Phase-to-phase spacer active anti-galloping method and device

Abstract

The invention belongs to the technical field of galloping prevention and control in the capital construction stage of a power transmission line, and particularly relates to an active galloping prevention method and device for phase-to-phase spacers, and the method comprises the steps: collecting related information of the power transmission line and meteorological data of prediction time; on the basis of the related information of the power transmission line and the meteorological data of the prediction time, utilizing a pre-established galloping disaster risk prediction model to predict galloping characteristic data of the power transmission line of the prediction time; and adjusting the opening and closing size of the umbrella skirt of the phase-to-phase spacer in the prediction time according to the galloping characteristic data of the power transmission line in the prediction time. According to the technical scheme provided by the invention, the accuracy of galloping risk prediction is improved, and when the galloping risk is predicted, the aerodynamic configuration and the flexural rigidity are adjusted by adjusting the opening and closing size of the umbrella skirts of the phase-to-phase spacers, so that the purpose of active galloping prevention is achieved, and the influence of icing galloping on a power transmission line is reduced.

Description

Technical Field

[0001] The invention belongs to the technical field of galloping prevention and control in the infrastructure stage of power transmission lines, and particularly relates to a method and device for actively preventing galloping of phase-to-phase spacer bars. Background Art

[0002] Due to the harsh environment of overhead wires, eccentric ice is easily formed on the wires, and with the effect of strong winds, it is easy to cause dancing and damage. The wires of infrastructure lines are not electrified, and their temperature is more affected by the environment. Therefore, they are more susceptible to ice dancing than operating lines, so the prevention and control requirements and difficulties are greater.

[0003] Most of the existing phase spacers are non-adjustable structures. Once installed, their appearance structure, installation position, stiffness, damping and other dynamic characteristics remain unchanged, and they are unable to adapt to the prevention and control needs of complex environments. Summary of the invention

[0004] In order to overcome the problems existing in the above-mentioned related technologies, the present application provides a method and device for actively preventing interphase spacer bars from dancing.

[0005] According to a first aspect of an embodiment of the present application, a method for actively preventing interphase spacer dancing is provided, comprising:

[0006] Collect relevant information of transmission lines and meteorological data at the forecast time;

[0007] Based on the relevant information of the power transmission line and the meteorological data at the predicted time, using a pre-established power transmission line sway disaster risk prediction model, the power transmission line sway characteristic data at the predicted time is predicted;

[0008] According to the dancing characteristic data of the power transmission line at the predicted time, the opening and closing size of the shed of the phase spacer at the predicted time is adjusted.

[0009] Preferably, the relevant information of the power transmission line includes: conductor parameters and topography;

[0010] The conductor parameters include: conductor diameter, number of splits and outer diameter of interphase spacer sheds;

[0011] The topography includes: altitude, terrain undulation and vegetation distribution.

[0012] Preferably, the meteorological data includes: wind speed, wind direction, temperature, humidity and snowfall;

[0013] The dancing characteristic data include: dancing amplitude and duration.

[0014] Preferably, the process of establishing the dancing disaster risk prediction model includes:

[0015] Collect historical meteorological data, historical transmission line related information and historical transmission line dancing characteristic data;

[0016] Processing the historical meteorological data, the historical information related to the power transmission lines, and the historical power transmission line dancing characteristic data to obtain a historical power transmission line dancing disaster data set;

[0017] Dividing the historical dancing disaster dataset into a training set and a validation set;

[0018] Using the training set to train the convolutional neural network to obtain a trained convolutional neural network;

[0019] The trained convolutional neural network is verified using the verification set. If the verification is successful, the trained convolutional neural network is the dancing disaster risk prediction model. If the verification fails, the hyperparameters of the convolutional neural network are adjusted and the convolutional neural network is retrained.

[0020] Preferably, the data processing of the historical meteorological data, the historical power transmission line related information and the historical power transmission line dancing characteristic data includes:

[0021] Performing data cleaning on the historical meteorological data, the historical information related to the power transmission line, and the historical power transmission line galloping characteristic data to remove abnormal values ​​and erroneous data in the historical meteorological data, the historical information related to the power transmission line, and the historical power transmission line galloping characteristic data to obtain data after data processing;

[0022] The processed data is standardized to obtain the historical dancing disaster data set.

[0023] Preferably, the using the training set to train the convolutional neural network to obtain the trained convolutional neural network includes:

[0024] The historical meteorological data and the related information of the historical power transmission lines in the training set are used as the input layer training samples of the convolutional neural network, and the dancing feature data of the historical power transmission lines in the training set are used as the output layer training samples of the convolutional neural network. The convolutional neural network is trained to obtain the trained convolutional neural network.

