System and method for early warning of bridge collision

Abstract

The invention relates to a method and a system for early warning of bridge collision, and the method comprises the steps: judging whether the bridge has the risk of being collided or not through the real-time monitoring of the driving track of a ship under the bridge and the tracking and prediction of the position of the outer contour of a target type ship, and carrying out the early warning of the passing ship in time. When the bridge is inevitably impacted, the working state of the main beam is judged according to the vibration response of the bridge and the relative displacement between the main beam and the bridge section, and when the bridge is damaged, early warning is given to bridge vehicles and ships under the bridge in time, so that secondary accidents are avoided. And the early warning comprehensiveness and the early warning accuracy are improved. The problem of low early warning accuracy caused by one-sidedness of early warning when early warning is carried out only for a bridge collision accident in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the technical field of bridge collision prevention, and in particular to a system and method for bridge collision warning. Background Art

[0002] With the continuous development and improvement of the transportation network, bridges, as important transportation hubs connecting the two sides and crossing obstacles, are shouldering increasingly heavy transportation tasks, and their number and scale are also increasing. However, the safety of bridges has always been a concern, among which bridges are hit by ships from time to time. Such accidents may not only cause serious damage to the bridge structure and affect the normal use of the bridge, but may also cause secondary accidents, posing a huge threat to traffic safety and people's lives and property.

[0003] In recent years, with the rapid development and popularization of machine vision technology, its application in the field of traffic monitoring and safety management has become more and more extensive. Machine vision technology has the advantages of non-contact, high efficiency, and strong real-time performance. It can achieve all-round and all-weather monitoring of bridges, providing a new solution for bridge safety management. However, the existing technology only provides early warning for bridge collision accidents, which is one-sided and leads to the problem of low early warning accuracy. Summary of the invention

[0004] The embodiments of the present application provide a method and system for bridge collision warning, so as to at least solve the problem that the related art only provides warning for bridge collision accidents, the warning is one-sided, and the warning accuracy is low.

[0005] In a first aspect, an embodiment of the present application provides a system for bridge collision warning, comprising a ship monitoring device, a bridge sensing device and a warning device; wherein:

[0006] The ship monitoring device includes a shooting module and a distance confirmation module, wherein the shooting module is used to record image information of the channel under the main beam, and the distance confirmation module is used to confirm the distance between the ship and the bridge;

[0007] The bridge sensing device includes a vibration detection module and a displacement detection module. The vibration detection module is used to collect vibration response data of the bridge being hit, and based on the vibration response data, identify the changes in modal parameters of the bridge before and after the impact. The displacement detection module is used to detect the displacement information of the bridge.

[0008] The early warning device is used to issue alarm information based on the monitoring information of the ship monitoring device and the sensing information of the bridge sensing device.

[0009] In one embodiment, the system further comprises:

[0010] A bridge traffic control device, the bridge traffic control device includes a traffic light and a vehicle interception device, the traffic light is arranged at the entrance of the bridge and on the piers, and is used to display warning information in a warning state to remind passing vehicles and ships; the vehicle interception device is arranged on the bridge deck corresponding to each of the piers, and is used to intercept vehicles when the displacement information is abnormal.

[0011] In one embodiment, the distance confirmation module includes a buoy, a radar positioning unit is installed on the top of the buoy, and the buoy is placed on a waterway with a preset length from the bridge pier.

[0012] In one embodiment, the buoy is connected to the river bottom by a cable, and the buoy includes an upper cavity, a lower cavity, an ejector, a base, a drive nut, a bracket, a drive motor and a drive screw;

[0013] The upper cavity is movably connected to the lower cavity, and the upper cavity and the lower cavity are in a sealed state; the lower cavity is fixed on the base, and the injector is fixed around the base; the drive nut is fixed to the inside of the upper cavity through a bracket; the drive screw passes through the drive nut, and the drive screw is connected to the drive motor, and the drive motor is fixed on the base.

[0014] In one embodiment, the driving motor drives the driving screw to rotate, and the driving nut moves on the driving screw, thereby driving the relative movement of the upper cavity and the lower cavity, thereby adjusting the volume of the internal cavity of the buoy. By adjusting the volume of the internal cavity of the buoy, the buoyancy of the buoy is adjusted. When the ship deviates from the channel, the buoyancy of the buoy is adjusted, and the buoy floats up to warn the ship that has deviated from the channel.

[0015] In one embodiment, after the buoy floats up, the angular velocity change of the buoy is calculated according to the moving speed of the ship, and the ejector adjusts the angular velocity of the buoy's rotation based on the angular velocity change through the ejected water flow to warn the ship that deviates from the channel.

[0016] In a second aspect, an embodiment of the present application provides a method for bridge collision warning, which is applied to the system of the first aspect, and the method includes:

[0017] The image information of the channel under the main beam is obtained in real time according to the shooting module, and the target type of ship is obtained;

[0018] According to the radar positioning unit, dynamically predict the distance vector between the target type ship and each buoy to obtain a dynamic prediction result;

[0019] Identify the outer contour of the target type ship, predict the future coordinates of the dangerous points of the target type ship through multi-point positioning according to the dynamic prediction result, and issue an alarm message when the coordinates of the dangerous points exceed a preset warning boundary line;

[0020] When a collision occurs, if the vibration response data exceeds the preset vibration warning value, an alarm message is issued; if the modal parameter change exceeds the preset threshold, an alarm message is issued; if the displacement sensor data in the displacement detection module exceeds the limit, it is determined that the main beam has slipped and fallen, an alarm message is issued, and the bridge traffic control device is activated.

