A spacer rod deicing intelligent control method and spacer rod control device

Abstract

The present invention relates to the field of cable technology, and specifically to an intelligent control method for spacer rod deicing and a spacer rod control device. By sensing and collecting an icing parameter array and an energy storage parameter array, icing prediction is performed based on the icing parameter array to obtain an icing amount array; a first vibration control parameter array of a vibration control unit array randomly configured and arranged in the spacer rod array is combined with the icing amount array to perform deicing rate prediction and equipment damage prediction to obtain a first deicing rate array and a first damage rate array, based on which an energy storage utilization rate analysis is performed to obtain a first energy storage utilization rate array; based on the above parameters, a first deicing score of the first vibration control parameter array is calculated and obtained, vibration control parameter optimization is performed to obtain an optimal deicing control parameter array, and the vibration control unit array is controlled to perform deicing control. The present invention achieves the technical effect of improving the deicing vibration control effect and reducing energy consumption.

Description

Technical Field

[0001] The present invention relates to the field of cable technology, and in particular to a spacer bar deicing intelligent control method and a spacer bar control device. Background Art

[0002] Icing on transmission lines is a major hidden danger that threatens the safe operation of the power grid. When the thickness of ice covering the conductors exceeds the design critical value, it may cause accidents such as line breakage and tower collapse. Traditional mechanical de-icing technology requires professionals to climb ice-covered towers, and the manual knocking method is inefficient and highly dangerous, with significant defects. Although mechanical vibration de-icing devices can remove ice below 30mm, the fixed parameters will lead to energy waste and equipment damage risks - when the vibration amplitude is too low, it cannot effectively break the ice, and when it is too high, it will accelerate the metal fatigue of the conductors and even cause the spacer rod structure to break. The existing mechanical vibration de-icing has technical problems such as poor de-icing vibration control effect and high energy consumption. Summary of the Invention

[0003] The present invention aims to solve the technical problems of poor deicing vibration control effect and high energy consumption in the prior art of vibration deicing, and provides a spacer rod deicing intelligent control method and a spacer rod control device to solve the problems.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] In a first aspect, the present invention provides an intelligent control method for spacer deicing, comprising: sensing and collecting an icing parameter array and an energy storage parameter array using a sensor array and a solar energy supply unit array within a spacer array disposed on a target line, performing icing prediction based on the icing parameter array to obtain an icing amount array; randomly configuring a first vibration control parameter array of a vibration control unit array disposed within the spacer array, and performing deicing rate prediction and equipment damage prediction in combination with the icing amount array to obtain a first deicing rate array and a first damage rate array; performing energy storage utilization analysis based on the first vibration control parameter array, the first deicing rate array, and the energy storage parameter array to obtain a first energy storage utilization rate array;

[0006] Based on the first deicing rate array, the first damage rate array, and the first energy storage utilization rate array, a first deicing score of the first vibration control parameter array is calculated and obtained, vibration control parameter optimization is performed to obtain an optimal deicing control parameter array, and the vibration control unit array is controlled to perform deicing control.

[0007] Optionally, the sensor array and the solar energy supply unit array arranged in the spacer array on the target line are used to sense and collect the icing parameter array and the energy storage parameter array, including:

[0008] By using a sensor array within a spacer array disposed on a target line, icing parameters at the spacer positions are sensed and collected to obtain an icing parameter array, wherein the spacer array includes a plurality of spacers disposed at a plurality of positions on the target line;

[0009] An array of energy storage parameters is sensed and collected through the solar energy supply unit array within the spacer rod array, wherein the energy storage parameters include the energy storage power within a recent preset time range.

[0010] Optionally, performing icing prediction according to the icing parameter array to obtain an icing amount array includes:

[0011] Based on the line icing monitoring data, collect the sample icing parameter set, and collect the average icing thickness when different sample icing parameters appear, and mark the obtained sample icing amount set;

[0012] Build an ice accumulation prediction network based on machine learning;

[0013] Iteratively tuning and training the icing amount prediction network using the sample icing parameter set and the sample icing amount set, and completing the training after test convergence;

[0014] The plurality of icing parameters in the icing parameter array are input into the icing amount prediction network, and the prediction output is used to obtain a plurality of icing amounts, thereby obtaining an icing amount array.

[0015] Optionally, randomly configuring a first vibration control parameter array of a vibration control unit array arranged in the spacer array, combining the ice amount array, performing deicing rate prediction and equipment damage prediction, and obtaining a first deicing rate array and a first damage rate array, includes:

[0016] Obtaining vibration control parameter intervals of the vibration control unit array within the spacer rod array, randomly generating first vibration control parameters respectively, and obtaining a first vibration control parameter array, wherein each vibration control unit includes a vibration motor and a control unit;

[0017] The first vibration control parameter array and the icing amount array are input into the constructed deicing prediction path, and the prediction output obtains a first deicing rate array and a first damage rate array, wherein the deicing prediction path includes a deicing rate prediction network and an equipment damage prediction network.

[0018] The step of constructing the deicing prediction path includes:

[0019] Using machine learning, a deicing rate prediction network and an equipment damage prediction network were constructed based on vibration control parameters and ice accumulation as input data, and deicing rate and equipment damage rate as output data, respectively.

