CN111539568A - Safety monitoring system and method based on UAV and 3D modeling technology - Google Patents

Abstract

The invention discloses a safety monitoring system based on an unmanned aerial vehicle and a three-dimensional modeling technology, belongs to the technical field of geology, and aims to provide a safety monitoring system based on the unmanned aerial vehicle and the three-dimensional modeling technology for accurate early warning of slope landslide; the safety prediction system comprises a three-dimensional modeling module, a danger prediction module and an early warning module, wherein the three-dimensional modeling module establishes a slope three-dimensional model according to the acquired information. The invention discloses a safety monitoring method based on an unmanned aerial vehicle and a three-dimensional modeling technology, belongs to the technical field of geology, and aims to provide a safety monitoring technology based on the unmanned aerial vehicle and the three-dimensional modeling technology, which is used for accurately early warning slope landslide.

Description

Safety monitoring system and method based on UAV and 3D modeling technology

technical field

The invention relates to the technical field of geology, in particular to a safety monitoring system and method based on unmanned aerial vehicles and three-dimensional modeling technology.

Background technique

High and steep rock slopes are a common type of rock slope stability analysis. They are widely distributed in mines and tunnels. Under the action of self-weight stress, with the progress of open-pit mining activities, the free surface of the slope gradually increases. , the probability of landslides increases gradually. The opening of cracks on the trailing edge of the slope allows the continuous infiltration of rainfall, the hydrostatic pressure and dynamic water pressure on the structure surface aggravate the danger of landslides, and the surface displacement continues to increase.

After the completion of the open-pit gold mining task, the pit is used as a tailings pond adjacent to the concentrator. The discharge of industrial water and the rainfall in the rainy season make the tailings pond continue to store water. The impact of the reservoir water on the slope mainly includes two aspects: First, the water The influence on the mechanical properties of the slope rock; the second is the influence of the water level rise and fall cycle on the slope rock. The slope stability analysis of tailings ponds in open pit mines is significantly affected by the water level of the ponds, and it is sudden, which often leads to large-scale landslide disasters.

At present, the commonly used landslide early warning and forecasting methods, the established model is simple, the landslide evaluation index is single, and the landslide early warning and forecasting system is not perfect. For example, the water level rise and fall cycle of the open pit will damage the mechanical properties of the slope rock and the water promotes the increase of the slope displacement; the commonly used mechanical theories such as the strength reduction method and limit equilibrium to analyze the slope stability, the evaluation index is the slope safety coefficient, there are the following shortcomings: First, the corresponding parameters can only be obtained through rock mechanical experiments, and the safety evaluation of the slope can only be qualitatively analyzed, and accurate timing and quantitative analysis cannot be achieved; Second, the tailings pond slope cannot be considered. The water level rise and fall cycle and the weakening effect of rainwater on the slope rock lead to the change of the slope condition; thirdly, the influence of the time factor on the slope stability cannot be considered, and the evaluation index is single.

SUMMARY OF THE INVENTION

In view of the deficiencies in the prior art, one of the purposes of the present invention is to provide a safety monitoring system based on UAV and three-dimensional modeling technology for accurate early warning of side slopes and landslides.

The above-mentioned purpose of the present invention is achieved through the following technical solutions:

A safety monitoring system based on UAV and three-dimensional modeling technology, including an information acquisition system and a safety prediction system,

The information acquisition system includes an unmanned aerial vehicle, an information acquisition module arranged on the unmanned aerial vehicle, and a wireless transmission module. The information acquisition module divides the slope into multiple monitoring areas, and obtains the slope, height, and area of the multiple monitoring areas. and photos;

The safety prediction system includes a three-dimensional modeling module, a danger prediction module and an early warning module,

Wherein, the information acquired by the information acquisition module transmits the acquired information to the three-dimensional modeling module and the risk prediction module through the wireless transmission module, and the three-dimensional modeling module establishes a three-dimensional model of the slope according to the acquired information;

The hazard prediction module establishes a hazard prediction model according to the acquired information, calculates the probability value of landslide in the monitored area through the hazard prediction model, and then calculates the probability value of the landslide in a plurality of monitored areas through the risk judgment model to calculate the probability of the monitored slope. dangerous value;

The pre-warning module executes pre-warning according to the value of the danger value when it reaches a prescribed pre-warning reference value.

