Limited space cable unmanned aerial vehicle inspection system based on GPS signal-free condition

Abstract

The invention relates to the technical field of unmanned aerial vehicles, in particular to a limited space cable unmanned aerial vehicle inspection system based on a GPS signal-free condition, which comprises an unmanned aerial vehicle navigation module, a cable detection module, an obstacle avoidance module, an environment monitoring module, a data processing and recording module and a power management module, autonomous navigation of the unmanned aerial vehicle in a limited space is realized, the cable detection module monitors the surface state of a cable based on a convolutional neural network model, the obstacle avoidance module dynamically detects obstacles and adjusts a flight path, and the environment monitoring module monitors temperature, humidity and air quality and gives an early warning when the temperature, humidity and air quality exceed a safety threshold. The data processing module processes data in real time in combination with an edge computing technology and uploads the data to a control center, and the power management module regulates and controls energy consumption through an intelligent algorithm and automatically returns or emergently lands when the electric quantity is insufficient; the method is suitable for a cable inspection task in a GPS-signal-free environment.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and in particular to a limited space cable unmanned aerial vehicle inspection system under the condition of no GPS signal. Background Art

[0002] In the maintenance of infrastructure such as electricity and communications, cable inspection is an important task to ensure the normal operation of the system. However, traditional manual inspection methods are inefficient and costly, and there are high safety risks in complex and dangerous environments (such as confined spaces such as tunnels and underground facilities). In recent years, drone inspection technology has gradually attracted attention due to its flexibility and efficiency, especially the ability to realize automated detection of cables. However, most of the current drone inspection systems rely on GPS signals for navigation and positioning, which is impossible in confined spaces because GPS signals are easily interfered with or completely unreceivable in closed or complex environments such as underground and tunnels.

[0003] Existing technologies cannot effectively solve the problems of autonomous navigation, obstacle avoidance, and accuracy of cable detection of UAVs in the absence of GPS signals. In addition, existing UAV inspection systems also face many challenges in battery management and endurance. Inspection tasks in confined spaces usually take a long time, and the battery life of UAVs is limited. If the battery runs out, the UAV may face the risk of accidental falling. Therefore, there is an urgent need for a UAV system that can adapt to environments without GPS signals and has efficient inspection capabilities. Summary of the invention

[0004] The present invention provides a limited space cable drone inspection system under the condition of no GPS signal.

[0005] The limited space cable drone inspection system based on the condition of no GPS signal includes drone navigation module, cable detection module, obstacle avoidance module, environmental monitoring module, data processing and recording module and power management module, among which;

[0006] The UAV navigation module is used to realize autonomous navigation of the UAV in a limited space. The navigation module adopts the visual SLAM (simultaneous localization and mapping) technology to realize accurate positioning and path planning of the UAV by matching the images collected by the camera with the environmental feature points;

[0007] The cable detection module is combined with the drone's onboard camera and infrared sensor to detect the cable surface status in real time. The cable detection module uses deep learning-based image recognition technology to analyze the wear, breakage and aging of the cable and generate corresponding alarm signals.

[0008] The obstacle avoidance module is used to identify obstacles in a complex limited space and effectively avoid them. The obstacle avoidance module combines ultrasonic sensors, infrared sensors and radar technology to perceive obstacles in the environment in real time and avoid collisions with obstacles through a path adjustment algorithm;

[0009] The environmental monitoring module is used to monitor environmental data within a limited space, including temperature, humidity and air quality, and make judgments based on preset safety thresholds. If environmental conditions exceed the threshold, the system will automatically issue an early warning to ensure the safety of drone and cable inspection tasks.

[0010] The data processing and recording module is used to process and record the cable surface status and environmental data collected during the inspection in real time. The data processing and recording module combines edge computing technology to realize real-time data analysis and transmit the analysis results to the ground control center through a preset wireless communication unit for subsequent processing and decision-making;

[0011] The power management module is used to monitor and manage the battery power of the drone when it conducts long-term inspections in a limited space. The power management module adopts an intelligent power management algorithm to dynamically adjust the energy consumption of the drone to ensure the smooth completion of the inspection mission. When the battery is low, the drone will automatically return to the charging station or make an emergency landing.

[0012] Optionally, the drone navigation module specifically includes:

[0013] Image acquisition: The drone continuously collects environmental images through the camera installed on its front end and generates an environmental map through visual SLAM technology;

[0014] Feature point extraction and matching: Extract environmental feature points from the collected environmental images, use the ORB algorithm, FAST corner detector and BRIEF descriptor to detect and describe feature points. The ORB algorithm calculates the brightness difference between adjacent pixels to determine the corner points in the image, generates feature descriptors, and matches feature points through Hamming distance calculation;

[0015] Position estimation: Based on the matched feature point pairs, the relative position of the drone is calculated using the camera projection geometry.