[0020] Based on the deicing data of transmission line spacers, a set of sample vibration control parameters and a set of sample icing amounts are collected. The deicing ratios after deicing according to different sample vibration control parameters and sample icing amounts, as well as the damage ratios of the lines and spacers, are collected. The sample deicing rate sets and the sample equipment damage rate sets are annotated.

[0021] Using the sample vibration control parameter set and the sample icing amount set as input training data, and using the sample deicing rate set and the sample equipment damage rate set as output supervision data, respectively, to perform supervised training on the deicing rate prediction network and the equipment damage prediction network;

[0022] After the training and testing converge, the deicing rate prediction network and the equipment damage prediction network are combined to obtain a deicing prediction path.

[0023] Optionally, performing energy storage utilization analysis based on the first vibration control parameter array, the first deicing rate array, and the energy storage parameter array to obtain a first energy storage utilization array includes:

[0024] Acquire the energy consumption power of the first vibration control parameter array to obtain a first energy consumption parameter array;

[0025] respectively calculating ratios of the energy storage parameter array and the first energy consumption parameter array to obtain a first basic utilization rate array;

[0026] The first energy storage utilization rate array is calculated by multiplying the first deicing rate array by the first basic utilization rate array.

[0027] Optionally, calculating and obtaining a first deicing score of the first vibration control parameter array based on the first deicing rate array, the first damage rate array, and the first energy storage utilization rate array, performing vibration control parameter optimization to obtain an optimal deicing control parameter array, and controlling the vibration control unit array to perform deicing control includes:

[0028] Calculating a first equipment availability array based on the first damage rate array;

[0029] A first spacer deicing score array of the first vibration control parameter array is obtained by weighted calculation based on the first deicing rate array, the first equipment integrity rate array, and the first energy storage utilization rate array;

[0030] The vibration control parameter array is continuously randomly configured to optimize the vibration control parameters. After the optimization converges, the deicing control parameter array with the largest spacer deicing score is retained to control the vibration control unit array to perform deicing control.

[0031] In a second aspect, the present invention provides a spacer rod control device, comprising:

[0032] An icing parameter prediction module is configured to sense and collect an icing parameter array and an energy storage parameter array through a sensor array and a solar energy supply unit array arranged in a spacer array on a target line, perform icing prediction based on the icing parameter array, and obtain an icing amount array;

[0033] a deicing parameter prediction module, configured to randomly configure a first vibration control parameter array of a vibration control unit array arranged within the spacer array, and perform deicing rate prediction and equipment damage prediction in combination with the ice accumulation array to obtain a first deicing rate array and a first damage rate array;

[0034] an energy storage utilization analysis module, configured to perform energy storage utilization analysis based on the first vibration control parameter array, the first deicing rate array, and the energy storage parameter array to obtain a first energy storage utilization array;

[0035] A control parameter optimization module is used to calculate and obtain a first deicing score for the first vibration control parameter array based on the first deicing rate array, the first damage rate array, and the first energy storage utilization rate array, perform vibration control parameter optimization, obtain an optimal deicing control parameter array, and control the vibration control unit array to perform deicing control.

[0036] In the embodiment of the present invention, a sensor array and a solar energy supply unit array arranged in a spacer array on a target line sense and collect an icing parameter array and an energy storage parameter array. Icing is predicted based on the icing parameter array to obtain an icing amount array, thereby achieving dynamic prediction of ice thickness and providing an accurate judgment basis for de-icing vibration control.

[0037] In an embodiment of the present invention, a first vibration control parameter array of a vibration control unit array randomly configured within the spacer array is combined with the ice accumulation array to perform deicing rate prediction and equipment damage prediction, thereby obtaining a first deicing rate array and a first damage rate array. A damage quantification index is introduced to achieve coordinated optimization of deicing efficiency and equipment safety.

[0038] In an embodiment of the present invention, an energy storage utilization analysis is performed based on the first vibration control parameter array, the first deicing rate array, and the energy storage parameter array to obtain a first energy storage utilization array, which provides a basis for energy consumption optimization, thereby reducing deicing power consumption and increasing effective deicing working time.

[0039] In an embodiment of the present invention, a first deicing score of the first vibration control parameter array is calculated based on the first deicing rate array, the first damage rate array, and the first energy storage utilization rate array, vibration control parameter optimization is performed to obtain an optimal deicing control parameter array, and the vibration control unit array is controlled to perform deicing control. By comprehensively considering the influence of multiple parameters, a global optimal solution for the vibration control parameters is obtained.

[0040] In summary, by implementing the present invention, the technical effects of improving the deicing vibration control effect and reducing energy consumption can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A schematic flow chart of an intelligent control method for spacer deicing provided by the present invention;

[0042] Figure 2 This is a structural schematic diagram of a spacer rod control device provided by the present invention.

