A multi-source sensing and adaptive control deicing method suitable for a catenary

Abstract

This invention relates to a de-icing method for overhead contact lines using multi-source sensing and adaptive control. The method includes: receiving multi-source monitoring data transmitted from various sensors deployed on the overhead contact line; predicting the icing status of at least one section of conductor within the overhead contact line in a future time period using a predictive model; outputting icing data to achieve accurate detection of the overhead contact line; determining the output power of a hot air assembly based on the icing data of the target conductor and a set de-icing strategy when the icing data of the target conductor meets the early warning triggering conditions, thereby achieving precise energy control and reducing energy consumption; controlling the hot air assembly to blow heat towards the target conductor at its output power, causing the target conductor to heat up and maintain at a set temperature, so as to at least partially melt the icing on the target conductor, achieving the technical effect of performing de-icing operations in advance based on the icing development trend, and solving the monitoring lag problem in related issues.

Description

Technical Field

[0001] This invention relates to the field of overhead contact line protection technology, and in particular to a de-icing method, apparatus, equipment, and storage medium suitable for multi-source sensing and adaptive control of overhead contact lines. Background Technology

[0002] The overhead contact system is the direct carrier for providing traction power to trains on electrified railways, and its stable power supply is a fundamental guarantee for safe train operation. However, in cold, rainy, and snowy weather during winter, the surfaces of the overhead contact wires and catenary cables are prone to icing. Icing can alter the geometry of the current-collecting interface of the overhead contact system, causing arcing and disconnection. In severe cases, the additional load can lead to wire breakage or damage to the supporting structure, seriously threatening the safety of railway operation.

[0003] Currently, the management of overhead contact line icing mainly relies on post-treatment methods such as mechanical removal and non-contact heating. Mechanical de-icing devices primarily depend on manual operation or physical operation via track-moving platforms, resulting in low efficiency and the risk of mechanical damage. While non-contact heating technologies, such as electromagnetic induction, avoid physical contact, they lack precise energy control mechanisms and are energy-intensive. Furthermore, online monitoring systems and de-icing devices are often independent systems, unable to intervene in de-icing operations in advance based on the icing development trend, leading to delayed response and insufficient coordination. Summary of the Invention

[0004] To address the aforementioned technical problems, this disclosure provides a de-icing method, apparatus, device, and storage medium suitable for multi-source sensing and adaptive control of overhead contact lines.

[0005] In a first aspect, embodiments of this disclosure provide a de-icing method suitable for multi-source sensing and adaptive control of overhead contact lines, comprising: Receives multi-source monitoring data transmitted from various sensors deployed on the overhead contact line; The pre-trained prediction model predicts the icing status of at least one section of the overhead contact line in a future period based on multi-source monitoring data, and outputs the icing data. If the icing data of the target conductor meets the early warning triggering conditions, the output power of the hot air component is determined based on the icing data of the target conductor and the set de-icing strategy. The hot air assembly is controlled to blow heat toward the target wire at its output power, causing the target wire to heat up and maintain at a set temperature, so as to at least partially melt the ice on the target wire.

[0006] Optionally, multiple sensors include monitoring sensors deployed on the contact network towers, infrared thermal imagers, and meteorological sensors. The monitoring sensors are used to collect ice thickness data of at least one section of conductor included in the contact network. The infrared thermal imagers are used to monitor the surface temperature distribution data of at least one section of conductor in real time. The meteorological sensors are used to collect environmental data around at least one section of conductor. The environmental data includes at least one of temperature, humidity, wind direction, and wind speed. The multi-source monitoring data includes ice thickness data, surface temperature distribution data, and environmental data.

[0007] Optionally, the prediction model includes a feature extraction layer, an analysis and calculation layer, and a type recognition layer. Based on multi-source monitoring data, the pre-trained prediction model predicts the icing condition of at least one section of the overhead contact line in a future time period and outputs icing data, including: Texture features of echo signals characterized by ice thickness data in multi-source monitoring data are extracted using a feature extraction layer. By analyzing the surface temperature distribution data and environmental data from texture features and multi-source monitoring data in the computational layer, the icing change trend over time is analyzed, and the icing growth rate of at least one section of the overhead contact line in the future period is obtained. The type identification layer distinguishes the icing pattern of at least one section of the conductor based on multi-source monitoring data; Calculate the icing thickness of at least one section of the conductor in the future period based on the icing growth rate, and generate icing data including icing thickness and / or icing growth rate as well as icing morphology.

[0008] Optionally, if the icing data of the target conductor meets the early warning triggering conditions, the output power of the hot air assembly is determined based on the icing data of the target conductor and the set de-icing strategy, including: If the icing growth rate in the icing data of the target conductor is greater than the first warning threshold, and / or the icing thickness in the icing data of the target conductor is greater than the second warning threshold, then the icing data of the target conductor is determined to meet the warning triggering conditions, and the warning is triggered. By comparing the icing thickness with the response threshold of the pre-set multi-level response mechanism, the target response for the target conductor is determined, wherein the de-icing strategy includes a multi-level response mechanism. Initiate the target response and determine the output power of the hot air assembly based on the icing pattern in the icing data of the target conductor and the set power range under the target response.

[0009] Optionally, the multi-level response mechanism includes Level 1, Level 2, and Level 3 responses. Level 1 response refers to activating the low-power mode of the hot air component, where the set power range is from the minimum adjustable power of the hot air component to the set power. Level 2 response refers to activating the high-power mode of the hot air component, where the set power range is from the set power to the maximum adjustable power of the hot air component. Level 3 response, based on Level 2 response, simultaneously triggers an alarm in the remote dispatch center to notify relevant personnel to assist in de-icing.

