Method, device, equipment and storage medium for predicting ice thickness on transmission lines

Abstract

The present application relates to the technical field of ice thickness prediction for transmission lines, and in particular to a method, device, equipment and storage medium for predicting ice thickness on transmission lines, wherein the method for predicting ice thickness on transmission lines comprises: obtaining meteorological data to be predicted in the area where the target transmission line is located; inputting the meteorological data to be predicted into a pre-trained CNN‑LSTM model to obtain a predicted value of ice thickness on the target transmission line; the CNN‑LSTM model is a model for predicting ice thickness values ​​on transmission lines based on meteorological data; wherein the hyperparameters in the CNN‑LSTM model are determined based on a snake optimization algorithm. The present application can effectively improve the accuracy of ice thickness on the target transmission line, so as to achieve accurate prediction of ice thickness on the target transmission line.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of ice thickness prediction on power transmission lines, and in particular, to a method, device, equipment and storage medium for predicting ice thickness on power transmission lines. Background Art

[0002] Transmission line icing is a multidisciplinary scientific issue with a very complex mechanism. As transmission lines are distributed over long distances, cross multiple regions and various terrains, it is not realistic to fully reflect the icing and sag conditions of transmission lines with only a small number of online monitoring devices.

[0003] Therefore, it is urgent to provide a new method for predicting ice thickness on transmission lines to reduce the manpower, financial and material resources required for natural ice observation. Summary of the invention

[0004] The present application provides a method, device, equipment and storage medium for predicting ice thickness on a transmission line, which can accurately predict the ice thickness on a target transmission line.

[0005] In a first aspect, a method for predicting ice thickness on a transmission line is provided, comprising: Obtain the meteorological data to be predicted in the area where the target transmission line is located; The meteorological data to be predicted is input into the pre-trained CNN-LSTM model to obtain the predicted value of ice thickness on the target transmission line; the CNN-LSTM model is a model used to predict the ice thickness value on the transmission line based on meteorological data; wherein, the hyperparameters in the CNN-LSTM model are determined according to the snake optimization algorithm.

[0006] Optionally, the hyperparameters in the CNN-LSTM model are determined by: According to the positions of each individual snake in the total snake population, the upper bound of the total snake population and the lower bound of the total snake population, an initialized total snake population is obtained; the total snake population includes the positions of multiple individual snakes, and the position of each individual snake is a set of hyperparameter values ​​corresponding to the CNN-LSTM model; The initialized total snake group is divided based on a preset ratio to obtain a male snake group and a female snake group; Based on the amount of food and the temperature of the total snake group, determine whether the male snakes in the male snake group and the female snakes in the female snake group have entered the mating mode; the amount of food and the temperature of the total snake group are calculated according to the current number of iterations and the preset number of iterations; If the male snakes in the male snake group and the female snakes in the female snake group enter the mating mode, then according to the mating abilities of the best male snakes in the male snake group and the best female snakes in the female snake group, it is determined whether there are hatching eggs between the best male snake and the best female snake; If there are hatching eggs between the best male snake and the best female snake, the hatching eggs will be replaced by the worst male snake in the male group and the worst female snake in the female group; If the number of iterations does not reach the preset number of iterations, the above steps are repeated until the number of iterations reaches the preset number of iterations to complete the optimization of the hyperparameters in the CNN-LSTM model.

[0007] Optionally, before determining whether the male snakes in the male snake group and the female snakes in the female snake group have entered a mating mode based on the amount of food and the temperature of the total snake group, the method further includes: Based on the comparison between the amount of food and the preset threshold, it is determined whether the male snakes in the male snake group and the female snakes in the female snake group have entered the exploration stage or the exploitation stage; If the male snakes in the male snake group and the female snakes in the female snake group enter the development stage, based on the comparison between the temperature of the total snake group and the preset temperature, it is determined whether the male snakes in the male snake group and the female snakes in the female snake group enter the movement mode or the mating mode; If the male snakes in the male snake group and the female snakes in the female snake group enter the mating mode, the best male snake in the male snake group and the best female snake in the female snake group are determined according to the corresponding fighting capabilities of the male snakes in the male snake group and the corresponding fighting capabilities of the female snakes in the female snake group.

[0008] Optionally, if the male snakes in the male snake group and the female snakes in the female snake group enter the development stage, based on the comparison between the temperature of the total snake group and the preset temperature, it is determined whether the male snakes in the male snake group and the female snakes in the female snake group enter the movement mode or the mating mode, including: If the temperature of the total snake group is lower than the preset temperature, the male snakes in the male snake group and the female snakes in the female snake group are determined to enter the mating mode; If the temperature of the total snake group is greater than a preset temperature, the male snakes in the male snake group and the female snakes in the female snake group are determined to enter a movement mode; After the male snakes in the male snake group and the female snakes in the female snake group enter the moving mode, the positions of the individual snakes in the total snake group are updated according to the moving positions of the male snakes in the male snake group and the female snakes in the female snake group.

[0009] Optionally, it also includes: If the male snakes in the male snake group enter the exploration phase, the corresponding moving positions of each male snake are determined according to the current positions, random positions, and food-finding abilities of each male snake; If the female snakes in the female snake group enter the exploration phase, the corresponding moving position of each female snake is determined according to the current position, random position, and food finding ability of each female snake; According to the moving positions corresponding to the male snakes and the moving positions corresponding to the female snakes, the male snakes and the female snakes are controlled to move respectively, and the positions of the individual snakes in the total snake group are updated.

