Power transmission line icing prediction method, system, equipment and medium
By improving the Harris Eagle optimization algorithm and introducing the gold sine algorithm and Gaussian random walk strategy, and combining the HKELM network to build an ice-cover thickness prediction model, the problem of insufficient ice-cover prediction accuracy of transmission lines in the existing technology is solved, and a higher Prediction accuracy and stability.
Patent Information
- Application Number
- CN202411120753.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-15
- Publication Date
- 2024-11-19
AI Technical Summary
The existing transmission line ice prediction method has poor results in accuracy and engineering applications, especially the BP neural network method based on the PSOEM-LSSVM model that does not screen for ice influencing factors and requires a large amount of sample data is not effective in engineering applications. .
By improving the Harris Eagle Optimization Algorithm (HHO) to the IHHO algorithm, the gold sine algorithm and the Gaussian random walk strategy were introduced, and the IHHO-HKELM ice-cover thickness prediction model was constructed in combination with the HKELM network to optimize the kernel parameters to improve the prediction accuracy.
The stability and accuracy of ice-covered prediction were improved, and simulation experiments showed that the mean square error and average relative error of the IHHO-HKELM model were better than the existing PSOEM-LSSVM and AMPSO-BP models.
Smart Images

Figure CN118982044A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of transmission line icing prediction, and in particular to a transmission line icing prediction method, system, device and medium. Background Art
[0002] As an important channel for power transmission, most transmission lines are distributed in the wild and are easily damaged by external damage, lightning strikes, icing, etc. during operation. Severe icing causes the mechanical properties of conductors and towers to deteriorate, causing accidents such as line breakage and tower collapse, which may cause large-scale power outages. From a physical point of view, line icing is an accumulation process. The thicker the ice, the faster the vertical load of the line increases. Therefore, improving the prediction accuracy of icing on transmission lines is of great significance for carrying out anti-icing and de-icing work.
[0003] The current transmission line icing prediction methods mainly include the following: 1. The least squares support vector machine (LSSVM) is optimized by using the extended memory particle swarm algorithm (Particle Swarm Optimization with Extended Memory, PSOEM), and a transmission line icing prediction model based on PSOEM-LSSVM is established to predict the icing of transmission lines; 2. The threshold and weight of the BP neural network are determined by the adaptive mutation particle swarm algorithm (Adaptive Mutation Particle Swarm Optimization, AMPSO), and the transmission line AMPSO-BP icing prediction model is established to predict the icing of transmission lines. However, the transmission line icing prediction model based on PSOEM-LSSVM does not screen the factors affecting icing, and the model prediction accuracy is poor. The icing prediction method based on the BP neural network requires a large amount of sample data for training, and the effect is not ideal in engineering applications.
[0004] Therefore, it is urgent to design a method to accurately predict the icing conditions of transmission lines. Summary of the invention
[0005] The present application provides a method, system, device and medium for predicting icing on a power transmission line, which are used to solve the problem of insufficient accuracy in predicting icing on a power transmission line.
[0006] In view of this, the first aspect of the present application provides a method for predicting icing of a transmission line, the method comprising:
[0007] The IHHO algorithm is obtained by improving the HHO algorithm. The improvements include: introducing the golden sine algorithm in the search phase, adjusting the escape energy in a nonlinear decreasing manner, and introducing the Gaussian random walk strategy in the capture phase;
[0008] Obtain multiple sets of sample data on historical conductor ice thickness and influencing factors;
[0009] The HKELM network is used as an ice thickness prediction model, and an IHHO-HKELM ice thickness prediction model is constructed based on the IHHO algorithm;
[0010] The sample data is divided into a training set and a test set, the IHHO-HKELM ice thickness prediction model is trained by the training set, and the IHHO-HKELM ice thickness prediction model is predicted by the test set to obtain a final ice thickness prediction model.
[0011] Optionally, the HHO algorithm is improved to obtain the IHHO algorithm, and the improvement includes: introducing the golden sine algorithm in the search phase, adjusting the escape energy in a nonlinear decreasing manner, and introducing the Gaussian random walk strategy in the capture phase, specifically including:
[0012] S11, after initializing the Harris Hawk population, calculate the initial population fitness value, and determine whether the escape energy factor E is not less than 1. If so, introduce the golden sine algorithm in the search phase, otherwise execute step S12;
[0013] S12, after adjusting the escape energy factor E in a nonlinear decreasing manner, determine whether the escape energy factor E is not less than 0.5, if so, use a fast dive soft encirclement strategy to update the individual position, otherwise use a hard encirclement strategy to update the individual position;
[0014] S13, introducing the Gaussian random walk strategy in the round-up phase and calculating the fitness value of the updated position, judging whether the updated individual position is the best among the individuals according to the fitness value, if so, updating the individual optimal position, otherwise not updating the position;
[0015] S14, compare and determine the individuals in the global optimal position, and determine whether the preset maximum number of iterations has been reached. If not, return to step S11. If so, output the optimal solution and kernel parameters.
