Method for supervising power transmission line construction by unmanned aerial vehicle

Abstract

The invention provides a method for supervising power transmission line construction through an unmanned aerial vehicle, and belongs to the technical field of electric power engineering. According to the method, data of a construction area are collected, captured images are analyzed in real time through an unmanned aerial vehicle, and key elements in the construction process are recognized; data and an identification result are transmitted in real time through a wireless communication link between the unmanned aerial vehicle and the ground monitoring center, and the ground monitoring center generates a three-dimensional visual model of the construction progress by using the data and detects a deviation with a pre-construction standard; when it is detected that the construction quality does not meet the standard, the unmanned aerial vehicle automatically hovers in a problem area, shoots detailed images and sends an instant alarm to a construction team through a ground monitoring center; and after the construction team carries out correction according to the feedback of the unmanned aerial vehicle, the unmanned aerial vehicle supervises the area again and confirms the correction effect. The construction progress and quality can be monitored in real time, problems in construction can be found and guided to be corrected in time, and construction safety and engineering quality are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power engineering, and in particular to a method for supervising the construction of power transmission lines using an unmanned aerial vehicle. Background Art

[0002] In the field of power engineering, transmission lines are important infrastructure for power transmission. Traditional transmission line construction supervision mainly relies on manual inspections, which involves regularly dispatching supervisors to the site to check the construction progress and quality. With the development of technology, drone technology has begun to be applied to transmission line construction supervision in order to improve supervision efficiency and coverage. Drones can carry high-definition cameras and other sensors, fly over the construction area, collect images and data, and provide support for construction supervision.

[0003] However, although drone technology has brought new possibilities to power transmission line construction supervision, the existing technology still has the following problems in practical application:

[0004] (1) Limited data collection and processing capabilities: Existing drone systems often lack efficient data processing capabilities when collecting construction area data and are unable to analyze and identify key elements in construction in real time.

[0005] (2) Unstable communication link: The communication link between the UAV and the ground monitoring center may be unstable, resulting in data transmission delay or loss, affecting the real-time and accuracy of construction supervision.

[0006] (3) Insufficient construction quality monitoring: Existing drone supervision systems often lack the ability to deeply monitor construction quality, making it difficult to detect construction problems and provide feedback in a timely manner.

[0007] (4) Imperfect response mechanism: When drones discover construction quality problems, the existing system lacks a rapid response mechanism and is unable to notify the construction team in time to make corrections.

[0008] (5) Data security and integrity issues: During data transmission, existing drone systems may lack effective data encryption and integrity verification mechanisms, posing the risk of data leakage and tampering. Summary of the invention

[0009] The purpose of the present invention is to provide a method for supervising the construction of power transmission lines by using a drone, which can monitor the construction progress and quality in real time, promptly discover and guide the correction of problems in the construction, and ensure construction safety and project quality.

[0010] To achieve the above object, the present invention provides a method for supervising the construction of a power transmission line using a drone, comprising the following steps:

[0011] S1. Collect construction area data;

[0012] S2, using the intelligent recognition algorithm configured on the drone to analyze the images captured by the drone in real time and identify key elements in the construction process;

[0013] S3, through the wireless communication link between the UAV and the ground monitoring center, the data and recognition results are transmitted in real time. The ground monitoring center uses the received data to generate a three-dimensional visualization model of the construction progress and detect deviations from the pre-construction standards;

[0014] S4. When it is detected that the construction quality does not meet the standards, the drone automatically hovers over the problem area, takes detailed images with a high-resolution camera, and sends an instant alarm to the construction team through the ground monitoring center;

[0015] S5. After the construction team makes corrections based on the feedback from the drone, the drone will supervise the area again to confirm the correction results.

[0016] Preferably, in step S1, the construction area data includes high-definition visible light images, infrared thermal imaging images, global positioning system data, inertial navigation system data and meteorological data;

[0017] Among them, the high-definition visible light image is an image of the construction area; the infrared thermal imaging data includes the temperature of the wire connection point, the insulator temperature, the tower base temperature, and the construction area temperature; the global positioning system data includes longitude and latitude, and altitude; the inertial navigation system data includes acceleration and angular velocity; and the meteorological data includes air pressure, temperature, humidity, and wind speed.

