Unmanned aerial vehicle line hanging method based on safe distance detection and related device

Through the drone line hanging method based on safe distance detection, combined with laser distance measurement of RGB images and LSTM models, and combined with real-time meteorological information to adjust the flight status, the problems of inefficiency and high safety risks of traditional line hanging methods are solved, and high efficiency is achieved , safe wire hang operation.

CN118962704APending Publication Date: 2024-11-15GUANGDONG YUEDIANKE TESTING TECH CO LTD
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202411030532.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-30
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The traditional X-ray detection drone wiring hanging method is inefficient and has a large safety risk, which cannot effectively improve wiring hanging efficiency and ensure safety of wiring hanging.

Method used

The drone line hanging method based on safe distance detection is adopted. By combining the coarse positioning of RGB images and the laser distance measurement of the LSTM model, and adjusting the flight status of the drone with real-time meteorological information to ensure line hanging operation within a safe distance , use ultraviolet images to monitor the discharge status of the line in real time to avoid collision risks.

Benefits of technology

It improves the efficiency and accuracy of hanging lines, reduces safety risks, enhances the safety and flexibility of high-altitude operations, and prevents the occurrence of power accidents.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118962704A_ABST
    Figure CN118962704A_ABST
Patent Text Reader

Abstract

The invention provides an unmanned aerial vehicle line hanging method based on safe distance detection and a related device, and belongs to the technical field of unmanned aerial vehicle operation. According to the method, high-precision recognition of the position of the power transmission overhead line is realized by combining coarse positioning of an RGB image and laser ranging precise positioning of an LSTM model, and then a safe distance is kept when an unmanned aerial vehicle approaches the power transmission overhead line through fusion analysis of precise laser ranging and an ultraviolet image, so that the collision risk is effectively avoided. Before wire hanging operation, the ultraviolet imaging technology is further utilized to monitor the discharge state of the power transmission line in real time, and electric power accidents are prevented. Finally, the flight strategy of the unmanned aerial vehicle is dynamically adjusted according to the real-time meteorological information, it is ensured that line hanging operation is executed under the optimal condition, and the flexibility and adaptability of operation are enhanced. According to the invention, real-time data analysis is carried out by using an artificial intelligence algorithm and a high-precision sensor, so that the application efficiency and safety of the unmanned aerial vehicle in the field of power inspection and maintenance can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of unmanned aerial vehicle operation, and in particular relates to a method for hanging a line on an unmanned aerial vehicle based on safety distance detection and a related device. Background Art

[0002] X-ray inspection is an effective way to detect defects in tension clamps of overhead power transmission lines. Traditional X-ray inspection of tension clamps requires power outage and tower climbing. X-ray live-line inspection drones use drones to carry inspection equipment and directly contact live-line clamps, which is more convenient than power outage inspection.

[0003] At present, most X-ray inspection drones use the method of pilots controlling the drones to hang the lines. This method is not only inefficient, but also has great safety risks. Therefore, how to improve the efficiency of drone hanging lines and develop an efficient and safe X-ray inspection drone hanging line method and device is an urgent problem to be solved by those skilled in the art. Summary of the invention

[0004] In view of this, the present invention aims to provide a drone hanging line method and related devices based on safety distance detection, which are used to fill the technical gap of safety distance testing of traditional manual hanging line methods, reduce drone hanging line accidents, improve the efficiency of drone hanging line, and ensure hanging line safety.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides a method for hanging a drone line based on safety distance detection, comprising the following steps:

[0007] Control the X-ray inspection drone to drive toward the overhead transmission line and collect RGB images, ultraviolet images and real-time meteorological information of the overhead transmission line;

[0008] Use image recognition algorithm to roughly locate the line position on RGB image;

[0009] Within the coarse positioning range, the real-time laser scanning data sequence is obtained by the UAV and the laser ranging data is obtained by using the pre-trained LSTM model. The LSTM model is trained using the laser scanning data sequence and meteorological information and is used to determine the model of the laser ranging data.

