Overhead line inspection method and device and storage medium

Abstract

The invention discloses an overhead line inspection method and device and a storage medium, and the method comprises the steps: receiving physical characteristic parameters which are collected by an optical fiber sensor disposed on an overhead line and are related to a force, and obtaining the position information of the overhead line if the physical characteristic parameters reach a preset risk threshold value, and controlling the automatic aircraft to fly to the position information to collect image data so as to identify whether the mining behavior of the construction machinery exists under the overhead line, if so, calculating the risk level of the mining behavior on the overhead line according to the image data, and performing safety protection on the overhead line according to the risk level. Potential threats of the construction site of the overhead line can be effectively identified, and the influence of the excavation behavior of the construction machinery on the safety of the overhead line can be evaluated in time, so that accurate protection is provided, line damage or safety accidents caused by the construction machinery are reduced, and the inspection efficiency and accuracy of the overhead line are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of inspection technology, and in particular to an inspection method, equipment and storage medium for overhead lines. Background Art

[0002] Overhead lines are one of the more important links in the power system and are often damaged by external factors, such as natural disasters, severe weather, and external force damage. At the 110kV and 220kV voltage levels, more than half of the external force damage to overhead lines is caused by illegal construction of large-scale construction machinery under the corridor. When large construction machinery invades the corridor under the transmission line, the machinery may touch the overhead line and cause line disconnection, phase short circuit, power outage, and tower tilt. External force damage can cause varying degrees of damage to overhead lines. In severe cases, it may threaten the safety of people's lives and huge losses of manpower and financial resources. Therefore, in order to protect overhead power lines from external damage and enhance the safety of overhead line operation, it is necessary to monitor and protect overhead lines.

[0003] At present, in the online monitoring system of overhead lines, for illegal construction of large vehicles, the front-end equipment generally captures pictures or videos regularly and sends them to the back-end center for manual analysis. It requires personnel to pay attention and make judgments continuously for a long time, which has huge manpower costs and low manual efficiency. Therefore, the inspection efficiency of overhead lines is low. Summary of the invention

[0004] The invention provides an overhead line inspection method, equipment and storage medium, which are used to improve the inspection efficiency and accuracy of the overhead line.

[0005] In a first aspect, an embodiment of the present invention provides an overhead line inspection method, the method comprising:

[0006] receiving physical characteristic parameters related to force collected by optical fiber sensors arranged on overhead lines;

[0007] If the physical characteristic parameter reaches a preset risk threshold, obtaining the location information of the overhead line;

[0008] Controlling the automatic flying vehicle to fly to the position information to collect image data to identify whether there is digging behavior of construction machinery under the overhead line;

[0009] If there is excavation behavior of the construction machinery, calculating the risk level of the excavation behavior to the overhead line based on the image data;

[0010] Safety protection is performed on the overhead line according to the risk level.

[0011] In a second aspect, an embodiment of the present invention further provides an overhead line inspection device, the device comprising:

[0012] A physical characteristic parameter acquisition module, used to receive physical characteristic parameters related to force acquired by optical fiber sensors arranged on overhead lines;

[0013] A location information acquisition module, configured to acquire the location information of the overhead line if the physical characteristic parameter reaches a preset risk threshold;

[0014] An image data acquisition module, used to control the automatic aircraft to fly to the position information to collect image data to identify whether there is digging behavior of construction machinery under the overhead line;

[0015] a risk level calculation module, for calculating the risk level of the overhead line caused by the excavation behavior based on the image data if there is an excavation behavior of the construction machinery;

[0016] A safety protection module is used to perform safety protection on the overhead line according to the risk level.

[0017] In a third aspect, an embodiment of the present invention further provides a computer device, the computer device comprising:

[0018] one or more processors;

[0019] A storage device for storing one or more programs;

[0020] When the one or more programs are executed by the one or more processors, the one or more processors implement the overhead line inspection method provided in the first aspect of the present invention.

