A Collaborative Control Method and System for Transmission Line De-icing Devices Based on Data Fusion

Abstract

This invention relates to the field of power grid icing prevention technology, and discloses a collaborative control method and system for transmission line de-icing devices based on data fusion. The method includes: fusing and analyzing temperature distribution data and wind speed and direction data to determine the conductor torsional load risk level of ultra-high voltage (UHV) lines; determining whether the conductor torsional load risk level is high-risk; if so, performing correlation calculations on temperature distribution data and wind speed and direction data to obtain the conductor ice adhesion force variation curve of the UHV lines; allocating power to each de-icing device control area to obtain a first control strategy for the corresponding de-icing device control area; and combining the first control strategy to perform operational planning for each de-icing device control area to obtain a second control strategy for the corresponding de-icing device control area. This invention effectively reduces the conductor torsional load risk of UHV lines through collaborative control of de-icing devices.

Description

Technical Field

[0001] This invention relates to the field of power grid icing prevention and control technology, and in particular to a collaborative control method and system for transmission line de-icing devices based on data fusion. Background Technology

[0002] Ice prevention and control on ultra-high voltage (UHV) and extra-high voltage (EHV) power lines plays a crucial role in maintaining the safe operation of the power grid. This is especially true in extreme environments such as high mountain passes, where torsional loads and line breakage risks caused by ice accumulation can severely impact grid stability. Therefore, ensuring the reliable operation of power lines under complex weather conditions is of great significance.

[0003] Currently, most ice-de-icing prevention methods rely on fixed de-icing devices or manual inspections. These methods suffer from slow response times, high energy consumption, and a lack of precise control, making it difficult to adapt to the dynamic changes in ice accumulation caused by drastic microclimate variations in high-altitude mountain passes. This results in low de-icing efficiency and may even exacerbate mechanical stress on power lines. For example, traditional fixed de-icing devices melt the ice by heating the conductors, but this requires interrupting power transmission, leading to high energy consumption and difficulty in flexibly adjusting power based on actual icing conditions. Manual inspections, on the other hand, rely on maintenance personnel climbing the lines and using handheld devices for testing, making it difficult to monitor large areas of the line in real time, resulting in slow response times and an inability to accurately locate severely iced areas.

[0004] Therefore, in order to cope with the rapid changes in the morphology and physical properties of ice cover in high-altitude mountain passes, it is necessary to propose an innovative method for controlling ice melting devices. Summary of the Invention

[0005] To improve the de-icing efficiency of ultra-high voltage power transmission lines in mountainous pass sections, this invention provides a collaborative control method and system for de-icing devices on power transmission lines based on data fusion.

[0006] In a first aspect, embodiments of the present invention provide a collaborative control method for a transmission line de-icing device based on data fusion, comprising:

[0007] Acquire temperature distribution data and wind speed and direction data of the high-altitude pass section of the ultra-high voltage line, and perform fusion analysis on the temperature distribution data and the wind speed and direction data to determine the conductor torsional load risk level of the ultra-high voltage line;

[0008] Determine whether the risk level of the conductor torsional load is high. If so, perform correlation calculation on the temperature distribution data and the wind speed and direction data to obtain the conductor ice adhesion force change curve of the ultra-high voltage line.

[0009] Based on the conductor ice adhesion change curve, the ultra-high voltage line is divided into several ice melting device control areas, and power is allocated to each ice melting device control area to obtain a first control strategy corresponding to the ice melting device control area. The first control strategy includes the power setting value of each fixed ice melting device in the corresponding ice melting device control area.

[0010] By combining the first control strategy with the operation planning of each ice-melting device control area, a second control strategy corresponding to the ice-melting device control area is obtained. The second control strategy includes the operation path and operation sequence of each mobile ice-melting device within the ice-melting device control area.

[0011] Preferably, the step of acquiring temperature distribution data and wind speed and direction data of the high-altitude pass section of the ultra-high voltage line, and performing fusion analysis on the temperature distribution data and the wind speed and direction data to determine the conductor torsional load risk level of the ultra-high voltage line includes:

[0012] Temperature distribution data and wind speed and direction data of the high-altitude pass section of the ultra-high voltage line are obtained, and icing calculations are performed on the temperature distribution data and wind speed and direction data based on the principle of heat and mass balance to obtain the asymmetric icing distribution characteristics of the ultra-high voltage line.

[0013] Spatiotemporal evolution analysis of the asymmetric icing distribution characteristics is performed to obtain icing difference characteristics. Based on the icing difference characteristics, frequency domain analysis is performed on the collected conductor vibration time domain data of the ultra-high voltage line to obtain the conductor vibration amplitude characteristics of the ultra-high voltage line.

[0014] Based on the conductor vibration amplitude characteristics, a torsional load risk assessment is performed on the ultra-high voltage line to obtain the conductor torsional load risk level of the ultra-high voltage line.