By adopting the above technical solutions, the information acquisition system obtains various data of the monitored slopes, including the slope, height, area and photos of the slopes through drones, and sends them to the safety prediction system through the wireless transmission module. The module establishes a three-dimensional model of the slope according to the obtained information and predicts the landslide situation of the slope. The early warning module executes the early warning according to the value of the dangerous value when it reaches the specified early warning reference value, so as to carry out multi-dimensional evaluation of the slope and improve the slope. The accuracy of accurate early warning of landslides.

In a preferred example of the present invention, the information acquisition module can be further configured as follows: the information acquisition module includes a microprocessor, a memory, a photosensitive module, and a light beam emission module, and the photosensitive module is used to capture a slope image and store it in the memory. , and sent to the safety prediction system through the wireless transmission module;

The light beam emission module is used to emit light beams and be captured by the light sensing module. After the light sensing module senses the first light beam, the microprocessor calculates the distance between the drone and the measuring point.

By adopting the above technical solution, the photosensitive module is used in conjunction with the beam emission module to measure the area, slope, length and other data of the monitored area, and provide accurate data support for the safety prediction system.

In a preferred example of the present invention, it can be further configured as follows: the information acquisition module further includes an angle sensor, the angle sensor is used for sensing the deflection angle of the photosensitive module, and the microprocessor detects the unmanned person through the deflection angle. Correct the distance between the machine and the measuring point.

By adopting the above technical solution, since the light sensing module and the beam emitting module may be deflected during use, the angle sensor corrects the deflection angle to reduce the inaccurate measurement results caused by the angle deflection.

In a preferred example of the present invention, the three-dimensional modeling module can be further configured as follows: the three-dimensional modeling module includes a three-dimensional modeling unit and a parameter setting unit,

The three-dimensional modeling unit builds a three-dimensional model through the slope, height, area and photos of the slope acquired by the information acquisition system;

The parameter setting unit inputs geological factors and hydrological factors in the three-dimensional model.

By adopting the above technical solutions, geological factors and hydrological factors are input into the three-dimensional model of the slope, so that the three-dimensional model has multi-dimensional evaluation criteria, and the prediction results are more accurate.

In a preferred example of the present invention, it may be further configured that: the safety prediction system further includes a rainfall intensity acquisition unit, and the rainfall intensity acquisition unit is configured to acquire the rainfall intensity of the monitoring area in real time.

By adopting the above technical solution, the rainfall intensity acquisition unit is used to acquire the rainfall intensity of the monitoring area in real time and import it into the 3D model, so that the 3D model is real-time and more accurate for the prediction results.

In a preferred example, the present invention can be further configured as: the risk prediction model E=F(h, s, t, x, l),

Among them, h represents the height of the monitoring area; S represents the area of the monitoring area; t represents the geological factor of the monitoring area; x represents the hydrological factor of the monitoring area; l represents the slope of the monitoring area.

By adopting the above technical solution, the hazard prediction model includes the height, area, geological factor, hydrological factor and slope of the monitored area, so the three-dimensional model established in this way is more accurate, and the result of hazard prediction is more accurate.

In a preferred example of the present invention, it can be further configured as follows: the risk prediction model establishes a feedback dynamic neural network, and the artificial intelligence fuzzy control method is used to put each parameter into the machine learning model for learning, so as to obtain the corresponding risk prediction Model.

By adopting the above technical solutions, the risk prediction model is more accurate through the training of the machine learning model, and the prediction of the results is more accurate.

In a preferred example, the present invention can be further configured as: the risk judgment model Y=n ₁ *E ₁ + n ₂ *E ₂ +n ₃ *E ₃ + n ₄ *E ₄ ……, where n ₁ + n ₂ +n ₃ +n ₄ +...=1.

By adopting the above technical solution, since each monitored area has different influences on the entire slope and landslide according to its different positions, different weights are allocated according to different positions, so that the possible prediction accuracy of the possible landslide of the slope is higher.