[0016] Optionally, the training of the IHHO-HKELM ice thickness prediction model by using the training set specifically includes:
[0017] S41, respectively initializing the parameters of the IHHO algorithm and the HKELM algorithm network, and training the IHHO-HKELM ice thickness prediction model through the training set;
[0018] S42, calculate the initial population fitness value, and determine whether the escape energy factor E is not less than 1, if not, execute step S3, if it is to update the individual position, execute step S4;
[0019] S43, judging whether the escape energy factor E is not less than 0.5, if so, when the population fitness value r is not less than 0.5, the soft encirclement strategy is adopted to update the individual position, and when the population fitness value r is less than 0.5, the fast dive soft encirclement strategy is adopted to update the individual position, if not, when the population fitness value r is less than 0.5, the soft encirclement strategy is adopted to update the individual position, and when the population fitness value r is greater than 0.5, the fast dive soft encirclement strategy is adopted to update the individual position;
[0020] S44, introducing a Gaussian random walk strategy in the round-up phase, and determining whether a preset number of iterations has been reached, if not, returning to step S42, and if so, outputting the optimal solution for the parameters of the HKELM network.
[0021] Optionally, the obtaining of multiple sets of sample data of historical conductor ice thickness and influencing factors specifically includes:
[0022] A plurality of groups of initial sample data of historical conductor ice thickness and influencing factors are obtained, correlation is determined according to the grey correlation between the conductor ice thickness and the influencing factors, and the initial sample data is screened according to the correlation to obtain final sample data.
[0023] A second aspect of the present application provides a transmission line icing prediction system, the system comprising:
[0024] An improvement unit, used for improving the HHO algorithm to obtain the IHHO algorithm, wherein the improvement includes: introducing the golden sine algorithm in the search phase, adjusting the escape energy in a nonlinear decreasing manner, and introducing the Gaussian random walk strategy in the roundup phase;
[0025] An acquisition unit, used for acquiring multiple sets of sample data of historical conductor ice thickness and influencing factors;
[0026] A construction unit, wherein the HKELM network is used as an ice thickness prediction model, and an IHHO-HKELM ice thickness prediction model is constructed based on the IHHO algorithm;
[0027] A training unit is used to divide the sample data into a training set and a test set, train the IHHO-HKELM ice thickness prediction model through the training set, and predict the IHHO-HKELM ice thickness prediction model through the test set to obtain a final ice thickness prediction model.
[0028] Optionally, the improvement unit is specifically used to:
[0029] S11, after initializing the Harris Hawk population, calculate the initial population fitness value, and determine whether the escape energy factor E is not less than 1. If so, introduce the golden sine algorithm in the search phase, otherwise execute step S12;
[0030] S12, after adjusting the escape energy factor E in a nonlinear decreasing manner, determine whether the escape energy factor E is not less than 0.5, if so, use a fast dive soft encirclement strategy to update the individual position, otherwise use a hard encirclement strategy to update the individual position;
[0031] S13, introducing the Gaussian random walk strategy in the round-up phase and calculating the fitness value of the updated position, judging whether the updated individual position is the best among the individuals according to the fitness value, if so, updating the individual optimal position, otherwise not updating the position;
[0032] S14, compare and determine the individuals in the global optimal position, and determine whether the preset maximum number of iterations has been reached. If not, return to step S11. If so, output the optimal solution and kernel parameters.