[0010] Optionally, the CNN-LSTM model is obtained by: The model training samples are divided into a training set and a test set; the model training samples include historical meteorological data and ice thickness values ​​on the transmission lines corresponding to the historical meteorological data; Train the CNN-LSTM model based on the training set to obtain the original CNN-LSTM model; use the model training samples in the test set to perform model testing on the original CNN-LSTM model to obtain the model testing results; If the model test result is passed, the original CNN-LSTM model is determined as the final CNN-LSTM model.

[0011] Optionally, the CNN-LSTM model includes a convolutional neural network, a bidirectional long short-term memory network, and a fully connected layer; Convolutional neural networks are used to extract spatial features of the meteorological data to be predicted; Bidirectional long short-term memory network is used to extract the time characteristics of the forecasted meteorological data; The fully connected layer is used to generate the predicted value of ice thickness on the target transmission line based on spatial and temporal characteristics.

[0012] In a second aspect, a device for predicting ice thickness on a transmission line is provided, comprising: A data acquisition module, used to obtain the meteorological data to be predicted in the area where the target transmission line is located; The prediction module is used to input the meteorological data to be predicted into the pre-trained CNN-LSTM model to obtain the predicted value of the ice thickness on the target transmission line; the CNN-LSTM model is a model used to predict the ice thickness value on the transmission line based on meteorological data; wherein, the hyperparameters in the CNN-LSTM model are determined according to the snake optimization algorithm.

[0013] According to a third aspect, an electronic device is provided, comprising: a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method in the first aspect or its various implementations.

[0014] According to a fourth aspect, a computer-readable storage medium is provided for storing a computer program, wherein the computer program enables a computer to execute the method according to the first aspect or its various implementations.

[0015] Through the technical solution provided by the present application, by determining the hyperparameters in the CNN-LSTM model based on the snake optimization algorithm, the hyperparameters in the CNN-LSTM model are effectively optimized, avoiding the random determination of the model hyperparameters in the related technology, thereby effectively improving the convergence speed of the hyperparameters in the CNN-LSTM model during the training process, and improving the prediction effect of the hyperparameters in the trained CNN-LSTM model. Furthermore, by inputting the meteorological data to be predicted into the pre-trained CNN-LSTM model, using the CNN-LSTM model to predict the ice thickness, and obtaining the predicted value of the ice thickness on the target transmission line, the accuracy of the ice thickness on the target transmission line can be effectively improved, so as to achieve accurate prediction of the ice thickness on the target transmission line.

[0016] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of 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 creative work.

[0018] Figure 1 An application scenario diagram provided for an embodiment of the present application; Figure 2 A flowchart of a method for predicting ice thickness on a transmission line provided in an embodiment of the present application; Figure 3 A schematic diagram of an ice thickness prediction device on a transmission line provided in an embodiment of the present application; Figure 4 It is a schematic block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] 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 making creative work are within the scope of protection of this application.

[0020] It should be noted that the terms "first", "second", etc. in the specification and claims 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. 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 server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0021] As mentioned above, with the development of technology, support vector regression (SVR) algorithm, extreme learning machine (ELM) neural network model and support vector machine (SVM) model based on particle swarm optimization are used to predict ice thickness of transmission lines. However, these machine learning-based ice prediction methods usually have more empirical parameters when establishing models, and the values ​​of model parameters are often difficult to determine, resulting in low model reusability.

[0022] In order to solve the above technical problems, the inventive concept of the present application is: obtain the meteorological data to be predicted in the area where the target transmission line is located; input the meteorological data to be predicted into the pre-trained CNN-LSTM model to obtain the predicted value of the ice thickness on the target transmission line. Among them, the CNN-LSTM model is a model for predicting the ice thickness value on the transmission line based on meteorological data; the hyperparameters in the CNN-LSTM model are determined according to the snake optimization algorithm. The present application determines the hyperparameters in the CNN-LSTM model based on the snake optimization algorithm to achieve effective optimization of the hyperparameters in the CNN-LSTM model, avoids the random determination of the model hyperparameters in the related art, thereby effectively improving the convergence speed of the hyperparameters in the CNN-LSTM model during the training process, and improving the prediction effect of the hyperparameters in the trained CNN-LSTM model. Furthermore, by inputting the meteorological data to be predicted into the pre-trained CNN-LSTM model, using the CNN-LSTM model to predict the ice thickness, and obtaining the predicted value of the ice thickness on the target transmission line, the accuracy of the ice thickness on the target transmission line can be effectively improved.

[0023] It should be understood that the technical solution of the present application can be applied to the following scenarios, but is not limited to: In some possible implementations, Figure 1 An application scenario diagram provided for an embodiment of the present application, such as Figure 1As shown, the application scenario may include an electronic device 110 and a network device 120. The electronic device 110 may establish a connection with the network device 120 via a wired network or a wireless network.

[0024] Exemplarily, the electronic device 110 may be a desktop computer, a laptop computer, a tablet computer, etc., but is not limited thereto. The network device 120 may be a terminal device or a server, but is not limited thereto. In one embodiment of the present application, the electronic device 110 may send a request message to the network device 120, and the request message may be used to request to obtain the meteorological data to be predicted in the area where the target transmission line is located. Further, the electronic device 110 may receive a response message sent by the network device 120, and the response message includes obtaining the meteorological data to be predicted in the area where the target transmission line is located.

