Method, system, non-transitory computer-readable medium and computer program product for determining the occurrence of buckling in railway lines

Abstract

Method for determining the occurrence of a buckling event on at least one rail of a railway line, comprising: - collecting a track circuit waveform signal provided by a track circuit installed along a track section of the railway line; - comparing over time the collected track circuit waveform signal with a predicted waveform signal for the track section; - if at least a portion of the collected waveform signal differs from the predicted waveform signal by at least a predetermined threshold for a predetermined interval of time, then - determining that a buckling event has occurred on at least one rail of the track section.

Description

METHOD, SYSTEM, NON-TRANSITORY COMPUTER-READABLE MEDIUM AND COMPUTER PROGRAM PRODUCT FOR DETERMINING THE OCCURRENCE OF BUCKLING IN RAILWAY LINESBACKGROUND OF THE DISCLOSURE

[0001] The present disclosure relates in general to the field or railway systems, and more specifically to a method, a system, a non-transitory computer-readable medium and a computer program product for determining the occurrence of rail bucking events in railway lines, which are caused by compressive forces in the rails.

[0002] As known, over the last few decades, in order to improve the ride comfort for passengers and to reduce mechanical wear of some assets used, such as tracks, wheels, et cetera, railroads have shifted more and more from jointed rails to continuous welded rails.

[0003] However, while the use of continuous welded rails allows improving comfort for passengers and reducing the mechanical wear of some of the assets used, it makes the management of mechanical forces in the rails an increasingly important factor for the reliability and safety of railway lines.

[0004] These mechanical forces can be compressive forces (pushing) or tensile forces (pulling) and their onset in the rails is largely if not exclusively caused by the varying temperatures of the rails. In particular, compressive forces occur when temperatures are high and the steel of the rails tends to expand, while tensile forces occur when temperatures are low and the steel of the rails tends to contract.

[0005] Due to the fact that continuous welded rails lack of relief points through mechanical joints along their extension, when there is certain level of compressive force, rails can buckle causing the gauge of the track to be out of compliance, thus creating a dangerous situation which can potentially lead to a derailment of a passing train. If instead there is a certain level of tensile force, a rail can break and pull apart, also entailing potential risks for derailments of passing trains.

[0006] While broken rails can be detected using existing technologies, for example via track circuits which are installed along a railway and are capable of identifying that electric currents flowing through the rails are interrupted due to such conditions of the rails, the practical detection of buckled rails is still an open and unresolved issue.BRIEF DESCRIPTION OF THE INVENTION

[0007] Hence, there is the need for a solution capable of determining that a buckling event has occurred on at least one rail of a railway line.

[0008] The present disclosure is aimed at providing such a solution and, in one aspect, it provides a method for determining the occurrence of a buckling event on at least one rail of a railway line, the method comprising:- collecting a track circuit waveform signal provided by at least one track circuit installed along a track section of the railway line;- comparing over time the collected track circuit waveform signal with a predicted waveform signal for the track section;- if at least a portion of the collected waveform signal differs from the predicted waveform signal by at least a predetermined threshold for a predetermined interval of time, then- determining that a buckling event has occurred on at least one rail of the track section.

[0009] In another aspect, the present disclosure provides a control system for determining the occurrence of a buckling event on at least one rail of a railway line, the system comprising:- at least one track circuit installed along a rail section of the railway line, the track circuit comprising a transmitter adapted to transmit along at least one rail of the track section one or more electrical signals, and a receiver positioned spaced apart from the transmitter along the at least one rail and configured to receive the one or more electrical signals transmitted by the transmitter;- a controller comprised in the track circuit or in operative communication with the track circuit and configured to:- collect a track circuit waveform signal provided by the at least one track circuit;- compare over time the collected track circuit waveform signal with a predicted waveform signal for the rail section; and- if at least a portion of the collected waveform signal differs from the predicted waveform signal by at least a predetermined threshold for a predetermined interval of time, determine that a buckling event has occurred on at least one rail of the railway section.

[0010] In a further aspect, the present disclosure provides a non-transitory computer-readable medium comprising coded instructions stored therein which, when executed by a processor or processing circuitry, cause the processor or processing circuitry to execute or to initiate the execution of a method for determining the occurrence of a buckling event on at least one rail of a railway line, which comprises:- collecting a track circuit waveform signal provided by at least one track circuit installed along a track section of the railway line;- comparing over time the collected track circuit waveform signal with a predicted waveform signal for the track section;- if at least a portion of the collected waveform signal differs from the predicted waveform signal by at least a predetermined threshold for a predetermined interval of time, then- determining that a buckling event has occurred on at least one rail of the track section.

[0011] In yet a further aspect, the present disclosure provides a computer program product comprising program code for performing, when executed by a processor or processing circuitry, a method for determining the occurrence of a buckling event on at least one rail of a railway line, which comprises:- collecting a track circuit waveform signal provided by at least one track circuit installed along a track section of the railway line;- comparing over time the collected track circuit waveform signal with a predicted waveform signal for the track section;- if at least a portion of the collected waveform signal differs from the predicted waveform signal by at least a predetermined threshold for a predetermined interval of time, then- determining that a buckling event has occurred on at least one rail of the track section.BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Detailed characteristics and advantages will become apparent from the description of some preferred but not exclusive exemplary embodiments of a method, a system and software code according to the present disclosure, illustrated only by way of non-limitative examples with the accompanying drawings, wherein:FIG. 1 is a block diagram schematically illustrating an embodiment of a control system for determining that a bucking event occurred in at least one rail of a railway;FIG. 2 is a flowchart schematically illustrating a method for determining that a bucking event occurred in at least one rail of a railway line, according to the present disclosure;FIG. 3 is a graph showing patterns of forces acting on a rail and temperature of the rail over a period of time, and the pattern of a track circuit waveform elaborated according to the method and system of the present disclosure evidencing the occurrence of buckling events.DETAILED DESCRIPTION OF THE DISCLOSURE

[0013] It should be noted that in the detailed description that follows, identical or similar components, either from a structural and / or functional point of view, may have the same reference numerals, regardless of whether they are shown in different embodiments of the present disclosure. It should be also noted that in order to clearly and concisely describe the present disclosure, the drawings may not necessarily be to scale and certain features of the disclosure may be shown in somewhat schematic form.