[0033] Optionally, the training of the IHHO-HKELM ice thickness prediction model by using the training set specifically includes:
[0034] S41, respectively initializing the parameters of the IHHO algorithm and the HKELM algorithm network, and training the IHHO-HKELM ice thickness prediction model through the training set;
[0035] S42, calculate the initial population fitness value, and determine whether the escape energy factor E is not less than 1, if not, execute step S43, if so, update the individual position and execute step S44;
[0036] S43, judging whether the escape energy factor E is not less than 0.5, if so, when the population fitness value r is not less than 0.5, the soft encirclement strategy is adopted to update the individual position, and when the population fitness value r is less than 0.5, the fast dive soft encirclement strategy is adopted to update the individual position, if not, when the population fitness value r is less than 0.5, the soft encirclement strategy is adopted to update the individual position, and when the population fitness value r is greater than 0.5, the fast dive soft encirclement strategy is adopted to update the individual position;
[0037] S44, introducing a Gaussian random walk strategy in the round-up phase, and determining whether a preset number of iterations has been reached, if not, returning to step S42, and if so, outputting the optimal solution for the parameters of the HKELM network.
[0038] Optionally, the acquisition unit is specifically used to:
[0039] A plurality of groups of initial sample data of historical conductor ice thickness and influencing factors are obtained, correlation is determined according to the grey correlation between the conductor ice thickness and the influencing factors, and the initial sample data is screened according to the correlation to obtain final sample data.
[0040] A third aspect of the present application provides a transmission line icing prediction device, the device comprising a processor and a memory:
[0041] The memory is used to store program code and transmit the program code to the processor;
[0042] The processor is used to execute the steps of the power transmission line icing prediction method as described in the first aspect according to the instructions in the program code.
[0043] A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store program code, and the program code is used to execute the power transmission line icing prediction method described in the first aspect above.
[0044] It can be seen from the above technical solutions that this application has the following advantages:
[0045] The present application provides a method for predicting icing of transmission lines. First, the HHO algorithm is improved by introducing the golden sine algorithm in the search stage, adjusting the escape energy in a nonlinear decreasing manner, and introducing the Gaussian random walk strategy in the roundup stage to obtain the IHHO algorithm; then, multiple groups of initial sample data of historical conductor ice thickness and influencing factors are obtained and screened through grey correlation to obtain sample data as input of the prediction model; then, the HKELM network is used as the ice thickness prediction model, and the IHHO-HKELM ice thickness prediction model is constructed based on the IHHO algorithm, and the kernel parameters of HKELM are optimized by using the IHHO algorithm, and finally the IHHO-HKELM ice thickness prediction model is obtained through sample data training. Through simulation experiments, it can be known that compared with the prior art, the IHHO-HKELM ice thickness prediction model of the present application has better stability and higher prediction accuracy in the ice prediction process. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] Figure 1 A schematic diagram of a flow chart of a method for predicting icing on a power transmission line provided in an embodiment of the present application;
[0047] Figure 2 An improved process of the Harris Hawk algorithm provided in the embodiments of the present application;
[0048] Figure 3 The training process of IHHO-HKELM provided in the embodiment of the present application;
[0049] Figure 4 This is a comparison of the prediction results errors of the three models provided in the embodiments of this application;
[0050] Figure 5 A schematic diagram of the structure of a power transmission line icing prediction system provided in an embodiment of the present application. DETAILED DESCRIPTION
[0051] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings 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.
[0052] See also Figure 1 , a transmission line icing prediction method provided in an embodiment of the present application includes:
[0053] Step 101, the HHO algorithm is improved to obtain the IHHO algorithm, wherein the improvement includes: introducing the golden sine algorithm in the search phase, adjusting the escape energy in a nonlinear decreasing manner, and introducing the Gaussian random walk strategy in the capture phase.
[0054] It should be noted that the HHO algorithm (Harris Hawk Optimization Algorithm) has a simple principle and few adjustment parameters, but the HHO algorithm is prone to fall into local extreme values or even fail to converge when optimizing multidimensional functions. This application proposes an improved Harris Hawk algorithm. Specifically, the golden sine algorithm is introduced in the search stage. The golden sine algorithm has good global search capabilities. The specific algorithm is as follows:
[0055]
[0056] In addition, the escape energy is adjusted in a nonlinear decreasing manner to improve the algorithm's global search capability in the early iteration and local optimization capability in the later iteration, as follows:
[0057]
[0058] Where: r and is a random number, r and∈(0,1);α、β are both constants, usually α=1.3 and β=1.7.
[0059] In addition, the introduction of the Gaussian random walk strategy in the roundup stage can increase the disturbance to the optimal individuals of the Harris hawk population and promote the generation of new individuals in the population, which is conducive to the algorithm to jump out of the local optimum and improve the convergence speed. The specific operation of the Gaussian random walk is as follows:
[0060]
[0061] Step 102: Obtain multiple sets of sample data of historical conductor ice thickness and influencing factors.
