7648 results about "Trackway" patented technology

The invention discloses a railway track damage detection method, and belongs to the technical field of railway track detection. According to the method, an image acquisition module and an ultrasonic detection module are installed at the bottom of a track detection vehicle, the detection vehicle is controlled to run, and track top face and side face image sequences and ultrasonic reflection signals are acquired; preprocessing the image, and respectively inputting the image into a deep convolutional neural network model and a support vector machine classifier to obtain a crack identification result and a wear level; processing an ultrasonic reflection signal, and judging a layering defect; and finally fusing the data, marking a damage position and generating a structured detection report. According to the method, the problems of incomplete detection, low precision and the like in the existing railway track damage detection are solved, efficient detection of track surface cracks, side abrasion and internal layering defects is realized through collaborative acquisition of the multi-modal sensor, intelligent algorithm processing and data fusion, and the comprehensiveness and reliability of detection are improved.

The invention provides a railway line monitoring alarm method and system, and relates to the technical field of computers, and the method comprises the steps: continuously collecting a dynamic monitoring data set comprising a track structure vibration waveform sequence, a track surface optical image sequence and an environment meteorological parameter sequence through a plurality of sensor nodes of a target railway line; carrying out multi-modal feature fusion processing on the dynamic monitoring data set, generating a comprehensive state evaluation matrix containing a vibration energy distribution vector and the like, carrying out risk alarm grade classification on the comprehensive state evaluation matrix by utilizing a preset track safety evaluation model, and outputting an abnormal event type code and an abnormal region position code; then, a multi-stage linkage control instruction set containing a train emergency braking triggering instruction and the like is generated based on the multi-stage linkage control instruction set, the multi-stage linkage control instruction set is synchronously transmitted to a central dispatching system, the central dispatching system is driven to execute rail blocking, train speed regulation and control and equipment maintenance operation according to instruction priorities, and comprehensive and intelligent monitoring and efficient alarm response to railway lines are achieved.

The invention relates to the technical field of track structure health monitoring, in particular to a track crack recognition and fatigue life prediction method and system based on deep learning and finite elements, and the method comprises the steps: collecting and preprocessing a track surface crack image, and obtaining crack image data; a deep neural network model is trained, and a corresponding track crack recognition algorithm based on deep learning is determined; identifying and extracting positions and geometric dimensions of the cracks; based on the geometrical characteristics and the material attributes of the track, establishing a corresponding track finite element model, and inputting the position and the geometric size of the crack into the track finite element model to generate and obtain a track model containing crack damage; based on wheel-rail rolling contact fatigue finite element simulation, simulating the mechanical response of a track structure, determining the fatigue life of the track in combination with the stress-strain distribution of the track, and predicting the development trends of cracks under different operation conditions; automatic and efficient identification of track cracks is realized, and the accuracy of fatigue life evaluation is improved.

The invention discloses a high-precision defect detection system for a track inspection robot, which relates to the technical field of track inspection and comprises a multi-mode visual acquisition module, a time sequence synchronization module, a data fusion processing module and a defect identification output module, by adopting a multi-modal visual fusion detection technology, various modal visual technologies of visible light vision, infrared vision and ultraviolet vision are combined, fusion processing is carried out on all modal image data, visual defects such as cracks and abrasion on the surface of a track can be clearly recognized through visible light vision, and the visual performance of the track is improved. The infrared vision can detect temperature abnormity of a track component to find out potential poor contact and other problems, the ultraviolet vision can be used for detecting corona discharge and other phenomena, track information is comprehensively obtained, the accuracy and reliability of defect recognition are effectively improved, defects which are difficult to find in a single mode can be detected, and the detection efficiency is improved. And powerful support is provided for safe operation and maintenance of the track.

The invention discloses a circulating type gravity energy storage transportation system which comprises a master controller, an annular rail, a high-position storage yard and a low-position storage yard, a transportation train is composed of a plurality of carriages which are flexibly connected and arranged on the annular rail, a low-position running rail is arranged on the annular rail, the high-position running rail is provided with a linear loading and unloading section, and the low-position running rail is provided with a linear loading and unloading section. A plurality of grabbing parts are arranged on the high-position storage yard and the low-position storage yard and move back and forth between the loading and unloading section and the stacking area, and the hoisting device is electrically connected with the master controller. By means of the double-circulation design of train circulation operation and heavy block rapid loading and unloading, the core pain points that an existing gravity energy storage system is not coherent in operation and low in efficiency are effectively solved, and the energy storage efficiency is improved. And a reliable system solution is provided for realizing large-scale, high-efficiency and fast-response gravity energy storage commercialized application.

