CN116476888A - Subway tunnel defect identification detection device and method - Google Patents

Subway tunnel defect identification detection device and method Download PDF

Info

Publication number
CN116476888A
CN116476888A CN202310456542.9A CN202310456542A CN116476888A CN 116476888 A CN116476888 A CN 116476888A CN 202310456542 A CN202310456542 A CN 202310456542A CN 116476888 A CN116476888 A CN 116476888A
Authority
CN
China
Prior art keywords
tunnel
detection module
defect
sensor
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310456542.9A
Other languages
Chinese (zh)
Inventor
邱冬炜
仝玉赐
万珊珊
丁克良
刘天成
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing University of Civil Engineering and Architecture
Original Assignee
Beijing University of Civil Engineering and Architecture
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing University of Civil Engineering and Architecture filed Critical Beijing University of Civil Engineering and Architecture
Priority to CN202310456542.9A priority Critical patent/CN116476888A/en
Publication of CN116476888A publication Critical patent/CN116476888A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/10—Simultaneous control of position or course in three dimensions
    • G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
    • G05D1/106—Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B61—RAILWAYS
    • B61D—BODY DETAILS OR KINDS OF RAILWAY VEHICLES
    • B61D15/00—Other railway vehicles, e.g. scaffold cars; Adaptations of vehicles for use on railways
    • B61D15/08—Railway inspection trolleys
    • B61D15/12—Railway inspection trolleys power propelled
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B61—RAILWAYS
    • B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
    • B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
    • B61K9/08—Measuring installations for surveying permanent way
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B61—RAILWAYS
    • B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
    • B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
    • B61K9/08—Measuring installations for surveying permanent way
    • B61K9/10—Measuring installations for surveying permanent way for detecting cracks in rails or welds thereof
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U10/00—Type of UAV
    • B64U10/10—Rotorcrafts
    • B64U10/13—Flying platforms
    • B64U10/14—Flying platforms with four distinct rotor axes, e.g. quadcopters
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U20/00—Constructional aspects of UAVs
    • B64U20/80—Arrangement of on-board electronics, e.g. avionics systems or wiring
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U20/00—Constructional aspects of UAVs
    • B64U20/80—Arrangement of on-board electronics, e.g. avionics systems or wiring
    • B64U20/87—Mounting of imaging devices, e.g. mounting of gimbals
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
    • G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
    • G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
    • G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
    • G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
    • G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
    • G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
    • G01C21/1652—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments with ranging devices, e.g. LIDAR or RADAR
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
    • G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
    • G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
    • G01C21/18—Stabilised platforms, e.g. by gyroscope
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20—Instruments for performing navigational calculations
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U2101/00—UAVs specially adapted for particular uses or applications
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U2101/00—UAVs specially adapted for particular uses or applications
    • B64U2101/30—UAVs specially adapted for particular uses or applications for imaging, photography or videography

Abstract

The invention discloses a subway tunnel defect identification detection device and method, and belongs to the field of subway tunnels. The intelligent service platform is used for continuously and fully-automatically monitoring tunnel environments and tracks in real time, positioning tunnel defect positions and improving the safety and reliability of subway operation.

