Double-machine cooperative electrified cleaning method and device

Abstract

The invention relates to the technical field of aircrafts, in particular to an electrified cleaning method and device for a high-voltage transmission line, and is used for cleaning the high-voltage transmission line. The method comprises the steps of determining an optimal receiving angle range of a cable through laboratory analogue simulation, obtaining wind speed and wind direction data above and below the cable in real time, establishing a simulation model to simulate changes of working parameters of an unmanned aerial vehicle under different wind speeds and wind directions, and outputting the working parameters of the unmanned aerial vehicle in the optimal receiving angle range to execute cleaning operation. And the cleaned cable is subjected to drying treatment. According to the method, double-machine collaborative operation is adopted, cleaning of the two sides of the cable can be completed through one-time flight, and the cleaning efficiency is greatly improved. Meanwhile, through analogue simulation and real-time data adjustment, effective coverage of the cleaning agent is ensured, generation of condensation or ice crystal effect is reduced, and cleaning quality and safety are improved. The method has remarkable technical advantages and application prospects, and a new solution is provided for electrified cleaning of power equipment.

Description

Technical Field

[0001] The present invention belongs to the technical field of aircraft, and in particular relates to a live cleaning method and device for high-voltage transmission lines. Background Art

[0002] In the field of power equipment maintenance, cleaning operations, especially for high-voltage transmission line components, have always been a vital task. With the continuous growth of electricity demand, it is particularly important to ensure the cleanliness and operating efficiency of power equipment. Most of the existing live cleaning technologies use single-machine operations. For high-voltage lines, only one side of the cable can be cleaned in one cleaning, and the other side needs to be cleaned again according to the route in a second flight, resulting in longer cleaning time and increased operational risks. In addition, unreasonable cleaning can cause condensation or ice crystal effects in local locations of the cable. In windy conditions, the cleaning agent sprayed by the drone will be disturbed by the wind, resulting in failure to maximize coverage of the target cleaning range. Summary of the invention

[0003] The present invention overcomes the shortcomings of the prior art and provides a dual-machine collaborative live cleaning method and device to improve cleaning efficiency and coverage, ensure that no condensation or ice crystal effect will occur during the cleaning process, and enhance the safety of UAV operations.

[0004] To achieve the above object, the technical solution adopted by the present invention is: a dual-machine collaborative live cleaning method, comprising the following steps:

[0005] S1. Conduct cable cleaning simulation in the laboratory, spray the cleaning agent onto the surface of the test cable, and confirm the optimal receiving angle range of the cable [θ min ,θ max ];

[0006] S2. Get the wind speed v above and below the cable w and wind direction w data;

[0007] S3. Establish a simulation model to simulate different wind speeds v w and wind direction w Under the condition, the receiving angle θ and the spray range R are obtained by changing the working parameters of the UAV;

[0008] S4, wind speed v w , wind direction η w and the optimal receiving angle range [θ min ,θ max ] is input into the simulation model, and the output receiving angle θ belongs to the optimal receiving angle range [θ min ,θ max ] within the time limit, and perform dual-machine collaborative live cleaning operations;

[0009] S5, drying the cleaned cables and controlling the flight path of the drone;

[0010] The receiving angle θ refers to the effective angle at which the cleaning agent is received by the cable; the optimal receiving angle range [θ min ,θ max ] is the receiving angle range in which the cable will not produce condensation or ice crystal effect under the same conditions; the UAV working parameters include lateral distance d, longitudinal distance h, nozzle elevation angle α, nozzle flow rate Q, nozzle flow velocity V, and nozzle pressure P; the spray range R is the maximum horizontal distance that the cleaning agent can reach.

[0011] In a preferred embodiment of the present invention, in step S1, the cleaning agent is sprayed on the cable sample in a simulated manner, and the optimal receiving angle range [θ min ,θ max ].

[0012] In a preferred embodiment of the present invention, in step S2, the wind speed v above and below the cable is collected. w and wind direction w After the data is collected, it is determined whether the flight conditions of the drone are met. If so, the drone will take off for cleaning operations. If not, it will not take off at all.

