The present disclosure generally relates to automated detection of railroad track features. Images of a railroad track are captured and analyzed to identify track features such as anchors, spikes, rail ties, tie plates, and joints. Various image processing techniques are utilized to accurately distinguish between track features and other objects in the captured images. Track features identified in the images are assigned identifiers and locations and stored in a database so that a status and/or condition of the track features may be monitored for maintenance purposes.

The invention relates to a method for monitoring the physical state of a longitudinal element (IO) of a railway-type rail, the method having a step of detecting mechanical waves moving along the longitudinal element (IO), in particular due to the passing of a train, by means of an array of mechanical wave sensors placed along and in contact with the longitudinal element, the array having at least one first pair (A) of sensors each positioned at one end of a first portion (IOa) of the longitudinal element (IO), and a step of processing the signals emitted by the sensors in the array of sensors, the processing step having the determination of at least one first interfered signal determined from signals provided by the sensors in the first pair (A) of sensors over a first predetermined period of time.

The present application provides a simulation method for equivalent fatigue damage of wheel-rail steel, and relates to the study of wheel-rail relationship of rail transportation. After obtaining the train load spectrum when the target train serves for the preset mileage, the wheel-rail systematic 3D model corresponding to the target train is assigned to simulate the load according to the train load spectrum to obtain the stress spectrum of the dangerous part of the rim, and determine the target stress and stress application frequency corresponding to the expected simulated mileage according to the stress spectrum of the dangerous part of the rim. Then, the driving fatigue test machine carries out fatigue tests on the wheel-rail steel fatigue sample of the target train according to the target stress and stress application frequency, and obtains the equivalent fatigue damage data of the wheel-rail steel at the expected simulated mileage of the target train.

A system and method for inspecting a railway track using sensors oriented at an oblique angle relative to a rail vehicle on which the system is traveling. The orientation of the sensors allows for different data to be gathered regarding a particular rail including rail design specifications (gathered based on manufacturer markings detected and analyzed by the system), rail seat abrasion values based on direct measurement of rails from the oblique angle, and other analysis of rail features including joint bars, rail welds, bond wires, rail holes, and broken rails. The use of an air blower, ducts, and one or more air distribution lids over the sensors helps remove debris from blocking the sensors and structured light generators.

The present disclosure discloses a rail corrugation recognition method and apparatus based on a support vector machine, a device, and a medium. The method includes: obtaining wheel-rail noise signals in different time periods, and obtaining wheel-rail noise time domain information; dividing the wheel-rail noise time domain information into segmented wheel-rail noise time domain information corresponding to each of the different time periods; preprocessing each piece of segmented wheel-rail noise time domain information, and extracting a time domain statistical characteristic quantity and frequency domain eigenmode energy of each piece of segmented wheel-rail noise time domain information, to obtain a multi-dimensional wheel-rail noise characteristic vector; constructing a rail corrugation state recognition model based on a support vector machine, and training the rail corrugation state recognition model; and recognizing to-be-recognized wheel-rail noise data by using the rail corrugation state recognition model based on a support vector machine, to obtain a rail corrugation state.

Provided is a rail head abrader including a base, a blade, a vertical measurement section and a horizontal measurement section; an upper end surface of the base is arranged horizontally and a base bevel edge intersects a base vertical edge; the blade is disposed on the base and perpendicular to the upper end surface of the base, an upper portion of the blade is provided with vertical wear rail type selection lines; the vertical measurement section includes a vertical scale frame, a vertical digital display device, and a vertical scale cursor; the horizontal measurement section includes a horizontal scale frame, a horizontal measuring rod, measuring rod rail type selection lines, a horizontal digital display device, and a horizontal scale frame cursor, and a horizontal scale frame cursor locating line corresponding to the side wear rail type selection lines; the horizontal measuring rod is slidably mounted on the horizontal scale frame.

Method and a device for detecting defects in an elongated structure able to act as an elastic-wave waveguide, the elongated structure being fitted with a plurality of transducers able to acquire measurement signals of characteristic quantities of elastic waves propagating in the elongated structure, each transducer being coupled to an electronic device, the set of electronic devices constituting a network of nodes configured to process measurement signals received from at least one transducer. The method is computer-implemented and comprises steps of: performing a plurality of local defect diagnoses, based on measurement signals received by a plurality of electronic devices, the measurement signals being acquired for multiple elastic wave emission phases; transmitting, to a remote server in accordance with a low-energy-consumption communication protocol, messages containing information relating to each local diagnosis, the messages being formatted in accordance with the low-energy-consumption communication protocol; aggregating the information contained in the received messages; and performing a global defect diagnosis for determining the presence or absence of a defect in the elongated structure.

A system for modeling risk of rail buckling in railroad infrastructure is presented. The system can receive a myriad of data related to railroad tracks and/or railroad operations, and weight the data using specially-designed weighting factors that can be unique to each data type. The weighted data can be transformed via specialized algorithms to generate location scores reflective of a risk isolated to a particular area. The system can further utilize additional specialized algorithms to elucidate how such isolated risk can be extrapolated from one location to another. The system can implement a multilayer approach, formulating one or more layers of risk models and aggregating such models into an overarching risk model that can more-accurately forecast risk of rail buckling in a railroad track.

A method for measuring wear of a rail (20) comprises detecting a first set of wheel signals (SW1) by a wheel sensor (21) mounted to the rail (20), determining a first average wheel signal (AV1) of the first set of wheel signals (SW1), detecting at least one second set of wheel signals (SW2) by the wheel sensor (21), where the second set of wheel signals (SW2) is detected after detecting the first set of wheel signals (SW1), determining a second average wheel signal (AV2) of the second set of wheel signals (SW2), and determining a difference signal (DIF) given by the difference between the second average wheel signal (AV2) and the first average wheel signal (AV1), wherein a wheel signal is detected when a wheel (22) of a rail vehicle passes the wheel sensor (21). Furthermore, an evaluation system (23) for measuring wear of a rail (20) is provided.

A system and method for monitoring a track and/or rail employs one or more distance measuring imagers mounted to a railcar and directed to image the track and/or rails wherein the images are geo-tagged with location data. Geo-tagged distance measurements are processed to determine at least track gauge and/or at least rail fastener integrity. The system and method may also determine other track and/or rail integrity issues including, e.g., rail profile, rail alignment, center point dip, cross level, rail cant, wheel wear, wheel integrity, rail wear, rail defects, and/or rail temperature. The system and method may also determine when inspection and/or maintenance of the track is indicated, and provide selected records of where and/or when such inspection and/or maintenance is indicated.