[0010] Based on the laser ranging data, the X-ray inspection drone is precisely positioned and controlled to approach the overhead transmission line. The discharge status of the overhead transmission line is detected in real time using ultraviolet images. When the overhead transmission line is detected to be discharged, the relative position of the X-ray inspection drone and the overhead transmission line is recorded based on the image recognition results and laser ranging data to obtain the safe distance when hanging the line.

[0011] The flight status of the drone is adjusted in combination with real-time meteorological information, and the transmission line hanging operation is carried out under the premise that there is no discharge in the overhead transmission line and the safety distance meets the requirements.

[0012] Furthermore, the real-time laser scanning data sequence is obtained by the UAV and the laser ranging data is obtained using the pre-trained LSTM model, including:

[0013] Control the X-ray inspection drone and the overhead power transmission line to be in a level state that meets the approximate level requirements;

[0014] Under the condition of horizontal state, adjust the angle of X-ray inspection drone to obtain real-time laser scanning data sequence and real-time meteorological information;

[0015] After preprocessing, the real-time laser scanning data sequence and real-time meteorological information are input into the pre-established LSTM model to obtain the distance information between the UAV and the overhead transmission line.

[0016] Furthermore, the establishment process of the LSTM model is:

[0017] Obtain the historical laser scanning data sequence and historical meteorological information of the X-ray detection drone, and mark the real location information corresponding to the drone, and use the historical laser scanning data sequence, historical meteorological information and corresponding real location information as training data;

[0018] Establish an LSTM network structure including an LSTM layer and a fully connected layer as the model to be trained;

[0019] The training data is preprocessed, and the preprocessed historical laser scanning data sequence and historical meteorological information are used as input. The preprocessed real position information is used as the supervised learning target to train the training model to obtain the LSTM model.

[0020] Furthermore, the training model is trained, including:

[0021] Input the preprocessed training data, extract features through the LSTM layer, and then get the output through the fully connected layer;

[0022] Select a loss function based on the task type to calculate the error between the predicted position information output by the model to be trained and the labeled real position information; the task type is a regression task or a classification task, which is used to obtain the coordinate value or location category of the overhead transmission line respectively;

[0023] The weights of the model to be trained are updated through the optimization algorithm to minimize the loss and obtain the LSTM model.

[0024] Furthermore, when the task type is a regression task or a classification task, the output of the corresponding fully connected layer is determined according to the following formula:

[0025] Returning mission:

[0026] position=W p ·h t +b p ;

[0027] Among them, position is the predicted transmission overhead line coordinate value; W p and b p are the weights and biases of the fully connected layer; h t is the hidden state of the current moment output by the LSTM layer;

[0028] Classification Task:

[0029] output_logits = W c ·h t +b c ;

[0030] predicted_class=softmax(output_logits);

[0031] Where: output_logits is the unnormalized output; predicted_class is the normalized predicted category probability distribution; softmax represents the softmax activation function, which is used to convert the output into a probability distribution, W c are the weights of the fully connected layer.

[0032] Furthermore, when performing the transmission line hanging operation, whether to perform the hanging operation is determined according to the following formula:

[0033]

[0034] Wherein, Linehanging(·) represents the line-hanging operation judgment function with RGB image, ultraviolet image UV, meteorological information W and laser scanning data sequence L as input. When it is 1, it means that the line-hanging operation is performed, and when it is 0, it means that the line-hanging operation is not performed. Positioning(·) represents the positioning process, Image(RGB) represents the coarse positioning process, LSTM(L,W) represents the fine positioning process, Image(UV) represents the discharge detection process, and AdjustFlight(W) represents the flight state adjustment process.

[0035] Furthermore, the preprocessing process includes: noise reduction and normalization.