[0018] Preferably, in step S2, the intelligent recognition algorithm configured on the drone is used to analyze the images captured by the drone in real time to identify key elements in the construction process. The specific operations are as follows:

[0019] S21, preprocessing the high-definition visible light image data and infrared thermal imaging data to obtain preprocessed data I pro ;

[0020] S22, build a regional proposal network RPN, and convert the preprocessed data I pro Input into the convolutional neural network to extract feature maps;

[0021] Generate multiple anchor boxes of different sizes and scales at each position on the feature map;

[0022] For each anchor box, two fully connected layers are used to predict the probability of object existence and the offset of the bounding box respectively;

[0023] O=W obj F+b obj R=W reg F+b reg ;

[0024] Among them, O represents the probability of the object existing; W obj represents the weight matrix of object classification; F represents the feature map; b obj represents the bias term for object classification; R represents the offset of the bounding box; W reg represents the weight matrix for bounding box regression; b reg Represents the bias term for bounding box regression;

[0025] Combine the anchor box and the predicted offset to get the final region proposal;

[0026]

[0027] Among them, (x, y, w, h) represents the adjusted bounding box; (x, y) represents the center coordinates of the region proposal; w represents the width of the region proposal; h represents the height of the region proposal; (x A ,y A ) represents the center coordinate of the anchor box; w A Indicates the width of the anchor box; h A Indicates the height of the anchor box; R x , R y , R w , R h Both represent the offset of bounding box regression prediction; A represents the anchor box set;

[0028] For each region proposal, calculate the corresponding confidence score;

[0029] s = Sigmoid(O);

[0030] Among them, s represents the classification score, that is, the confidence score;

[0031] S23, performing NMS processing on the detected target;

[0032] B final =NMS(B,s,NMS threshold );

[0033] Among them, B final Represents the bounding box set after NMS processing; NMS threshold Represents the threshold for non-maximum suppression;

[0034] S24, identifying each bounding box to determine whether it contains a key element;

[0035] C=Classifier(B final )=softmax(W cls F1+b cls );

[0036] Where C represents the recognition result; W cls represents the weight matrix of the classifier; b cls Represents the bias term of the classifier; F1 represents the regional proposal feature obtained from RPN;

[0037] S25, combining the identification results with global positioning system data, inertial navigation system data and meteorological data to obtain comprehensive information on the construction status;

[0038] S=concat(C,nor(GPS),nor(INS),nor(M));

[0039] Among them, S represents comprehensive status information; GPS represents global positioning system data; INS represents inertial navigation system data; M represents meteorological data; and nor represents normalization function.

[0040] Preferably, in step S3, data and recognition results are transmitted in real time through a wireless communication link between the UAV and the ground monitoring center. The ground monitoring center uses the received data to generate a three-dimensional visualization model of the construction progress and detects deviations from the pre-construction standard. The specific operations are as follows:

[0041] S31, encapsulating the comprehensive state information S, the adjusted bounding box (x, y, w, h), the global positioning system data, the inertial navigation system data and the meteorological data into a data packet;

[0042] D packet ={S,(x,y,w,h),GPS,INS,M};

[0043] Among them, D packet Indicates a data packet;

[0044] S32, transmitting the encapsulated data packets to the ground monitoring center in real time through the wireless communication module on the drone;

[0045] S33, the ground monitoring center analyzes the received data packets, extracts the encapsulated information, and generates a three-dimensional visualization model of the construction progress by combining GIS technology;

[0046] S34. Setting a threshold for deviation detection according to a preset construction standard;

[0047] S35. Compare the actual construction data with the preset construction standard to see whether the deviation exceeds a threshold.

[0048] Preferably, in step S5, after the construction team makes corrections based on the feedback from the drone, the drone supervises the area again to confirm the correction effect. The specific operations are as follows:

[0049] S51. The construction team formulates corrective measures based on the deviation analysis results and corrects the problem areas according to the corrective measures;

[0050] S52. Record corrective actions and provide feedback to the drone;

[0051] S53. The UAV operator develops a new flight plan based on the revised information provided by the construction team and determines the route and data collection points for re-supervision;

[0052] S54. The UAV flies to the construction area according to the new flight plan and re-collects data of the construction area;

[0053] S55. Compare the newly collected data with the data before correction, check the changes in the construction area, and evaluate whether the correction effect is achieved.