Description

Subway tunnel defect identification detection device and method
Technical Field
The invention relates to the field of subway tunnels, in particular to a subway tunnel defect identification detection device and method.
Background
Tunnel environment and rail damage are common problems in subway operation, such as tunnel lining cracks, lining flaking, tunnel deformation, water leakage, tunnel freeze injury, lining bulge, rail cracks, rail damage, pipeline damage, and the like. These problems not only lead to instability in subway operation, but also pose a threat to the safety of passengers. Therefore, it is important to identify and detect tunnel environments and track problems in time.
Disclosure of Invention
The invention aims to provide a subway tunnel defect identification detection device and method, which can continuously and fully monitor tunnel environment and track in real time, position tunnel defect positions and improve the safety and reliability of subway operation.
In order to achieve the above object, the present invention provides the following solutions:
a subway tunnel defect identification and detection device, comprising: the system comprises a tunnel detection module, a flight detection module and an intelligent service platform;
the tunnel detection module, the flight detection module and the intelligent service platform are connected with each other;
the tunnel detection module is used for collecting tunnel monitoring data in real time during the running of the train and determining subway tunnel defect basic information according to the tunnel monitoring data collected in real time;
The intelligent service platform is used for planning an optimal flight path for the flight detection module according to the subway tunnel defect basic information after receiving the subway tunnel defect basic information;
the flight detection module is used for carrying out tunnel inspection according to the optimal flight path when the train is stopped, and further detecting detailed information of tunnel defects and environmental information in the tunnel;
the intelligent service platform is used for obtaining subway tunnel defect identification results according to the subway tunnel defect basic information and the tunnel defect detailed information, and predicting the subway tunnel defect according to the environment information in the tunnel.
The subway tunnel defect identifying and detecting method applies the subway tunnel defect identifying and detecting device, and comprises the following steps:
determining subway tunnel defect basic information according to tunnel monitoring data acquired in real time;
planning an optimal flight path for the flight detection module according to the subway tunnel defect basic information;
when the train stops running, the flight detection module carries out tunnel inspection according to the optimal flight path, and further detects detailed tunnel defect information and environment information in the tunnel;
And obtaining subway tunnel defect identification results according to the subway tunnel defect basic information and the tunnel defect detailed information, and predicting the subway tunnel defect according to the environment information in the tunnel.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention discloses a subway tunnel defect identification detection device and method, wherein a tunnel detection module acquires tunnel monitoring data in real time during train operation, determines subway tunnel defect basic information according to the tunnel monitoring data acquired in real time, an intelligent service platform plans an optimal flight path for a flight detection module according to the subway tunnel defect basic information after receiving the subway tunnel defect basic information, the flight detection module carries out tunnel inspection according to the optimal flight path when the train stops operation, further detects tunnel defect detailed information and environment information in a tunnel, the intelligent service platform obtains a subway tunnel defect identification result according to the subway tunnel defect basic information and the tunnel defect detailed information, carries out subway tunnel defect prediction according to the environment information in the tunnel, realizes real-time continuous and full-automatic monitoring of tunnel environment and track, positions the tunnel defect position, and improves the safety and reliability of subway operation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural diagram of a subway tunnel defect identifying and detecting device provided by an embodiment of the invention;
fig. 2 is a main diagram of a tunnel detection module according to an embodiment of the present invention;
FIG. 3 is an internal diagram of a tunnel detection module according to an embodiment of the present invention;
FIG. 4 is a front view of a flight detection module according to an embodiment of the present invention;
FIG. 5 is a top view of a flight detection module according to an embodiment of the present invention;
FIG. 6 is an internal view of a flight detection module according to an embodiment of the present invention;
FIG. 7 is a block diagram of an intelligent service platform according to an embodiment of the present invention;
fig. 8 is a flowchart of a subway tunnel defect identifying and detecting method provided by an embodiment of the invention.
Symbol description: 1-wheels, 2-reflective strips, 3-rail wear detector, 4-ultrasonic rangefinder, 5-ultrasonic thickness gauge, 6-first high speed camera, 7-first LED lamp, 8-infrared detector, 9-laser rangefinder, 10-first laser radar, 11-first speed sensor, 12-first obstacle avoidance sensor, 13-first flying machine landing stage, 14-tooth spindle, 15-hook, 16-first accelerometer, 17-first gyroscope, 18-magnetometer, 19-first barometer, 20-first central control system, 21-first data interaction module, 22-fan, 23-equipment monitoring sensor, 24-data copy interface, 25-first storage system, 26-first power supply, 27-a power interface, 28-a first temperature sensor, 29-a first humidity sensor, 30-an ultrasonic sensor, 31-a second high speed camera, 32-a second lidar, 33-a second LED light, 34-a second obstacle avoidance sensor, 35-a multispectral camera, 36-a flying power device, 37-a second speed sensor, 38-a second temperature sensor, 39-a second humidity sensor, 40-a second barometer, 41-a second gyroscope, 42-a flight control computer, 43-a motor drive, 44-a first wireless charging sensor, 45-an electrical tone, 46-a second power source, 47-a second accelerometer, 48-a human-machine interaction interface, 49-a second storage system, the system comprises a cloud computing server transmission end, a 51-second wireless charging sensor, a 52-second flying machine landing stage, a 53-data processor, a 54-second central control system and a 55-third central control system.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention aims to provide a subway tunnel defect identification detection device and method, which can continuously and fully monitor tunnel environment and track in real time, position tunnel defect positions and improve the safety and reliability of subway operation.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
As shown in fig. 1, an embodiment of the present invention provides a subway tunnel defect identifying and detecting device, including: the system comprises a tunnel detection module, a flight detection module and an intelligent service platform.
The tunnel detection module, the flight detection module and the intelligent service platform are mutually connected. The tunnel detection module is used for collecting tunnel monitoring data in real time during the running of the train and determining subway tunnel defect basic information according to the tunnel monitoring data collected in real time. The intelligent service platform is used for planning an optimal flight path for the flight detection module according to the subway tunnel defect basic information after receiving the subway tunnel defect basic information. And the flight detection module is used for carrying out tunnel inspection according to the optimal flight path when the train is stopped, and further detecting detailed information of tunnel defects and environmental information inside the tunnel. The intelligent service platform is used for obtaining subway tunnel defect identification results according to the subway tunnel defect basic information and the tunnel defect detailed information, and predicting the subway tunnel defect according to the environment information in the tunnel.
With reference to fig. 1, the main functions of each structure in the subway tunnel defect identifying and detecting device are as follows:
and a tunnel detection module: the detection, diagnosis, positioning and data acquisition of diseases can be carried out on the structures and facilities in the tunnel. Such as tunnel deformation, pipeline leakage, wall cracking and other diseases, and can perform data interaction with the other two modules.
And a flight detection module: the module can be matched with various sensors to carry out the inspection of the inside of the tunnel for diseases when the train is stopped, so that the working time of the whole device is ensured to be continuous and uninterrupted, and more comprehensive tunnel condition information is obtained. The train condition can be acquired through the instruction of the intelligent service platform. Meanwhile, the module can be provided with various sensors to acquire environmental parameter information such as gas concentration, temperature, humidity, air pressure and the like in the tunnel in real time so as to monitor the environment in the tunnel in real time.
An intelligent service platform: and analyzing and processing the collected tunnel monitoring data and train conditions in real time, generating an analysis report and uploading the analysis report to the cloud service platform. And comprehensive health state monitoring and fault prediction are provided, and meanwhile, the control operations such as task distribution, charging, health state monitoring, flight path planning and the like are also carried out on the tunnel detection module and the flight detection module.
The working flow of the subway tunnel defect identifying and detecting device is as follows:
(1) The tunnel detection module is started before the train is operated, and self-checking and positioning are carried out on the equipment. Meanwhile, the inertial navigation system starts to monitor the position and the gesture of the detection vehicle in real time, so that the accuracy of data is ensured. During the driving process, the sensor is used for detecting the tunnel and collecting data.
(2) And the tunnel detection module transmits the acquired data to the intelligent service platform for analysis and processing. Or the data interaction module is used for carrying out data interaction with the flying detection robot or receiving an instruction from the service platform through the flying robot when the train is stopped.
(3) The flight detection module operates when the train is stopped, tunnel data acquisition or data collection and instruction transmission of the tunnel detection module are performed according to instructions and route planning of the intelligent service platform, and the data are transmitted to the intelligent service platform through the data interaction module.
(4) The intelligent service platform processes and analyzes the transmitted scanning data, and feeds back analysis results to the tunnel detection module and related management staff in real time, so that the state of the tunnel can be known in time, and the tunnel is uploaded to the cloud service platform. Meanwhile, various intelligent services such as man-machine interaction, data visualization, intelligent alarm and the like are provided to help management personnel to manage tunnels better.