[0021] In one embodiment, dynamically predicting the distance vector between the target type ship and each buoy according to the radar positioning unit to obtain the dynamic prediction result includes:

[0022] The radar positioning unit on the buoy transmits electromagnetic waves of different frequencies, receives reflected signals from the target type ship, and calculates the distance between the target type ship and each of the buoys by calculating the time difference between transmitting the electromagnetic wave and receiving the reflected signal;

[0023] Through the deep neural network, each distance is dynamically predicted to obtain the dynamic prediction results.

[0024] In one embodiment, the outer contour of the target type ship is identified, and according to the dynamic prediction result, the future coordinates of the dangerous points of the target type ship are predicted by multi-point positioning, and when the coordinates of the dangerous points exceed the preset warning boundary line, an alarm message is issued, including:

[0025] Determine the outer contour of the target type ship through image recognition, take each of the buoys as the center of the sphere, take the distance of the dynamic prediction result as the radius of the sphere, construct a sphere based on the center of the sphere and the radius of the sphere, establish a virtual hull based on the outer contour of the target type ship, move the virtual hull, obtain the real position of the target type ship when the virtual hull is tangent to each of the spheres, and determine the future coordinates of the dangerous point of the target type ship, wherein the coordinates of the dangerous point are the coordinates of the closest point between the target type ship and the bridge;

[0026] Compare the coordinates of the danger point to see if they exceed the preset warning boundary line. If they exceed the first warning boundary line, a green alarm will be issued; if they exceed the second warning boundary line, a yellow alarm will be issued; if they exceed the third warning boundary line, a red alarm will be issued, and a sound reminder will be issued.

[0027] In one embodiment, when a collision occurs, if the vibration response data exceeds a preset vibration warning value, if the modal parameter change exceeds a preset threshold, an alarm message is issued, including:

[0028] According to a pre-constructed bridge numerical model, different impact loads are used as inputs of the bridge numerical model, vibration response data of the bridge under different impact loads are analyzed, acceleration values ​​at the middle and quarter points of the bridge are obtained, and the acceleration values ​​are used as vibration warning values;

[0029] According to the vibration response data of the bridge when it is hit, when the vibration response data exceeds a preset multiple of the vibration response data of the bridge under environmental excitation, the traffic light is activated and an alarm message is issued;

[0030] When the vibration response data exceeds the preset vibration warning value, it is determined that the bridge component has entered a plastic state, and the bridge modal parameters under the collision state are identified. If the difference between the bridge modal parameters under the collision state and the bridge modal parameters under the normal state exceeds a preset threshold, an alarm message is issued, wherein the bridge modal parameters include frequency, vibration mode and damping ratio;

[0031] The displacement detection module is used to detect whether the beam body is displaced. When the displacement sensor data in the displacement detection module exceeds the preset limit, it is determined that the main beam has slipped and fallen, an alarm message is issued, and the bridge traffic control device is activated.

[0032] A method and system for bridge collision warning provided by an embodiment of the present application have at least the following technical effects.

[0033] The target type ship is obtained by acquiring the image information of the channel under the main beam in real time. According to the radar positioning unit, the distance vector between the target type ship and each buoy is dynamically predicted to obtain the dynamic prediction result. The outer contour of the target type ship is identified, and according to the dynamic prediction result, the future coordinates of the dangerous point of the target type ship are predicted by multi-point positioning, and an alarm message is issued when the coordinates of the dangerous point exceed the preset warning boundary line. In the event of a collision, if the vibration response data exceeds the preset vibration warning value, an alarm message is issued, if the modal parameter change exceeds the preset threshold, an alarm message is issued, if the displacement sensor data in the displacement detection module exceeds the limit, it is determined that the main beam has slipped and fallen, an alarm message is issued, and the bridge traffic control device is activated. The application monitors the driving trajectory of the ship under the bridge in real time, and by tracking and predicting the position of the outer contour of the target type ship, it is determined whether the bridge is at risk of being hit, and timely warns the passing ship. When the bridge is inevitably hit, the vibration response of the bridge and the relative displacement between the main beam and the bridge section are used to judge the working state of the main beam. When the bridge is damaged, a warning is issued to the bridge vehicle and the ship under the bridge in time to avoid secondary accidents. The comprehensiveness and accuracy of the early warning are improved, and the problem that the relevant technology only provides early warning for bridge collision accidents, the early warning is one-sided, and the early warning accuracy is low is solved.

[0034] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0036] Figure 1 is a block diagram of a system for bridge collision warning;

[0037] Figure 2 is a schematic diagram showing the arrangement of a ship monitoring device according to an exemplary embodiment;

[0038] Figure 3 is a top view of a buoy according to an exemplary embodiment;

[0039] Figure 4 is a front view of a buoy shown according to an exemplary embodiment;

[0040] Figure 5 According to an exemplary embodiment Figure 3 Middle AA section view;

[0041] Figure 6 is a schematic diagram of an installation structure of a displacement detection module according to an exemplary embodiment;

[0042] Figure 7 is a flow chart of a method for bridge collision warning according to an exemplary embodiment;

[0043] Figure 8 is a flow chart of collision warning and post-event warning according to an exemplary embodiment;

[0044] Fig. 9 is a flow chart of a bridge collision warning according to an exemplary embodiment;

[0045] Fig.10 is a schematic diagram of a warning distance according to an exemplary embodiment;

[0046] Fig.11 The present invention is a flow chart showing a bridge collision according to an exemplary embodiment.