[0025] also, Figure 1 An electronic device 110 and a network device 120 are provided as an example, but other numbers of electronic devices and network devices may actually be included, and the present application does not impose any limitation on this.

[0026] In other possible implementations, the technical solution of the present application may also be executed by the above-mentioned electronic device 110, or the technical solution of the present application may also be executed by the above-mentioned network device 120, and the present application does not impose any limitation on this.

[0027] After introducing the application scenarios of the embodiments of the present application, the technical solutions of the present application will be described in detail below: Figure 2 A flowchart of a method for predicting ice thickness on a transmission line provided in an embodiment of the present application. The method can be performed as follows: Figure 1 The electronic device 110 shown is executed, but is not limited thereto. Figure 2 As shown, the method may include the following steps: S210, obtaining the meteorological data to be predicted in the area where the target transmission line is located.

[0028] Here, the meteorological data to be predicted may include temperature, humidity, wind speed, and rainfall in the area where the target transmission line is located.

[0029] S220: Input the meteorological data to be predicted into the pre-trained CNN-LSTM model to obtain the predicted value of ice thickness on the target transmission line.

[0030] Among them, the CNN-LSTM model is a model used to predict the ice thickness value on the transmission line based on meteorological data; the hyperparameters in the CNN-LSTM model are determined according to the snake optimization algorithm.

[0031] By adopting the above method, the hyperparameters in the CNN-LSTM model are determined based on the snake optimization algorithm, which realizes the effective optimization of the hyperparameters in the CNN-LSTM model and avoids the random determination of the model hyperparameters in the related technology, thereby effectively improving the convergence speed of the hyperparameters in the CNN-LSTM model during the training process and improving the prediction effect of the hyperparameters in the trained CNN-LSTM model. Furthermore, by inputting the meteorological data to be predicted into the pre-trained CNN-LSTM model, the CNN-LSTM model is used to predict the ice thickness, and the predicted value of the ice thickness on the target transmission line is obtained, which can effectively improve the accuracy of the ice thickness on the target transmission line.

[0032] In some optional embodiments, the hyperparameters in the CNN-LSTM model are determined by: S310, obtaining an initialized total snake population according to the positions of each individual snake in the total snake population, the upper bound of the total snake population and the lower bound of the total snake population; the total snake population includes the positions of multiple individual snakes, and the position of each individual snake is a set of hyperparameter values ​​corresponding to the CNN-LSTM model.

[0033] Among them, hyperparameters can include learning rate, regularization coefficient and number of neurons.

[0034] Here, the total snake population is a random population with uniform distribution of individual snakes, so that the optimization algorithm can be started based on the total snake population. The total snake population can be initialized by the following formula:

[0035] Where: is the position of the i-th snake individual, r is a random number between 0 and 1, , They are the lower and upper bounds of the total snake population respectively.

[0036] S320, dividing the initialized total snake group based on a preset ratio to obtain male snake groups and female snake groups.

[0037] Taking the preset ratio of 50% as an example, the total snake population is divided into two groups: male snake population and female snake population, which can be expressed as follows:

[0038]

[0039] Where: N is the number of snakes in the total snake population, is the number of male snakes in the total population, is the number of female snakes in the total population.

[0040] S330: Based on the amount of food and the temperature of the entire snake group, determine whether the male snakes in the male snake group and the female snakes in the female snake group have entered a mating mode.

[0041] Here, the amount of food and the temperature of the total snake population are calculated based on the current number of iterations and the preset number of iterations.

[0042] Among them, the temperature of the total snake group can be calculated according to the current number of iterations and the preset number of iterations by the following formula:

[0043] Where: It expresses the temperature of the total snake population, t represents the current iteration number, and T represents the preset iteration number.

[0044] The amount of food can be calculated based on the current number of iterations and the preset number of iterations using the following formula:

[0045] In the formula, Q represents the amount of food, t represents the current number of iterations, and T represents the preset number of iterations. 0.5.

[0046] S340. If the male snakes in the male snake group and the female snakes in the female snake group enter the mating mode, then according to the mating abilities of the best male snake in the male snake group and the best female snake in the female snake group respectively, it is determined whether there are hatching eggs between the best male snake and the best female snake.

[0047] Prior to this step, the best male snake and the worst male snake in the male snake group, and the best female snake and the worst female snake in the female snake group are also determined, wherein the best male snake and the worst male snake can be determined according to the fighting ability of each male snake in the male snake group, that is, the male snake with the highest fighting ability is the best male snake, and the male snake with the worst fighting ability is the worst male snake; similarly, the best female snake and the worst female snake can also be determined according to the fighting ability of each female snake in the female snake group, that is, the female snake with the highest fighting ability is the best female snake, and the female snake with the worst fighting ability is the worst female snake.

[0048] Here, the mating ability of the best male snake is calculated by the following formula:

[0049] Where: is the best male snake's mating ability, is the fitness of the best male snake, is the fitness of the best female snake.

[0050] Here, the mating ability of the best female snake is calculated by the following formula:

[0051] Where: is the mating ability of the best female snakes, is the fitness of the best male snake, is the fitness of the best female snake.