[0036] In a second aspect, the present invention provides a drone wire hanging device based on safety distance detection, comprising:

[0037] The information acquisition module is used to control the X-ray inspection drone to drive toward the overhead transmission line and collect RGB images, ultraviolet images and real-time meteorological information of the overhead transmission line;

[0038] An image recognition module is used to roughly locate the line position of the RGB image using an image recognition algorithm;

[0039] The laser positioning module is used to obtain real-time laser scanning data sequences through the UAV within the rough positioning range and obtain laser ranging data using a pre-trained LSTM model. The LSTM model is trained using the laser scanning data sequence and meteorological information and is used to determine the model for laser ranging data.

[0040] The discharge detection module is used to perform precise positioning based on laser ranging data, and control the X-ray detection drone to approach the overhead transmission line, and use ultraviolet images to detect the discharge status of the overhead transmission line in real time. When the overhead transmission line is detected to be discharged, the relative position of the X-ray detection drone and the overhead transmission line is recorded based on the image recognition result and laser ranging data to obtain the safe distance when hanging the line;

[0041] The control module is used to adjust the flight status of the UAV in combination with real-time meteorological information, and perform transmission line hanging operations on the premise that there is no discharge in the transmission overhead line and the safety distance meets the requirements.

[0042] Accordingly, the present invention also provides a computer device, the device comprising a processor and a memory:

[0043] The memory is used to store the computer program and send the instructions of the computer program to the processor;

[0044] The processor executes a method for hanging a line of an X-ray detection drone according to the instructions of the computer program as described in the first aspect.

[0045] Correspondingly, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for hanging a line of an X-ray detection drone as described in the first aspect is implemented.

[0046] In summary, the present invention provides a method and related device for hanging a line of a UAV based on safety distance detection. First, by combining the rough positioning of RGB images with the precise positioning of laser ranging of LSTM model, high-precision identification of the position of overhead transmission lines is achieved, and the operation efficiency and accuracy are improved. Then, by the fusion analysis of precise laser ranging and ultraviolet images, it is ensured that the UAV maintains a safe distance when approaching the overhead transmission line, effectively avoiding the risk of collision and improving the safety of high-altitude operations. Before the hanging line operation, ultraviolet imaging technology is further used to monitor the discharge state of the transmission line in real time, so that a response can be made at the first time when safety hazards are discovered to prevent the occurrence of power accidents. Finally, the flight strategy of the UAV is dynamically adjusted according to real-time meteorological information to ensure that the hanging line operation is performed under the best conditions, thereby enhancing the flexibility and adaptability of the operation. The present invention can improve the efficiency and safety of the application of UAVs in the field of power inspection and maintenance by using artificial intelligence algorithms and high-precision sensors for real-time data analysis. The existing method of hanging lines of UAVs controlled by pilots is solved, which has the problems of low efficiency and high safety risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] 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 will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 A schematic diagram of a flow chart of a drone line hanging method based on safety distance detection provided by an embodiment of the present invention;

[0049] Figure 2 A schematic diagram of the structure of a drone wire hanging device based on safety distance detection provided by an embodiment of the present invention;

[0050] Figure 3 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below 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.

[0052] See also Figure 1This embodiment provides a method for drone line hanging based on safety distance detection, comprising the following steps:

[0053] S1: Control the X-ray inspection drone to drive towards the overhead transmission line and collect RGB images, ultraviolet images and real-time meteorological information of the overhead transmission line.

[0054] It should be noted that this step first uses the autonomous navigation function of the drone to accurately guide it to the vicinity of the overhead transmission line. In addition to the X-ray detection equipment, the X-ray detection drone is also equipped with a color camera, ultraviolet imaging equipment and high-precision sensors. The color camera is used to collect RGB images of the overhead transmission line, and the ultraviolet imaging equipment is used to collect ultraviolet images of the overhead transmission line. The ultraviolet image is used to determine whether the overhead transmission line is discharged. The high-precision sensor is used to collect real-time meteorological information, such as wind speed and wind direction information.

[0055] S2: Use image recognition algorithm to roughly locate the line position in RGB image.