An intelligent fault-in-rail analysis method based on multimodal fusion learning. Ultrasonic analysis data of the rail and high-definition rail surface images taken by line scan cameras are exploited in combination to detect and display internal and surface faults of the rail through different renditions using multimodal data. Rail DEtection TRansformer (R-DETR) technology or a You Only Look Once (YOLO) inspection machine-learning algorithm are employed in a deep convolutional neural network to analyze B-scan and rail surface image data to recognize rail line faults. After obtaining expressive data through data enhancement by computer processing, faults are recognized and pinpointed using the deep convolutional neural network learning algorithm. Analysis results are corrected with expert systems. The disclosed automatic ultrasonic fault-in-rail inspection solves the problem of slow detection and difficulties in tracking faults in everyday routine maintenance while also protecting the safety of rail operation and maintenance personnel.

The invention provides a railway track periodical intelligent monitoring method based on the Internet of Things. The railway track periodical intelligent monitoring method comprises the steps that track geometric deformation data and track temperature distribution data are collected through sensing nodes deployed beside a track and on the track; extracting abnormal sections in the track geometric deformation data based on time window segmentation, and mapping the abnormal sections to a space grid of the track temperature distribution data to generate a deformation-temperature incidence matrix; calculating a track stress change gradient by combining the matrix and historical track temperature distribution data, and generating a track health degree evaluation index; and when the track health degree evaluation index meets a preset degradation condition, inputting the time sequence multi-source fusion data into a deep learning track state prediction module, and outputting a track failure risk level. According to the invention, the efficiency, accuracy and intelligent level of railway track monitoring can be improved, and the safety and reliability of railway transportation are guaranteed.

The invention relates to a railway bridge post-earthquake traffic safety probability evaluation method and device, which are applied to the technical field of traffic safety, and the method comprises the steps: obtaining an earthquake-induced damage value set of each component through a probability distribution function of different material parameters of a railway track-bridge system; the method comprises the following steps: acquiring a mapping relation between the earthquake-induced damage of a key component and track irregularity through a balance differential equation of a bridge and railway track structural mechanical model, and acquiring earthquake-induced track random irregularity samples of different components based on an earthquake-induced damage value set of each component and the mapping relation between the earthquake-induced damage of the key component and track irregularity; constructing a power spectrum of the track irregularity caused by vibration of different components; establishing a rapid prediction model of the driving performance indexes on the axle after the earthquake through the earthquake-induced track irregularity sample and the coupling dynamic response result; through a Monte Carlo method, based on the earthquake-induced track irregularity power spectrum and the rapid prediction model, the overrun probability and the confidence interval of the driving safety on the axle after the earthquake are rapidly and accurately obtained.

The invention discloses a track bridge health assessment method based on deep learning and multi-modal data fusion, and aims to overcome the technical defects of insufficient multi-source data collaboration and weak spatial-temporal characteristic coupling capability in the existing method. The spatial-temporal deep analysis of multi-modal data is realized by constructing a CNN-LSTM-DNN model. According to the technical scheme, the method comprises the following steps: 1) deploying acceleration, strain and temperature sensor clusters, and generating a space-time aligned heterogeneous data set through time synchronization, low-pass filtering and normalization processing; 2) extracting spatial topological features of a sensor network by using a CNN, and capturing a structure local deformation and load distribution mode; 3) analyzing a time sequence evolution rule of parameters such as bridge vibration and temperature change through LSTM, and establishing a long-term dependency relationship of dynamic load-environmental disturbance-structural response; 4) designing a weighted attention mechanism, fusing the spatial-temporal feature vector, and generating a comprehensive feature containing multi-physics coupling information, and 5) constructing a nonlinear mapping model based on DNN, outputting a comprehensive health index (CHI), and dividing damage levels.

