Blasting hidden danger troubleshooting system based on unmanned aerial vehicle tomography

Abstract

The invention provides a blasting hidden danger troubleshooting system based on unmanned aerial vehicle tomography, and the system comprises a data collection assembly which carries out the three-dimensional modeling and tomography of a blasting target region through an unmanned aerial vehicle carrying a laser radar or a multispectral sensor, and generates high-resolution point cloud data and a tomographic image; the risk assessment assembly analyzes the point cloud data and the cross-sectional image, automatically identifies blasting hidden dangers such as rock mass looseness, crack propagation and geological faults, performs risk assessment in combination with a geomechanical model, and generates a hidden danger distribution diagram and a risk level report; the dynamic early warning assembly monitors a blasting key area for a long time, the unmanned aerial vehicle scans a blasting target area regularly, and a three-dimensional model and hidden danger data are updated in real time; and when hidden danger change is detected, an early warning mechanism is automatically triggered, and early warning information is pushed through a visual interface or a mobile terminal. The invention provides an intelligent and efficient blasting safety monitoring and early warning system, and the safety of blasting engineering is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer vision technology, and particularly to a blasting hazard detection system based on UAV tomography. Background Art

[0002] Blasting hazard detection is a very important task, mainly for comprehensive safety inspections of places, equipment, and operation processes involving blasting operations, aiming to discover and eliminate potential safety hazards to ensure the safety and controllability of blasting operations. This work is usually responsible for by professional blasting engineers or safety management personnel, involving detailed inspections of various aspects such as blasting equipment, blasting environment, and operation specifications. Blasting operations are usually applied in fields such as mine exploitation, tunnel construction, and water conservancy projects, and the geological conditions in these areas are complex and variable. The stability of rock masses is directly related to blasting safety, so it is necessary to conduct in-depth research on the structure, fracture distribution, mechanical properties, etc. of rock masses. Traditional geological exploration mainly relies on means such as manual drilling and ground penetrating radar, but these methods have problems such as low efficiency, high cost, and limited coverage. In recent years, with the progress of rock mechanics theory and detection technology, high-precision geological modeling and hazard identification have become possible.

[0003] Prior Art One, Application No.: CN 202411019273.0 discloses a method for quickly detecting unexploded detonators at the post-blasting operation site, including a sticker-type wireless transmission device and a mobile detector supporting the wireless transmission device. The wireless transmission device is an RFID electronic tag; the wireless transmission device is loaded into the blasting hole together with the detonator. After blasting, if the detonator is successfully detonated, the sensor of the accompanying wireless transmission device is damaged; if the detonator fails to blast, the sensor of the accompanying wireless transmission device remains intact; the unexploded detonator receives the signal emitted by the wireless transmission device through the mobile detector, so as to locate and find it at the blasting operation site. Although all detonator data can be completely collected, the accurate information such as the number and landing point of unexploded detonators can be safely and quickly detected, avoiding the safety hazards brought by the uncertainty of detecting unexploded detonators, being convenient to carry and operate, and applicable to harsh environments such as chamber excavation; however, the installation of the wireless transmission device is relatively complex, and due to the effect of the detonator, it will cause certain interference to the operation of the wireless transmission device, and there are certain safety hazards for the detection of detonation.

[0004] Prior Art 2, Application No.: CN202310106600.5 discloses a mechanized combined drilling and blasting mining process and system for gypsum mines, including: selecting a target gypsum mining area, investigating and eliminating potential safety hazards at the top and side floating rocks in the target gypsum mining area; determining the working face of the target gypsum mining area after eliminating potential safety hazards, drilling cut holes on the working face, and blasting the cut holes into cut cavities; obtaining a first hydraulic crushing device, making the crushing head of the first hydraulic crushing device perpendicular to the gypsum surface near the cut cavity, turning on the crushing device until the gypsum is crushed, and then stopping the crushing operation to obtain caved gypsum rocks; screening the gypsum rocks with a particle size greater than a preset threshold, and using the first hydraulic crushing device to perform secondary crushing on the screened rocks until the particle size of the gypsum rocks after secondary crushing is less than the preset threshold. Although it reduces the use of explosive materials, significantly weakens various blasting harmful effects, greatly improves safety, and significantly improves production efficiency; however, it still relies too much on the experience of professionals, not only fails to improve the safety of blasting, but also cannot effectively improve the efficiency of mining.

[0005] Prior Art 3, Application No.: CN201810059286.9 discloses a method for dispatching and commanding the safety warning of drone blasting. By using the functions of remote control command, aerial hovering photography and videography of drones, it can collect global or local image data of the blasting area and its surrounding environment in real time, and conduct real-time analysis of the pre-blasting warning effect, monitoring of the warning status of the blasting area, recording of the blasting process, inspection of the post-blasting environmental impact, blind shot investigation and identification, and remote collection of blind shot information, so as to realize the dispatching and commanding of the safety warning of blasting. Although it uses drone technology to carry out the dispatching and commanding work of the safety warning of blasting, it improves the timeliness, safety and reliability of the safety warning of blasting and the investigation and handling of potential hazards in the links of blasting warning, blasting area inspection, blind shot investigation, etc., and finally realizes the purpose of safe and efficient initiation and elimination of potential hazards left after blasting; however, it pays attention to too many contents and does not focus on the investigation after blasting, resulting in the need to further improve the accuracy of potential hazard investigation.

[0006] Currently, Prior Art 1, Prior Art 2 and Prior Art 3 have the problems that the technical means for investigating blasting potential hazards are relatively single, lacking certain intelligent means, resulting in poor accuracy of the investigation results and the need to further reduce potential safety hazards. Therefore, the present invention provides a blasting potential hazard investigation system based on drone tomography. Summary of the Invention

[0007] In order to solve the above technical problems, the present invention provides a blasting potential hazard investigation system based on drone tomography, including:

[0008] A data acquisition component, which is responsible for performing three-dimensional modeling and tomography on the blasting target area to generate high-resolution point cloud data and tomographic images;

[0009] A risk assessment component, responsible for analyzing point cloud data and tomographic images, and automatically identifying potential hazards such as rock mass loosening, crack expansion, and geological fault blasting;

[0010] A dynamic warning component, responsible for long-term monitoring of key blasting areas. Drones regularly scan the blasting target areas, and the 3D models and hazard data are updated in real time.

[0011] Optionally, a data acquisition component includes:

[0012] A signal emission module, responsible for emitting signals, calculating the time difference of the signal round-trip, and capturing the subtle undulations and structural features of the target area;

[0013] A dynamic scanning module, responsible for scanning by drones at a fixed altitude and path according to the dynamic scanning strategy;

[0014] An image generation module, responsible for generating high-resolution point cloud data. The point cloud data is processed to generate tomographic images through tomographic scanning.

[0015] Optionally, the dynamic scanning module includes:

[0016] A basic parameter calculation sub-module, responsible for calculating the distance from the drone to the explosion target area and the environmental temperature parameter;

[0017] A flight altitude adjustment sub-module, responsible for calculating the influence of angle adjustment based on the signal reflection intensity and average value, and adjusting the altitude in combination with the influence of temperature on the speed of sound;

[0018] A comprehensive adjustment sub-module, responsible for comprehensively calculating the results, as well as the influence of the square root value of the signal strength ratio and the sine function, to obtain the new flight altitude of the adjusted drone.