[0010] Optionally, the hot air assembly includes a power-adjustable heating element and a power-adjustable blower. The heating element includes multiple heating elements connected in parallel; the blower includes multiple fans connected in parallel; controlling the hot air assembly to blow heat towards the target conductor at the output power includes: The heating assembly is positioned below the target conductor using a rotating lifting device; At least one heating element is controlled to switch on and off using a solid-state relay, and the output power of the heating component is adjusted to the first power in the output power by the pulse width modulation module and incremental algorithm built into the heating element, so that the heating component generates heat. At least one fan is controlled to switch on and off by a solid-state switch, and the output power of the blower is adjusted to a second power by the permanent magnet synchronous motor, frequency converter and pulse control algorithm on the blower, so that the blower blows out air volume that matches the first power and blows the heat generated by the heating component to the target wire.

[0011] Optionally, after controlling the hot air assembly to blow heat towards the target conductor at the output power, the method further includes: Based on the ambient humidity data from multi-source monitoring, determine the spray interval and spray volume of antifreeze to be sprayed onto the target conductor; After the target conductor is de-iced, antifreeze is uniformly sprayed onto the surface of the target conductor according to the spray interval until the spray volume is reached, so as to form an anti-icing coating of a set thickness on the surface of the target conductor.

[0012] Secondly, embodiments of this disclosure provide a de-icing device suitable for multi-source sensing and adaptive control of overhead contact lines, comprising: The receiving unit is used to receive multi-source monitoring data transmitted by various sensors deployed on the overhead contact line; The prediction unit is used to predict the icing status of at least one section of the overhead contact line in a future period based on multi-source monitoring data using a pre-trained prediction model, and outputs icing data. The determining unit is used to determine the output power of the hot air assembly based on the icing data of the target conductor and the set de-icing strategy when the icing data of the target conductor meets the early warning triggering conditions. The control unit controls the hot air assembly to blow heat toward the target wire at the output power, so that the target wire is heated and maintained at the set temperature to at least partially melt the ice on the target wire.

[0013] Thirdly, embodiments of this disclosure provide an electronic device, including: Memory; Processor; and Computer programs; The computer program is stored in memory and configured to be executed by a processor to implement the first aspect of the method described above.

[0014] Fourthly, embodiments of this disclosure provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect above.

[0015] The de-icing method for multi-source sensing and adaptive control applicable to overhead contact lines disclosed herein includes: receiving multi-source monitoring data transmitted by various sensors deployed on the overhead contact line, predicting the icing status of at least one section of conductor in the overhead contact line during a future period using a predictive model, and outputting icing data to achieve accurate detection of the overhead contact line; determining the output power of the hot air assembly based on the icing data of the target conductor and a set de-icing strategy when the icing data of the target conductor meets the early warning triggering conditions, so as to achieve precise energy control and reduce energy consumption; controlling the hot air assembly to blow heat toward the target conductor at the output power, so that the target conductor is heated and maintained at a set temperature, so as to at least partially melt the icing on the target conductor, achieving the technical effect of carrying out de-icing operations in advance according to the icing development trend, and solving the monitoring lag problem existing in related issues. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0017] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A schematic diagram of a de-icing system for multi-source sensing and adaptive control of overhead contact lines, provided in an embodiment of this disclosure; Figure 2 A flowchart illustrating a de-icing method for multi-source sensing and adaptive control of overhead contact lines provided in this embodiment of the present disclosure; Figure 3 A flowchart illustrating another de-icing method for multi-source sensing and adaptive control of overhead contact lines provided in this disclosure embodiment; Figure 4 A schematic diagram of a de-icing device for multi-source sensing and adaptive control of overhead contact lines provided in an embodiment of this disclosure; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0019] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0020] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0021] Specifically, the overhead contact line, as the lifeline for power supply to railway trains, is highly susceptible to icing in cold, rainy, and snowy winter weather. This can range from minor issues like abnormal pantograph power collection to serious problems like tower tilting and collapse, severely threatening railway operational safety. Existing technologies for controlling overhead contact line icing have significant shortcomings: mechanical de-icing devices rely on manual operation or track-moving platforms, resulting in low de-icing efficiency and potential damage to the contact wires; while electromagnetic induction de-icing can achieve non-contact heating, it lacks a precise energy control mechanism, leading to excessive energy consumption; and monitoring systems and de-icing devices often operate independently, failing to anticipate icing trends and resulting in delayed responses.

[0022] In related technologies, contact wire de-icing devices remove ice through a combination of tapping, vibration, and scraping, but still require movable supports for operation, making them unsuitable for real-time de-icing needs in complex terrain sections. Magnetic energy induction de-icing devices use fixed power output but cannot dynamically adjust heating energy according to ice thickness. UAV-based de-icing systems are limited by endurance, making it difficult to complete continuous de-icing operations over long distances of contact wires. Therefore, developing an integrated system capable of precise monitoring and efficient de-icing, linking monitoring and de-icing, has become an urgent technical problem to be solved.

[0023] To address the aforementioned technical problems, this disclosure provides a de-icing method for overhead contact lines using multi-source sensing and adaptive control. This will be described in detail through one or more of the following embodiments.

[0024] The de-icing method for multi-source sensing and adaptive control applicable to overhead contact lines provided in this disclosure is applicable to overhead contact line de-icing scenarios. This method can be executed by an overhead contact line de-icing device, which can be implemented in software and / or hardware and can be integrated into an electronic device. The electronic device can include, but is not limited to, mobile terminals such as smartphones, laptops, digital radio receivers, personal digital assistants (PDAs), tablet PCs, PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), wearable devices, etc., as well as fixed terminals such as digital televisions, desktop computers, smart home devices, etc.