Each structure in the subway tunnel defect recognition detection apparatus is explained in detail below with reference to fig. 2 to 7.
Tunnel detection module
Referring to fig. 2 and 3, the tunnel detection module includes: the device comprises a detection vehicle, a steel rail abrasion detector 3, an ultrasonic distance meter 4, an ultrasonic thickness meter 5, a high-speed camera array, an infrared detector 8, a laser distance meter 9, a first laser radar 10, an inertial navigation system, a first central control system 20 and a first data interaction module 21.
The detection vehicle is connected with the tail part of the train in the travelling direction and runs on the rail along with the train; the steel rail abrasion detector 3, the ultrasonic distance meter 4, the ultrasonic thickness meter 5, the high-speed camera array, the infrared detector 8, the laser distance meter 9, the first laser radar 10, the inertial navigation system, the first central control system 20 and the first data interaction module 21 are all arranged on the detection vehicle.
The steel rail abrasion detector 3, the ultrasonic distance meter 4, the ultrasonic thickness meter 5, the high-speed camera array, the infrared detector 8, the laser distance meter 9, the first laser radar 10 and the inertial navigation system are all connected with the first central control system 20; the first data interaction module 21 is respectively connected with the first central control system 20, the flight detection module and the intelligent service platform.
The infrared detector 8 is used for carrying out thermal imaging scanning on the tunnel wall to obtain an infrared thermal image of the tunnel wall; the inertial navigation system is used for monitoring the position of the train in real time; the first central control system 20 is used for controlling the laser range finder 9 to start measuring the distance from the detection vehicle to the tunnel wall defect when judging that the tunnel wall has the defect according to the tunnel wall infrared thermal image, and determining the position and the size of the tunnel wall defect by combining the position of the train.
Each high-speed camera (first high-speed camera 6) in the high-speed camera array is for capturing an image of the inside of the tunnel; the first laser radar 10 is used for acquiring three-dimensional space information of a tunnel; the first central control system 20 is further configured to determine detailed information of tunnel wall defect and a type of tunnel wall defect according to the internal image of the tunnel and three-dimensional space information of the tunnel.
The steel rail abrasion detector 3 is used for measuring the abrasion loss of the steel rail; the ultrasonic thickness gauge 5 is used for measuring the thickness of the steel rail; the ultrasonic distance meter 4 is used for measuring the distance from the detection vehicle to the steel rail; the first central control system 20 is also used for judging rail wear and tear according to the rail wear and tear and rail thickness, and judging rail corrosion and tear according to the distance from the detection vehicle to the rail.
The first data interaction module 21 is configured to perform data interaction with the flight detection module after acquiring all data of the first central control system 20, and transmit the interaction content to the intelligent service platform, and simultaneously receive an instruction from the intelligent service platform and transmit the instruction to the flight detection module.
The tunnel detection module further includes: a speed sensor, an obstacle avoidance sensor, a device monitoring sensor 23, a storage system, an LED lamp, a data copying interface 24 and a hook 15. One end of the hook 15 is connected with the detection vehicle, and the other end of the hook 15 is buckled at the tail part of the train in the travelling direction. The steel rail abrasion detector 3, the ultrasonic distance meter 4, the ultrasonic thickness meter 5, the high-speed camera, the high-speed infrared measuring instrument, the laser distance meter 9, the first laser radar 10, the inertial navigation system, the first central control system 20, the first data interaction module 21, the speed sensor, the obstacle avoidance sensor, the storage system and the LED lamp are all connected with the equipment monitoring sensor 23. The speed sensor, obstacle avoidance sensor, equipment monitoring sensor 23 and storage system are all connected to the first central control system 20.
The speed sensor is used for measuring the speed of the detection vehicle. The obstacle avoidance sensor is used for measuring state information of the obstacle. The device monitoring sensor 23 is used for detecting the operation state of each device in real time. The storage system is used to store data in the first central control system 20. The LED lamp is used for providing illumination for shooting of the high-speed camera.
The tunnel detection module mainly comprises a high-speed infrared measuring instrument (infrared ray detector 8), a high-speed moving photographic camera (first high-speed video camera 6), a high-speed laser distance measuring instrument (laser distance measuring instrument 9), a laser radar (first laser radar 10), an accelerometer (first accelerometer 16), a gyroscope (first gyroscope 17), a magnetometer 18, a barometer (first barometer 19), a data processor (a data processor in a first central control system 20), a data interaction module (first data interaction module 21), a steel rail abrasion detector 3, an ultrasonic distance measuring instrument 4, an ultrasonic thickness measuring instrument 5, an LED lamp (first LED lamp 7), an obstacle avoidance sensor (first obstacle avoidance sensor 12), a speed sensor (first speed sensor 11), a power supply (first power supply 26), a storage system (first storage system 25), an anti-collision device, a dust-proof device, a waterproof device and an equipment monitoring sensor 23. The high-speed infrared measuring instrument can perform thermal imaging scanning on the tunnel wall to detect temperature abnormality of the disease area; the high-speed moving photographic camera can shoot the internal condition of the tunnel and assist in identifying the disease type; the high-speed laser range finder can measure the position and the size of a disease area; the laser radar is used for acquiring three-dimensional space information of a target object, including position, shape, size and the like; the inertial navigation system consisting of the accelerometer, the gyroscope, the magnetometer 18 and the barometer can monitor the position and the gesture of the detection vehicle in real time, so that the accuracy of data is ensured; the data processor is in charge of processing the acquired data and analyzing to obtain the information such as the type, the position, the size and the like of the diseases; and the data interaction module is used for carrying out data interaction with the flight detection module. The data interaction module can interact with the data of the flight detection module and transmit the data to the intelligent service platform, and can also receive the instruction from the platform and transmit the instruction to the flight detection module. Therefore, the detection and diagnosis data of tunnel defects can be effectively transmitted and shared between the detection vehicle and the flight detection module; the ultrasonic distance meter 4 measures the distance between the instrument and the steel rail through the characteristic of ultrasonic rebound; the ultrasonic thickness gauge 5 detects whether the interior of the steel is corroded by ultrasonic waves; the power supply is mainly responsible for providing power support for the tunnel detection module, the sensor, the communication equipment and the like. In order to meet the requirements of the complex environment inside the tunnel, the power supply system has stable voltage output and protection functions, so that the power supply of the tunnel detection module can be connected with the train power supply system through the power interface 27. The storage system is responsible for storing equipment data such as the detection module, the sensor and the like so as to be uploaded to the intelligent service platform at any time, and has the functions of data backup and recovery. At the same time, the storage system should have sufficient storage capacity to meet the long-term data storage requirements. The anti-collision device is used for avoiding that the detection vehicle collides with objects in the tunnel during operation, and the anti-collision device such as a rubber protection pad or a metal anti-collision beam can be additionally arranged on the periphery of the detection module; the dustproof device is characterized in that a large amount of dust and sundries possibly exist in the tunnel, and the sundries possibly affect the operation of equipment, so that the dustproof device such as a filter element or a dustproof cover is required to be additionally arranged at the key part of the detection vehicle; the waterproof device is characterized in that water seepage phenomenon can occur due to the fact that cracks of cement, reinforcing steel bars and other materials possibly exist in the tunnel, and in order to avoid damage of water to equipment, the waterproof device such as sealant, waterproof sleeve and the like is required to be additionally arranged at key parts of the detection vehicle; the device monitoring sensor 23 is used to detect the operating state of the device in real time.
Because the inner space of the tunnel wall is relatively wide, two or more infrared detectors 8 and laser rangefinders 9 are required to be arranged, and if disease information is detected when one high-speed infrared detector is used for measurement, the laser rangefinder 9 on the same side as the infrared detector 8 can be controlled by a central control system for measurement. The method is realized by the logic control of the position information and the detection result of the infrared detector 8 and the laser range finder 9 in a central control system.
In fig. 1 and 2, the tunnel detection module is further provided with a wheel 1, a reflector strip 2, a first flying machine landing stage 13, a gear shaft 14 (rotatable), a fan 22, a first temperature sensor 28 and a first humidity sensor 29.
(II) flight detection Module
Referring to fig. 4 to 6, the flight detection module includes: a flying robot, a multispectral camera 35, an ultrasonic sensor 30, a second lidar 32, a temperature sensor (second temperature sensor 38), a humidity sensor (second humidity sensor 39), an optical sensor, a barometric pressure sensor (second barometer 40), a second central control system 54, and a second data interaction module.
The multispectral camera 35, the ultrasonic sensor 30, the second lidar 32, the temperature sensor, the humidity sensor, the optical sensor, the air pressure sensor, the second central control system 54 and the second data interaction module are all mounted on the flying robot. The multispectral camera 35, the ultrasonic sensor 30, the second laser radar 32, the temperature sensor, the humidity sensor, the optical sensor and the air pressure sensor are all connected with the second central control system 54, and the second central control system 54 is connected with the tunnel detection module and the intelligent service platform through the second data interaction module.