[0043] In the accompanying drawings, the components represented by the reference numerals are as follows:

[0044] Icing parameter prediction module 11, deicing parameter prediction module 12, energy storage utilization analysis module 13, control parameter optimization module 14. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0046] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0047] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0048] Example 1, as Figure 1As shown, an embodiment of the present invention provides an intelligent control method for spacer deicing, including:

[0049] S100: Using a sensor array and a solar energy supply unit array arranged in a spacer array on a target line, sensing and collecting an icing parameter array and an energy storage parameter array, performing icing prediction based on the icing parameter array, and obtaining an icing amount array;

[0050] S200: randomly configuring a first vibration control parameter array of a vibration control unit array arranged within the spacer array, and performing deicing rate prediction and equipment damage prediction in combination with the ice accumulation array to obtain a first deicing rate array and a first damage rate array;

[0051] S300: performing energy storage utilization analysis based on the first vibration control parameter array, the first deicing rate array, and the energy storage parameter array to obtain a first energy storage utilization array;

[0052] S400: Based on the first deicing rate array, the first damage rate array, and the first energy storage utilization rate array, calculate and obtain a first deicing score for the first vibration control parameter array, optimize the vibration control parameters, obtain an optimal deicing control parameter array, and control the vibration control unit array to perform deicing control.

[0053] In step S100 of this embodiment, the sensor array and the solar energy supply unit array arranged in the spacer array on the target line sense and collect the icing parameter array and the energy storage parameter array, including:

[0054] By using a sensor array within a spacer array disposed on a target line, icing parameters at the spacer positions are sensed and collected to obtain an icing parameter array, wherein the spacer array includes a plurality of spacers disposed at a plurality of positions on the target line;

[0055] An array of energy storage parameters is sensed and collected through the solar energy supply unit array within the spacer rod array, wherein the energy storage parameters include the energy storage power within a recent preset time range.

[0056] In this embodiment, sensing and collecting an icing parameter array and an energy storage parameter array is used to provide basic data support for adjusting the vibration de-icing strategy based on the displayed icing status of the target line and the energy storage status of the energy storage unit. The target line is a section of transmission line (e.g., 1 km) requiring de-icing. Spacers are devices installed on split conductors to stabilize the spacing between each split conductor to prevent whiplash and suppress breeze vibration and oscillation. Multiple spacers (e.g., 50) on the target line constitute the spacer array. Icing parameters are environmental parameters that may affect the amount of icing on the wires, including temperature, humidity, and wind speed. These icing parameters can be monitored in real time by deploying temperature, humidity, and wind speed sensors to obtain icing parameters (e.g., temperature -10°C, humidity 80%, wind speed 12 m / s). These sensors are deployed at the spacers of the target line. Icing parameters at the spacers of multiple target lines are collected to obtain the icing parameter array.

[0057] In an embodiment of the present application, a solar energy array is used to power a deicing device comprising a plurality of spacers (e.g., 50) within a target line (e.g., 1 km). The solar energy array is composed of multiple solar panels and multiple energy storage batteries. The energy storage power (generation rate) of the solar panels within a recent preset time range (e.g., 20 minutes) is the aforementioned energy storage parameter, which can be acquired using a power sensor (e.g., 5W, 10W, etc.). The energy storage parameters of the multiple solar energy supply units in the solar energy supply unit array are acquired to obtain an energy storage parameter array.

[0058] In step S100 of this embodiment, icing prediction is performed based on the icing parameter array to obtain an icing amount array, including:

[0059] Based on the line icing monitoring data, collect the sample icing parameter set, and collect the average icing thickness when different sample icing parameters appear, and mark the obtained sample icing amount set;

[0060] Build an ice accumulation prediction network based on machine learning;

[0061] Iteratively tuning and training the icing amount prediction network using the sample icing parameter set and the sample icing amount set, and completing the training after test convergence;

[0062] The plurality of icing parameters in the icing parameter array are input into the icing amount prediction network, and the prediction output is used to obtain a plurality of icing amounts, thereby obtaining an icing amount array.

[0063] In this embodiment of the present application, the sample icing parameters include the aforementioned parameters such as temperature, humidity, and wind speed. For example, a set of sample icing parameters may include a temperature of -10°C, a humidity of 80%, and a wind speed of 12 m / s. The sample icing volume is the average thickness of ice (e.g., 20 mm) actually formed on the target line under the aforementioned sample icing parameters.

[0064] The aforementioned average ice thickness can be measured and averaged using piezoelectric ice thickness sensors installed on the surface of the spacer rods and adjacent conductors. By labeling each sample icing parameter in the sample icing parameter set with the actual average ice thickness generated under that parameter, a sample icing volume set can be obtained. This sample icing volume set (collecting at least 1000 sets of sample ice volume) is divided into a training set, a validation set, and a test set in a 70%:15%:15% ratio for training, validation, and testing, to train the icing volume prediction network.

[0065] Optionally, in view of the performance requirements of the ice amount prediction network in this embodiment, a regression model based on a BP neural network can be used to build the ice amount prediction network.

[0066] In one embodiment, in terms of the structural parameters of the ice accumulation prediction network, the input layer has 3 nodes (temperature, humidity, wind speed); the hidden layer has 2 layers, each with 16 nodes (using the ReLU activation function); the output layer has 1 node (using a linear activation function to output the predicted ice thickness); L2 regularization (λ=0.01) is used, and the Dropout probability is 0.2; its structure from front to back is Input(3), Dense(16,ReLU), Dropout(0.2), Dense(16,ReLU), Dense(1).