[0025] Preferably, the verifying the trained convolutional neural network using the verification set includes:

[0026] Using the historical meteorological data and the historical transmission line related information in the verification set as inputs to the trained convolutional neural network, and outputting predicted transmission line dancing feature data;

[0027] The prediction accuracy is determined based on the predicted power transmission line dancing feature data and the historical power transmission line dancing feature data in the verification set. If the prediction accuracy is greater than or equal to the prediction threshold, the verification is successful; if the prediction accuracy is less than the prediction threshold, the verification fails, the hyperparameters of the convolutional neural network are adjusted, and the convolutional neural network with the adjusted hyperparameters is retrained until the verification is successful.

[0028] Preferably, the method of predicting the dancing characteristic data of the power transmission line at the prediction time based on the relevant information of the power transmission line and the meteorological data at the prediction time by using a pre-established dancing disaster risk prediction model comprises:

[0029] Setting the iteration range of the outer diameter of the phase spacer shed in the conductor parameters;

[0030] Based on the iteration range of the outer diameter of the phase-to-phase spacer shed in the conductor parameters, the conductor parameters, the topography and the meteorological data at the prediction time are used as inputs of the dancing disaster risk prediction model, and the dancing characteristic data of the transmission line at the prediction time corresponding to the outer diameter of each phase-to-phase spacer shed in the iteration range is iteratively output;

[0031] The outer diameters of the sheds of each phase spacer rod in the iteration range are traversed in ascending order using the dancing disaster risk prediction model.

[0032] Preferably, adjusting the opening and closing size of the shed of the phase spacer within the predicted time according to the dancing characteristic data of the power transmission line within the predicted time comprises:

[0033] The outer diameter of the phase spacer shed in the iteration range corresponding to the dancing characteristic data of the power transmission line at the predicted time that meets the screening condition is selected as the opening and closing adjustment size of the shed of the phase spacer; wherein the screening condition is: the dancing amplitude is greater than or equal to the dancing amplitude threshold and the dancing time is less than or equal to the dancing time threshold;

[0034] According to the opening and closing adjustment size of the shed of the interphase spacer bar, the opening and closing size of the shed of the interphase spacer bar within the predicted time is adjusted.

[0035] According to a second aspect of an embodiment of the present application, there is provided an interphase spacer active anti-dancing device, comprising:

[0036] A collection unit, used to collect relevant information of the transmission line and meteorological data at the forecast time;

[0037] A prediction unit, configured to predict and obtain the dancing characteristic data of the power transmission line at the prediction time based on the relevant information of the power transmission line and the meteorological data at the prediction time and using a pre-established dancing disaster risk prediction model;

[0038] The adjusting unit is used to adjust the opening and closing size of the shed of the phase spacer within the predicted time according to the dancing characteristic data of the power transmission line within the predicted time.

[0039] According to a third aspect of an embodiment of the present application, there is provided a computer device, including: one or more processors;

[0040] The processor is used to store one or more programs;

[0041] When the one or more programs are executed by the one or more processors, the interphase spacer rod active anti-dancing method is implemented.

[0042] According to a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed, the active anti-dance method for interphase spacer bars is implemented.

[0043] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:

[0044] The present invention provides an active anti-dancing method and device for phase spacers. The method collects relevant information of a transmission line and meteorological data at a predicted time, and based on the relevant information of the transmission line and the meteorological data at the predicted time, uses a pre-established dancing disaster risk prediction model to predict the dancing characteristic data of the transmission line at the predicted time, thereby improving the accuracy of the dancing risk prediction. The method adjusts the opening and closing size of the shed of the phase spacer within the predicted time according to the dancing characteristic data of the transmission line at the predicted time, thereby achieving the purpose of active anti-dancing by adjusting the opening and closing size of the shed of the phase spacer when the dancing risk is predicted, and reducing the influence of ice dancing on the transmission line. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 is a flow chart of an active anti-dance method for interphase spacer bars provided by an embodiment of the present invention;

[0047] Figure 2 is a flow chart of an active anti-dance method for interphase spacer bars provided by an embodiment of the present invention;

[0048] Figure 3 is a schematic diagram of the structure of a convolutional neural network provided by an embodiment of the present invention;

[0049] Figure 4 is a schematic diagram of a convolutional neuron structure provided by an embodiment of the present invention;

[0050] Figure 5 is a flow chart of the gateway control logic provided by an embodiment of the present invention;

[0051] Figure 6 is a schematic diagram of shed size control provided by an embodiment of the present invention;

[0052] Figure 7 The invention is a block diagram of a phase-to-phase spacer rod active anti-dance device provided in an embodiment of the invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the following embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Embodiment 1

[0055] The present invention provides a method for actively preventing interphase spacer bars from dancing, such as Figure 1 As shown, the following steps are included:

[0056] Step 101: Collect relevant information of the power transmission line and meteorological data at the forecast time;

[0057] Step 102: Based on the relevant information of the power transmission line and the meteorological data at the prediction time, using the pre-established power transmission line sway disaster risk prediction model, predict the sway characteristic data of the power transmission line at the prediction time;

[0058] Step 103: adjusting the opening and closing size of the shed of the phase spacer within the prediction time according to the dancing characteristic data of the power transmission line within the prediction time.