[0056] It should be noted that the collected image data is processed by an image recognition algorithm to identify and preliminarily locate key features of the transmission line, such as conductors, towers, insulators, etc. This step quickly determines the approximate location of the line and provides a range reference for subsequent precise positioning. The image recognition algorithm can use deep learning models such as RCNN, YOLO, or other neural network algorithms, and the present invention does not limit this.

[0057] S3: Within the coarse positioning range, the real-time laser scanning data sequence is obtained through the UAV and the laser ranging data is obtained using the pre-trained LSTM model. The LSTM model is trained using the laser scanning data sequence and meteorological information and is used to determine the model of the laser ranging data.

[0058] It should be noted that laser ranging precision positioning relies on accurately measuring the round-trip time of laser pulses to determine the distance of the target object, and the data generated in this process is often time-series and highly dynamic. As a deep learning model, the LSTM algorithm can effectively capture the long-term dependencies in time series data and improve the accuracy and stability of ranging by learning the inherent laws of the data. In the actual application of laser ranging, factors such as environmental noise, the reflection characteristics of the target object, and the propagation speed of the laser pulse may affect the measurement results. The LSTM algorithm can automatically adjust the model parameters to adapt to the ranging scenario of drones for overhead lines by learning these complex factors. In addition, the LSTM algorithm also has a strong generalization ability and can maintain good prediction performance even when the training data is limited.

[0059] Based on the preliminary positioning, the drone uses the laser rangefinder on board to continuously scan the transmission line and collect a series of real-time laser echo data. These data sequences contain rich time series information, reflecting the dynamic changes in the distance between the drone and the line. By applying the long short-term memory network (LSTM) deep learning model to analyze and process these time series data, we can effectively capture the dependencies between data and filter out environmental noise, thereby achieving high-precision three-dimensional spatial positioning of the transmission line. The advantage of the LSTM algorithm is that it can handle long-term dependencies in time series data, which is particularly important for accurate distance measurement.

[0060] Therefore, using the LSTM algorithm for laser ranging not only helps to improve the accuracy and stability of ranging, but also can better adapt to the complex ranging environment when the drone is flying. A trained long short-term memory (LSTM) neural network model is used, which not only considers the laser scanning data sequence, but also incorporates real-time meteorological information to more accurately predict the actual distance between the drone and the transmission line. LSTM is good at processing time series data, so it is very suitable for such dynamic ranging tasks.

[0061] S4: Based on the laser ranging data, precise positioning is performed and the X-ray inspection drone is controlled to approach the overhead transmission line. The discharge status of the overhead transmission line is detected in real time using ultraviolet images. When the overhead transmission line is detected to be discharged, the relative position of the X-ray inspection drone and the overhead transmission line is recorded based on the image recognition results and laser ranging data to obtain the safe distance when hanging the line.

[0062] It should be noted that when the drone approaches the transmission line based on the laser ranging results, the discharge of the line is monitored in real time by analyzing the ultraviolet image. Once the discharge phenomenon is detected, the system will record the relative position of the drone and the transmission line at this time, and this position will be regarded as the reference distance for safe hanging of the line. This is because discharge usually means that the line is defective or overloaded, and the distance at this time can be regarded as the minimum threshold to ensure the safety of the operation.

[0063] S5: Adjust the flight status of the drone in combination with real-time meteorological information, and perform transmission line hanging operations on the premise that there is no discharge in the overhead transmission line and the safety distance meets the requirements.

[0064] It should be noted that according to the precise positioning results provided by the LSTM algorithm, the control system of the drone will receive accurate line hanging position information. Subsequently, the drone dynamically adjusts the flight parameters of the drone based on real-time meteorological information to ensure operation in the most suitable environment, avoid risks brought by bad weather, and ensure that the X-ray detection equipment or line hanging tools are accurately aligned with the target position. After ensuring a safe distance and precise alignment, the line hanging operation is performed, such as deploying detection sensors, performing maintenance tasks, etc., to complete close-range detection or maintenance operations on the transmission line.

