Vehicle-mounted track detection system

Abstract

The invention provides a vehicle-mounted track detection system, which comprises a vehicle bottom detection beam, an in-vehicle detection host and a remote control terminal, and is characterized in that the vehicle bottom detection beam is arranged at the compartment bottom of a target train and is used for acquiring train track data including image data and non-image data; the system comprises a sensor unit, a pre-processing unit, a data exchange unit and a power conversion module. The in-train detection host is arranged in a carriage of the target train and comprises a rail detection host, a switch and a fusion algorithm host; and the remote control terminal comprises human-computer interface software. The train bottom detection beam is arranged at the bottom of the train compartment, the collected train track data is processed by the in-train detection host, the accuracy of track detection is improved through image data, and the accuracy of track geometric parameter calculation under the variable speed condition is guaranteed.

Description

Technical Field

[0001] The present application relates to the field of track detection technology, and in particular to a vehicle-mounted track detection system. Background Art

[0002] As one of the main components of the vehicle-mounted network track and tunnel inspection system, the vehicle-mounted track inspection system is mainly responsible for the structural health inspection and abnormal situation investigation of infrastructure such as the roadbed, drainage ditches, and rails under the vehicle.

[0003] At present, the traditional vehicle-mounted track detection system includes track geometry parameter detection system, acceleration measurement system and wheel-rail force measurement system in terms of functions. The main principle is to collect signal detection data by adding sensors, so as to calculate and evaluate the detection items. However, the status of the track is not only for signal detection, but also for image visualization detection. Summary of the invention

[0004] In view of this, an embodiment of the present application provides a vehicle-mounted track detection system to solve the technical defects existing in the prior art.

[0005] According to a first aspect of an embodiment of the present application, a vehicle-mounted track detection system is provided, comprising a vehicle bottom detection beam, an in-vehicle detection host, and a remote control terminal, wherein: The vehicle bottom detection beam is arranged at the bottom of the carriage of the target train, and is used to collect train track data including image data and non-image data, and includes a sensor unit, a pre-processing unit, a data exchange unit, and a power conversion module; The in-vehicle detection host is arranged in the carriage of the target train, and includes a track inspection host, a switch, and a fusion algorithm host; The remote control terminal includes human-machine interface software.

[0006] Optionally, the sensor unit includes a fiber optic inertial navigation sensor, a tilt sensor, a rail surface 2D camera, and a 3D camera for identifying abnormalities of track bed fasteners, wherein: The optical fiber inertial navigation sensor collects train operation data, wherein the train operation data includes vibration data and deflection data generated during the train operation; The inclination sensor collects train inclination data; The rail surface 2D camera collects rail profile image data; The roadbed fastener anomaly recognition 3D camera collects track three-dimensional image data, and the train operation data, the train inclination data, the track profile image data and the track three-dimensional image data constitute the train track data.

[0007] Optionally, the pre-processing unit includes an MCU controller, an inspection camera controller, and an AD data acquisition conversion module, wherein: The MCU controller triggers the rail surface 2D camera to collect data; The inspection camera controller triggers the track bed fastener abnormality recognition 3D camera to collect data.

[0008] Optionally, the track inspection host reads the train operation data, the train inclination data and the track profile image data collected by the sensor unit in the vehicle bottom detection beam, and sends the reading result to the fusion algorithm host.

[0009] Optionally, the fusion algorithm host determines the train angular velocity data based on the train operation data and through the Sagnac principle, determines the train spatial coordinate change data by combining the train angular velocity data with the train inclination data, and determines the track geometry parameter data based on the train spatial coordinate change data.

[0010] Optionally, the fusion algorithm host performs track surface positioning based on the track profile image data, and performs damage identification according to the positioning result to obtain track damage data.

[0011] Optionally, the fusion algorithm host reads the track three-dimensional image data.

[0012] Optionally, the fusion algorithm host locates the fastener area based on the track three-dimensional image data, and performs abnormality identification according to the positioning result to obtain fastener area abnormality data.