[0054] Preferably, the drone and the ground monitoring center have two-way communication, and the communication protocol supports encrypted data transmission, as follows:

[0055] Key generation step: Use the CRYSTALS-Kyber algorithm to generate a key pair including a private key and a public key;

[0056] In the key encapsulation step, the drone uses the public key of the ground monitoring center to perform key encapsulation and generate encapsulation keys and shared keys;

[0057] Data transmission step, the drone sends the encapsulated key and data to the ground monitoring center;

[0058] Key decapsulation step: the ground monitoring center uses its private key to decapsulate the key and obtain the shared key;

[0059] Data decryption step: the ground monitoring center uses the shared key to decrypt the received encrypted data to obtain the original data;

[0060] Integrity verification step, the drone uses the shared key to generate a message authentication code before sending data, and the ground monitoring center uses the shared key to verify the integrity of the data after decrypting the data.

[0061] Therefore, the present invention adopts the above-mentioned method of unmanned aerial vehicle supervision of power transmission line construction, and the beneficial technical effects are as follows:

[0062] (1) The present invention uses an intelligent recognition algorithm configured on the drone to analyze captured images in real time and quickly identify key elements in the construction process, such as conductors, insulators, tower foundations, etc., effectively improving data collection and processing capabilities.

[0063] (2) In the present invention, the ground monitoring center uses the data transmitted by the drone to generate a three-dimensional visualization model of the construction progress, so that management personnel can intuitively understand the construction progress and timely discover construction deviations by comparing with the pre-construction standards, thereby improving the accuracy and efficiency of construction supervision.

[0064] (3) In the present invention, when it is detected that the construction quality does not meet the standards, the drone can automatically hover over the problem area, take detailed images, and send an immediate alarm to the construction team through the ground monitoring center. This rapid response mechanism helps the construction team to find problems in time and make corrections, ensuring construction quality and safety.

[0065] (4) In the present invention, after the construction team makes corrections based on the feedback from the drone, the drone can supervise the area again to confirm the correction effect. This process not only optimizes the correction process, but also accurately evaluates the correction effect by comparing the data before and after the correction, further improving the construction quality and efficiency.

[0066] (5) In the present invention, the two-way communication protocol between the UAV and the ground monitoring center supports encrypted data transmission, including the steps of key generation, key encapsulation, data transmission, key decapsulation, data decryption and integrity verification, which effectively ensures the security and integrity of the data and prevents the risk of data leakage and tampering. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 This is a flow chart of a method for using a drone to supervise the construction of a power transmission line according to the present invention;

[0068] Figure 2 Figure 1 is for data collection and processing;

[0069] Figure 3 Diagram for communication and data transmission. DETAILED DESCRIPTION

[0070] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0071] Unless otherwise defined, technical or scientific terms used in the present invention shall have the common meanings understood by one having ordinary skills in the field to which the present invention belongs.

[0072] Embodiment 1

[0073] like Figure 1 As shown, it is a flow chart of a method for supervising power transmission line construction by using a drone according to the present invention, which specifically includes the following steps:

[0074] S1. Collect construction area data.

[0075] like Figure 2As shown, the construction area data includes high-definition visible light images, infrared thermal imaging images, global positioning system data, inertial navigation system data and meteorological data.

[0076] High-definition visible light image acquisition: Use the high-definition camera carried by the drone to collect real-time images of the construction area.

[0077] Infrared thermal imaging image acquisition: Use infrared thermal imaging cameras to monitor the temperature of key parts such as wire connection points, insulators, and tower bases.

[0078] Global Positioning System (GPS) data collection: Use the GPS module to obtain the precise latitude, longitude and altitude information of the construction area.

[0079] Inertial Navigation System (INS) data acquisition: The acceleration and angular velocity data of the construction area are collected through the INS module.