[0059] Further, relevant information of the transmission line includes: conductor parameters and topography;

[0060] Conductor parameters include: conductor diameter, number of splits and outer diameter of phase spacer sheds;

[0061] Topography includes: altitude, terrain undulation and vegetation distribution.

[0062] Further, meteorological data, including: wind speed, wind direction, temperature, humidity and snowfall;

[0063] The dancing characteristic data include: dancing amplitude and duration.

[0064] Furthermore, the method further includes: Step 100: establishing a dancing disaster risk prediction model; Step 100, including:

[0065] Step 1001: Collect historical meteorological data, historical information related to power transmission lines, and historical dancing characteristic data of power transmission lines;

[0066] Step 1002: Processing historical meteorological data, historical power transmission line related information and historical power transmission line galloping characteristic data to obtain a historical galloping disaster data set;

[0067] Step 1003: Divide the historical dancing disaster dataset into a training set and a validation set;

[0068] Step 1004: training the convolutional neural network using the training set to obtain a trained convolutional neural network;

[0069] Step 1005: Use the validation set to validate the trained convolutional neural network. If the validation is successful, the trained convolutional neural network is a dancing disaster risk prediction model. If the validation fails, adjust the hyperparameters of the convolutional neural network and retrain the convolutional neural network.

[0070] Further, step 1002 includes:

[0071] Performing data cleaning on historical meteorological data, historical information related to power transmission lines, and historical power transmission line galloping characteristic data to remove abnormal values ​​and erroneous data in the historical meteorological data, historical information related to power transmission lines, and historical power transmission line galloping characteristic data to obtain data processed;

[0072] The processed data are standardized to obtain the historical dancing disaster dataset.

[0073] Further, step 1004 includes:

[0074] The historical meteorological data and the related information of the historical power transmission lines in the training set are used as the input layer training samples of the convolutional neural network, and the dancing feature data of the historical power transmission lines in the training set are used as the output layer training samples of the convolutional neural network. The convolutional neural network is trained to obtain the trained convolutional neural network.

[0075] Further, step 1005 includes:

[0076] The historical meteorological data and the related information of the historical power transmission lines in the verification set are used as the input of the trained convolutional neural network, and the predicted power transmission line dancing feature data is output;

[0077] The prediction accuracy is determined based on the predicted power transmission line dancing feature data and the historical power transmission line dancing feature data in the verification set. If the prediction accuracy is greater than or equal to the prediction threshold, the verification is successful; if the prediction accuracy is less than the prediction threshold, the verification fails, and the hyperparameters of the convolutional neural network are adjusted, and the convolutional neural network with the adjusted hyperparameters is retrained until the verification is successful. In some embodiments, other methods can also be used to verify the trained convolutional neural network using the verification set, but are not limited to.

[0078] It should be noted that the methods of "determining the prediction accuracy based on the predicted power line dancing feature data and the historical power line dancing feature data in the verification set" and "adjusting the hyperparameters of the convolutional neural network" involved in the embodiments of the present invention are well known to those skilled in the art, and therefore, their specific implementation methods will not be described in detail.

[0079] For example, there are a total of 100 groups of data in the verification set, and there are also 100 groups of predicted transmission line dancing feature data. According to the comparison between the predicted transmission line dancing feature data and the historical transmission line dancing feature data in the verification set, 97 groups of the predicted transmission line dancing feature data are consistent with the historical transmission line dancing feature data, and the prediction accuracy is 97%.

[0080] The present invention does not limit the "prediction threshold value", which can be set by those skilled in the art according to engineering needs or experimental data, etc. In some embodiments, the prediction threshold value can be, but is not limited to, 99%.

[0081] Further, step 102 includes:

[0082] Set the iteration range of the outer diameter of the phase spacer shed in the conductor parameters;

[0083] Based on the iteration range of the outer diameter of the shed of the phase spacer in the conductor parameters, the conductor parameters, topography and meteorological data at the prediction time are used as the input of the galloping disaster risk prediction model, and the galloping characteristic data of the transmission line at the prediction time corresponding to the outer diameter of the shed of each phase spacer in the iteration range is iteratively output;

[0084] Among them, the outer diameters of the sheds of each phase spacer rod in the iteration range are traversed in ascending order using the dancing disaster risk prediction model.

[0085] The present invention does not limit the "iterative range of the outer diameter of the interphase spacer rod shed", which can be set by those skilled in the art according to engineering needs or experimental data.