[0067] Furthermore, in the training of the icing amount prediction network, the optimizer can use the Adam optimizer (learning rate = 0.001, β1 = 0.9, β2 = 0.999); the loss function selects the mean absolute error (MAE); the batch size is 64; the number of training rounds is 200 (an early stopping mechanism is introduced, and the training is terminated if the validation set loss does not decrease for 10 consecutive rounds); the convergence criterion can be set to validation set MAE ≤ 0.5 mm. When the convergence criterion is reached, convergence is judged to obtain the icing amount prediction network.

[0068] Finally, by inputting icing parameters (e.g., temperature -10°C, humidity 80%, wind speed 12 m / s) into the icing amount prediction network, the icing amount (e.g., 20 mm) corresponding to these parameters can be predicted. By inputting multiple icing parameters within the icing parameter array into the icing amount prediction network, multiple icing amounts can be predicted and output, resulting in an icing amount array.

[0069] In step S200 of the embodiment of the present application, the first vibration control parameter array of the vibration control unit array randomly configured in the spacer array is combined with the ice amount array to perform deicing rate prediction and equipment damage prediction to obtain a first deicing rate array and a first damage rate array, including:

[0070] Obtaining vibration control parameter intervals of the vibration control unit array within the spacer rod array, randomly generating first vibration control parameters respectively, and obtaining a first vibration control parameter array, wherein each vibration control unit includes a vibration motor and a control unit;

[0071] The first vibration control parameter array and the icing amount array are input into the constructed deicing prediction path, and the prediction output obtains a first deicing rate array and a first damage rate array, wherein the deicing prediction path includes a deicing rate prediction network and an equipment damage prediction network.

[0072] In the embodiment of the present application, de-icing rate prediction and equipment damage prediction are performed in order to evaluate the rationality of vibration control parameters based on the prediction results so as to optimize the vibration control parameters.

[0073] To implement the above steps, it is first necessary to obtain the vibration control parameter range of the vibration control unit array within the spacer array. The vibration control unit is the de-icing equipment described in the embodiments of this application. In actual implementation, multiple vibration control units are deployed at the spacers of the transmission line to form a vibration control unit array. The vibration control unit includes two parts: a vibration motor and a control unit. The vibration motor is used to apply a certain frequency of vibration to the target line, causing the ice layer to crack and break away from the transmission line. The control unit is used to control the start and stop of the vibration motor and the vibration parameters.

[0074] The vibration control parameters of the vibration control unit array typically include vibration frequency and vibration time. The vibration control parameter interval is an optional interval of the vibration motor's vibration control parameters. For example, if a vibration motor supports a maximum vibration frequency of 80 Hz and a minimum vibration frequency of 20 Hz, the vibration control parameter interval is [20 Hz, 80 Hz]. For another example, if a vibration time of more than 20 seconds can normally remove most ice, the vibration time parameter interval can be set to [0 s, 20 s]. Randomly generate vibration control parameters within this vibration control parameter interval, which is the first vibration control parameter (e.g., 35 Hz, 10 seconds). The same method is used to generate multiple vibration control parameters for the vibration control units within the vibration control unit array, thus obtaining the first vibration control parameter array.

[0075] The step of constructing the deicing prediction path includes:

[0076] Using machine learning, a deicing rate prediction network and an equipment damage prediction network were constructed based on vibration control parameters and ice accumulation as input data, and deicing rate and equipment damage rate as output data, respectively.

[0077] Based on the deicing data of transmission line spacers, a set of sample vibration control parameters and a set of sample icing amounts are collected. The deicing ratios after deicing according to different sample vibration control parameters and sample icing amounts, as well as the damage ratios of the lines and spacers, are collected. The sample deicing rate sets and the sample equipment damage rate sets are annotated.

[0078] Using the sample vibration control parameter set and the sample icing amount set as input training data, and using the sample deicing rate set and the sample equipment damage rate set as output supervision data, respectively, to perform supervised training on the deicing rate prediction network and the equipment damage prediction network;

[0079] After the training and testing converge, the deicing rate prediction network and the equipment damage prediction network are combined to obtain a deicing prediction path.

[0080] In an embodiment of the present application, in order to obtain the aforementioned first deicing rate array and first damage rate array through deicing prediction path prediction, it is first necessary to train the deicing rate prediction network and equipment damage prediction network contained in the deicing prediction path respectively.

[0081] First, the input features of the deicing rate prediction network include sample vibration control parameters (e.g., 35 Hz, 10 s) and sample ice amount (e.g., 20 mm), and the output features are the deicing ratio after deicing under the sample vibration control parameters and sample ice amount.

[0082] The de-icing ratio can be calculated as (ice thickness after de-icing / ice thickness before de-icing) * 100%. For example, if the ice thickness before de-icing is 20 mm and the ice thickness after de-icing is 15 mm, the de-icing ratio = (15 / 20) * 100% = 75%.