[0015] Preferably, the step of assessing the torsional load risk of the ultra-high voltage line based on the conductor vibration amplitude characteristics to obtain the conductor torsional load risk level of the ultra-high voltage line includes:

[0016] Multi-scale feature extraction is performed on the vibration amplitude characteristics of the conductor to obtain the vibration load characteristics of the conductor;

[0017] The random forest algorithm is used to classify the torsional load risk of the conductor vibration load characteristics, and the torsional load risk level of the conductor of the ultra-high voltage line is obtained.

[0018] Preferably, the step of determining whether the conductor torsional load risk level is high-risk, and if so, performing correlation calculations on the temperature distribution data and the wind speed and direction data to obtain the conductor ice adhesion force variation curve of the ultra-high voltage line, includes:

[0019] If the risk level of the conductor torsional load exceeds the preset high-risk threshold, the risk level of the conductor torsional load is determined to be high-risk.

[0020] The temperature distribution data and wind speed and direction data are coupled and calculated based on the energy balance equation to obtain the temperature change characteristics of the ice layer interface of the ultra-high voltage line.

[0021] The melting rate of the ice surface and the frequency of the melting-refreezing cycle of the ice surface are calculated based on the temperature change characteristics of the ice layer interface.

[0022] Based on the melting rate of the ice surface and the melting-refreezing cycle frequency of the ice surface, a mapping analysis of the temperature change characteristics of the ice interface is performed to obtain the conductor ice adhesion change curve of the ultra-high voltage line.

[0023] Preferably, the step of mapping and analyzing the temperature change characteristics of the ice layer interface based on the melting rate of the ice layer surface and the melting-refreezing cycle frequency of the ice layer surface to obtain the conductor ice adhesion change curve of the ultra-high voltage line includes:

[0024] Based on the melting rate of the ice surface and the melting-refreezing cycle frequency of the ice surface, the random forest algorithm is used to map the ice adhesion force of the ice interface temperature change characteristics to obtain the ice adhesion force change curve of the conductor of the ultra-high voltage line.

[0025] Preferably, the process of dividing the ultra-high voltage line into several de-icing device control areas based on the conductor ice adhesion change curve, and allocating power to each de-icing device control area to obtain a first control strategy corresponding to the de-icing device control area, includes:

[0026] Based on the variation curve of ice adhesion on the conductor, the ultra-high voltage line is divided into regions, and the obtained regions are merged to obtain several ice melting device control areas.

[0027] Power is allocated to each control area of ​​the ice-melting device to obtain the power density value per unit length of the corresponding control area of ​​the ice-melting device.

[0028] Based on the power density value per unit length and the length of each ice-melting device control area, linear programming is used to calculate the initial power value of each fixed ice-melting device within the corresponding ice-melting device control area.

[0029] Based on the regional temperature response characteristics, the initial power value of each fixed ice-melting device within the control area of ​​each ice-melting device is corrected to obtain the power setting value of each fixed ice-melting device within the control area of ​​the corresponding ice-melting device.

[0030] Preferably, the step of allocating power to each of the ice-melting device control areas to obtain the power density value per unit length of the corresponding ice-melting device control area includes:

[0031] A power allocation model is constructed based on deep reinforcement learning, and power is allocated to each control area of ​​the ice melting device according to the power allocation model to obtain the power density value per unit length of the control area of ​​the ice melting device. The power allocation model is configured to take at least the regional ice adhesion force, regional length and regional temperature distribution as input data, and the regional power density per unit length as output data.

[0032] Preferably, the step of combining the first control strategy to perform operational planning for each ice-melting device control area to obtain a second control strategy corresponding to the ice-melting device control area includes:

[0033] Based on the temperature distribution data, the control areas of all the ice melting devices are prioritized to obtain the area ranking results;

[0034] Based on the regional sorting results and the first control strategy, the ant colony optimization algorithm is used to sequentially plan the path for each of the ice-melting device control areas to obtain the movement path of each mobile ice-melting device within the corresponding ice-melting device control area.

[0035] Based on the movement path of each mobile ice-melting device within the control area of ​​each ice-melting device, calculate the movement duration and working dwell time of the corresponding mobile ice-melting device within the control area of ​​the ice-melting device.

[0036] Based on the movement duration and working dwell time of each mobile ice-melting device within the control area of ​​each ice-melting device, the working sequence of the corresponding mobile ice-melting device within the control area of ​​the ice-melting device is determined.

[0037] Preferably, after determining the operation sequence of the corresponding mobile ice-melting device within the control area of ​​each ice-melting device based on the movement duration and the operation dwell time of each mobile ice-melting device within the control area of ​​each ice-melting device, the method further includes:

[0038] Based on the operating sequence of each mobile ice-melting device within the control area of ​​each ice-melting device, a genetic algorithm is used to optimize the start interval of each mobile ice-melting device within the control area of ​​the ice-melting device.