[0021] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the overhead line inspection method provided in the first aspect of the present invention.

[0022] In a fifth aspect, an embodiment of the present invention further provides a computer program product, the computer program product comprising a computer program, and when the computer program is executed by a processor, the overhead line inspection method provided in the first aspect of the present invention is implemented.

[0023] In an embodiment of the present invention, physical characteristic parameters related to force collected by optical fiber sensors arranged on overhead lines are received. If the physical characteristic parameters reach a preset risk threshold, the location information of the overhead lines is obtained, and the automatic aircraft is controlled to fly to the location information to collect image data to identify whether there is digging behavior of construction machinery under the overhead lines. If there is digging behavior of construction machinery, the risk level of the digging behavior to the overhead lines is calculated based on the image data, and safety protection is performed on the overhead lines based on the risk level. The inspection method based on optical fiber sensors and automatic aircraft can effectively identify potential threats to the construction site of overhead lines by real-time monitoring of physical characteristic parameters of overhead lines, accurately locating problems, automatically identifying risks of construction machinery, and performing dynamic evaluations. This method can timely evaluate the impact of digging behavior of construction machinery on the safety of overhead lines, thereby providing accurate protection, reducing line damage or safety accidents caused by construction machinery, and effectively improving the inspection efficiency and accuracy of overhead lines. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A flowchart of an overhead line inspection method provided in Embodiment 1 of the present invention;

[0025] Figure 2 A structural block diagram of an overhead line inspection device provided in Embodiment 2 of the present invention;

[0026] Figure 3 A schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 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 should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can cover sequential implementations other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] See also Figure 1 , shows a flow chart of an overhead line inspection method provided by Embodiment 1 of the present invention, the method can be executed by an overhead line inspection device, the overhead line inspection device can be implemented in the form of hardware and / or software, and the overhead line inspection device can be configured in a computer device. Figure 1 As shown, the method includes:

[0031] Step 101: Receive force-related physical characteristic parameters collected by optical fiber sensors arranged on overhead lines.

[0032] Overhead lines are lines suspended by poles or towers for transmitting electricity or communication signals. They are usually made of metal wires and are exposed to environmental factors such as wind, snow, and lightning strikes, so they need to be inspected and maintained regularly. Technologies such as optical fiber sensors are widely used to monitor the physical characteristics of overhead lines in real time to ensure the safe and stable operation of overhead lines.

[0033] Fiber optic sensor is a sensor based on fiber optic technology, which obtains physical quantities of the surrounding environment (such as temperature, pressure, vibration, etc.) by detecting changes in optical signals. Fiber optic sensors are often used for long-distance monitoring and real-time monitoring, and have the advantages of high sensitivity and strong anti-interference ability. The embodiment of the present invention uses fiber optic sensing technology to achieve all-day real-time monitoring of the entire overhead line, solving the problem of limited monitoring range of the prior art.

[0034] In this embodiment, optical fiber sensors are arranged on overhead power lines to monitor physical characteristic parameters of overhead lines related to force. These optical fiber sensors can collect physical characteristic parameters of overhead lines, thereby reflecting in real time whether there are abnormal conditions in the operation of overhead lines. By monitoring these physical characteristic parameters, potential risks can be discovered in time, such as damage to overhead lines by external forces or other damage, and corresponding preventive measures can be taken.

[0035] Exemplarily, the physical characteristic parameters include pressure parameters and / or vibration parameters, and the optical fiber sensor is arranged at least one location at a corner of the overhead line, at a crossing of the overhead line, and in a support pole of the overhead line.

[0036] Step 102: If the physical characteristic parameter reaches a preset risk threshold, the location information of the overhead line is obtained.

[0037] The risk threshold is a preset critical value. When the physical characteristic parameters reach or exceed this risk threshold, the system considers that the overhead line has been damaged by external forces. The risk threshold is set based on historical experience of external force damage. When the physical characteristic parameters collected by the optical fiber sensor reach this risk threshold, it is considered that the overhead line has been damaged by external forces and further inspection of the overhead line is required.