[0025] Figure 1 This is a schematic diagram of a multi-source sensing and adaptive control de-icing system for overhead contact lines, provided in an embodiment of this disclosure. The system includes a multi-source monitoring module, an intelligent decision-making module, an adaptive de-icing module, and an anti-icing maintenance module. Each module interacts with the other via a wireless communication network. The overhead contact system is an overhead power line system that supplies power to electric trains. Its core structure, from top to bottom, includes: supports and cantilever arms forming the supporting framework; catenary cables suspending the contact wire (also called the conductor) via droppers, maintaining its straightness and height; and positioners fixing the horizontal position of the contact wire. Insulators ensure electrical isolation, and segmented insulators achieve power supply zone control. Trains obtain continuous power by sliding contact with the conductor via a pantograph on the roof. Therefore, the overhead contact system de-icing system can be understood as a de-icing system suitable for multi-source sensing and adaptive power regulation of the overhead contact system.

[0026] The multi-source monitoring module includes various sensors deployed on the overhead contact line. These sensors monitor the contact line and collect data, including linear microwave monitoring sensors, infrared thermal imagers, and meteorological sensor arrays distributed across the contact line towers. The monitoring data collected by these sensors can be understood as multi-source monitoring data. Furthermore, the multi-source monitoring module employs BeiDou short message communication technology to encrypt and transmit monitoring data to the intelligent decision-making module in frame structure, with a single frame data size ≤ 100 bytes, ensuring stable transmission in areas without public network coverage.

[0027] The intelligent decision-making module includes an early warning calculation unit and a cloud platform analysis system. The early warning calculation unit calculates the icing growth rate based on multi-source monitoring data and triggers early warnings. The cloud platform analysis system distinguishes different icing patterns, providing a basis for formulating appropriate de-icing strategies. Furthermore, the intelligent decision-making module has a self-learning function, dynamically optimizing the early warning threshold based on historical de-icing results.

[0028] The adaptive de-icing module includes an adjustable PTC heating element, an adjustable blower, and a power control unit. The adjustable PTC heating element generates heat by adjusting its output power, and the adjustable blower directs the heat towards the contact wire by adjusting its power. The power control unit, based on the output of the intelligent decision module, uses a gradient temperature control algorithm to determine the output power of the heating element and the blower, achieving directional and precise heating. Additionally, the adaptive de-icing module is equipped with a temperature feedback sensor; when the surface temperature of the conductor reaches 5°C, it automatically reduces the power to the heat preservation setting to prevent damage to the conductor due to overheating.

[0029] The anti-icing maintenance module includes an antifreeze storage tank and a metering spray device. The antifreeze uses environmentally friendly nanofluid materials. The spray device is linked with the adaptive de-icing module. After the de-icing operation is completed, it automatically sprays a uniform coating onto the surface of the conductor to form an anti-icing coating, effectively delaying the time of secondary icing.

[0030] The contact wire de-icing system disclosed herein achieves an integrated prevention and control system that combines precise icing monitoring and efficient de-icing through the dynamic coordination of various modules. It can effectively solve the problems of monitoring lag, high de-icing energy consumption, and poor equipment coordination in related contact wire icing prevention and control technologies.

[0031] Figure 2 This is a flowchart illustrating a de-icing method for multi-source sensing and adaptive control applicable to overhead contact lines, provided in an embodiment of this disclosure. Applied to the aforementioned overhead contact line de-icing system, it specifically includes, as follows: Figure 2 The following steps are shown: S201: Receives multi-source monitoring data transmitted from various sensors deployed on the overhead contact line.

[0032] Understandably, S201 is executed by the multi-source monitoring module. It receives real-time multi-source monitoring data from various sensors deployed on the overhead contact line. These sensors are deployed in a distributed manner; for example, monitoring units are installed on overhead contact line towers at 500-meter intervals, and each monitoring unit includes at least one sensor. Multi-source monitoring data refers to relevant data used to predict the icing condition of the overhead contact line in the future, including current icing data, environmental data, and surface data of the overhead contact line conductors. All collected sensor data is packaged and processed by a microprocessor, and then encrypted and transmitted according to a custom frame format using BeiDou short message communication technology. The transmitted data is recorded as multi-source monitoring data. In one embodiment, all sensor data is packaged and processed by an STM32H743 microprocessor and transmitted via the BeiDou BD-2B1I module according to a custom frame format. The frame structure includes a 4-byte frame header, a 5-byte device identifier, a 60-byte data body, and a 2-byte CRC checksum. Other possible frame structures are not limited.

[0033] The various sensors include monitoring sensors deployed on the contact network towers, infrared thermal imagers, and meteorological sensors. The monitoring sensors are used to collect data on the ice thickness of at least one section of the conductor in the contact network. The infrared thermal imagers are used to monitor the surface temperature distribution data of at least one section of the conductor in real time. The meteorological sensors are used to collect environmental data around at least one section of the conductor. The environmental data includes at least one of temperature, humidity, wind direction, and wind speed. The multi-source monitoring data includes ice thickness data, surface temperature distribution data, and environmental data.