[0039] Secondly, embodiments of the present invention provide a collaborative control system for a power transmission line de-icing device based on data fusion, comprising:

[0040] The risk level determination module is used to acquire temperature distribution data and wind speed and direction data of the high mountain pass section of the ultra-high voltage line, and to perform fusion analysis on the temperature distribution data and the wind speed and direction data to determine the conductor torsional load risk level of the ultra-high voltage line.

[0041] The correlation calculation module is used to determine whether the risk level of the conductor torsional load is high. If so, the temperature distribution data and the wind speed and direction data are correlated and calculated to obtain the conductor ice adhesion force change curve of the ultra-high voltage line.

[0042] The first strategy determination module is used to divide the ultra-high voltage line into several de-icing device control areas based on the conductor ice adhesion change curve, and to allocate power to each of the de-icing device control areas to obtain a first control strategy corresponding to the de-icing device control area. The first control strategy includes a power setting value for each fixed de-icing device in the de-icing device control area.

[0043] The second strategy determination module is used to combine the first control strategy to perform operation planning for each of the ice-melting device control areas to obtain a second control strategy corresponding to the ice-melting device control area. The second control strategy includes the operation path and operation sequence of each mobile ice-melting device within the ice-melting device control area.

[0044] Compared with existing technologies, the present invention discloses a data fusion-based collaborative control method and system for transmission line de-icing devices. Its advantages include: merging temperature distribution data and wind speed and direction data to comprehensively consider the impact of meteorological conditions on conductor loads, accurately determine the torsional load risk level, and provide a reliable basis for subsequent decision-making; when a high risk is identified, the conductor ice adhesion change curve is obtained through correlation calculation, providing key data support for de-icing operations; dividing the control area of ​​the de-icing device based on the ice adhesion curve and scientifically allocating power allows the fixed de-icing device to output energy on demand, avoiding energy waste and localized insufficient de-icing; and combining the first control strategy with the operation planning of the mobile de-icing device ensures that the path and operation sequence of the mobile device closely match actual needs, forming efficient collaboration with the fixed de-icing device. Through the fusion analysis and in-depth mining of multi-source data, this invention achieves accurate assessment of transmission line icing risks, effectively reduces conductor torsional load risks, and improves the safety of power grid operation. Attached Figure Description

[0045] Figure 1 This is a flowchart illustrating a collaborative control method for a power transmission line de-icing device based on data fusion, according to an embodiment of the present invention.

[0046] Figure 2This is a schematic diagram of the structure of a collaborative control system for a power transmission line de-icing device based on data fusion, according to an embodiment of the present invention.

[0047] Figure label:

[0048] 1. Risk level determination module; 2. Correlation calculation module; 3. First strategy determination module; 4. Second strategy determination module. Detailed Implementation

[0049] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0050] In the description of this invention, it should be understood that the terms "first" and "second," etc., are used to distinguish different objects, rather than to describe a specific order.

[0051] In the description of this invention, it should be noted that, unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by those skilled in the art. The terminology used in this specification is for the purpose of describing specific embodiments only and is not intended to limit the invention. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0052] like Figure 1 As shown, this embodiment of the invention provides a collaborative control method for transmission line de-icing devices based on data fusion, including the following steps:

[0053] S1. Obtain temperature distribution data and wind speed and direction data of the high-altitude pass section of the ultra-high voltage line, and perform fusion analysis on the temperature distribution data and wind speed and direction data to determine the conductor torsional load risk level of the ultra-high voltage line.

[0054] Specifically, step S1 includes:

[0055] 1) Obtain temperature distribution data and wind speed and direction data of the high mountain pass section of the ultra-high voltage line, and perform icing calculation on the temperature distribution data and wind speed and direction data based on the principle of heat and mass balance to obtain the asymmetric icing distribution characteristics of the ultra-high voltage line;

[0056] By deploying monitoring devices with temperature detection units at high-altitude mountain passes along ultra-high voltage power transmission lines, real-time temperature distribution data along the line is collected, and wind speed and direction data are monitored and recorded in real time by wind speed and wind direction sensors.

[0057] Due to differences in solar radiation and ventilation conditions received at different locations along ultra-high voltage (UHV) power lines, the surface temperature distribution becomes uneven, resulting in sun-facing and shaded sides. The sun-facing side receives more solar radiation and has a relatively higher temperature, potentially leading to different icing conditions compared to the shaded side. In this context, the heat-mass balance principle primarily considers the transfer and balance of heat and mass in the environment surrounding the UHV line. By establishing a heat conduction calculation model, using acquired temperature distribution data and wind speed and direction data as input parameters, and considering processes such as heat transfer, water vapor condensation, and freezing, the model predicts and analyzes the icing distribution characteristics of the sun-facing and shaded sides of the UHV line—specifically, the asymmetric icing distribution characteristics, including differences in ice thickness, density gradient, and coverage area.

[0058] 2) Spatiotemporal evolution analysis of asymmetric icing distribution characteristics is performed to obtain icing difference characteristics. Based on the icing difference characteristics, frequency domain analysis is performed on the collected conductor vibration time domain data of ultra-high voltage lines to obtain conductor vibration amplitude characteristics of ultra-high voltage lines.