[0019] Optionally, the expression for obtaining the new flight altitude of the adjusted drone is:

[0020]

[0021] In the formula, H new is the new flight altitude of the adjusted drone; H old is the current flight altitude of the drone; L signal is the reflection intensity of the current signal; L avgis the average value of the signal reflection intensity over a period of time, used to eliminate environmental noise; d is the distance from the drone to the explosion target area, which can be calculated by the time difference t between the signal round-trip and the speed of light c; θ is the scanning angle of the drone; arctan is the arctangent function, used to adjust the height according to the signal reflection intensity and distance; cos is the cosine function, used to take into account the influence of angle adjustment; k is the Boltzmann constant, used to calculate the influence of temperature on the speed of sound; T is the environmental temperature; log is the logarithmic function, used to calculate the logarithm of the signal intensity ratio; e is the base of the natural logarithm; is the square root function, used to calculate the square root value of the signal intensity ratio; sin is the sine function, used to take into account the influence of angle adjustment.

[0022] Optionally, the image generation module includes:

[0023] The weighted average calculation sub-module is responsible for performing a weighted average calculation on the parameters of the signal to generate a preliminary reflection intensity value;

[0024] The standard deviation calculation sub-module is responsible for calculating the standard deviation of the reflection intensity, reflecting the volatility and local changes of the signal;

[0025] The result integration calculation sub-module is responsible for multiplying the weighted average result by the standard deviation to generate the final tomographic image.

[0026] Optionally, the expression of the tomographic image of the image generation module is:

[0027]

[0028] In the formula, w i represents the weight coefficient, used to adjust the influence degree of different parameters on the final result. The larger the weight, the more significant the influence of the corresponding parameter on the result; r i (x,y) represents the signal reflection intensity, indicating the intensity of the reflected signal received at the position (x,y); d i represents the time difference, indicating the time delay of the signal from transmission to reception, usually related to the length of the signal propagation path; t i represents the time parameter, indicating the time characteristics of the signal, which may be related to the propagation speed or attenuation characteristics of the signal; μ(x,y) represents the rock mechanical property parameter, indicating the mechanical properties of the rock at the position (x,y), used to correct the attenuation of the signal; L(x,y) represents the bedding structure parameter, indicating the geological bedding structure at the position (x,y), used to adjust the reflection characteristics of the signal; τ(x,y) represents the signal time parameter, which may be related to the propagation time or time resolution of the signal; θ(x,y) represents the bedding structure parameter, related to the angle or direction of the geological bedding; φ(x,y) represents the rock mechanical property parameter, related to the physical properties of the rock; It represents the ratio of the reflection intensity to the time difference, indicating the reflection intensity per unit time; I f (x, y) represents the preliminary reflection intensity value generated by the weighted average part; I final (x, y) represents the finally generated tomographic image, indicating the reflection intensity value at the position (x, y).

[0029] Optionally, the risk assessment component includes:

[0030] The feature extraction module is responsible for aligning and integrating the data from the lidar and multispectral sensors in the spatio-temporal dimension, decomposing the original data into feature components at different scales, and obtaining geological features;

[0031] The hidden danger identification module is responsible for classifying hidden dangers into three categories: rock mass loosening, crack expansion, and geological faults, and displaying different types of hidden dangers in layers in three-dimensional space to form a hidden danger distribution map;

[0032] The report generation module is responsible for evaluating the risk level of each hidden danger area based on the hidden danger distribution map, and presenting the generated risk level report visually.

[0033] Optionally, the crack expansion identification sub-module of the hidden danger identification module includes:

[0034] The quantum state feature detection unit is responsible for establishing a quantum sensor network in direct contact with the crack edge, detecting the crack edge using quantum effects, and sensing the changes in the microscopic quantum state; analyzing the quantum state features of the crack edge, converting the quantum state features into recognizable information, and encoding and decoding the quantum state;

[0035] The quantum state feature mapping unit is responsible for converting the non-classical characteristics of the quantum state into image data, and mapping the analyzed feature information onto the three-dimensional image of the crack; using the feature information of the quantum state to dynamically track the crack edge, and predicting the expansion trend and speed of the crack by real-time monitoring of the changes in the quantum state of the crack edge, so as to achieve real-time monitoring of the dynamic behavior of the crack;

[0036] The quantum image segmentation unit is responsible for segmenting the crack area and constructing the segmented crack area into an independent layer.

[0037] Optionally, the quantum state feature detection unit encodes and decodes the quantum state to obtain microscopic physical phenomena including changes in reflectivity and phase shift.

[0038] Optionally, the quantum image segmentation unit constructs an independent layer containing all the quantum state feature information of the crack.

[0039] The data acquisition component of the present invention can quickly and efficiently perform 3D modeling and tomography scanning on the blasting target area by using drones equipped with lidar or multispectral sensors; generate high-resolution point cloud data and tomographic images, providing accurate basic data for blasting hazard investigation and analysis; the application of drone technology makes data acquisition more flexible, capable of covering complex terrains and dangerous areas, and reducing manual intervention. The risk assessment component performs intelligent analysis on the point cloud data and tomographic images, automatically identifying potential hazards such as rock mass loosening, crack expansion, and geological faults; combining with geomechanical models, quantitatively assessing the risks of potential hazards, generating potential hazard distribution maps and risk level reports; using artificial intelligence to improve the accuracy and efficiency of potential hazard identification. The dynamic warning component conducts long-term monitoring on key blasting areas, with drones regularly scanning and real-time updating 3D models and potential hazard data; when detecting changes in potential hazards (such as crack expansion, rock mass displacement, etc.), automatically triggering the warning mechanism; pushing warning information through a visual interface or mobile device to achieve real-time monitoring and rapid response.

[0040] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the written specification and the drawings.

[0041] The following will further describe the technical solution of the present invention in detail through the drawings and embodiments. Description of the Drawings

[0042] The drawings are used to provide further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0043] Figure 1 It is the block diagram of the blasting hazard investigation system based on drone tomography in Embodiment 1 of the present invention;

[0044] Figure 2 It is the block diagram of the data acquisition component in Embodiment 2 of the present invention;

[0045] Figure 3 It is the block diagram of the dynamic scanning module in Embodiment 3 of the present invention;

[0046] Figure 4 It is the block diagram of the image generation module in Embodiment 4 of the present invention;

[0047] Figure 5 It is the block diagram of the risk assessment component in Embodiment 5 of the present invention;

[0048] Figure 6 It is the block diagram of the potential hazard identification module in Embodiment 6 of the present invention;

[0049] Figure 7 It is the block diagram of the rock mass loosening identification sub-module in Embodiment 7 of the present invention;

[0050] Figure 8 It is the block diagram of the crack propagation identification sub-module in Embodiment 8 of the present invention. Detailed implementation manners

[0051] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0052] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the embodiments of the present application. In the embodiments of the present application, the singular forms of "a", "the" and "said" are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0053] When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are only examples of devices and methods consistent with some aspects of the present application. In the description of the present application, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and do not have to be used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0054] Embodiment 1: As Figure 1 shown, the embodiment of the present invention provides a blasting hazard detection system based on UAV tomography, including:

[0055] A data acquisition component, which is responsible for performing three-dimensional modeling and tomography on the blasting target area through a UAV equipped with a lidar or a multispectral sensor, and generating high-resolution point cloud data and tomographic images;

[0056] A risk assessment component, which is responsible for analyzing the point cloud data and tomographic images, automatically identifying blasting hazards such as rock mass loosening, crack propagation, and geological faults, and combining with a geomechanical model to perform risk assessment, and generating a hazard distribution map and a risk level report;

[0057] The dynamic warning component is responsible for long-term monitoring of key blasting areas. The drone regularly scans the blasting target area to update the 3D model and potential hazard data in real time. When changes in potential hazards are detected (such as crack expansion, rock mass displacement, etc.), the warning mechanism is automatically triggered, and warning information is pushed through the visualization interface or the mobile terminal.