[0080] Meteorological data collection: Integrated meteorological sensors to monitor meteorological conditions such as air pressure, temperature, humidity and wind speed in real time.

[0081] S2. Use the intelligent recognition algorithm configured on the drone to analyze the images captured by the drone in real time and identify the key elements in the construction process. The specific operations are as follows:

[0082] S21, preprocessing the high-definition visible light image data and infrared thermal imaging data to obtain preprocessed data I pro ;

[0083] S22, build a regional proposal network RPN, and convert the preprocessed data I pro Input into the convolutional neural network to extract feature maps;

[0084] Generate multiple anchor boxes of different sizes and scales at each position on the feature map;

[0085] For each anchor box, two fully connected layers are used to predict the probability of object existence and the offset of the bounding box respectively;

[0086] O=W obj F+b obj R=W reg F+b reg ;

[0087] Among them, O represents the probability of the object existing; W obj represents the weight matrix of object classification; F represents the feature map; b obj represents the bias term for object classification; R represents the offset of the bounding box; W reg represents the weight matrix for bounding box regression; b reg Represents the bias term for bounding box regression;

[0088] Combine the anchor box and the predicted offset to get the final region proposal;

[0089]

[0090] Among them, (x, y, w, h) represents the adjusted bounding box; (x, y) represents the center coordinates of the region proposal; w represents the width of the region proposal; h represents the height of the region proposal; (x A ,y A ) represents the center coordinate of the anchor box; w A Indicates the width of the anchor box; h A Indicates the height of the anchor box; R x , R y ; R w ; R h Both represent the offset of bounding box regression prediction; A represents the anchor box set;

[0091] For each region proposal, calculate the corresponding confidence score;

[0092] s = Sigmoid(O);

[0093] Among them, s represents the classification score, that is, the confidence score;

[0094] S23, performing NMS processing on the detected target;

[0095] B final =NMS(B,s,NMS threshold );

[0096] Among them, B final Represents the bounding box set after NMS processing; NMS threshold Represents the threshold for non-maximum suppression;

[0097] S24, identifying each bounding box to determine whether it contains a key element;

[0098] C=Classifier(B final )=softmax(W cls F1+b cls );

[0099] Where C represents the recognition result; W cls represents the weight matrix of the classifier; b cls Represents the bias term of the classifier; F1 represents the regional proposal feature obtained from RPN;

[0100] S25, combining the identification results with global positioning system data, inertial navigation system data and meteorological data to obtain comprehensive information on the construction status;

[0101] S=concat(C,nor(GPS),nor(INS),nor(M));

[0102] Among them, S represents comprehensive status information; GPS represents global positioning system data; INS represents inertial navigation system data; M represents meteorological data; and nor represents normalization function.

[0103] S3. Data and recognition results are transmitted in real time through the wireless communication link between the UAV and the ground monitoring center. The ground monitoring center uses the received data to generate a three-dimensional visualization model of the construction progress and detect deviations from the pre-construction standards. The specific operations are as follows:

[0104] S31, encapsulating the comprehensive state information S, the adjusted bounding box (x, y, w, h), the global positioning system data, the inertial navigation system data and the meteorological data into a data packet;

[0105] D packet ={S,(x,y,w,h),GPS,INS,M};

[0106] Among them, D packet Indicates a data packet;

[0107] S32, transmitting the encapsulated data packets to the ground monitoring center in real time through the wireless communication module on the drone;

[0108] S33, the ground monitoring center analyzes the received data packets, extracts the encapsulated information, and generates a three-dimensional visualization model of the construction progress by combining GIS technology;

[0109] S34. Setting a threshold for deviation detection according to a preset construction standard;

[0110] S35. Compare the actual construction data with the preset construction standard to see whether the deviation exceeds a threshold.