[0083] Therefore, when training the de-icing rate prediction network, it is necessary to collect the actual de-icing ratios of de-icing under the sample vibration control parameters and the sample icing amount, mark the actual de-icing ratios of de-icing under multiple sample vibration control parameters and the sample icing amount, and obtain the sample de-icing rate set.

[0084] Secondly, the input features of the equipment damage prediction network include sample vibration control parameters (such as 35Hz, 10s) and sample ice amount (such as 20mm), and the output features are the equipment damage rate after deicing under the sample vibration control parameters and sample ice amount.

[0085] The equipment damage rate can be calculated by observing the propagation length of microcracks on the surface of the transmission line material after vibration using a scanning electron microscope (SEM), quantifying the damage by the number of cracks per unit area or the average length. For example, the transmission line can be vibrated using randomly selected parameters within a vibration control parameter range. The average propagation length of microcracks on the surface of the transmission line material after each vibration is recorded (e.g., 20 microns) to measure the extent of equipment damage. Multiple equipment damage level values ​​are obtained, and the maximum value (e.g., 50 microns) is selected. The ratio of the equipment damage level measured after each vibration (e.g., 40 microns) to this maximum value is used as the equipment damage rate. In this example, the equipment damage rate = 40 microns / 50 microns = 0.8 = 80%.

[0086] In the construction of the de-icing rate prediction network and the equipment damage prediction network, taking the de-icing rate prediction network as an example, the core architecture can adopt multi-layer perceptron (MLP) + adaptive feature fusion.

[0087] The input layer consists of 3 neurons, corresponding to vibration frequency (Hz), vibration duration (s), and initial ice thickness (mm).

[0088] There are three hidden layers. The first layer has 64 neurons and the activation function is ReLU. Dropout (0.2) is introduced to prevent overfitting. The second layer has 32 neurons and the activation function is LeakyReLU (α=0.1) to enhance nonlinear expression capabilities. The third layer has 6 neurons and Batch Normalization is used to accelerate convergence.

[0089] The output layer consists of one neuron, and the activation function is Sigmoid (the output range is 0 to 1, corresponding to the de-icing ratio of 0% to 100%).

[0090] The optimizer used was AdamW (learning rate = 0.001, weight decay = 0.01), balancing convergence speed and generalization. The loss function used was Huber Loss (δ = 0.5) to reduce the impact of outliers on training. The batch size was 32 to 64, balancing training speed and gradient stability. L2 regularization (λ = 0.001) was used to prevent parameter overfitting.

[0091] To train the de-icing rate prediction network, the sample de-icing rate dataset (consisting of at least 1000 data sets) is divided into a training set, a validation set, and a test set with a 70%:15%:15% ratio. The initial number of training rounds is set to 200, with early stopping (terminating after 10 consecutive rounds of validation set loss without a decrease). A cosine annealing strategy (initial learning rate 0.001, minimum learning rate 0.0001) is used to avoid local optimality. The model convergence criterion can be set to a validation set mean absolute error (MAE) ≤ 5%. When this criterion is met, the model is considered converged, and the de-icing rate prediction network is obtained.

[0092] By using the same method, the equipment damage prediction network can be trained by simply replacing the training data from the sample deicing rate set with the sample equipment damage rate set, which will not be repeated here.

[0093] After training and testing of the deicing rate prediction network and the equipment damage prediction network reach convergence, the deicing rate prediction network and the equipment damage prediction network are combined (specifically, they can be combined in parallel) to obtain a deicing prediction path. The constructed deicing prediction path is inputted into the first vibration control parameter array and the ice accumulation array, resulting in the predicted outputs of the first deicing rate array and the first damage rate array.

[0094] In step S300 of the embodiment of the present application, energy storage utilization analysis is performed based on the first vibration control parameter array, the first deicing rate array, and the energy storage parameter array to obtain a first energy storage utilization array, including:

[0095] Acquire the energy consumption power of the first vibration control parameter array to obtain a first energy consumption parameter array;

[0096] respectively calculating ratios of the energy storage parameter array and the first energy consumption parameter array to obtain a first basic utilization rate array;

[0097] The first energy storage utilization rate array is calculated by multiplying the first deicing rate array by the first basic utilization rate array.

[0098] In this embodiment of the present application, the energy consumption power of the first vibration control parameter array is the actual power of the vibration motor when performing a de-icing operation using the first vibration control parameters. This power can be directly calculated by measuring the real-time voltage and current values ​​of the vibration motor. The actual power of the vibration motor corresponding to each set of vibration control parameters in the first vibration control parameter array (e.g., 20W, 30W, etc.) is calculated to obtain the first energy consumption parameter array.

[0099] Next, the ratios of the energy storage parameter array and the first energy consumption parameter array need to be calculated to obtain a first basic utilization rate array. For example, if a certain energy storage parameter is 50W and the first energy consumption parameter is 30W, the first basic utilization rate is 30W / 50W = 0.6 = 60%. Using the above method, all first basic utilization rates corresponding to the energy storage parameter array and the first energy consumption parameter array can be calculated to obtain a first basic utilization rate array.