[0062] Step 103: adopt the HKELM network as the ice thickness prediction model, and construct the IHHO-HKELM ice thickness prediction model based on the IHHO algorithm.
[0063] It should be noted that this application adopts the HKELM network (hybrid kernel extreme learning machine). HKELM uses a hybrid kernel function to map sample data to a high-dimensional feature space for regression, and has better generalization performance and stability in the learning process. For this reason, this application uses HKELM to predict the ice thickness of transmission lines.
[0064] The role of kernel function is to map and process sample data. Typical kernel functions include Gaussian kernel function (GKF) and polynomial kernel function (PKF). Among them, GKF is a global kernel function and PKF is a local kernel function. Studies have shown that the hybrid kernel function composed of GKF and PKF can give full play to the advantages of different kernel functions, optimize the mapping relationship between independent variables and dependent variables, and improve the regression performance of KELM. The expression of the hybrid kernel function is:
[0065]
[0066] Where: is the Gaussian kernel parameter; is the linear kernel parameter; λ is the kernel coefficient.
[0067] Step 104: divide the sample data into a training set and a test set, train the IHHO-HKELM ice thickness prediction model through the training set, and predict the IHHO-HKELM ice thickness prediction model through the test set to obtain a final ice thickness prediction model.
[0068] In one embodiment, Figure 2 As shown, step 101 specifically includes:
[0069] S11. After initializing the Harris Hawk population, calculate the initial population fitness value and determine whether the escape energy factor E is not less than 1. If so, introduce the golden sine algorithm in the search phase, otherwise execute step S12.
[0070] S12, after adjusting the escape energy factor E in a nonlinear decreasing manner, determine whether the escape energy factor E is not less than 0.5, if so, use a fast dive soft encirclement strategy to update the individual position, otherwise use a hard encirclement strategy to update the individual position;
[0071] S13, in the round-up phase, introduce the Gaussian random walk strategy and calculate the fitness value of the updated position, and judge whether the updated individual position is the best among the individuals according to the fitness value. If so, update the individual optimal position, otherwise do not update the position;
[0072] S14, compare and determine the individuals in the global optimal position, and determine whether the preset maximum number of iterations has been reached. If not, return to step S11. If so, output the optimal solution and kernel parameters.
[0073] In one embodiment, step 102 specifically includes:
[0074] Multiple groups of initial sample data of historical conductor ice thickness and influencing factors are obtained, the correlation is determined according to the grey correlation between the conductor ice thickness and the influencing factors, the initial sample data is screened according to the correlation, and the final sample data is obtained.
[0075] In one embodiment, Figure 3 As shown (for ease of understanding, Figure 3 The method also includes the processing of dividing the sample data into a training set and a test set in step 104, which is a common method in the art). In step 104, the IHHO-HKELM ice thickness prediction model is trained by the training set, specifically including:
[0076] S41, respectively initializing the parameters of the IHHO algorithm and the HKELM network, and training the IHHO-HKELM ice thickness prediction model through the training set;
[0077] S42, calculate the initial population fitness value, and determine whether the escape energy factor E is not less than 1, if not, execute step S43, if so, update the individual position and execute step S44;
[0078] S43, judging whether the escape energy factor E is not less than 0.5, if so, when the population fitness value r is not less than 0.5, the soft encirclement strategy is adopted to update the individual position, and when the population fitness value r is less than 0.5, the fast dive soft encirclement strategy is adopted to update the individual position, if not, when the population fitness value r is less than 0.5, the soft encirclement strategy is adopted to update the individual position, and when the population fitness value r is greater than 0.5, the fast dive soft encirclement strategy is adopted to update the individual position;
[0079] S44. Introduce the Gaussian random walk strategy in the round-up phase and determine whether the preset number of iterations has been reached. If not, return to step S42. If so, output the optimal solution for the parameters of the HKELM network.
[0080] The following is a simulation comparison:
[0081] like Figure 4 As shown in the figure, the various errors of the ice thickness prediction results of the test set by the IHHO-HKELM prediction model adopted in this application and the existing PSOEM-LSSVM and AMPSO-BP models. By comparing the data in the table, it can be seen that the mean square error, maximum error and average relative error of the IHHO-HKELM model are 0.285, 0.86 mm and 2.83% respectively, and all kinds of error indicators are better than those of the PSOEM-LSSVM model and the AMPSO-BP model. It can be seen that the IHHO-HKELM model adopted in this application has better stability and higher prediction accuracy in the ice prediction process, which verifies the correctness and superiority of the ice prediction model adopted in this application.