[0013] The present application provides a vehicle-mounted track detection system, including a vehicle bottom detection beam, an in-vehicle detection host, and a remote control terminal, wherein the vehicle bottom detection beam is arranged at the bottom of the target train compartment, and is used to collect train track data including image data and non-image data, and includes a sensor unit, a pre-processing unit, a data exchange unit, and a power conversion module; the in-vehicle detection host is arranged in the compartment of the target train, and includes a track detection host, a switch, and a fusion algorithm host; the remote control terminal includes a human-machine interface software. Compared with the traditional track detection system, by adding cameras to complete the track detection function items, image-based visual detection is incorporated into the track detection, so that the comprehensiveness of the undercarriage beam detection is improved, and the detection accuracy is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0015] Figure 1 It is a structural schematic diagram of a vehicle-mounted track detection system provided in one embodiment of the present application; Figure 2 It is a structural block diagram of a vehicle-mounted track detection system provided by an embodiment of the present application; Figure 3 This is a network topology diagram of a vehicle-mounted track detection system provided in one embodiment of the present application. DETAILED DESCRIPTION

[0016] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0017] The terms used in one or more embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present application. The singular forms of "a", "said" and "the" used in one or more embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of the present application refers to and includes any or all possible combinations of one or more associated listed items.

[0018] It should be understood that, although the terms first, second, etc. may be used to describe various information in one or more embodiments of the present application, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0019] In the present application, a vehicle-mounted track detection system is provided. Figure 1 The structure diagram of a vehicle-mounted track detection system provided according to an embodiment of the present application is shown, which specifically includes a vehicle bottom detection beam, an in-vehicle detection host and a remote control terminal, wherein: The vehicle bottom detection beam is arranged at the bottom of the carriage of the target train, and is used to collect train track data including image data and non-image data, and includes a sensor unit, a pre-processing unit, a data exchange unit, and a power conversion module; The in-vehicle detection host is arranged in the carriage of the target train, and includes a track inspection host, a switch, and a fusion algorithm host; The remote control terminal includes human-machine interface software.

[0020] Specifically, the target train can be understood as a train that is installed with a vehicle-mounted track detection system in order to detect the track; the undercarriage detection beam is arranged on the bottom side of the outside of the target train's carriage. Since it needs to collect train track data in the form of image data, it is arranged outside the carriage to facilitate image acquisition by related cameras; in the undercarriage detection beam, the sensor unit is used for data acquisition, the pre-processing unit is used to provide trigger signals for each sensor in the sensor unit, the data exchange unit is used for convergence and conversion of data transmission channels, and the power conversion unit is used to provide a power source for the target train that is converted into the power source required by each device.

[0021] In addition, in order to ensure the stability of the vehicle-mounted track detection system, in addition to the necessity of installing the underbody detection beam outside the car, the on-board detection host needs to be arranged in the car of the target train; the track inspection host and algorithm fusion host included in the on-board detection host receive the data collected by the underbody detection beam, and further perform data analysis and processing. The processing results are sent to the remote control terminal through the switch. The human-machine interface software contained in the remote control terminal displays the data processing results. Users can operate the human-machine interface components according to their needs to realize the call, viewing, and sending of relevant data.

[0022] It should be noted that the remote control terminal can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.) or other types of mobile devices, or a stationary computing device such as a desktop computer or a PC. The remote control terminal can also be a mobile or stationary server.

[0023] The components of the remote control terminal include, but are not limited to, a memory and a processor; the processor is connected to the memory through a bus, and data is stored through the database of the remote control terminal; the remote control terminal also includes an access device, which enables the remote control terminal to communicate via one or more networks. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device may include one or more of any type of network interface (e.g., a network interface card (NIC)) of wired or wireless, such as an IEEE802.11 wireless local area network (WLAN) wireless interface, a global interconnection for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0024] In one embodiment of the present application, the above components of the remote control terminal and other components not shown may also be connected to each other, for example, through a bus. It should be understood that those skilled in the art may add or replace other components as needed.

[0025] For example, in actual use scenarios, the vehicle-mounted track detection system can be arranged as follows: Figure 2 As shown in the structural block diagram of a vehicle-mounted track detection system provided, the vehicle bottom detection beam crossbeam includes a sensor, a front unit, a data conversion and a power conversion, that is, the vehicle bottom detection beam includes a sensor unit, a front processing unit, a data conversion unit and a power conversion module.

[0026] The in-vehicle detection host includes a host computer module, which includes a track inspection host, an algorithm host, and a switch. It should be noted that the algorithm host is a fusion algorithm host. In addition, a patrol host can be arranged to receive data collected by the patrol camera in the sensor unit and perform analysis and processing.

[0027] Specifically, the power conversion module is used to convert the vehicle's DC 110V power supply into the power required by various devices, including 24V, 5V, etc. The DC24V switching power supply supplies power to the PCB control board, which manages the power supply and short-circuit protection of all loads under the vehicle. It also has an input interface anti-reverse connection function, and each 24V power output is designed with a fuse, which can be controlled by the MCU to delay opening, realize the system step-by-step power-on function, avoid excessive impact of simultaneous power-on, and realize independent power-off and restart of each device.