The invention belongs to the technical field of track detection devices, and particularly relates to a contact rail, induction plate and track static geometric parameter comprehensive inspection tester and an inspection method.The contact rail, induction plate and track static geometric parameter comprehensive inspection tester comprises a walking frame, and a track inspection assembly, a contact rail measurement assembly and an induction plate measurement assembly are arranged on the walking frame; static geometric parameters, contact rail parameters and induction plate parameters of the track can be measured at the same time, the walking frame is pushed on the track, three different types of geometric parameters are continuously measured in the pushing process, the number of on-track measuring personnel is reduced, the labor intensity is reduced, and the working efficiency is improved. The contact rail measurement assembly and the induction plate measurement assembly in the comprehensive inspection tester are detachably assembled and can be selectively used according to field conditions, and the use mode is flexible. The comprehensive inspection tester is provided with the lower contact type contact rail measurement assembly and the upper contact type contact rail measurement assembly, and can adapt to measurement of geometric parameters of contact rails in different power supply modes.

The embodiment of the invention provides a multi-unmanned aerial vehicle cooperative surveying and mapping method and system for areas along a railway, and belongs to the technical field of railway surveying and mapping. The method comprises the steps that the unmanned aerial vehicle collects monitoring data in the flight process; the relative position and posture between the aircrafts are dynamically adjusted, and an observation configuration with variable baseline parameters is constructed; laser ranging modules carried by the unmanned aerial vehicles are controlled to execute synchronous ranging operation, and multiple sets of laser point cloud data covering the railway structure area are generated; performing coordinate registration and fusion on the collected laser point cloud data, and combining position information and attitude information of each unmanned aerial vehicle; and extracting geometric dimension parameters of the railway structure from the compensated three-dimensional model, and outputting the geometric dimension parameters as measurement results. According to the scheme, high-precision non-contact measurement of geometric dimension parameters such as the track gauge, the height difference and the roll angle of a railway track structure is achieved.

The invention provides a rail turnout foreign matter detection and type analysis method and system, and the method comprises the steps: arranging a first camera group at the front end of a train, recognizing the position of a turnout through a preset target detection model, and calibrating foreign matters in the turnout through a preset foreign matter detection model; shooting an image calibrated to the foreign matter in the turnout through a second camera group as a to-be-analyzed image; extracting a second boundary region rolled by a wheel on the foreign matter from the to-be-analyzed image through a preset wheel rolling track detection model, performing coarse classification on the foreign matter in the to-be-analyzed image to obtain a coarse classification result, and selecting a boundary detection strategy to identify the first boundary region according to the coarse classification result in the foreign matter image; and respectively extracting corresponding texture features in the first boundary region and the second boundary region through a deep learning network, performing one-to-one mapping on the extracted texture features to obtain a mapping relation group, performing analysis through the mapping relation group to obtain a feature change rate, and performing analysis through a multi-feature analysis strategy to obtain a specific foreign matter type.

The invention discloses a convergence method and device for a train safety envelope, and relates to the technical field of railway train driving. According to the scheme, for a train running on a railway line, an RBC can receive a train position report from a vehicle-mounted ATP according to a preset time period through train-ground wireless communication equipment and vehicle-mounted interaction, and after an interlocking device handles a route for the train and the train drives into the route, the RBC sends the train position report to the vehicle-mounted ATP, and the RBC receives the train position report from the vehicle-mounted ATP according to the preset time period. According to the data information in the train position report fed back at the moment, the last relevant transponder group of the train path can be determined, so that the train envelope is calculated according to the train position report and the rail section position determined by the last relevant transponder group, and the train path is determined. The train envelope on the railway line correspondingly occupies a certain number of track sections, so that the track section which is currently in an unlocking state is determined from the track sections according to section unlocking state information fed back by interlocking equipment, and the track section is used for converging the train envelope.

The invention discloses a rapid measurement method and system for geometric irregularity of a track in a turnout zone. The method comprises the steps that complete three-dimensional point cloud data of the surface of a railway turnout steel rail are obtained in real time through a multi-angle line structure laser scanner on a special detection vehicle body; accurate attitude and position data of the detected vehicle body in the measurement process are obtained in real time through an inertial navigation measurement unit and an odometer; obtaining a high-precision pose of a detected vehicle body through a robust dead reckoning method of an IMU (Inertial Measurement Unit) assisted by a speedometer dynamic lever arm value based on a variable wheel-rail contact point; constructing a turnout area three-dimensional point cloud model; extracting geometric irregularity key points of turnout steel rail point cloud from the turnout area three-dimensional point cloud model; calculating parameters of track gauge, horizontal and rail direction irregularity and unevenness; the special detection vehicle body can quickly and stably pass through a turnout area to complete continuous and accurate measurement of geometric irregularity of a track.