[0058] The working principle and beneficial effects of the above technical solution are as follows: The data acquisition component in this embodiment uses a drone equipped with a lidar or a multispectral sensor to perform 3D modeling and tomographic scanning on the blasting target area, generating high-resolution point cloud data and tomographic images; the risk assessment component analyzes the point cloud data and tomographic images, automatically identifies blasting hazards such as rock mass loosening, crack expansion, and geological faults, and combines with a geomechanics model to conduct a risk assessment, generating a hazard distribution map and a risk level report; the dynamic warning component conducts long-term monitoring on the key blasting areas, the drone regularly scans the blasting target area, and updates the 3D model and hazard data in real time; when detecting changes in hazards (such as crack expansion, rock mass displacement, etc.), it automatically triggers the warning mechanism and pushes warning information through a visualization interface or a mobile terminal. The data acquisition component of the above solution can quickly and efficiently perform 3D modeling and tomographic scanning on the blasting target area by using a drone equipped with a lidar or a multispectral sensor; generate high-resolution point cloud data and tomographic images, providing accurate basic data for the investigation and analysis of blasting hazards; the application of drone technology makes data acquisition more flexible, can cover complex terrains and dangerous areas, and reduces manual intervention. Significance: It provides a high-precision 3D model and geological fault information of the blasting area, laying a data foundation for risk assessment and dynamic monitoring; improves the efficiency and safety of data acquisition, and reduces the potential risks of manual operations; provides a scientific basis for the design, construction, and safety management of blasting projects. The risk assessment component conducts intelligent analysis on the point cloud data and tomographic images, automatically identifies hazards such as rock mass loosening, crack expansion, and geological faults; combines with a geomechanics model to conduct a quantitative risk assessment on the hazards, generating a hazard distribution map and a risk level report; uses artificial intelligence to improve the accuracy and efficiency of hazard identification. Significance: It can discover potential risks in the blasting area in advance, providing a scientific basis for engineering decisions; through the hazard distribution map and risk level report, it helps managers intuitively understand the risk distribution and severity, and formulate targeted countermeasures; reduces the accident risk of blasting projects and ensures the safety of personnel and equipment. The dynamic warning component conducts long-term monitoring on the key blasting areas, the drone regularly scans and updates the 3D model and hazard data in real time; when detecting changes in hazards (such as crack expansion, rock mass displacement, etc.), it automatically triggers the warning mechanism; pushes warning information through a visualization interface or a mobile terminal to achieve real-time monitoring and rapid response. Significance: It realizes the dynamic monitoring and real-time warning of the blasting area, can timely discover changes in hazards and take countermeasures; improves the safety management level of blasting projects and reduces the occurrence probability of sudden accidents; through the visualization interface and mobile terminal push, it is convenient for managers to master the safety status of the blasting area anytime and anywhere, improving the management efficiency.

[0059] In summary, the three components of this embodiment jointly constitute an intelligent and efficient blasting safety monitoring and warning system. The data acquisition component provides high-precision basic data for the system. The risk assessment component identifies potential hazards and quantifies risks through intelligent analysis. The dynamic warning component realizes real-time monitoring and rapid response. It not only improves the safety of blasting projects but also provides a scientific basis and technical support for project management, having important engineering practical significance and social value.

[0060] Embodiment 2: As Figure 2 shown, based on Embodiment 1, the data acquisition component provided by the embodiment of the present invention includes:

[0061] A signal emission module, which is responsible for the lidar or multispectral sensor to emit signals at a high frequency. After the signal contacts the surface or rock mass of the explosion target area, it is reflected back to the sensor. Calculate the time difference of the signal round-trip to capture the subtle undulations and structural features of the target area;

[0062] A dynamic scanning module, which is responsible for the drone to scan at a fixed height and path according to the dynamic scanning strategy. At the same time, according to the real-time feedback signal, automatically adjust the flight height and scanning angle;

[0063] An image generation module, which is responsible for optimizing the point cloud data using algorithms, considering the reflection intensity and time difference of the signal, and also combining the bedding structure and rock mechanics characteristics in geology. Through the fusion of multi-dimensional data, high-resolution point cloud data is generated. The point cloud data is processed to generate a tomographic image through tomographic scanning.

[0064] The working principle and beneficial effects of the above technical solution are as follows: The signal emission module of this embodiment, namely lidar or multispectral sensor, emits signals at a high frequency. After the signals contact the surface or rock mass of the explosion target area, they are reflected back to the sensor. The time difference of the round-trip of the signals is calculated to capture the subtle undulations and structural features of the target area. The dynamic scanning module, according to the dynamic scanning strategy, the unmanned aerial vehicle (UAV) scans at a fixed altitude and path, and at the same time, automatically adjusts the flight altitude and scanning angle according to the real-time feedback signals. The image generation module uses an algorithm to optimize the point cloud data, considering the reflection intensity and time difference of the signals, and also combines the bedding structure and rock mechanics characteristics in geology. Through the fusion of multi-dimensional data, high-resolution point cloud data is generated, and the point cloud data is processed to generate a tomographic image through tomographic scanning. The signal emission module of the above solution emits laser or multispectral signals at a high frequency; precisely captures the subtle undulations and structural features of the target area; measures the round-trip time difference of the reflected signals. The signal emission module improves the resolution and fineness of data acquisition, and can obtain the microscopic structure information of the surface or rock mass; through the time difference measurement, the distance between the signal and the target area can be calculated to achieve precise positioning in three-dimensional space; it provides high-quality data as the basis for data processing and analysis. The dynamic scanning module dynamically adjusts the flight altitude and scanning angle of the UAV according to the strategy; feeds back signals in real time, automatically optimizes the scanning path; controls the UAV to perform continuous scanning at a fixed altitude and path. The dynamic scanning module improves the efficiency and coverage rate of data acquisition by dynamically adjusting flight parameters, reduces omissions and repeated scans; the real-time feedback signals make the scanning more flexible, can automatically optimize the path according to terrain changes, and improve the uniformity of acquisition; continuous scanning can obtain a continuous data sequence, which is convenient for subsequent processing and analysis. The image generation module uses an algorithm to optimize the point cloud data; fuses multi-dimensional data to generate high-resolution point clouds; combines geological theories to generate tomographic images through tomographic scanning. The image generation module improves the accuracy and reliability of the point cloud data through the optimized algorithm; the multi-dimensional data fusion can more comprehensively reflect the characteristic information of the target area; the tomographic image can intuitively display the geological structure, which is convenient for analysis and interpretation.