[0111] like Figure 3 As shown, the drone and the ground monitoring center have two-way communication, and its communication protocol supports encrypted data transmission, as follows:

[0112] Key generation step: Use the CRYSTALS-Kyber algorithm to generate a key pair including a private key and a public key;

[0113] In the key encapsulation step, the drone uses the public key of the ground monitoring center to perform key encapsulation and generate encapsulation keys and shared keys;

[0114] Data transmission step, the drone sends the encapsulated key and data to the ground monitoring center;

[0115] Key decapsulation step: the ground monitoring center uses its private key to decapsulate the key and obtain the shared key;

[0116] Data decryption step: the ground monitoring center uses the shared key to decrypt the received encrypted data to obtain the original data;

[0117] Integrity verification step, the drone uses the shared key to generate a message authentication code before sending data, and the ground monitoring center uses the shared key to verify the integrity of the data after decrypting the data.

[0118] S4. When it is detected that the construction quality does not meet the standards, the drone automatically hovers over the problem area, takes detailed images with a high-resolution camera, and sends an instant alarm to the construction team through the ground monitoring center.

[0119] S5. After the construction team makes corrections based on the feedback from the drone, the drone will supervise the area again to confirm the correction effect. The specific operations are as follows:

[0120] S51. The construction team formulates corrective measures based on the deviation analysis results and corrects the problem areas according to the corrective measures;

[0121] S52. Record corrective actions and provide feedback to the drone;

[0122] S53. The UAV operator develops a new flight plan based on the revised information provided by the construction team and determines the route and data collection points for re-supervision;

[0123] S54. The UAV flies to the construction area according to the new flight plan and re-collects data of the construction area;

[0124] S55. Compare the newly collected data with the data before correction, check the changes in the construction area, and evaluate whether the correction effect is achieved.

[0125] It is worth noting that the contents not elaborated in detail in the present invention are all prior art and are well known to those skilled in the art.

[0126] Therefore, the present invention adopts the above-mentioned method of using a drone to supervise the construction of power transmission lines, which can monitor the construction progress and quality in real time, promptly discover and guide the correction of problems in the construction, and ensure construction safety and project quality.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for supervising power transmission line construction using an unmanned aerial vehicle, characterized in that: The following steps are involved: S1. Collect construction area data; S2, using the intelligent recognition algorithm configured on the drone to analyze the images captured by the drone in real time and identify key elements in the construction process; S3, through the wireless communication link between the UAV and the ground monitoring center, the data and recognition results are transmitted in real time. The ground monitoring center uses the received data to generate a three-dimensional visualization model of the construction progress and detect deviations from the pre-construction standards; S4. When it is detected that the construction quality does not meet the standards, the drone automatically hovers over the problem area, takes detailed images with a high-resolution camera, and sends an instant alarm to the construction team through the ground monitoring center; S5. After the construction team makes corrections based on the feedback from the drone, the drone will supervise the area again to confirm the correction results.

2. The method for supervising power transmission line construction using an unmanned aerial vehicle according to claim 1, characterized in that: In step S1, the construction area data includes high-definition visible light images, infrared thermal imaging images, global positioning system data, inertial navigation system data and meteorological data; Among them, the high-definition visible light image is an image of the construction area; the infrared thermal imaging data includes the temperature of the wire connection point, the insulator temperature, the tower base temperature, and the construction area temperature; the global positioning system data includes longitude and latitude, and altitude; the inertial navigation system data includes acceleration and angular velocity; and the meteorological data includes air pressure, temperature, humidity, and wind speed.