[0086] For example, based on the relevant information of the transmission line and the meteorological data at the prediction time, using the pre-established swaying disaster risk prediction model, the swaying characteristic data of the transmission line at the prediction time is predicted, including the following steps:

[0087] Step a: The iteration range of the outer diameter R of the phase spacer shed in the conductor parameters is set to [1.2D, 20D], and the iteration interval is 0.2D; wherein D is the core diameter of the phase spacer;

[0088] Step b: let the outer diameter of the phase spacer shed in the conductor parameters be R=1.2D;

[0089] Step c: using conductor parameters, topography and meteorological data at the prediction time as inputs to the power transmission line swaying disaster risk prediction model, and outputting the power transmission line swaying characteristic data at the prediction time;

[0090] Step d: Determine whether the outer diameter R of the phase spacer shed in the conductor parameters is greater than or equal to 20D. If the outer diameter R of the phase spacer shed in the conductor parameters is greater than or equal to 20D, execute step e; otherwise, set R=R+0.2D and return to step c;

[0091] Step e: selecting the outer diameter of the phase spacer shed in the iteration range corresponding to the dancing characteristic data of the power transmission line at the prediction time that meets the screening condition as the opening and closing adjustment size of the phase spacer shed;

[0092] Step f: adjusting the size of the sheds of the interphase spacers according to the opening and closing of the sheds, and adjusting the opening and closing size of the sheds of the interphase spacers within the predicted time.

[0093] Further, step 103 includes:

[0094] The outer diameter of the phase spacer shed in the iteration range corresponding to the dancing characteristic data of the power transmission line at the predicted time that meets the screening condition is selected as the opening and closing adjustment size of the shed of the phase spacer; wherein the screening condition is: the dancing amplitude is greater than or equal to the dancing amplitude threshold and the dancing time is less than or equal to the dancing time threshold;

[0095] According to the opening and closing adjustment size of the shed of the phase spacer, the opening and closing size of the shed of the phase spacer within the predicted time is adjusted.

[0096] It should be noted that the present invention does not limit the "screening conditions", which can be set by those skilled in the art according to engineering needs or experimental data, etc. In some embodiments, the screening conditions can be, but are not limited to: dancing amplitude ≥ 6m and dancing duration ≤ 6h; dancing amplitude ≥ 2m and dancing duration ≤ 6h.

[0097] If multiple dancing characteristic data of power transmission lines at predicted times that meet the screening conditions are obtained, the outer diameter of the interphase spacer shed in the iteration range corresponding to the smallest dancing amplitude or the smallest dancing duration in the dancing characteristic data is selected as the opening and closing adjustment size of the shed of the interphase spacer, or the outer diameter of the interphase spacer shed in the iteration range corresponding to the smallest dancing amplitude and the smallest dancing duration in the dancing characteristic data is selected as the opening and closing adjustment size of the shed of the interphase spacer. Those skilled in the art can also select the best set of dancing characteristic data of power transmission lines at predicted times from "multiple dancing characteristic data of power transmission lines at predicted times that meet the screening conditions" according to experimental data or engineering needs.

[0098] For example, the screening condition is set as: dancing amplitude ≥ 6m and dancing duration ≤ 6h, and there are two groups of dancing characteristic data of the transmission line at the predicted time that meet the screening condition, the first group is: dancing amplitude = 6.1m and dancing duration = 6h, and the second group is: dancing amplitude = 6.2m and dancing duration = 6h. Then, the outer diameter of the phase spacer shed in the iteration range corresponding to the first group of dancing characteristic data of the transmission line at the predicted time is selected as the opening and closing adjustment size of the shed of the phase spacer.

[0099] It can be understood that the present invention, based on the dancing characteristic data of the transmission line at the prediction time, combined with the relationship between the input parameter set and the output parameter set represented by the dancing disaster risk prediction model constructed above, traverses the opening and closing sizes of the shed from small to large, and integrates the line meteorological data (at this time, forecast data, replacing the case meteorological data in the training stage), topography and other conductor parameters to analyze and judge the dancing characteristic data, and uses the relatively small and most stable dancing amplitude as the optimal target condition to reversely determine the optimal value of the opening and closing adjustment size of the shed of the phase spacer, and then adjusts the opening and closing size of the shed of the phase spacer within the prediction time according to the optimal value, so as to achieve the purpose of active anti-dancing and reduce the impact of ice dancing on the transmission line.