[0028] The data exchange unit is used for the aggregation and conversion of data transmission channels; it provides Ethernet data exchange and aggregation transmission capabilities, 485 / 232 serial data conversion, etc.

[0029] Furthermore, the sensor unit includes a fiber optic inertial navigation sensor, an inclination sensor, a 2D camera on the rail surface, and a 3D camera for identifying abnormalities in roadbed fasteners, wherein the fiber optic inertial navigation sensor collects train operation data, wherein the train operation data includes vibration data and deflection data generated during the train operation; the inclination sensor collects train inclination data; the 2D camera on the rail surface collects track profile image data; the 3D camera for identifying abnormalities in roadbed fasteners collects track three-dimensional image data, and the train operation data, the train inclination data, the track profile image data and the track three-dimensional image data constitute the train track data.

[0030] In actual usage scenarios, such as Figure 2 As shown in the structural block diagram of a vehicle-mounted track detection system provided, the rail profile camera is a 2D camera on the rail surface, the inspection camera is a 3D camera for identifying abnormalities of the ballast fasteners, and the sensor unit includes not only the fiber optic inertial navigation, the inclination sensor, the rail profile camera, and the inspection camera, but also an RFID reader. The data collected by the 2D camera on the rail surface can be used for the calculation of track geometry parameters, the calculation of the corrugation overrun ratio, and the identification of rail surface defects. Specifically, the image recognition technology can be used to identify rail surface defects such as peeling, scratches, abrasions, and fatigue cracks; the 3D camera for identifying abnormalities of the ballast fasteners can take three-dimensional track images for defect diagnosis, that is, the image detection technology is used to identify foreign objects and looseness in the fastener area.

[0031] Furthermore, the front-end processing unit includes an MCU controller, an inspection camera controller, and an AD data acquisition conversion module, wherein the MCU controller triggers the rail surface 2D camera to collect data; the inspection camera controller triggers the track bed fastener abnormality recognition 3D camera to collect data.

[0032] In actual usage scenarios, such as Figure 2 As shown in the structural block diagram of a vehicle-mounted track detection system provided, the MCU controller is used to control the power on and off of each unit module, provide accurate trigger signals to each acquisition sensor, and provide an external interface for the host computer to issue instructions and operations; since there are multiple different power sensors under the vehicle, the MCU can isolate and filter the external speed signal (encoder) and input it to the single-chip microcomputer, which is divided into three isolated outputs after frequency division by the single-chip microcomputer software. The frequency division coefficient of each channel can be set separately, and the working status indication is fed back in real time. It has a highly integrated wiring harness, which saves installation space under the vehicle. It also has anti-reverse connection and surge protection functions to protect the normal operation of the connected equipment under the vehicle and ensure the stable operation of each functional module.

[0033] Furthermore, the track inspection host reads the train operation data, the train inclination data and the track profile image data collected by the sensor unit in the vehicle bottom detection beam, and sends the reading result to the fusion algorithm host.

[0034] Furthermore, the fusion algorithm host determines the train angular velocity data based on the train operation data and the Sagnac principle, determines the train spatial coordinate change data by combining the train angular velocity data with the train inclination data, and determines the track geometry parameter data based on the train spatial coordinate change data.

[0035] Among them, Figure 2 As shown in the structural block diagram of a vehicle-mounted track detection system provided, the track inspection host integrates inertial navigation data acquisition, rail surface image acquisition, etc., and receives data collected by other sensors in the sensor unit except the inspection camera. Specifically, the data of the rail profile camera, serial port server and switch are transmitted through Ethernet, and the analyzed and processed data are transmitted to the fusion algorithm host, that is, the algorithm host, through Ethernet.

[0036] The fusion algorithm host involves abnormal identification and detection of rail surfaces and fastener areas, so it has high requirements for computing power. By using AI acceleration computing cards and independent signal processing acceleration boards to improve computing power, it can achieve high-load performance, improve signal parallel computing processing capabilities, collect vehicle speed signals, and send synchronous trigger signals to subsystems.

[0037] Furthermore, the fusion algorithm host performs track surface positioning based on the track profile image data, and performs damage identification according to the positioning result to obtain track damage data.

[0038] Furthermore, the fusion algorithm host reads the track three-dimensional image data.