[0038] In this embodiment, the physical characteristic parameters of the overhead line monitored by the optical fiber sensor have reached a preset risk threshold, indicating that the overhead line may be damaged or there is a risk. The system locates the problem area of ​​the overhead line by collecting the position information of these optical fiber sensors, so as to take further inspection and protection measures in time.

[0039] Specifically, the system receives the location information generated by the positioning tag arranged on the optical fiber sensor as the location information of the overhead line, and sends the location information to the mobile phone of the staff to inform the staff that the overhead line may be at risk of external force damage.

[0040] The positioning tag includes at least any one of a radio frequency identification tag, a global positioning system and a distributed optical fiber sensing technology of an optical fiber sensor.

[0041] Radio Frequency Identification Tag (RFID): is a technology that uses radio frequency signals for automatic identification and positioning, usually used for short-range, low-cost location tracking. By deploying RFID tags, the accurate location information of the optical fiber sensor can be read.

[0042] Global Positioning System (GPS): A technology that uses satellite signals for positioning, suitable for accurate positioning over a large range. By equipping the fiber optic sensor with a GPS module, the location information of the fiber optic sensor can be obtained worldwide.

[0043] Distributed fiber optic sensing technology: This is a high-precision monitoring technology based on optical fiber. It can monitor the physical characteristics of overhead lines in real time by transmitting optical signals in the optical fiber and analyzing the changes in the signal. It can also provide the location information of the fiber optic sensor through the distributed characteristics of the optical fiber.

[0044] Step 103: Control the automatic aerial vehicle to fly to the location information to collect image data to identify whether there is digging behavior of construction machinery under the overhead line.

[0045] In this embodiment, the automatic aircraft is used to fly to the area indicated by the location information collected by the system, and the image recognition technology in the edge computing box carried by the automatic aircraft obtains the image data of the area indicated by the location information to determine whether there is construction machinery digging under the overhead line. Through the flight of the automatic aircraft and the collection of image data, construction activities near the overhead line can be effectively monitored, construction machinery that may pose a threat to the overhead line can be discovered in time, and the efficiency and accuracy of overhead line inspection can be improved.

[0046] The automatic aircraft has an automatic obstacle avoidance function and can flexibly adjust the flight altitude and route according to environmental and climatic conditions. After reaching the specified location information, the automatic aircraft will hover and start collecting image data. During the automatic aircraft inspection process, the staff can view the image data transmitted by the automatic aircraft in real time through the application, and manually adjust the flight path of the automatic aircraft as needed to expand or reduce the inspection range. The embodiment of the present invention uses an automatic aircraft and an artificial intelligence algorithm to automatically identify whether the overhead line is damaged by external forces, and at the same time identify the excavation behavior of construction machinery, thereby improving the recognition accuracy and reducing the impact of human factors.

[0047] In one embodiment of the present invention, step 103 may include the following steps:

[0048] Step 1031: When the automatic aircraft is controlled to fly to the position information, video data is collected downward.

[0049] In this embodiment, the automatic aircraft arrives at the designated area according to the location information provided by the positioning tag arranged on the optical fiber sensor, and collects real-time video data of the location information. Real-time monitoring and identification of whether there is construction machinery under the overhead line can be carried out to further determine the possible risks to the overhead line. The continuity and dynamics of the video data make it possible to identify the activities of the construction machinery in real time, so as to more accurately assess its impact on the overhead line. The video data contains multiple frames of image data.

[0050] Step 1032: Perform target detection operations in each frame of image data to detect construction machinery.

[0051] Target detection is a computer vision technology that can automatically identify the type, location and other information of the target object by analyzing the content in the image data. In this embodiment, the main purpose of the target detection operation is to detect whether there is construction machinery under the overhead line, so as to further determine whether there is a potential risk. Target detection can use convolutional neural networks (CNNs) such as the YOLO series and single shot multi-frame detectors (SSD), and the present invention is not limited here.