[0065] In summary, the three modules of this embodiment cooperate with each other, making the data acquisition process more efficient, refined and comprehensive. The high-quality data provides a solid foundation for geological analysis and applications.

[0066] Embodiment 3: As Figure 3 shown, on the basis of Embodiment 2, the dynamic scanning module provided by the embodiment of the present invention includes:

[0067] The basic parameter calculation sub-module is responsible for calculating parameters such as the distance from the UAV to the explosion target area and the environmental temperature;

[0068] The flight altitude adjustment sub-module is responsible for adjusting the flight altitude of the UAV by using the calculated basic parameters, signal reflection intensity, etc.; calculating the influence of angle adjustment according to the signal reflection intensity and average value, and adjusting the altitude in combination with the influence of temperature on the speed of sound;

[0069] The comprehensive adjustment sub-module is responsible for comprehensively calculating the results, as well as the square root value of the signal strength ratio and the influence of the sine function, to obtain the new flight altitude of the adjusted UAV.

[0070] Among them,

[0071]

[0072] In the formula, H new is the new flight altitude of the adjusted UAV; H old is the current flight altitude of the UAV; L signal is the reflection intensity of the current signal; L avg is the average value of the signal reflection intensity over a period of time, used to eliminate environmental noise; d is the distance from the UAV to the explosion target area, which can be calculated by the time difference t of the signal round-trip and the speed of light c; θ is the scanning angle of the UAV; arctan is the arctangent function, used to adjust the altitude according to the signal reflection intensity and distance; cos is the cosine function, used to take into account the influence of angle adjustment; k is the Boltzmann constant, used to calculate the influence of temperature on the speed of sound; T is the environmental temperature; log is the logarithmic function, used to calculate the logarithm value of the signal strength ratio; e is the base of the natural logarithm; is the square root function, used to calculate the square root value of the signal strength ratio; sin is the sine function, used to take into account the influence of angle adjustment.

[0073] The working principle and beneficial effects of the above technical solution are as follows: The basic parameter calculation sub-module of this embodiment calculates parameters such as the distance from the UAV to the explosion target area and the ambient temperature; the flight altitude adjustment sub-module adjusts the flight altitude of the UAV by using the calculated basic parameters and signal reflection intensity, etc.; calculates the influence of angle adjustment according to the signal reflection intensity and the average value, and adjusts the altitude in combination with the influence of temperature on the speed of sound; the comprehensive adjustment sub-module synthesizes the calculation results, as well as the square root value of the signal strength ratio and the influence of the sine function, to obtain the new flight altitude of the adjusted UAV. The basic parameter calculation sub-module of the above solution provides necessary data support for the flight adjustment of the UAV by calculating basic parameters such as the distance from the UAV to the target area and the ambient temperature. Significance: Accurate environmental parameters are the key to ensuring the safe and effective execution of tasks by the UAV; distance calculation can help the UAV plan its flight path and avoid obstacles; while the temperature parameter is related to the calculation of the speed of sound, which in turn affects signal propagation and the reaction speed of the UAV. The flight altitude adjustment sub-module adjusts the flight altitude of the UAV by using the calculated basic parameters and signal reflection intensity, etc., calculates the difference between the signal reflection intensity and the average value, thereby calculating the influence of angle adjustment on the flight altitude, and further adjusts the flight altitude in combination with the influence of temperature on the speed of sound. Significance: Precise adjustment of the flight altitude can not only improve the safety of UAV flight, but also improve the efficiency and accuracy of task execution; analysis of the signal reflection intensity helps the UAV identify and avoid obstacles, and consideration of the influence of temperature on the speed of sound can ensure that the UAV can accurately execute tasks under different environmental conditions. The comprehensive adjustment sub-module synthesizes the calculation results, as well as the square root value of the signal strength ratio and the influence of the sine function, to obtain the new flight altitude of the adjusted UAV. Significance: By comprehensively considering multiple factors (such as signal strength, temperature, etc.), the flight adjustment of the UAV becomes more refined and intelligent. The introduction of the square root value of the signal strength ratio and the sine function may be to take into account the uneven distribution of signal strength in different directions and the influence of environmental factors on signal propagation, so as to achieve more accurate altitude adjustment.

[0074] In summary, the collaborative work of the sub-modules of this embodiment enables the UAV to automatically adapt to complex and changing environments, improves the safety of flight and the accuracy of task execution, and has important significance for the application of UAVs in fields such as search and rescue, environmental monitoring, and logistics distribution; through the application of these technologies, the UAV can more flexibly cope with various challenges and achieve more efficient and intelligent flight control.

[0075] Embodiment 4: As Figure 4 shown, on the basis of Embodiment 2, the image generation module provided by the embodiment of the present invention includes:

[0076] The weighted average calculation sub-module is responsible for calculating the weighted average of parameters such as the reflection intensity, time difference, geological structure, and rock mechanical properties of the signal to generate a preliminary reflection intensity value;

[0077] The standard deviation calculation sub-module is responsible for calculating the standard deviation of the reflection intensity to reflect the volatility and local changes of the signal;

[0078] The result comprehensive calculation sub-module is responsible for multiplying the weighted average result by the standard deviation to generate the final fault image; combining the global characteristics and local changes of the signal to generate a high-resolution image.

[0079] Among them, the expression of the fault image of the image generation module is:

[0080]

[0081] In the formula, w i represents the weight coefficient, which is used to adjust the influence degree of different parameters on the final result. The larger the weight, the more significant the influence of the corresponding parameter on the result; r i (x, y) represents the reflection intensity of the signal, indicating the intensity of the reflected signal received at the position (x, y); d i represents the time difference, indicating the time delay of the signal from transmission to reception, which is usually related to the length of the signal propagation path; t i represents the time parameter, indicating the time characteristics of the signal, which may be related to the propagation speed or attenuation characteristics of the signal; μ(x, y) represents the rock mechanical property parameter, indicating the mechanical properties of the rock (such as elastic modulus, density, etc.) at the position (x, y), which is used to correct the attenuation of the signal; L(x, y) represents the bedding structure parameter, indicating the geological bedding structure at the position (x, y), which is used to adjust the reflection characteristics of the signal; τ(x, y) represents the signal time parameter, which may be related to the propagation time or time resolution of the signal; θ(x, y) represents the bedding structure parameter, which may be related to the angle or direction of the geological bedding; φ(x, y) represents the rock mechanical property parameter, which may be related to the physical properties of the rock (such as porosity, permeability, etc.); represents the ratio of the reflection intensity to the time difference, indicating the reflection intensity per unit time; I f (x, y) represents the preliminary reflection intensity value generated by the weighted average part; I final(x, y) represents the finally generated tomographic image, indicating the reflection intensity value at the position (x, y); the weighted average part generates a preliminary reflection intensity value by synthesizing parameters such as reflection intensity, time difference, rock mechanical properties, and bedding structure. Its role is to extract the global features of the signal and optimize the influence of parameters through weight assignment to ensure the accuracy and physical meaning of the calculation results; the standard deviation part is used to quantify the volatility and local changes of the reflection intensity. By calculating the deviation between the reflection intensity and the preliminary reflection intensity value, the standard deviation can reflect the local details and abnormal areas of the signal. Its role is to enhance the detail information of the image and provide local features for subsequent image generation; it considers both the reflection intensity and time difference of the signal, and combines geological structure and rock mechanical properties to finally generate a high-resolution tomographic image. In this way, point cloud data can be processed more efficiently, and a more accurate and detailed image can be generated.