[0052] In addition, after the male snakes in the male snake group and the female snakes in the female snake group enter the mating mode, the corresponding moving positions of the best female snake and the best male snake can be determined according to the mating ability of the best female snake and the mating ability of the best male snake, and the corresponding positions of the best female snake and the best male snake in the total snake group are updated; wherein, the corresponding moving positions of the best female snake and the best male snake are determined by the following formula:

[0053]

[0054] Where: is the best position for male snakes, is the best position for female snakes, is the best male snake's mating ability, is the mating ability of the best female snake, Q is the amount of food, is a random number between 0 and 1, .

[0055] S350. If there are hatching eggs between the best male snake and the best female snake, the hatching eggs will replace the worst male snake in the male snake group and the worst female snake in the female snake group.

[0056] Among them, the hatched eggs will replace the worst male snake in the male snake group and the worst female snake in the female snake group according to the following formula:

[0057] Where: This is the worst position for male snakes. This is the worst position for female snakes. is a random number between 0 and 1, , They are the lower and upper bounds of the total snake population respectively.

[0058] S360. When the number of iterations does not reach the preset number of iterations, repeat the above steps until the number of iterations reaches the preset number of iterations to complete the optimization of the hyperparameters in the CNN-LSTM model.

[0059] By adopting the above method, the hyperparameters used by the CNN-LSTM model are determined based on the snake swarm optimization algorithm, and the hyperparameters of the CNN-LSTM model are effectively optimized, thereby effectively improving the convergence speed of the CNN-LSTM model during the training process and improving the prediction effect of the trained CNN-LSTM model.

[0060] In some possible embodiments, before determining whether male snakes in the male snake group and female snakes in the female snake group have entered the mating mode based on the amount of food and the temperature of the total snake group, the following steps may also be included: S410: Based on the comparison between the amount of food and a preset amount threshold, determine whether the male snakes in the male snake group and the female snakes in the female snake group have entered the exploration stage or the development stage.

[0061] Taking the preset quantity threshold of 0.25 as an example, when the amount of food is less than 0.25, the male snakes in the male snake group and the female snakes in the female snake group are judged to enter the exploration stage; when the amount of food is greater than 0.25, the male snakes in the male snake group and the female snakes in the female snake group are judged to enter the development stage.

[0062] S420. If the male snakes in the male snake group and the female snakes in the female snake group enter the development stage, based on the comparison between the temperature of the total snake group and the preset temperature, it is determined whether the male snakes in the male snake group and the female snakes in the female snake group enter the movement mode or the mating mode.

[0063] S430. If the male snakes in the male snake group and the female snakes in the female snake group enter the mating mode, the best male snake in the male snake group and the best female snake in the female snake group are determined according to the corresponding fighting capabilities of the male snakes in the male snake group and the corresponding fighting capabilities of the female snakes in the female snake group.

[0064] Before the male snakes in the male snake group and the female snakes in the female snake group enter the mating mode, the fighting capabilities of the male snakes in the male snake group and the female snakes in the female snake group in the fighting mode are calculated to obtain a basis for determining the best male snake in the male snake group and the best female snake in the female snake group.

[0065] Among them, the best male snake in the male snake group is determined by the following formula:

[0066] Where: is the position of the ith male snake, It is the position of the best male snake among the females, and FM refers to the fighting ability of the male snake.

[0067] Here, the fighting ability of the best male snake in the male snake group is calculated by the following formula:

[0068] Where: is the fitness value of the best male snake, and fi is the target fitness.

[0069] Among them, the best female snake in the female snake group is determined by the following formula:

[0070] In the formula is the position of the ith female snake, It refers to the position of the best female snake in the male group, and MM is the fighting ability of the female snake.

[0071] Here, the fighting ability of the best female snake in the female snake group is calculated by the following formula:

[0072] Where: is the fitness value of the best female snake, and fi is the target fitness.

[0073] By using the above method, by comparing the corresponding fighting capabilities of male snakes in the male snake group and female snakes in the female snake group in mating mode, the best male snake and the best female snake can be quickly determined to improve the optimization efficiency of the snake group optimization algorithm for the hyperparameters of the CNN-LSTM model.

[0074] In some possible embodiments, if the male snakes in the male snake group and the female snakes in the female snake group enter the development stage, based on the comparison between the temperature of the total snake group and the preset temperature, determining whether the male snakes in the male snake group and the female snakes in the female snake group enter the movement mode or the mating mode may include the following steps: S510: If the temperature of the entire snake group is lower than a preset temperature, the male snakes in the male snake group and the female snakes in the female snake group are determined to enter a mating mode.

[0075] Taking the preset temperature of 0.6°C as an example, if the temperature of the total snake group is less than 0.6°C, it is determined that the male snakes in the male snake group and the female snakes in the female snake group enter the mating mode.

[0076] S520, if the temperature of the total snake group is greater than a preset temperature, determining that the male snakes in the male snake group and the female snakes in the female snake group enter a moving mode; Taking the preset temperature of 0.6°C as an example, if the temperature of the total snake group is greater than 0.6°C, it is determined that the male snakes in the male snake group and the female snakes in the female snake group enter the mobile mode.

[0077] S530: After the male snakes in the male snake group and the female snakes in the female snake group enter the moving mode, the positions of the individual snakes in the total snake group are updated according to the moving positions of the male snakes in the male snake group and the female snakes in the female snake group.