[0016] Posture optimization: BA algorithm is used to globally optimize the posture of the UAV;

[0017] Path planning: Based on the environment map generated by visual SLAM, the D*Lite algorithm is used for path planning.

[0018] Optionally, the cable detection module specifically includes:

[0019] Data collection: The surface status of the cable is continuously collected through the drone’s onboard high-definition camera and infrared sensor;

[0020] Image preprocessing: preprocess the collected images, use the median filter algorithm to remove noise, and grayscale and edge enhance the images to improve the recognition effect of cable defects;

[0021] Feature extraction: Use a convolutional neural network model to extract features from images of the cable surface. The convolutional neural network model includes multiple convolutional layers, pooling layers, and fully connected layers. It automatically learns the structural features of the cable surface and identifies abnormal conditions such as wear, damage, and aging of the cable surface.

[0022] Cable status classification: The extracted features are mapped into feature vectors of fixed dimensions through the fully connected layer, and the Softmax classifier is used to classify the status of the cable surface. The output categories include normal, worn, damaged, and aged.

[0023] Alarm generation: Based on the classification results, the system generates corresponding alarm signals. When the cable surface condition is detected as "worn", "damaged" or "aged", the system sends the alarm signal to the ground control center through the preset wireless communication unit, and records the fault information and marks the location of the problem area.

[0024] Optionally, the obstacle avoidance module specifically includes:

[0025] Multi-sensor obstacle detection: Use ultrasonic sensors, infrared sensors and radars to simultaneously detect obstacles in the environment;

[0026] Obstacle position estimation: Combined with multi-sensor obstacle detection data, the Kalman filter algorithm is used to fusion estimate the obstacle position information;

[0027] Dynamic path planning: Based on obstacle position estimation, the D*Lite algorithm is used to re-plan the path;

[0028] Obstacle avoidance execution: adjust the flight speed and direction of the drone according to the new path planned by the D*Lite algorithm;

[0029] Adaptive path update: During the flight of the drone, the obstacle avoidance module dynamically adjusts the path according to the movement trajectory of the obstacles.

[0030] Optionally, the environment monitoring module specifically includes:

[0031] Environmental data collection: The environmental monitoring module collects temperature, humidity and air quality data in real time through multiple sensors;

[0032] Data preprocessing: The collected environmental data is preprocessed by using a low-pass filter to remove sensor noise, and the temperature and humidity data are processed using a moving average filter algorithm;

[0033] Safety threshold judgment: The system makes real-time judgments on environmental data based on preset safety thresholds;

[0034] Warning signal generation: When the environmental data is detected to exceed the safety threshold, the environmental monitoring module generates a warning signal and transmits the warning information to the ground control center through the preset wireless communication unit;

[0035] Real-time feedback and adjustment: After issuing a warning signal, the environmental monitoring module adjusts the mission parameters of the drone in real time based on the detected abnormal conditions.

[0036] Optionally, the data processing and recording module specifically includes:

[0037] Data collection and integration: The data processing and recording module collects cable surface status data and environmental data from the cable detection module and the environmental monitoring module respectively, and integrates the collected data synchronously according to the timestamp;

[0038] Data preprocessing: preprocess the collected cable status data and environmental data, including noise filtering and data normalization;

[0039] Edge computing analysis: Use edge computing nodes deployed on drones to perform real-time analysis of cable status data and environmental data;

[0040] Data recording and storage: The data processing and recording module stores the analyzed results and raw data in the local storage device;

[0041] Wireless data transmission: Through the preset wireless communication unit, the data processing and recording module transmits the analysis results to the ground control center;

[0042] Real-time feedback and adjustment: After receiving the analysis results, if the ground control center detects that the cable is severely worn or the environmental data exceeds the safety threshold, it will send adjustment instructions to the drone through the wireless communication unit.

[0043] Optionally, the power management module specifically includes:

[0044] Real-time power monitoring: The power management module monitors the remaining power, voltage and current of the battery in real time through the battery management system integrated in the drone;

[0045] Dynamic adjustment of energy consumption: The power management module dynamically adjusts the energy consumption of the drone based on the remaining battery power and the current mission requirements of the drone;

[0046] Emergency strategy for low battery: When the battery power drops to 10%, the power management module automatically triggers the emergency strategy.

[0047] Optionally, the power management module further includes:

[0048] Battery health management: The power management module monitors the battery health. If the battery health drops below 80%, the system will issue an alarm to remind the battery that it needs to be replaced or maintained.