[0047] Reference numerals:

[0048] Buoy 1, camera 2, waterway 3, bridge pier 4, main beam 5, support 6, wire-type displacement meter 7, wire-type displacement meter auxiliary installation device 8, upper cavity 9, lower cavity 10, ejector 11, base 12, drive nut 13, bracket 14, drive motor 15, and drive screw 16. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0050] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0051] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0052] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0053] In a first aspect, an embodiment of the present application provides a system for bridge collision warning. Figure 1 is a block diagram of a system for bridge collision warning, such as Figure 1 As shown, the system includes a ship monitoring device, a bridge sensing device and an early warning device; wherein,

[0054] The ship monitoring device includes a shooting module and a distance confirmation module, the shooting module is used to record the image information of the channel 3 under the main beam, and the distance confirmation module is used to confirm the distance between the ship and the bridge;

[0055] The bridge sensing device includes a vibration detection module and a displacement detection module. The vibration detection module is used to collect vibration response data of the bridge being hit, and based on the vibration response data, identify the changes in modal parameters of the bridge before and after the impact. The displacement detection module is used to detect the displacement information of the bridge.

[0056] The early warning device is used to issue alarm information based on the monitoring information of the ship monitoring device and the sensing information of the bridge sensing device.

[0057] In summary, the embodiment of the present application provides a system for bridge collision warning. It includes a ship monitoring device, a bridge sensing device and an early warning device. Among them, the ship monitoring device includes a shooting module and a distance confirmation module. The shooting module is used to record the image information of the channel 3 under the main beam, and the distance confirmation module is used to confirm the distance between the ship and the bridge. The bridge sensing device includes a vibration detection module and a displacement detection module. The vibration detection module is used to collect vibration response data of the bridge being hit, and based on the vibration response data, identify the modal parameter changes before and after the bridge is hit. The displacement detection module is used to detect the displacement information of the bridge. The early warning device is used to issue an alarm message based on the monitoring information of the ship monitoring device and the sensing information of the bridge sensing device. The comprehensiveness and accuracy of the early warning are improved, and the problem that the relevant technology only provides early warning for bridge collision accidents, the early warning is one-sided, and the early warning accuracy is low is solved.

[0058] In one embodiment, the ship monitoring device includes a shooting module and a distance confirmation module, wherein the shooting module is used to record the image information of the channel 3 under the main beam, and the distance confirmation module is used to confirm the distance between the ship and the bridge. Specifically, it includes:

[0059] Optionally, Figure 2 FIG. 1 is a schematic diagram showing the arrangement of a ship monitoring device according to an exemplary embodiment. Figure 2 As shown, the shooting module includes a camera 2. The camera 2 is arranged on the top of the pier 4. The cameras 2 are arranged in pairs to record video information in two directions to ensure that the all-round view of the channel 3 under the main beam 5 can be captured, which is used to monitor the position, speed, heading and other information of the ship on the channel 3 in real time. The camera 2 is fixedly installed to avoid shaking in a harsh service environment. When the position of the camera 2 changes, the boundary line is recalibrated. In addition, the shooting module can also be a shooting device such as an infrared camera 2, a thermal imaging camera and a panoramic camera 2. The distance confirmation module includes a buoy 1, and a radar positioning unit is provided on the top of the buoy 1. It is worth noting that the distance confirmation module can also be a distance confirmation device such as a GPS locator and an ultrasonic sensor. A radar laser trigger device is set at a preset distance from the pier (for example, it can be set to 150m). When a ship passes by, the camera 2 and the radar positioning unit are activated to avoid excessive data processing. The frame rate of the camera 2 is not less than 120 frames. Through the combination of high-frame rate camera 2 and multi-point radar positioning, high-precision real-time monitoring and dynamic prediction of ships in the channel 3 under the bridge are achieved, which effectively reduces the amount of data processing, improves the accuracy and timeliness of early warning, and ensures the safe operation of bridges and ships.

[0060] In one embodiment, the distance confirmation module includes a buoy 1, a radar positioning unit is installed on the top of the buoy 1, and the buoy 1 is placed on a channel 3 at a preset length from the bridge pier. Specifically, it includes:

[0061] A radar positioning unit is installed on the top of the buoy 1, and the buoy 1 is placed on the channel 3 at a preset distance from the bridge pier according to actual needs. For example, in this embodiment, the buoy 1 is placed on the channel 3 at a distance of 20m, 50m, 100m and 150m from the bridge pier.

[0062] Figure 3 is a top view of a buoy 1 according to an exemplary embodiment. Figure 4 is a front view of a buoy 1 according to an exemplary embodiment. Figure 5 According to an exemplary embodiment Figure 3 AA section view. Figure 3-Figure 5 As shown, the buoy 1 is riveted to the river bottom with a cable, and the buoy 1 includes an upper cavity 9, a lower cavity 10, an ejector 11, a base 12, a drive nut 13, a bracket 14, a drive motor 15 and a drive screw 16. The upper cavity 9 is nested inside the lower cavity 10, the upper cavity 9 and the lower cavity 10 are movable links, and the connection is sealed, the lower cavity 10 is fixed on the base 12, the ejector 11 is fixed around the base 12, the drive nut 13 is fixed inside the upper cavity 9 through the bracket 14, the drive screw 16 passes through the drive nut 13, the drive screw 16 is connected to the drive motor 15, and the drive motor 15 is fixed on the base 12.