[0100] Finally, multiply the first basic utilization rate (e.g., 60%) by the aforementioned first deicing rate (e.g., 80%) to obtain the first energy storage utilization rate (e.g., 60% * 80% = 48%). The first energy storage utilization rate array is obtained by multiplying the first deicing rate array by all first energy storage utilization rates corresponding to the first deicing rates and first basic utilization rates in the first basic utilization rate array.

[0101] In step S400 of the embodiment of the present application, a first deicing score of the first vibration control parameter array is calculated based on the first deicing rate array, the first damage rate array, and the first energy storage utilization rate array, vibration control parameter optimization is performed to obtain an optimal deicing control parameter array, and the vibration control unit array is controlled to perform deicing control, including:

[0102] Calculating a first equipment availability array based on the first damage rate array;

[0103] A first spacer deicing score array of the first vibration control parameter array is obtained by weighted calculation based on the first deicing rate array, the first equipment integrity rate array, and the first energy storage utilization rate array;

[0104] The vibration control parameter array is continuously randomly configured to optimize the vibration control parameters. After the optimization converges, the deicing control parameter array with the largest spacer deicing score is retained to control the vibration control unit array to perform deicing control.

[0105] In the embodiment of the present application, among the various evaluation parameters calculated above, since the first damage rate represents the degree of damage to the target line caused by the deicing operation under certain vibration parameters, it is necessary to convert the first damage rate into the first equipment integrity rate for ease of calculation. For example, the first damage rate can be subtracted from 1 to obtain the corresponding first equipment integrity rate. For example, if the first damage rate under certain vibration parameters is 60%, the corresponding first equipment integrity rate is 1-60%=40%. Using this method, the entire first damage rate array can be converted to obtain the first equipment integrity rate array.

[0106] Next, a comprehensive evaluation of these vibration control parameters is performed in conjunction with other performance indicators of the vibration control parameters in the vibration control parameter array corresponding to the first equipment availability array. Evaluation factors include the first deicing rate, first equipment availability, and first energy storage utilization rate of the vibration control parameters in the vibration control parameter array (the vibration control parameter array corresponding to the first equipment availability array).

[0107] The calculation method can be weighted summation. Different weights are assigned to the first deicing rate, the first equipment availability rate, and the first energy storage utilization rate according to actual operation, and the sum is calculated. For example, the weights can be set to 0.3 for the first deicing rate, 0.3 for the first equipment availability rate, and 0.4 for the first energy storage utilization rate.

[0108] If the first deicing rate, the first equipment availability rate, and the first energy storage utilization rate are 80%, 60%, and 60%, respectively, then the first spacer deicing score is 0.3*80%+0.3*60%+0.4*60%=0.66. Calculate multiple first spacer deicing scores to obtain a first spacer deicing score array.

[0109] Next, the vibration control parameter array is randomly configured to optimize the vibration control parameters. For example, when the first spacer de-icing score corresponding to each spacer is optimized more than 10 times or a de-icing score with a score value greater than 0.8 appears, the optimization is judged to have converged, and the de-icing control parameter with the largest de-icing score corresponding to the spacer is retained. The de-icing control parameters with the largest de-icing scores for multiple array spacers are obtained to obtain a de-icing control parameter array. The de-icing control parameters in the de-icing control parameter array are used to control the vibration control unit array in the target line to perform de-icing control.

[0110] Example 2, as Figure 2 As shown, based on the same inventive concept as the spacer rod deicing intelligent control method provided in the first embodiment, the embodiment of the present invention further provides a spacer rod control device, comprising:

[0111] An icing parameter prediction module 11 is configured to sense and collect an icing parameter array and an energy storage parameter array using a sensor array and a solar energy supply unit array within a spacer array arranged on a target line, perform icing prediction based on the icing parameter array, and obtain an icing amount array;

[0112] A deicing parameter prediction module 12 is configured to randomly configure a first vibration control parameter array of the vibration control unit array arranged within the spacer array, and perform deicing rate prediction and equipment damage prediction in combination with the ice accumulation array to obtain a first deicing rate array and a first damage rate array;

[0113] an energy storage utilization analysis module 13, configured to perform energy storage utilization analysis based on the first vibration control parameter array, the first deicing rate array, and the energy storage parameter array to obtain a first energy storage utilization array;

[0114] The control parameter optimization module 14 is used to calculate and obtain a first deicing score for the first vibration control parameter array based on the first deicing rate array, the first damage rate array, and the first energy storage utilization rate array, perform vibration control parameter optimization, obtain an optimal deicing control parameter array, and control the vibration control unit array to perform deicing control.

[0115] Furthermore, the icing parameter prediction module 11 is further configured to:

[0116] By using a sensor array within a spacer array disposed on a target line, icing parameters at the spacer positions are sensed and collected to obtain an icing parameter array, wherein the spacer array includes a plurality of spacers disposed at a plurality of positions on the target line;

[0117] An array of energy storage parameters is sensed and collected through the solar energy supply unit array within the spacer rod array, wherein the energy storage parameters include the energy storage power within a recent preset time range.