The multispectral camera 35 is used for shooting tunnel wall images, train side images and train bottom images; the ultrasonic sensor 30 is used for detecting the internal condition of the tunnel wall; the second lidar 32 is used to scan the contours and surfaces of the tunnel wall; the second central control system 54 is used to further determine tunnel defect details from the tunnel wall images, train side images, train bottom images, the interior conditions of the tunnel wall, and the contours and surfaces of the tunnel wall.
The temperature sensor, the humidity sensor, the optical sensor, and the barometric sensor are respectively configured to detect a temperature, a humidity, an illumination intensity, and a barometric pressure of an environment in which the flying robot is located, and transmit the detected temperatures, the detected humidity, the illumination intensity, and the barometric pressure to the second central control system 54.
The second data interaction module is configured to perform data interaction with the tunnel detection module and the intelligent service platform after acquiring all data of the second central control system 54, and receive an instruction from the intelligent service platform and transmit the instruction to the tunnel detection module.
The flight detection module mainly consists of a multispectral camera 35, an ultrasonic sensor 30, a laser radar (second laser radar 32), a wireless charging sensor (first wireless charging sensor 44), an acceleration sensor, a temperature sensor (second temperature sensor 38), a humidity sensor (second humidity sensor 39), an optical sensor, a barometric sensor (second barometer 40) and a flight control computer 42, an Inertial Measurement Unit (IMU), an accelerometer, a gyroscope (second gyroscope 41), a motor driver 43, an obstacle avoidance sensor (second obstacle avoidance sensor 34), an electric adjustment 45, a data interaction module (second data interaction module), and a device monitoring sensor 23. The multispectral camera 35 can perform high-resolution imaging on the tunnel wall, and detect the color, texture and other characteristics of the disease area. The images of the side face and the bottom of the train can be shot for detecting surface defects and damage conditions; the ultrasonic sensor 30 can detect the working state and damage condition of the train parts; the laser radar can measure the position and the size of a disease area, can also scan the environment around a train and is used for detecting contours, obstacles and the like; the inertial navigation system consisting of the accelerometer, the gyroscope, the magnetometer 18 and the barometer can monitor the position and the gesture of the flight detection module in real time, so that the accuracy of data is ensured; the wireless charging sensor can wirelessly charge the flight detection robot which falls on the intelligent service platform; the acceleration sensor is used for judging whether the flight detection module is impacted or vibrated according to the acceleration of the flight detection module during movement, so that the running condition of the flight detection module is known; the gyroscope sensor is used for detecting the rotation state of the flight detection module and judging whether the robot rotates unstably or not; the temperature sensor is used for detecting the temperature change of the robot, judging whether the flight detection module has overheat or supercooling conditions, and further knowing the health state of the module; the humidity sensor is used for detecting humidity change of the surrounding environment of the flight detection module and judging whether the flight detection module is in a humid environment or not; the optical sensor is used for detecting the illumination intensity around the flight detection module and judging whether the flight detection module is in an environment with darker light or too strong light; the air pressure sensor is used for detecting air pressure changes around the flight detection module so as to know the underground depth and plan the movement path better; the flight control system is composed of components such as a flight control computer 42, an Inertial Measurement Unit (IMU), an accelerometer, a gyroscope, a motor driver 43, an electric regulator 45 and the like, and is used for controlling the flight track of the flight detection module so as to ensure the stable and accurate flight of the flight detection module; the data interaction module can interact with the data of the tunnel detection module, can also interact with the data interaction module of the intelligent service platform, and can also receive the instruction from the platform and transmit the instruction to the tunnel detection module; the device monitoring sensor 23 is used to detect the operating state of the device in real time.
For tunnel wall defect detailed information, after receiving a defect information data processing result of the tunnel detection module, the intelligent service platform plans a flight path of the flight detection module, and can plan a detected optimal path for each flight detection module, so that the flight detection module can shoot all the defect areas detected by the vehicle-mounted detection module as far as possible, and further information confirmation and information supplementation are carried out on the defect areas. Meanwhile, parameters such as illuminance, temperature, humidity and the like, which are fed back to the central control system through various sensors installed in the flight detection module, can be set up through an internal adjusting system to shooting parameters such as exposure time, aperture and the like of the multispectral camera 35 so as to ensure the quality and definition of the shot image. The multispectral camera 35 can acquire image data of a plurality of wave bands, so that richer information is provided, and small changes, such as tiny cracks, scratches, water stains and the like, which cannot be distinguished by human eyes can be identified. And the lidar and ultrasonic sensor 30 in the flight detection module may also scan and detect the tunnel wall. The lidar may scan the contours and surfaces of the tunnel wall and the ultrasonic sensor 30 may detect the internal condition of the tunnel wall. The multispectral camera 35 may take images of the tunnel wall for detecting surface defects and damage conditions.
The flight detection module can also go to tunnel environments in which some subway trains cannot reach and therefore disease information cannot be detected.
In fig. 4 to 6, the flight detection module is further provided with a second high-speed camera 31, a second LED lamp 33, a flight power vehicle 36, a second speed sensor 37, a second power supply 46, and a second accelerometer 47.
(III) intelligent service platform
Referring to fig. 7, the intelligent service platform includes: a third data interaction module, a data processor 53, a cloud computing server, a remote control system, a sensor monitoring system, and a human-machine interaction interface 48.
The data processor 53 is connected with the tunnel detection module and the flight detection module through a third data interaction module, and the data processor 53 is also connected with the cloud computing server; the data processor 53 is configured to obtain, through a third data interaction module, subway tunnel defect basic information, tunnel defect detailed information, and environment information inside the tunnel from the tunnel detection module and the flight detection module, form a comprehensive diagnosis report, and upload the comprehensive diagnosis report to the cloud computing server. The cloud computing server is used for providing an optimization scheme and suggestions according to the comprehensive diagnosis report. The remote control system is connected with the tunnel detection module and the flight detection module through the third data interaction module and is used for remotely monitoring and managing the tunnel detection module and carrying out optimal route planning, task distribution and charging on the flight detection module. The sensor monitoring system is connected with the tunnel detection module and the flight detection module through the third data interaction module and is used for monitoring the health condition of each sensor in the tunnel detection module and the flight detection module. The man-machine interaction interface 48 is respectively connected with the data processor 53, the cloud computing server, the remote control system and the sensor monitoring system; the human-machine interface 48 is used for human-machine interaction and data visualization.
The intelligent service platform mainly comprises a data interaction module (a third data interaction module), a data processor 53, a cloud computing server, a man-machine interaction interface 48, a sensor monitoring system, a multi-source data fusion function and a remote control system. The data processor 53 can process, store, analyze and the like the collected data to form a comprehensive diagnosis report, and upload the report to the cloud computing server through the cloud computing server transmission end 50; the cloud computing server is responsible for comprehensively analyzing the diagnosis report and providing an optimization scheme and suggestions; the man-machine interaction interface 48 provides an interface for personnel to interact with the platform; the sensor monitoring system can monitor the health condition of each sensor and ensure the accuracy of data acquisition; as the core of the full-automatic disease identification and detection device, the functions of monitoring the health state of a sensor, distributing the tasks of an aircraft, charging the flying robot, interacting data, transmitting, storing, analyzing and the like can be realized. Meanwhile, the platform can also realize automatic control and remote control operation of the flying robot, and real-time transmission and analysis processing of data. In addition, the intelligent service platform also has the functions of on-line maintenance support, fault prediction, early warning and the like, and can provide omnibearing service support for the operation and maintenance of tunnel equipment. The data processor 53 of the intelligent service platform is a structure in the third central control system 55.
In fig. 7, the intelligent service platform is further provided with a second storage system 49, a second wireless charging sensor 51 and a second flying machine landing stage 52.
After the intelligent service platform identifies the diseases, the results can be displayed to the user for interaction through a graphical interface. The user can view the recognition results, analyze the chart, generate reports, etc. through this interface. On the interface, the user can also edit, annotate, classify, etc. the recognition results to better manage and use the data. The intelligent service platform can upload the data to the cloud server so as to facilitate the storage, sharing and analysis of the data. The cloud server may also provide powerful computing and analysis functions such as machine learning algorithms, deep learning frameworks, image processing, etc., to support more complex data analysis and applications. When the data is uploaded to the cloud server, the intelligent service platform adopts strict data protection measures to ensure that the safety and privacy of the data are not violated. This includes data encryption, access control, authentication, auditing, etc. measures to ensure that the data is not accessed, tampered with, or compromised by unauthorized third parties.