[0063] The driving motor 15 drives the driving screw 16 to rotate, and the driving nut 12 moves on the driving screw 16, thereby driving the relative movement of the upper cavity 9 and the lower cavity 10. The relative distance between the upper cavity 9 and the lower cavity 10 is adjusted by rotating the driving screw 16, thereby adjusting the volume of the internal cavity. The interior of the buoy 1 is filled with compressed air, and the buoyancy of the buoy 1 is adjusted by adjusting the volume inside the buoy 1. When the ship deviates, the driving screw 16 inside the buoy 1 rotates, and the upper cavity 9 and the lower cavity 10 are separated. When the buoyancy is greater than the gravity, the buoy 1 floats up to warn the passing ships. After the buoy 1 floats up, the angular velocity change of the buoy 1 is calculated according to the moving speed of the ship. The ejector adjusts the angular velocity of the buoy 1 based on the angular velocity change through the ejected water flow, so that the buoy 1 can track the ship that deviates from the channel in real time and warn the ship that deviates from the channel 3.

[0064] In addition, the buoy 1 is made of lightweight and high-strength material, and the exterior is made of flexible material, so as to avoid damage to the ship or the buoy 1 when the ship cannot avoid collision.

[0065] The buoy 1 realizes accurate positioning and real-time warning of ships in the channel 3 through the radar positioning unit and adjustable buoyancy design. When the ship deviates from the channel 3, the buoy 1 floats up by adjusting the volume of the internal cavity, and sprays water through the ejector to adjust the angular velocity of the buoy 1, so that the buoy 1 can track the ship that deviates from the channel in real time, effectively warn the ship, and ensure the safety of the channel 3.

[0066] In one embodiment, the bridge sensing device includes a vibration detection module and a displacement detection module. The vibration detection module is used to collect vibration response data of the bridge being hit, and based on the vibration response data, identify the changes in modal parameters of the bridge before and after the impact. The displacement detection module is used to detect the displacement information of the bridge. Specifically, it includes:

[0067] Optionally, Figure 6 is a schematic diagram of the installation structure of the displacement detection module according to an exemplary embodiment. Figure 6 As shown, the vibration detection module includes an acceleration sensor, which is arranged in the middle and quarter points of the bridge (1 / 4, 4 / 2, 4 / 3, and 4 / 4 of the centerline length of the bridge) to collect vibration response data when the bridge is hit, and to collect bridge vibration signals before and after the bridge is hit, and to identify changes in bridge modal parameters. It is worth noting that the vibration detection module can also be a device for detecting vibration, such as a strain gauge and a piezoelectric sensor. The displacement detection module includes a wire-drawing displacement meter 7, which is arranged between the bridge deck 5 and the pier 4, to collect the relative displacement between the main beam and the pier, and to detect whether the beam body has slipped. It is worth noting that the displacement detection module can also be a device for detecting displacement, such as a laser displacement sensor and an inclination sensor.

[0068] The vibration detection module and displacement detection module can collect the vibration and displacement data of the bridge in real time and with high precision, ensuring the accuracy and reliability of the data. The sensors are arranged at key positions of the bridge (such as the middle and the quarter points) to comprehensively monitor the overall structural status of the bridge. By analyzing the vibration response data and identifying the changes in the modal parameters before and after the bridge impact, damage or abnormalities in the bridge structure can be discovered in time. When the modal parameter changes exceed the preset threshold, the system can issue an early warning in time to remind relevant personnel to take measures to prevent accidents.

[0069] In one embodiment, the early warning device is used to issue alarm information based on the monitoring information of the ship monitoring device and the sensing information of the bridge sensing device. Specifically, it includes:

[0070] Optionally, the position, speed and heading of the ship on the channel 3 are monitored in real time through equipment such as camera 2 and buoy 1, and the coordinates of the future dangerous points are determined according to the predicted ship trajectory. When the coordinates of the dangerous points exceed the preset warning boundary line, an alarm message is issued. The vibration response and displacement information of the bridge are monitored in real time through equipment such as acceleration sensors and displacement sensors. When the vibration response data exceeds the preset vibration warning value, and / or when the modal parameter changes exceed the preset threshold, an alarm message is issued. Among them, the alarm information includes three lights of green, yellow and red emitted by the sound and light alarm, and the sound and light alarm is arranged at the entrance and piers of the bridge. Among them, green: indicates a safe state and needs to be monitored more. Yellow: indicates that there is a potential danger and further monitoring is required. Red: indicates that there is a serious danger and immediate measures need to be taken. Sound alarm: In dangerous situations, a sound alarm is issued to remind passing ships and vehicles to pay attention to safety.

[0071] By integrating the data of ship monitoring devices and bridge sensing devices, comprehensive monitoring and multi-level early warning of bridges and waterways 3 are achieved. High-precision monitoring data and timely alarm information ensure the safe operation of ships and bridges, effectively prevent potential safety accidents and provide early warning after collisions.

[0072] In one embodiment, the system further includes a bridge traffic control device, which includes a traffic light and a vehicle interception device. The traffic light is arranged at the entrance of the bridge and on the piers, and is used to display warning information in the warning state to remind passing vehicles and ships. The vehicle interception device is arranged on the bridge deck corresponding to each pier, and is used to intercept vehicles when the displacement information is abnormal. Specifically including:

[0073] When the displacement sensor data in the displacement detection module exceeds the preset limit, it is determined that the beam body has slipped and fallen, activating the bridge traffic control device, sending out an alarm message through the traffic lights to alert passing vehicles and ships, and intercepting vehicles through the vehicle interception device, where the vehicle interception device includes a vehicle interception net, a pneumatic vehicle blocker, etc., which are used to intercept vehicles when the displacement information is abnormal. Prevent vehicles from passing through the damaged bridge and physically prevent them from moving forward. Through the vehicle interception device, vehicles are prevented from passing through the damaged bridge, reducing further damage to the bridge and ensuring the safe operation of the bridge.