[0052] In this embodiment, target detection is performed in each frame of the image data to identify whether there is a construction machine in the image. Timely identification of the existence of construction machinery and tracking its activities can help assess risks and take corresponding safety protection measures.

[0053] Step 1033: When a construction machine is detected, the motion trajectory of the construction machine is tracked in multiple frames of image data.

[0054] In this embodiment, the movement path of construction machinery (such as excavators, bulldozers and other construction machinery) is identified and tracked through continuous image data, so as to further track the movement trajectory of the construction machinery, so as to more accurately understand the position changes of the construction machinery, thereby evaluating whether it is approaching or performing dangerous operations that may affect overhead lines.

[0055] Specifically, in each frame of image data, the position of the construction machinery is identified, and the boundaries of the construction machinery are calibrated by an outer bounding box (i.e., a rectangular box surrounding the construction machinery). The contextual information of the construction machinery is located in the outer bounding box representing the construction machinery. The contextual information usually refers to the background information related to the construction machinery, such as the surrounding environment, the layout of the work area, etc., which helps to understand the movements and behaviors of the construction machinery.

[0056] The motion information of the construction machinery is extracted based on the context information. By analyzing the context information, the motion information of the construction machinery can be extracted, such as position change, speed, direction, etc. This motion information helps to understand the motion pattern of the construction machinery and then infer its possible behavior (for example, whether it is performing an excavation operation).

[0057] In the multi-frame image data, the motion information extracted from each frame is correlated, which is divided into local and global level analysis. The local level refers to the analysis of the local motion of the construction machinery within a single frame of image data, while the global level is the tracking and correlation of the motion of the construction machinery across frames. This helps to determine the motion trajectory of the construction machinery at different time points.

[0058] Step 1034: In the process of tracking the motion trajectory of the construction machinery, the construction machine is positioned by thermal mapping to obtain the activity of the construction machinery.

[0059] Heatmap localization is a commonly used technique in computer vision, usually used for tasks such as object detection, key point detection, and pose estimation. Heatmap localization generates a heatmap to represent the location of the target object or key point in the form of a highlighted area. Each pixel value in the heatmap represents the "activation" intensity or probability of the location. Generally, the brighter the area, the higher the probability of the location of the target or key point. In object detection, heatmap localization can help the model locate the specific location of the object or the coordinates of the key point more accurately.

[0060] In this embodiment, when tracking the motion trajectory of the construction machinery, heat map positioning technology is used to accurately capture the activities of the construction machinery, especially in complex environments (such as multiple machines operating at the same time), so as to determine whether the activities include excavation behavior that may pose a threat to overhead lines.

[0061] Specifically, the image data is input into the High-Resolution Network for Human Pose Estimation (HRNet) in the posture network to calculate the probability of each joint point of the construction machine; HRNet is generally based on deep learning technologies such as convolutional neural networks (CNN). It is a deep learning model specifically used to process the positioning of joints and key points of human bodies or objects in image data. It is used to identify and locate the key points or joint points of objects from image data. HRNet outputs the probability of each joint point, which is usually achieved by classifying and regressing the image data. Each pixel in the image data is assigned a probability value belonging to a certain joint point, indicating which joint point the pixel may belong to. Joint points refer to the various moving parts or connection points of a construction machine, such as the joints of a robotic arm.

[0062] The above calculated probabilities are used as response values ​​to generate heat maps for each joint of the construction machine. Heat maps are images that represent the probability distribution of each joint. Each joint has a corresponding heat map, which reflects the posture network's prediction of the joint position, usually generated by a softmax function or other probability estimation methods.

[0063] Furthermore, the heat map is downsampled, and downsampling is to improve efficiency and reduce computational complexity. Downsampling the heat map reduces the resolution of the heat map, thereby reducing the amount of computation. This process can be achieved through pooling layers, convolution operations, etc., in order to reduce redundant information and retain high-probability areas of joints.

