Tunnel inner wall water seepage and vibration monitoring and analyzing device based on artificial intelligence

Abstract

The invention relates to the field of tunnel monitoring, in particular to a tunnel inner wall water seepage and vibration monitoring and analyzing device based on artificial intelligence, which comprises a vibration sensor and a controller, and a mounting frame is arranged on the vibration sensor; a humidity sensor is fixedly connected to the end, away from the mounting frame, of the vibration sensor, a water absorption cotton strip is detachably connected to the humidity sensor, the humidity sensor is used for detecting the humidity of the water absorption cotton strip, one end of the water absorption cotton strip is detachably connected with the inner wall of the tunnel, and the other end of the water absorption cotton strip extends into the tunnel; the end, away from the inner wall of the tunnel, of the water absorption cotton strip is fixedly connected with an inertial sensor. The vibration sensor, the humidity sensor and the inertial sensor are in signal connection with the controller. The controller is used for judging the fluttering amplitude of the water-absorbing cotton sliver in the tunnel based on the inertial sensor, and judging whether the vibration data monitored by the vibration sensor is vibration generated by vehicle passing based on the difference between the fluttering amplitude of the water-absorbing cotton sliver and the fluttering amplitude of the water-absorbing cotton sliver which only vibrates caused by airflow generated by the vehicle in the tunnel.

Description

Technical Field

[0001] The present invention relates to the field of tunnel monitoring, and in particular to an artificial intelligence-based tunnel inner wall water seepage and vibration monitoring and analysis device. Background Art

[0002] Tunnel seepage refers to the phenomenon that water seeps into the tunnel due to various reasons during the construction or operation of the tunnel. Tunnel seepage not only affects the structural safety and service life of the tunnel, but also threatens driving safety. Long-term seepage may reduce the strength of the tunnel lining concrete, accelerate the aging and damage of the concrete, and even cause lining voids, reducing the bearing capacity of the tunnel.

[0003] Tunnel vibration refers to the vibration phenomenon caused by various internal and external factors during operation. These vibrations may come from the operation of construction machinery, the passage of traffic vehicles, changes in geological conditions, and even natural earthquake activities. Tunnel vibration not only affects the comfort of surrounding residents, but also threatens the structural safety of buildings. In severe cases, it may even cause damage to the tunnel structure.

[0004] In the prior art, vibration sensors are usually used to detect tunnel vibration, and humidity sensors are used to detect tunnel water seepage. However, during the process of tunnel vibration, there are many sources of vibration. It is difficult for conventional vibration sensors to classify the detected vibration according to the cause of the vibration. Humidity sensors can determine whether there is water seepage, but the monitoring range is small and the practicality is poor. Summary of the invention

[0005] To solve the above problems, the present invention provides an artificial intelligence-based tunnel inner wall water seepage and vibration monitoring and analysis device for long-term detection of tunnel vibration and water seepage, and distinguishing between vibrations caused by the passage of traffic vehicles and other vibrations.

[0006] In order to achieve the above-mentioned purpose, the technical solution of the present invention is as follows: a tunnel inner wall water seepage and vibration monitoring and analysis device based on artificial intelligence, comprising a vibration sensor and a controller, wherein a mounting frame is provided on the vibration sensor, and the mounting frame is used to fix the vibration sensor to the inner wall of the tunnel;

[0007] The end of the vibration sensor away from the mounting frame is fixedly connected to a humidity sensor, and a water-absorbing cotton strip is detachably connected to the humidity sensor. The humidity sensor is used to detect the humidity of the water-absorbing cotton strip. One end of the water-absorbing cotton strip is detachably connected to the inner wall of the tunnel, and the other end of the water-absorbing cotton strip extends into the tunnel. The end of the water-absorbing cotton strip away from the inner wall of the tunnel is fixedly connected to an inertial sensor. The vibration sensor, the humidity sensor and the inertial sensor are all connected to the controller signal;

[0008] The controller is used to judge the fluttering amplitude of the absorbent cotton strip in the tunnel based on the inertial sensor, and to judge whether the vibration data monitored by the vibration sensor is the vibration caused by the passage of vehicles based on the difference between the fluttering amplitude of the absorbent cotton strip caused by the airflow generated by the vehicles running in the tunnel and the fluttering amplitude of the absorbent cotton strip that only vibrates.