[0065] This embodiment provides a method for hanging lines on drones based on safe distance detection. By combining the rough positioning of the image recognition algorithm with the precise positioning of the laser fixed point, it is more accurate than the single deep learning image recognition positioning, and saves more positioning time and flight costs than the single laser fixed point. At the same time, the present invention also combines laser ranging with LSTM, which can more accurately determine the location of the overhead transmission line, provide an accurate data basis for the drone hanging line operation, and improve the success rate of hanging lines. The present invention fills the shortcomings of the traditional manual hanging line method, greatly improves the safety and stability of X-ray detection, and significantly improves the hanging line efficiency and success rate.

[0066] In a preferred embodiment of the present invention, a real-time laser scanning data sequence is obtained by a drone and laser ranging data is obtained by using a pre-trained LSTM model, including the following steps:

[0067] S21: Control the X-ray inspection drone and the overhead transmission line to be in a horizontal state that meets the approximate horizontal requirements.

[0068] It should be noted that this step ensures that the X-ray inspection drone and the overhead transmission line are roughly horizontal. This operation is crucial to the accuracy of subsequent laser ranging, because the non-horizontal state may introduce unnecessary angle errors and affect the ranging accuracy. Through the drone's automatic control system or manual remote control, adjust its posture to the ideal level to create good conditions for subsequent data collection.

[0069] S22: Under the condition of horizontal state, adjust the angle of the X-ray inspection drone to obtain real-time laser scanning data sequence and real-time meteorological information.

[0070] It should be noted that after the drone reaches a horizontal state, its angle is further fine-tuned. This step may involve adjusting the pitch angle or yaw angle to ensure that the laser scanning can accurately capture the key parts of the transmission overhead line. At the same time, at this precisely adjusted angle, the drone begins to collect laser scanning data sequences in real time. This data sequence contains the distance information from the drone to multiple points on the surface of the target object, which is the basis for subsequent processing. In addition, real-time meteorological information (such as temperature, humidity, wind speed, etc.) is collected synchronously, because these factors may affect the laser propagation speed and path, and thus affect the ranging accuracy.

[0071] S23: After preprocessing the real-time laser scanning data sequence and the real-time meteorological information, the data are input into the pre-established LSTM model to obtain the distance information between the UAV and the overhead transmission line.

[0072] It should be noted that the collected raw laser scanning data sequence and meteorological information need to be preprocessed to remove noise, correct errors, standardize, etc., to ensure that the data quality meets the model input requirements. The preprocessed data is then input into a pre-trained LSTM (long short-term memory) model. As a special recurrent neural network, LSTM is good at processing time series data. It can learn the law of laser scanning data sequence changes over time and the influence of meteorological factors on laser ranging. After training, the model can predict the exact distance between the drone and the overhead transmission line based on the input information. It can be understood that compared with directly determining the laser ranging information based on the laser scanning data sequence, meteorological information (such as wind speed and wind direction information) as an additional feature input can enable the LSTM model to output corrected laser ranging data, which is more in line with the needs of drone hanging line operation in actual scenarios.

[0073] In some specific embodiments, when the reflected laser brightness of the X-ray inspection drone is the highest, the X-ray inspection drone is in a horizontal state with the overhead transmission line. The process of preprocessing the real-time laser scanning data sequence includes noise reduction and normalization.

[0074] In a further embodiment of the present invention, the process of establishing the LSTM model is as follows:

[0075] Data collection: Obtain the historical laser scanning data sequence and historical meteorological information of the X-ray detection drone, and mark the corresponding real location information of the drone. Use the historical laser scanning data sequence, historical meteorological information and corresponding real location information as training data.

[0076] Model construction: Establish an LSTM network structure including an LSTM layer and a fully connected layer as the model to be trained.

[0077] Model training: The training data is preprocessed, and the preprocessed historical laser scanning data sequence and historical meteorological information are used as input. The preprocessed real position information is used as the supervised learning target to train the training model to obtain the LSTM model.