[0059] Specifically, through spatiotemporal evolution analysis, the differences in icing distribution characteristics caused by the temporal and spatial variations can be discovered. Due to differences in temperature, sunlight, and other conditions on the sun-facing and sun-facing sides of the line, the rate and extent of icing growth will differ, and this difference manifests in spatiotemporal terms as the icing difference characteristics.

[0060] Furthermore, time-domain data of conductor vibration of the ultra-high voltage (UHV) line were collected by multiple monitoring sensors deployed on the conductor surface. These data reflect physical quantities such as conductor displacement, velocity, or acceleration at different times. Based on the icing difference characteristics, frequency domain analysis of the conductor vibration time-domain data was performed using Fourier transform to obtain the conductor vibration amplitude and frequency characteristics of the UHV line.

[0061] 3) Based on the characteristics of conductor vibration amplitude, the torsional load risk assessment of ultra-high voltage lines is carried out to obtain the conductor torsional load risk level of ultra-high voltage lines.

[0062] Specifically, step 3) includes:

[0063] i) Perform multi-scale feature extraction on the conductor vibration amplitude characteristics to obtain the conductor vibration load characteristics;

[0064] Wavelet decomposition is used to separate the conductor vibration amplitude features at multiple scales, obtaining the conductor vibration amplitude feature sequences at different scales, and establishing the conductor vibration load features. Specifically, in this embodiment, four-level wavelet decomposition is used in the multi-scale feature extraction, corresponding to the 0.5~1Hz frequency band, 1~2Hz frequency band, 2~4Hz frequency band, and 4~8Hz frequency band, respectively.

[0065] ii) The random forest algorithm is used to classify the torsional load risk of conductor vibration load characteristics to obtain the torsional load risk level of ultra-high voltage lines.

[0066] In torsional load risk assessment, a preset risk threshold is established based on a large amount of historical data. The torsional deviation value in the conductor vibration load characteristics is compared, and a random forest algorithm is used to classify the torsional load risk of the conductor vibration load characteristics according to the torsional deviation value, thus obtaining the conductor torsional load risk level of the ultra-high voltage line. Specifically, this embodiment establishes preset high-risk, medium-risk, and low-risk thresholds. Correspondingly, the conductor torsional load risk level includes high risk, medium risk, and low risk.

[0067] S2. Determine whether the risk level of conductor torsional load is high. If so, perform correlation calculations on temperature distribution data and wind speed and direction data to obtain the conductor ice adhesion force change curve of ultra-high voltage line.

[0068] Specifically, step S2 includes:

[0069] 1) If the risk level of conductor torsional load exceeds the preset high-risk threshold, the risk level of conductor torsional load is determined to be high-risk;

[0070] When the torsional load risk level of a conductor is determined to be high, it indicates that the torsional load borne by the conductor may have a significant impact on the safe operation of the line. In this case, further analysis and assessment of the risk situation are necessary.

[0071] 2) Based on the energy balance equation, coupled calculations are performed on temperature distribution data and wind speed and direction data to obtain the temperature variation characteristics of the ice layer interface of ultra-high voltage lines;

[0072] Based on the energy balance equation, and taking into account the heat transfer between the ice layer and the surrounding environment, including factors such as solar radiation, convective heat transfer, and heat conduction, the temperature change characteristics of the ice layer interface of ultra-high voltage lines are calculated using temperature distribution data and wind speed and direction data.

[0073] 3) Calculate the surface melting rate and the frequency of ice surface melting-refreezing cycles based on the characteristics of ice layer interface temperature change;

[0074] The temperature change at the ice interface directly determines the melting rate of the ice surface. When the temperature rises above the melting point of ice, the ice begins to melt; the higher the temperature, the faster the melting rate. Simultaneously, due to fluctuations in ambient temperature and factors such as wind speed, the ice may undergo a cycle of melting and refreezing. Based on the characteristics of the ice interface temperature change, the melting rate of the ice surface is calculated. The melting and refreezing state of the ice is determined based on this melting rate, and the number of melting-refreezing cycles is recorded to determine the frequency of the ice surface melting-refreezing cycle.

[0075] 4) Based on the melting rate of the ice surface and the frequency of melting and refreezing cycles of the ice surface, a mapping analysis of the temperature change characteristics of the ice interface is performed to obtain the change curve of ice adhesion force of the conductors of ultra-high voltage lines.

[0076] Specifically, based on the ice surface melting rate and the ice surface melting-refreezing cycle frequency, a random forest algorithm is used to map the ice adhesion force of the ice interface temperature change characteristics, resulting in the ice adhesion force change curve of the conductors in ultra-high voltage transmission lines. Furthermore, this embodiment uses a random forest regressor to establish the mapping relationship between ice interface temperature and ice adhesion force. The random forest regressor integrates multiple decision trees, and the input features include the ice interface temperature.