[0078] Among them, after the male snake and the female snake enter the moving mode, the calculation formula of their respective corresponding target moving positions is as follows:

[0079] Where: Is it the position of a male snake or a female snake? It is the food location. Describe the temperature of the total snake population, is a random number between 0 and 1, 2.

[0080] After determining the target moving positions corresponding to the male snakes and the female snakes respectively, it can also include: controlling the movement of each male snake and each female snake respectively according to the target moving positions corresponding to each male snake and the target moving positions corresponding to each female snake, and updating the positions of each individual snake in the total snake group.

[0081] By adopting the above method, it is possible to quickly determine whether the male snakes in the male snake group and the female snakes in the female snake group are in mating mode, so as to improve the optimization efficiency of the snake group optimization algorithm for the hyperparameters of the CNN-LSTM model.

[0082] In some possible embodiments, the present invention further includes: S610: If the male snakes in the male snake group enter the exploration phase, the moving position of each male snake is determined according to the current position, random position, and food finding ability of each male snake.

[0083] Since, when the male snakes in the male snake group enter the exploration phase, it means that all male snakes in the male snake group enter the exploration phase, that is, each male snake will randomly choose any position to find food and update its position accordingly. Here, the corresponding moving position of each male snake can be determined by the following formula:

[0084] In the formula is the current position of the ith male snake, refers to the random position corresponding to each male snake, is the male snake's ability to find food. , are the lower and upper bounds of the total snake population, respectively. is a random number between 0 and 1, = 0.05. Here, the sign direction operator ± is also called the diversity factor, which provides the possibility of increasing or decreasing the position solution so that a good search is performed in all possible directions of the given search space so that this parameter is randomly generated to achieve randomization.

[0085] Among them, the ability to find food for male snakes is expressed as follows:

[0086] Where: yes The fitness of is the fitness of the i-th male snake.

[0087] S620: If the female snakes in the female snake group enter the exploration phase, the corresponding moving position of each female snake is determined according to the current position, random position, and food finding ability of each female snake.

[0088] Here, the moving position of each female snake can be determined by the following formula:

[0089] In the formula is the current position of the ith female snake, refers to the random position of each female snake. The ability to find food. , are the lower and upper bounds of the total snake population, respectively. is a random number between 0 and 1, =0.05.

[0090] Among them, the female snake's ability to find food is shown by the following formula:

[0091] Where: yes The fitness of is the fitness of the i-th female snake in the female snake group.

[0092] S630, according to the corresponding moving positions of the male snakes and the corresponding moving positions of the female snakes, control the male snakes and the female snakes to move respectively, and update the positions of the individual snakes in the total snake group.

[0093] By adopting the above method, after the male snakes in the male snake group and the female snakes in the female snake group enter the exploration stage, the male snakes and the female snakes can be controlled to move respectively by determining the moving positions based on the current positions, random positions, and food-finding abilities of the male snakes and the female snakes, and the positions of the individual snakes in the total snake group can be updated, so as to facilitate the iterative optimization of the hyperparameters in the CNN-LSTM model in a new round.

[0094] In some possible implementations, the CNN-LSTM model is obtained by the following method: S710, dividing the model training samples into a training set and a test set; the model training samples include historical meteorological data and ice thickness values ​​on the transmission lines corresponding to the historical meteorological data; S720, training a CNN-LSTM model based on the training set to obtain an original CNN-LSTM model; using the model training samples in the test set to perform a model test on the original CNN-LSTM model to obtain a model test result; S730: If the model test result is that the test passes, the original CNN-LSTM model is determined as the final CNN-LSTM model.

[0095] By adopting the above method, a CNN-LSTM model can be obtained which can accurately predict the ice thickness value on the transmission line, thereby effectively improving the accuracy of the ice thickness on the target transmission line.

[0096] Furthermore, the CNN-LSTM model includes a convolutional neural network, a bidirectional long short-term memory network and a fully connected layer; the convolutional neural network is used to extract spatial features of the predicted meteorological data; the bidirectional long short-term memory network is used to extract temporal features of the predicted meteorological data; the fully connected layer is used to generate a predicted value of ice thickness on the target transmission line based on spatial and temporal features.

[0097] Here, the convolutional neural network (CNN) can effectively reduce the number of parameters and data dimensions of the deep neural network while deeply mining the spatial features of the input data through local connectivity, weight sharing and pooling operations, thereby improving the computing speed and data analysis capabilities of the CNN. Among them, the main components of CNN include convolutional layer, pooling layer, fully connected layer and output layer, and here, the convolutional layer and pooling layer are the core parts.

[0098] Specifically, the convolution layer here includes multiple convolution kernels, which mainly complete the data feature extraction by convolution operation on the input meteorological data to be predicted, and different feature mappings are realized by different convolution kernel calculations. Here, the specific process of this step operation can be: first, the input is convolved by the convolution kernel, and then the result is activated by the activation function to complete the nonlinear calculation. The specific mathematical calculation formula of the convolution layer is shown as follows:

[0099] In the formula, and Represent the weight and bias of the k convolution kernel in the lth convolution layer respectively; Represents the input information of the (i, j) region in the l-layer convolution; The activation function representing the convolution layer helps to improve the fitting ability of the model. Here, the activation function used in CNN can be one of Sigmoid function, Tanh function and Relu function.