[0100] The present invention provides an active anti-dancing method and device for phase spacers. The method collects relevant information of a transmission line and meteorological data at a predicted time, and based on the relevant information of the transmission line and the meteorological data at the predicted time, uses a pre-established dancing disaster risk prediction model to predict the dancing characteristic data of the transmission line at the predicted time, thereby improving the accuracy of the dancing risk prediction. The method adjusts the opening and closing size of the shed of the phase spacer within the predicted time according to the dancing characteristic data of the transmission line at the predicted time, thereby achieving the purpose of active anti-dancing by adjusting the opening and closing size of the shed of the phase spacer when the dancing risk is predicted, and reducing the influence of ice dancing on the transmission line.

[0101] To further explain the above-mentioned active anti-dancing method of the interphase spacer, the present invention provides a specific example, that is, using artificial intelligence methods to learn and model historical dancing cases, analyze, summarize and optimize different factors, clarify the dancing risk judgment under on-site meteorological conditions, and use meteorological monitoring devices, gateways that integrate the "artificial neural network judgment and control instructions" function, and active adjustment mechanisms to achieve automatic opening and closing of the interphase spacer sheds, thereby adjusting the stiffness of the interphase spacer and achieving active anti-dancing. Specifically, as Figure 2 As shown, the following steps are included:

[0102] Step 1: Consider the historical galloping disaster dataset of the interphase spacer shed size

[0103] The thickness of the shed of the phase spacer will affect the overall aerodynamic force of the multi-split conductor. Taking this relationship into consideration as well as factors such as meteorological conditions, conductor parameters and topography, a transmission line galloping feature dataset is constructed using rain, snow and freezing disaster inspection data.

[0104] The transmission line dancing characteristic data (including dancing amplitude and duration, etc.), meteorological data (such as wind speed, wind direction, temperature, humidity, snowfall, etc.), conductor parameters (such as conductor diameter, number of splits, outer diameter of phase spacer shed, etc.) and topographic data (such as altitude, terrain undulation, vegetation distribution, etc.) during rain, snow and freezing disasters are collected from historical records.

[0105] The data in the historical records are cleaned to remove abnormal values ​​(such as span greater than 2000m, temperature greater than 10℃ or lower than -10℃, extremely special or unreliable data) and erroneous data (dancing characteristic frequency greater than 10Hz, amplitude less than 0.1m, no interphase spacer shed size data, etc.). Then the data is standardized (all spans are divided by 2000m for normalization; the landform features are parameterized, such as whether there are tall trees or tall buildings, 1 for them, and 0 for them) to make different parameters comparable.

[0106] After completing the above steps, a historical dancing disaster data set can be constructed, which consists of four types of data: dancing characteristic data, meteorological data, conductor parameters, and topography. It should be made clear that the data on the size of the interphase spacer sheds are indispensable.

[0107] 80% of the data in the historical dancing disaster dataset is randomly selected as the training set, and 20% of the data is used as the validation set.

[0108] Step 2: Training of the risk prediction model for the impact of interlaced spacer rods and shed skirt size on the risk of dancing disasters based on artificial neural networks

[0109] Taking the meteorological data, conductor parameters (including the size of the interlaced spacer shed) and topography in the training set as input data, and the dancing feature data as output data, a convolutional neural network (CNN) is selected, and the number of reasonable input features (which should match the number of selected features), the number of hidden layers and the number of neurons in each layer are designed. Figure 3 As shown in the figure, the model structure of the convolutional neural network includes: input layer, convolution layer, hidden layer and output layer.

[0110] (1) The input layer includes:

[0111] Meteorological data: including wind speed, wind direction, temperature, humidity, etc. These data can be input as one-dimensional feature vectors;

[0112] Conductor parameters: conductor diameter, material properties, interphase spacer shed size, etc., are also input as one-dimensional feature vectors;

[0113] Topography: Altitude, terrain undulations, vegetation distribution, etc., can be encoded as numerical features or embedded (such as using one-hot encoding).

[0114] (2) Figure 4 As shown, the convolutional layer includes:

[0115] 1) Convolutional layer: A one-dimensional convolutional layer is used to try to capture local features. This layer will use an appropriate number of convolution kernels (32 kernels can be set according to the analysis requirements of the dancing input parameters), and the size of each convolution kernel can be adjusted according to the dimension of the input data (length is 5). The stride of the convolution kernel is 1, and the padding is also set to 1.

[0116] 2) Activation function: The convolution layer is usually followed by an activation function, such as ReLU (Rectified Linear Unit), to increase the nonlinearity of the model.

[0117] 3) Pooling layer: In order to reduce the data dimension and reduce the amount of calculation, a pooling layer (maximum pooling, Max Pooling) can be added after the convolution layer.

[0118] (3) The hidden layer includes:

[0119] 1) Fully connected layer 1: After the convolutional layer, the data will be flattened and input into the first fully connected layer. This layer will contain 3 neurons and use the ReLU function as the activation function to fully demonstrate the nonlinear characteristics of this layer. The formula of the ReLU function is:

[0120]

[0121] In the above formula, x is the normalized matrix eigenvalue of the input layer data matrix.