[0078] In some specific implementations, the actual location information and the predicted location information are in the same information format, which is a transmission overhead line coordinate value or location category.

[0079] In a preferred embodiment of the present invention, training the model to be trained includes:

[0080] Input the preprocessed training data, extract features through the LSTM layer, and then get the output through the fully connected layer;

[0081] Select a loss function based on the task type to calculate the error between the predicted position information output by the model to be trained and the labeled real position information; the task type is a regression task or a classification task, which is used to obtain the coordinate value or location category of the overhead transmission line respectively;

[0082] The weights of the model to be trained are updated through the optimization algorithm to minimize the loss and obtain the LSTM model.

[0083] The update formula of the LSTM model is:

[0084] Input gate: i t =σ(W xi ·x t +W hi ·i {t-1} +b i );

[0085] Forget gate: f t =σ(W xf ·x t +W hf ·h {t-1} +b f );

[0086] Cell state update: c' t =tanh(W xc ·x t +W hc ·h {t-1} +b c );c t =f t ·c {t-1} +i t ·c' t ;

[0087] Output gate: o t =σ(W xo ·x t +W ho ·h {t-1} +b o );h t =o t ·tanh(c t );

[0088] Among them, σ is the sigmoid activation function; tanh is the hyperbolic tangent activation function; i t 、f t , o t are the outputs of the input gate, forget gate, and output gate respectively; c t 、c' t are the current and candidate cell states respectively; h t is the hidden state at the current moment; Wxi , W hi , W xf , W hf , W xc , W hc , W xo , W ho and b i , b f , b c , b o are the weights and bias parameters that need to be learned; x t is the input at the current moment; h {t-1} It is the hidden state at the previous moment.

[0089] In a preferred embodiment of the present invention, when the task type is a regression task or a classification task, which is used to obtain the coordinate value or location category of the overhead transmission line, the output of the corresponding fully connected layer is determined according to the following formula:

[0090] Returning mission:

[0091] position=W p ·h t +b p ;

[0092] Among them, position is the predicted transmission overhead line coordinate value; W p and b p are the weights and biases of the fully connected layer; h t is the hidden state of the current moment output by the LSTM layer;

[0093] Classification Task:

[0094] output_logits = W c ·h t +b c ;

[0095] predicted_class=softmax(output_logits);

[0096] Where: output_logits is the unnormalized output; predicted_class is the normalized predicted category probability distribution; softmax represents the softmax activation function, which is used to convert the output into a probability distribution, W c are the weights of the fully connected layer.

[0097] In a preferred embodiment of the present invention, when performing a transmission line hanging operation, whether to perform the hanging operation is determined according to the following formula:

[0098]

[0099] Wherein, Linehanging(·) represents the line-hanging operation judgment function with RGB image, ultraviolet image UV, meteorological information W and laser scanning data sequence L as input. When it is 1, it means that the line-hanging operation is performed, and when it is 0, it means that the line-hanging operation is not performed. Positioning(·) represents the positioning process, Image(RGB) represents the coarse positioning process, LSTM(L,W) represents the fine positioning process, Image(UV) represents the discharge detection process, and AdjustFlight(W) represents the flight state adjustment process.

[0100] That is, in this embodiment, only when the drone hooking operation completely executes the positioning process, the discharge detection process and the flight state adjustment process, the corresponding hooking operation is performed to maximize the operational safety.

[0101] Based on the same inventive concept, the embodiment of the present application also provides a drone hanging line device based on safety distance detection for implementing the drone hanging line method based on safety distance detection involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the drone hanging line device embodiment based on safety distance detection provided below can refer to the limitations of the drone hanging line method based on safety distance detection above, and will not be repeated here.