[0077] S3. Based on the change curve of ice adhesion force of conductor, the ultra-high voltage line is divided into several ice melting device control areas, and power is allocated to each ice melting device control area to obtain the first control strategy of the corresponding ice melting device control area.

[0078] Specifically, the first control strategy includes the power setting value of each fixed ice-melting device within the control area of ​​the corresponding ice-melting device.

[0079] Further, step S3 includes:

[0080] 1) Based on the variation curve of ice adhesion force on conductors, the ultra-high voltage line is divided into regions, and the obtained regions are merged to obtain several ice melting device control areas;

[0081] The ice adhesion force variation curve of the conductor reflects the spatial variation of ice adhesion force at different locations along the line. Analyzing this curve using a region segmentation algorithm can determine the differences in ice adhesion force across different regions. Based on these differences, the line can be divided into different regions for targeted control of the de-icing device.

[0082] Meanwhile, in order to simplify the control complexity of the ice melting device, an adaptive clustering algorithm is used to merge regions with similar ice adhesion based on the similarity of ice adhesion, thus obtaining several control regions for the ice melting device.

[0083] 2) Distribute power to the control area of ​​each ice-melting device to obtain the power density value per unit length of the corresponding ice-melting device control area;

[0084] Specifically, a power allocation model is constructed based on deep reinforcement learning, and power is allocated to the control area of ​​each ice-melting device according to the power allocation model to obtain the power density value per unit length of the corresponding ice-melting device control area. The power allocation model is configured to take at least the regional ice adhesion force, regional length, and regional temperature distribution as input data, learn and analyze the input data, and take the regional power density per unit length as output data.

[0085] 3) Based on the power density per unit length and the length of the control area of ​​each ice-melting device, linear programming is used to calculate the initial power value of each fixed ice-melting device within the control area of ​​the corresponding ice-melting device.

[0086] Based on the power density per unit length and the length of the control area of ​​each ice-melting device, the total power demand of the control area of ​​each ice-melting device can be calculated. Using the total power demand, linear programming is then used to calculate the initial power value of each fixed ice-melting device within the control area of ​​each ice-melting device. However, when using linear programming to calculate the initial power value of each fixed ice-melting device, the power supply capacity limitations of the power system must be considered.

[0087] 4) Based on the regional temperature response characteristics, the initial power value of each fixed ice-melting device within the control area of ​​each ice-melting device is corrected to obtain the power setting value of each fixed ice-melting device within the corresponding ice-melting device control area.

[0088] The regional temperature response characteristics describe the impact of different regional temperatures on the ice-melting process. Adjusting the power allocation according to the actual temperature conditions can make the ice-melting operation more in line with actual needs, thereby improving the efficiency of ice-melting. Specifically, the regional temperature response characteristics in this embodiment show that when the ambient temperature is -5℃, there is a temperature correction coefficient of 0.8 between the power input and the temperature response. Based on this, the initial power value is corrected to obtain the power setting value of each fixed ice-melting device within the control area of ​​each ice-melting device.

[0089] S4. Combine the first control strategy to perform operation planning for the control area of ​​each ice melting device, and obtain the second control strategy for the corresponding ice melting device control area.

[0090] Specifically, the second control strategy includes the operating path and operation sequence of each mobile ice-melting device within the control area of ​​the corresponding ice-melting device.

[0091] Further, step S4 includes:

[0092] 1) Prioritize all ice-melting device control areas based on temperature distribution data to obtain the area ranking results;

[0093] Temperature distribution data reflects the temperature conditions at different locations along the power line. Due to environmental factors and line load, the temperature distribution along the line is often uneven. Some areas have lower temperatures, making them more prone to ice formation and potentially resulting in thicker ice layers. These areas are the key areas for de-icing. By analyzing the temperature distribution data and prioritizing the control areas of all de-icing devices, the specific locations requiring priority de-icing operations can be determined, thus laying the foundation for subsequent de-icing work.

[0094] 2) Based on the regional sorting results and the first control strategy, the ant colony optimization algorithm is used to perform path planning for each ice-melting device control area in turn, so as to obtain the movement path of each mobile ice-melting device in the corresponding ice-melting device control area.

[0095] Based on the regional sorting results, and combined with the power setting value of each fixed ice-melting device within the control area of ​​the corresponding ice-melting device in the first control strategy, the ant colony optimization algorithm can be used to generate the movement path of each mobile ice-melting device within the control area of ​​the corresponding ice-melting device.

[0096] It should be noted that the ant colony optimization algorithm, which simulates the foraging behavior of ants, can find a more optimized movement path for the mobile ice-melting device, taking into account the power output of the fixed ice-melting device and the priority of the de-icing area. These movement paths determine the locations that the mobile ice-melting device needs to reach during the de-icing process.

[0097] 3) Based on the movement path of each mobile ice-melting device within the control area of ​​each ice-melting device, calculate the movement duration and working dwell time of the corresponding mobile ice-melting device within the control area of ​​the corresponding ice-melting device.