[0122] 2) Fully connected layer 2: The output of fully connected layer 1 will be used as the input of the second fully connected layer, which also contains 3 neurons and an activation function (using the derivative of the ReLU function). The formula for the derivative of the ReLU function is:

[0123]

[0124] In the above formula, x is the normalized matrix eigenvalue of the input layer data matrix.

[0125] (4) The output layer includes:

[0126] The convolutional neural network will output two values, the amplitude and duration of the power line vibration. Therefore, the output layer will contain two neurons, and a linear activation function can be used to produce continuous prediction values.

[0127] (5) Training and optimization of convolutional neural networks

[0128] Loss function: For continuous output, the mean squared error is usually used as the loss function.

[0129]

[0130] In the above formula, x is the normalized matrix eigenvalue of the input layer data matrix, y i and f xi are the true value and the corresponding predicted value of the i-th sample respectively (here the relationship between the size of the interlaced spacer rod shed and the dancing amplitude and duration can be highlighted), and n is the overall sample size.

[0131] Optimizer: Select the Adam optimizer to update the network weights.

[0132] Batch processing and iteration: The data will be divided into small batches for training, and the size of each batch can be set to 16×16. Using convolutional neural networks to process a set of one-dimensional feature vectors is a relatively unique structural design form. After training, a validation set is needed to adjust the hyperparameters and evaluate the final performance of the model on the test set.

[0133] Step 3: Consider ground meteorological receiving devices, analysis of meteorological satellite data and control gateway

[0134] like Figure 5 As shown, based on the dancing disaster risk prediction model trained in step 2, the logic control code is written and made into an integrated circuit, which is packaged into a gateway form. The current weather conditions are determined by using ground meteorological receiving devices and meteorological satellite data (including but not limited to wind speed and direction, temperature and humidity, irradiance, etc.).

[0135] Under certain meteorological conditions, the gateway is powered on and turned on to enter the analysis working mode.

[0136] After startup, the gateway begins to analyze, evaluate and determine the risk of conductor galloping in real time based on the current meteorological data, and sends control instructions to the adjustable phase spacer to adjust the shed size in real time. The shed size can directly affect the force exerted by the wind field on it. When the adjustable phase spacer receives the control instruction sent by the gateway, it means that the on-site environment has the risk of galloping. The shed size can be increased or decreased by adjusting the opening and closing degree of the shed, thereby destroying the aerodynamic conditions induced by the galloping and achieving the purpose of actively preventing and controlling the galloping.

[0137] During adjustment, the structural design and action of the phase spacer, such as Figure 6 As shown in the figure, the adjustment of the shed size is mainly achieved by controlling the volume of hydraulic oil at the top of the casing through the pump control module installed at the top of the interphase spacer, so that the central axis and the casing move relative to each other, and indirectly drive the movable joints connecting the casing and the shed to adjust the opening and closing degree of the shed. Since the shed can be made of composite materials (such as industrial rubber, etc.), it has good elasticity, thereby increasing or reducing the overall windward area of ​​the interphase spacer. Finally, the anti-dancing effect is achieved with the optimal shed size.

[0138] The above example provided by the present invention carries out artificial neural network learning and modeling for the historical dancing case data set of the transmission line, and clarifies what kind of meteorological conditions will cause dancing, as well as the method and rules for adjusting the size of the phase spacer shed. The model results are then deployed to the analysis and control gateway together with the control instructions. By using real-time environmental condition data perception devices such as remote sensing satellites and ground monitoring devices, external meteorological data is perceived in real time. If the current environmental conditions are judged to have a dancing risk through the artificial intelligence neural network, a control instruction can be issued through the network to appropriately adjust the opening and closing size of the phase spacer shed, so that its aerodynamic shape and the bending stiffness of the rod body are more conducive to anti-dancing work in the current environment.

[0139] Embodiment 2

[0140] An active anti-dance device for phase-to-phase spacer bars, such as Figure 7 As shown, including:

[0141] A collection unit, used to collect relevant information of the transmission line and meteorological data at the forecast time;

[0142] A prediction unit, for predicting the dancing characteristic data of the transmission line at the prediction time based on the relevant information of the transmission line and the meteorological data at the prediction time, using a pre-established dancing disaster risk prediction model;

[0143] The adjusting unit is used to adjust the opening and closing size of the shed of the phase spacer within the predicted time according to the dancing characteristic data of the power transmission line within the predicted time.

[0144] Further, relevant information of the transmission line includes: conductor parameters and topography;

[0145] Conductor parameters include: conductor diameter, number of splits and outer diameter of phase spacer sheds;

[0146] Topography includes: altitude, terrain undulation and vegetation distribution.