[0049] Data recording and analysis: Power monitoring and battery health data are recorded and stored through the data processing and recording module.

[0050] Optionally, the preset wireless communication unit uses the 5G network for high-bandwidth and low-latency data transmission. During the transmission process, the data is encrypted using the AES encryption algorithm to ensure the security of the data during transmission.

[0051] Beneficial effects of the present invention:

[0052] The present invention realizes autonomous navigation and efficient obstacle avoidance capabilities of the UAV in the absence of GPS signals by adopting a UAV navigation module and obstacle avoidance module based on visual SLAM. The UAV navigation module uses a camera to collect and match environmental feature points in real time, and combines the ORB algorithm, Kalman filter algorithm and D*Lite path planning algorithm to ensure accurate positioning and path planning of the UAV in a limited space. The obstacle avoidance module detects obstacles in real time and dynamically adjusts the flight path by integrating ultrasonic sensors, infrared sensors and radar technology, ensuring that the UAV can avoid obstacles in complex environments, significantly improving the safety and reliability of inspection tasks, and is particularly suitable for complex and confined spaces such as tunnels and underground facilities.

[0053] In the present invention, the cable detection module realizes real-time monitoring of the cable surface status by combining the convolutional neural network model and multi-sensor data fusion technology, and can accurately identify wear, breakage and aging problems. Combined with edge computing technology, cable detection data can be processed in real time, reducing data transmission delays and improving the real-time nature of cable status judgment. At the same time, the environmental monitoring module monitors temperature, humidity and air quality in real time, and makes judgments based on preset safety thresholds to ensure that inspection tasks are carried out under appropriate environmental conditions. When the environment exceeds the safety threshold, the system automatically sends a warning signal, further ensuring the safety of drone and cable detection tasks.

[0054] In the present invention, the power management module adopts an intelligent power management algorithm to dynamically monitor and manage the battery power of the drone. When the battery is low, the system can reduce the flight speed and turn off non-critical sensors through a dynamic energy consumption adjustment mechanism to extend the inspection time. At the same time, the power management module automatically triggers emergency strategies when the battery is lower than the set threshold, including automatic return to the charging station or emergency landing to ensure that the drone lands safely before the battery is exhausted. This intelligent management solution significantly improves the endurance and mission completion rate of drones in limited space inspection tasks, and reduces the risks caused by power exhaustion. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the present invention or 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 in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1 is a system schematic diagram of an embodiment of the present invention;

[0057] Figure 2 The figure is a schematic diagram of the cable detection module flow in an embodiment of the present invention. DETAILED DESCRIPTION

[0058] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0059] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0060] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0061] like Figure 1-Figure 2 As shown, the limited space cable UAV inspection system based on the condition of no GPS signal includes a UAV navigation module, a cable detection module, an obstacle avoidance module, an environmental monitoring module, a data processing and recording module and a power management module, wherein;

[0062] The UAV navigation module is used to realize autonomous navigation of the UAV in a limited space. The navigation module adopts the visual SLAM (simultaneous localization and mapping) technology to achieve accurate positioning and path planning of the UAV by matching the images collected by the camera with the environmental feature points.

[0063] The cable detection module is combined with the drone's onboard camera and infrared sensor to detect the cable surface status in real time. The cable detection module uses deep learning-based image recognition technology to analyze the wear, breakage and aging of the cable and generate corresponding alarm signals.

[0064] The obstacle avoidance module is used to identify obstacles and avoid them effectively in a complex and limited space. The obstacle avoidance module combines ultrasonic sensors, infrared sensors and radar technology to sense obstacles in the environment in real time and avoid collisions with obstacles through path adjustment algorithms.

[0065] The environmental monitoring module is used to monitor environmental data within a limited space, including temperature, humidity and air quality, and make judgments based on preset safety thresholds. If environmental conditions exceed the threshold, the system will automatically issue an early warning to ensure the safety of drone and cable inspection tasks.

[0066] The data processing and recording module is used to process and record the cable surface status and environmental data collected during the inspection in real time. The data processing and recording module combines edge computing technology to realize real-time data analysis and transmit the analysis results to the ground control center through a preset wireless communication unit for subsequent processing and decision-making;

[0067] The power management module is used to monitor and manage the battery power of the drone when it is patrolling for a long time in a limited space. The power management module adopts an intelligent power management algorithm to dynamically adjust the energy consumption of the drone to ensure the smooth completion of the inspection mission. When the battery is low, the drone will automatically return to the charging station or make an emergency landing.