[0082] The above is a transmission line icing prediction method provided in an embodiment of the present application, and the following is a transmission line icing prediction system provided in an embodiment of the present application.
[0083] See also Figure 5 , a transmission line icing prediction system provided in an embodiment of the present application includes:
[0084] The improvement unit 201 is used to improve the HHO algorithm to obtain the IHHO algorithm, and the improvement includes: introducing the golden sine algorithm in the search phase, adjusting the escape energy in a nonlinear decreasing manner, and introducing the Gaussian random walk strategy in the capture phase.
[0085] The acquisition unit 202 is used to acquire multiple sets of sample data of historical conductor ice thickness and influencing factors.
[0086] In construction unit 203, the HKELM network is generally used as an ice thickness prediction model, and an IHHO-HKELM ice thickness prediction model is constructed based on the IHHO algorithm.
[0087] The training unit 204 is used to divide the sample data into a training set and a test set, train the IHHO-HKELM ice thickness prediction model through the training set, and predict the IHHO-HKELM ice thickness prediction model through the test set to obtain a final ice thickness prediction model.
[0088] Furthermore, an embodiment of the present application also provides a transmission line icing prediction device, the device comprising a processor and a memory:
[0089] The memory is used to store program code and transmit the program code to the processor;
[0090] The processor is used to execute the steps of the power transmission line icing prediction method as described in the above method embodiment according to the instructions in the program code.
[0091] Furthermore, a computer-readable storage medium is provided in an embodiment of the present application, and the computer-readable storage medium is used to store program code, and the program code is used to execute the power transmission line icing prediction method described in the above method embodiment.
[0092] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0093] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0094] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0095] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0096] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0097] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0098] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or 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 to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program codes.
[0099] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for predicting icing on transmission lines. It is characterized in that include: The IHHO algorithm is obtained by improving the HHO algorithm. The improvements include: introducing the golden sine algorithm in the search phase, adjusting the escape energy in a nonlinear decreasing manner, and introducing the Gaussian random walk strategy in the capture phase; Obtain multiple sets of sample data on historical conductor ice thickness and influencing factors; The HKELM network is used as an ice thickness prediction model, and an IHHO-HKELM ice thickness prediction model is constructed based on the IHHO algorithm; The sample data is divided into a training set and a test set, the IHHO-HKELM ice thickness prediction model is trained by the training set, and the IHHO-HKELM ice thickness prediction model is predicted by the test set to obtain a final ice thickness prediction model.
2. The method for predicting icing of a transmission line according to claim 1, It is characterized in that The IHHO algorithm is obtained by improving the HHO algorithm. The improvement includes: introducing the golden sine algorithm in the search phase, adjusting the escape energy in a nonlinear decreasing manner, and introducing the Gaussian random walk strategy in the capture phase, specifically including: S11, after initializing the Harris Hawk population, calculate the initial population fitness value, and determine whether the escape energy factor E is not less than 1. If so, introduce the golden sine algorithm in the search phase, otherwise execute step S12; S12, after adjusting the escape energy factor E in a nonlinear decreasing manner, determine whether the escape energy factor E is not less than 0.5, if so, use a fast dive soft encirclement strategy to update the individual position, otherwise use a hard encirclement strategy to update the individual position; S13, introducing the Gaussian random walk strategy in the round-up phase and calculating the fitness value of the updated position, judging whether the updated individual position is the best among the individuals according to the fitness value, if so, updating the individual optimal position, otherwise not updating the position; S14, compare and determine the individuals in the global optimal position, and determine whether the preset maximum number of iterations has been reached. If not, return to step S11. If so, output the optimal solution and kernel parameters.
3. The method for predicting icing of a transmission line according to claim 1, It is characterized in that The training of the IHHO-HKELM ice thickness prediction model by using the training set specifically includes: S41, respectively initializing the parameters of the IHHO algorithm and the HKELM algorithm network, and training the IHHO-HKELM ice thickness prediction model through the training set; S42, calculate the initial population fitness value, and determine whether the escape energy factor E is not less than 1, if not, execute step S43, if so, update the individual position and execute step S44; S43, judging whether the escape energy factor E is not less than 0.5, if so, when the population fitness value r is not less than 0.5, the soft encirclement strategy is adopted to update the individual position, and when the population fitness value r is less than 0.5, the fast dive soft encirclement strategy is adopted to update the individual position, if not, when the population fitness value r is less than 0.5, the soft encirclement strategy is adopted to update the individual position, and when the population fitness value r is greater than 0.5, the fast dive soft encirclement strategy is adopted to update the individual position; S44, introducing a Gaussian random walk strategy in the round-up phase, and determining whether a preset number of iterations has been reached, if not, returning to step S42, and if so, outputting the optimal solution for the parameters of the HKELM network.
4. The method for predicting icing of a transmission line according to claim 1, It is characterized in that The obtaining of multiple sets of sample data of historical conductor ice thickness and influencing factors specifically includes: A plurality of groups of initial sample data of historical conductor ice thickness and influencing factors are obtained, correlation is determined according to the grey correlation between the conductor ice thickness and the influencing factors, and the initial sample data is screened according to the correlation to obtain final sample data.
5. A transmission line icing prediction system, It is characterized in that include: An improvement unit, used for improving the HHO algorithm to obtain the IHHO algorithm, wherein the improvement includes: introducing the golden sine algorithm in the search phase, adjusting the escape energy in a nonlinear decreasing manner, and introducing the Gaussian random walk strategy in the roundup phase; An acquisition unit, used for acquiring multiple sets of sample data of historical conductor ice thickness and influencing factors; A construction unit, wherein the HKELM network is used as an ice thickness prediction model, and an IHHO-HKELM ice thickness prediction model is constructed based on the IHHO algorithm; A training unit is used to divide the sample data into a training set and a test set, train the IHHO-HKELM ice thickness prediction model through the training set, and predict the IHHO-HKELM ice thickness prediction model through the test set to obtain a final ice thickness prediction model.
6. The power transmission line icing prediction system according to claim 5, It is characterized in that The improvement unit is specifically used for: S11, after initializing the Harris Hawk population, calculate the initial population fitness value, and determine whether the escape energy factor E is not less than 1. If so, introduce the golden sine algorithm in the search phase, otherwise execute step S12; S12, after adjusting the escape energy factor E in a nonlinear decreasing manner, determine whether the escape energy factor E is not less than 0.5, if so, use a fast dive soft encirclement strategy to update the individual position, otherwise use a hard encirclement strategy to update the individual position; S13, introducing the Gaussian random walk strategy in the round-up phase and calculating the fitness value of the updated position, judging whether the updated individual position is the best among the individuals according to the fitness value, if so, updating the individual optimal position, otherwise not updating the position; S14, compare and determine the individuals in the global optimal position, and determine whether the preset maximum number of iterations has been reached. If not, return to step S11. If so, output the optimal solution and kernel parameters.
7. The power transmission line icing prediction system according to claim 5, It is characterized in that The training of the IHHO-HKELM ice thickness prediction model by using the training set specifically includes: S41, respectively initializing the parameters of the IHHO algorithm and the HKELM algorithm network, and training the IHHO-HKELM ice thickness prediction model through the training set; S42, calculate the initial population fitness value, and determine whether the escape energy factor E is not less than 1, if not, execute step S43, if so, update the individual position and execute step S44; S43, judging whether the escape energy factor E is not less than 0.5, if so, when the population fitness value r is not less than 0.5, the soft encirclement strategy is adopted to update the individual position, and when the population fitness value r is less than 0.5, the fast dive soft encirclement strategy is adopted to update the individual position, if not, when the population fitness value r is less than 0.5, the soft encirclement strategy is adopted to update the individual position, and when the population fitness value r is greater than 0.5, the fast dive soft encirclement strategy is adopted to update the individual position; S44, introducing a Gaussian random walk strategy in the round-up phase, and determining whether a preset number of iterations has been reached, if not, returning to step S42, and if so, outputting the optimal solution for the parameters of the HKELM network.
8. The power transmission line icing prediction system according to claim 5, It is characterized in that The acquisition unit is specifically used for: A plurality of groups of initial sample data of historical conductor ice thickness and influencing factors are obtained, correlation is determined according to the grey correlation between the conductor ice thickness and the influencing factors, and the initial sample data is screened according to the correlation to obtain final sample data.
9. A transmission line icing prediction device, It is characterized in that The device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the transmission line icing prediction method according to any one of claims 1-4 according to the instructions in the program code.
10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium is used to store program codes, and the program codes are used to execute the transmission line icing prediction method according to any one of claims 1 to 4.