[0147] Further, meteorological data, including: wind speed, wind direction, temperature, humidity and snowfall;

[0148] The dancing characteristic data include: dancing amplitude and duration.

[0149] Furthermore, the device also includes: an establishment unit for establishing a dancing disaster risk prediction model;

[0150] Establishment unit, including:

[0151] A collection module, used to collect historical meteorological data, historical transmission line related information and historical transmission line dancing characteristic data;

[0152] A data processing module is used to process historical meteorological data, historical transmission line related information and historical transmission line dancing characteristic data to obtain a historical dancing disaster data set;

[0153] A partitioning module is used to divide the historical dancing disaster dataset into a training set and a validation set;

[0154] A training module, used to train the convolutional neural network using the training set to obtain a trained convolutional neural network;

[0155] The verification module is used to verify the trained convolutional neural network using the verification set. If the verification is successful, the trained convolutional neural network is a dancing disaster risk prediction model; if the verification fails, the hyperparameters of the convolutional neural network are adjusted and the convolutional neural network is retrained.

[0156] Furthermore, the data processing module is specifically used for:

[0157] Performing data cleaning on historical meteorological data, historical information related to power transmission lines, and historical power transmission line galloping characteristic data to remove abnormal values ​​and erroneous data in the historical meteorological data, historical information related to power transmission lines, and historical power transmission line galloping characteristic data to obtain data processed;

[0158] The processed data are standardized to obtain the historical dancing disaster dataset.

[0159] Furthermore, the training module is specifically used to:

[0160] The historical meteorological data and the related information of the historical power transmission lines in the training set are used as the input layer training samples of the convolutional neural network, and the dancing feature data of the historical power transmission lines in the training set are used as the output layer training samples of the convolutional neural network. The convolutional neural network is trained to obtain the trained convolutional neural network.

[0161] Furthermore, the verification module is specifically used to:

[0162] The historical meteorological data and the related information of the historical power transmission lines in the verification set are used as the input of the trained convolutional neural network, and the predicted power transmission line dancing feature data is output;

[0163] The prediction accuracy is determined based on the predicted transmission line dancing feature data and the historical transmission line dancing feature data in the verification set. If the prediction accuracy is greater than or equal to the prediction threshold, the verification is successful; if the prediction accuracy is less than the prediction threshold, the verification fails.

[0164] Furthermore, the prediction unit is specifically used for:

[0165] Set the iteration range of the outer diameter of the phase spacer shed in the conductor parameters;

[0166] Based on the iteration range of the outer diameter of the shed of the phase spacer in the conductor parameters, the conductor parameters, topography and meteorological data at the prediction time are used as the input of the galloping disaster risk prediction model, and the galloping characteristic data of the transmission line at the prediction time corresponding to the outer diameter of the shed of each phase spacer in the iteration range is iteratively output;

[0167] Among them, the outer diameters of the sheds of each phase spacer rod in the iteration range are traversed in ascending order using the dancing disaster risk prediction model.

[0168] Furthermore, the adjustment unit is specifically used for:

[0169] The outer diameter of the phase spacer shed in the iteration range corresponding to the dancing characteristic data of the power transmission line at the predicted time that meets the screening condition is selected as the opening and closing adjustment size of the shed of the phase spacer; wherein the screening condition is: the dancing amplitude is greater than or equal to the dancing amplitude threshold and the dancing time is less than or equal to the dancing time threshold;

[0170] According to the opening and closing adjustment size of the shed of the phase spacer, the opening and closing size of the shed of the phase spacer within the predicted time is adjusted.

[0171] It can be understood that the device embodiment provided above corresponds to the method embodiment described above, and the corresponding specific contents can be referenced to each other and will not be repeated here.

[0172] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0173] Embodiment 3

[0174] Based on the same inventive concept, the present invention also provides a computer device, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function, so as to implement the steps of the active anti-dance method of the interphase spacer in the above embodiment.

[0175] Embodiment 4

[0176] Based on the same inventive concept, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It can be understood that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the steps of an active anti-dance method for interphase spacer bars in the above embodiment.

[0177] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0178] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0179] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0180] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0181] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. An active anti-dance method for interphase spacer bars, characterized in that: include: Collect relevant information of transmission lines and meteorological data at the forecast time; Based on the relevant information of the power transmission line and the meteorological data at the predicted time, using a pre-established power transmission line sway disaster risk prediction model, the power transmission line sway characteristic data at the predicted time is predicted; According to the dancing characteristic data of the power transmission line at the predicted time, the opening and closing size of the shed of the phase spacer at the predicted time is adjusted.

2. The method according to claim 1, characterized in that The relevant information of the transmission line includes: conductor parameters and topography; The conductor parameters include: conductor diameter, number of splits and outer diameter of interphase spacer sheds; The topography includes: altitude, terrain undulation and vegetation distribution.