The central control system is a core control system of each module and is responsible for coordinating the work inside each module and the work between the modules. In the detection device of the invention, the central control system comprises a data preprocessing system, a data processing system, a control system and a regulating system. The control system can control the switch and working mode of each sensor, such as the switch time of each sensor, the switch and brightness adjustment of the LED lamp, etc., to ensure the sensor to work according to the required time sequence; the adjusting system can adjust the sensitivity and the working mode of the sensor, such as controlling the acquisition frequency of the sensor, adjusting the sensitivity and the working mode of the sensor, and the like, so as to meet different detection requirements.
In the disease detection process, the central control system receives measurement data from the high-speed infrared measuring instrument, analyzes whether disease information or temperature abnormality information exists, and then transmits instructions to the high-speed laser range finder 9 through the control system to emit laser beams to a disease information area. The central control system can coordinate the work of other detection modules according to the requirement, such as adjusting the shooting angle of the multispectral camera 35 or controlling the path planning of the flight detection module.
The functions of the tunnel detection module, the flight detection module and the data interaction module in the intelligent service platform are as follows: the tunnel detection module acquires data inside the tunnel through the sensor, the data can be uploaded to the intelligent service platform in a wireless communication mode after being processed, the flight detection module can also stop on the tunnel detection module to perform safer data interaction work, and meanwhile, the flight detection module can also transmit instructions from the intelligent service platform for the flight detection module. The flight detection module works when the train is stopped, and can acquire data of the external environment of the train through the sensor, for example, a camera can shoot images of the side face and the bottom of the train, and a radar can scan the surrounding environment of the train and the like. The data is also processed and then uploaded to the intelligent service platform through wireless communication. The intelligent service platform can identify diseases according to the data, generate corresponding reports and suggestions according to the identification results, and feed the results back to the tunnel detection module and the flight detection module to guide further work. Meanwhile, the intelligent service platform can send instructions to the tunnel detection module and the flight detection module, such as adjusting sensor parameters, starting or stopping detection and the like.
The invention provides a full-automatic, efficient and continuous detection device for identifying tunnel defects, which can be used for automatically and continuously finding, positioning and measuring the positions of tunnel defects and monitoring tunnel environment indexes in real time, so that the safety and reliability of subway operation are improved.
Aiming at the prior art and the problems and difficulties, a full-automatic disease identification and detection device system is provided. Compared with the traditional tunnel detection instrument, the device system has the following advantages:
1. higher security: when the train runs, a tunnel detection module in the device runs at a high speed along with the subway train in the tunnel. When the train stops running at night, tunnel diseases can be detected in real time and subway environments can be monitored through the flight detection module, personnel are not required to enter the tunnel, and operation safety is improved.
2. Higher flexibility: traditional tunnel detection car can receive tunnel size and train operating time's restriction, and the flexibility is lower. The full-automatic disease identification and detection device can detect when a train works, can also collect data and monitor environment when the train stops running, and improves flexibility and efficiency.
3. More accurate data acquisition: the defect of the subway tunnel can be detected more accurately and comprehensively. For the images and the marked coordinates acquired by the tunnel detection module, such as water leakage, cracks and the like, the flight detection module is assigned to acquire the image information with higher resolution of the disease area through task distribution of the intelligent service platform, and the more detailed information is captured.
The embodiment of the invention also provides a subway tunnel defect identifying and detecting method, which applies the subway tunnel defect identifying and detecting device, as shown in fig. 8, and comprises the following steps:
step 1: and determining subway tunnel defect basic information according to the tunnel monitoring data acquired in real time.
Exemplary, the main process of automatic disease detection is:
(1) And judging that the subway tunnel has defects according to the tunnel monitoring data acquired in real time.
Subway tunnel defects comprise tunnel wall defects, rail defects and the like.
Thermally imaging the tunnel wall and using the formula e=kt based on the radiation energy E received by the thermally imaging scan 4 Determining the temperature T of the tunnel wall; wherein K is a proportionality coefficient;
when the temperature T of the tunnel wall is greater than or equal to a temperature threshold value, judging that the tunnel wall has diseases;
before the detection starts, measuring the average distance from the tunnel detection module to the steel rail;
and after the detection is started, if the difference value between the detected distance from the tunnel detection module to the steel rail and the average distance is larger than a distance threshold value, judging that the steel rail has the concave or convex defect.
(2) And recording the position of the train when each piece of disease information is obtained, and determining the position of the tunnel detection module in the tunnel when each piece of disease information is obtained according to the position of the train.
(3) According to the position of the tunnel detection module in the tunnel when each defect information is obtained, the formula x is utilized h ＝Δxcosθ t +Δysinθ t +x t And y h ＝-Δxsinθ t +Δycosθ t Calculating the position (x h ,y h ) The method comprises the steps of carrying out a first treatment on the surface of the Wherein Deltax and Deltay respectively represent the relative positions of the center coordinates of the diseases in the tunnel detection module coordinate system and the train head, and x t And theta t The position and the direction of the tunnel detection module in the tunnel when obtaining the defect information are respectively shown, and t represents the time when obtaining the defect information.
(4) And measuring the distance from the tunnel detection module to the defect, and determining the actual depth and the actual size of the defect according to the distance from the tunnel detection module to the defect.
(5) And identifying the disease category according to the tunnel internal images continuously shot in the running process of the train.
Selecting tunnel internal images containing the defects from continuously shot tunnel internal images as defect images; dividing the distance from the high-speed camera to the tunnel wall into a plurality of discrete distance segments, and calculating the resolution corresponding to each distance segment according to the spatial resolution of the high-speed camera; reserving disease images corresponding to the distance segment with highest resolution, which is shot by the same high-speed camera; placing the reserved disease images of the same disease in the same coordinate system; stitching the disease images in the same coordinate system into an image, and registering at the joint by adopting an image registration method of feature matching to obtain a complete disease area image; an image enhancement method is adopted to enhance the signal intensity of diseases in the complete disease area image; and inputting the disease area image after image enhancement into a convolutional neural network model, and outputting disease types.
Wherein, place the disease image of the same disease that remains in the same coordinate system, specifically include:
acquiring three-dimensional point cloud of tunnelGenerating a tunnel section by utilizing the three-dimensional point cloud; expanding the tunnel section to serve as a reference coordinate space; using the formulaDetermining coordinates of each disease image in a reference coordinate space; in (x) i ,y i ) Representing coordinates of a disease image captured by the camera i in a reference coordinate space, d i For the working distance of camera i, beta i The angle between the camera i and the horizontal plane is H, and the height of the camera from the ground is the intersection point of the center axis.
The detailed process of automatic disease detection is as follows:
when the train runs, various sensors in the tunnel detection module start working along with the running of the train. The high-speed infrared measuring instrument can perform thermal imaging scanning on the tunnel wall, and temperature abnormality of the disease area is detected. The radiant energy E received by the high-speed infrared measuring instrument is in direct proportion to the temperature T of the target object, namely E=KT 4 Where K is a scaling factor, which can be obtained by instrument calibration. For a tunnel, we set a threshold offset x, and assuming that the tunnel reference temperature value is t, the threshold temperature value t 'can be expressed as t' =t+x. If the detected temperature value T satisfies the following conditions: If the disease exists, the high-speed laser range finder works to measure the position and the size of the disease area through the central control system. The high speed laser rangefinder emits a laser beam into the lesion area and measures the time t required from emission to reflection back, and then obtains a single pass time t/2. The high-speed laser distance meter calculates the distance d of the light beam in the round trip process through a built-in clock and a distance calculator. Specifically, d is equal to the product of the speed of light c and the round trip time t divided by 2, i.e., d=ct/2. Finally, the high-speed laser range finder can determine the size of the disease area by using the measured distance information. And combining the train running speed v and the time for obtaining the disease size to obtain the disease position. And upload the disease location to the data storage center.
In order to ensure the accuracy of positioning, the vehicle-mounted detection device ensures the accuracy of positioning information of diseases in a mode of combining two positioning methods. One of the detection devices is a central control system which can be connected to a train, and the position information of the train when each disease information is obtained is recorded to determine the position of the detection device in the tunnel. The second method is to obtain disease position information by an inertial navigation system in the onboard detection device.
Inertial navigation systems calculate the position, speed and direction of a train by recording the acceleration and angular velocity of the train. Combining these data with the measured defect location, the position information of the defect in the tunnel can be determined. At time t, the position, speed and direction of the on-vehicle detection device are respectively x t 、v t 、θ t The acceleration and angular velocity of the train at this time are a respectively t 、ω t . Assume that the initial position, speed and direction of the onboard detection device are x respectively 0 、v、θ 0 The position, speed and direction of the on-vehicle detection device at the moment t of acquiring the disease information can be calculated according to the following formula:
v τ 、a τ 、ω τ the speed, acceleration, and angular velocity of the onboard detection device at time τ are represented, respectively, and the speed and direction are obtained by integration. Assuming that the disease is at time t h Is detected that its center coordinate of the coordinate system under the onboard detection device is (x) h ,y h ) Through x h ＝Δxcosθ t +Δysinθ t +x t 、y h ＝-Δxsinθ t +Δycosθ t And calculating the position of the disease under the geodetic coordinate system. Δx and Δy respectively represent the center coordinates (x) of the disease in the on-vehicle detection device h ,y h ) Relative to the head of the train. The accuracy of disease position information can be improved by combining the two positioning modes for comparison analysis.
The high-speed moving photographic camera shoots videos and images in the tunnel in the whole process, and the disease type is identified in an auxiliary mode. The ultrasonic rangefinder 4 measures the distance of the instrument from the rail by the characteristic of ultrasonic rebound. Before detection starts, the instrument automatically releases ultrasonic signals to acquire m times of distance data, and the average value of the m times of distance data is assumed to be n (mm), if the distance is within a reasonable threshold range, the instrument is characterized as no depression or protrusion of the track, and if the distance exceeds the threshold range, the track is depression or protrusion.
When the train is stopped, the flight detection module starts working. The multispectral camera 35 can capture images of the train side and bottom for detecting surface defects and damage conditions. Lidar may scan the environment surrounding the train for detection of contours, obstructions, and the like. The ultrasonic sensor 30 can detect the operating state and damage condition of the train components. The data acquired by the sensors are processed and analyzed to obtain detailed information of tunnel wall faults and state and fault information of each part of the train.
The data acquired by the sensors is typically transmitted to a central control system for processing and analysis. In processing and analyzing data, a data processing system in the central control system may run algorithms and programs to process and analyze the data to extract useful information. The algorithms and programs may be run locally in the central control system or may be retrieved by invoking algorithm data, manual subsequent copying and replenishment in a remote server.
The intermediate transmission process of the sensor data to the central control system is generally as follows: the sensor (responsible for collecting raw data from the sensor and converting the data into digital signals for subsequent digital processing), the data transmission device (responsible for transmitting the collected data to a data processor in a central control system, the main device inside the device is an optical fiber), the data preprocessor (responsible for preprocessing the collected data, such as removing noise, filtering, amplifying and the like, for subsequent signal processing and analysis), the data processing system (responsible for analyzing and processing the preprocessed data and extracting disease information), and the data storage system (responsible for storing the collected data and the processed data for subsequent query and analysis).
Aiming at the disease position and information obtained by the high-speed infrared measuring instrument and the high-speed laser range finder, the high-speed moving photographic camera is combined to shoot the video and image in the tunnel in the whole course to obtain the detailed disease information and disease category.
In order to obtain the complete tunnel internal condition, a plurality of high-speed motion photographic cameras are formed into a camera array and independently collect sequence images in the tunnel. To ensure the integrity and continuity of the images, there is a partial overlap region between adjacent images. This results in the possibility of varying assessment results for the collected tunnel defect data such as cracks. For example, a long crack may be divided into a plurality of short cracks, and a short crack may be determined as a long crack by the continuity of the picture. Therefore, it is necessary to perform a stitching process on the images, thereby providing accuracy in detecting tunnel defects.
In addition, the tunnel detection module cannot be guaranteed to be stably operated in the movement process, and the distance from each camera to the tunnel wall is dynamically changed. This results in the resolution of the captured image also being dynamically variable. It is necessary to calculate the quality parameters of the image from the camera parameters and the effective imaging distance of the camera for cropping, and the best data is retained as final data. The specific process is as follows: the spatial resolution of the camera may be calculated from parameters such as the number of pixels of the camera, the imaging sensor size, the camera lens, etc. Let the resolution of the camera be r c The camera angle of view is θ and the camera distance to the tunnel wall is d, then the resolution on the tunnel wall r p It can be calculated as:where h represents the height of the image. Due to camera-to-tunnelThe distance between the wall is dynamically changed, so that when the image is cut, the distance from the camera to the wall of the tunnel is divided into a plurality of discrete distance segments, and the corresponding resolution r is calculated according to the d value of each distance segment p . Then, the image corresponding to the distance segment with the highest resolution may be selected as the final image. In addition, other quality parameters, such as brightness, contrast, etc., of the image may also be considered.
Based on this, it is assumed that the two cameras a and B parameters are identical. The camera A is far from the top of the tunnel, the field of view range of the camera is larger, and the resolution ratio is low; the camera B is closer to the tunnel in the horizontal direction, the field of view range of the camera is small, and the resolution ratio is high. During the detection process, the shooting areas of the two cameras are partially overlapped. Using cameras to obtain calibration parameters and laser radar measurements, cross-section coordinates (x A ,y A ) And (x) B ,y B ). And continuously measuring and acquiring a three-dimensional point cloud of the tunnel by using the laser radar, expanding a tunnel section generated by using the three-dimensional point cloud, and using the section as a reference coordinate space for positioning a sequence image on the section. From the following components The coordinates of the intersection point of the imaging optical axis and the tunnel curved surface can be determined, wherein beta i For the angle of camera i to the horizontal plane, d i And H is the ground clearance of the intersection point of the center axes of the cameras. Taking camera A as an example, x A For detecting the system coordinate system origin (x 0 =0), y A For the intersection point of the imaging optical axis and the tunnel curved surface to the origin (y) of the tunnel section 0 =0). Using the same method, camera B is centered in the imaging reference frame. Satisfying the collineation of the centre points, i.e. x A ＝x B . The co-linear coplanarity of the multiple cameras can improve the utilization efficiency of section data splicing, and further the shot sequence images can be obtained better.
The images of the overlapped part are spliced into a high-resolution image by image stitching, but some structural dislocation of the images is usually existed at the jointThe image overlap region forms a ghost or a seam at the image edge. Can be solved by a feature matching image registration method. The present invention uses acceleration robust features (SpeededUpRobustFeatures, SURF) for feature matching. First, a Hessian matrix is obtained for each pixel in a picture taken by the camera A, B: The function value f (x, y) is the gray value corresponding to (x, y) on the image. Wherein the discriminant of the Hessian matrix is: />When the discriminant takes a locally larger value, the point on the surface is brighter or darker than other points in the surrounding neighborhood, so that the position of the disease key point is determined. The image is then layered using a multi-layer filter, each layer being used to reflect the image features at that scale. In each layer of image, a rectangular region block of 4×4 surrounding the feature points is extracted, the main direction of the region block is calculated by using the Haar wavelet characteristics in the circular neighborhood of the feature points, and the Haar wavelet characteristics (dx, dy) of each sub-region relative to the main direction are calculated. Will->As a feature vector of the pixel region block of m×n in size, a total of 4×4×4=64-dimensional vectors are used as descriptors of SURF. The function of the descriptor is to represent the feature matching degree between any two feature points by using the Euclidean distance. And extracting m characteristic points from each image, wherein m groups of pairing relations are shared among the characteristic points, and solving an optimal matching model by using a random sampling consistency algorithm. The random sampling consistency algorithm selects a random subset of n pairing relationships from among them repeatedly. The probability of belonging to the subset per sample is +. >All of the samples belonging to the sub-The probability of the set is: p=1- (1- ω) n ) k Where p is the data randomly selected from the dataset during the iterative process. And carrying out image registration based on the matching result. Wherein the transformation relationship between every two adjacent images can be described using a transformation model with 8 or 9 degrees of freedom parameters:(x, y) (x ', y') is distributed as coordinates of corresponding matching points of the two images. Substituting the coordinates of a plurality of matching characteristic points into the formula, and solving m in a transformation matrix 0 ～m 8 For describing the registration relationship between the images.
And the complete disease area image can be obtained through the splicing and registering of the sequence images. The contrast between the damaged area and the background of the tunnel wall in the image is shown by the larger difference between the gray scale range of the crack in the local area and the gray scale range of the background. Firstly, enhancing the signal intensity of diseases by adopting image enhancement, and then classifying, detecting and dividing the diseases by utilizing a convolutional neural network (Convolutional Neural Networks, CNN) neural network model.
Step 2: and planning an optimal flight path for the flight detection module according to the subway tunnel defect basic information.
Step 3: and when the train stops running, the flight detection module carries out tunnel inspection according to the optimal flight path, and further detects detailed tunnel defect information and environment information in the tunnel.
Step 4: and obtaining subway tunnel defect identification results according to the subway tunnel defect basic information and the tunnel defect detailed information, and predicting the subway tunnel defect according to the environment information in the tunnel.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.