[0074] In summary, the embodiment of the present application provides a system for bridge collision warning. It includes a ship monitoring device, a bridge sensing device and an early warning device. Among them, the ship monitoring device includes a shooting module and a distance confirmation module. The shooting module is used to record the image information of the channel 3 under the main beam, and the distance confirmation module is used to confirm the distance between the ship and the bridge. The bridge sensing device includes a vibration detection module and a displacement detection module. The vibration detection module is used to collect vibration response data of the bridge being hit, and based on the vibration response data, identify the modal parameter changes before and after the bridge is hit. The displacement detection module is used to detect the displacement information of the bridge. The early warning device is used to issue an alarm message based on the monitoring information of the ship monitoring device and the sensing information of the bridge sensing device. The comprehensiveness and accuracy of the early warning are improved, and the problem that the relevant technology only provides early warning for bridge collision accidents, the early warning is one-sided, and the early warning accuracy is low is solved.

[0075] In a second aspect, an embodiment of the present application provides a method for bridge collision warning. Figure 7 FIG. 1 is a flow chart of a method for bridge collision warning according to an exemplary embodiment. Figure 7 As shown, the method includes:

[0076] Step S101, obtaining image information of the channel 3 under the main beam in real time according to the shooting module, and obtaining the target type of ship;

[0077] Step S102: dynamically predict the distance vector between the target type ship and each buoy 1 according to the radar positioning unit to obtain a dynamic prediction result;

[0078] Step S103, identifying the outer contour of the target type ship, and predicting the future coordinates of the dangerous points of the target type ship through multi-point positioning according to the dynamic prediction results, and issuing an alarm message when the coordinates of the dangerous points exceed the preset warning boundary line;

[0079] Step S104: When a collision occurs, if the vibration response data exceeds the preset vibration warning value, an alarm message is issued; if the modal parameter change exceeds the preset threshold, an alarm message is issued; if the displacement sensor data in the displacement detection module exceeds the limit, it is determined that the beam body has slipped and fallen, an alarm message is issued, and the bridge traffic control device is activated.

[0080] In summary, the present application provides a method for bridge collision warning. Figure 8 FIG. 1 is a flowchart of collision warning and post-event warning according to an exemplary embodiment. Figure 8As shown, the target type ship is obtained by acquiring the image information of the channel 3 under the main beam in real time. According to the radar positioning unit, the distance vector between the target type ship and each buoy 1 is dynamically predicted to obtain the dynamic prediction result. The outer contour of the target type ship is identified, and according to the dynamic prediction result, the future dangerous point coordinates of the target type ship are predicted through multi-point positioning. When the dangerous point coordinates exceed the preset warning boundary line, an alarm message (collision warning) is issued. In the event of a collision, if the vibration response data exceeds the preset vibration warning value, an alarm message is issued, if the modal parameter change exceeds the preset threshold, an alarm message is issued, if the displacement sensor data in the displacement detection module exceeds the limit, it is determined that the beam body has slipped and fallen, an alarm message is issued, and the bridge traffic control device is activated (post-event warning). This application monitors the driving trajectory of the ship under the bridge in real time, and by tracking and predicting the position of the outer contour of the target type ship, it is determined whether the bridge is at risk of being hit, and timely warns the passing ships. When the bridge is inevitably hit, the vibration response of the bridge and the relative displacement between the main beam and the bridge section are used to judge the working state of the main beam. When the bridge is damaged, a warning is issued to the bridge vehicle and the ship under the bridge in time to avoid secondary accidents. The comprehensiveness and accuracy of the early warning are improved, and the problem that the relevant technology only provides early warning for bridge collision accidents, the early warning is one-sided, and the early warning accuracy is low is solved.

[0081] In one embodiment, step S101, based on real-time acquisition of image information of the channel 3 under the main beam, obtains the target type of ship. Specifically includes:

[0082] The image information of the channel 3 under the main beam is acquired in real time. When the ship enters the radar laser triggering position, the ship in the image is identified. When the ship is detected as a small ship, the tracking of the ship is abandoned to save computing resources. When the ship is detected as a large ship, the speed of the ship is measured. When the speed is lower than the preset speed threshold, the tracking of the ship is abandoned to save computing resources. Large ships with a speed greater than or equal to the preset speed threshold are regarded as target type ships. In this embodiment, the preset speed threshold is set to 30km / h. It is worth noting that an image processing algorithm (such as a convolutional neural network CNN) is used to identify the size type of the ship in the image. The speed of large ships is measured using a radar positioning unit.

[0083] By acquiring real-time image information of Channel 3 under the main beam, combined with image processing and radar positioning technology, efficient identification and classification of ships is achieved. By abandoning the tracking of small ships and slow-speed large ships, computing resources can be concentrated on high-risk target type ships, improving monitoring efficiency and safety. Not only does it ensure the safe operation of the bridge and Channel 3, it also optimizes the use of computing resources.

[0084] In one embodiment, step S102, based on the radar positioning unit, dynamically predicts the distance vector between the target type ship and each buoy 1 to obtain a dynamic prediction result. Specifically, it includes:

[0085] The radar positioning unit on the buoy 1 transmits electromagnetic waves of different frequencies, receives reflected signals from target type ships, and calculates the distance of the target type ships from each buoy 1 by calculating the time difference between transmitting the electromagnetic waves and receiving the reflected signals;

[0086] Through the deep neural network, each distance is dynamically predicted to obtain the dynamic prediction results.