To sum up, the present invention includes at least one of the following beneficial technical effects:

The second purpose of the present invention is achieved through the following technical solutions:

9. A method for using a safety monitoring system based on UAV and three-dimensional modeling technology, the specific steps are as follows:

S1: The UAV carries an information acquisition module and a wireless transmission module, and the information acquisition module divides the slope into multiple monitoring areas;

S2: Select two points on the same projection line in the monitored area, the beam emission module emits beams to the two points in the monitored area, the light sensing module senses the reflected beam, and calculates the straight line between the drone and the monitored area. distance, and obtain the vertical distance between two points through the drone, and then calculate the slope of the monitored area;

S3: After obtaining the slope of the monitored area, the length and width of the boundary of the monitored area are measured by the drone, so as to measure the area of the monitored area, and the measured area, slope and height of the monitored area are passed through The wireless transmission module is sent to the safety prediction system;

S4: The 3D modeling unit builds a 3D model based on the slope, height, area and photos obtained by the information acquisition system, and inputs geological factors and hydrological factors into the 3D model;

S5: The hazard prediction module establishes a hazard prediction model according to the obtained information, and calculates the probability value of the landslide in the monitored area through the hazard prediction model, and then calculates the probability value of the landslide in the monitored area through the risk judgment model to calculate the probability of the monitored slope. dangerous value;

S6: The early warning module executes the early warning according to the value of the dangerous value when it reaches the specified early warning reference value.

By adopting the above technical solutions, the possibility of landslides can be predicted in advance, especially in the rainy season, accidents caused by landslides can be prevented, and prevention can be done in advance.

In a preferred example of the present invention, it may be further configured that: in S5, the rainfall intensity obtaining unit is used to obtain the rainfall intensity of the monitoring area in real time, and adjust the hydrological factor according to the rainfall intensity.

By adopting the above technical solution, the real-time rainfall intensity is input into the hazard prediction model, and the prediction result can be more accurate.

To sum up, the present invention includes at least one of the following beneficial technical effects:

1. The information acquisition system obtains various data of the monitored slope through the drone, including the slope, height, area and photos of the slope, and sends it to the safety prediction system through the wireless transmission module. The three-dimensional modeling module is based on the obtained data. The information establishes a three-dimensional model of the slope and predicts the landslide situation of the slope. The early warning module executes the early warning according to the value of the dangerous value when it reaches the specified early warning reference value, so as to carry out multi-dimensional evaluation of the slope and improve the accurate early warning of the slope and landslide. accuracy;

2. Since the photosensitive module and the beam emission module may be deflected during use, the angle sensor corrects the deflection angle to reduce the inaccurate measurement results caused by the angle deflection;

3. Since each monitored area has different influences on the entire slope and landslide according to its location, different weights are assigned according to each location, so that the possible prediction accuracy of the possible landslide of the slope is higher.

Description of drawings

Figure 1 is a system block diagram of a safety monitoring system based on UAV and 3D modeling technology.

Figure 2 is a system block diagram of an information acquisition module.

Figure 3 is a system block diagram of the 3D modeling module.

Detailed ways

The present invention will be further described in detail below with reference to the accompanying drawings.

Embodiment: Referring to FIG. 1 , it is a safety monitoring system based on UAV and three-dimensional modeling technology disclosed in the present invention, including an information acquisition system and a safety prediction system.

Referring to Figure 1, the information acquisition system includes an unmanned aerial vehicle, an information acquisition module and a wireless transmission module arranged on the unmanned aerial vehicle. The information acquisition module divides the slope into multiple monitoring areas, and obtains the slope, height, and area of the multiple monitoring areas. and photos.

The wireless transmission module can use Bluetooth, WIFI, 4G, ZIGBE, GPRS and other wireless transmission modules.

The drone is also equipped with a digital barometer, electronic gyroscope, GPS positioning module, ultra-wave speed measurement or pitot tube or micro-differential pressure wind speed sensor, which are used to measure the altitude, posture, speed and position of the drone respectively.

2 , the information acquisition module includes a microprocessor, a memory, a photosensitive module, and a beam emission module. The photosensitive module is used to capture the slope image, store it in the memory, and send it to the safety prediction system through the wireless transmission module.

The beam emission module is used to emit light beams and be captured by the light sensor module. After the light sensor module senses the first light beam, the distance between the drone and the measuring point is calculated by the microprocessor according to the speed-time formula.

The information acquisition module also includes an angle sensor, the angle sensor is used to sense the deflection angle of the photosensitive module, and the microprocessor corrects the distance between the drone and the measuring point through the deflection angle.

The information acquisition system is mainly used to acquire the slope, height, area and photos of the monitored area, and send it to the safety prediction system through the wireless transmission module.

1 and 3, the safety prediction system includes a three-dimensional modeling module, a danger prediction module and an early warning module.