[0034] Understandably, the various sensors include linear microwave monitoring sensors deployed on the contact network towers, infrared thermal imagers, and meteorological sensor arrays. The multi-source monitoring data includes: linear microwave monitoring sensors for collecting ice thickness data on the contact network conductors; infrared thermal imagers for real-time monitoring of the conductor surface temperature distribution; and meteorological sensors for synchronously collecting environmental data such as ambient temperature, humidity, wind direction, and wind speed. In one embodiment, a 24GHz linear microwave monitoring sensor measures ice thickness using the Doppler effect, with a sampling frequency of 1Hz and a measurement accuracy of ±0.1mm. The infrared thermal imager uses a 640×480 resolution and a frame rate of 5FPS to capture the conductor surface temperature distribution in real time. The meteorological sensor integrates temperature, humidity, wind speed, and liquid water content sensors, with a temperature measurement range of -50~85℃, a humidity measurement range of 0~100%RH, a wind speed measurement range of 0-60m / s, and a data update cycle of 1 minute.

[0035] In one embodiment, a linear microwave monitoring sensor collects ice thickness data every 3 minutes, an infrared thermal imager monitors the conductor temperature in real time, and a meteorological sensor group records environmental parameters synchronously. All data is transmitted encrypted via BeiDou short message service.

[0036] S202. Using a pre-trained prediction model, predict the icing status of at least one section of the overhead contact line in a future period based on multi-source monitoring data, and output the icing data.

[0037] Understandably, S202 is executed by the intelligent decision-making module. Based on S201 above, the early warning calculation unit of the intelligent decision-making module incorporates a hybrid prediction model. This model, combined with multi-source monitoring data, predicts in real time the icing situation of the overhead contact line, including at least one section of conductor, in the future, and outputs icing data, such as predicting the icing thickness growth rate or icing thickness within one hour. In one embodiment, the early warning calculation unit uses the Ascend 310BAI chip and runs an improved CNN-LSTM (Convolutional Neural Network-Long Short-Term Memory) hybrid prediction model. The hybrid prediction model built into the early warning calculation unit is used to calculate the icing growth rate of the conductor in real time, where the icing data only includes the icing growth rate or the icing thickness growth rate. In another embodiment, the cloud platform analysis system establishes an icing type recognition model through big data training to distinguish different icing forms on the conductor, such as rime ice and hoarfrost, providing a basis for formulating appropriate de-icing strategies. Here, the icing data includes the icing form and the icing thickness growth rate. In another embodiment, a hybrid prediction model performs the tasks of real-time calculation of icing growth rate and icing morphology differentiation, and outputs icing data including icing morphology and icing thickness growth rate.

[0038] The prediction model includes a feature extraction layer, an analysis and calculation layer, and a type recognition layer.

[0039] Understandably, the following embodiments are described in detail using a prediction model to perform the tasks of classifying icing morphology and calculating the icing thickness growth rate.

[0040] Optionally, a pre-trained prediction model is used to predict the icing status of at least one section of the overhead contact line in a future time period based on multi-source monitoring data, and outputs icing data, including: The feature extraction layer extracts the texture features of the echo signal characterized by icing thickness data from multi-source monitoring data; the analysis and calculation layer analyzes the icing change trend over time based on the texture features, surface temperature distribution data from multi-source monitoring data, and environmental data to obtain the icing growth rate of at least one section of the overhead contact line in the future period; the type identification layer distinguishes the icing morphology of at least one section of the conductor based on multi-source monitoring data; the icing thickness of at least one section of the conductor in the future period is calculated based on the icing growth rate, and icing data including icing thickness and / or icing growth rate and icing morphology is generated.

[0041] Understandably, the texture features of the echo signal from the linear microwave monitoring sensor are extracted using a feature extraction module (CNN layer). An analysis and computation layer (LSTM layer) analyzes the icing or subsequent icing trends over time based on the texture features, surface temperature distribution data from multi-source monitoring data, and environmental data, obtaining the icing thickness growth rate or icing rate increase. A type recognition layer distinguishes the icing morphology of at least one section of the conductor based on the multi-source monitoring data, such as different icing morphologies like rime and hoarfrost. Subsequently, the icing thickness of the conductor in future time periods is calculated based on the icing growth rate or subsequent icing rate increase, generating icing data.

[0042] S203. If the icing data of the target conductor meets the early warning triggering conditions, determine the output power of the hot air assembly based on the icing data of the target conductor and the set de-icing strategy.

[0043] Understandably, based on the above S202, the icing data includes the icing status of at least one conductor. The icing status of each conductor is compared with the warning threshold in the warning triggering conditions to identify the target conductors with icing problems requiring de-icing operations, i.e., to identify the target conductors that meet the warning triggering conditions. Subsequently, a de-icing plan is generated based on the icing thickness and icing pattern, wherein the de-icing plan includes the adjustable output power of the hot air assembly.

[0044] Optionally, if the icing data of the target conductor meets the early warning triggering conditions, the output power of the hot air assembly is determined based on the icing data of the target conductor and the set de-icing strategy, including: If the icing growth rate in the icing data of the target conductor is greater than the first warning threshold, and / or the icing thickness in the icing data of the target conductor is greater than the second warning threshold, then the icing data of the target conductor meets the warning triggering conditions, and the warning is triggered; the icing thickness is compared with the response threshold of the pre-set multi-level response mechanism to determine the target response for the target conductor, wherein the de-icing strategy includes the multi-level response mechanism; the target response is activated, and the output power of the hot air component is determined according to the icing pattern in the icing data of the target conductor and the set power range under the target response.

[0045] Understandably, the ice thickness or ice thickness growth rate of the target conductor is compared with a warning threshold for alarm processing, instructing relevant personnel to carry out de-icing operations in a timely manner. For example, an alarm is triggered when the predicted ice thickness growth rate exceeds 1mm (first warning threshold) or the ice thickness reaches 3mm (second warning threshold) within one hour, where the warning thresholds include both the first and second warning thresholds. In one embodiment, when the ice thickness reaches 3mm (warning threshold) within one hour, the warning calculation unit immediately activates a local alarm and uploads the warning information to the cloud platform via 4G / BeiDou dual-mode communication. The cloud platform adopts a B / S architecture, supporting real-time display of ice heat maps and de-icing operation status on the web interface, with a historical data storage period of more than one year. Understandably, the intelligent decision-making module also has a self-learning function, which can dynamically optimize the warning threshold based on historical de-icing effects.

[0046] In one embodiment, the early warning computing unit performs real-time analysis of multi-source monitoring data. When the analyzed icing data meets the requirements of icing thickness ≥ 3 mm or icing thickness growth rate ≥ 1 mm per hour, it sends an early warning signal to the cloud platform and activates a local audible and visual alarm.

[0047] In one embodiment, when the icing thickness reaches a 3mm warning threshold, the intelligent decision-making module activates a specific response mechanism by comparing the icing thickness with the response threshold of a pre-set multi-level response mechanism. This determines the target response mechanism for the target conductor, where the de-icing strategy includes a multi-level response mechanism. Subsequently, the target response is activated, and the output power of the hot air assembly is determined based on the icing pattern in the target conductor's icing data and the set power range under the target response. For example, the set power range is 10-20kW. Within this range, different icing patterns correspond to different output power. For instance, if frost is difficult to de-ice, the output power is increased to 20kW, while if rime is easier to de-ice, the output power is set to 10kW. It is understood that the output power of different components within the hot air assembly may vary, and this is not limited here.

[0048] The multi-level response mechanism includes Level 1, Level 2, and Level 3 responses. Level 1 response refers to activating the low-power mode of the hot air component, where the set power range is from the minimum adjustable power of the hot air component to the set power. Level 2 response refers to activating the high-power mode of the hot air component, where the set power range is from the set power to the maximum adjustable power of the hot air component. Level 3 response, based on Level 2 response, simultaneously triggers an alarm in the remote dispatch center to notify relevant personnel to assist in de-icing.

[0049] In one embodiment, the multi-level response mechanism includes a first-level response, a second-level response, and a third-level response. The first-level response (ice thickness of 3-5mm) activates only the low-power mode of the hot air assembly (including the heating element and the blower), with a power range of 10-20kW, where 20kW is the set power and 10kW is the minimum adjustable power of the hot air assembly. The second-level response (ice thickness of 5-10mm) activates the high-power mode, with a power range of 20-100kW, to heat and prepare for anti-icing maintenance, where 100kW is the maximum adjustable power of the hot air assembly, which can be adjusted within the range of 10-100kW. The third-level response (ice thickness of ≥10mm) simultaneously triggers an alarm in the remote dispatch center, requesting manual assistance for de-icing, based on the second-level response.

[0050] S204. Control the hot air assembly to blow heat towards the target wire at the output power, so that the target wire is heated and maintained at the set temperature, so as to at least partially melt the ice on the target wire.

[0051] Understandably, S204 is executed by the adaptive de-icing module. Based on S202 above, the output power of the hot air assembly is dynamically adjusted to raise the temperature of the wire to 2-5℃ (set temperature) using high-intensity hot air, thereby melting and removing at least part of the ice on the wire. In addition, the adaptive de-icing module is also equipped with a temperature feedback sensor, which automatically reduces the power to the heat preservation setting when the surface temperature of the wire reaches 5℃, avoiding damage to the wire caused by overheating.

[0052] The hot air assembly includes a power-adjustable heating element and a power-adjustable blower. The heating element includes multiple heating elements connected in parallel, and the blower includes multiple fans connected in parallel.

[0053] Understandably, the hot air assembly includes a power-adjustable heating element and a power-adjustable blower. In one embodiment, the power-adjustable heating element is a power-adjustable PTC heating element, composed of PTC heating elements arranged in a series, including ten 10kW standard PTC units connected in parallel. On / off control is achieved via IGBT solid-state relays, with a minimum power step of 10kW. Each unit also incorporates a built-in PWM pulse width modulation module with an adjustable duty cycle of 0-100%, coupled with an incremental PID algorithm to achieve 100W-level precision fine-tuning (fine-tuning within a given range). The power-adjustable blower is a power-adjustable blower, consisting of ten 10kW standard blower units connected in parallel. On / off control is achieved via IGBT solid-state switches, with a minimum power step of 10kW, adapting to the zoned coarse-tuning requirements of the PTC heating element. Each unit is equipped with a permanent magnet synchronous motor and a PWM frequency converter, supporting stepless speed regulation from 0-50Hz, with a power adjustment accuracy of ±0.5kW. Combined with PWM pulse control, dynamic matching of heating power and airflow is achieved.

[0054] Optionally, controlling the hot air assembly to blow heat towards the target conductor at the output power includes: The heating element is positioned below the target conductor using a rotating lifting device; at least one heating element is switched on and off using a solid-state relay, and the output power of the heating element is adjusted to a first power level using a pulse width modulation module and incremental algorithm built into the heating element, so that the heating element generates heat; at least one fan is switched on and off using a solid-state switch, and the output power of the fan is adjusted to a second power level using a permanent magnet synchronous motor, frequency converter, and pulse control algorithm mounted on the fan, so that the fan blows out an airflow matching the first power level to direct the heat generated by the heating element toward the target conductor.

[0055] Understandably, the power-adjustable PTC heating element adopts a U-shaped opening design, allowing it to be positioned below the target conductor via a rotating lifting mechanism, for example, 5-10 cm directly below the conductor. This rotating lifting mechanism is driven by dual hydraulic cylinders and has an adjustable range of 0-180°. In one embodiment, the heating element is integrated onto the rotating lifting mechanism, which is mounted on a movable device. In response to a warning trigger operation, the movable device is moved to the working area of ​​the target conductor. The heating element is positioned below the target conductor via the rotating lifting mechanism, while simultaneously adjusting the distance between the blower outlet and the heating element or the target conductor. The heat generated by the heating element is then blown onto the target conductor by the blower. After anti-icing maintenance of the target conductor is completed, the device can be moved to the next conductor for anti-icing maintenance.

[0056] Understandably, the heating element is controlled as follows: On / off control is achieved via a solid-state relay. The pulse width modulation module built into the heating element, combined with an incremental PID algorithm, adjusts the output power within a given range to a first power level, ensuring the heating element generates enough heat to at least partially melt the ice on the conductor. The blower is controlled as follows: On / off control is achieved via a solid-state switch. Variable frequency technology is employed, using a three-phase PWM inverter to adjust the blower's output power to a second power level, achieving dynamic matching between the heating element's output power and the blower's airflow. The second power and the first power may be the same or different.

[0057] Understandably, the power regulation of the hot air assembly is achieved by a power control unit, which is based on an STM32F407 microcontroller. When the wire temperature exceeds 5°C, over-temperature protection is triggered, automatically cutting off the heating power supply.

[0058] Optionally, after controlling the hot air assembly to blow heat towards the target conductor at the output power, the method further includes: Based on the ambient humidity from multi-source monitoring data, the spray interval and spray volume of antifreeze to be sprayed onto the target conductor are determined; after the target conductor is de-iced, antifreeze is uniformly sprayed onto the surface of the target conductor based on the spray interval until the spray volume is reached, so as to form an anti-icing coating of a set thickness on the surface of the target conductor.

[0059] Understandably, after de-icing is completed, the system automatically switches to anti-icing maintenance mode, automatically spraying antifreeze to form an anti-icing coating. Simultaneously, a multi-source monitoring module continuously tracks the conductor's status until the warning is lifted; for example, after 4 hours of continuous monitoring without ice buildup, it returns to standby mode. The anti-icing maintenance mode is executed by an anti-icing maintenance module, which includes an antifreeze storage tank and a metered spraying device. The antifreeze uses environmentally friendly nanofluid materials. The spraying device is linked to the adaptive de-icing module, automatically and uniformly spraying the conductor surface after de-icing to form a 5-10μm thick anti-icing coating, effectively delaying secondary icing. The spray volume and interval of the antifreeze can be dynamically adjusted according to ambient humidity. The system has a built-in ambient humidity linkage logic for antifreeze spray control; for example, when humidity > 85%, the spray volume increases by 30%; when humidity ≤ 60%, the spray interval is 30 minutes / time; and when humidity > 60%, it is shortened to 15 minutes / time, ensuring coating effectiveness.

[0060] In one embodiment, the antifreeze storage tank has a capacity of 5L and uses an electric diaphragm pump to achieve quantitative injection, with a nozzle diameter of 0.5mm and an injection pressure of 0.3MPa.

[0061] This disclosure provides a de-icing method for overhead contact lines using multi-source sensing and adaptive control, fundamentally improving the safety and reliability of railway power supply networks under extreme weather conditions and forming a complete technical closed loop of "precise sensing - intelligent decision-making - efficient execution." First, multiple sensors are deployed on the overhead contact line to form a multi-source sensing network. Utilizing sensor fusion technology and predictive models, real-time monitoring of ice thickness and early prediction of short-term ice accumulation risks are achieved, solving the problem of delayed alarms in related technologies. Second, addressing the high energy consumption of the de-icing process, an adaptive power control mechanism is adopted. This mechanism, based on real-time monitoring data, dynamically calculates and outputs the minimum gradient power required for de-icing through gradient power control and temperature feedback, and combines this with closed-loop adjustment using temperature feedback to maximize the optimal design of de-icing energy efficiency and eliminate potential damage from conductor overheating. Finally, all modules are integrated and linked through a highly reliable wireless communication network, allowing for real-time adjustment of de-icing operation parameters according to environmental changes, significantly improving the system's overall adaptability to complex and variable operating environments.

[0062] Based on the above embodiments, Figure 3This is a flowchart illustrating another de-icing method for multi-source sensing and adaptive control of overhead contact lines provided in this disclosure embodiment, specifically including as follows: Figure 3 The following steps are shown: S301: Multi-source monitoring, which collects monitoring data of the overhead contact line through linear microwave monitoring sensors, infrared thermal imagers and meteorological sensor groups.

[0063] S302: Intelligent early warning, which analyzes monitoring data in real time and triggers an alarm when the predicted ice thickness reaches the warning threshold in the future.

[0064] S303: Adaptive de-icing generates a de-icing scheme based on ice thickness and ice type, and dynamically adjusts the output power of the PCT heating components and blower.

[0065] S304: Anti-icing maintenance. After de-icing is completed, antifreeze is automatically sprayed.

[0066] Understandably, the specific implementation details of S1-S4 can be found in the above embodiments and will not be repeated here.

[0067] Figure 4 This is a schematic diagram of a de-icing device for multi-source sensing and adaptive control of overhead contact lines, provided in an embodiment of this disclosure. The de-icing device for multi-source sensing and adaptive control of overhead contact lines provided in this embodiment can execute the processing flow provided in the embodiments of the de-icing method for multi-source sensing and adaptive control of overhead contact lines, such as... Figure 4 As shown, the de-icing device 400 (hereinafter referred to as de-icing device 400) suitable for multi-source sensing and adaptive control of overhead contact lines includes: The receiving unit 401 is used to receive multi-source monitoring data transmitted by various sensors deployed on the overhead contact line; Prediction unit 402 is used to predict the icing status of at least one section of conductor in the overhead contact system in a future period based on multi-source monitoring data using a pre-trained prediction model, and output icing data. The determining unit 403 is used to determine the output power of the hot air assembly based on the icing data of the target conductor and the set de-icing strategy when the icing data of the target conductor meets the early warning triggering conditions. Control unit 404 is used to control the hot air assembly to blow heat toward the target wire at the output power, so that the target wire is heated and maintained at a set temperature, so as to at least partially melt the ice on the target wire.

