned prediction of ice thickness of overhead transmission lines. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiment of the prediction system for ice thickness of overhead transmission lines provided below can refer to the limitations of the prediction method for ice thickness of overhead transmission lines in the above text, and will not be repeated here.

[0080] In an exemplary embodiment, a system for predicting ice thickness of an overhead transmission line is provided, comprising:

[0081] The data acquisition module is used to obtain sensor data of the overhead transmission line to be predicted in a historical set time period and sensor data at the current moment; the sensor data includes wind speed, wind direction, temperature, liquid water content in the air and ice thickness.

[0082] A preprocessing module is used to preprocess the sensor data of the historical set time period and the sensor data at the current moment respectively to obtain processed historical sensor data and processed current sensor data; the preprocessing includes normalization processing and window processing; the processed sensor data is a matrix of m rows and n columns; wherein the columns are data collected by multiple sensors at a certain moment; and the rows are data collected by a certain sensor at multiple moments.

[0083] A freezing coefficient prediction module is used to determine the freezing coefficient of the overhead transmission line to be predicted based on the processed historical sensor data and the processed current sensor data using a freezing coefficient prediction model; wherein the freezing coefficient prediction model is obtained by training a Transformer-based machine learning model using a training data set.

[0084] The growth calculation module is used to determine the growth of ice thickness at the current moment according to the wind speed at the current moment, the liquid water content of the air at the current moment and the freezing coefficient using the ice thickness growth calculation model.

[0085] The ice thickness prediction module is used to determine the ice thickness of the overhead transmission line to be predicted at the prediction time according to the ice thickness at the current time and the ice thickness growth amount.

[0086] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above-mentioned method for predicting ice thickness of overhead transmission lines when executing the computer program.

[0087] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which, when executed by a processor, implements the above-mentioned method for predicting ice thickness of overhead transmission lines.

[0088] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the above-mentioned method for predicting ice thickness of overhead transmission lines when executed by a processor.

[0089] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting the ice thickness of an overhead transmission line is implemented.

[0090] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0091] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0092] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0093] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0094] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0095] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for predicting ice thickness of overhead transmission lines, characterized in that: include: Obtain sensor data of the overhead transmission line to be predicted in a historical set period and sensor data at the current moment; The sensor data includes wind speed, wind direction, temperature, air liquid water content and ice thickness; Preprocessing the sensor data of the historical set time period and the sensor data at the current moment respectively to obtain processed historical sensor data and processed current sensor data; The preprocessing includes normalization processing and window processing; The processed sensor data is a matrix of m rows and n columns, where columns are data collected by multiple sensors at a certain moment, and rows are data collected by a sensor at multiple moments. According to the processed historical sensor data and the processed current sensor data, a freezing coefficient prediction model is used to determine the freezing coefficient of the overhead transmission line to be predicted; wherein the freezing coefficient prediction model is obtained by training a Transformer-based machine learning model using a training data set; According to the wind speed at the current moment, the liquid water content of the air at the current moment and the freezing coefficient, the ice thickness growth amount at the current moment is determined by using an ice thickness growth amount calculation model; The ice thickness of the overhead power transmission line to be predicted at the prediction time is determined according to the ice thickness at the current time and the ice thickness growth amount.

2. The method for predicting ice thickness of overhead transmission lines according to claim 1, characterized in that: The calculation model of ice thickness growth is: Among them, ΔH is the increase in ice thickness at the current moment; t is the current moment; t+Δt is the predicted moment, ρ is the ice density; α1 is the collision coefficient; α2 is the collection coefficient; α3 is the freezing coefficient; ω is the liquid water content in the air at the current moment; v is the wind speed at the current moment.

3. The method for predicting ice thickness of overhead transmission lines according to claim 1, characterized in that: Determining the ice thickness of the overhead transmission line to be predicted at the prediction time according to the ice thickness at the current time and the ice thickness growth amount, specifically includes: Using formula H t+Δt =H t +ΔH determines the ice thickness of the overhead transmission line to be predicted at the prediction time; where H t+Δt is the ice thickness at time t+Δt, t+Δt is the prediction time; H t is the ice thickness at time t, t is the current time; ΔH is the increase in ice thickness at time t.

4. The method for predicting ice thickness of overhead transmission lines according to claim 1, characterized in that: The normalization process is a Min-Max normalization method.

5. The method for predicting ice thickness of overhead transmission lines according to claim 1, characterized in that: The Transformer-based machine learning model includes a 3-layer encoder and a 3-layer decoder.

6. An overhead transmission line ice thickness prediction system, characterized in that: include: A data acquisition module, used to acquire sensor data of the overhead transmission line to be predicted in a historical set period and sensor data at the current moment; The sensor data includes wind speed, wind direction, temperature, air liquid water content and ice thickness; A preprocessing module, used to preprocess the sensor data of the historical set time period and the sensor data at the current moment respectively, to obtain processed historical sensor data and processed current sensor data; The preprocessing includes normalization processing and window processing; The processed sensor data is a matrix of m rows and n columns, where columns are data collected by multiple sensors at a certain moment, and rows are data collected by a sensor at multiple moments. A freezing coefficient prediction module, used to determine the freezing coefficient of the overhead transmission line to be predicted based on the processed historical sensor data and the processed current sensor data using a freezing coefficient prediction model; wherein the freezing coefficient prediction model is obtained by training a Transformer-based machine learning model using a training data set; An increase amount calculation module is used to determine the increase amount of ice thickness at the current moment according to the wind speed at the current moment, the liquid water content of the air at the current moment and the freezing coefficient, using an ice thickness increase amount calculation model; The ice thickness prediction module is used to determine the ice thickness of the overhead transmission line to be predicted at the prediction time according to the ice thickness at the current time and the ice thickness growth amount.

7. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for predicting ice thickness of overhead transmission lines according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting ice thickness of overhead transmission lines according to any one of claims 1 to 5 is implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for predicting ice thickness of overhead transmission lines according to any one of claims 1 to 5 is implemented.

Images