[0098] Specifically, based on the movement path of each mobile de-icing device within the control area of ​​each de-icing device, and according to the distance between nodes along the movement path and the distribution location of fixed de-icing devices, the movement time of the corresponding mobile de-icing device within the control area of ​​the corresponding de-icing device is calculated. The distance between nodes determines the time required for the mobile de-icing device to move, while the distribution location of the fixed de-icing devices affects the movement path and speed of the mobile de-icing device. By calculating the movement time, the operating time of the mobile de-icing device can be planned more accurately, ensuring that it can efficiently carry out de-icing operations in different areas.

[0099] Furthermore, based on the movement duration and the fluctuation period of the power output of the fixed ice-melting device, a neural network is used to calculate the working dwell time of the mobile ice-melting device at each node in the movement path, thereby obtaining the working dwell time of each mobile ice-melting device within the control area of ​​each ice-melting device.

[0100] 4) Based on the movement time and working dwell time of each mobile ice-melting device within the control area of ​​each ice-melting device, determine the working sequence of the corresponding mobile ice-melting device within the control area of ​​the corresponding ice-melting device.

[0101] Based on the duration of movement and the time spent at work, an operation time sequence matrix is ​​established for the mobile ice-melting device. The operation time sequence matrix reflects the collaborative relationship between multiple mobile ice-melting devices. For example, the matrix dimension of the operation time sequence matrix is ​​4×25, corresponding to the operation arrangement of 4 mobile ice-melting devices at 25 nodes.

[0102] Furthermore, following step 4), the following step is also included:

[0103] 5) Based on the operation sequence of each mobile ice-melting device within the control area of ​​each ice-melting device, a genetic algorithm is used to optimize the start-up interval of each mobile ice-melting device within the control area of ​​the corresponding ice-melting device.

[0104] Genetic algorithms optimize the start-up intervals of mobile de-icing devices by simulating biological evolution, thereby improving the efficiency and coordination of the overall de-icing operation. This ultimately yields the start-up intervals for each mobile de-icing device, enabling precise control of the de-icing operation. Specifically, in this embodiment, when optimizing the start-up intervals using a genetic algorithm, the goal is to minimize the total operation time. The calculation results show that a 30-minute interval between the start-up of each mobile de-icing device is the most reasonable.

[0105] This invention discloses a collaborative control method for transmission line de-icing devices based on data fusion. By integrating temperature distribution data and wind speed and direction data, it comprehensively considers the impact of meteorological conditions on conductor loads, accurately determines the torsional load risk level, and provides a reliable basis for subsequent decision-making. When a high-risk condition is identified, the method obtains the conductor ice adhesion change curve through correlation calculation, providing crucial data support for de-icing operations. Based on the ice adhesion curve, the method divides the control area of ​​the de-icing device and scientifically allocates power, enabling fixed de-icing devices to output energy on demand, avoiding energy waste and localized insufficient de-icing. Combined with a first control strategy, the method plans the operation of mobile de-icing devices, ensuring that the path and operation sequence of the mobile devices closely match actual needs, forming efficient collaboration with fixed de-icing devices. This invention, through the fusion analysis and in-depth mining of multi-source data, achieves accurate assessment of transmission line icing risks, effectively reduces conductor torsional load risks, and improves the safety of power grid operation.

[0106] Based on the above-mentioned collaborative control method for transmission line de-icing devices based on data fusion, such as... Figure 2 As shown, this embodiment of the invention provides a collaborative control system for a transmission line de-icing device based on data fusion, comprising:

[0107] Risk level determination module 1 is used to acquire temperature distribution data and wind speed and direction data of the high mountain pass section of the ultra-high voltage line, and to perform fusion analysis on the temperature distribution data and wind speed and direction data to determine the conductor torsional load risk level of the ultra-high voltage line.

[0108] The correlation calculation module 2 is used to determine whether the risk level of conductor torsional load is high. If so, it performs correlation calculation on temperature distribution data and wind speed and direction data to obtain the conductor ice adhesion force change curve of ultra-high voltage line.

[0109] The first strategy determination module 3 is used to divide the ultra-high voltage line into several de-icing device control areas based on the conductor ice adhesion change curve, and to allocate power to each de-icing device control area to obtain the first control strategy of the corresponding de-icing device control area. The first control strategy includes the power setting value of each fixed de-icing device in the corresponding de-icing device control area.

[0110] The second strategy determination module 4 is used to combine the first control strategy to perform operation planning for each ice-melting device control area to obtain the second control strategy for the corresponding ice-melting device control area. The second control strategy includes the operation path and operation sequence of each mobile ice-melting device within the corresponding ice-melting device control area.

[0111] It should be noted that each module in the aforementioned collaborative control system for transmission line de-icing devices based on data fusion can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module. For specific limitations regarding the collaborative control system for transmission line de-icing devices based on data fusion, please refer to the limitations of the collaborative control method for transmission line de-icing devices based on data fusion described above; both have the same function and role, and will not be repeated here.

[0112] In summary, this invention provides a data fusion-based collaborative control method and system for transmission line de-icing devices. By integrating temperature distribution data and wind speed and direction data, it comprehensively considers the impact of meteorological conditions on conductor loads, accurately determines the torsional load risk level, and provides a reliable basis for subsequent decision-making. When a high-risk condition is identified, the system obtains the conductor ice adhesion change curve through correlation calculation, providing crucial data support for de-icing operations. By dividing the control area of ​​the de-icing device based on the ice adhesion curve and scientifically allocating power, the fixed de-icing device can output energy on demand, avoiding energy waste and insufficient local de-icing. Combined with a first control strategy, the mobile de-icing device's operation is planned, ensuring that the mobile device's path and operation sequence closely match actual needs, forming efficient collaboration with the fixed de-icing device. This invention, through the fusion analysis and in-depth mining of multi-source data, achieves accurate assessment of transmission line icing risks, effectively reduces conductor torsional load risks, and improves the safety of power grid operation.

[0113] The various embodiments in this specification are described in a progressive manner. For directly identical or similar parts of the embodiments, refer to each other. Each embodiment focuses on its differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. It should be noted that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0114] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be considered within the scope of protection of the present invention.

Claims

1. A collaborative control method for a transmission line de-icing device based on data fusion, characterized in that, include: Acquire temperature distribution data and wind speed and direction data of the high-altitude pass section of the ultra-high voltage line, and perform fusion analysis on the temperature distribution data and the wind speed and direction data to determine the conductor torsional load risk level of the ultra-high voltage line; Determine whether the risk level of the conductor torsional load is high. If so, perform correlation calculation on the temperature distribution data and the wind speed and direction data to obtain the conductor ice adhesion force change curve of the ultra-high voltage line. Based on the conductor ice adhesion change curve, the ultra-high voltage line is divided into several ice melting device control areas, and power is allocated to each ice melting device control area to obtain a first control strategy corresponding to the ice melting device control area. The first control strategy includes the power setting value of each fixed ice melting device in the corresponding ice melting device control area. By combining the first control strategy with the operation planning of each ice-melting device control area, a second control strategy corresponding to the ice-melting device control area is obtained. The second control strategy includes the operation path and operation sequence of each mobile ice-melting device within the ice-melting device control area.

2. The collaborative control method for transmission line de-icing devices based on data fusion according to claim 1, characterized in that, The process of acquiring temperature distribution data and wind speed and direction data for the high-altitude pass section of the ultra-high voltage power transmission line, and performing fusion analysis on the temperature distribution data and the wind speed and direction data to determine the conductor torsional load risk level of the ultra-high voltage power transmission line includes: Temperature distribution data and wind speed and direction data of the high-altitude pass section of the ultra-high voltage line are obtained, and icing calculations are performed on the temperature distribution data and wind speed and direction data based on the principle of heat and mass balance to obtain the asymmetric icing distribution characteristics of the ultra-high voltage line. Spatiotemporal evolution analysis of the asymmetric icing distribution characteristics is performed to obtain icing difference characteristics. Based on the icing difference characteristics, frequency domain analysis is performed on the collected conductor vibration time domain data of the ultra-high voltage line to obtain the conductor vibration amplitude characteristics of the ultra-high voltage line. Based on the conductor vibration amplitude characteristics, a torsional load risk assessment is performed on the ultra-high voltage line to obtain the conductor torsional load risk level of the ultra-high voltage line.

3. The collaborative control method for transmission line de-icing devices based on data fusion according to claim 2, characterized in that, The torsional load risk assessment of the ultra-high voltage line based on the conductor vibration amplitude characteristics, to obtain the conductor torsional load risk level of the ultra-high voltage line, includes: Multi-scale feature extraction is performed on the vibration amplitude characteristics of the conductor to obtain the vibration load characteristics of the conductor; The random forest algorithm is used to classify the torsional load risk of the conductor vibration load characteristics, and the torsional load risk level of the conductor of the ultra-high voltage line is obtained.

4. The collaborative control method for transmission line de-icing devices based on data fusion according to claim 1, characterized in that, The step of determining whether the conductor torsional load risk level is high-risk, and if so, performing correlation calculations on the temperature distribution data and the wind speed and direction data to obtain the conductor ice adhesion force variation curve of the ultra-high voltage line, including: If the risk level of the conductor torsional load exceeds the preset high-risk threshold, the risk level of the conductor torsional load is determined to be high-risk. The temperature distribution data and wind speed and direction data are coupled and calculated based on the energy balance equation to obtain the temperature change characteristics of the ice layer interface of the ultra-high voltage line. The melting rate of the ice surface and the frequency of the melting-refreezing cycle of the ice surface are calculated based on the temperature change characteristics of the ice layer interface. Based on the melting rate of the ice surface and the melting-refreezing cycle frequency of the ice surface, a mapping analysis of the temperature change characteristics of the ice interface is performed to obtain the conductor ice adhesion change curve of the ultra-high voltage line.

5. The collaborative control method for transmission line de-icing devices based on data fusion according to claim 4, characterized in that, The mapping analysis of the ice layer interface temperature change characteristics based on the ice layer surface melting rate and the ice layer surface melting-refreezing cycle frequency yields the conductor ice adhesion change curve of the ultra-high voltage line, including: Based on the melting rate of the ice surface and the melting-refreezing cycle frequency of the ice surface, the random forest algorithm is used to map the ice adhesion force of the ice interface temperature change characteristics to obtain the ice adhesion force change curve of the conductor of the ultra-high voltage line.

6. The collaborative control method for transmission line de-icing devices based on data fusion according to claim 1, characterized in that, The ultra-high voltage line is divided into several de-icing device control areas based on the conductor ice adhesion change curve, and power is allocated to each de-icing device control area to obtain a first control strategy corresponding to the de-icing device control area, including: Based on the variation curve of ice adhesion on the conductor, the ultra-high voltage line is divided into regions, and the obtained regions are merged to obtain several ice melting device control areas. Power is allocated to each control area of ​​the ice-melting device to obtain the power density value per unit length of the corresponding control area of ​​the ice-melting device. Based on the power density value per unit length and the length of each ice-melting device control area, linear programming is used to calculate the initial power value of each fixed ice-melting device within the corresponding ice-melting device control area. Based on the regional temperature response characteristics, the initial power value of each fixed ice-melting device within the control area of ​​each ice-melting device is corrected to obtain the power setting value of each fixed ice-melting device within the control area of ​​the corresponding ice-melting device.

7. The collaborative control method for transmission line de-icing devices based on data fusion according to claim 6, characterized in that, The step of allocating power to each control area of ​​the ice-melting device to obtain the power density value per unit length of the corresponding control area includes: A power allocation model is constructed based on deep reinforcement learning, and power is allocated to each control area of ​​the ice melting device according to the power allocation model to obtain the power density value per unit length of the control area of ​​the ice melting device. The power allocation model is configured to take at least the regional ice adhesion force, regional length and regional temperature distribution as input data, and the regional power density per unit length as output data.

8. The collaborative control method for transmission line de-icing devices based on data fusion according to claim 1, characterized in that, The step of combining the first control strategy to perform operational planning for each ice-melting device control area to obtain a second control strategy corresponding to the ice-melting device control area includes: Based on the temperature distribution data, the control areas of all the ice melting devices are prioritized to obtain the area ranking results; Based on the regional sorting results and the first control strategy, the ant colony optimization algorithm is used to sequentially plan the path for each of the ice-melting device control areas to obtain the movement path of each mobile ice-melting device within the corresponding ice-melting device control area. Based on the movement path of each mobile ice-melting device within the control area of ​​each ice-melting device, calculate the movement duration and working dwell time of the corresponding mobile ice-melting device within the control area of ​​the ice-melting device. Based on the movement duration and working dwell time of each mobile ice-melting device within the control area of ​​each ice-melting device, the working sequence of the corresponding mobile ice-melting device within the control area of ​​the ice-melting device is determined.

9. The collaborative control method for transmission line de-icing devices based on data fusion according to claim 8, characterized in that, After determining the operation sequence of the corresponding mobile ice-melting device within the control area of ​​each ice-melting device based on the movement duration and operation dwell time of each mobile ice-melting device within the control area of ​​each ice-melting device, the method further includes: Based on the operating sequence of each mobile ice-melting device within the control area of ​​each ice-melting device, a genetic algorithm is used to optimize the start interval of each mobile ice-melting device within the control area of ​​the ice-melting device.

10. A collaborative control system for a power transmission line de-icing device based on data fusion, characterized in that, include: The risk level determination module is used to acquire temperature distribution data and wind speed and direction data of the high mountain pass section of the ultra-high voltage line, and to perform fusion analysis on the temperature distribution data and the wind speed and direction data to determine the conductor torsional load risk level of the ultra-high voltage line. The correlation calculation module is used to determine whether the risk level of the conductor torsional load is high. If so, the temperature distribution data and the wind speed and direction data are correlated and calculated to obtain the conductor ice adhesion force change curve of the ultra-high voltage line. The first strategy determination module is used to divide the ultra-high voltage line into several de-icing device control areas based on the conductor ice adhesion change curve, and to allocate power to each of the de-icing device control areas to obtain a first control strategy corresponding to the de-icing device control area. The first control strategy includes a power setting value for each fixed de-icing device in the de-icing device control area. The second strategy determination module is used to combine the first control strategy to perform operation planning for each of the ice-melting device control areas to obtain a second control strategy corresponding to the ice-melting device control area. The second control strategy includes the operation path and operation sequence of each mobile ice-melting device within the ice-melting device control area.

Images