Claims (10)

1. Subway tunnel defect discernment detection device, its characterized in that includes: the system comprises a tunnel detection module, a flight detection module and an intelligent service platform;
the tunnel detection module, the flight detection module and the intelligent service platform are connected with each other;
the tunnel detection module is used for collecting tunnel monitoring data in real time during the running of the train and determining subway tunnel defect basic information according to the tunnel monitoring data collected in real time;
The intelligent service platform is used for planning an optimal flight path for the flight detection module according to the subway tunnel defect basic information after receiving the subway tunnel defect basic information;
the flight detection module is used for carrying out tunnel inspection according to the optimal flight path when the train is stopped, and further detecting detailed information of tunnel defects and environmental information in the tunnel;
the intelligent service platform is used for obtaining subway tunnel defect identification results according to the subway tunnel defect basic information and the tunnel defect detailed information, and predicting the subway tunnel defect according to the environment information in the tunnel.
2. The subway tunnel defect identification detection apparatus according to claim 1, wherein the tunnel detection module includes: the system comprises a detection vehicle, a steel rail abrasion detector, an ultrasonic distance meter, an ultrasonic thickness meter, a high-speed camera array, an infrared detector, a laser distance meter, a first laser radar, an inertial navigation system, a first central control system and a first data interaction module;
the detection vehicle is connected with the tail part of the train in the travelling direction and runs on the rail along with the train; the steel rail abrasion detector, the ultrasonic distance meter, the ultrasonic thickness meter, the high-speed camera array, the infrared detector, the laser distance meter, the first laser radar, the inertial navigation system, the first central control system and the first data interaction module are all arranged on the detection vehicle;
The steel rail abrasion detector, the ultrasonic distance meter, the ultrasonic thickness meter, the high-speed camera array, the infrared detector, the laser distance meter, the first laser radar and the inertial navigation system are all connected with the first central control system; the first data interaction module is respectively connected with the first central control system, the flight detection module and the intelligent service platform;
the infrared detector is used for carrying out thermal imaging scanning on the tunnel wall to obtain an infrared thermal image of the tunnel wall; the inertial navigation system is used for monitoring the position of the train in real time; the first central control system is used for controlling the laser range finder to start measuring the distance from the detection vehicle to the tunnel wall defect when judging that the tunnel wall has the defect according to the tunnel wall infrared thermal image, and determining the position and the size of the tunnel wall defect by combining the position of the train;
each high-speed camera in the high-speed camera array is used for shooting an image of the interior of the tunnel; the first laser radar is used for acquiring three-dimensional space information of the tunnel; the first central control system is also used for determining detailed information of tunnel wall defects and categories of tunnel wall defects according to the internal images of the tunnel and the three-dimensional space information of the tunnel;
the steel rail abrasion detector is used for measuring the abrasion loss of the steel rail; the ultrasonic thickness gauge is used for measuring the thickness of the steel rail; the ultrasonic distance meter is used for measuring the distance from the detection vehicle to the steel rail; the first central control system is also used for judging rail abrasion diseases according to the rail abrasion quantity and the rail thickness, and judging rail corrosion diseases according to the distance from the detection vehicle to the rail;
The first data interaction module is used for carrying out data interaction with the flight detection module after acquiring all data of the first central control system, transmitting interaction content to the intelligent service platform, receiving an instruction from the intelligent service platform, and transmitting the instruction to the flight detection module.
3. The subway tunnel defect identification detection apparatus according to claim 2, wherein the tunnel detection module further comprises: the device comprises a speed sensor, an obstacle avoidance sensor, an equipment monitoring sensor, a storage system, an LED lamp, a data copying interface and a hook;
one end of the hook is connected with the detection vehicle, and the other end of the hook is buckled at the tail part of the train in the travelling direction;
the device comprises a steel rail abrasion detector, an ultrasonic distance meter, an ultrasonic thickness meter, a high-speed camera, a high-speed infrared measuring instrument, a laser distance meter, a first laser radar, an inertial navigation system, a first central control system, a first data interaction module, a speed sensor, an obstacle avoidance sensor, a storage system and an LED lamp, wherein the storage system and the LED lamp are all connected with a device monitoring sensor;
the speed sensor, the obstacle avoidance sensor, the equipment monitoring sensor and the storage system are all connected with the first central control system;
the speed sensor is used for measuring the speed of the detection vehicle;
The obstacle avoidance sensor is used for measuring state information of the obstacle;
the equipment monitoring sensor is used for detecting the working state of each equipment in real time;
the storage system is used for storing data in the first central control system;
the LED lamp is used for providing illumination for shooting of the high-speed camera.
4. The subway tunnel defect identification detection apparatus according to claim 1, wherein the flight detection module includes: the system comprises a flying robot, a multispectral camera, an ultrasonic sensor, a second laser radar, a temperature sensor, a humidity sensor, an optical sensor, an air pressure sensor, a second central control system and a second data interaction module;
the multispectral camera, the ultrasonic sensor, the second laser radar, the temperature sensor, the humidity sensor, the optical sensor, the air pressure sensor, the second central control system and the second data interaction module are all carried on the flying robot;
the multispectral camera, the ultrasonic sensor, the second laser radar, the temperature sensor, the humidity sensor, the optical sensor and the air pressure sensor are all connected with a second central control system, and the second central control system is connected with the tunnel detection module and the intelligent service platform through a second data interaction module;
The multispectral camera is used for shooting tunnel wall images, train side images and train bottom images; the ultrasonic sensor is used for detecting the internal condition of the tunnel wall; the second laser radar is used for scanning the outline and the surface of the tunnel wall; the second central control system is used for further determining detailed information of tunnel defects according to the tunnel wall images, the train side images, the train bottom images, the internal conditions of the tunnel walls and the outlines and the surfaces of the tunnel walls;
the temperature sensor, the humidity sensor, the optical sensor and the barometric sensor are respectively used for detecting the temperature, the humidity, the illumination intensity and the barometric pressure of the environment where the flying robot is located and transmitting the detected temperatures, the detected humidity, the illumination intensity and the barometric pressure to the second central control system;
the second data interaction module is used for carrying out data interaction with the tunnel detection module and the intelligent service platform after acquiring all data of the second central control system, receiving an instruction from the intelligent service platform and transmitting the instruction to the tunnel detection module.
5. The subway tunnel defect identification and detection device according to claim 1, wherein the intelligent service platform comprises: the cloud computing system comprises a third data interaction module, a data processor, a cloud computing server, a remote control system, a sensor monitoring system and a human-computer interaction interface;
The data processor is connected with the tunnel detection module and the flight detection module through a third data interaction module, and is also connected with the cloud computing server; the data processor is used for acquiring subway tunnel defect basic information, tunnel defect detailed information and environment information in the tunnel from the tunnel detection module and the flight detection module through the third data interaction module to form a comprehensive diagnosis report, and uploading the comprehensive diagnosis report to the cloud computing server;
the cloud computing server is used for providing an optimization scheme and suggestions according to the comprehensive diagnosis report;
the remote control system is connected with the tunnel detection module and the flight detection module through a third data interaction module and is used for remotely monitoring and managing the tunnel detection module and carrying out optimal route planning, task distribution and charging on the flight detection module;
the sensor monitoring system is connected with the tunnel detection module and the flight detection module through a third data interaction module and is used for monitoring the health condition of each sensor in the tunnel detection module and the flight detection module;
the human-computer interaction interface is respectively connected with the data processor, the cloud computing server, the remote control system and the sensor monitoring system; the man-machine interaction interface is used for carrying out man-machine interaction and data visualization.
6. A subway tunnel defect identification and detection method, which is characterized in that the subway tunnel defect identification and detection method uses the subway tunnel defect identification and detection device according to any one of claims 1 to 5, and the subway tunnel defect identification and detection method comprises the following steps:
determining subway tunnel defect basic information according to tunnel monitoring data acquired in real time;
planning an optimal flight path for the flight detection module according to the subway tunnel defect basic information;
when the train stops running, the flight detection module carries out tunnel inspection according to the optimal flight path, and further detects detailed tunnel defect information and environment information in the tunnel;
and obtaining subway tunnel defect identification results according to the subway tunnel defect basic information and the tunnel defect detailed information, and predicting the subway tunnel defect according to the environment information in the tunnel.
7. The subway tunnel defect identification and detection method according to claim 6, wherein the determining subway tunnel defect basic information according to the tunnel monitoring data collected in real time specifically comprises:
judging that the subway tunnel has defects according to the tunnel monitoring data acquired in real time;
recording the position of the train when each piece of disease information is obtained, and determining the position of the tunnel detection module in the tunnel when each piece of disease information is obtained according to the position of the train;
According to the position of the tunnel detection module in the tunnel when each defect information is obtained, the formula x is utilized h ＝Δxcosθ t +Δysinθ t +x t And y h ＝-Δxsinθ t +Δycosθ t Calculating the position (x h ,y h ) The method comprises the steps of carrying out a first treatment on the surface of the Wherein Deltax and Deltay respectively represent the relative positions of the center coordinates of the diseases in the tunnel detection module coordinate system and the train head, and x t And theta t Respectively representing the position and the direction of the tunnel detection module in the tunnel when obtaining the defect information, and t represents the time when obtaining the defect information;
measuring the distance from the tunnel detection module to the defect, and determining the actual depth and the size of the defect according to the distance from the tunnel detection module to the defect;
and identifying the disease category according to the tunnel internal images continuously shot in the running process of the train.
8. The subway tunnel defect identification and detection method according to claim 7, wherein the determining that the subway tunnel has defects according to the tunnel monitoring data collected in real time specifically comprises:
thermally imaging the tunnel wall and using the formula e=kt based on the radiation energy E received by the thermally imaging scan 4 Determining the temperature T of the tunnel wall; wherein K is a proportionality coefficient;
when the temperature T of the tunnel wall is greater than or equal to a temperature threshold value, judging that the tunnel wall has diseases;
Before the detection starts, measuring the average distance from the tunnel detection module to the steel rail;
and after the detection is started, if the difference value between the detected distance from the tunnel detection module to the steel rail and the average distance is larger than a distance threshold value, judging that the steel rail has the concave or convex defect.
9. The subway tunnel defect identification and detection method according to claim 7, wherein the identifying defect type according to the tunnel interior images continuously shot during the train operation specifically comprises:
selecting tunnel internal images containing the defects from continuously shot tunnel internal images as defect images;
dividing the distance from the high-speed camera to the tunnel wall into a plurality of discrete distance segments, and calculating the resolution corresponding to each distance segment according to the spatial resolution of the high-speed camera;
reserving disease images corresponding to the distance segment with highest resolution, which is shot by the same high-speed camera;
placing the reserved disease images of the same disease in the same coordinate system;
stitching the disease images in the same coordinate system into an image, and registering at the joint by adopting an image registration method of feature matching to obtain a complete disease area image;
an image enhancement method is adopted to enhance the signal intensity of diseases in the complete disease area image;
And inputting the disease area image after image enhancement into a convolutional neural network model, and outputting disease types.
10. The subway tunnel defect identification and detection method according to claim 9, wherein the placing the remaining defect images of the same defect in the same coordinate system specifically comprises:
acquiring a three-dimensional point cloud of a tunnel, and generating a tunnel section by utilizing the three-dimensional point cloud;
expanding the tunnel section to serve as a reference coordinate space;
using the formulaDetermining coordinates of each disease image in a reference coordinate space;
in (x) i ,y i ) Representing coordinates of a disease image captured by the camera i in a reference coordinate space, d i For the working distance of camera i, beta i The angle between the camera i and the horizontal plane is H, and the height of the camera from the ground is the intersection point of the center axis.
CN202310456542.9A 2023-04-26 2023-04-26 Subway tunnel defect identification detection device and method Pending CN116476888A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310456542.9A CN116476888A (en) 2023-04-26 2023-04-26 Subway tunnel defect identification detection device and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310456542.9A CN116476888A (en) 2023-04-26 2023-04-26 Subway tunnel defect identification detection device and method