[0118] Based on the line icing monitoring data, collect the sample icing parameter set, and collect the average icing thickness when different sample icing parameters appear, and mark the obtained sample icing amount set;

[0119] Build an ice accumulation prediction network based on machine learning;

[0120] Iteratively tuning and training the icing amount prediction network using the sample icing parameter set and the sample icing amount set, and completing the training after test convergence;

[0121] The plurality of icing parameters in the icing parameter array are input into the icing amount prediction network, and the prediction output is used to obtain a plurality of icing amounts, thereby obtaining an icing amount array.

[0122] Furthermore, the deicing parameter prediction module 12 is further configured to:

[0123] Obtaining vibration control parameter intervals of the vibration control unit array within the spacer rod array, randomly generating first vibration control parameters respectively, and obtaining a first vibration control parameter array, wherein each vibration control unit includes a vibration motor and a control unit;

[0124] The first vibration control parameter array and the icing amount array are input into the constructed deicing prediction path, and the prediction output obtains a first deicing rate array and a first damage rate array, wherein the deicing prediction path includes a deicing rate prediction network and an equipment damage prediction network.

[0125] The step of constructing the deicing prediction path includes:

[0126] Using machine learning, a deicing rate prediction network and an equipment damage prediction network were constructed based on vibration control parameters and ice accumulation as input data, and deicing rate and equipment damage rate as output data, respectively.

[0127] Based on the deicing data of transmission line spacers, a set of sample vibration control parameters and a set of sample icing amounts are collected. The deicing ratios after deicing according to different sample vibration control parameters and sample icing amounts, as well as the damage ratios of the lines and spacers, are collected. The sample deicing rate sets and the sample equipment damage rate sets are annotated.

[0128] Using the sample vibration control parameter set and the sample icing amount set as input training data, and using the sample deicing rate set and the sample equipment damage rate set as output supervision data, respectively, to perform supervised training on the deicing rate prediction network and the equipment damage prediction network;

[0129] After the training and testing converge, the deicing rate prediction network and the equipment damage prediction network are combined to obtain a deicing prediction path.

[0130] Furthermore, the energy storage utilization analysis module 13 is also used to:

[0131] Acquire the energy consumption power of the first vibration control parameter array to obtain a first energy consumption parameter array;

[0132] respectively calculating ratios of the energy storage parameter array and the first energy consumption parameter array to obtain a first basic utilization rate array;

[0133] The first energy storage utilization rate array is calculated by multiplying the first deicing rate array by the first basic utilization rate array.

[0134] Furthermore, the control parameter optimization module 14 is also used to:

[0135] Calculating a first equipment availability array based on the first damage rate array;

[0136] A first spacer deicing score array of the first vibration control parameter array is obtained by weighted calculation based on the first deicing rate array, the first equipment integrity rate array, and the first energy storage utilization rate array;

[0137] The vibration control parameter array is continuously randomly configured to optimize the vibration control parameters. After the optimization converges, the deicing control parameter array with the largest spacer deicing score is retained to control the vibration control unit array to perform deicing control.

[0138] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0139] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, 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 magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0140] 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 flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, 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 computer, 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 flowcharts and / or block diagrams. 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.

[0141] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0142] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0143] Although preferred embodiments of the present invention have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts become known.

[0144] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A spacer rod deicing intelligent control method, characterized in that: The method comprises: The method includes: sensing and collecting an icing parameter array and an energy storage parameter array through a sensor array and a solar energy supply unit array arranged in a spacer array on a target line; performing icing prediction based on the icing parameter array to obtain an icing amount array; and Based on the line icing monitoring data, collect the sample icing parameter set, and collect the average icing thickness when different sample icing parameters appear, and mark the obtained sample icing amount set; Build an ice accumulation prediction network based on machine learning; Iteratively tuning and training the icing amount prediction network using the sample icing parameter set and the sample icing amount set, and completing the training after test convergence; Inputting a plurality of icing parameters in the icing parameter array into the icing amount prediction network, and outputting a plurality of icing amounts to obtain an icing amount array; Randomly configuring a first vibration control parameter array of a vibration control unit array arranged in the spacer array, combining the ice amount array, performing deicing rate prediction and equipment damage prediction, and obtaining a first deicing rate array and a first damage rate array, including: Obtaining vibration control parameter intervals of the vibration control unit array within the spacer rod array, randomly generating first vibration control parameters respectively, and obtaining a first vibration control parameter array, wherein each vibration control unit includes a vibration motor and a control unit; Inputting the first vibration control parameter array and the ice amount array into the constructed deicing prediction path, and predicting output to obtain a first deicing rate array and a first damage rate array, wherein the deicing prediction path includes a deicing rate prediction network and an equipment damage prediction network, and the first damage rate includes the degree of damage to the line; Performing an energy storage utilization analysis based on the first vibration control parameter array, the first deicing rate array, and the energy storage parameter array to obtain a first energy storage utilization rate array, wherein the first energy storage utilization rate is the product of a ratio of the energy storage parameter to the first energy consumption parameter corresponding to the first vibration control parameter and the first deicing rate; Based on the first deicing rate array, the first damage rate array, and the first energy storage utilization rate array, a first deicing score of the first vibration control parameter array is calculated and obtained, vibration control parameter optimization is performed to obtain an optimal deicing control parameter array, and the vibration control unit array is controlled to perform deicing control.