[0087] Optionally, each buoy 1 transmits electromagnetic waves of different frequencies and receives reflected signals from target type ships. The distance of the target type ship from each buoy 1 is calculated by calculating the time difference between transmission and reception, and a distance vector of the target type ship from each buoy 1 is established. The distance vector is a vector composed of the distances between the target ship and each buoy. On this basis, a deep neural network (such as an LSTM model and a GRU model) is trained using historical distance data to enable it to predict the distance between the ship and each buoy 1 at a future time point. The real-time distance vector is input into the deep neural network model, and the predicted future distance vector is output.

[0088] By transmitting and receiving electromagnetic waves from buoy 1, the distance between the ship and each buoy 1 is calculated, and a distance vector is established. A deep neural network model is used for dynamic prediction to establish a predicted distance vector between the ship and each buoy 1. This not only achieves high-precision distance measurement and real-time dynamic prediction, but also improves overall efficiency and safety, ensuring the safe operation of the bridge and channel 3.

[0089] In one embodiment, Fig. 9 is a flow chart of a bridge collision warning according to an exemplary embodiment, as shown in FIG. Fig. 9 As shown, step S103, identifying the outer contour of the target type ship, predicting the future coordinates of the dangerous points of the target type ship through multi-point positioning according to the dynamic prediction results, and issuing an alarm message when the coordinates of the dangerous points exceed the preset warning boundary line. Specifically including:

[0090] The outer contour of the target type ship is identified through images, and each buoy 1 is used as the center of the sphere. A sphere is made with the distance of the dynamic prediction result as the radius. Based on the outer contour of the target type ship, a virtual hull is established, and the virtual hull is moved. The virtual hull is tangent to each sphere to obtain the real position of the target type ship and determine the future coordinates of the dangerous point of the target type ship, where the coordinates of the dangerous point are the coordinates of the closest point between the target type ship and the bridge.

[0091] The coordinates of the dangerous point are compared to see if they exceed the preset warning boundary line. A green alarm is issued when it exceeds the first warning boundary line, a yellow alarm is issued when it exceeds the second warning boundary line, and a red alarm is issued when it exceeds the third warning boundary line, and a sound reminder is given.

[0092] Optionally, use camera 2 to obtain image information of the channel 3 under the main beam in real time, identify the outer contour of the target type of ship through image processing technology (such as edge detection, contour extraction, etc.), and extract the outer contour of the ship for subsequent virtual hull modeling. Establish multiple spheres with each buoy 1 as the center and the distance of the state prediction result as the radius. Establish a virtual hull model based on the extracted outer contour of the ship. Move the virtual hull model in three-dimensional space until the surface of the virtual hull is tangent to each sphere to determine the true position of the ship. Based on the true position of the ship, determine the highest point or the outermost point of the ship as the coordinate of the dangerous point. Identify the pixel coordinates of each dangerous point. Use time series prediction deep neural networks such as LSTM or GRU to predict the coordinates of the most dangerous points on the ship within the next 20m.

[0093] Fig.10 is a schematic diagram of warning distance according to an exemplary embodiment. Fig.10 As shown, a camera 2 is used to record the information of the channel 3 under the bridge in real time, and the recorded image is calibrated. The positions of 0.1m, 0.2m and 0.5m from the boundary line of the channel 3 are calibrated respectively, and they are used as the preset warning boundary lines for hitting the bridge. The predicted coordinates of the danger point are compared with these preset warning boundary lines. When the coordinates of the danger point exceed the 0.1m warning boundary line, a green alarm is issued to remind the ship to pay attention. When the coordinates of the danger point exceed the 0.1m-0.2m warning boundary line, a yellow alarm is issued to remind the ship to slow down or adjust its course. When the coordinates of the danger point exceed the 0.2m-0.5m warning boundary line, a red alarm is issued, and a sound reminder is issued to remind the ship to take emergency measures immediately, such as stopping or avoiding.

[0094] The outer contour of the target type of ship is extracted through image recognition, and combined with multi-point positioning and virtual hull models, the real position of the ship is determined with high precision. Time series prediction deep neural networks such as LSTM or GRU are used to predict the coordinates of the most dangerous points of future ships. By dynamically predicting the coordinates of the dangerous points of target type ships and comparing them with the preset warning boundary lines, a multi-level warning mechanism is implemented. Through real-time monitoring and multi-level warning, the system can effectively prevent potential safety accidents and ensure the safety of bridges and passing ships.

[0095] In one embodiment, Fig.11 is a flow chart of a bridge collision according to an exemplary embodiment, as shown in FIG. Fig.11As shown, step S104, when a collision occurs, if the vibration response data exceeds the preset vibration warning value, an alarm message is issued, if the modal parameter change exceeds the preset threshold, an alarm message is issued, if the displacement sensor data in the displacement detection module exceeds the limit, it is determined that the beam body has slipped and fallen, an alarm message is issued, and the bridge traffic control device is activated, including:

[0096] According to the pre-constructed bridge numerical model, different impact loads are used as the input of the bridge numerical model, the vibration response data of the bridge under different impact loads are analyzed, the acceleration values ​​at the middle and quarter points of the bridge are obtained, and the acceleration values ​​are used as vibration warning values.

[0097] Optionally, a numerical model is used to construct a numerical model of the bridge, and different impact loads (such as collisions of ships of different tonnages, collisions of different speeds, etc.) are used as input to simulate the vibration response of the bridge under different impact loads (model output). Through numerical simulation, the vibration response data of the bridge under different impact loads are obtained, and the acceleration values ​​at the middle and quarter points of the bridge are obtained. The obtained acceleration values ​​are used as vibration warning values ​​for subsequent vibration response monitoring and warning.

[0098] According to the vibration response data of the bridge when it is hit, when the vibration response data exceeds a preset multiple of the vibration response data of the bridge under environmental excitation, the traffic light is activated and an alarm message is issued.