[0100] The pooling layer here comes after the convolution layer. Since a large amount of feature information is obtained after the convolution operation, the pooling layer can reduce the dimension of a large amount of complex information, and then summarize and extract the effective information. It is generally divided into maximum pooling and average pooling. It is convenient for subsequent feature classification. The output layer is the last layer of the convolutional neural network, which is mainly used to output the final prediction results. The fully connected layer here plays the role of a classifier as a whole. It is set between the pooling layer and the output layer. It is mainly used to summarize and store the feature information learned by the convolution and pooling layers in the same space to generate the predicted value of ice thickness on the target transmission line.

[0101] The bidirectional long short-term memory network (LSTM) in this embodiment is a special recurrent neural network model that aims to solve the gradient vanishing problem in traditional RNN. Here, LSTM uses a gated cell structure to regulate the information flow, allowing the previous information to be selectively retained or forgotten while incorporating new information. This design enhances the efficiency of LSTM in processing sequence data. The core of LSTM lies in its gated cell structure, which consists of three gated components and a cell state component: the input gate controls the input of new information, the output gate determines the output information, and the forget gate determines which irrelevant information can be forgotten for the current task. The cell state reflects the information previously memorized. These gates are implemented by combining sigmoid and tanh functions. The gating mechanism of LSTM gives it excellent long-term memory capabilities and excellent performance in processing long sequence data, so it is widely used in various fields.

[0102] Among them, LSTM contains a unique "gate" mechanism, which consists of three different elements: input gate, output gate and forget gate. Here, the formula corresponding to the input gate is: ; The formula corresponding to the forget gate is: ; The formula corresponding to the memory unit is: ; The formula corresponding to the output gate is: ; The formula corresponding to the hidden layer output is: ;in, , , and is the weight matrix, is the output of the previous unit, is the input, is the previous state of the unit, and , , and is the bias, is the output of the sigmoid gate.

[0103] Figure 3 is a schematic diagram of an ice thickness prediction device 800 on a transmission line according to an embodiment of the present invention, the device 800 comprising: The data acquisition module 810 is used to acquire the meteorological data to be predicted in the area where the target power transmission line is located; The prediction module 820 is used to input the meteorological data to be predicted into the pre-trained CNN-LSTM model to obtain the predicted value of the ice thickness on the target transmission line; the CNN-LSTM model is a model used to predict the ice thickness value on the transmission line based on the meteorological data; wherein the hyperparameters in the CNN-LSTM model are determined according to the snake optimization algorithm.

[0104] In some implementations, the apparatus 800 further includes a hyperparameter determination module, and the parameter determination module includes: The total snake population initialization unit is used to obtain an initialized total snake population according to the positions of each individual snake in the total snake population, the upper bound of the total snake population, and the lower bound of the total snake population; the total snake population includes the positions of multiple individual snakes, and the position of each individual snake is a set of hyperparameter values ​​corresponding to the CNN-LSTM model; A snake group division unit, used for dividing the initialized total snake group based on a preset ratio to obtain male snake groups and female snake groups; A first judgment unit is used to judge whether the male snakes in the male snake group and the female snakes in the female snake group have entered the mating mode based on the amount of food and the temperature of the total snake group; the amount of food and the temperature of the total snake group are calculated according to the current iteration number and the preset iteration number; The second judgment unit is used for judging whether there are hatching eggs between the best male snake and the best female snake according to the mating abilities of the best male snake in the male snake group and the best female snake in the female snake group respectively if the male snakes in the male snake group and the female snakes in the female snake group enter the mating mode; a replacement unit for replacing the hatched eggs with the worst male snake in the male snake group and the worst female snake in the female snake group if there are hatched eggs between the best male snake and the best female snake; The iteration unit is used to repeatedly execute the above steps when the number of iterations does not reach the preset number of iterations, until the number of iterations reaches the preset number of iterations, so as to complete the optimization of the hyperparameters in the CNN-LSTM model.

[0105] In some possible implementations, the parameter determination module further includes: A third judgment unit is used to judge whether the male snakes in the male snake group and the female snakes in the female snake group have entered the exploration stage or the development stage based on the comparison between the food quantity and the preset quantity threshold; a fourth judgment unit, for judging whether the male snakes in the male snake group and the female snakes in the female snake group have entered a moving mode or a mating mode based on a comparison between a temperature of the total snake group and a preset temperature if the male snakes in the male snake group and the female snakes in the female snake group have entered a development stage; A determination unit is used to determine the best male snake in the male snake group and the best female snake in the female snake group according to the corresponding fighting capabilities of the male snakes in the male snake group and the corresponding fighting capabilities of the female snakes in the female snake group if the male snakes in the male snake group and the female snakes in the female snake group enter a mating mode.

[0106] In some possible implementations, the fourth determination unit includes: A first determining subunit is used to determine that the male snakes in the male snake group and the female snakes in the female snake group enter a mating mode if the temperature of the total snake group is lower than a preset temperature; The second determining subunit is used to determine that the male snakes in the male snake group and the female snakes in the female snake group enter the moving mode if the temperature of the total snake group is greater than a preset temperature; After the male snakes in the male snake group and the female snakes in the female snake group enter the moving mode, the positions of the individual snakes in the total snake group are updated according to the moving positions of the male snakes in the male snake group and the female snakes in the female snake group.

[0107] In some possible implementations, the parameter determination module further includes: A first moving position determining unit is used to determine the moving position corresponding to each male snake according to the current position, random position, and food finding ability of each male snake if the male snakes in the male snake group enter the exploration stage; A second mobile position determination unit is used to determine the mobile position corresponding to each female snake according to the current position, random position, and food finding ability of each female snake if the female snakes in the female snake group enter the exploration stage; The position updating unit is used to control the movement of each male snake and each female snake according to the corresponding moving position of each male snake and the corresponding moving position of each female snake, and to update the position of each individual snake in the total snake group.

[0108] In some implementations, the device 800 further includes a model training module, and the model training module includes: A sample division unit is used to divide the model training samples into a training set and a test set; the model training samples include historical meteorological data and ice thickness values ​​on the transmission line corresponding to the historical meteorological data; A sample training unit is used to train a CNN-LSTM model based on a training set to obtain an original CNN-LSTM model; The testing unit is used to use the model training samples in the test set to perform model testing on the original CNN-LSTM model and obtain the model testing results; The model determination unit is used to determine the original CNN-LSTM model as the final CNN-LSTM model if the model test result is that the test passes.

[0109] In some implementations, the CNN-LSTM model includes a convolutional neural network, a bidirectional long short-term memory network, and a fully connected layer; Convolutional neural networks are used to extract spatial features of the meteorological data to be predicted; Bidirectional long short-term memory network is used to extract the time characteristics of the forecasted meteorological data; The fully connected layer is used to generate the predicted value of ice thickness on the target transmission line based on spatial and temporal characteristics.

[0110] It should be understood that the embodiment of the ice thickness prediction device on the transmission line and the embodiment of the ice thickness prediction method on the transmission line can correspond to each other, and similar descriptions can refer to the embodiment of the ice thickness prediction method on the transmission line. To avoid repetition, they will not be repeated here. Specifically, Figure 3 The device 800 shown can execute the above-mentioned embodiment of the ice thickness prediction method on the transmission line, and the above-mentioned and other operations and / or functions of each module in the device 800 are respectively for realizing the corresponding processes in the above-mentioned ice thickness prediction method on the transmission line, which will not be repeated here for the sake of brevity.

[0111] In the above, the device 800 of the embodiment of the present invention is described from the perspective of the functional module in conjunction with the accompanying drawings. It should be understood that the functional module can be implemented in the form of hardware, can be implemented by instructions in the form of software, and can also be implemented by a combination of hardware and software modules. Specifically, the steps of the ice thickness prediction method and the detection method embodiment on the transmission line in the embodiment of the present invention can be completed by the hardware integrated logic circuit and / or software instructions in the processor, and the steps of the ice thickness prediction method and the detection method on the transmission line disclosed in the embodiment of the present invention can be directly embodied as a hardware decoding processor to execute, or a combination of hardware and software modules in the decoding processor. Optionally, the software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps in the above-mentioned ice thickness prediction method and the detection method embodiment on the transmission line in combination with its hardware.

[0112] Figure 4 is a schematic block diagram of an electronic device 110 according to an embodiment of the present invention.

[0113] like Figure 4 As shown, the electronic device 110 may include: The memory 111 and the processor 112, the memory 111 is used to store the computer program and transmit the program code to the processor 112. In other words, the processor 112 can call and run the computer program from the memory 111 to implement the method in the embodiment of the present invention.

[0114] For example, the processor 112 may be configured to execute the above method embodiments according to instructions in the computer program.

[0115] In some embodiments of the present invention, the electronic device 110 may include but is not limited to: General-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0116] In some embodiments of the present invention, the memory 111 includes but is not limited to: Volatile memory and / or non-volatile memory. Among them, the non-volatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM) or flash memory. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct memory bus random access memory (Direct Rambus RAM, DR RAM).

[0117] In some embodiments of the present invention, the computer program may be divided into one or more modules, which are stored in the memory 111 and executed by the processor 112 to complete the method provided by the present invention. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the controller.

[0118] like Figure 4 As shown, the electronic device 110 may further include: The transceiver 113 may be connected to the processor 112 or the memory 111 .

[0119] The processor 112 may control the transceiver 113 to communicate with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices. The transceiver 113 may include a transmitter and a receiver. The transceiver 113 may further include an antenna, and the number of antennas may be one or more.

[0120] It should be understood that the various components in the electronic device are connected via a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus and a status signal bus.

[0121] The present invention also provides a computer storage medium having a computer program stored thereon, which enables the computer to perform the method of the above method embodiment when the computer program is executed by the computer. In other words, an embodiment of the present invention also provides a computer program product containing instructions, which enables the computer to perform the method of the above method embodiment when the instructions are executed by the computer.

[0122] When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integration. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disc (Digital Video Disc, DVD)), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0123] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0124] In the several embodiments provided by the present invention, 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 module is only a logical function division. There may be other division methods in actual implementation, such as multiple modules 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 through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0125] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. For example, each functional module in each embodiment of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0126] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in this application, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for predicting ice thickness on a transmission line, characterized in that: include: Obtain the meteorological data to be predicted in the area where the target transmission line is located; The meteorological data to be predicted is input into a pre-trained CNN-LSTM model to obtain a predicted value of ice thickness on the target transmission line; the CNN-LSTM model is a model used to predict the ice thickness value on the transmission line based on meteorological data; wherein the hyperparameters in the CNN-LSTM model are determined based on a snake optimization algorithm.