[0064] If the heat map is downsampled, the Deep Adaptive Receptive Kernel (DARK) technology is used to restore the joint points in the heat map to sub-pixel positions. When the sub-pixel positions are restored, the rotation angles between the joint points can be calculated through geometric transformation. It is usually necessary to analyze the relative positions of the joints to calculate the rotation angles and postures of the joints of the construction machinery. The calculated rotation angles can be used to infer the active movements of the construction machinery. That is, according to the changes in the angles between the joints, the active movements of the construction machinery, such as the rotation and extension of the robotic arm, can be determined.

[0065] Step 1035: Perform spatial domain collision detection based on the activity action to determine whether the construction machinery is engaged in excavation behavior.

[0066] Spatial domain collision detection is a technology that determines whether objects or object motion trajectories collide or overlap by analyzing their relative positions in three-dimensional space. Spatial domain collision detection is widely used in fields such as computer vision, robotics, and physical simulation to help detect and avoid physical conflicts between objects. In specific applications, such as monitoring of construction machinery and overhead lines, spatial domain collision detection can identify potential dangerous behaviors in real time and prevent damage to overhead lines or safety accidents caused by the movement of construction machinery.

[0067] In this embodiment, the motion trajectory and activity of the construction machinery are located through target detection and tracking technology in the image data, and then spatial domain collision detection is performed based on the activity. The collision detection process is to analyze the spatial position relationship between the activity of the construction machinery and the overhead line, determine whether there is contact or threat, and then infer whether potential destructive activities such as excavation are being carried out, improve the accuracy and timeliness of detection, and provide a basis for the safety protection of overhead lines.

[0068] Exemplarily, the collision detection method used in the embodiment of the present invention may include but is not limited to the following:

[0069] Bounding Box-based method: Preliminary collision detection is performed by calculating whether the bounding box of the construction machinery's active motion overlaps with the bounding box of the overhead line.

[0070] Grid-based method: The three-dimensional overhead line environment and the movements of construction machinery are converted into grids, and collision is determined by detecting whether the grids overlap.

[0071] Method based on physical simulation: Use a physical engine to simulate the interaction between the movements of construction machinery and overhead lines, determine whether a collision occurs, and calculate the reaction after the collision.

[0072] The collision detection algorithms used include but are not limited to AABB (axis-aligned bounding box), OBB (oriented bounding box), and precise geometric collision detection.

[0073] Step 104: If there is excavation behavior of the construction machinery, the risk level of the excavation behavior to the overhead line is calculated based on the image data.

[0074] In this embodiment, when the system detects that the construction machinery has excavation behavior through image data, it is necessary to further analyze the possible risks of the excavation behavior to the overhead lines. The risk level of the excavation behavior to the overhead lines is calculated using the hierarchical analysis method based on the image data. The system will implement different protection strategies for the overhead lines based on the risk level. When the system does not detect the excavation behavior of the construction machinery, the automatic aircraft automatically captures the on-site image data and transmits the image data back to the local storage device for storage for subsequent analysis and tracing.

[0075] Specifically, influencing factors of the excavation behavior are extracted from the image data; the influencing factors include damage range, damage intensity and damage location, which help determine the severity of the excavation behavior and its potential harm to overhead lines.

[0076] Furthermore, the analytic hierarchy process (AHP) is used to assign weights to each influencing factor. The analytic hierarchy process is a decision support tool that compares the importance of different influencing factors and reasonably determines their relative weights in risk assessment, ensuring that the contribution of each influencing factor to the final risk assessment is accurately reflected.

[0077] Next, multiply each influencing factor by its corresponding weight value and sum them up to get a comprehensive risk value. Quantifying the impact of multiple influencing factors into a numerical value makes risk assessment more systematic, objective and automated.