[0102] See also Figure 2 , this embodiment provides a drone hanging line device based on safety distance detection, including:

[0103] The information acquisition module is used to control the X-ray inspection drone to drive toward the overhead transmission line and collect RGB images, ultraviolet images and real-time meteorological information of the overhead transmission line;

[0104] An image recognition module is used to roughly locate the line position of the RGB image using an image recognition algorithm;

[0105] The laser positioning module is used to obtain real-time laser scanning data sequences through the UAV within the rough positioning range and obtain laser ranging data using a pre-trained LSTM model. The LSTM model is trained using the laser scanning data sequence and meteorological information and is used to determine the model for laser ranging data.

[0106] The discharge detection module is used to perform precise positioning based on laser ranging data, and control the X-ray detection drone to approach the overhead transmission line, and use ultraviolet images to detect the discharge status of the overhead transmission line in real time. When the overhead transmission line is detected to be discharged, the relative position of the X-ray detection drone and the overhead transmission line is recorded based on the image recognition result and laser ranging data to obtain the safe distance when hanging the line;

[0107] The control module is used to adjust the flight status of the UAV in combination with real-time meteorological information, and perform transmission line hanging operations on the premise that there is no discharge in the transmission overhead line and the safety distance meets the requirements.

[0108] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0109] Reference Figure 3 The embodiment of the present invention further provides a computer device 3, comprising: a memory 302 and a processor 301 and a computer program 303 stored in the memory 302. When the computer program 303 is executed on the processor 301, the drone hanging line method based on safety distance detection as described in any one of the above methods is implemented.

[0110] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that Figure 3 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0111] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0112] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0113] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for hanging a drone line based on safety distance detection as described in any one of the above methods is implemented.

[0114] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0115] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0116] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0117] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0118] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A drone hanging line method based on safety distance detection, It is characterized in that The steps include: Control the X-ray inspection drone to drive toward the overhead transmission line and collect RGB images, ultraviolet images and real-time meteorological information of the overhead transmission line; Using an image recognition algorithm to roughly locate the line position on the RGB image; Within the coarse positioning range, a real-time laser scanning data sequence is obtained by a UAV and laser ranging data is obtained by using a pre-trained LSTM model. The LSTM model is trained using the laser scanning data sequence and meteorological information and is used to determine the model of the laser ranging data. Based on the laser ranging data, precise positioning is performed, and the X-ray inspection drone is controlled to approach the overhead transmission line, and the discharge state of the overhead transmission line is detected in real time using the ultraviolet image. When the overhead transmission line is detected to be discharged, the relative position of the X-ray inspection drone and the overhead transmission line is recorded based on the image recognition result and the laser ranging data to obtain a safe distance when hanging the line; The flight state of the UAV is adjusted in combination with the real-time meteorological information, and the transmission line hanging operation is performed on the premise that there is no discharge in the overhead transmission line and the safety distance meets the requirements.

2. The drone hanging line method based on safety distance detection according to claim 1, It is characterized in that Obtain real-time laser scanning data sequences through drones and use pre-trained LSTM models to obtain laser ranging data, including: Control the X-ray inspection drone and the overhead power transmission line to be in a level state that meets the approximate level requirements; Under the condition of the horizontal state, adjusting the angle of the X-ray detection drone to obtain a real-time laser scanning data sequence and real-time meteorological information; After preprocessing, the real-time laser scanning data sequence and the real-time meteorological information are input into a pre-established LSTM model to obtain the distance information between the UAV and the overhead transmission line.

3. The drone hanging line method based on safety distance detection according to claim 2, It is characterized in that The establishment process of the LSTM model is as follows: Obtaining a historical laser scanning data sequence and historical meteorological information of an X-ray detection UAV, and marking the real location information corresponding to the UAV, and using the historical laser scanning data sequence, the historical meteorological information and the corresponding real location information as training data; Establish an LSTM network structure including an LSTM layer and a fully connected layer as the model to be trained; The training data is preprocessed, and the preprocessed historical laser scanning data sequence and the historical meteorological information are used as input, and the preprocessed real position information is used as a supervised learning target to train the model to be trained to obtain the LSTM model.