[0068] The drone navigation module specifically includes:

[0069] Image acquisition: The drone continuously collects environmental images through the camera installed on its front end. The image frame rate is 30 frames per second, ensuring that the drone captures the visual information of the environment in real time during flight. The camera has high-definition resolution and wide-angle field of view, so as to obtain more complete environmental information in a limited space, and generate environmental maps through visual SLAM technology;

[0070] Feature point extraction and matching: Extract environmental feature points from the collected environmental images, use the ORB (OrientedFAST and Rotated BRIEF) algorithm, use the FAST corner detector and BRIEF descriptor to detect and describe feature points. The ORB algorithm calculates the brightness difference between adjacent pixels to determine the corner points in the image and generates feature descriptors. The feature points are matched by Hamming distance calculation. The Hamming distance calculation is expressed as:

[0071]

[0072] Among them, D(p,q) represents the Hamming distance between feature points p and q, p i and q i is the binary value of the corresponding position of the descriptor, n is the length of the descriptor, represents the XOR operation, which ensures the relevance of environmental information by matching feature point pairs in the image;

[0073] Position estimation: Based on the matched feature point pairs, the relative position of the drone is calculated using the camera projection geometry. The pose estimation of the drone is expressed as:

[0074] P = K[R|t];

[0075] Among them, P is the projection matrix of the image, K is the camera internal parameter matrix, R is the rotation matrix, which represents the change of the drone's posture, and t is the translation vector, which represents the displacement change of the drone;

[0076] The current position of the drone is calculated by combining the known parameters of the camera's internal and external parameters with the position changes of feature points in multiple frames of images.

[0077] Posture optimization: The BA (Bundle Adjustment) algorithm is used to globally optimize the posture of the drone. The BA algorithm optimizes the posture parameters by minimizing the reprojection error, which is expressed as:

[0078]

[0079] Where E is the total error, xi is the actual observed image coordinate, is the predicted image coordinates obtained based on the pose estimation, n is the number of observation points, and the positioning error is reduced by jointly optimizing the poses of multiple image frames;

[0080] Path planning: Based on the environment map generated by visual SLAM, the D*Lite algorithm is used for path planning. The path planning formula of the D*Lite algorithm is:

[0081]

[0082] Where h(s) is the heuristic cost of state s, A(s) is the set of possible actions in state s, c(s,a) is the cost of the action between state s and state s′, and g(s′) is the estimated cost of the subsequent state;

[0083] The drone dynamically adjusts its path to avoid obstacles and reach the target location;

[0084] The UAV navigation module uses the ORB algorithm to extract and match feature points, combines the projection matrix to calculate the position of the UAV, performs global optimization through the BA algorithm, and then uses the D*Lite algorithm for path planning to ensure the UAV's autonomous navigation accuracy and path planning efficiency in a limited space.

[0085] The cable detection module specifically includes:

[0086] Data collection: The surface status of the cable is continuously collected through the drone's onboard high-definition camera and infrared sensor. The camera obtains visible light images, and the infrared sensor is used to detect changes in the surface temperature of the cable. The frame rate of image acquisition is 30 frames per second, ensuring that high-resolution images can capture tiny defects in the cable.

[0087] Image preprocessing: The collected images are preprocessed, and the median filter algorithm is used to remove noise, and the images are grayed and edge enhanced to improve the recognition effect of cable defects. The preprocessed images are normalized to ensure the consistency of brightness and contrast of the subsequent deep learning model input images;

[0088] Feature extraction: Use a convolutional neural network model to extract features from images of the cable surface. The convolutional neural network model includes multiple convolutional layers, pooling layers, and fully connected layers. It automatically learns the structural features of the cable surface and identifies abnormal conditions such as wear, damage, and aging of the cable surface. The convolution kernel size is 3×3, and the activation function is ReLU (Rectified Linear Unit). The output feature map is further reduced in dimension through the maximum pooling layer to ensure the efficiency and accuracy of the calculation.

[0089] Cable status classification: The extracted features are mapped into a feature vector of fixed dimension through the fully connected layer, and the Softmax classifier is used to classify the status of the cable surface. The output categories include normal, worn, damaged and aged. The expression of the Softmax function is:

[0090]

[0091] Where P(y=i|x) represents the probability that the cable surface state is of the i-th category, x is the feature vector, θ i is the weight vector of the i-th category, k is the number of classification categories, and according to the probability value output by Softmax, the category corresponding to the maximum probability is selected as the current state of the cable;

[0092] Alarm generation: Based on the classification results, the system generates corresponding alarm signals. When the cable surface condition is detected as "worn", "damaged" or "aged", the system sends the alarm signal to the ground control center through the preset wireless communication unit, and records the fault information and marks the location of the problem area. The triggering of the alarm signal is based on the set classification probability threshold. When the probability of the classification result exceeds 90%, the system considers the detection to be accurate and triggers the alarm;

[0093] The cable detection module analyzes the cable surface status in real time and combines the flight path information of the drone to dynamically adjust the camera's viewing angle and the sensor's acquisition parameters. Through feedback control, it ensures the real-time and accuracy of cable detection and reduces detection errors caused by flight jitter or environmental interference.

[0094] The cable detection module extracts and classifies the cable surface status through deep learning convolutional neural network, realizes real-time detection of cable wear, breakage and aging problems, and calculates the probability of cable status through Softmax classifier.

[0095] The obstacle avoidance module specifically includes:

[0096] Multi-sensor obstacle detection: Use ultrasonic sensors, infrared sensors and radars to simultaneously detect obstacles in the environment;

[0097] Ultrasonic sensors are used for close-range obstacle detection, with a detection range of 0.2 meters to 5 meters, and can sense the distance and size of obstacles;

[0098] Infrared sensors are used to identify obstacles with smooth surfaces or that are difficult to identify visually. They have a detection accuracy of ±0.05 meters and are suitable for working in low-light or strong-light environments.

[0099] Radar is used for long-range obstacle detection with a detection range of up to 50 meters, mainly used to locate large obstacles in front of the drone's flight path;

[0100] Obstacle position estimation: Combining multi-sensor obstacle detection data, the Kalman filter algorithm is used to fusion estimate the obstacle position information. The state estimation equation of the Kalman filter is:

[0101]

[0102] in, is the estimated position of the obstacle at the current moment, z k is the sensor measurement value, H is the measurement matrix, which defines the actual obstacle position observed by the sensor, and K k is the Kalman gain, and the calculation formula is:

[0103] K k =P k-1 H T (HP k-1 H T +R) -1 ;

[0104] Among them, P k-1 is the covariance matrix of the previous moment, and R is the covariance matrix of the measurement noise;

[0105] By fusing data from multiple sensors, the accuracy of obstacle position estimation is ensured;

[0106] Dynamic path planning: Based on obstacle position estimation, the D*Lite algorithm is used to re-plan the path. The D*Lite algorithm can dynamically update the path in a complex environment. When an obstacle is detected, the system recalculates the optimal path to avoid the obstacle and ensure the safe flight of the drone. The planning formula of D*Lite is:

[0107]

[0108] Among them, g(s) is the cost function of state s, A(s) is the set of actions that can be taken in state s, and c(s,a) is the state s entering state s through action a. ′ The cost, g(s ′ ) is state s ′ the estimated cost of

[0109] Through continuous iteration, the flight path is dynamically adjusted to avoid obstacles;

[0110] Obstacle avoidance execution: According to the new path planned by the D*Lite algorithm, the flight speed and direction of the drone are adjusted. By controlling the attitude and acceleration of the drone, the drone is ensured to avoid obstacles smoothly and continue to perform inspection tasks. The flight control formula is:

[0111]

[0112] Among them, a t is the acceleration control value of the UAV, v d is the expected speed, v c is the current speed, is the expected acceleration, is the current acceleration, K p and K d are the proportional and differential gain coefficients, which ensure safe obstacle avoidance by controlling the flight parameters of the drone;

[0113] Adaptive path update: During the flight of the drone, the obstacle avoidance module dynamically adjusts the path according to the moving trajectory of the obstacle. When the obstacle moves, the system updates the flight path in real time to ensure the drone's flexible obstacle avoidance ability in complex environments. The adaptive update algorithm combines the drone's flight status with the relative speed of the obstacle to ensure the continuity of the obstacle avoidance process;

[0114] The obstacle avoidance module uses multi-sensor fusion technology to achieve real-time detection of obstacles, and combines the Kalman filter algorithm to accurately estimate the obstacle position. It uses the D*Lite dynamic path planning algorithm to update the flight path in real time, and uses the acceleration control formula to ensure that the drone can safely avoid obstacles in a limited space, further improving the stability and safety of inspection tasks.

[0115] The environmental monitoring module specifically includes:

[0116] Environmental data collection: The environmental monitoring module collects temperature, humidity and air quality data in real time through multiple sensors, as follows:

[0117] Temperature sensor: collects ambient temperature data, with a temperature detection range of -40°C to 85°C;

[0118] Humidity sensor: detects relative humidity, the humidity range is 0% to 100%;

[0119] Air quality sensor: Analyze air quality in real time by detecting the concentration of carbon dioxide, carbon monoxide and volatile organic compounds;

[0120] Data preprocessing: The collected environmental data is preprocessed by using a low-pass filter to remove sensor noise. The temperature and humidity data are processed using a moving average filter algorithm. The formula is as follows:

[0121]

[0122] in, is the smoothed value at time t, x(ti) is the measured value at the previous N moments, and N is the window size, ensuring that the environmental data is stable and has no mutations;

[0123] Safety threshold judgment: The system makes real-time judgments on environmental data based on the preset safety threshold. The threshold judgment formula is:

[0124]

[0125] Among them, F(x) is the threshold judgment result, x is the environmental data value, T min and T max The preset minimum and maximum safety thresholds;

[0126] For temperature, the threshold range is set as: T min =0℃,T max =50℃;

[0127] For humidity, the threshold range is set as: T min =30,T max =70;

[0128] For air quality, the threshold value of carbon dioxide is T max =1000ppm, the threshold of carbon monoxide is T max =10ppm, the threshold value of volatile organic matter is T m ax=500ppm.

[0129] When the detected environmental data exceeds the above threshold range, the system will trigger the alarm mechanism;

[0130] Warning signal generation: When it is detected that the environmental data exceeds the safety threshold, the environmental monitoring module generates a warning signal and transmits the warning information to the ground control center through the preset wireless communication unit. The content of the warning signal includes the type of data exceeding the threshold (such as temperature, humidity or air quality), the detection value and the time period exceeding the range;

[0131] Real-time feedback and adjustment: After the environmental monitoring module issues a warning signal, it adjusts the mission parameters of the drone in real time according to the detected abnormal conditions. If the temperature or air quality exceeds the safety threshold, the system adjusts the flight altitude or mission path of the drone to avoid dangerous areas and ensure the safety of the drone and cable inspection mission.

[0132] The environmental monitoring module uses temperature and humidity sensors and air quality sensors, combined with preset safety thresholds, to monitor and warn environmental data in real time. The module ensures the accuracy of monitoring data through noise filtering and threshold judgment, and automatically issues warning signals under abnormal environmental conditions, ensuring the safe flight of drones in complex environments and the smooth progress of inspection tasks.

[0133] The data processing and recording module specifically includes:

[0134] Data collection and integration: The data processing and recording module collects cable surface status data and environmental data from the cable detection module and the environmental monitoring module respectively, and integrates the collected data synchronously according to timestamps to ensure that various types of data can be correlated and analyzed;

[0135] Data preprocessing: The collected cable status data and environmental data are preprocessed, including noise filtering and data normalization. The cable status data is filtered through a Gaussian filter to remove image noise, and the environmental data is normalized.

[0136] Edge computing analysis: Use edge computing nodes deployed on drones to perform real-time analysis of cable status data and environmental data, including:

[0137] Cable status analysis: The cable image data is processed through a convolutional neural network model to analyze whether there are abnormal conditions such as wear, damage, and aging;

[0138] Environmental data analysis: Environmental data is judged in real time through edge computing nodes, and temperature, humidity, and air quality are evaluated based on the set safety thresholds to determine whether the current environmental conditions are suitable for continuing the inspection task;

[0139] Data recording and storage: The data processing and recording module stores the analysis results and raw data in the local storage device. The stored data includes cable surface inspection results, environmental parameters and the flight status of the drone. Data recording uses compression storage technology to store large-scale image data through lossless compression to reduce storage space occupation;

[0140] Wireless data transmission: Through the preset wireless communication unit, the data processing and recording module transmits the analysis results to the ground control center;

[0141] Real-time feedback and adjustment: After receiving the analysis results, if the ground control center detects that the cable is severely worn or the environmental data exceeds the safety threshold, it will send adjustment instructions to the drone through the wireless communication unit, including changing the flight path, reducing the flight speed or suspending the inspection task. The real-time feedback mechanism ensures that the drone can dynamically adjust the task execution according to environmental changes and detection results;

[0142] The data processing and recording module processes and analyzes data locally through edge computing technology, realizing real-time judgment of cable status and environmental data during the inspection process. The module transmits the results securely to the ground control center through the wireless communication unit, and adjusts the inspection tasks of the drone through the real-time feedback mechanism to ensure the efficiency and safety of the inspection tasks.

[0143] The power management module specifically includes:

[0144] Real-time power monitoring: The power management module monitors the remaining power, voltage and current of the battery in real time through the battery management system integrated in the drone;

[0145] Dynamic adjustment of energy consumption: The power management module dynamically adjusts the energy consumption of the drone according to the remaining battery power and the current mission requirements of the drone. The adjustment methods include:

[0146] Flight speed adjustment: When the battery power drops to a preset critical value (e.g. 30%), the power management module automatically reduces the flight speed of the drone to reduce energy consumption;

[0147] Power consumption optimization of sensors and modules: When the battery power is less than 20%, non-critical sensors (such as infrared sensors) and auxiliary functions (such as indicator lights, etc.) will be automatically turned off to save power, leaving only core modules (such as drone navigation, obstacle avoidance, and data processing and recording modules) in working state;

[0148] Emergency strategy for low battery: When the battery power drops to 10%, the power management module automatically triggers the emergency strategy, which includes:

[0149] (1) Automatic return to charging station: If the drone is within a safe range (e.g., within 500 meters) of the preset charging station, the power management module will trigger the drone's automatic return function and plan the shortest path back to the charging station. The return path is calculated in real time by the drone navigation module based on the current drone position and flight status.

[0150] (2) Emergency landing: If the drone cannot return to the charging station before the battery runs out, the power management module will trigger the emergency landing procedure. At this time, the drone will automatically land in the nearest and safest area.

[0151] The power management module monitors the battery power in real time and dynamically adjusts the energy consumption of the drone. When the battery is low, the module triggers the automatic return or emergency landing procedure to ensure the safety and efficiency of the drone in complex inspection tasks.

[0152] The power management module further includes:

[0153] Battery health management: The power management module monitors the battery health to ensure the reliability of the battery in the inspection task. If the battery health drops below 80%, the system will issue an alarm to remind the battery that it needs to be replaced or maintained. The battery health is calculated as:

[0154]

[0155] Among them, SoH represents the long-term health of the battery, Q current is the maximum charge capacity of the current battery, Q ratedis the rated charging capacity of the battery;

[0156] Data recording and analysis: Power monitoring and battery health data are recorded and stored through the data processing and recording module, including the number of battery charge and discharge cycles, energy consumption of each mission, and emergency event records (such as the number of emergency landings, etc.).

[0157] The preset wireless communication unit uses the 5G network for high-bandwidth and low-latency data transmission. The data is encrypted using the AES encryption algorithm during the transmission process to ensure the security of the data during transmission. The transmitted data includes cable surface status detection results, environmental data analysis results, alarm model, flight trajectory, mission progress and other information.

[0158] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0159] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. Based on the limited space cable drone inspection system without GPS signal, it is characterized by: It includes UAV navigation module, cable detection module, obstacle avoidance module, environmental monitoring module, data processing and recording module and power management module, among which; The UAV navigation module is used to realize autonomous navigation of the UAV in a limited space. The navigation module adopts the visual SLAM technology to realize the positioning and path planning of the UAV by matching the images collected by the camera with the environmental feature points; The cable detection module is combined with the drone's onboard camera and infrared sensor to detect the cable surface status in real time. The cable detection module uses deep learning-based image recognition technology to analyze the wear, breakage and aging of the cable and generate corresponding alarm signals. The obstacle avoidance module is used to identify obstacles in a complex limited space and effectively avoid them. The obstacle avoidance module combines ultrasonic sensors, infrared sensors and radar technology to perceive obstacles in the environment in real time and avoid collisions with obstacles through a path adjustment algorithm; The environmental monitoring module is used to monitor environmental data within a limited space, including temperature, humidity and air quality, and make judgments based on preset safety thresholds. If environmental conditions exceed the threshold, the system will automatically issue an early warning. The data processing and recording module is used to process and record the cable surface status and environmental data collected during the inspection in real time. The data processing and recording module combines edge computing technology to realize real-time data analysis and transmit the analysis results to the ground control center through a preset wireless communication unit; The power management module is used to monitor and manage the battery power of the drone when it is patrolling for a long time in a limited space. The power management module adopts an intelligent power management algorithm to dynamically adjust the energy consumption of the drone. When the power is low, the drone will automatically return to the charging station or make an emergency landing.

2. The limited space cable drone inspection system based on the condition of no GPS signal according to claim 1 is characterized in that: The drone navigation module specifically includes: Image acquisition: The drone continuously collects environmental images through the camera installed on its front end and generates an environmental map through visual SLAM technology; Feature point extraction and matching: Extract environmental feature points from the collected environmental images, use the ORB algorithm, use the FAST corner detector and BRIEF descriptor to detect and describe the feature points, and match the feature points through Hamming distance calculation; Position estimation: Based on the matched feature point pairs, the relative position of the drone is calculated using the camera projection geometry relationship; Posture optimization: BA algorithm is used to globally optimize the posture of the UAV; Path planning: Based on the environment map generated by visual SLAM, the D*Lite algorithm is used for path planning.