The invention relates to an expansion joint (10) for connecting regions of a rail-based grid storage system (50, 50′, 50″; 104, 104′, 104″), the expansion joint (10) comprising: —a first rail element (12) and a second rail element (11), the rail elements (12, 11) being elongate and configured to slide relative to one another in a longitudinal direction in a junction area where they overlap, —the expansion joint (10) having a profiled upper surface that defines one or more tracks (27′, 27″) for supporting container handling vehicles (200, 300, 400), the tracks (27′, 27″) extending from the first rail element (12) through the junction area to the second rail element (11), wherein in the junction area, each rail element (11, 12) provides a portion of the or each track (27′, 27″) of the profiled upper surface so that there is a transition extending along the expansion joint (10) from the first rail element (12) to the second rail element (10) for the or each track (27′, 27″). The invention further relates to an automated storage and retrieval system comprising said expansion joint (10) and a method of connecting regions (50, 50′, 50″; 104, 104′, 104″) of a rail-based grid storage system and / or delivery rail system using one or more of the expansion joints (10)

The invention relates to the field of intelligent operation and maintenance of a high-speed railway overhead line system, provides a machine learning-based optimization method and system for dropper arrangement of the high-speed railway overhead line system, and aims to solve the problems of insufficient pantograph-catenary coupling stability and relatively low abrasion uniformity of the overhead line system. The method comprises the steps that contact force space distribution characteristics of a pantograph and a contact net are collected, and contact force balance constraint conditions are generated; constructing a line parameter compensation mechanism by combining the track ultrahigh value, the vertical curve curvature and the elevation data of the suspension point acquired by the laser scanner, and outputting a compensation three-dimensional coordinate of the suspension point of the overhead line system; a programmable gate array is adopted to implement parallel acceleration on neural network weight calculation and space coordinate transformation, contact force constraint and compensation coordinates are iteratively processed, and dropper arrangement parameters are generated; based on the segmented tension value and the node offset compensation value, driving equipment to finish accurate adjustment and positioning installation of the dropper. According to the technical scheme provided by the invention, the pantograph-catenary coupling stability and the wear uniformity of the catenary are improved.

The invention relates to the field of rail transit equipment, and discloses a rail transit equipment multi-source sensing data real-time fault-tolerant decision-making system, which comprises a multi-source sensing module used for collecting rail environment and locomotive state data through a 3D laser radar, a binocular camera and a Beidou positioning terminal, including obstacle, turnout, signal lamp and locomotive position information; the data fusion processing module is used for carrying out preprocessing, redundancy check and feature extraction on the multi-source sensing data to generate a fusion sensing result; and the fault-tolerant decision module is used for judging the safety state of the track based on the fusion sensing result, triggering an alarm / braking instruction and executing self-checking logic when the sensor is abnormal. Through the combination of double groups of redundant sensors and a three-level progressive fault-tolerant strategy, closed-loop control from data acquisition to safety decision is formed, the system robustness under complex working conditions is remarkably improved, and an omnibearing safety protection barrier is constructed for rail transit equipment.

The invention relates to a railway bridge damage and driving performance mapping method and device and a storage medium, and is applied to the technical field of traffic safety, and the method comprises the steps: building a mapping relation between rail-bridge key component earthquake-induced damage and rail irregularity, and comprehensively considering the influence of rail-bridge system earthquake-induced damage on driving safety performance; a deep learning method is adopted, a deep learning model is trained through a component earthquake-induced damage numerical value of the rail-bridge system and a train-rail-bridge coupling dynamic response result, and then a quantitative mapping relation between structural earthquake-induced damage of the rail-bridge system and driving performance is established. Therefore, safety and stability indexes of driving on the railway bridge track after key components or parts of the railway bridge track are damaged due to earthquakes can be quickly and accurately provided.