4. The drone hanging line method based on safety distance detection according to claim 3, It is characterized in that Training the model to be trained includes: Input the preprocessed training data, extract features through the LSTM layer, and then get the output through the fully connected layer; A loss function is selected according to the task type to calculate the error between the predicted position information output by the model to be trained and the marked real position information; the task type is a regression task or a classification task, which is used to obtain the coordinate value or position category of the overhead transmission line respectively; The weights of the model to be trained are updated through the optimization algorithm to minimize the loss and obtain the LSTM model.

5. The drone hanging line method based on safety distance detection according to claim 4, It is characterized in that When the task type is a regression task or a classification task, the output of the corresponding fully connected layer is determined according to the following formula: Returning mission: position=W p ·h t +b p ; Among them, position is the predicted transmission overhead line coordinate value; W p and b p are the weights and biases of the fully connected layer; h t is the hidden state of the current moment output by the LSTM layer; Classification Task: output_logits=W c ·h t +b c ; predicted_class=softmax(output_logits); Where: output_logits is the unnormalized output; predicted_class is the normalized predicted category probability distribution; softmax represents the softmax activation function, which is used to convert the output into a probability distribution, W c are the weights of the fully connected layer.

6. The drone hanging line method based on safety distance detection according to claim 1, It is characterized in that When performing the transmission line hanging operation, determine whether to perform the hanging operation according to the following formula: Wherein, Linehanging(·) represents the line-hanging operation judgment function with RGB image, ultraviolet image UV, meteorological information W and laser scanning data sequence L as input. When it is 1, it means that the line-hanging operation is performed, and when it is 0, it means that the line-hanging operation is not performed. Positioning(·) represents the positioning process, Image(RGB) represents the coarse positioning process, LSTM(L,W) represents the fine positioning process, Image(UV) represents the discharge detection process, and AdjustFlight(W) represents the flight state adjustment process.

7. The drone hanging line method based on safety distance detection according to claim 2, It is characterized in that The preprocessing process includes: denoising and normalization.

8. A drone hanging line device based on safety distance detection, It is characterized in that include: The information acquisition module is used to control the X-ray inspection drone to drive toward the overhead transmission line and collect RGB images, ultraviolet images and real-time meteorological information of the overhead transmission line; An image recognition module, used for roughly locating the line position of the RGB image using an image recognition algorithm; A laser positioning module is used to obtain a real-time laser scanning data sequence through a UAV within a rough positioning range and obtain laser ranging data using a pre-trained LSTM model. The LSTM model is trained using the laser scanning data sequence and meteorological information and is used to determine a model for laser ranging data. A discharge detection module is used to perform precise positioning based on the laser ranging data, and control the X-ray detection drone to approach the overhead transmission line, and use the ultraviolet image to detect the discharge state of the overhead transmission line in real time. When the overhead transmission line is detected to be discharged, the relative position of the X-ray detection drone and the overhead transmission line is recorded based on the image recognition result and the laser ranging data to obtain a safe distance when hanging the line; The control module is used to adjust the flight state of the UAV in combination with the real-time meteorological information, and perform the transmission line hanging operation under the premise that there is no discharge in the transmission overhead line and the safety distance meets the requirements.

9. A computer device, It is characterized in that The device comprises a processor and a memory: The memory is used to store a computer program and send instructions of the computer program to the processor; The processor executes a wire hanging method for an X-ray detection drone according to any one of claims 1 to 7 according to the instructions of the computer program.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method for hanging a line for an X-ray detection drone according to any one of claims 1 to 7 is implemented.

Citation Information

Cited By

  • Safety detection system and safety detection method for power transmission line, and storage medium

    CN119880967A

  • Unmanned aerial vehicle hanging line self-adaptive alignment system and method based on AI vision

    CN122469850A

  • An unmanned aerial vehicle hanging line self-adaptive alignment system and method based on AI vision

    CN122469850B