[0009] The above scheme has the following beneficial effects:

[0010] 1. In this solution, the vibration sensor can detect the vibration of the tunnel, thereby obtaining the vibration condition of the tunnel. The absorbent cotton strip can guide the seepage water in the tunnel through capillary action, thereby guiding the seepage water to the humidity sensor, thereby judging the water seepage and increasing the detection range of the humidity sensor.

[0011] 2. In this solution, the absorbent cotton strips are extended into the tunnel. When vehicles pass through the tunnel, the passing of the vehicles will drive the change of the airflow in the tunnel, causing the absorbent cotton strips to float with the airflow. In tunnels such as subways or trains, the airflow effect is obvious because the tunnels are smaller and the vehicles are large and fast. The controller determines the floating amplitude of the absorbent cotton strips through the inertial sensor at the end of the absorbent cotton strips, thereby distinguishing between vibrations caused by vehicle passage and vibrations caused by other reasons.

[0012] 3. In this scheme, the large fluttering amplitude of the end of the absorbent cotton strip will make the water evaporate faster at the end of the absorbent cotton strip, thereby generating suction in the capillary of the absorbent cotton strip to form a liquid column effect, making it easier for moisture to move from the inner wall of the tunnel to the humidity sensor, thereby enhancing the convergence effect of the absorbent cotton strip on the seeping water.

[0013] Furthermore, the width of the end of the absorbent cotton strip connected to the inner wall of the tunnel is greater than the width of the end away from the inner wall of the tunnel.

[0014] Beneficial effect: The seepage water will be gathered to the humidity sensor through the absorbent cotton strips, so the width of the end connected to the inner wall of the tunnel is widened, so that the seepage water in a larger area of ​​the tunnel can be guided to the humidity sensor.

[0015] Furthermore, one end of the absorbent cotton strip connected to the inner wall of the tunnel is composed of a plurality of bifurcated branches, and the branches are detachably connected to different positions of the inner wall of the tunnel.

[0016] Beneficial effect: The bifurcated branch can reduce the overall volume of the absorbent cotton strip, so that the seeped water extends farther along the absorbent cotton strip.

[0017] Furthermore, the absorbent cotton strip is detachably connected to the inner wall of the tunnel via an adhesive sheet.

[0018] Beneficial effect: The adhesive sheet enables the absorbent cotton strip to be easily installed on the inner wall of the tunnel, making it easy to deploy.

[0019] Furthermore, the controller is used to perform a type of vibration data output by a trained convolutional neural network, wherein the convolutional neural network is trained based on inertial sensor detection values ​​generated by several vehicle driving and inertial sensor detection values ​​when only vibration occurs, and the convolutional neural network is used to input inertial sensor detection values ​​and output vibration data.

[0020] Beneficial effect: Since the end of the absorbent cotton strip extending into the tunnel is movable, vibration alone will also cause the absorbent cotton strip to flutter, but the fluttering amplitude and period are different from the airflow generated by the passage of vehicles. Through training with the inertial sensor detection values ​​generated by several vehicles and the inertial sensor detection values ​​of only vibration, a mapping for distinguishing different vibration data can be established, which is convenient for distinguishing the type of vibration caused by the inertial sensor detection values.

[0021] Furthermore, the convolutional neural network is also trained based on the vehicle driving under different humidity conditions and the inertial sensor detection values ​​when only vibration occurs. The convolutional neural network is used to input the humidity sensor detection values ​​and the inertial sensor detection values ​​to output the vibration data type.

[0022] Beneficial effect: The floating amplitude of the absorbent cotton strip will be affected by humidity, which will directly affect the quality of the absorbent cotton strip, thereby affecting the floating amplitude. By training under various humidity conditions, the absorbent cotton strip can still have a good floating performance after being soaked.

[0023] Furthermore, the convolutional neural network is trained based on the classification of various types of vehicles passing through the tunnel, and based on different preset vehicle types based on the tunnel's traffic functions.

[0024] Beneficial effect: Different vehicle models generate different airflow disturbances when passing through tunnels. By training different types of vehicle models with tunnel passage functions, the ability to judge paired tunnel passage functions can be acquired, which can better refine the judgment of vibrations caused by vehicles passing through the tunnel.

[0025] Furthermore, when the tunnel passage function is for trains, subways, light rails, high-speed rails and motor vehicles, the controller is used to preset a passing time period according to the departure schedule, and the controller is used to determine whether the vibration data is vibration generated by the passage of vehicles within the passing time period.