[0013] In a preferred embodiment of the present invention, in step S3, based on the electromagnetic interference of the live cable to the drone, the safe operating distance S of the drone is determined. min .

[0014] In a preferred embodiment of the present invention, in step S3, the setting of the simulation model includes data collection and preprocessing and physical formula preprocessing; data collection and preprocessing are used to collect historical data and transform the historical data into data features required to generate the model; physical formula preprocessing is used to estimate and generate initial working parameters.

[0015] In a preferred embodiment of the present invention, the simulation model in step S3 is constructed using a multilayer perceptron, the simulation model is trained based on historical data, and the simulation model is optimized using Bayesian optimization.

[0016] In a preferred embodiment of the present invention, in step S4, after the drone cleans the cable surface, the actual coverage of the cleaning agent is collected, and the accuracy of the model is evaluated based on the mean square error, root mean square error and mean absolute error.

[0017] In a preferred embodiment of the present invention, in step S4, the dual-machine collaborative live cleaning operation is to use a group of two drones to perform cleaning operations on the uninterrupted power cables; wherein the two drones are located in the radial direction of the cable and are symmetrically distributed around the cable.

[0018] The present invention also provides a dual-machine collaborative live cleaning device for implementing the above method, comprising two drones and a ground workstation. The two drones are located in the radial direction of the cable and are symmetrically distributed with the cable as the center. The ground control station is connected to the drone signal to monitor the drone status, control the cleaning operation process, and receive and process data.

[0019] In a preferred embodiment of the present invention, the drone includes a fuselage and a cleaning mechanism, a sensor mechanism, a drying mechanism and a control system arranged on the fuselage;

[0020] The cleaning mechanism includes a nozzle, a spray pump, and a detergent storage tank, and is used for spraying the detergent;

[0021] The sensor mechanism includes a wind speed sensor, a wind direction sensor, and a distance sensor, which are used to obtain real-time environmental data;

[0022] The drying mechanism is used to dry the cables after cleaning;

[0023] The control system includes a data processor and a flight controller, which are used to receive sensor data, perform cleaning operations and control the flight of the drone.

[0024] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0025] (1) The present invention provides a dual-machine collaborative live cleaning method and device, which improves the cleaning efficiency and safety of power equipment such as high-voltage transmission lines and insulators. The present invention achieves effective coverage and rapid drying of the cleaning agent and reduces operational risks through simulation, real-time environmental data acquisition, model optimization and collaborative operation.

[0026] (2) The present invention uses dual-machine collaborative operation, determines the optimal receiving angle range through simulation, and adjusts the drone working parameters according to real-time wind speed and wind direction data. The dual-machine collaborative operation can clean both sides of the cable in one flight, greatly improving the cleaning efficiency. At the same time, simulation and real-time data adjustment ensure effective coverage of the cleaning agent and reduce the number of repeated operations. Compared with the single-machine operation in the prior art, the present invention reduces the time of repeated operations and reduces the operating costs, thereby improving the overall cleaning efficiency.

[0027] (3) The present invention determines the optimal receiving angle range through simulation experiments to avoid the generation of condensation or ice crystal effects, and sets a safe operating distance to ensure the stable operation of the UAV under electromagnetic interference. The determination of the optimal receiving angle range allows the cleaning agent to cover the cable surface more evenly, avoiding the generation of local condensation or ice crystal effects. At the same time, the setting of the safe operating distance and the enhancement of the anti-interference ability of the UAV ensure the stable operation of the UAV near high-voltage transmission lines. Compared with the condensation or ice crystal effects caused by the direct cleaning method in the prior art, the present invention significantly improves the cleaning quality and safety.