[0078] Finally, based on the calculated risk value, it is mapped to the specific risk level of the excavation behavior to the overhead line, which is usually low, medium, and high, so as to facilitate the subsequent adoption of corresponding protective measures or early warnings, thereby more effectively protecting the safety of the overhead lines.

[0079] In this embodiment, after the system collects a large amount of image data, the hierarchical analysis method can be used to evaluate the degree of damage caused by the excavation behavior of the construction machinery, add risk levels to the excavation behavior, improve the image data processing and analysis capabilities, and be able to timely and accurately identify the degree of damage and impact of the excavation behavior.

[0080] Step 105: Perform safety protection on the overhead lines according to the risk level.

[0081] In this embodiment, the automatic aerial vehicle flies to the specified location information, analyzes the different risk levels (i.e., different risk levels) that the excavation behavior may cause to the overhead lines, and takes corresponding safety protection measures to ensure the safety and stability of the overhead lines, improve the response speed of overhead line inspections, and reduce the probability of failures.

[0082] Specifically, the risk level includes a preset first target level and a preset second target level, and the first target level is lower than the second target level; the preset first target level and the preset second target level can be a single level or a collection of multiple levels, which are set according to needs, and the present invention does not limit this. If the risk level is the preset first target level, the system controls the automatic aircraft to perform early warning operations to protect the overhead lines and formulate an automatic aircraft inspection plan. The early warning operation includes real-time monitoring of the overhead lines, alarm triggering of abnormal conditions, risk assessment, and automatic formulation of an automatic aircraft inspection plan, aiming to identify potential problems in advance and take action to prevent accidents and ensure the safety of overhead lines; if the risk level is the preset second target level, a task for repairing the overhead lines that is compatible with the risk level is formulated, and the task is distributed to the account of the maintenance personnel. The staff protects the overhead lines according to the issued tasks.

[0083] In an embodiment of the present invention, physical characteristic parameters related to force collected by optical fiber sensors arranged on overhead lines are received. If the physical characteristic parameters reach a preset risk threshold, the location information of the overhead lines is obtained, and the automatic aircraft is controlled to fly to the location information to collect image data to identify whether there is digging behavior of construction machinery under the overhead lines. If there is digging behavior of construction machinery, the risk level of the digging behavior to the overhead lines is calculated based on the image data, and safety protection is performed on the overhead lines based on the risk level. The inspection method based on optical fiber sensors and automatic aircraft can effectively identify potential threats to the construction site of overhead lines by real-time monitoring of physical characteristic parameters of overhead lines, accurately locating problems, automatically identifying risks of construction machinery, and performing dynamic evaluations. This method can timely evaluate the impact of digging behavior of construction machinery on the safety of overhead lines, thereby providing accurate protection, reducing line damage or safety accidents caused by construction machinery, and effectively improving the inspection efficiency and accuracy of overhead lines.

[0084] Embodiment 2

[0085] Figure 2 A schematic diagram of the structure of an overhead line inspection device provided in Embodiment 2 of the present invention is shown in FIG. Figure 2 As shown, the device comprises:

[0086] A physical characteristic parameter acquisition module 201 is used to receive physical characteristic parameters related to force acquired by optical fiber sensors arranged on overhead lines;

[0087] A location information acquisition module 202, configured to acquire the location information of the overhead line if the physical characteristic parameter reaches a preset risk threshold;

[0088] An image data acquisition module 203 is used to control the automatic aircraft to fly to the position information to collect image data to identify whether there is excavation behavior of construction machinery under the overhead line;

[0089] a risk level calculation module 204, for calculating the risk level of the overhead line caused by the excavation behavior according to the image data if there is an excavation behavior of the construction machinery;

[0090] The safety protection module 205 is used to perform safety protection on the overhead line according to the risk level.

[0091] In one embodiment of the present invention, the physical characteristic parameters include pressure parameters and / or vibration parameters; the optical fiber sensor is arranged at least one location at a corner of the overhead line, at an intersection of the overhead line, and in a support pole of the overhead line.