3. The method according to claim 1, characterized in that The meteorological data include: wind speed, wind direction, temperature, humidity and snowfall; The dancing characteristic data include: dancing amplitude and duration.

4. The method according to claim 1, characterized in that: The process of establishing the dancing disaster risk prediction model includes: Collect historical meteorological data, historical transmission line related information and historical transmission line dancing characteristic data; Processing the historical meteorological data, the historical information related to the power transmission lines, and the historical power transmission line dancing characteristic data to obtain a historical power transmission line dancing disaster data set; Dividing the historical dancing disaster dataset into a training set and a validation set; Using the training set to train the convolutional neural network to obtain a trained convolutional neural network; The trained convolutional neural network is verified using the verification set. If the verification is successful, the trained convolutional neural network is the dancing disaster risk prediction model. If the verification fails, the hyperparameters of the convolutional neural network are adjusted and the convolutional neural network is retrained.

5. The method according to claim 4, characterized in that The data processing of the historical meteorological data, the historical transmission line related information and the historical transmission line dancing characteristic data includes: Performing data cleaning on the historical meteorological data, the historical information related to the power transmission line, and the historical power transmission line galloping characteristic data to remove abnormal values ​​and erroneous data in the historical meteorological data, the historical information related to the power transmission line, and the historical power transmission line galloping characteristic data to obtain data after data processing; The processed data is standardized to obtain the historical dancing disaster data set.

6. The method according to claim 4, characterized in that The step of training the convolutional neural network using the training set to obtain a trained convolutional neural network includes: The historical meteorological data and the related information of the historical power transmission lines in the training set are used as the input layer training samples of the convolutional neural network, and the dancing feature data of the historical power transmission lines in the training set are used as the output layer training samples of the convolutional neural network. The convolutional neural network is trained to obtain the trained convolutional neural network.

7. The method according to claim 4, characterized in that The using the verification set to verify the trained convolutional neural network includes: Using the historical meteorological data and the historical transmission line related information in the verification set as inputs to the trained convolutional neural network, and outputting predicted transmission line dancing feature data; The prediction accuracy is determined based on the predicted power transmission line dancing feature data and the historical power transmission line dancing feature data in the verification set. If the prediction accuracy is greater than or equal to the prediction threshold, the verification is successful; if the prediction accuracy is less than the prediction threshold, the verification fails, the hyperparameters of the convolutional neural network are adjusted, and the convolutional neural network with the adjusted hyperparameters is retrained until the verification is successful.

8. The method according to claim 2, characterized in that: The method of predicting the power transmission line's dancing characteristic data at the prediction time based on the relevant information of the power transmission line and the meteorological data at the prediction time by using a pre-established dancing disaster risk prediction model includes: Setting the iteration range of the outer diameter of the phase spacer shed in the conductor parameters; Based on the iteration range of the outer diameter of the phase-to-phase spacer shed in the conductor parameters, the conductor parameters, the topography and the meteorological data at the prediction time are used as inputs of the dancing disaster risk prediction model, and the dancing characteristic data of the transmission line at the prediction time corresponding to the outer diameter of each phase-to-phase spacer shed in the iteration range is iteratively output; The outer diameters of the sheds of each phase spacer rod in the iteration range are traversed in ascending order using the dancing disaster risk prediction model.

9. The method according to claim 8, characterized in that The step of adjusting the opening and closing size of the shed of the phase spacer within the predicted time according to the dancing characteristic data of the power transmission line within the predicted time comprises: The outer diameter of the phase spacer shed in the iteration range corresponding to the dancing characteristic data of the power transmission line at the predicted time that meets the screening condition is selected as the opening and closing adjustment size of the shed of the phase spacer; wherein the screening condition is: the dancing amplitude is greater than or equal to the dancing amplitude threshold and the dancing time is less than or equal to the dancing time threshold; According to the opening and closing adjustment size of the shed of the interphase spacer bar, the opening and closing size of the shed of the interphase spacer bar within the predicted time is adjusted.

10. An active anti-dance device for phase spacing bars, characterized in that: include: A collection unit, used to collect relevant information of the transmission line and meteorological data at the forecast time; A prediction unit, configured to predict and obtain the dancing characteristic data of the power transmission line at the prediction time based on the relevant information of the power transmission line and the meteorological data at the prediction time and using a pre-established dancing disaster risk prediction model; The adjusting unit is used to adjust the opening and closing size of the shed of the phase spacer within the predicted time according to the dancing characteristic data of the power transmission line within the predicted time.

11. A computer device, characterized in that: include: one or more processors; The processor is used to store one or more programs; When the one or more programs are executed by the one or more processors, the active anti-dancing method for interphase spacer bars according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed, the active anti-dance method for interphase spacer bars as claimed in any one of claims 1 to 9 is implemented.

Images