2. The method according to claim 1, characterized in that: The hyperparameters in the CNN-LSTM model are determined in the following way: According to the positions of the individual snakes in the total snake population, the upper bound of the total snake population and the lower bound of the total snake population, an initialized total snake population is obtained; The total snake group includes the positions of multiple individual snakes, and the position of each individual snake is a set of hyperparameter values ​​corresponding to the CNN-LSTM model; Dividing the initialized total snake group based on a preset ratio to obtain a male snake group and a female snake group; Based on the amount of food and the temperature of the total snake group, determining whether the male snakes in the male snake group and the female snakes in the female snake group have entered a mating mode; the amount of food and the temperature of the total snake group are both calculated based on the current number of iterations and the preset number of iterations; If the male snakes in the male snake group and the female snakes in the female snake group enter the mating mode, judging whether there are hatching eggs between the best male snake and the best female snake according to the mating abilities of the best male snake in the male snake group and the best female snake in the female snake group respectively; If there are hatched eggs between the best male snake and the best female snake, the hatched eggs are used to replace the worst male snake in the male snake group and the worst female snake in the female snake group; When the number of iterations does not reach the preset number of iterations, the above steps are repeated until the number of iterations reaches the preset number of iterations to complete the optimization of the hyperparameters in the CNN-LSTM model.

3. The method according to claim 2, characterized in that Before judging whether the male snakes in the male snake group and the female snakes in the female snake group have entered the mating mode based on the amount of food and the temperature of the total snake group, the method further includes: Based on the comparison between the amount of food and a preset amount threshold, determining whether the male snakes in the male snake group and the female snakes in the female snake group have entered an exploration phase or an exploitation phase; If the male snakes in the male snake group and the female snakes in the female snake group enter the development stage, based on the comparison between the temperature of the total snake group and the preset temperature, it is determined whether the male snakes in the male snake group and the female snakes in the female snake group enter the movement mode or the mating mode; If the male snakes in the male snake group and the female snakes in the female snake group enter the mating mode, the best male snake in the male snake group and the best female snake in the female snake group are determined according to the corresponding fighting capabilities of the male snakes in the male snake group and the corresponding fighting capabilities of the female snakes in the female snake group.

4. The method according to claim 3, characterized in that If the male snakes in the male snake group and the female snakes in the female snake group enter the development stage, based on the comparison between the temperature of the total snake group and the preset temperature, it is judged whether the male snakes in the male snake group and the female snakes in the female snake group enter the movement mode or the mating mode, including: If the temperature of the total snake group is lower than a preset temperature, the male snakes in the male snake group and the female snakes in the female snake group are determined to enter a mating mode; If the temperature of the total snake group is greater than a preset temperature, the male snakes in the male snake group and the female snakes in the female snake group are determined to enter a moving mode; After the male snakes in the male snake group and the female snakes in the female snake group enter the moving mode, the positions of the individual snakes in the total snake group are updated according to the moving positions of the male snakes in the male snake group and the female snakes in the female snake group.

5. The method according to claim 3, characterized in that: Also includes: If the male snakes in the male snake group enter the exploration phase, the moving positions of the male snakes are determined according to the current positions, random positions, and food finding abilities of the male snakes; If the female snakes in the female snake group enter the exploration phase, the corresponding moving positions of the female snakes are determined according to the current positions, random positions, and food finding abilities of the female snakes; According to the moving positions corresponding to the male snakes and the moving positions corresponding to the female snakes, the male snakes and the female snakes are controlled to move respectively, and the positions of the individual snakes in the total snake group are updated.

6. The method according to claim 1, characterized in that The CNN-LSTM model is obtained by the following method: Dividing the model training samples into a training set and a test set; the model training samples include historical meteorological data and ice thickness values ​​on the transmission line corresponding to the historical meteorological data; Training the CNN-LSTM model based on the training set to obtain an original CNN-LSTM model; using the model training samples in the test set to perform a model test on the original CNN-LSTM model to obtain a model test result; If the model test result is passed, the original CNN-LSTM model is determined as the final CNN-LSTM model.

7. The method according to claim 6, characterized in that The CNN-LSTM model includes a convolutional neural network, a bidirectional long short-term memory network and a fully connected layer; The convolutional neural network is used to extract spatial features of the meteorological data to be predicted; The bidirectional long short-term memory network is used to extract the time characteristics of the meteorological data to be predicted; The fully connected layer is used to generate a predicted value of ice thickness on the target transmission line according to the spatial feature and the temporal feature.

8. A device for predicting ice thickness on a transmission line, characterized in that: include: A data acquisition module, used to obtain the meteorological data to be predicted in the area where the target transmission line is located; A prediction module is used to input the meteorological data to be predicted into a pre-trained CNN-LSTM model to obtain a predicted value of ice thickness on the target transmission line; the CNN-LSTM model is a model for predicting the ice thickness value on the transmission line based on meteorological data; wherein the hyperparameters in the CNN-LSTM model are determined based on a snake optimization algorithm.

9. An electronic device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, and the processor being used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein the computer program enables a computer to execute the method according to any one of claims 1 to 7.

Images