The 3D modeling module builds a 3D model of the slope according to the obtained information, and inputs various parameters.

Risk prediction model E=F(h, s, t, x, l), where h represents the height of the monitoring area; S represents the area of the monitoring area; t represents the geological factor of the monitoring area; x represents the hydrological factor of the monitoring area; l represents the slope of the monitoring area.

The 3D modeling module includes a 3D modeling unit and a parameter setting unit. The 3D modeling unit builds a 3D model through the slope, height, area and photos of the slope obtained by the information acquisition system. The parameter setting unit inputs geological and hydrological factors in the 3D model.

The safety prediction system further includes a rainfall intensity acquisition unit, which is used to acquire the rainfall intensity of the monitoring area in real time.

The hazard prediction module establishes a hazard prediction model based on the obtained information, and calculates the probability value of the landslide in the monitored area through the hazard prediction model, and then calculates the risk value of the monitored slope by using the probability value of the landslide in multiple monitored areas through the hazard judgment model. .

The hazard prediction model establishes a feedback dynamic neural network, and uses the artificial intelligence fuzzy control method to put each parameter into the machine learning model for learning, so as to obtain the corresponding hazard prediction model.

Risk judgment model Y=n ₁ *E ₁ + n ₂ *E ₂ + n ₃ *E ₃ + n ₄ *E ₄ ……, where n ₁ +n ₂ +n ₃ +n ₄ +……=1.

The pre-warning module executes the pre-warning according to the value of the dangerous value when it reaches the specified pre-warning reference value.

Embodiment: a method of using a safety monitoring system based on unmanned aerial vehicle and three-dimensional modeling technology disclosed in the present invention, the specific steps are as follows:

S1: The UAV carries an information acquisition module and a wireless transmission module, and the information acquisition module divides the slope into multiple monitoring areas;

S2: Select two points on the same projection line in the monitored area, the beam emission module emits beams to the two points in the monitored area, the light sensing module senses the reflected beam, and calculates the straight line between the drone and the monitored area. distance, and obtain the vertical distance between two points through the drone, and then calculate the slope of the monitored area;

S3: After obtaining the slope of the monitored area, the length and width of the boundary of the monitored area are measured by the drone, so as to measure the area of the monitored area, and the measured area, slope and height of the monitored area are passed through The wireless transmission module is sent to the safety prediction system;

S4: The 3D modeling unit builds a 3D model based on the slope, height, area and photos obtained by the information acquisition system, and inputs geological factors and hydrological factors into the 3D model;

S5: The hazard prediction module establishes a hazard prediction model according to the obtained information, and calculates the probability value of the landslide in the monitored area through the hazard prediction model, and then calculates the probability value of the landslide in the monitored area through the risk judgment model to calculate the probability of the monitored slope. dangerous value;

S6: The early warning module executes the early warning according to the value of the dangerous value when it reaches the specified early warning reference value.

In S5, the rainfall intensity acquisition unit is used to acquire the rainfall intensity of the monitoring area in real time, and adjust the hydrological factor according to the rainfall intensity.

The embodiments of this specific embodiment are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore: all equivalent changes made according to the structure, shape and principle of the present invention should be covered in within the protection scope of the present invention.

Claims (10)

1. The utility model provides a safety monitoring system based on unmanned aerial vehicle and three-dimensional modeling technique which characterized in that: comprises an information acquisition system and a safety prediction system,

the information acquisition system comprises an unmanned aerial vehicle, an information acquisition module and a wireless transmission module, wherein the information acquisition module and the wireless transmission module are arranged on the unmanned aerial vehicle, and the information acquisition module divides the side slope into a plurality of monitoring areas and acquires the gradient, the height, the area and the pictures of the plurality of monitoring areas;

the safety prediction system comprises a three-dimensional modeling module, a danger prediction module and an early warning module,

the information acquired by the information acquisition module is transmitted to the three-dimensional modeling module and the danger prediction module through the wireless transmission module, and the three-dimensional modeling module establishes a three-dimensional slope model according to the acquired information;

the risk prediction module establishes a risk prediction model according to the acquired information, calculates the probability value of collapse of the monitored area through the risk prediction model, and then calculates the risk value of the monitored side slope through the risk judgment model according to the probability values of collapse of the monitored areas;

and the early warning module executes early warning when the value of the danger value reaches a specified early warning reference value.