[0028] (4) The present invention determines the optimal receiving angle range through simulation to ensure effective coverage of the detergent and avoid the generation of condensation or ice crystal effects, and adjusts the UAV working parameters according to real-time wind speed and wind direction data to achieve dual-machine collaborative operation and improve cleaning efficiency. This combination not only improves the cleaning efficiency and coverage, but also ensures that no condensation or ice crystal effects will occur during the cleaning process, and enhances the safety of UAV operations. Overall, the present invention provides an efficient, safe and reliable method for live cleaning of power equipment, which has significant technical advantages and application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 It is a flow chart of the dual-machine collaborative live cleaning method provided by the present invention;

[0031] Figure 2 It is a structural schematic diagram of a dual-machine cooperative live cleaning device provided by the present invention;

[0032] Figure 3 is a schematic diagram of the structure of a drone in a preferred embodiment of the present invention;

[0033] In the figure: 100, drone; 200, ground workstation; 300, cable; 1, cleaning mechanism; 2, sensor mechanism; 3, drying mechanism; 11, nozzle; 12, jet pump; 13, detergent tank; 21, wind speed sensor; 22, wind direction sensor; 23, distance sensor. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0036] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the scope of protection of the present application. In addition, the terms "first", "second", etc. are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, features defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the invention, unless otherwise specified, "multiple" means two or more.

[0037] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0038] Application Overview

[0039] Existing technologies mainly rely on a single-machine operation mode for live cleaning. In this mode, drones or cleaning equipment can usually only clean one side of the cable. After cleaning one side, they need to adjust their position or rearrange the flight to clean the other side. This operation method is not only inefficient, but also increases operational risks and costs. In addition, since it is impossible to accurately control the spray angle and coverage of the cleaning agent, unreasonable cleaning operations may also cause condensation or ice crystal effects in local locations of the cable, further affecting the safe operation of power equipment.

[0040] In actual operation, the impact of environmental factors such as wind speed and direction on cleaning operations cannot be ignored. Traditional cleaning methods often lack the ability to monitor and dynamically adjust environmental factors in real time, resulting in the cleaning agent being unable to accurately cover the target area under the influence of wind, reducing the cleaning effect.

[0041] Exemplary Methods

[0042] like Figure 1 As shown, a dual-machine collaborative live cleaning method includes the following steps:

[0043] S1. Conduct cable cleaning simulation in the laboratory, spray the cleaning agent onto the surface of the test cable, and confirm the optimal receiving angle range of the cable [θ min ,θ max ];

[0044] S2. Get the wind speed v above and below the cable w and wind direction w data;

[0045] S3. Establish a simulation model to simulate different wind speeds v w and wind direction w Under the condition, the receiving angle θ and the spray range R are obtained by changing the working parameters of the UAV;

[0046] S4, wind speed v w , wind direction η w and the optimal receiving angle range [θ min ,θ max ] is input into the simulation model, and the output receiving angle θ belongs to the optimal receiving angle range [θ min ,θ max ] within the time limit, and perform dual-machine collaborative live cleaning operations;

[0047] S5, drying the cleaned cables and controlling the flight path of the drone;

[0048] The receiving angle θ refers to the effective angle at which the cleaning agent is received by the cable; the optimal receiving angle range [θ min ,θ max] is the receiving angle range in which the cable will not produce condensation or ice crystal effect under the same conditions; the UAV working parameters include lateral distance d, longitudinal distance h, nozzle elevation angle α, nozzle flow rate Q, nozzle flow velocity V, and nozzle pressure P; the spray range R is the maximum horizontal distance that the cleaning agent can reach.

[0049] Below, each step will be described in detail.

[0050] In step S1, the cleaning agent is sprayed on the cable sample in a simulated manner, and the optimal receiving angle range [θ min ,θ max ].

[0051] In a specific embodiment, a test cable is prepared and hung, a cleaning agent spraying device is set, a high-speed camera is installed to record the spraying process, a measuring tool is used to measure the cleaning agent coverage area and thickness, an infrared device is used to monitor the amount of condensation and ice crystals on the cable surface, a condensation index and an ice crystal index are generated based on the amount of condensation and ice crystals, and the time required for the cable to go from wet to completely dry is recorded. To ensure the accuracy of the data, multiple tests are required and the average value is taken.