The invention discloses a track board pavement fine adjustment trolley. Comprising a supporting frame body, a plate grabbing mechanism arranged on the supporting frame body, a plurality of fine adjustment claws arranged on the periphery of a track plate, a twisting mechanism arranged on the plate grabbing mechanism and used for adjusting the fine adjustment claws, a walking mechanism arranged at the bottom of the supporting frame body and a control box arranged on the side face of the supporting frame body. A control module is arranged in the control box; the fine adjusting claw comprises an adjuster base, a vertical adjusting screw rod, a transverse adjusting screw rod and a steering gear; the vertical adjusting screw rod is connected to the adjuster base and is perpendicular to the adjuster base, and the vertical adjusting screw rod moves up and down by rotating the vertical adjusting screw rod. The device is simple in structure and reasonable in design, grabbing, lifting, transverse moving, longitudinal moving and fine adjusting of the track plate are achieved, paving and fine adjusting work of the double-line track plate in the ballastless track can be rapidly completed, frequent manual intervention is not needed, manpower and material resources are saved, and the construction efficiency is improved.

The invention discloses a rail transit fastener model identification system and method, and relates to the technical field of fastener overhaul, an initial image of a rail is acquired through an image acquisition module, and an image preprocessing module is used for preprocessing to obtain a reference image; the image analysis module inputs the reference image into a preset model for processing, completes segmentation of the fastener assembly and the steel rail assembly, and obtains segmented images; the positioning module is used for screening the images of part of fastener assemblies and the images of the rail bottom of the steel rail and restoring the images to the reference images; the feature acquisition module is used for acquiring a reference adjustment line based on the segmented image of the rail bottom, acquiring feature parameters of the partial components based on the segmented images of the partial components, and correcting by using the reference adjustment line to obtain reference feature parameters; and the model identification module is used for matching the reference characteristic parameters of the screening component with the data in the constructed database and outputting a corresponding fastener model. According to the invention, efficient identification of the models of the fasteners can be realized, and the identification accuracy is also guaranteed.

Techniques for dividing a lane into a first virtual lane and a second virtual lane are described. A narrow track vehicle may determine that the narrow track vehicle is traversing a lane that is at least 10 feet wide. The narrow track vehicle may divide the lane into a first virtual lane and a second virtual lane and traverse one of the first virtual lane or the second virtual lane based at least in part on location (e.g., when traversing a highway lane, residential lane, etc.) and / or speed of traffic (e.g., when traffic is traveling at or below a threshold speed). In examples, the narrow track vehicle may traverse the environment in between a first lane and a second lane upon determining that a distance between a first object in the first lane and a second object in the second lane meets a threshold distance.

The invention provides a track board drilling parameter intelligent optimization method and system based on deep learning, and relates to the technical field of deep learning, and the method comprises the steps: recognizing a feature region in three-dimensional scanning data through a deep learning semantic segmentation network, building a local coordinate system, calculating hole site deviation, constructing a pose correction field, and achieving the intelligent correction of drilling process parameters. And an optimal drilling track is generated by using a state space search algorithm. The method can adapt to actual geometric errors of the track plate, the drilling precision and efficiency are improved, the drilling failure rate is reduced, and the manufacturing quality of the track plate is improved.

The invention relates to the technical field of target detection, and provides a track operator safety wearing detection method, device and equipment and a storage medium, and the method comprises the steps: collecting a video image of a track operation construction site, and inputting the video image into a pre-trained safety wearing detection model, detecting the safety wear of each operator in the video image to obtain a detection result of the safety wear of each operator; wherein the safe wearing detection model is constructed by taking a memory efficient visual converter with a cascade grouping attention mechanism as a backbone network of a real-time target detector model and taking an ADown downsampling layer as a downsampling layer of the real-time target detector model. Through the constructed safe wearing detection model, the detection efficiency and the detection effect of safe wearing of the operating personnel are improved, the requirements of real-time performance and accuracy of safe wearing condition detection of the operating personnel in a rail transit scene can be met, and the workload of safety patrol of management personnel is reduced.

Disclosed in the present invention are an image generation method, system and device for subway tunnel clearance, and a storage medium. The method comprises: a LiDAR collecting three-dimensional laser point cloud data along a railway, and an odometer collecting encoder data along the railway; determining current subway tunnel section point cloud data on the basis of a subway clearance detection project, the three-dimensional laser point cloud data and the encoder data; determining a clearance violation area on the basis of the current subway tunnel section point cloud data and clearance; optimizing intrinsic and extrinsic parameters of a camera on the basis of point cloud information corresponding to the clearance violation area, so as to obtain calibrated intrinsic and extrinsic parameters of the camera; and on the basis of the calibrated intrinsic and extrinsic parameters, generating a camera projection map from the current subway tunnel section point cloud data, and constructing an image of subway tunnel clearance on the basis of the camera projection map. The present invention realizes, on the basis of point cloud data and clearance, track clearance violation detection during a high-speed inspection process, thus facilitating inspection and viewing by means of constructing an image of subway tunnel clearance.