2. The safety monitoring system based on unmanned aerial vehicle and three-dimensional modeling technology of claim 1, characterized in that: the information acquisition module comprises a microprocessor, a memory, a light sensing module and a light beam emission module, wherein the light sensing module is used for shooting and storing a slope image in the memory and sending the slope image to the safety prediction system through the wireless transmission module;

the light beam emitting module is used for emitting light beams and is captured by the light sensing module, and after the light sensing module senses the first light beam, the distance between the unmanned aerial vehicle and the measuring point is calculated through the microprocessor.

3. The safety monitoring system based on unmanned aerial vehicle and three-dimensional modeling technology of claim 2, characterized in that: the information acquisition module comprises an angle sensor, the angle sensor is used for sensing the deflection angle of the light sensing module, and the microprocessor corrects the distance between the unmanned aerial vehicle and the measuring point through the deflection angle.

4. The safety monitoring system based on unmanned aerial vehicle and three-dimensional modeling technology of claim 3, characterized in that: the three-dimensional modeling module comprises a three-dimensional modeling unit and a parameter setting unit,

the three-dimensional modeling unit establishes a three-dimensional model through the slope, the height, the area and the picture of the side slope acquired by the information acquisition system;

the parameter setting unit inputs a geological factor and a hydrological factor in the three-dimensional model.

5. The safety monitoring system based on unmanned aerial vehicle and three-dimensional modeling technology of claim 4, characterized in that: the safety prediction system further comprises a rainfall intensity acquisition unit, and the rainfall intensity acquisition unit is used for acquiring the rainfall intensity of the monitoring area in real time.

6. The safety monitoring system based on unmanned aerial vehicle and three-dimensional modeling technology of claim 5, characterized in that: the risk prediction model E = F (h, s, t, x, l),

wherein h represents the height of the monitoring area; s represents the area of the monitoring area; t represents a geological factor of the monitored area; x represents a hydrological factor of the monitored area; l represents the gradient of the monitored area.

7. The safety monitoring system based on unmanned aerial vehicle and three-dimensional modeling technology of claim 6, characterized in that: and the risk prediction model establishes a feedback dynamic neural network, and each parameter is put into a machine learning model for learning by adopting an artificial intelligence fuzzy control method, so that a corresponding risk prediction model is obtained.

8. The safety monitoring system based on unmanned aerial vehicle and three-dimensional modeling technology of claim 6, characterized in that: the danger judging model Y = n₁*E₁+ n₂*E₂+ n₃*E₃+ n₄*E₄… …, wherein n is₁+n₂+n₃+n₄+……=1。

9. A safety monitoring system using method based on an unmanned aerial vehicle and a three-dimensional modeling technology is characterized in that: the method comprises the following specific steps:

s1: the unmanned aerial vehicle carries an information acquisition module and a wireless transmission module, and the information acquisition module divides the side slope into a plurality of monitoring areas;

s2: selecting two points on the same projection line in a monitored area, enabling the light beam emitting module to emit light beams to the two points in the monitored area, enabling the light sensing module to sense the reflected light beams, calculating the linear distance between the unmanned aerial vehicle and the two points in the monitored area, obtaining the vertical distance between the two points through the unmanned aerial vehicle, and obtaining the gradient of the monitored area through calculation;

s3: after the gradient of the monitored area is obtained, the boundary length and the width of the monitored area are measured through the unmanned aerial vehicle, so that the area of the monitored area is measured, and the measured area, gradient and height of the monitored area are sent to a safety prediction system through the wireless transmission module;

s4: the three-dimensional modeling unit establishes a three-dimensional model through the slope, the height, the area and the picture of the slope acquired by the information acquisition system, and inputs a geological factor and a hydrological factor into the three-dimensional model;

s5: the danger prediction module establishes a danger prediction model according to the acquired information, calculates the probability value of collapse of the monitored area through the danger prediction model, and then calculates the danger value of the monitored side slope through the danger judgment model according to the probability values of collapse of the monitored areas;

s6: and the early warning module executes early warning when the value of the danger value reaches a specified early warning reference value.

10. The method for using the safety monitoring system based on the unmanned aerial vehicle and the three-dimensional modeling technology according to claim 9, is characterized in that: in S5, the rainfall intensity obtaining unit is configured to obtain the rainfall intensity of the monitored area in real time, and implement adjustment of the hydrological factor according to the rainfall intensity.

Images