[0099] Optionally, the vibration response data of the bridge under normal environmental excitation is obtained through historical data or experimental data. For example, the vibration response data of the bridge in the absence of impact can be recorded as a reference for the normal state. Acceleration sensors are arranged in the middle and quarter points of the bridge to ensure that the vibration of the bridge can be fully monitored. The data of the acceleration sensor is collected in real time, and the real-time collected vibration response data is compared with the vibration response data under normal environmental excitation. When the vibration response data exceeds 2 times the vibration response data of the bridge under environmental excitation, the traffic light is activated and an alarm message is issued.

[0100] When the vibration response data exceeds the preset vibration warning value, it is determined that some components of the bridge have entered a plastic state, and the modal parameters of the bridge under the collision state are identified. If the difference between the modal parameters of the bridge under the collision state and the modal parameters of the bridge under the normal state exceeds the preset threshold, an alarm message is issued, where the modal parameters of the bridge include frequency, vibration mode and damping ratio.

[0101] Optionally, when the vibration response data exceeds the preset vibration warning value, it is judged that some components of the bridge may enter a plastic state. The preset vibration warning value can be 85%-95% of the vibration response data. In this embodiment, the preset vibration warning value is 95% of the vibration response data. Through modal analysis technology, the modal parameters of the bridge under the collision state are identified, including frequency, vibration mode and damping ratio, where the vibration mode is a vector and the position where the sensor is installed is used as a feature point. The modal parameters under the collision state are compared with the modal parameters under the normal state, and the difference is calculated. When the difference in modal parameters exceeds a preset threshold, an alarm message is issued. The preset threshold can be 15%-25%. In this example, by comparing the difference values ​​of each feature point (frequency, vibration mode and damping ratio), if any point exceeds 20%, an alarm is issued. For example, a traffic light warning is performed.

[0102] The displacement detection module is used to detect whether the beam has been displaced. When the displacement sensor data in the displacement detection module exceeds the preset limit, it is determined that the beam has slipped and fallen, an alarm message is issued, and the bridge traffic control device is activated.

[0103] Optionally, a displacement sensor is arranged between the main beam and the pier of the bridge to ensure that the displacement of the beam can be monitored in real time. The data of the displacement sensor is collected in real time, and the limit of the displacement sensor is preset. For example, when the displacement detected by the displacement sensor exceeds 10 mm, it is considered that the beam has slipped and fallen. The real-time collected displacement data is compared with the preset limit. When the displacement sensor data exceeds the preset limit, an alarm message is issued, and the bridge traffic control device, including traffic lights and vehicle interception devices, is activated to intercept vehicles on the bridge deck and prevent vehicles from passing through the damaged bridge.

[0104] In summary, the present application provides a method for bridge collision warning. The target type ship is obtained by acquiring the image information of the channel 3 under the main beam in real time. According to the radar positioning unit, the distance vector between the target type ship and each buoy 1 is dynamically predicted to obtain the dynamic prediction result. The outer contour of the target type ship is identified, and the future dangerous point coordinates of the target type ship are predicted by multi-point positioning according to the dynamic prediction result. When the coordinates of the dangerous point exceed the preset warning boundary line, an alarm message is issued. In the event of a collision, if the vibration response data exceeds the preset vibration warning value, an alarm message is issued, if the modal parameter change exceeds the preset threshold, an alarm message is issued, if the displacement sensor data in the displacement detection module exceeds the limit, it is determined that the beam body has slipped and fallen, an alarm message is issued, and the bridge traffic control device is activated. The present application monitors the driving trajectory of the ship under the bridge in real time, and by tracking and predicting the position of the outer contour of the target type ship, it is determined whether the bridge is at risk of being hit, and timely warns the passing ship. When the bridge is inevitably hit, the vibration response of the bridge and the relative displacement between the main beam and the bridge section are used to judge the working state of the main beam. When the bridge is damaged, a warning is issued to the bridge vehicle and the ship under the bridge in time to avoid secondary accidents. The comprehensiveness and accuracy of the early warning are improved, and the problem that the relevant technology only provides early warning for bridge collision accidents, the early warning is one-sided, and the early warning accuracy is low is solved.

[0105] It should be noted that the system for bridge collision warning provided in this embodiment is used to implement the above-mentioned implementation mode, and the descriptions that have been made will not be repeated. As used above, the terms "module", "unit", "subunit" and the like can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the above embodiment is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0106] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a program stored thereon. When the program is executed by a processor, a method for bridge collision warning provided in the first aspect is implemented.

[0107] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0108] In a possible implementation manner, the present invention can also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of a method for bridge collision warning provided in the first aspect.

[0109] Among them, the program code for executing the present invention can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0110] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0111] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A system for bridge collision warning, characterized in that: The system includes a ship monitoring device, a bridge sensing device and an early warning device; wherein, The ship monitoring device includes a shooting module and a distance confirmation module, wherein the shooting module is used to record image information of the channel under the main beam, and the distance confirmation module is used to confirm the distance between the ship and the bridge; The bridge sensing device includes a vibration detection module and a displacement detection module. The vibration detection module is used to collect vibration response data of the bridge being hit, and based on the vibration response data, identify the changes in modal parameters of the bridge before and after the impact. The displacement detection module is used to detect the displacement information of the bridge. The early warning device is used to issue alarm information based on the monitoring information of the ship monitoring device and the sensing information of the bridge sensing device.