[0082] The working principle and beneficial effects of the above technical solution are as follows: The weighted average calculation sub-module in this embodiment performs weighted average calculations on parameters such as the reflection intensity, time difference, geological structure, and rock mechanical properties of the signal to generate a preliminary reflection intensity value; the standard deviation calculation sub-module calculates the standard deviation of the reflection intensity to reflect the volatility and local changes of the signal; the result comprehensive calculation sub-module multiplies the weighted average result by the standard deviation to generate the final fault image; by combining the global characteristics and local changes of the signal, a high-resolution image is generated. The weighted average calculation sub-module of the above solution performs weighted average on multiple key parameters such as the reflection intensity, time difference, geological structure, and rock mechanical properties of the signal to generate a preliminary reflection intensity value; through the allocation of weights, it ensures that important parameters have a greater impact on the result, thereby improving the accuracy of the calculation; by combining parameters such as rock mechanical properties and bedding structure, attenuation correction and structural adjustment are performed on the signal to ensure that the physical meaning of the signal is reasonably reflected. The achieved significance is that the weighted average calculation sub-module can extract global characteristics from complex signals and provide basic data for image generation; through weighted average, the influence of noise and outliers can be effectively reduced, and the reliability and stability of the data can be improved; by combining geological and rock mechanical properties, it ensures that the generated reflection intensity value has a clear physical meaning and provides a scientific basis for geological analysis. The standard deviation calculation sub-module, by calculating the standard deviation of the reflection intensity, quantifies the volatility and local changes of the signal and reflects the detailed information in the image; the standard deviation can reveal the degree of dispersion of the data distribution and help identify abnormal or highly variable regions in the signal; as an indicator of local changes, the standard deviation can be combined with the weighted average result to further enhance the details and resolution of the image. The achieved significance is that the standard deviation calculation sub-module can capture local changes in the signal and provide detailed information for image generation; through the calculation of the standard deviation, abnormal regions in the signal can be quickly identified, providing important references for geological analysis; by combining the standard deviation with the weighted average result, a high-resolution image can be generated to meet the needs of fine geological analysis. The result comprehensive calculation sub-module multiplies the weighted average result by the standard deviation, combines the global characteristics and local changes of the signal, and generates the final fault image; through comprehensive calculation, it can balance the global consistency and local details of the image and avoid over-smoothing or over-sharpening; the finally generated image has high resolution and can clearly display the fault structure and geological features. The achieved significance is that the result comprehensive calculation sub-module can generate high-quality fault images, providing reliable data support for blasting hazard investigation; by combining global characteristics and local changes, the generated image has both overall consistency and rich detailed information; the high-resolution fault image can provide important basis for fields such as engineering planning and has wide application value.

[0083] In summary, the weighted average calculation sub-module of this embodiment extracts global features, optimizes parameters, and ensures the reliability and physical meaning of data; the standard deviation calculation sub-module quantifies local changes, enhances details, and identifies abnormal regions; the result integration calculation sub-module combines global and local features to generate high-quality and high-resolution tomographic images. It not only improves the efficiency and accuracy of image generation, but also provides strong technical support for blasting hazard detection, with important scientific significance and application value.

[0084] Embodiment 5: As Figure 5 shown, based on Embodiment 1, the risk assessment component provided by the embodiment of the present invention includes:

[0085] A feature extraction module, which is responsible for aligning and integrating the data of the lidar and the multispectral sensor in the spatio-temporal dimension, decomposing the original data into feature components of different scales, removing high-frequency noise and low-frequency redundant information to obtain geological features; at the same time, dynamically adjusting the filtering parameters through a quantum-inspired optimization algorithm;

[0086] A hidden danger identification module, which is responsible for classifying hidden dangers into three categories: rock mass loosening, crack expansion, and geological faults, embedding the identified hidden danger features through high-dimensional manifold, performing non-linear mapping and integration in three-dimensional space, and displaying different types of hidden dangers in layers in three-dimensional space to form a hidden danger distribution map, and the hidden danger distribution map reflects the type, severity, and dynamic change trend of hidden dangers through quantum state coding;

[0087] A report generation module, which is responsible for evaluating the risk level of each hidden danger area based on the hidden danger distribution map, and the generated risk level report is presented visually, including the hidden danger distribution map, the risk level distribution map, and a text description.

[0088] Among them, the data of the lidar and the multispectral sensor need to be aligned and integrated in the spatio-temporal dimension. Assuming that the lidar data is L(x, y, t) and the multispectral sensor data is M(x, y, t, λ), where (x, y) represents the spatial coordinates, t represents the time, and λ represents the spectral wavelength, the formula for alignment and integration is as follows:

[0089]

[0090] In the formula, D(x, y, t) represents the integrated spatio-temporal data; α(λ, τ) represents the spatio-temporal alignment weight function, which is used to adjust the data contribution under different wavelengths and time delays; τ represents the time delay variable, which is used to align the timestamps of different sensors; λ represents the spectral wavelength, representing different bands of the multispectral sensor;

[0091] After the original data is aligned, geological features need to be extracted through multi-scale decomposition. A method combining wavelet transform and quantum-inspired optimization algorithm is adopted, and the formula is as follows:

[0092]

[0093] In the formula, F k (x, y, t) represents the feature component at the k-th scale; ψ k (u, v, s) represents the wavelet basis function, which is used to extract features at different scales; Ω represents the integration domain, indicating the range of space and time; (u, v, s) represents the integration variables, representing the offsets of space and time respectively;

[0094] Quantum-inspired filtering parameter optimization formula. Assuming the filtering parameter is β k , the optimization goal is to minimize the energy of noise and redundant information, and the formula is expressed as follows:

[0095]

[0096] In the formula, β k represents the filtering parameter at the k-th scale; represents the filtered feature component; γ represents the regularization parameter, which is used to control the smoothness of the filtering parameter; represents the gradient of the filtering parameter, indicating the change trend of the parameter;

[0097] The finally extracted geological feature G(x, y, t) is obtained by the weighted combination of multi-scale feature components and is represented as:

[0098]

[0099] In the formula, G(x, y, t) represents the extracted geological feature; w k represents the weight coefficient at the k-th scale; σ k represents the standard deviation of the feature distribution at the k-th scale;

[0100] Formula for removing high-frequency noise and low-frequency redundant information:

[0101]

[0102] In the formula, G clean (x, y, t) represents the geological feature after removing noise and redundant information; LPF k represents the low-pass filter, which is used to remove low-frequency redundant information; HPF k represents the high-pass filter, which is used to remove high-frequency noise; η k , μ kRepresents the weight coefficients of the filter. The above formula constitutes the core calculation framework of the feature extraction module, which can efficiently process lidar and multispectral sensor data, extract high-quality geological features, and provide a solid foundation for hazard identification and risk assessment.