3. The method for supervising power transmission line construction using an unmanned aerial vehicle according to claim 2, characterized in that: In step S2, the intelligent recognition algorithm configured on the drone is used to analyze the images captured by the drone in real time to identify key elements in the construction process. The specific operations are as follows: S21, preprocessing the high-definition visible light image data and infrared thermal imaging data to obtain preprocessed data I pro ; S22, build the region proposal network RPN, and convert the preprocessed data I pro Input into the convolutional neural network to extract feature maps; Generate multiple anchor boxes of different sizes and scales at each position on the feature map; For each anchor box, two fully connected layers are used to predict the probability of object existence and the offset of the bounding box respectively; O=W obj F+b obj R=W reg F+b reg ; Among them, O represents the probability of the object existing; W obj represents the weight matrix of object classification; F represents the feature map; b obj represents the bias term for object classification; R represents the offset of the bounding box; W reg represents the weight matrix for bounding box regression; b reg Represents the bias term for bounding box regression; Combine the anchor box and the predicted offset to get the final region proposal; Among them, (x, y, w, h) represents the adjusted bounding box; (x, y) represents the center coordinates of the region proposal; w represents the width of the region proposal; h represents the height of the region proposal; (x A ,y A ) represents the center coordinate of the anchor box; w A Indicates the width of the anchor box; h A Indicates the height of the anchor box; R x , R y , R w , R h Both represent the offset of bounding box regression prediction; A represents the anchor box set; For each region proposal, calculate the corresponding confidence score; s = Sigmoid(O); Among them, s represents the classification score, that is, the confidence score; S23, performing NMS processing on the detected target; B final =NMS(B,s,NMS threshold ); Among them, B final Represents the bounding box set after NMS processing; NMS threshold Represents the threshold for non-maximum suppression; S24, identifying each bounding box to determine whether it contains key elements; C=Classifier(B final )=softmax(W cls F1+b cls ); Where C represents the recognition result; W cls represents the weight matrix of the classifier; b cls Represents the bias term of the classifier; F1 represents the regional proposal feature obtained from RPN; S25, combining the identification results with global positioning system data, inertial navigation system data and meteorological data to obtain comprehensive information on the construction status; S=concat(C,nor(GPS),nor(INS),nor(M)); Among them, S represents comprehensive status information; GPS represents global positioning system data; INS represents inertial navigation system data; M represents meteorological data; and nor represents normalization function.

4. The method for supervising power transmission line construction using an unmanned aerial vehicle according to claim 3, characterized in that: In step S3, data and recognition results are transmitted in real time through the wireless communication link between the UAV and the ground monitoring center. The ground monitoring center uses the received data to generate a three-dimensional visualization model of the construction progress and detects deviations from the pre-construction standards. The specific operations are as follows: S31, encapsulating the comprehensive state information S, the adjusted bounding box (x, y, w, h), the global positioning system data, the inertial navigation system data and the meteorological data into a data packet; D packet ={S,(x,y,w,h),GPS,INS,M}; Among them, D packet Indicates a data packet; S32, transmitting the encapsulated data packets to the ground monitoring center in real time through the wireless communication module on the drone; S33, the ground monitoring center analyzes the received data packets, extracts the encapsulated information, and generates a three-dimensional visualization model of the construction progress by combining GIS technology; S34. Setting a threshold for deviation detection according to a preset construction standard; S35. Compare the actual construction data with the preset construction standard to see whether the deviation exceeds a threshold.

5. The method for supervising power transmission line construction using an unmanned aerial vehicle according to claim 4, characterized in that: In step S5, after the construction team makes corrections based on the feedback from the drone, the drone will supervise the area again to confirm the correction effect. The specific operations are as follows: S51. The construction team formulates corrective measures based on the deviation analysis results and corrects the problem areas according to the corrective measures; S52. Record corrective actions and provide feedback to the drone; S53. The UAV operator develops a new flight plan based on the revised information provided by the construction team and determines the route and data collection points for re-supervision; S54. The UAV flies to the construction area according to the new flight plan and re-collects data of the construction area; S55. Compare the newly collected data with the data before correction, check the changes in the construction area, and evaluate whether the correction effect is achieved.

6. The method for supervising power transmission line construction using an unmanned aerial vehicle according to claim 5, characterized in that: The drone and the ground monitoring center have two-way communication, and its communication protocol supports encrypted data transmission, as follows: Key generation step: Use the CRYSTALS-Kyber algorithm to generate a key pair including a private key and a public key; In the key encapsulation step, the drone uses the public key of the ground monitoring center to perform key encapsulation and generate encapsulation keys and shared keys; Data transmission step, the drone sends the encapsulated key and data to the ground monitoring center; Key decapsulation step: the ground monitoring center uses its private key to decapsulate the key and obtain the shared key; Data decryption step: the ground monitoring center uses the shared key to decrypt the received encrypted data to obtain the original data; Integrity verification step, the drone uses the shared key to generate a message authentication code before sending data, and the ground monitoring center uses the shared key to verify the integrity of the data after decrypting the data.

Images