[0026] Beneficial effects: For tunnels such as those used by trains, subways, light rails, high-speed rails and motor vehicles, the vibration time period caused by the passage of vehicles can be predicted based on the departure schedule, and vibration classification can be performed based on the time period, thereby making the judgment of vibration more accurate.

[0027] Furthermore, the signal on the controller is connected to a reset button, which is used to be triggered when the absorbent cotton strip is replaced. The controller is used to issue an alarm that the absorbent cotton strip needs to be replaced after a preset time has passed after the reset button is triggered.

[0028] Beneficial effect: Algae will grow or dust will adhere to the absorbent cotton strip after being used for a long time, so it needs to be replaced at a certain period. The reset button can be triggered when the absorbent cotton strip is replaced, and the use time of the absorbent cotton strip is counted, thereby reminding the user to replace it.

[0029] Furthermore, the mounting frame includes an arc-shaped plate, on which a plurality of threaded holes are provided, and the threaded holes are used for assembling bolts.

[0030] Beneficial effect: The arc-shaped plate can fit the inner wall of the tunnel more closely, and the mounting frame can be fixed by fitting bolts in the threaded holes.

[0031] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is an axonometric diagram of an embodiment of a tunnel inner wall water seepage and vibration monitoring and analysis device based on artificial intelligence of the present invention;

[0033] Figure 2 It is a side view schematic diagram of an embodiment of a tunnel inner wall water seepage and vibration monitoring and analysis device based on artificial intelligence of the present invention;

[0034] Figure 3 The present invention is a logical schematic diagram of an embodiment of the tunnel inner wall water seepage and vibration monitoring and analysis device based on artificial intelligence.

[0035] The figure marks in the drawings of the specification include: 1. vibration sensor; 2. arc-shaped plate; 3. humidity sensor; 4. absorbent cotton strip; 5. inertial sensor; 6. threaded hole. DETAILED DESCRIPTION

[0036] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0038] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0039] Example 1

[0040] The following is further described in detail through specific implementation methods:

[0041] As attached Figure 1-Figure 3 As shown: an artificial intelligence-based tunnel inner wall water seepage and vibration monitoring and analysis device includes a vibration sensor 1 and a controller. A mounting frame is bolted to the vibration sensor 1. The mounting frame includes an arc-shaped plate 2. A plurality of threaded holes 6 are provided on the arc-shaped plate 2. The threaded holes 6 are used to assemble bolts.

[0042] A humidity sensor 3 is bolted to one end of the vibration sensor 1 away from the mounting frame, and a water-absorbing cotton strip 4 is detachably connected to the humidity sensor 3. The humidity sensor 3 is used to detect the humidity of the water-absorbing cotton strip 4. One end of the water-absorbing cotton strip 4 is detachably connected to the inner wall of the tunnel, and the other end of the water-absorbing cotton strip 4 extends into the tunnel. An inertial sensor 5 is adhesively fixed to one end of the water-absorbing cotton strip 4 away from the inner wall of the tunnel. The vibration sensor 1, the humidity sensor 3 and the inertial sensor 5 are all connected to the controller signal.

[0043] The controller is used to judge the fluttering amplitude of the absorbent cotton strip 4 in the tunnel based on the inertial sensor 5, and to judge whether the vibration data monitored by the vibration sensor 1 is the vibration generated by the passage of vehicles based on the difference between the fluttering amplitude of the absorbent cotton strip 4 caused by the airflow generated by the vehicles running in the tunnel and the fluttering amplitude of the absorbent cotton strip 4 that only vibrates.

[0044] The width of one end of the absorbent cotton strip 4 connected to the inner wall of the tunnel is greater than the end away from the inner wall of the tunnel. The absorbent cotton strip 4 is detachably connected to the inner wall of the tunnel through a sticky sheet, which is convenient for installing and replacing the absorbent cotton strip 4.

[0045] The vibration sensor 1 can detect the vibration of the tunnel, thereby obtaining the vibration condition of the tunnel. The absorbent cotton strip 4 can guide the seepage water of the tunnel through capillary action, thereby guiding the seepage water to the humidity sensor 3, thereby making a water seepage judgment and increasing the detection range of the humidity sensor 3.

[0046] The absorbent cotton strip 4 is further extended into the tunnel. When vehicles pass through the tunnel, the passing of the vehicles will drive the change of the airflow in the tunnel, causing the absorbent cotton strip 4 to float with the airflow. In tunnels such as subways or trains, the airflow effect is obvious because the tunnel is smaller and the vehicles are large and fast. The controller determines the floating amplitude of the absorbent cotton strip 4 through the inertial sensor 5 at the end of the absorbent cotton strip 4, thereby distinguishing the vibration caused by the passing of vehicles from the vibration caused by other reasons.