Publications (1)

Publication Number Publication Date
CN116476888A true CN116476888A (en) 2023-07-25

Family

ID=87213467

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310456542.9A Pending CN116476888A (en) 2023-04-26 2023-04-26 Subway tunnel defect identification detection device and method

Country Status (1)

Country Link
CN (1) CN116476888A (en)

Similar Documents

Publication Publication Date Title
US20210396842A1 (en) Multi-scale inspection and intelligent diagnosis system and method for tunnel structural defects
CN108496129B (en) Aircraft-based facility detection method and control equipment
Loupos et al. Autonomous robotic system for tunnel structural inspection and assessment
US9952593B2 (en) Collaborative robot for visually inspecting an aircraft
CN105302151B (en) A kind of system and method for aircraft docking guiding and plane type recognition
US10641898B1 (en) Structural displacement measurement using unmanned aerial vehicles equipped with lasers
WO2018122819A1 (en) Binocular image analysis-based asphalt road surface damage detection system
CN110161043A (en) A kind of subway tunnel structure synthetic detection vehicle
Protopapadakis et al. Autonomous robotic inspection in tunnels
CN108974044A (en) Railroad track assets survey system
KR102277633B1 (en) Automatic robot measuring system for transit tunnel safety inspection
US11120280B2 (en) Geometry-aware instance segmentation in stereo image capture processes
CN114373138A (en) Full-automatic unmanned aerial vehicle inspection method and system for high-speed railway
EP4079597A1 (en) Method for in-situ and real-time collection and processing of geometric parameters of railway lines
CN103837087B (en) Pantograph automatic testing method based on active shape model
CN109901623B (en) Method for planning inspection route of pier body of bridge
CN114113118B (en) Rapid detection device and detection method for subway tunnel lining crack leakage water disease
CN113050654A (en) Obstacle detection method, vehicle-mounted obstacle avoidance system and method for inspection robot
Cheng et al. Automatic detection of shield tunnel leakages based on terrestrial mobile LiDAR intensity images using deep learning
CN113503927A (en) Drainage pipeline detection robot with flight time module and detection method thereof
CN114241177A (en) Airport pavement apparent image detection system based on linear array scanning imaging
EP4063279B1 (en) Automated assessment of aircraft structure damage
CN116337102A (en) Unmanned environment sensing and navigation method based on digital twin technology
Kersten et al. Potentials of autonomous UAS and automated image analysis for structural health monitoring
Pan et al. Enhancement of external wall decoration material for the building in safety inspection method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination