Anti-icing treatment method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide an anti-icing processing method and device, electronic equipment and a storage medium. The method obtains surrounding environment information of a distribution network line, inputs the surrounding environment information into a preset anti-icing model to obtain a target icing probability of the distribution network line, and trains a machine learning model based on multiple environment information and multiple icing probabilities. If the target icing probability is greater than a preset probability, the distribution network line is subjected to anti-icing processing according to the surrounding environment information. This scheme can realize dynamic decision-making based on actual meteorological risks, improve the accuracy of icing trend identification and the timeliness of disposal, enhance the pertinence of protection strategies in different section scenarios, reduce the lag and mismatch caused by reliance on artificial experience, and thus improve the operation safety of the distribution network and the economy of anti-icing disposal.

Description

Technical Field

[0001] This application relates to the field of power grid technology, and in particular to an anti-icing treatment method, apparatus, electronic device, and storage medium. Background Technology

[0002] In the application of existing distribution network line anti-icing, technical means such as thermal de-icing, mechanical de-icing, surface protection and environmental monitoring and early warning are often used to maintain the stable operation of distribution network lines.

[0003] However, the above solutions mostly rely on manual experience or fixed handling methods, making it difficult to adjust measures in a timely manner according to weather changes; thermal de-icing consumes a lot of energy and its long-term effects can affect the lifespan of line components; mechanical de-icing is significantly limited by terrain and weather; and passive protection and simple early warning are difficult to continuously and effectively control risks during the icing process, making it difficult to balance anti-icing effect and operational economy in complex environments.

[0004] Therefore, how to improve the real-time performance, adaptability, and economy of distribution network line anti-icing under complex weather conditions has become an urgent technical problem to be solved. Summary of the Invention

[0005] This application provides an anti-icing treatment method, apparatus, electronic device, and storage medium to achieve the technical effect of improving the braking safety of electronic devices in emergency situations.

[0006] In a first aspect, embodiments of this application provide an anti-icing treatment method, including:

[0007] Obtain information about the surrounding environment of the distribution network lines;

[0008] The surrounding environmental information is input into a preset anti-icing model to obtain the target icing probability of the distribution network line. The anti-icing model is obtained by training a machine learning model based on multiple environmental information and multiple icing probabilities.

[0009] If the target icing probability is greater than the preset probability, anti-icing treatment is carried out on the distribution network line according to the surrounding environmental information.

[0010] In one or more embodiments, before inputting the surrounding environment information into a preset anti-icing model to obtain the target icing probability of the distribution network line, the method further includes:

[0011] Acquire multiple environmental information items and label the icing probability for each environmental information item separately;

[0012] The machine learning model is trained based on the multiple environmental information and the multiple icing probabilities to obtain the anti-icing model, wherein the machine learning model adopts the random forest algorithm.

[0013] In one or more embodiments, the step of performing anti-icing treatment on the distribution network lines based on the surrounding environment information includes:

[0014] If the surrounding environment information indicates that the power distribution line is in the first stage, the power distribution line is sprayed with an anti-icing coating. The first stage is when the ambient temperature is lower than the first preset temperature and the ambient humidity is higher than the first preset humidity.

[0015] If the surrounding environment information indicates that the power distribution line is in the second stage, the power distribution line is heated. The second stage is when the ice layer thickness is greater than a preset threshold and the ambient temperature is continuously lower than the second preset temperature for a duration greater than the first preset duration.

[0016] If the surrounding environment information indicates that the power distribution line is in the third stage, the power distribution line is subjected to heating treatment and anti-icing coating spraying treatment. The third stage includes: the first stage and the second stage.

[0017] In one or more embodiments, the heating process includes: controlling a heating unit to heat the power distribution line, wherein the heating unit employs a graphene heating film;

[0018] The anti-icing coating spraying process includes: controlling an anti-icing coating spraying unit to spray an anti-icing coating onto the power distribution line, wherein the anti-icing coating spraying unit includes: a paint storage tank, a micro nozzle, and a drive device.

[0019] In one or more embodiments, the corresponding environmental information includes: ambient temperature collected by a temperature sensor, ambient humidity monitored by a humidity sensor, wind speed collected by a wind speed sensor, atmospheric pressure collected by a barometric pressure sensor, and surface condition and thermal imaging of the line captured by an image acquisition device.

[0020] In one or more embodiments, before inputting the surrounding environment information into a preset anti-icing model to obtain the target icing probability of the distribution network line, the method further includes:

[0021] The ambient temperature, ambient humidity, wind speed, atmospheric pressure, line surface condition, and thermal imaging data in the surrounding environment information are normalized to obtain normalized surrounding environment information.

[0022] In one or more embodiments, obtaining the surrounding environment information of the distribution network line includes:

[0023] The surrounding environment information is acquired in the form of data packets via a wireless network consisting of Bluetooth Low Energy or ZigBee at a preset frequency.

[0024] Secondly, embodiments of this application provide an anti-icing treatment device, comprising:

[0025] The acquisition module is used to acquire information about the surrounding environment of the distribution network lines.

[0026] The first processing module is used to input the surrounding environmental information into a preset anti-icing model to obtain the target icing probability of the distribution network line. The anti-icing model is obtained by training a machine learning model based on multiple environmental information and multiple icing probabilities.

[0027] The second processing module is used to perform anti-icing processing on the distribution network line based on the surrounding environment information when the target icing probability is greater than a preset probability.

[0028] In one or more embodiments, before inputting the surrounding environment information into a preset anti-icing model to obtain the target icing probability of the distribution network line, the first processing module is further configured to:

[0029] Acquire multiple environmental information items and label the icing probability for each environmental information item separately;

[0030] The machine learning model is trained based on the multiple environmental information and the multiple icing probabilities to obtain the anti-icing model, wherein the machine learning model adopts the random forest algorithm.

[0031] In one or more embodiments, the second processing module performs anti-icing treatment on the distribution network line based on the surrounding environment information, specifically for:

[0032] If the surrounding environment information indicates that the power distribution line is in the first stage, the power distribution line is sprayed with an anti-icing coating. The first stage is when the ambient temperature is lower than the first preset temperature and the ambient humidity is higher than the first preset humidity.

[0033] If the surrounding environment information indicates that the power distribution line is in the second stage, the power distribution line is heated. The second stage is when the ice layer thickness is greater than a preset threshold and the ambient temperature is continuously lower than the second preset temperature for a duration greater than the first preset duration.

[0034] If the surrounding environment information indicates that the power distribution line is in the third stage, the power distribution line is subjected to heating treatment and anti-icing coating spraying treatment. The third stage includes: the first stage and the second stage.

[0035] In one or more embodiments, the heating process includes: controlling a heating unit to heat the power distribution line, wherein the heating unit employs a graphene heating film;

[0036] The anti-icing coating spraying process includes: controlling an anti-icing coating spraying unit to spray an anti-icing coating onto the power distribution line, wherein the anti-icing coating spraying unit includes: a paint storage tank, a micro nozzle, and a drive device.

[0037] In one or more embodiments, the corresponding environmental information includes: ambient temperature collected by a temperature sensor, ambient humidity monitored by a humidity sensor, wind speed collected by a wind speed sensor, atmospheric pressure collected by a barometric pressure sensor, and surface condition and thermal imaging of the line captured by an image acquisition device.

[0038] In one or more embodiments, before inputting the surrounding environment information into a preset anti-icing model to obtain the target icing probability of the distribution network line, the second processing module is further configured to:

[0039] The ambient temperature, ambient humidity, wind speed, atmospheric pressure, line surface condition, and thermal imaging data in the surrounding environment information are normalized to obtain normalized surrounding environment information.

[0040] In one or more embodiments, the acquisition module acquires information about the surrounding environment of the distribution network line, specifically for:

[0041] The surrounding environment information is acquired in the form of data packets via a wireless network consisting of Bluetooth Low Energy or ZigBee at a preset frequency.

[0042] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0043] The memory stores computer-executed instructions;

[0044] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0045] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0046] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0047] The anti-icing treatment method, apparatus, electronic device, and storage medium provided in this application embodiment acquire surrounding environmental information of the distribution network line; input the surrounding environmental information into a preset anti-icing model to obtain the target icing probability of the distribution network line. The anti-icing model is obtained by training a machine learning model based on multiple environmental information and multiple icing probabilities; if the target icing probability is greater than the preset probability, anti-icing treatment is performed on the distribution network line according to the surrounding environmental information. In this technical solution, by acquiring surrounding environmental information of the distribution network line and inputting it into a preset anti-icing model to obtain the target icing probability of the distribution network line, and performing anti-icing treatment on the distribution network line according to the surrounding environmental information when the target icing probability is greater than the preset probability, it can make a more accurate judgment on the icing risk based on the current environmental state of the line, and implement corresponding treatment in a timely manner when the icing risk is high, thereby improving the real-time performance, adaptability, and economy of distribution network line anti-icing treatment. Attached Figure Description

[0048] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0049] Figure 1 Flowchart of the anti-icing treatment method provided in the embodiments of this application Figure 1 ;

[0050] Figure 2 Flowchart of the anti-icing treatment method provided in the embodiments of this application Figure 2 ;

[0051] Figure 3 Flowchart of the anti-icing treatment method provided in the embodiments of this application Figure 3 ;

[0052] Figure 4 This is a schematic diagram of the anti-icing treatment system provided in the embodiments of this application;

[0053] Figure 5 This is a schematic diagram of the anti-icing treatment device provided in the embodiments of this application;

[0054] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0055] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0056] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0057] The anti-icing technology for distribution network lines is mainly applied in cold regions, areas with frequent rain, snow and ice, and distribution network operation scenarios with large temperature differences between day and night and significant humidity changes. It is especially suitable for environments with complex distribution network lines and high inspection difficulty, such as mountainous areas, forest areas, hilly areas, cross-river valley areas, and urban-rural fringe areas.

[0058] In such scenarios, overhead distribution lines are exposed to external meteorological conditions such as low temperatures, high humidity, freezing rain, fog, and strong winds for extended periods. Condensation and frost easily form on the surfaces of conductors, insulators, and related line components, which can further develop into icing. Once icing forms, it not only increases the mechanical load on the lines but can also trigger a chain reaction of problems, including increased conductor sag, intensified galloping, decreased insulation performance, and abnormal stress on towers, thereby affecting local power supply stability and the safe operation of the distribution network.

[0059] To maintain the safe operation of such lines, existing systems typically need to have the ability to acquire environmental information. This means that monitoring equipment deployed along the line or in key sections collects information on the surrounding environment, such as temperature, humidity, wind speed, and precipitation. This information is then combined with the experience of maintenance personnel or the operational rules of the dispatching side to analyze and address potential icing risks on the line.

[0060] Existing anti-icing technologies can be mainly divided into the following three categories:

[0061] 1) Thermal de-icing: This method melts the ice layer on the circuit surface by heating the conductor with a short-circuit current or by installing heating devices such as resistance wires or electric heating films. Although this method can quickly remove ice, it consumes a lot of energy, can easily lead to aging of the circuit insulation with long-term use, and requires continuous power supply, resulting in high maintenance costs.

[0062] 2) Mechanical de-icing: This involves removing ice by manual knocking, ice scrapers, or helicopter de-icing. These methods rely on manual operation or large equipment, are difficult to implement in complex terrain or inclement weather, are inefficient, and pose safety risks associated with working at heights.

[0063] 3) Passive protection: such as spraying anti-icing coatings or installing anti-icing umbrellas. Anti-icing coatings delay icing by reducing the surface energy of the conductors, but cannot actively respond to sudden icing; anti-icing umbrellas and other structures may fail due to snow accumulation or icing, and cannot adapt to dynamic environmental changes.

[0064] This application addresses the shortcomings of existing technologies by proposing the following technical problems:

[0065] 1) Energy consumption and equipment damage issues: Traditional thermal de-icing technology requires continuous high energy consumption, and the heating process can easily accelerate the aging of circuit insulation and reduce equipment life.

[0066] 2) Efficiency and safety issues: Mechanical de-icing relies on manual labor or large equipment, which is inefficient in complex terrain or in bad weather, and poses safety hazards such as falls from heights and electric shocks.

[0067] 3) Limitations of passive protection: Existing passive protection measures (such as anti-icing coatings) can only delay icing and cannot actively adjust anti-icing strategies according to environmental changes. Their effectiveness decreases significantly when meteorological conditions change abruptly.

[0068] 4) Lack of intelligent control capabilities: Existing technologies are mostly single-function devices that cannot sense environmental parameters in real time and dynamically adjust anti-icing strategies, resulting in anti-icing measures being out of touch with actual needs and making it difficult to adapt to the icing prevention needs under different climatic conditions.

[0069] Accordingly, addressing the technical problems existing in the prior art, the inventors of this application conceive as follows: If real-time environmental information such as temperature, humidity, and wind speed around the distribution network line can be collected, the current external meteorological conditions faced by the line can be objectively characterized; then, the acquired environmental information is input into a preset anti-icing model, which outputs the target icing probability of the distribution network line; when the target icing probability is greater than the preset probability, anti-icing treatment is then applied to the distribution network line based on the environmental information, thus ensuring that line handling is no longer based on general experience, but on the corresponding analysis between environmental information and icing probability. Combining the operational scenario of environmental monitoring, risk analysis, and treatment execution along the distribution network line, this is equivalent to introducing a dynamic decision-making mechanism into the existing anti-icing business process, using environmental information as input and the target icing probability as the judgment criterion. This allows the line to implement more targeted anti-icing treatment based on the actual risk level when facing different meteorological conditions, thus providing a clear technical conceptual foundation for the subsequent development of specific anti-icing technical solutions.

[0070] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments.

[0071] The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0072] It should be understood that the executing electronic device in the embodiments of this application may be: a distribution network line anti-icing treatment terminal, an edge computing device deployed in a substation or power supply station, or a dispatch center server.

[0073] Figure 1 Flowchart of the anti-icing treatment method provided in the embodiments of this application Figure 1 ,like Figure 1 As shown, the method includes:

[0074] Step 11: Obtain information about the surrounding environment of the distribution network line;

[0075] In this step, the distribution network lines are the target of this method and the target of icing prevention. Specifically, they can be overhead distribution lines, line sections, span sections between towers, and key monitoring locations that are closely related to the operating status of the conductors.

[0076] Surrounding environmental information is used to characterize the current external meteorological conditions of the distribution network lines and their impact on icing formation. This information can include: ambient temperature, relative humidity, wind speed, wind direction, precipitation type, precipitation intensity, air pressure, visibility, rime conditions, conductor surface temperature, and local microclimate information related to topography. Based on the above analysis, obtaining surrounding environmental information does not simply mean reading values ​​from a single sensor; rather, it involves collecting, summarizing, verifying, and organizing environmental conditions related to icing formation to provide structured input data for subsequent calculations of the target icing probability.

[0077] Optionally, any environmental information may include: ambient temperature collected by a temperature sensor, ambient humidity monitored by a humidity sensor, wind speed collected by a wind speed sensor, atmospheric pressure collected by a barometric pressure sensor, and surface condition and thermal imaging of the line captured by an image acquisition device.

[0078] In one possible embodiment, environmental data acquisition devices can be deployed along key icing sections of the line. These devices include temperature and humidity sensors, wind speed and direction sensors, rain and snow detection sensors, air pressure sensors, and image acquisition equipment. Each sensor collects data according to a preset sampling period and uploads it to the processing platform via a private wireless network, carrier communication, fiber optic communication, or a public network encrypted link.

[0079] For areas with significant microclimate differences, such as mountainous areas, river valleys, and forest areas, environmental information can be collected separately according to tower locations, section center locations, or historically high-risk locations to avoid localized distortions caused by using uniform environmental parameters for the entire line.

[0080] In another implementation, external environmental data can be synchronously acquired from meteorological department interfaces, regional automatic weather stations, historical operation and maintenance databases, and online monitoring terminals, and then integrated with locally collected data of the lines to form an environmental information set suitable for assessing the risk of icing on distribution network lines.

[0081] Optionally, during processing, the collected raw environmental data can first be time-aligned to unify the sampling times of different sensors and data sources; then outlier removal and missing value compensation can be performed, for example, data that significantly exceeds the sensor's range can be marked, and short-term missing data can be filled by interpolation of nearby times, substitution by nearby stations, or estimation by historical similar meteorological conditions; subsequently, various environmental information can be normalized or dimensionally unified to ensure that data such as temperature, humidity, wind speed, and precipitation status can meet the input requirements of the subsequent anti-icing model.

[0082] For example, precipitation status can be converted into discrete categorical variables, corresponding to no precipitation, rain, snow, freezing rain, fog, etc.; wind direction can be converted into crosswind and longitudinal wind components based on the line alignment to more accurately reflect the impact of wind-induced icing; temperature parameters can be characterized by a combination of ambient temperature and conductor surface temperature to enhance the ability to identify critical icing conditions.

[0083] By employing the aforementioned environmental information collection methods, joint perception of micro-meteorological conditions and surface thermal states around the line can be achieved, improving the comprehensiveness and accuracy of icing identification and providing more representative input data for anti-icing models. Since the image acquisition equipment simultaneously outputs visible light and thermal images, it can identify surface temperature anomalies and changes in attached water film before icing fully forms, thereby improving the timeliness of early warning and response, and reducing energy consumption and maintenance risks associated with handling icing after it has developed.

[0084] Optionally, one possible implementation of step 11 could be:

[0085] The system acquires surrounding environmental information in the form of data packets via a wireless network formed by Bluetooth Low Energy or ZigBee at a preset frequency.

[0086] In this embodiment, Bluetooth Low Energy (BLE) is one of the data transmission methods used to form a wireless network at a preset frequency and obtain information about the surrounding environment. Specifically, it is implemented by collecting and transmitting information about the surrounding environment in the form of data packets through the Bluetooth Low Energy network. ZigBee is another data transmission method used to form a wireless network at a preset frequency and obtain information about the surrounding environment. Specifically, it is implemented by collecting and transmitting information about the surrounding environment in the form of data packets through the ZigBee wireless network.

[0087] Wireless networks are used to transmit data packets carrying information about the surrounding environment. They support acquiring environmental information at preset frequencies and are specifically implemented through Bluetooth Low Energy or ZigBee networking to achieve wireless transmission of sensor data. Data packets are the transmission carriers for carrying information about the surrounding environment, enabling the acquired environmental data to be sent and received within the wireless network. Specifically, they encapsulate information such as ambient temperature, humidity, and wind speed before transmission.

[0088] In this implementation, multiple environmental monitoring nodes can be deployed along the distribution network line. Each monitoring node is connected to temperature, humidity, wind speed, and other environmental sensors. The communication module within each node encapsulates the collected raw monitoring values ​​into data packets and sends them to the aggregation terminal. The communication module can use a low-power Bluetooth chip or a ZigBee communication chip. The former is suitable for low-power, short-range scenarios with relatively concentrated nodes, while the latter is suitable for scenarios with multi-node self-organizing networks and strong topology expansion requirements.

[0089] In practical applications, other models of this component can also be selected, and this application embodiment does not limit this. The preset frequency can be configured according to the risk level of the line section, for example, it can be set to collect data once every few seconds, tens of seconds or a fixed minute cycle, so as to ensure that the surrounding environmental conditions can still be reflected in a timely manner when the weather changes rapidly.

[0090] This implementation method enables the continuous acquisition of surrounding environmental information in a stable, low-power manner suitable for distributed deployment, thereby improving the real-time performance and completeness of environmental perception for distribution network lines. Data packetization also reduces transmission interference from multi-source environmental data in the wireless link, facilitating unified analysis and subsequent model calculations. By collecting data at preset frequencies, parameters such as temperature, humidity, and wind speed around the lines can reflect meteorological changes in a timely manner, providing a continuous and reliable data foundation for icing probability assessment, thus improving the response speed and adaptability of anti-icing measures.

[0091] Step 12: Input the surrounding environmental information into the preset anti-icing model to obtain the target icing probability of the distribution network line;

[0092] Among them, the anti-icing model is obtained by training a machine learning model based on multiple environmental information and multiple icing probabilities;

[0093] In this step, the anti-icing model is used to output the target icing probability of the distribution network lines based on the input surrounding environmental information, thereby determining whether anti-icing measures are needed. Essentially, this anti-icing model is a pre-trained machine learning prediction model, trained on the correlation between multiple environmental information sets and corresponding historical samples of icing probabilities. The target icing probability characterizes the likelihood of the distribution network lines becoming iced or entering a state of significant icing risk under current environmental conditions; it can be represented by a probability value between 0 and 1, or output as a percentage.

[0094] During the inference process, the received and processed information about the surrounding environment is acquired and assembled into a data format consistent with that of the anti-icing model training phase.

[0095] For example, an environmental feature vector can be formed by following a fixed field order. If the input features include temperature T, humidity H, wind speed W, precipitation state P, and air pressure Q, then an environmental input set X = {T, H, W, P, Q} can be constructed. The anti-icing model calculates the target icing probability Y based on the mapping function f on this input set, where Y = f(X).

[0096] In this representation, X characterizes the current external environment of the distribution network, f represents the predictive relationship between the environment and icing risk obtained through training with historical samples, and Y represents the probability output of icing occurring under the current conditions.

[0097] If the anti-icing model output value is close to 1, it indicates that the current environment is highly similar to historical high-risk icing scenarios; if the anti-icing model output value is close to 0, it indicates that the probability of icing is low. In this way, qualitative judgments that originally relied on human experience can be transformed into calculable and comparable quantitative results.

[0098] Furthermore, in this embodiment, to ensure the usability of the output results, confidence verification, time smoothing, and segment correlation correction can be added after model inference. For example, a moving average is applied to the target icing probability over multiple consecutive sampling periods to reduce misjudgments caused by single measurement disturbances; spatial consistency analysis is performed on the prediction results of adjacent segments of the same line, and a verification mechanism can be triggered when an isolated point deviates significantly and the surrounding environment does not support its high-risk state. This makes the model output more consistent with the actual meteorological distribution and icing propagation patterns along the distribution network line.

[0099] Optionally, before step 12, the following can also be performed: normalize the ambient temperature, ambient humidity, wind speed, atmospheric pressure, line surface condition and thermal imaging in the surrounding environment information to obtain normalized surrounding environment information.

[0100] In practical implementation, continuous data such as ambient temperature and atmospheric pressure can be converted into values ​​within a preset range by normalizing the maximum and minimum values, and ambient humidity and wind speed can be transformed according to the same scale; the surface condition of the line can be converted from image recognition results into numerical labels representing icing, snow accumulation or no abnormality, and then participate in normalization processing; thermal imaging can extract features from pixel grayscale or temperature matrix and then perform scale unification.

[0101] After the above processing, the normalized surrounding environmental information can be used as the standard input for the anti-icing model, thereby improving the consistency of input data under different monitoring sections and different acquisition equipment conditions. In practical applications, this normalization module can also adopt other data standardization implementation methods, which are not limited in this embodiment.

[0102] This approach ensures that all types of environmental information have a unified data scale before being input into the anti-icing model, reducing prediction bias caused by differences in sensor range and image feature amplitude, enhancing the model's stability in identifying icing risks under complex weather conditions, and improving the accuracy and comparability of target icing probability calculation results.

[0103] Step 13: If the target icing probability is greater than the preset probability, anti-icing treatment is carried out on the distribution network lines based on the surrounding environmental information.

[0104] In this step, the preset probability is the threshold for triggering anti-icing treatment. It can be set according to the importance level of the line, the historical icing failure rate, regional climate characteristics, power supply reliability requirements and treatment costs. For example, it can be set to 0.60, 0.70 or other probability thresholds suitable for on-site operation and management.

[0105] When the target icing probability is greater than the preset probability, it indicates that the distribution network line has entered a state of high icing risk under the current environmental conditions. This means that the distribution network line can be subjected to corresponding anti-icing measures based on the specific meteorological conditions and risk level reflected by the surrounding environmental information, thereby avoiding passive measures only after icing has clearly formed.

[0106] In one possible embodiment, anti-icing measures may include heating the line for anti-icing, activating local de-icing devices, spraying anti-icing media, adjusting load operation modes, issuing on-site inspection commands, switching to backup power supply paths, or implementing graded alarm linkage for key sections. For distribution network lines with active heating capabilities, the heating power and duration can be determined based on ambient temperature, wind speed, and the target icing probability.

[0107] For example, in low-temperature conditions accompanied by freezing rain, the local heating intensity of the line can be increased to suppress the initial adhesion of ice. In conditions of high humidity condensation but weak precipitation, a preventative heating method with lower power and longer duration can be used to reduce energy consumption. For sections equipped with spraying equipment, the amount and cycle of anti-icing fluid spray can be controlled according to humidity, precipitation status, and conductor surface temperature to maintain a state unfavorable to ice adhesion on the conductor surface. For sections that do not yet have direct physical treatment devices, maintenance and handling suggestions can be automatically generated based on model results, including increasing personnel for inspection, preparing emergency repair resources, temporarily adjusting power supply paths, and focusing on monitoring high-risk sections.

[0108] Accordingly, in specific execution, the target icing probability can be compared with the preset probability. If Y > Y0, an anti-icing processing decision is triggered, where Y represents the target icing probability and Y0 represents the preset probability threshold. Subsequently, key parameters from the current surrounding environment information are read to form the processing strategy selection conditions.

[0109] For example, when the ambient temperature is below the critical freezing temperature, the relative humidity is above a set threshold, and the precipitation is freezing rain, the scenario is identified as a rapid icing scenario, and a high-response-level processing mode is selected. When the temperature is close to zero degrees Celsius, the humidity is high, but there is no significant precipitation, it is identified as a slow icing scenario, and a low-energy-consumption preventative processing mode is selected. Processing instructions can be sent to line heating equipment, spray devices, or edge controllers via the control terminal, or pushed to the maintenance personnel's terminal through scheduling management, forming an automatic or semi-automatic execution link.

[0110] After completing the anti-icing treatment, environmental information can be collected again and the anti-icing model can be called up again to recalculate the target icing probability after treatment, so as to determine whether to maintain, enhance, weaken or end the current treatment process.

[0111] In this embodiment, implementing differentiated anti-icing measures based on surrounding environmental information ensures that the actions taken match the actual risk level, avoiding insufficient protection or over-treatment caused by uniformly adopting a single approach. Especially when there are significant environmental differences between different sections of the same distribution network, this step can execute different intensity and duration processing strategies according to the segmented risk results, thus balancing safety, real-time performance, and economy. Based on the above analysis, this embodiment establishes a continuous business link of environmental information acquisition—model probability prediction—condition-triggered processing, transforming anti-icing decision-making from an experience-driven approach to a data-driven approach. This allows distribution network lines to enter a targeted protection state in advance under complex weather disturbances, reducing cascading risks such as increased conductor sag, intensified galloping, decreased insulation performance, and abnormal tower stress, thereby improving the continuous power supply capacity and line operation stability of the distribution system. It should be understood that the above examples are merely illustrative and not limiting.

[0112] The anti-icing method provided in this application involves acquiring information about the surrounding environment of the distribution network line; inputting this information into a preset anti-icing model to obtain the target icing probability of the distribution network line. The anti-icing model is trained on a machine learning model based on multiple environmental information and multiple icing probabilities. If the target icing probability is greater than the preset probability, anti-icing treatment is applied to the distribution network line according to the surrounding environmental information. This technical solution, by acquiring information about the surrounding environment of the distribution network line and inputting it into a preset anti-icing model to obtain the target icing probability, and by applying anti-icing treatment to the distribution network line based on the surrounding environmental information when the target icing probability is greater than the preset probability, can more accurately judge the icing risk based on the current environmental state of the line and implement corresponding measures in a timely manner when the icing risk is high, thereby improving the real-time performance, adaptability, and economy of anti-icing measures for distribution network lines.

[0113] Based on the above embodiments, Figure 2 Flowchart of the anti-icing treatment method provided in the embodiments of this application Figure 2 ,like Figure 2 As shown, before step 12, the following may also be included:

[0114] Step 21: Obtain multiple environmental information items and label the icing probability for each environmental information item separately;

[0115] In this step, multiple environmental information sources can come from monitoring devices along the line, weather stations, or historical operation records. The environmental information includes at least one or more of the following: temperature, humidity, wind speed, and precipitation status.

[0116] The icing probability of each environmental information can be labeled based on historical icing records, manual verification results, or on-site handling results, and then a training sample can be formed by corresponding environmental information one by one.

[0117] Step 22: Train the machine learning model based on multiple environmental information and multiple icing probabilities to obtain an anti-icing model;

[0118] The machine learning model uses the random forest algorithm.

[0119] In this step, when building a random forest model based on training samples, the training samples can be cleaned, normalized, or have missing values ​​filled in. The processed environmental features are then input into the random forest algorithm for training, and the anti-icing model is output after training is completed.

[0120] In practical applications, the anti-icing model serves as the core for predicting the probability of target icing. After inputting the currently collected surrounding environmental information, the anti-icing model can output a probability value reflecting the current icing risk of the distribution network line.

[0121] The random forest algorithm is characterized by its strong robustness to outliers and good fitting ability to complex nonlinear relationships, thus making it suitable for application scenarios with significant microclimate differences along distribution network lines. Furthermore, other models of this component can be selected in practical applications, and this application does not limit the specific choices.

[0122] The anti-icing processing method provided in this application acquires multiple environmental information sets and labels the icing probability for each set. A machine learning model is trained based on these environmental information sets and icing probabilities to obtain an anti-icing model, which employs a random forest algorithm. In this technical solution, by using the above training method, the anti-icing model can continuously learn the correspondence between environmental conditions and icing risk, making the model output more closely match the actual operating environment. Compared to methods relying on fixed thresholds or human experience, this model can provide a more stable target icing probability after inputting multi-source environmental information, thereby improving the targeting, real-time performance, and consistency of subsequent anti-icing processing, and reducing the probability of misjudgment and missed judgment under complex meteorological conditions.

[0123] Based on the above embodiments, Figure 3 Flowchart of the anti-icing treatment method provided in the embodiments of this application Figure 3 ,like Figure 3 As shown, step 13, based on the surrounding environmental information, performs anti-icing treatment on the distribution network lines, which may include any of the following steps:

[0124] Step 31: If the surrounding environment information indicates that the distribution network line is in the first stage, apply an anti-icing coating to the distribution network line.

[0125] The first stage is characterized by an ambient temperature lower than a first preset temperature and an ambient humidity higher than a first preset humidity.

[0126] In this step, the first stage is used to characterize the environmental state of the distribution network line in the early stage of icing. When the ambient temperature is lower than the first preset temperature and the ambient humidity is higher than the first preset humidity, condensation is easily formed on the line surface and further develops into initial ice crystals. At this time, anti-icing coating spraying treatment can form a hydrophobic or low adhesion interface on the surface of conductors, insulators or fittings, thereby delaying the adhesion of moisture.

[0127] Optionally, the anti-icing coating spraying process includes: controlling the anti-icing coating spraying unit to spray the distribution network lines with an anti-icing coating, wherein the anti-icing coating spraying unit includes: a paint storage tank, a micro nozzle and a drive device.

[0128] In this implementation, the anti-icing coating spraying unit is used to spray anti-icing coating onto the surface of the distribution network line. Its paint storage tank is used to store anti-icing coating material and is connected to the micro nozzle through a corrosion-resistant delivery pipe. The driving device is used to provide spraying power and control the paint output pressure, so that the micro nozzle atomizes the paint and evenly adheres it to the line surface.

[0129] The micro-nozzles can be arranged at intervals along the line and spray directionally toward the outer surface of the conductor to improve the uniformity of coating coverage. In practical applications, other models of this component can also be selected, but this application embodiment does not limit this.

[0130] Correspondingly, with the above structure, the graphene heating film can heat up the line in a shorter time, reducing energy loss and mitigating the thermal shock to the line structure caused by traditional heating methods; the anti-icing coating spraying unit can form a surface protective layer without changing the main structure of the line, improving the line's adaptability to low-temperature and high-humidity environments. The combination of these two technologies enhances the timeliness, stability, and environmental adaptability of anti-icing measures for distribution network lines.

[0131] Step 32: If the surrounding environment information indicates that the distribution network line is in the second stage, heat the distribution network line.

[0132] The second stage is characterized by an ice layer thickness greater than a preset threshold and an ambient temperature that remains below a second preset temperature for a duration greater than a first preset duration.

[0133] In this step, the second stage is used to characterize the state where the distribution network line is already significantly iced. When the ice layer thickness exceeds the preset threshold and the low temperature duration exceeds the first preset duration, it indicates that the ice layer has the conditions to continue to thicken. At this time, heat can be introduced into the line through heating treatment to increase the surface temperature and weaken the bonding force of the ice layer.

[0134] Optionally, the heating process includes: controlling the heating unit to heat the distribution network line, wherein the heating unit adopts a graphene heating film;

[0135] In this implementation, the heating unit is used to perform the heating process of the distribution network line. The graphene heating film used is composed of a graphene thermal conductive layer and a flexible bearing layer. It can quickly generate heat after being powered on and evenly transfer it to the outer surface of the conductor to reduce the risk of local icing.

[0136] The graphene heating film can be attached or wrapped around the outer periphery of the conductor and fixedly connected to the power grid line through a low-temperature resistant insulating adhesive layer. In practical applications, other models of this component can also be selected, but this application embodiment does not limit this.

[0137] Step 33: If the surrounding environment information indicates that the distribution network line is in the third stage, perform heating treatment and anti-icing coating spraying treatment on the distribution network line.

[0138] The third phase includes the first and second phases.

[0139] In this step, the third stage is used to characterize the combined situation where the above two states coexist. When the conditions of low temperature and high humidity and ice layer thickening are met at the same time, the heating treatment and anti-icing coating spraying treatment are carried out in conjunction, which can take into account both the reduction of the existing ice layer and the suppression of subsequent icing.

[0140] It should be understood that in the above implementation, when it is determined that the line needs heating, the graphene heating film rapidly heats up under the action of the driving power supply, and transfers heat to the conductor and its surface adhesion layer, thereby causing the existing thin ice to melt or inhibiting the continued growth of frost. When it is determined that the line needs to be sprayed with an anti-icing coating, the driving device pushes the coating in the storage tank to be sprayed out through a micro-nozzle and deposited on the surface of the line, forming a hydrophobic or low-adhesion protective layer. By performing the heating treatment and the anti-icing coating spraying treatment respectively according to different risk conditions, the line can obtain targeted protection before and after icing formation.

[0141] With the above structure, the graphene heating film can heat up the line in a short time, reducing energy loss and mitigating the thermal shock to the line structure caused by traditional heating methods; the anti-icing coating spraying unit can form a surface protective layer without changing the main structure of the line, improving the line's adaptability to low-temperature and high-humidity environments. The combination of these two technologies enhances the timeliness, stability, and environmental adaptability of anti-icing measures for distribution network lines.

[0142] The model of the above-mentioned component can be selected according to the line voltage level, conductor specifications and on-site power supply conditions to meet the anti-icing requirements of different sections. In practical applications, other models of the component can also be selected, but this application embodiment does not limit this.

[0143] The anti-icing treatment method provided in this application embodiment involves spraying an anti-icing coating on the power distribution line if the surrounding environmental information indicates that the power distribution line is in a first stage, wherein the ambient temperature is lower than a first preset temperature and the ambient humidity is higher than a first preset humidity; if the surrounding environmental information indicates that the power distribution line is in a second stage, the power distribution line is heated, wherein the ice layer thickness is greater than a preset threshold and the duration of the ambient temperature remaining lower than the second preset temperature is greater than a first preset duration; and if the surrounding environmental information indicates that the power distribution line is in a third stage, the power distribution line is heated and sprayed with an anti-icing coating, wherein the third stage includes the first stage and the second stage. The phased anti-icing strategy in this technical solution dynamically matches differentiated response measures according to the severity of environmental conditions: In the first stage (low temperature and high humidity but no ice has formed or the ice layer is relatively thin), anti-icing coating spraying is used first to actively inhibit ice crystal adhesion, which is a low-energy preventive protection; in the second stage (when a certain thickness of ice has formed and the low temperature continues), heating treatment is used to directly melt the ice, which is a highly targeted remedial operation; in the third stage (when the conditions of the first two stages are met at the same time, that is, there is both continuous low temperature and high humidity and a relatively thick ice layer), heating and coating spraying are used in combination to achieve the synergistic effect of active anti-icing and passive melting, thereby avoiding the uniform use of high-energy-consuming heating methods. Under mild weather conditions, only coating can save energy; under severe conditions where ice has formed, timely heating is used to prevent the ice disaster from worsening; under extreme and complex conditions, combined treatment ensures thorough de-icing and inhibits secondary icing.

[0144] Based on the above embodiments, Figure 4 This is a schematic diagram of the anti-icing treatment system provided in the embodiments of this application, as shown below. Figure 4 As shown, the anti-icing system may include: an environmental monitoring module, an intelligent control module, and an anti-icing execution module.

[0145] Accordingly, a possible embodiment of the above method may be as follows:

[0146] Firstly, in the environmental monitoring module:

[0147] The environmental monitoring module, acting as the "eyes" of the anti-icing system, is crucial for accurately acquiring environmental information, and its design and operation mechanism are essential. At the hardware level, a high-precision platinum resistance temperature sensor is used. Based on the characteristic that the resistance of platinum metal exhibits a good linear relationship with temperature changes, it can accurately measure ambient temperature with an accuracy of ±0.5℃. It can sensitively detect subtle fluctuations in air temperature, providing reliable data for determining whether the temperature range for icing risk has been entered. The humidity sensor is a capacitive humidity sensor, utilizing the principle that the dielectric constant of a polymer changes after absorbing moisture, thus altering its capacitance. It monitors ambient humidity in real time, offering fast response and timely feedback on humidity changes.

[0148] The wind speed sensor uses a three-cup anemometer. The three cups rotate under wind force, and the rotational speed of the cups is measured and converted into a wind speed value using an algorithm. The barometric pressure sensor is based on the piezoresistive effect; when the air pressure changes, the resistance of the pressure-sensitive resistor inside the sensor changes, thus measuring the air pressure. The image acquisition equipment uses a dual-lens design with both infrared and visible light. The visible light lens can clearly capture the icing condition of the line surface, while the infrared lens can penetrate a certain degree of clouds, fog, rain, and snow to obtain a thermal image of the line under adverse weather conditions. By analyzing the surface temperature distribution of the line, the presence of potential icing hazards can be determined.

[0149] These sensors form a wireless sensor network via Bluetooth Low Energy or ZigBee wireless communication protocols, transmitting the collected data to the intelligent control module in the form of data packets. To ensure the accuracy and reliability of the data, the sensors perform preliminary filtering on the collected data before transmission to remove noise data caused by factors such as electromagnetic interference, ensuring that the data transmitted to the intelligent control module truly reflects the environmental conditions.

[0150] Secondly, in the intelligent control module:

[0151] The intelligent control module is the brain of the entire anti-icing system, responsible for analyzing and processing the data transmitted from the environmental monitoring module and making decisions. Its core component is an edge computing chip, which possesses powerful local data processing capabilities, enabling rapid analysis and computation of large amounts of environmental data without relying on cloud servers. The chip's built-in anti-icing model is a machine learning model trained on a large amount of historical meteorological data and icing event data. For example, it uses the random forest algorithm to classify and predict data by constructing multiple decision trees, and combines the results of multiple decision trees to improve the accuracy and stability of predictions.

[0152] After receiving data from the environmental monitoring module, the intelligent control module first normalizes the data, converting different types and magnitudes of data to the same scale to facilitate analysis by the algorithm model. Then, the processed data is input into the anti-icing algorithm model. The model calculates the probability of icing risk under the current environmental conditions based on preset icing risk judgment rules (e.g., humidity > 85%, temperature between -5℃ and 0℃ for more than 30 minutes). When the icing risk probability exceeds a set threshold, the intelligent control module immediately generates a control command, triggering the anti-icing execution module.

[0153] In addition, the intelligent control module has a self-learning function, which records and analyzes environmental data, judgment results, and actual icing conditions each time. As the running time increases and more data is accumulated, the intelligent control module will use this new data to retrain and optimize the anti-icing algorithm model, continuously adjusting the model's parameters and judgment rules to better adapt to environmental changes in different regions and seasons, thereby improving the accuracy and timeliness of icing risk prediction.

[0154] Thirdly, in the anti-icing execution module:

[0155] The anti-icing module is the executor of the device's anti-icing function, working in conjunction with the intelligent heating unit and the anti-icing coating spraying unit. The intelligent heating unit utilizes a novel graphene heating film. Graphene possesses excellent electrical properties and thermal conductivity; when current passes through the graphene heating film, electrical energy is rapidly converted into heat energy, heating the circuit. The current flowing through the graphene heating film is adjusted by a pulse width modulation (PWM) signal output from the intelligent control module, thereby precisely controlling the heating temperature. Compared to traditional resistance wire heating, the graphene heating film improves heating efficiency by more than 30%, enabling the circuit temperature to rise to a suitable range in a shorter time, melting existing thin ice while preventing the formation of new ice layers.

[0156] The anti-icing coating spraying unit consists of a paint storage tank, micro-nozzles, and a drive unit. The paint storage tank contains environmentally friendly superhydrophobic anti-icing paint. This paint has extremely low surface energy, causing water droplets to form spherical shapes on its surface, reducing the contact area between water droplets and the line surface, and decreasing the adhesion of ice to the conductor surface. When the intelligent control module determines that the line is in the early stage of icing, it sends a start command to the anti-icing coating spraying unit. The drive unit then activates the micro-nozzles to evenly spray the anti-icing paint onto the transmission line surface. The nozzles employ a special atomization design, enabling the paint to form fine droplets, ensuring uniform coverage of the conductor and forming an ultra-thin anti-icing coating that effectively prevents the growth and accumulation of ice on the conductor.

[0157] The anti-icing system provided in this application has the following technical effects:

[0158] Technical benefits 1) Proactive prevention and efficient de-icing: Through real-time environmental monitoring and intelligent prediction, proactive intervention is carried out before icing forms, which can reduce the incidence of icing accidents by more than 80% compared with traditional passive de-icing methods.

[0159] Technical effect 2) Energy saving and consumption reduction: The intelligent heating unit supplies power on demand, and combined with the long-term protection of the anti-icing coating, it reduces energy consumption by more than 50% compared with traditional thermal ice melting technology.

[0160] Technical benefits 3) Safety and reliability: Avoids the safety hazards of manual or mechanical de-icing. The device uses insulating materials and protective design, and can operate stably in environments ranging from -40℃ to 80℃, with a service life of more than 10 years.

[0161] Technical effect 4) Intelligent adaptation: Based on big data analysis and machine learning, the system can continuously optimize anti-icing strategies, automatically adapt to climate differences in different regions and seasons, and improve the accuracy of anti-icing measures.

[0162] Based on the above embodiments, Figure 5 This is a schematic diagram of the anti-icing treatment device provided in the embodiments of this application, as shown below. Figure 5 As shown, the anti-icing device may include:

[0163] Module 51 is used to acquire information about the surrounding environment of the distribution network line.

[0164] The first processing module 52 is used to input the surrounding environmental information into the preset anti-icing model to obtain the target icing probability of the distribution network line. The anti-icing model is obtained by training a machine learning model based on multiple environmental information and multiple icing probabilities.

[0165] The second processing module 53 is used to perform anti-icing processing on the distribution network lines based on the surrounding environment information when the target icing probability is greater than the preset probability.

[0166] In one or more embodiments, before inputting surrounding environmental information into a preset anti-icing model to obtain the target icing probability of the distribution network line, the first processing module 52 is further configured to:

[0167] Acquire multiple environmental information items and label the icing probability for each environmental information item separately;

[0168] The machine learning model is trained based on multiple environmental information and multiple icing probabilities to obtain an anti-icing model. The machine learning model adopts the random forest algorithm.

[0169] In one or more embodiments, the second processing module 53 performs anti-icing treatment on the distribution network lines based on surrounding environmental information, specifically for:

[0170] If the surrounding environmental information indicates that the distribution network line is in the first stage, the distribution network line is sprayed with an anti-icing coating. The first stage is when the ambient temperature is lower than the first preset temperature and the ambient humidity is higher than the first preset humidity.

[0171] If the surrounding environment information indicates that the distribution network line is in the second stage, the distribution network line will be heated. The second stage is when the ice layer thickness is greater than the preset threshold and the ambient temperature is lower than the second preset temperature for a longer period than the first preset duration.

[0172] If the surrounding environmental information indicates that the distribution network line is in the third stage, the distribution network line will be subjected to heating treatment and anti-icing coating spraying treatment. The third stage includes the first stage and the second stage.

[0173] In one or more embodiments, the heating process includes: controlling a heating unit to heat the distribution network line, wherein the heating unit employs a graphene heating film;

[0174] The anti-icing coating spraying process includes: controlling the anti-icing coating spraying unit to spray anti-icing coating onto the distribution network lines. The anti-icing coating spraying unit includes: a paint storage tank, a micro nozzle, and a drive device.

[0175] In one or more embodiments, the corresponding environmental information includes: ambient temperature collected by a temperature sensor, ambient humidity monitored by a humidity sensor, wind speed collected by a wind speed sensor, atmospheric pressure collected by a barometric pressure sensor, and surface condition and thermal imaging of the line captured by an image acquisition device.

[0176] In one or more embodiments, before inputting surrounding environmental information into a preset anti-icing model to obtain the target icing probability of the distribution network line, the second processing module 53 is further configured to:

[0177] The ambient temperature, ambient humidity, wind speed, atmospheric pressure, surface condition of the line, and thermal imaging data in the surrounding environment information are normalized to obtain normalized surrounding environment information.

[0178] In one or more embodiments, the acquisition module 51 acquires information about the surrounding environment of the distribution network line, specifically for:

[0179] The system acquires surrounding environmental information in the form of data packets via a wireless network formed by Bluetooth Low Energy or ZigBee at a preset frequency.

[0180] It should be noted that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical element, or they can be physically separated. Furthermore, these modules can be implemented entirely in software through processing element calls, or entirely in hardware. Alternatively, some modules can be implemented through processing element calls in software, while others can be implemented in hardware. Moreover, these modules can be integrated together or implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. During implementation, each step of the above method or each of the above modules can be completed through the integrated logic circuits in the hardware of the processor element or through software instructions.

[0181] As can be seen from the above, the anti-icing treatment device provided in this embodiment can perform the method provided in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be described in detail here.

[0182] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device provided in this embodiment includes at least one processor 61 and a memory 62.

[0183] Optionally, the electronic device also includes a communication component 63.

[0184] The processor 61, memory 62, and communication component 63 are connected via bus 64.

[0185] In a specific implementation, at least one processor 61 executes computer execution instructions stored in memory 62, causing at least one processor 61 to perform the above-described method.

[0186] The specific implementation process of processor 61 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0187] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0188] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0189] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0190] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0191] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0192] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0193] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0194] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0195] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0196] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0197] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0198] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0199] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for preventing icing, characterized in that, include: Obtain information about the surrounding environment of the distribution network lines; The surrounding environmental information is input into a preset anti-icing model to obtain the target icing probability of the distribution network line. The anti-icing model is obtained by training a machine learning model based on multiple environmental information and multiple icing probabilities. If the target icing probability is greater than the preset probability, anti-icing treatment is carried out on the distribution network line according to the surrounding environmental information.

2. The method according to claim 1, characterized in that, Before inputting the surrounding environmental information into a preset anti-icing model to obtain the target icing probability of the distribution network line, the method further includes: Acquire multiple environmental information items and label the icing probability for each environmental information item separately; The machine learning model is trained based on the multiple environmental information and the multiple icing probabilities to obtain the anti-icing model, wherein the machine learning model adopts the random forest algorithm.

3. The method according to claim 1 or 2, characterized in that, The step of performing anti-icing treatment on the distribution network lines based on the surrounding environmental information includes: If the surrounding environment information indicates that the power distribution line is in the first stage, the power distribution line is sprayed with an anti-icing coating. The first stage is when the ambient temperature is lower than the first preset temperature and the ambient humidity is higher than the first preset humidity. If the surrounding environment information indicates that the power distribution line is in the second stage, the power distribution line is heated. The second stage is when the ice layer thickness is greater than a preset threshold and the ambient temperature is continuously lower than the second preset temperature for a duration greater than the first preset duration. If the surrounding environment information indicates that the power distribution line is in the third stage, the power distribution line is subjected to heating treatment and anti-icing coating spraying treatment. The third stage includes: the first stage and the second stage.

4. The method according to claim 3, characterized in that, The heating process includes: controlling a heating unit to heat the power distribution line, wherein the heating unit uses a graphene heating film; The anti-icing coating spraying process includes: controlling an anti-icing coating spraying unit to spray an anti-icing coating onto the power distribution line, wherein the anti-icing coating spraying unit includes: a paint storage tank, a micro nozzle, and a drive device.

5. The method according to claim 1 or 2, characterized in that, The corresponding environmental information includes: ambient temperature collected by the temperature sensor, ambient humidity monitored by the humidity sensor, wind speed collected by the wind speed sensor, atmospheric pressure collected by the air pressure sensor, and surface condition and thermal imaging of the line captured by the image acquisition equipment.

6. The method according to claim 5, characterized in that, Before inputting the surrounding environmental information into a preset anti-icing model to obtain the target icing probability of the distribution network line, the method further includes: The ambient temperature, ambient humidity, wind speed, atmospheric pressure, line surface condition, and thermal imaging data in the surrounding environment information are normalized to obtain normalized surrounding environment information.

7. The method according to claim 1 or 2, characterized in that, The acquisition of the surrounding environment information of the distribution network line includes: The surrounding environment information is acquired in the form of data packets via a wireless network consisting of Bluetooth Low Energy or ZigBee at a preset frequency.

8. An anti-icing treatment device, characterized in that, include: The acquisition module is used to acquire information about the surrounding environment of the distribution network lines. The first processing module is used to input the surrounding environmental information into a preset anti-icing model to obtain the target icing probability of the distribution network line. The anti-icing model is obtained by training a machine learning model based on multiple environmental information and multiple icing probabilities. The second processing module is used to perform anti-icing processing on the distribution network line based on the surrounding environment information when the target icing probability is greater than a preset probability.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

Images