[0047] The large fluttering amplitude of the end of the absorbent cotton strip 4 will make the evaporation speed of the water at the end of the absorbent cotton strip 4 faster, thereby generating suction in the capillary of the absorbent cotton strip 4 to form a liquid column effect, making it easier for the water to move from the inner wall of the tunnel to the humidity sensor 3, thereby enhancing the convergence effect of the absorbent cotton strip 4 on the seepage water. The end of the absorbent cotton strip 4 connected to the inner wall of the tunnel is composed of a plurality of forked branches, so that it can absorb the seepage water from multiple positions, thereby detecting the seepage water at multiple points on the inner wall of the tunnel. With the enhancement of the liquid column effect, the absorbent cotton strip 4 can cover a larger inner wall of the tunnel, thereby increasing the detection range of the humidity sensor 3.

[0048] The controller is used to perform the training through the trained convolutional neural network, which is trained based on the inertial sensor 5 detection values ​​generated by the driving of several vehicles and the inertial sensor 5 detection values ​​when only vibration occurs. The convolutional neural network is used to input the inertial sensor 5 detection value and output the vibration data resulting in the type.

[0049] Since the end of the absorbent cotton strip 4 extending into the tunnel is movable, vibration alone will also cause the absorbent cotton strip 4 to flutter, but the fluttering amplitude and period are different from the airflow generated by the passing of vehicles. Through training with the inertial sensor 5 detection values ​​generated by several vehicles running and the inertial sensor 5 detection values ​​of only vibration, a mapping for distinguishing different vibration data can be established, which is convenient for distinguishing the type of vibration caused by the inertial sensor 5 detection value.

[0050] The convolutional neural network is also trained based on the vehicle driving of the absorbent cotton strip 4 under different humidity conditions and the detection values ​​of the inertial sensor 5 where only vibration occurs. The convolutional neural network is used to input the detection values ​​of the humidity sensor 3 and the inertial sensor 5 to output the vibration data resulting in the type.

[0051] The floating amplitude of the absorbent cotton strip 4 will be affected by humidity, which will directly affect the quality of the absorbent cotton strip 4, thereby affecting the floating amplitude. By training under various humidity conditions, the absorbent cotton strip 4 can still have a good floating performance after being soaked.

[0052] The convolutional neural network is trained based on the classification of various types of vehicles passing through the tunnel, and based on different preset vehicle types based on the tunnel's traffic functions.

[0053] Different types of vehicles generate different airflow disturbances when passing through tunnels. By training different types of vehicles with tunnel passage functions and acquiring the ability to judge paired tunnel passage functions, we can better refine the judgment of vibrations caused by vehicles passing through the tunnel.

[0054] When the tunnel passage function is for trains, subways, light rails, high-speed rails and motor vehicles to pass through, the controller is used to preset the passing time period according to the departure schedule, and the controller is used to determine whether the vibration data is the vibration generated by the passage of vehicles within the passing time period.

[0055] For example, in tunnels used by trains, subways, light rails, high-speed rails and EMUs, the time period of vibration caused by the passage of vehicles can be predicted based on the departure schedule, and vibration classification can be performed based on this time period, thereby making the judgment of vibration more accurate.

[0056] The signal on the controller is connected to a reset button, which is used to be triggered when the absorbent cotton strip 4 is replaced. The controller is used to issue an alarm that the absorbent cotton strip 4 needs to be replaced after a preset time has passed after the reset button is triggered.

[0057] The absorbent cotton strip 4 will grow algae or be attached with dust after being used for a long time, so it needs to be replaced at a certain period. The reset button can be triggered when the absorbent cotton strip 4 is replaced, and the use time of the absorbent cotton strip 4 is counted, thereby reminding the user to replace it.

[0058] Example 2

[0059] The difference from the above embodiment is that the end of the absorbent cotton strip 4 connected to the inner wall of the tunnel is composed of a plurality of bifurcated branches, and the branches are detachably connected to different positions of the inner wall of the tunnel.

[0060] The bifurcated branch can reduce the overall volume of the absorbent tampon 4, so that the seeped water extends further along the absorbent tampon 4.