[0092] In one embodiment of the present invention, the location information acquisition module 202 includes:

[0093] The location information acquisition module is used to receive the location information generated by the positioning tag arranged on the optical fiber sensor as the location information of the overhead line; the positioning tag includes at least one of a radio frequency identification tag, a global positioning system and the distributed optical fiber sensing technology of the optical fiber sensor.

[0094] In one embodiment of the present invention, the image data acquisition module 203 includes:

[0095] A video data acquisition module, used to control the automatic aircraft to fly to the position information and collect video data downward; the video data includes multiple frames of image data;

[0096] A target detection module, used to perform target detection operations in the image data of each frame to detect the construction machinery;

[0097] A motion trajectory detection module, used to track the motion trajectory of the construction machinery in multiple frames of the image data when the construction machinery is detected;

[0098] An activity acquisition module, used to perform heat map positioning on the construction machine in the process of tracking the motion trajectory of the construction machine, and obtain the activity of the construction machine;

[0099] The excavation behavior judgment module is used to perform spatial domain collision detection based on the activity action to determine whether the construction machine has excavation behavior.

[0100] In one embodiment of the present invention, the motion trajectory detection module includes:

[0101] A context information positioning module, used to locate the context information of the construction machine in an outer bounding box representing the construction machine in each frame of the image data;

[0102] A motion information extraction module, used to extract the motion information of the construction machine according to the context information;

[0103] The motion trajectory acquisition module is used to associate the motion information of the construction machinery in multiple frames of image data at two levels, local and global, to obtain the motion trajectory of the construction machinery.

[0104] In one embodiment of the present invention, the activity action acquisition module includes:

[0105] A probability calculation module, used for inputting the image data into a posture network to calculate the probability of each joint point of the construction machine;

[0106] A heat map generation module, used to generate a heat map for each joint point of the construction machine using the probability as a response value;

[0107] A heat map downsampling module, used for downsampling the heat map;

[0108] The joint point rotation angle calculation module is used to restore the joint points in the heat map to sub-pixel positions if downsampling is completed, and use the sub-pixel positions to calculate the rotation angles between the joint points to obtain the active movements of the construction machinery.

[0109] In one embodiment of the present invention, the risk level calculation module 204 includes:

[0110] An influencing factor extraction module is used to extract influencing factors of the mining behavior from the image data; the influencing factors include damage range, damage intensity and damage location;

[0111] A weight value calculation module, used to query the weight value calculated for the influencing factors according to the hierarchical analysis method;

[0112] A risk value calculation module, used for summing the product between the influencing factors and the weight values ​​to obtain a risk value;

[0113] The risk level mapping module is used to map the risk value to the risk level of the excavation behavior to the overhead line.

[0114] In one embodiment of the present invention, the security protection module 205 includes:

[0115] an early warning operation module, configured to control the automatic aerial vehicle to perform an early warning operation for protecting the overhead line if the risk level is a preset first target level;

[0116] A maintenance task formulation module, for formulating a task for maintaining the overhead line adapted to the risk level if the risk level is a preset second target level, and distributing the task to an account of a maintenance personnel;

[0117] Wherein, the first target level is lower than the second target level.

[0118] The overhead line inspection device provided in the embodiment of the present invention can execute the overhead line inspection method provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the overhead line inspection method.

[0119] Embodiment 3

[0120] See also Figure 3 , showing a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. The computer device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, blade servers, mainframe computers, and other suitable computers. The computer device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0121] like Figure 3 As shown, the computer device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the computer device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0122] A number of components in the computer device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the computer device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0123] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the inspection method of the overhead line.

[0124] In some embodiments, the inspection method of the overhead line can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the computer device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the inspection method of the overhead line described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the inspection method of the overhead line in any other appropriate manner (for example, by means of firmware).