[0039] Furthermore, the fusion algorithm host locates the fastener area based on the track three-dimensional image data, and performs abnormality identification according to the positioning result to obtain fastener area abnormality data.

[0040] Among them, Figure 3 As shown in the network topology diagram of a vehicle-mounted track inspection system provided, the 3D camera, i.e. the abnormal identification 3D camera of the track bed fastener, directly transmits the collected data to the fusion algorithm host for analysis and processing via Ethernet. The 2D and 3D cameras are connected to different hosts, which speeds up data storage and algorithm processing and avoids the loss of images due to bandwidth and hard disk storage speed limitations.

[0041] In addition, it should be noted that for the rail surface 2D camera and the ballast fastener anomaly recognition 3D camera, the number of related sub-cameras may not be one, as shown in the following example: Figure 3 As shown, left / right profile cameras and left / right 3D cameras may be arranged. Figure 2 As shown in the structural block diagram of a vehicle-mounted track detection system provided, the data transmission of the fiber optic inertial navigation, RFID reader / writer, and PCB control board is transmitted to the serial port server through RS-485 and RS-232 buses, and the serial port server transmits the data to the track inspection host through Ethernet, which has the characteristics of less wiring and reduced interface usage; and the data transmission interface can be expanded through a switch to avoid the need to wire from the bottom of the vehicle to the inside of the vehicle again when adding subsequent equipment.

[0042] It should be noted that in actual usage scenarios, there are situations where the speed of the target train is fast and changing. There are certain errors in calculating the track geometry parameters by means of integral displacement. In order to meet and optimize the detection accuracy requirements of the height and track direction under low-speed conditions, that is, braking deceleration and starting acceleration stages, the trajectory method based on the inertial principle is integrated and the speed change is comprehensively considered; specifically, by using inertial components (inertial navigation) and the Sagnac principle to detect the angular velocity of the on-board track detection system during movement, the deflection angle is obtained by integration, and the spatial coordinate change relative to the measurement point is calculated by combining the train inclination data. The formula is used to solve and obtain the track direction and height and height values, thereby calculating the track direction and height irregularity data of any wavelength of the line.

[0043] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0044] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0045] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0046] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A vehicle-mounted track detection system, characterized in that: It includes the vehicle bottom detection beam, the vehicle interior detection host and the remote control terminal, among which: The vehicle bottom detection beam is arranged at the bottom of the carriage of the target train, and is used to collect train track data including image data and non-image data, and includes a sensor unit, a pre-processing unit, a data exchange unit, and a power conversion module; The in-vehicle detection host is arranged in the carriage of the target train, and includes a track inspection host, a switch, and a fusion algorithm host; The remote control terminal includes human-machine interface software.

2. The system according to claim 1, characterized in that The sensor unit includes a fiber optic inertial navigation sensor, an inclination sensor, a rail surface 2D camera, and a 3D camera for abnormal identification of track bed fasteners, wherein: The optical fiber inertial navigation sensor collects train operation data, wherein the train operation data includes vibration data and deflection data generated during the train operation; The inclination sensor collects train inclination data; The rail surface 2D camera collects rail profile image data; The roadbed fastener anomaly recognition 3D camera collects track three-dimensional image data, and the train operation data, the train inclination data, the track profile image data and the track three-dimensional image data constitute the train track data.

3. The system according to claim 2, characterized in that The pre-processing unit includes an MCU controller, an inspection camera controller, and an AD data acquisition conversion module, wherein: The MCU controller triggers the rail surface 2D camera to collect data; The inspection camera controller triggers the track bed fastener abnormality recognition 3D camera to collect data.

4. The system according to claim 2, characterized in that The track inspection host reads the train operation data, the train inclination data and the track profile image data collected by the sensor unit in the vehicle bottom detection beam, and sends the reading result to the fusion algorithm host.

5. The system according to claim 4, characterized in that The fusion algorithm host determines the train angular velocity data based on the train operation data and the Sagnac principle, determines the train spatial coordinate change data by combining the train angular velocity data with the train inclination data, and determines the track geometry parameter data based on the train spatial coordinate change data.

6. The system according to claim 4, characterized in that The fusion algorithm host performs track surface positioning based on the track profile image data, and performs damage identification according to the positioning result to obtain track damage data.

7. The system according to claim 2, characterized in that The fusion algorithm host reads the track three-dimensional image data.

8. The system according to claim 7, characterized in that The fusion algorithm host locates the fastener area based on the track three-dimensional image data, and performs abnormality identification according to the positioning result to obtain fastener area abnormality data.

Images