The invention relates to the technical field of positioning, in particular to a rail-mounted robot high-precision fusion positioning method and system. According to the method, the error compensation model of each track segment is constructed, dynamic correction is carried out in combination with real-time environment interference data, dynamic compensation can be carried out on pulse data generated by an incremental encoder in real time, accumulation of position errors is remarkably reduced, it is ensured that the position of the robot is more accurate, and the accuracy of the robot is improved. By fusing satellite positioning data, motion state data and pulse data after error compensation, the positioning precision of the orbital robot in each orbital segment is remarkably improved, and by monitoring the position deviation in real time and comparing the position deviation with a preset threshold value, the unqualified orbital segments can be repeatedly corrected according to needs, so that the accuracy of the orbital robot is improved. And the accuracy of the positioning result is ensured, so that the robot can adaptively optimize the positioning precision under different working scenes and environment changes, and the continuity of high-precision positioning is ensured.

Described herein is a lightweight, power-efficient edge computing system, called the Autonomous Power-efficient Track Inspection System (APTIS), designed specifically for railroad track component inspection, and methods for making same, using an edge-computing device equipped with a custom computer vision model for meticulous track inspection that employs advanced deep learning and AI technologies, enabling automated detection and evaluation of the condition of various track components in concert with built-in cameras for surveillance.

A system for guiding the movement of one or more load handling devices in operation includes: a) a first set of parallel tracks and a second set of parallel tracks, the first and second sets of parallel tracks sharing a common track, each track of the first and second set of parallel tracks providing a track surface; and b) a first load handling device and a second load handling device, each having a wheel assembly engaging with the track surface and with the track surface of the common track; wherein each track of the first and second sets of parallel tracks include only two guide surfaces extending from the track surface for guiding the first and second load handing devices along their respective first and second sets of parallel tracks.

An umbrella includes a vertical support having a track carried on an outer surface of the vertical support, the track extending longitudinally, and a canopy configured to switch between an open state and a closed state. The umbrella also includes a sliding collar coupled to the vertical support and configured to slidingly engage the vertical support to control an angle of the canopy with respect to the vertical support, a first arm coupled between the sliding collar and the canopy, and a second arm coupled between the vertical support and the first arm. The sliding collar has a housing defining a recess, an activation button slidingly received by the recess of the housing and switching between an extended state and a retracted state, and a locking device carried by the housing. The locking device is configured to pivot about the housing to selectively engage the track in the extended state.

The invention discloses a high-speed rail seamless track displacement real-time detection system based on Beidou navigation, and relates to the technical field of traffic engineering, a target locking module is used for receiving Beidou observation data by using a Beidou GNSS receiver, locking GNSS lock losing signals at various monitoring moments based on the Beidou observation data, and transmitting the locked GNSS lock losing signals to the target locking module; the GNSS lock losing signal comprises a GNSS interruption starting point, a signal lock losing time period and a corresponding track space position; the interruption compensation module is used for initializing a mapping vector according to a track state before a signal lock losing time period to form a track estimation sequence, and judging whether IMU drift tends to systematic deviation or not after modal residual verification; the reconstruction module is used for performing error compensation on track position points at all moments in a signal lock losing time period if the deviation tends to systematic deviation; and the identification module is used for carrying out feature extraction in a signal lock losing time period based on the reconstruction module, and delimiting a dominant source of the current displacement in a form of a spatial domain angle.

The invention discloses a railway track collaborative flaw detection method based on double mobile robots. An existing track flaw detection method cannot meet the railway track detection requirement. Equipment adopted by the collaborative flaw detection method comprises double-mobile-robot track flaw detection equipment, a data processing and analyzing terminal and a main control system, the double mobile robots are responsible for cooperatively performing flaw detection operation on a railway track; the main control system is used for uniformly planning and controlling collaborative operation of the double robots; the data transmission module is responsible for transmitting flaw detection data of the double robots to a processing center in real time for subsequent processing and analysis; and the data processing and analyzing terminal is used for processing and analyzing flaw detection data of the double robots and identifying defects on the railway track. According to the invention, comprehensive and meticulous detection of the railway track is realized, the flaw detection efficiency and accuracy are improved, and the maintenance cost and safety risk are reduced.