[0052] In this embodiment, the cable has a diameter of 10 mm, a length of 1 m, and a standard smooth surface; the ambient temperature is 20°C, the humidity is 50% RH, and the simulated wind speed is 2 m / s; the receiving angle range is 0° to 90°, and a data point is divided every 5°; a total of three rounds of tests are conducted, and the data generated by taking the average value of the three tests is shown in Table 1:

[0053] Table 1 Simulation experiment data table

[0054]

[0055]

[0056] Coverage area (cm 2 ) indicates the area of ​​the cleaning agent covering the cable surface, the covering thickness (mm) indicates the average thickness of the cleaning agent on the cable surface, and the condensation index (CI) is an indicator to measure the degree of condensation (water droplets) formed on the cable surface. The ice crystal index (ICI) is an indicator to measure the degree of ice crystals formed on the cable surface. The drying time (min) refers to the time required for the cleaning agent to go from a wet state to completely dry.

[0057] Taking the above into consideration, the optimal receiving angle in this embodiment is 15° to 35°.

[0058] In step S2, the wind speed v above and below the cable is collected w and wind direction wAfter the data is collected, it is determined whether the flight conditions of the drone are met. If so, the drone will take off for cleaning operations. If not, it will not take off at all.

[0059] In a specific embodiment, the maximum wind speed allowed for the drone to fly is 10 m / s (about 36 km / h or 22 mph), and the minimum wind speed allowed for the drone to fly is 1 m / s (about 3.6 km / h or 2.2 mph).

[0060] It should be noted that although there is no clear minimum wind speed limit, in the case of no wind at all, the drone may be affected by other small air currents, so there is at least a slight wind speed to help the drone stay stable.

[0061] In addition, since side winds have a greater impact on drones, the side winds allowed for takeoff and landing of drones should not exceed 5m / s (about 18km / h or 11mph) to ensure that the drone can take off and land smoothly.

[0062] In step S3, based on the electromagnetic interference of the cable to the drone, the safe operating distance S of the drone is determined. min The steps to determine the safe operating distance of a drone include: evaluating cable characteristics, evaluating the drone's anti-interference capabilities, referring to relevant standards, performing electromagnetic field measurements, and determining a safe distance.

[0063] In a specific embodiment, a cleaning operation is performed on a high-voltage transmission line, where the current intensity of the high-voltage transmission line is 1000A and the frequency is 50Hz. The specific steps for determining the safe operating distance of the drone are as follows:

[0064] T1. Evaluate cable characteristics: Confirm that the cable type is a high-voltage transmission line, the current intensity is 1000A, and the frequency is 50Hz;

[0065] T2. Evaluate the anti-interference capability of the drone: According to the drone model and manufacturer's recommendations, the maximum magnetic field strength that the drone can withstand is 10μT, and the maximum electric field strength is 1kV / m;

[0066] T3. Reference to relevant standards: Reference to international standards IEEE Std C95.6-2002 and CENELEC EN 50169-2:2005;

[0067] T4. Conduct electromagnetic field measurement: Use an electromagnetic field intensity meter to measure the electromagnetic field intensity around the cable at different distances. The measurement results are shown in Table 2:

[0068] Table 2 Electromagnetic field measurement results

[0069] Distance(m) Magnetic field strength (μT) Electric field strength (V / m) 0.5 80 2000 1.0 20 500 2.0 5 100 3.0 2 50 4.0 1 20

[0070] T5. Determine the safe distance: From the measurement data, it can be seen that at a distance of 2 meters, the magnetic field strength is 5μT and the electric field strength is 100V / m, both of which are lower than the maximum allowable value of the drone. At a distance of 3 meters and above, the magnetic field strength is 2μT and the electric field strength is 50V / m, further reducing the risk of electromagnetic interference.

[0071] Based on the above measurements and analysis, the safe operating distance between drones and high-voltage transmission lines should be at least 2 meters. In order to further improve safety and leave a certain margin, the safe operating distance is set to 3 meters, and the anti-interference ability of drones is enhanced by improving the built-in shielding and filters.

[0072] In step S3, the setting of the simulation model includes data collection and preprocessing and physical formula preprocessing.

[0073] Data collection and preprocessing are used to collect a large amount of historical data, including wind speed, wind direction, drone operating parameters and corresponding cleaning effects, and then standardize or normalize the above data to convert the historical data into the data features required by the model.

[0074] Physical formula preprocessing includes making preliminary estimates of various parameters based on physical formulas and generating a set of initial working parameters. The required estimation formulas include:

[0075] Horizontal distance d = (v0 cosα + v w cos(η w -α))·t; where d is the lateral distance, i.e. the horizontal distance between the cleaning agent injection point and the target point; v0 is the velocity at the nozzle outlet, i.e. the injection velocity; α is the nozzle elevation angle, i.e. the angle between the nozzle and the horizontal line; v w is the wind speed; η w is the wind direction, that is, the angle relative to the nozzle direction; t is the injection time, that is, the time required for the detergent to reach the target from the nozzle outlet.

[0076] Longitudinal distance Where h is the longitudinal distance, i.e. the vertical distance between the detergent injection point and the target point; g is the gravitational acceleration.

[0077] Acceptance Angle Where θ is the receiving angle, i.e. the effective angle at which the cleaning agent is received by the cable; Δh is the effect of wind on the vertical distance, which can be estimated by the simplified formula: Δh = k h ·v w ·sin(η w -α), where k h is an empirical coefficient used to adjust the effect of wind on vertical distance; Δd ​​is the effect of wind on horizontal distance, which can be estimated by a simplified formula: Δd = k d ·vw ·cos(η w -α), where k d is an empirical coefficient used to adjust the effect of wind on lateral distance.

[0078] The relationship between nozzle flow rate and flow velocity is Q=A·V; where Q is the nozzle flow rate, that is, the volume of detergent passing through the nozzle per unit time; A is the nozzle cross-sectional area, that is, the area of ​​the nozzle opening; V is the nozzle flow velocity, that is, the speed at which the detergent passes through the nozzle.

[0079] Nozzle pressure Where P is the nozzle pressure, that is, the pressure at the nozzle outlet; P atm is atmospheric pressure; ρ is the density of the detergent.

[0080] Spray range Where R is the spray range, that is, the maximum horizontal distance that the cleaning agent can reach.

[0081] Corrected injection range Among them, R * is the corrected injection range; k R It is an empirical coefficient used to adjust the effect of wind on the spray range.

[0082] Injection time Where t is the injection time, which is the time required for the cleaning agent to reach the target point from the nozzle outlet.

[0083] In a specific embodiment, 1,000 sets of historical data are collected, each set of data includes wind speed, wind direction, nozzle elevation, nozzle flow, nozzle flow rate, nozzle pressure, lateral distance, longitudinal distance, receiving angle and cleaning effect, a multi-layer perceptron (MLP) model is constructed, and Bayesian optimization is used to find the best hyperparameter combination.

[0084] According to the actual environmental data, the wind speed v w is 5m / s, wind direction θ w is 45°, atmospheric pressure P atm The initial parameters of the UAV operation include nozzle flow rate v0 of 20m / s, nozzle elevation angle α of 30°, detergent density of 1000kg / m3, and empirical coefficient k h is 0.1, k d is 0.1, k R is 0.2, and the optimal range of the receiving angle is 15° to 35°.

[0085] The above data are input into the model and the initial data are calculated according to the estimation formula: the nozzle elevation angle α is 30.00°, the receiving angle θ is 26.61°, the lateral distance d is 37.14m, the longitudinal distance h is 18.53m, the injection time t is 2.04 seconds, the nozzle pressure P is 121325.00Pa, the injection range R is 41.56m, and the corrected injection range is 45.88m.

[0086] The working parameters obtained by model optimization are: nozzle elevation angle α is 35.00°, receiving angle θ is 27.00°, lateral distance d is 38.00m, longitudinal distance h is 20.00m, injection time t is 2.20 seconds, nozzle pressure P is 121325.00Pa, injection range R is 45.00m, and the corrected injection range is 50.00m.

[0087] The initial data and model optimization data are shown in Table 3:

[0088] Table 3 Summary of initial data and model optimization data

[0089] parameter Initial value (30° elevation angle) After optimization (35° elevation angle) Spray time(s) 2.04 2.20 Horizontal distance (m) 37.14 38.00 Longitudinal distance (m) 18.53 20.00 Acceptance angle (°) 26.61 27.00 Nozzle pressure (Pa) 121325.00 121325.00 Spray range(m) 41.56 45.00 Corrected spray range (m) 45.88 50.00

[0090] By increasing the nozzle elevation angle to 35°, the optimized spray range (45.00 m) is larger than the initial value (41.56 m), while keeping the receiving angle within the optimal range.

[0091] In step S4, after the drone cleans the cable surface, the actual cleaning agent coverage is collected, and the mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) are used to evaluate the accuracy of the model.

[0092] In a specific embodiment, the cleaning conditions of 10 data points are collected, as shown in Table 4:

[0093] Table 4 Comparison of actual injection coverage and the corrected injection coverage predicted by the model

[0094]

[0095]

[0096] Calculate mean square error In this embodiment, MSE=0.058 m2.

[0097] Calculate the root mean square error In this embodiment, RSEM=0.241m.

[0098] Calculate mean absolute error In this embodiment, MAE=0.22m.

[0099] The values ​​of MSE, RMSE and MAE of the above indicators are small, indicating that the deviation between the model prediction value and the actual value is small, reflecting that the model has a strong prediction ability and can better reflect the actual injection coverage.

[0100] In step S4, the dual-drone collaborative live cleaning operation is to use a group of two drones to clean the uninterrupted power cables; wherein the two drones are located in the radial direction of the cable and are symmetrically distributed around the cable.

[0101] In step S5, the method of drying the cleaned cable includes one or more of natural air drying, compressed air drying and infrared drying.

[0102] The drone's flight mode is autonomous navigation. Based on the location of the current cleaning point, the coverage of the detergent, and the spray range of the next cleaning point, the drone autonomously plans and executes the flight path.

[0103] Exemplary Systems

[0104] like Figure 2 As shown, a dual-machine cooperative live cleaning device is used to implement the above method, including two drones 100 and a ground workstation 200. The two drones 100 are located in the radial direction of the cable 300 and are symmetrically distributed with the cable 300 as the center. The ground control station 200 is connected to the drone 100 by signal, and is used to monitor the status of the drone 100, control the cleaning operation process, and receive and process data.

[0105] like Figure 3 As shown, in a specific embodiment, the drone includes a fuselage and a cleaning mechanism 1, a sensor mechanism 2, a drying mechanism 3 and a control system arranged on the fuselage.

[0106] The cleaning mechanism 1 includes a nozzle 11, a jet pump 12, and a detergent storage tank 13, and is used to spray the detergent;

[0107] The sensor mechanism 2 includes a wind speed sensor 21, a wind direction sensor 22 and a distance sensor 23, which are used to obtain real-time environmental data;

[0108] The drying mechanism 3 is used to dry the cleaned cables;

[0109] The control system includes a data processor and a flight controller, which are used to receive sensor data, perform cleaning operations and control the flight of the drone.

[0110] The above is based on the ideal embodiment of the present invention. Through the above description, relevant personnel can make various changes and modifications without departing from the technical concept of the present invention. The technical scope of the present invention is not limited to the content in the specification, and the technical scope must be determined according to the scope of the claims.

Claims

1. A dual-machine collaborative live cleaning method, characterized in that: The following steps are involved: S1. Conduct cable cleaning simulation in the laboratory, spray the cleaning agent onto the surface of the test cable, and confirm the optimal receiving angle range of the cable [θ min ,θ max ]; S2. Get the wind speed v above and below the cable w and wind direction w data; S3. Establish a simulation model to simulate different wind speeds v w and wind direction w Under the condition, the receiving angle θ and the spray range R are obtained by changing the working parameters of the UAV; S4, wind speed v w , wind direction η w and the optimal receiving angle range [θ min ,θ max ] is input into the simulation model, and the output receiving angle θ belongs to the optimal receiving angle range [θ min ,θ max ] within the time limit, and perform dual-machine collaborative live cleaning operations; S5, drying the cleaned cables and controlling the flight path of the drone; The receiving angle θ refers to the effective angle at which the cleaning agent is received by the cable; the optimal receiving angle range [θ min ,θ max ] is the receiving angle range in which the cable will not produce condensation or ice crystal effect under the same conditions; the UAV working parameters include lateral distance d, longitudinal distance h, nozzle elevation angle α, nozzle flow rate Q, nozzle flow velocity V, and nozzle pressure P; the spray range R is the maximum horizontal distance that the cleaning agent can reach.

2. The dual-machine collaborative live cleaning method according to claim 1 is characterized in that: In step S1, the cleaning agent is sprayed on the cable sample in a simulated manner, and the optimal receiving angle range [θ min ,θ max ].

3. The dual-machine collaborative live cleaning method according to claim 2 is characterized in that: In step S2, the wind speed v above and below the cable is collected w and wind direction w After the data is collected, it is determined whether the flight conditions of the drone are met. If so, the drone will take off for cleaning operations. If not, it will not take off at all.

4. The dual-machine collaborative live cleaning method according to claim 3 is characterized in that: In step S3, based on the electromagnetic interference of the live cables to the drone, the safe operating distance S of the drone is determined. min .

5. The dual-machine coordinated live cleaning method according to claim 4 is characterized in that: In step S3, the setting of the simulation model includes data collection and preprocessing and physical formula preprocessing; data collection and preprocessing are used to collect historical data and transform the historical data into data features required by the model; Physical formula preprocessing is used to estimate and generate initial operating parameters.

6. The dual-machine collaborative live cleaning method according to claim 5 is characterized in that: The simulation model in step S3 is constructed using a multilayer perceptron, the simulation model is trained based on historical data, and the simulation model is optimized using Bayesian optimization.

7. The dual-machine coordinated live cleaning method according to claim 6 is characterized in that: In step S4, after the drone cleans the cable surface, the actual coverage of the cleaning agent is collected, and the accuracy of the model is evaluated based on the mean square error, root mean square error, and mean absolute error.

8. The dual-machine collaborative live cleaning method according to claim 1, characterized in that: In step S4, the dual-machine collaborative live cleaning operation is to use a group of two drones to clean the uninterrupted power cable; wherein the two drones are located in the radial direction of the cable and are symmetrically distributed with the cable as the center.

9. A dual-machine coordinated live cleaning device, based on the method described in any one of claims 1 to 8, characterized in that: It includes two drones and a ground workstation; the two drones are located in the radial direction of the cable and are symmetrically distributed with the cable as the center, and are used to perform cleaning operations; the ground control station is connected to the drone signal to monitor the drone status, control the cleaning operation process, and receive and process data.

10. The dual-machine cooperative live cleaning device according to claim 9, characterized in that: The drone includes a fuselage and a cleaning mechanism, a sensor mechanism, a drying mechanism and a control system arranged on the fuselage; The cleaning mechanism includes a spray head, a spray pump, and a detergent storage tank, and is used to spray the detergent; The sensor mechanism includes a wind speed sensor, a wind direction sensor and a distance sensor, which are used to obtain real-time environmental data; The drying mechanism is used to dry the cleaned cables; The control system includes a data processor and a flight controller, which are used to receive sensor data, perform cleaning operations and control the flight of the drone.

Images