2. The intelligent control method for spacer deicing according to claim 1, characterized in that: Through the sensor array and solar energy supply unit array arranged in the spacer array on the target line, the icing parameter array and energy storage parameter array are sensed and collected, including: By using a sensor array within a spacer array disposed on a target line, icing parameters at the spacer positions are sensed and collected to obtain an icing parameter array, wherein the spacer array includes a plurality of spacers disposed at a plurality of positions on the target line; An array of energy storage parameters is sensed and collected through the solar energy supply unit array within the spacer rod array, wherein the energy storage parameters include the energy storage power within a recent preset time range.

3. The intelligent control method for spacer deicing according to claim 1, characterized in that: The steps of constructing the deicing prediction path include: Using machine learning, a deicing rate prediction network and an equipment damage prediction network were constructed based on vibration control parameters and ice accumulation as input data, and deicing rate and equipment damage rate as output data, respectively. Based on the deicing data of transmission line spacers, a set of sample vibration control parameters and a set of sample icing amounts are collected. The deicing ratios after deicing according to different sample vibration control parameters and sample icing amounts, as well as the damage ratios of the lines and spacers, are collected. The sample deicing rate sets and the sample equipment damage rate sets are annotated. Using the sample vibration control parameter set and the sample icing amount set as input training data, and using the sample deicing rate set and the sample equipment damage rate set as output supervision data, respectively, to perform supervised training on the deicing rate prediction network and the equipment damage prediction network; After the training and testing converge, the deicing rate prediction network and the equipment damage prediction network are combined to obtain a deicing prediction path.

4. The intelligent control method for spacer deicing according to claim 1, characterized in that: Performing energy storage utilization analysis based on the first vibration control parameter array, the first deicing rate array, and the energy storage parameter array to obtain a first energy storage utilization array includes: Acquire the energy consumption power of the first vibration control parameter array to obtain a first energy consumption parameter array; respectively calculating ratios of the energy storage parameter array and the first energy consumption parameter array to obtain a first basic utilization rate array; The first energy storage utilization rate array is calculated by multiplying the first deicing rate array by the first basic utilization rate array.

5. The intelligent control method for spacer deicing according to claim 1, characterized in that: The method includes calculating and obtaining a first deicing score of the first vibration control parameter array based on the first deicing rate array, the first damage rate array, and the first energy storage utilization rate array, optimizing the vibration control parameters to obtain an optimal deicing control parameter array, and controlling the vibration control unit array to perform deicing control, including: Calculating a first equipment availability array based on the first damage rate array; A first spacer deicing score array of the first vibration control parameter array is obtained by weighted calculation based on the first deicing rate array, the first equipment integrity rate array, and the first energy storage utilization rate array; The vibration control parameter array is continuously randomly configured to optimize the vibration control parameters. After the optimization converges, the deicing control parameter array with the largest spacer deicing score is retained to control the vibration control unit array to perform deicing control.

6. A spacer rod control device, characterized in that: The device comprises: The icing parameter prediction module is used to sense and collect an icing parameter array and an energy storage parameter array through a sensor array and a solar energy supply unit array arranged in a spacer array on a target line, perform icing prediction based on the icing parameter array, and obtain an icing amount array, including: Based on the line icing monitoring data, collect the sample icing parameter set, and collect the average icing thickness when different sample icing parameters appear, and mark the obtained sample icing amount set; Build an ice accumulation prediction network based on machine learning; Iteratively tuning and training the icing amount prediction network using the sample icing parameter set and the sample icing amount set, and completing the training after test convergence; Inputting a plurality of icing parameters in the icing parameter array into the icing amount prediction network, and outputting a plurality of icing amounts to obtain an icing amount array; A deicing parameter prediction module is configured to randomly configure a first vibration control parameter array of the vibration control unit array arranged within the spacer array, and perform deicing rate prediction and equipment damage prediction in combination with the ice accumulation array to obtain a first deicing rate array and a first damage rate array, including: Obtaining vibration control parameter intervals of the vibration control unit array within the spacer rod array, randomly generating first vibration control parameters respectively, and obtaining a first vibration control parameter array, wherein each vibration control unit includes a vibration motor and a control unit; Inputting the first vibration control parameter array and the ice amount array into the constructed deicing prediction path, and predicting output to obtain a first deicing rate array and a first damage rate array, wherein the deicing prediction path includes a deicing rate prediction network and an equipment damage prediction network, and the first damage rate includes the degree of damage to the line; an energy storage utilization analysis module, configured to perform energy storage utilization analysis based on the first vibration control parameter array, the first deicing rate array, and the energy storage parameter array to obtain a first energy storage utilization rate array, wherein the first energy storage utilization rate is a product of a ratio of the energy storage parameter to the first energy consumption parameter corresponding to the first vibration control parameter and the first deicing rate; A control parameter optimization module is used to calculate and obtain a first deicing score for the first vibration control parameter array based on the first deicing rate array, the first damage rate array, and the first energy storage utilization rate array, perform vibration control parameter optimization, obtain an optimal deicing control parameter array, and control the vibration control unit array to perform deicing control.

Images