[0068] Optionally, the de-icing device 400 includes various sensors such as monitoring sensors deployed on the contact network towers, infrared thermal imagers, and meteorological sensors. The monitoring sensors are used to collect ice thickness data of at least one section of conductor included in the contact network. The infrared thermal imagers are used to monitor the surface temperature distribution data of at least one section of conductor in real time. The meteorological sensors are used to collect environmental data around at least one section of conductor. The environmental data includes at least one of temperature, humidity, wind direction, and wind speed. The multi-source monitoring data includes ice thickness data, surface temperature distribution data, and environmental data.

[0069] Optionally, the prediction model includes a feature extraction layer, an analysis and computation layer, and a type recognition layer.

[0070] Optionally, prediction unit 402 is used for: Texture features of echo signals characterized by ice thickness data in multi-source monitoring data are extracted using a feature extraction layer. By analyzing the surface temperature distribution data and environmental data from texture features and multi-source monitoring data in the computational layer, the icing change trend over time is analyzed, and the icing growth rate of at least one section of the overhead contact line in the future period is obtained. The type identification layer distinguishes the icing pattern of at least one section of the conductor based on multi-source monitoring data; Calculate the icing thickness of at least one section of the conductor in the future period based on the icing growth rate, and generate icing data including icing thickness and / or icing growth rate as well as icing morphology.

[0071] Optionally, the determining unit 403 is used for: If the icing growth rate in the icing data of the target conductor is greater than the first warning threshold, and / or the icing thickness in the icing data of the target conductor is greater than the second warning threshold, then the icing data of the target conductor is determined to meet the warning triggering conditions, and the warning is triggered. By comparing the icing thickness with the response threshold of the pre-set multi-level response mechanism, the target response for the target conductor is determined, wherein the de-icing strategy includes a multi-level response mechanism. Initiate the target response and determine the output power of the hot air assembly based on the icing pattern in the icing data of the target conductor and the set power range under the target response.

[0072] Optionally, the multi-level response mechanism in the determination unit 403 includes a first-level response, a second-level response, and a third-level response. The first-level response refers to starting the low-power mode of the hot air component, where the set power range in the low-power mode is from the minimum adjustable power of the hot air component to the set power. The second-level response refers to starting the high-power mode of the hot air component, where the set power range in the high-power mode is from the set power to the maximum adjustable power of the hot air component. The third-level response, based on the second-level response, synchronously triggers an alarm in the remote dispatch center to notify relevant personnel to assist in de-icing.

[0073] Optionally, the hot air assembly includes a power-adjustable heating element and a power-adjustable blower, wherein the heating element includes multiple heating elements connected in parallel; and the blower includes multiple fans connected in parallel.

[0074] Optionally, the control unit 404 is used for: The heating assembly is positioned below the target conductor using a rotating lifting device; At least one heating element is controlled to switch on and off using a solid-state relay, and the output power of the heating component is adjusted to the first power in the output power by the pulse width modulation module and incremental algorithm built into the heating element, so that the heating component generates heat. At least one fan is controlled to switch on and off by a solid-state switch, and the output power of the blower is adjusted to a second power by the permanent magnet synchronous motor, frequency converter and pulse control algorithm on the blower, so that the blower blows out air volume that matches the first power and blows the heat generated by the heating component to the target wire.

[0075] Optionally, the de-icing device 400 is also used for: Based on the ambient humidity data from multi-source monitoring, determine the spray interval and spray volume of antifreeze to be sprayed onto the target conductor; After the target conductor is de-iced, antifreeze is uniformly sprayed onto the surface of the target conductor according to the spray interval until the spray volume is reached, so as to form an anti-icing coating of a set thickness on the surface of the target conductor.

[0076] Figure 4 The de-icing device shown in the embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and will not be described again here.

[0077] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. See below for details. Figure 5 The diagram illustrates a structural schematic suitable for implementing the electronic device 500 in the embodiments of this disclosure. The electronic device 500 in the embodiments of this disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), wearable electronic devices, etc., as well as fixed terminals such as digital TVs, desktop computers, smart home devices, etc. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0078] like Figure 5As shown, the electronic device 500 may include a processing unit 501 (e.g., a central processing unit, a graphics processor, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503 to implement a de-icing method for multi-source sensing and adaptive control of overhead contact lines, as described in the embodiments of this disclosure. The RAM 503 also stores various programs and data required for the operation of the electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0079] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0080] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts, thereby implementing the de-icing method for multi-source sensing and adaptive control of overhead contact lines as described above. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, it performs the functions defined in the methods of embodiments of this disclosure.

[0081] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0082] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0083] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0084] Optionally, when one or more of the above-described procedures are executed by the electronic device, the electronic device may also perform other steps described in the above embodiments.

[0085] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0086] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0087] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0088] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0089] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0090] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or gateway that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or gateway. Without further limitations, an element defined by the phrase "comprising a contact wire de-icing" does not exclude the presence of other identical elements in the process, method, article, or gateway that includes said element.