[0125] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0126] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0127] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0128] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0129] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0130] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0131] Embodiment 4

[0132] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the overhead line inspection method provided by any embodiment of the present invention is implemented.

[0133] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0134] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0135] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for inspecting an overhead line, characterized in that: include: receiving physical characteristic parameters related to force collected by optical fiber sensors arranged on overhead lines; If the physical characteristic parameter reaches a preset risk threshold, obtaining the location information of the overhead line; Controlling the automatic flying vehicle to fly to the position information to collect image data to identify whether there is digging behavior of construction machinery under the overhead line; If there is excavation behavior of the construction machinery, calculating the risk level of the excavation behavior to the overhead line based on the image data; Safety protection is performed on the overhead line according to the risk level.

2. The method according to claim 1, characterized in that The physical characteristic parameters include pressure parameters and / or vibration parameters; the optical fiber sensor is arranged at least one location at a corner of the overhead line, at a crossing of the overhead line, and in a support pole of the overhead line.

3. The method according to claim 2, characterized in that The obtaining the location information of the overhead line comprises: The location information generated by the positioning tag arranged on the optical fiber sensor is received as the location information of the overhead line; the positioning tag includes at least one of a radio frequency identification tag, a global positioning system and a distributed optical fiber sensing technology of the optical fiber sensor.

4. The method according to claim 1, characterized in that: The controlling the automatic flying vehicle to fly to the position information to collect image data to identify whether there is excavation behavior of the construction machinery under the overhead line includes: When the automatic aircraft is controlled to fly to the position information, video data is collected downward; the video data includes multiple frames of image data; performing a target detection operation in each frame of the image data to detect the construction machinery; When the construction machine is detected, tracking the motion trajectory of the construction machine in multiple frames of the image data; In the process of tracking the motion trajectory of the construction machine, the construction machine is positioned by heat map to obtain the activity of the construction machine; Spatial domain collision detection is performed based on the active action to determine whether the construction machine has any excavation behavior.

5. The method according to claim 4, characterized in that When the construction machine is detected, tracking the motion trajectory of the construction machine in multiple frames of image data includes: In each frame of the image data, locating the context information of the construction machine in an outer bounding box representing the construction machine; extracting motion information of the construction machinery according to the context information; At both local and global levels, the motion information of the construction machinery in multiple frames of image data is associated to obtain the motion trajectory of the construction machinery.

6. The method according to claim 4, characterized in that The step of performing heat map positioning on the construction machine to obtain the activity of the construction machine includes: Inputting the image data into a posture network to calculate the probability of each joint point of the construction machine; Using the probability as a response value, generating a heat map for each joint point of the construction machine; Downsampling the heat map; If downsampling is completed, the joint points in the heat map are restored to sub-pixel positions, and the rotation angles between the joint points are calculated using the sub-pixel positions to obtain the active movements of the construction machinery.

7. The method according to claim 1, characterized in that If there is an excavation behavior of the construction machinery, calculating the risk level of the excavation behavior to the overhead line according to the image data includes: Extracting the influencing factors of the mining behavior from the image data; the influencing factors include damage range, damage intensity and damage location; Query the weight value calculated for the influencing factors according to the hierarchical analysis method; Sum the products of the influencing factors and the weight values ​​to obtain a risk value; The risk value is mapped to a risk level of the excavation behavior to the overhead line.

8. The method according to any one of claims 1 to 7, characterized in that: The performing safety protection on the overhead line according to the risk level includes: If the risk level is a preset first target level, controlling the automatic aerial vehicle to perform an early warning operation to protect the overhead line; If the risk level is a preset second target level, formulating a task for repairing the overhead line adapted to the risk level, and distributing the task to an account of a maintenance personnel; Wherein, the first target level is lower than the second target level.

9. A computer device, characterized in that: The computer device comprises: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the overhead line inspection method as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the overhead line inspection method as described in any one of claims 1 to 8 is implemented.

Images