3. The limited space cable drone inspection system based on the condition of no GPS signal according to claim 2 is characterized in that: The cable detection module specifically includes: Data collection: The drone's onboard camera and infrared sensor are used to continuously collect images of the cable's surface status; Image preprocessing: preprocess the collected images, use the median filter algorithm to remove noise, and grayscale and edge enhance the images to improve the recognition effect of cable defects; Feature extraction: Use a convolutional neural network model to extract features from images of the cable surface. The convolutional neural network model includes multiple convolutional layers, pooling layers, and fully connected layers. It automatically learns the structural features of the cable surface and identifies abnormal conditions such as wear, damage, and aging of the cable surface. Cable status classification: The extracted features are mapped into feature vectors of fixed dimensions through the fully connected layer, and the Softmax classifier is used to classify the status of the cable surface. The output categories include normal, worn, damaged, and aged. Alarm generation: Based on the classification results, the system generates corresponding alarm signals. When the cable surface condition is detected as worn, damaged or aged, the system sends the alarm signal to the ground control center through the preset wireless communication unit, and records the fault information and marks the location of the problem area.

4. The limited space cable drone inspection system based on the condition of no GPS signal according to claim 3 is characterized in that: The obstacle avoidance module specifically includes: Multi-sensor obstacle detection: Use ultrasonic sensors, infrared sensors and radars to simultaneously detect obstacles in the environment; Obstacle position estimation: Combined with multi-sensor obstacle detection data, the Kalman filter algorithm is used to fusion estimate the obstacle position information; Dynamic path planning: Based on obstacle position estimation, the D*Lite algorithm is used to re-plan the path; Obstacle avoidance execution: adjust the flight speed and direction of the drone according to the new path planned by the D*Lite algorithm; Adaptive path update: During the flight of the drone, the obstacle avoidance module dynamically adjusts the path according to the movement trajectory of the obstacles.

5. The limited space cable drone inspection system based on the condition of no GPS signal according to claim 4 is characterized in that: The environmental monitoring module specifically includes: Environmental data collection: The environmental monitoring module collects temperature, humidity and air quality data in real time through multiple sensors; Data preprocessing: The collected environmental data is preprocessed by using a low-pass filter to remove sensor noise, and the temperature and humidity data are processed using a moving average filter algorithm; Safety threshold judgment: The system makes real-time judgments on environmental data based on preset safety thresholds; Warning signal generation: When the environmental data is detected to exceed the safety threshold, the environmental monitoring module generates a warning signal and transmits the warning information to the ground control center through the preset wireless communication unit; Real-time feedback and adjustment: After issuing a warning signal, the environmental monitoring module adjusts the mission parameters of the drone in real time based on the detected abnormal conditions.

6. The limited space cable drone inspection system based on the condition of no GPS signal according to claim 5 is characterized in that: The data processing and recording module specifically includes: Data collection and integration: The data processing and recording module collects cable surface status data and environmental data from the cable detection module and the environmental monitoring module respectively, and integrates the collected data synchronously according to the timestamp; Data preprocessing: preprocess the collected cable status data and environmental data, including noise filtering and data normalization; Edge computing analysis: Use edge computing nodes deployed on drones to perform real-time analysis of cable status data and environmental data; Data recording and storage: The data processing and recording module stores the analyzed results and raw data in the local storage device; Wireless data transmission: Through the preset wireless communication unit, the data processing and recording module transmits the analysis results to the ground control center; Real-time feedback and adjustment: After receiving the analysis results, if the ground control center detects that the cable is severely worn or the environmental data exceeds the safety threshold, it will send adjustment instructions to the drone through the wireless communication unit.

7. The limited space cable drone inspection system based on the condition of no GPS signal according to claim 1 is characterized in that: The power management module specifically includes: Real-time power monitoring: The power management module monitors the remaining power, voltage and current of the battery in real time through the battery management system integrated in the drone; Dynamic adjustment of energy consumption: The power management module dynamically adjusts the energy consumption of the drone based on the remaining battery power and the current mission requirements of the drone; Emergency strategy for low battery: When the battery power drops to 10%, the power management module automatically triggers the emergency strategy.

8. The limited space cable drone inspection system based on the condition of no GPS signal according to claim 7 is characterized in that: The power management module further comprises: Battery health management: The power management module monitors the battery health. If the battery health drops below 80%, the system will issue an alarm to remind the battery that it needs to be replaced or maintained. Data recording and analysis: Power monitoring and battery health data are recorded and stored through the data processing and recording module.

9. The limited space cable drone inspection system based on the condition of no GPS signal according to claim 6 is characterized in that: The preset wireless communication unit uses a 5G network for data transmission, and the data is encrypted using an AES encryption algorithm during the transmission process.

Images