2. The system according to claim 1, characterized in that The system further comprises: A bridge traffic control device, the bridge traffic control device includes a traffic light and a vehicle interception device. The traffic light is arranged at the entrance of the bridge and on the piers, and is used to display warning information in a warning state to remind passing vehicles and ships. The vehicle interception device is arranged on the bridge deck corresponding to each of the piers, and is used to intercept vehicles when the displacement information is abnormal.

3. The system according to claim 1, characterized in that The distance confirmation module comprises a buoy, a radar positioning unit is installed on the top of the buoy, and the buoy is placed on a waterway with a preset length from the bridge pier.

4. The system according to claim 3, characterized in that The buoy is connected to the river bottom through a cable, and the buoy includes an upper cavity, a lower cavity, an ejector, a base, a drive nut, a bracket, a drive motor and a drive screw; The upper cavity is movably connected to the lower cavity, and the upper cavity and the lower cavity are in a sealed state; the lower cavity is fixed on the base, and the injector is fixed around the base; the drive nut is fixed to the inside of the upper cavity through a bracket; the drive screw passes through the drive nut, and the drive screw is connected to the drive motor, and the drive motor is fixed on the base.

5. The system according to claim 4, characterized in that The driving motor drives the driving screw to rotate, and the driving nut moves on the driving screw, driving the relative movement of the upper cavity and the lower cavity to adjust the volume of the internal cavity of the buoy. By adjusting the volume of the internal cavity of the buoy, the buoyancy of the buoy is adjusted. When the ship deviates from the channel, the buoyancy of the buoy is adjusted, and the buoy floats up to warn the ship that has deviated from the channel.

6. The system according to claim 5, characterized in that After the buoy floats up, the change in angular velocity of the buoy is calculated according to the moving speed of the ship. The ejector adjusts the angular velocity of the buoy's rotation based on the change in angular velocity through the ejected water flow to warn the ship that has deviated from the channel.

7. A method for bridge collision warning, applied to the system according to any one of claims 1 to 6, characterized in that: The method comprises: The image information of the channel under the main beam is obtained in real time according to the shooting module, and the target type of ship is obtained; According to the radar positioning unit, dynamically predict the distance vector between the target type ship and each buoy to obtain a dynamic prediction result; Identify the outer contour of the target type ship, predict the future coordinates of the dangerous points of the target type ship through multi-point positioning according to the dynamic prediction results, and issue an alarm message when the coordinates of the dangerous points exceed a preset warning boundary line; When a collision occurs, if the vibration response data exceeds the preset vibration warning value, an alarm message is issued; if the modal parameter change exceeds the preset threshold, an alarm message is issued; if the displacement sensor data in the displacement detection module exceeds the limit, it is determined that the main beam has slipped and fallen, an alarm message is issued, and the bridge traffic control device is activated.

8. The method according to claim 7, characterized in that The method of dynamically predicting the distance vector between the target type ship and each buoy according to the radar positioning unit to obtain the dynamic prediction result includes: The radar positioning unit on the buoy transmits electromagnetic waves of different frequencies, receives reflected signals from the target type ship, and calculates the distance between the target type ship and each of the buoys by calculating the time difference between transmitting the electromagnetic wave and receiving the reflected signal; Through the deep neural network, each distance is dynamically predicted to obtain the dynamic prediction results.

9. The method according to claim 7, characterized in that: Identify the outer contour of the target type ship, predict the future coordinates of the dangerous points of the target type ship through multi-point positioning according to the dynamic prediction results, and issue an alarm message when the coordinates of the dangerous points exceed the preset warning boundary line, including: Determine the outer contour of the target type ship through image recognition, take the center of each buoy as the center of the sphere, take the distance of the dynamic prediction result as the radius of the sphere, construct a sphere based on the center of the sphere and the radius of the sphere, establish a virtual hull based on the outer contour of the target type ship, move the virtual hull, obtain the real position of the target type ship when the virtual hull is tangent to each sphere, and determine the future coordinates of the dangerous point of the target type ship, wherein the coordinates of the dangerous point are the coordinates of the closest point between the target type ship and the bridge; Compare the coordinates of the danger point to see if they exceed the preset warning boundary line. If they exceed the first warning boundary line, a green alarm will be issued; if they exceed the second warning boundary line, a yellow alarm will be issued; if they exceed the third warning boundary line, a red alarm will be issued, and a sound reminder will be issued.

10. The method according to claim 7, characterized in that When a collision occurs, if the vibration response data exceeds a preset vibration warning value, an alarm message is issued; if the modal parameter change exceeds a preset threshold, an alarm message is issued; if the displacement sensor data in the displacement detection module exceeds the limit, it is determined that the main beam has slipped and fallen, an alarm message is issued, and the bridge traffic control device is activated, including: According to a pre-constructed bridge numerical model, different impact loads are used as inputs of the bridge numerical model, vibration response data of the bridge under different impact loads are analyzed, acceleration values ​​at the middle and quarter points of the bridge are obtained, and the acceleration values ​​are used as vibration warning values; According to the vibration response data of the bridge when it is hit, when the vibration response data exceeds a preset multiple of the vibration response data of the bridge under environmental excitation, the traffic light is activated and an alarm message is issued; When the vibration response data exceeds the preset vibration warning value, it is determined that the bridge component has entered a plastic state, and the bridge modal parameters under the collision state are identified. If the difference between the bridge modal parameters under the collision state and the bridge modal parameters under the normal state exceeds a preset threshold, an alarm message is issued, wherein the bridge modal parameters include frequency, vibration mode and damping ratio; The displacement detection module is used to detect whether the beam body is displaced. When the displacement sensor data in the displacement detection module exceeds the preset limit, it is determined that the main beam has slipped and fallen, an alarm message is issued, and the bridge traffic control device is activated.

Images