[0103] The working principle and beneficial effects of the above technical solution are as follows: The feature extraction module in this embodiment aligns and integrates the data from lidar and multispectral sensors in the spatio-temporal dimension, decomposes the original data into feature components of different scales, removes high-frequency noise and low-frequency redundant information, and obtains geological features. At the same time, the filtering parameters are dynamically adjusted through a quantum-inspired optimization algorithm. The hidden danger identification module classifies hidden dangers into three categories: rock mass loosening, crack expansion, and geological faults. The identified hidden danger features are embedded through high-dimensional manifold embedding, and non-linear mapping and integration are performed in three-dimensional space. Different types of hidden dangers are displayed in layers in three-dimensional space to form a hidden danger distribution map. The hidden danger distribution map reflects the type, severity, and dynamic change trend of hidden dangers through quantum state coding. The report generation module evaluates the risk level for each hidden danger area based on the hidden danger distribution map, and the generated risk level report is presented visually, including the hidden danger distribution map, risk level distribution map, and text description. The feature extraction module of the above solution solves the problem of multi-source heterogeneous data fusion by spatio-temporally aligning the data from lidar and multispectral sensors, ensuring the integrity and consistency of the data. It decomposes the original data into feature components of different scales, effectively removes high-frequency noise and low-frequency redundant information, and retains key geological features. Through the quantum-inspired optimization algorithm, the filtering parameters are dynamically adjusted to ensure the accuracy and adaptability of feature extraction, avoiding the limitations of fixed parameters in traditional methods. The achieved significance is as follows: Through multi-scale decomposition and dynamic optimization, the accuracy and robustness of geological feature extraction are significantly improved. The introduction of the quantum-inspired optimization algorithm realizes the combination of traditional signal processing and quantum computing, providing a high-quality data basis for subsequent hidden danger identification. Through precise feature extraction, the interference of noise on hidden danger identification is reduced, and the misjudgment rate is lowered. The hidden danger identification module classifies hidden dangers into three categories: rock mass loosening, crack expansion, and geological faults. Through high-dimensional manifold embedding technology, non-linear mapping and integration are performed in three-dimensional space, realizing the precise classification and positioning of hidden dangers. Different types of hidden dangers are displayed in layers in three-dimensional space to form a hidden danger distribution map, and the type, severity, and dynamic change trend of hidden dangers are intuitively reflected through quantum state coding. Through regular scanning by drones and quantum real-time computing technology, the hidden danger distribution map is dynamically updated to ensure the timeliness and accuracy of the data. The achieved significance is as follows: Through high-dimensional manifold embedding technology, the precise positioning and classification of hidden dangers are realized, providing a scientific basis for subsequent risk assessment. Through three-dimensional layered display and quantum state coding, the distribution and severity of hidden dangers are intuitively presented, facilitating decision-makers to quickly understand the hidden danger situation. Through dynamic tracking and updating, the real-time monitoring of hidden dangers is realized, significantly improving the safety of blasting operations.The report generation module conducts a risk level assessment for each potential hazard area based on the potential hazard distribution map, in combination with the quantum geomechanics model and the dynamic change trend of potential hazards. Through quantum visualization technology, it generates a risk level report that includes the potential hazard distribution map, the risk level distribution map, and a detailed written description. When detecting dynamic changes in potential hazards, the system automatically generates a warning signal through the quantum state triggering mechanism and pushes it to the mobile terminals of relevant personnel via quantum communication technology. Significance achieved: Through risk level assessment and visualization reports, it provides a scientific basis for blasting operations, helping decision-makers formulate more reasonable blasting plans; through the dynamic warning mechanism, it realizes real-time response to changes in potential hazards, significantly reducing the risks of blasting operations; the introduction of quantum visualization technology and quantum communication technology enhances the intuitiveness and real-time nature of the reports, providing an innovative solution for the safety management of blasting operations.

[0104] In summary, this embodiment has achieved precise identification, dynamic monitoring, and scientific assessment of blasting potential hazards. The feature extraction module has improved data quality and reduced the misjudgment rate, providing a high-quality data foundation for potential hazard identification. The potential hazard identification module has achieved precise positioning and classification of potential hazards, and through three-dimensional hierarchical display and dynamic monitoring, it has significantly improved the safety of blasting operations. The report generation module provides a scientific basis for blasting operations through risk level assessment and visualization reports, and through the dynamic warning mechanism, it realizes real-time response to changes in potential hazards.

[0105] Embodiment 6: As Figure 6 shown, based on Embodiment 5, the potential hazard identification module provided by the embodiment of the present invention includes:

[0106] The rock mass loosening identification sub-module is responsible for identifying local density abnormal regions in point cloud data through fractal geometry and chaotic dynamics analysis; combining multi-scale entropy value analysis of fault images to quantify the degree of looseness inside the rock mass, and dynamically tracking the boundary and depth of the loosening region;

[0107] The crack propagation identification sub-module is responsible for using quantum images to capture the quantum state characteristics of crack edges (such as reflectivity phase changes), combining spatio-temporal correlation analysis of point cloud data to dynamically predict the extension direction and propagation rate of cracks; precisely separating the crack region from the complex background through quantum image segmentation to form an independent feature layer;

[0108] The geological fault identification sub-module is responsible for identifying the non-linear characteristics of formation dislocation and fracture regions based on the non-linear dynamics model of fault images; reconstructing the three-dimensional structure of the fault through quantum interpolation, and combining stress field simulation in quantum mechanics to evaluate its potential impact on blasting safety.

[0109] The working principles and beneficial effects of the above technical solution are as follows: The rock mass loosening identification sub-module in this embodiment identifies the locally dense abnormal regions in the point cloud data through fractal geometry and chaotic dynamics analysis; combines the multi-scale entropy value analysis of the fault image to quantify the looseness degree inside the rock mass, and dynamically tracks the boundary and depth of the loosening region; the crack propagation identification sub-module uses quantum images to capture the quantum state characteristics (such as reflectance phase changes) at the crack edges, combines the spatio-temporal correlation analysis of the point cloud data, and dynamically predicts the extension direction and propagation rate of the cracks; accurately separates the crack region from the complex background through quantum image segmentation to form an independent feature layer; the geological fault identification sub-module identifies the non-linear characteristics of the formation dislocation and fracture regions based on the non-linear dynamics model of the fault image; reconstructs the three-dimensional structure of the fault through quantum interpolation, and combines the stress field simulation in quantum mechanics to evaluate its potential impact on blasting safety. The rock mass loosening identification sub-module of the above solution uses fractal geometry and chaotic dynamics analysis to capture the abnormal change regions of local density from the point cloud data; quantifies the looseness degree inside the rock mass by analyzing the multi-scale entropy value of the fault image, and dynamically tracks the boundary and depth of the loosening region. Significance: Rock mass loosening is one of the important precursors of geological disasters. Being able to identify the loosening region in advance provides early warning information for engineering safety and avoids accidents such as collapses and landslides caused by rock mass instability; at the same time, the dynamic tracking function provides accurate data support for engineering treatment and helps to formulate more effective reinforcement plans. The crack propagation identification sub-module can monitor the dynamic changes of cracks in real time, predict their development trends, and provide a scientific basis for engineering safety assessment; the accurate crack separation technology also provides a reliable data basis for repair and reinforcement work. The geological fault identification sub-module can accurately identify the three-dimensional structure of the fault and its stress distribution, provide scientific guidance for blasting design and construction, and avoid engineering accidents caused by fault activities; at the same time, the stress field simulation technology also provides important support for the long-term monitoring and early warning of geological disasters.