[0061] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. Tunnel inner wall water seepage and vibration monitoring and analysis device based on artificial intelligence, characterized in that: It comprises a vibration sensor (1) and a controller, wherein a mounting frame is provided on the vibration sensor (1), and the mounting frame is used to fix the vibration sensor (1) to the inner wall of the tunnel; The end of the vibration sensor (1) away from the mounting frame is fixedly connected to a humidity sensor (3), and the humidity sensor (3) is detachably connected to a water-absorbing cotton strip (4). The humidity sensor (3) is used to detect the humidity of the water-absorbing cotton strip (4). One end of the water-absorbing cotton strip (4) is detachably connected to the inner wall of the tunnel, and the other end of the water-absorbing cotton strip (4) extends into the tunnel. The end of the water-absorbing cotton strip (4) away from the inner wall of the tunnel is fixedly connected to an inertial sensor (5). The vibration sensor (1), the humidity sensor (3) and the inertial sensor (5) are all connected to the controller signal. The controller is used to judge the fluttering amplitude of the absorbent cotton strip (4) in the tunnel based on the inertial sensor (5), and to judge whether the vibration data monitored by the vibration sensor (1) is the vibration generated by the passage of the vehicle based on the difference between the fluttering amplitude of the absorbent cotton strip (4) caused by the airflow generated by the vehicle running in the tunnel and the fluttering amplitude of the absorbent cotton strip (4) that only vibrates.

2. The tunnel inner wall water seepage and vibration monitoring and analysis device based on artificial intelligence according to claim 1 is characterized in that: The width of the end of the absorbent cotton strip (4) connected to the inner wall of the tunnel is greater than the width of the end away from the inner wall of the tunnel.

3. The tunnel inner wall water seepage and vibration monitoring and analysis device based on artificial intelligence according to claim 1 is characterized in that: One end of the absorbent cotton strip (4) connected to the inner wall of the tunnel is composed of a plurality of bifurcated branches, and the branches are detachably connected to different positions of the inner wall of the tunnel.

4. The tunnel inner wall water seepage and vibration monitoring and analysis device based on artificial intelligence according to claim 2 is characterized in that: The absorbent cotton strip (4) is detachably connected to the inner wall of the tunnel via an adhesive sheet.

5. The tunnel inner wall water seepage and vibration monitoring and analysis device based on artificial intelligence according to claim 4 is characterized in that: The controller is used to perform the operation through a trained convolutional neural network, wherein the convolutional neural network is trained based on detection values ​​of an inertial sensor (5) generated by the running of a plurality of vehicles and detection values ​​of an inertial sensor (5) only vibrating, and the convolutional neural network is used to input the detection values ​​of the inertial sensor (5) and output vibration data to result in a type.

6. The tunnel inner wall water seepage and vibration monitoring and analysis device based on artificial intelligence according to claim 5 is characterized in that: The convolutional neural network is also trained based on the vehicle driving under different humidity conditions with the absorbent cotton strip (4) and the detection value of the inertial sensor (5) that only vibrates. The convolutional neural network is used to input the detection value of the humidity sensor (3) and the detection value of the inertial sensor (5) to output the vibration data resulting in the type.

7. The tunnel inner wall water seepage and vibration monitoring and analysis device based on artificial intelligence according to claim 6 is characterized in that: The convolutional neural network is trained based on the classification of various types of vehicles passing through the tunnel, and based on different preset vehicle types based on the tunnel's traffic functions.

8. The tunnel inner wall water seepage and vibration monitoring and analysis device based on artificial intelligence according to claim 7 is characterized in that: When the tunnel passage function is for trains, subways, light rails, high-speed rails and motor vehicles to pass through, the controller is used to preset the passing time period according to the departure schedule, and the controller is used to determine whether the vibration data is the vibration generated by the passage of vehicles within the passing time period.

9. The tunnel inner wall water seepage and vibration monitoring and analysis device based on artificial intelligence according to claim 8 is characterized in that: The signal on the controller is connected to a reset button, which is used to be triggered when the absorbent cotton strip (4) is replaced. The controller is used to issue an alarm that the absorbent cotton strip (4) needs to be replaced after a preset time has passed after the reset button is triggered.

10. The tunnel inner wall water seepage and vibration monitoring and analysis device based on artificial intelligence according to claim 9 is characterized in that: The mounting frame comprises an arc-shaped plate (2), on which a plurality of threaded holes (6) are provided, and the threaded holes (6) are used for assembling bolts.

Images