[0091] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A de-icing method for overhead contact lines using multi-source sensing and adaptive control, characterized in that, include: Receives multi-source monitoring data transmitted from various sensors deployed on the overhead contact line; The pre-trained prediction model predicts the icing status of at least one section of the overhead contact line in a future period based on the multi-source monitoring data, and outputs the icing data. If the icing data of the target conductor meets the early warning triggering conditions, the output power of the hot air assembly is determined based on the icing data of the target conductor and the set de-icing strategy. The hot air assembly is controlled to blow heat toward the target conductor at the output power, causing the target conductor to heat up and maintain at a set temperature, so as to at least partially melt the ice on the target conductor.

2. The method according to claim 1, characterized in that, The multiple sensors include monitoring sensors, infrared thermal imagers, and meteorological sensors deployed on the catenary towers. The monitoring sensors are used to collect ice thickness data of at least one section of conductor in the catenary. The infrared thermal imagers are used to monitor the surface temperature distribution data of the at least one section of conductor in real time. The meteorological sensors are used to collect environmental data around the at least one section of conductor. The environmental data includes at least one of temperature, humidity, wind direction, and wind speed. The multi-source monitoring data includes the ice thickness data, the surface temperature distribution data, and the environmental data.

3. The method according to claim 1, characterized in that, The prediction model includes a feature extraction layer, an analysis and calculation layer, and a type recognition layer. The pre-trained prediction model predicts the icing condition of at least one section of the overhead contact line in a future time period based on the multi-source monitoring data, and outputs icing data, including: The texture features of the echo signal characterized by ice thickness data in the multi-source monitoring data are extracted through the feature extraction layer. The analysis and calculation layer analyzes the icing trend over time based on the texture features, surface temperature distribution data from the multi-source monitoring data, and environmental data, and obtains the icing growth rate of at least one section of the conductor included in the contact network in the future period. The type identification layer distinguishes the icing morphology of at least one section of the conductor based on the multi-source monitoring data; The ice thickness of the at least one section of the conductor in the future time period is calculated based on the ice growth rate, and ice data including the ice thickness and / or the ice growth rate and the ice morphology is generated.

4. The method according to claim 1, characterized in that, When the icing data of the target conductor meets the early warning triggering conditions, the output power of the hot air assembly is determined based on the icing data of the target conductor and the set de-icing strategy, including: If the icing growth rate in the icing data of the target conductor is greater than the first warning threshold, and / or the icing thickness in the icing data of the target conductor is greater than the second warning threshold, then the icing data of the target conductor is determined to meet the warning triggering conditions, and a warning is triggered. By comparing the ice thickness with the response threshold of a pre-set multi-level response mechanism, a target response is determined for the target conductor, wherein the set de-icing strategy includes the multi-level response mechanism; The target response is initiated, and the output power of the hot air assembly is determined based on the icing pattern in the icing data of the target conductor and the set power range under the target response.

5. The method according to claim 4, characterized in that, The multi-level response mechanism includes a first-level response, a second-level response, and a third-level response. The first-level response refers to activating the low-power mode of the hot air component, where the set power range in the low-power mode is from the minimum adjustable power of the hot air component to the set power. The second-level response refers to activating the high-power mode of the hot air component, where the set power range is from the set power to the maximum adjustable power of the hot air component. The third-level response, based on the second-level response, synchronously triggers an alarm in the remote dispatch center to notify relevant personnel to assist in de-icing.

6. The method according to claim 1, characterized in that, The hot air assembly includes a power-adjustable heating element and a power-adjustable blower. The heating element includes multiple heating plates connected in parallel; the blower includes multiple fans connected in parallel; controlling the hot air assembly to blow heat towards the target conductor at the output power includes: The heating assembly is positioned below the target conductor using a rotating lifting device; At least one heating element is controlled to switch on and off using a solid-state relay, and the output power of the heating component is adjusted to a first power in the output power by the pulse width modulation module and incremental algorithm built into the heating element, so that the heating component generates heat. At least one fan is controlled to switch on and off by a solid-state switch, and the output power of the fan is adjusted to a second power by the permanent magnet synchronous motor, frequency converter and pulse control algorithm mounted on the fan, so that the fan blows out an air volume that matches the first power to blow the heat generated by the heating component toward the target conductor.

7. The method according to claim 1, characterized in that, After controlling the hot air assembly to blow heat toward the target conductor at the output power, the method further includes: Based on the ambient humidity from the multi-source monitoring data, determine the spray interval and spray volume of antifreeze to be sprayed onto the target conductor; After the target conductor is de-iced, antifreeze is uniformly sprayed onto the surface of the target conductor based on the spray interval until the spray amount is reached, so as to form an anti-icing coating of a set thickness on the surface of the target conductor.

8. A de-icing device suitable for multi-source sensing and adaptive control of overhead contact lines, characterized in that, include: The receiving unit is used to receive multi-source monitoring data transmitted by various sensors deployed on the overhead contact line; The prediction unit is used to predict the icing status of at least one section of conductor in the overhead contact system in a future period based on the multi-source monitoring data using a pre-trained prediction model, and outputs the icing data. The determining unit is used to determine the output power of the hot air assembly based on the icing data of the target conductor and the set de-icing strategy when the icing data of the target conductor meets the early warning triggering conditions. A control unit is configured to control the hot air assembly to blow heat toward the target conductor at the output power, thereby raising the temperature of the target conductor and maintaining it at a set temperature to at least partially melt the ice covering the target conductor.

9. An electronic device, characterized in that, include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the de-icing method for multi-source sensing and adaptive control of overhead contact lines as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the de-icing method for multi-source sensing and adaptive control of overhead contact lines as described in any one of claims 1 to 7.

Images