[0110] In summary, through the technical means of multidisciplinary intersection in this embodiment, the comprehensive monitoring and analysis of the rock mass state are realized. It can not only detect potential safety hazards in advance, but also provide accurate data support for engineering treatment, significantly improving the construction safety and stability of rock mass engineering; and can reduce the incidence of engineering accidents.

[0111] Example 7: As Figure 7 shown, on the basis of Example 6, the rock mass loosening identification sub-module provided by the embodiment of the present invention includes:

[0112] The fractal geometry analysis unit is responsible for calculating the fractal dimension of the point cloud data to identify the self-similarity characteristics on the surface and inside of the rock mass; by analyzing the dynamic changes of the point cloud data, monitoring the key parameters of the change rate and fluctuation range to identify those density abnormal regions showing non-linear characteristics;

[0113] The rock mass loosening quantification unit is responsible for performing multi-scale decomposition on the fault image and extracting the distribution characteristics of entropy values at different scales; combining the density anomaly regions in the point cloud data to obtain the loosening degree inside the rock mass, and quantifying its spatial distribution and intensity; quantifying the loosening degree of the rock mass as a probability density function and generating a distribution map of the loosening degree inside the rock mass.

[0114] The boundary and tracking unit is responsible for using the analysis results of fractal geometry to identify the boundary characteristics of the loosening region and updating the boundary contour in real time using dynamic threshold segmentation; combining the spatial distribution characteristics of the point cloud data and the multi-scale entropy value analysis of the fault image to calculate the depth distribution of the loosening region, reconstruct the three-dimensional structure of the loosening region, and dynamically update its depth change.

[0115] The working principle and beneficial effects of the above technical solution are as follows: The fractal geometry analysis unit in this embodiment calculates the fractal dimension of the point cloud data to identify the self-similarity characteristics on the surface and inside of the rock mass; by analyzing the dynamic changes of the point cloud data, it monitors the key parameters of the change rate and fluctuation range to identify those density anomaly regions showing non-linear characteristics; the rock mass looseness quantification unit performs multi-scale decomposition on the fault image and extracts the distribution characteristics of entropy values at different scales; combining with the density anomaly regions in the point cloud data, it obtains the looseness degree inside the rock mass and quantifies its spatial distribution and intensity; quantifies the looseness degree of the rock mass into a probability density function and generates a distribution map of the looseness degree inside the rock mass; the boundary and tracking unit uses the analysis results of fractal geometry to identify the boundary characteristics of the loosened area and uses dynamic threshold segmentation to update the boundary contour in real time; combining with the spatial distribution characteristics of the point cloud data and the multi-scale entropy value analysis of the fault image, it calculates the depth distribution of the loosened area, reconstructs the three-dimensional structure of the loosened area, and dynamically updates its depth change. The fractal geometry analysis unit of the above solution can identify the self-similarity characteristics on the surface and inside of the rock mass by calculating the fractal dimension of the point cloud data, so as to capture the complex structure and details of the rock mass; by monitoring the dynamic changes of the point cloud data, it can identify those density anomaly regions with non-linear characteristics, which is crucial for judging the stability of the rock mass. Significance: Through this method, potential unstable factors in the rock mass can be identified more accurately, providing a scientific basis for preventing geological disasters and thus ensuring the safety of personnel and equipment. The rock mass looseness quantification unit performs multi-scale decomposition on the fault image and extracts the distribution characteristics of entropy values at different scales, combines with the density anomaly regions in the point cloud data, realizes the quantification of the looseness degree inside the rock mass, and forms a probability density function distribution map, intuitively showing the spatial distribution and intensity of the looseness degree inside the rock mass. Significance: Quantifying and visualizing the looseness degree of the rock mass can provide detailed and accurate rock mass state information for engineering design and construction, helping to optimize the construction plan and prevent disasters such as rock mass collapse. The boundary and tracking unit uses the results of fractal geometry analysis to identify the boundary characteristics of the loosened area and updates the boundary contour in real time through dynamic threshold segmentation technology; combining with the spatial distribution of the point cloud data and the multi-scale entropy value analysis of the fault image, it calculates the depth distribution of the loosened area and reconstructs the three-dimensional structure of the loosened area, while dynamically updating its depth change. Significance: Dynamically tracking the changes in the loosened area is crucial for timely adjusting the construction plan and coping with potential risks; the real-time monitoring and analysis capabilities greatly improve the monitoring efficiency and response speed of the rock mass stability.

[0116] In summary, the rock mass loosening identification sub-module of this embodiment can not only accurately evaluate the stability and looseness degree of the rock mass by comprehensively applying advanced technologies such as fractal geometry analysis, multi-scale decomposition, and probability density function quantification, but also provide strong technical support for the prevention of geological disasters and engineering safety.

[0117] Example 8: As Figure 8 shown, based on Example 6, the crack propagation identification sub-module provided by the embodiments of the present invention includes:

[0118] A quantum state feature detection unit, which is responsible for establishing a quantum sensor network in direct contact with the crack edge, detecting the crack edge using quantum effects, perceiving the changes in the microscopic quantum state; analyzing the quantum state features of the crack edge, converting the quantum state features into recognizable information, encoding and decoding the quantum state, and obtaining microscopic physical phenomena such as changes in reflectivity and phase offsets.

[0119] A quantum state feature mapping unit, which is responsible for converting the non-classical characteristics of the quantum state into image data, and mapping the analyzed feature information onto the three-dimensional image of the crack; using the feature information of the quantum state to dynamically track the crack edge, predicting the propagation trend and speed of the crack by real-time monitoring the changes in the quantum state of the crack edge, and realizing the real-time monitoring of the dynamic behavior of the crack.

[0120] A quantum image segmentation unit, which is responsible for segmenting the crack region, and constructing the segmented crack region into an independent layer, including all the quantum state feature information of the crack.

[0121] The working principle and beneficial effects of the above technical solution are as follows: The quantum state feature detection unit in this embodiment establishes a quantum sensor network in direct contact with the crack edge, uses quantum effects to detect the crack edge, and senses changes in the microscopic quantum state; analyzes the quantum state features of the crack edge, converts the quantum state features into recognizable information, encodes and decodes the quantum state to obtain microscopic physical phenomena such as changes in reflectivity and phase offsets; the quantum state feature mapping unit converts the non-classical characteristics of the quantum state into image data, and maps the analyzed feature information onto the three-dimensional image of the crack; uses the feature information of the quantum state to dynamically track the crack edge, predicts the expansion trend and speed of the crack by real-time monitoring of the changes in the quantum state of the crack edge, and realizes real-time monitoring of the dynamic behavior of the crack; the quantum image segmentation unit segments the crack area, constructs the segmented crack area into an independent layer, containing all the quantum state feature information of the crack. The quantum state feature detection unit of the above solution can provide in-depth information on the crack state, which is crucial for the early identification and preventive maintenance of cracks; through highly sensitive detection, problems can be detected in time before the crack expansion causes structural damage, thereby reducing costs and improving safety. The quantum state feature mapping unit can visually observe and understand the crack condition by mapping the quantum state features onto an image, which helps to better understand the dynamic changes of the crack and provides more accurate data support for structural maintenance and safety assessment; predicting the crack expansion trend and speed helps to take preventive measures in advance and avoid potential structural damage. The independent layer obtained by the quantum image segmentation unit can facilitate further analysis and processing of the crack, such as crack morphology analysis, depth estimation, etc.; the segmentation technology can improve the accuracy and efficiency of crack analysis, and helps to carry out repair and maintenance work targeted.

[0122] In summary, by comprehensively using quantum technology in this embodiment, the accuracy and real-time performance of crack identification are improved, which is of great significance for ensuring structural safety, extending service life, reducing maintenance costs, etc.

[0123] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the equivalent technology of the present invention, the present invention also intends to include these changes and modifications.

Claims

1. A blasting hazard detection system based on UAV tomography, characterized in that, Include: A data acquisition component, responsible for performing 3D modeling and tomographic scanning on the blasting target area to generate high-resolution point cloud data and tomographic images; A risk assessment component, responsible for analyzing the point cloud data and tomographic images to automatically identify potential blasting hazards such as rock mass loosening, crack propagation, and geological faults; A dynamic warning component, responsible for long-term monitoring of key blasting areas, with drones regularly scanning the blasting target area to update the 3D model and hazard data in real time.

2. The blasting hazard detection system based on UAV tomography according to claim 1, characterized in that, The data acquisition component includes: A signal emission module, responsible for emitting signals, calculating the time difference of the signal round trip, and capturing the subtle undulations and structural features of the target area; A dynamic scanning module, responsible for scanning by drones at a fixed height and path according to the dynamic scanning strategy; An image generation module, responsible for generating high-resolution point cloud data, and the point cloud data is processed to generate tomographic images through tomographic scanning.

3. The blasting hazard detection system based on UAV tomography according to claim 2, wherein The dynamic scanning module includes: A basic parameter calculation sub-module, responsible for calculating the distance from the drone to the explosion target area and the environmental temperature parameter; A flight height adjustment sub-module, responsible for calculating the influence of angle adjustment based on the signal reflection intensity and average value, and adjusting the height in combination with the influence of temperature on the speed of sound; A comprehensive adjustment sub-module, responsible for comprehensively calculating the results, as well as the square root value of the signal strength ratio and the influence of the sine function, to obtain the new flight height of the adjusted drone.

4. The blasting hazard detection system based on UAV tomography according to claim 3, wherein, The expression for the new flight height of the adjusted drone is: Where, H new is the new flight altitude after the UAV is adjusted; H old is the current flight altitude of the UAV; L signal is the reflection intensity of the current signal; L avg is the average value of the signal reflection intensity over a period of time, which is used to eliminate environmental noise; d is the distance from the UAV to the explosion target area, which is calculated by the time difference t of the signal round-trip and the speed of light c; θ is the scanning angle of the UAV; arctan is the arctangent function, which is used to adjust the altitude according to the signal reflection intensity and the distance; cos is the cosine function, used to take into account the influence of angle adjustment; k is the Boltzmann constant, used to calculate the influence of temperature on the speed of sound; T is the environmental temperature; log is the logarithmic function, used to calculate the logarithm of the signal strength ratio; e is the base of the natural logarithm; √ is the square root function, used to calculate the square root value of the signal strength ratio; sin is the sine function, used to take into account the influence of angle adjustment.

5. The blasting hazard detection system based on UAV tomography according to claim 2, characterized in that, The image generation module includes: A weighted average calculation sub-module, responsible for performing weighted average calculations on the parameters of the signal to generate a preliminary reflection intensity value; A standard deviation calculation sub-module, responsible for calculating the standard deviation of the reflection intensity, reflecting the volatility and local changes of the signal; A result comprehensive calculation sub-module, responsible for multiplying the weighted average result by the standard deviation to generate the final tomographic image.

6. The blasting hazard detection system based on UAV tomography according to claim 5, wherein, The expression for the tomographic image of the image generation module is: Where, w i represents the weight coefficient, which is used to adjust the influence degree of different parameters on the final result. The larger the weight, the more significant the influence of the corresponding parameter on the result; r i (x, y) represents the reflection intensity of the signal, indicating the intensity of the reflected signal received at the position (x, y); d i represents the time difference, indicating the time delay of the signal from transmission to reception, which is usually related to the length of the signal propagation path; t i represents the time parameter, indicating the time characteristics of the signal, which is related to the propagation speed or attenuation characteristics of the signal; μ(x, y) represents the rock mechanical property parameter, indicating the mechanical properties of the rock at the position (x, y), which is used to correct the attenuation of the signal; L(x, y) represents the bedding structure parameter, indicating the geological bedding structure at the position (x, y), which is used to adjust the reflection characteristics of the signal; τ(x, y) represents the signal time parameter, which is related to the propagation time or time resolution of the signal; θ(x, y) represents the bedding structure parameter, which is related to the angle or direction of the geological bedding; φ(x, y) represents the rock mechanical property parameter, which is related to the physical properties of the rock; represents the ratio of the reflection intensity to the time difference, indicating the reflection intensity per unit time; I f (x, y) represents the preliminary reflection intensity value generated by the weighted average part; I final (x, y) represents the finally generated fault image, indicating the reflection intensity value at the position (x, y).

7. The blasting hazard detection system based on UAV tomography according to claim 1, characterized in that, The risk assessment component includes: A feature extraction module, responsible for aligning and integrating the data of lidar and multispectral sensors in the spatio-temporal dimension, decomposing the original data into feature components of different scales to obtain geological features; A hazard identification module, responsible for classifying hazards into three categories: rock mass loosening, crack propagation, and geological faults, and displaying different types of hazards in layers in 3D space to form a hazard distribution map; A report generation module, responsible for evaluating the risk level of each hazard area based on the hazard distribution map, and presenting the generated risk level report visually.

8. The blasting hazard detection system based on UAV tomography according to claim 6, wherein, The crack propagation identification sub-module of the hazard identification module includes: The quantum state feature detection unit is responsible for establishing a quantum sensor network in direct contact with the crack edge, detecting the crack edge using quantum effects, and sensing changes in the microscopic quantum state; analyzing the quantum state features of the crack edge, converting the quantum state features into recognizable information, and encoding and decoding the quantum state; The quantum state feature mapping unit is responsible for converting the non-classical characteristics of the quantum state into image data, and mapping the analyzed feature information onto the three-dimensional image of the crack; dynamically tracking the crack edge using the feature information of the quantum state, predicting the propagation trend and speed of the crack by real-time monitoring of the changes in the quantum state of the crack edge, and realizing real-time monitoring of the dynamic behavior of the crack; The quantum image segmentation unit is responsible for segmenting the crack area and constructing the segmented crack area into an independent layer.

9. The blasting hazard detection system based on UAV tomography according to claim 8, wherein The quantum state feature detection unit encodes and decodes the quantum state to obtain microscopic physical phenomena including changes in reflectivity and phase shift.

10. The blasting hazard detection system based on UAV tomography according to claim 8, wherein, The quantum image segmentation unit constructs an independent layer containing all the quantum state feature information of the crack.

Images