[0014] Further, when the term "adapted" or "arranged" or "configured" or "shaped", is used herein while referring to any component as a whole, or to any part of a component, or to a combination of components, it has to be understood that it means and encompasses correspondingly either the structure, and / or configuration and / or form and / or positioning. In particular, for electronic and / or software means, each of the above listed terms means and encompasses electronic circuits or parts thereof, as well as stored, embedded or running software codes and / or routines, algorithms, or complete programs, suitably designed for achieving the technical result and / or the functional performances for which such means are devised. In addition, when the term “substantial” or “substantially” is used herein, it has to be understood as encompassing an actual variation of plus or minus 5% with respect to an indicated reference value, device or part thereof, time or position.

[0015] FIG. 1 and FIG. 2 illustrate a control system 100 and a method 200, respectively, for determining that a bucking event occurred in at least one rail of a railway line, according to possible exemplary embodiments of the present disclosure.

[0016] In particular, in FIG. 1 there is schematically illustrated only one track or rail section 1 of a railway line having a certain overall length, e.g. of some miles or kilometers. The track section 1 comprises a first rail 2 and a second rail 3, with the rails 2 and 3 running parallel to each other and forming a path along which railway vehicles can travel.

[0017] According to solutions well known in the art and therefore not described herein in details, the rail 2 is for example attached to the rail 3 through ties 6 which are laid in the ground and are substantially covered with ballast 7, i.e. small stones, to hold the ties in place. In FIG. 1 there is illustrated only one tie 6 and the ballast 7 has been represented only at a small area just for ease of illustration.

[0018] Clearly, the railway line comprises a plurality of track sections, laid one after the other along the extension of the railway line.

[0019] The control system 100 comprises one or more track circuits installed along the railway line.

[0020] As well known in the art, or in any case readily available to those skilled in the art, and therefore herein not described in details, track circuits are devices installed over railway lines and are primarily used to detect whether a train is present on a track section.They can be also used to detect broken rails within the track section, and / or to transmit signal aspect information through the rails, for example to communicate movement authorities of transiting trains. To this end, track circuits use electrical signals applied to the rails which are in electrical series with a signal transmitter and a signal receiver, usually positioned at respective ends of a given rail section. The signal transmitter applies a voltage, sometimes referred to as a transmit voltage, to the rails; as a result, a current signal, sometimes referred to as a transmit current, is transmitted through the rails. A portion of the transmit current, sometimes referred to as a receive current is detected by the receiver. When a train composed of one or multiple vehicles or railcars is located on the track section of the relevant track circuit, the wheels of the railcars act as a shunt between the rails and form a shunt path. The shunt path creates an electrical short between the rails at the location of the train, and such short path effectively prevents the receive current from being received / detected by the signal receiver.

[0021] In the exemplary embodiment of FIG. 1 there is illustrated one track circuit installed the track section 1 .

[0022] As schematically illustrated, such track circuit comprises a transmitter 1 10 which is coupled to the track section 1 , for example at or adjacent to a first end 4 of the track section, and a receiver 120 which is coupled to the track section 1 , for example at or adjacent to the second opposite end 5.

[0023] For example, the transmitter 110 is adapted to transmit along at least one rail of the track section one or more electrical signals, and the receiver 120, positioned spaced apart from the transmitter along the at least one rail, is configured to receive the one or more electrical signals transmitted by the transmitter 1 10.

[0024] In one possible aspect, the transmitter 110 comprises for instance an energy source 1 15 and is configured to apply a predefined transmit voltage to the track section 1 during operations. For example, the transmitter 110 may be configured to apply a voltage across the track section 1 at the end 4, thereby generating a transmit current. To this end, the transmitter 1 10 can be provided for example by suitable circuitry 1 16, adapted to generate different levels of coded voltages, e.g. DC voltages.

[0025] The receiver 120 comprises an energy source 125 and is configured to receive signal with a receive voltage and to detect a receive current during operations based on the applied transmit voltage.

[0026] In one embodiment, as illustrated in FIG. 1 , the transmitter 110 and the receiver 120 are in practice realized as substantially identical devices, and thus they can exchange their role, functioning one as transmitter and the other as receiver, and vice versa.

[0027] The system 100 further comprises a controller 101 which can be part of the track circuit or in operative communication with it.

[0028] For example, the controller 101 can be placed remotely from the transmitter 110 and the receiver 120, or it can be part of the receiver 120 or of the transmitter 1 10.

[0029] Measurements of currents and voltages can be carried out by the transmitter 110 and the receiver 120 themselves and then communicated to the controller 101 .

[0030] Alternatively, corresponding signals indicative of such current values and can be transmitted to the controller 101 which can perform the calculations and related measurements of the relevant values.

[0031] To this end, at least one of, preferably both the transmitter 110 and the receiver 120 comprise a respective communication module 11 1 and 121 in data communication to each other and with at least the controller 101 . Further, at least one of, preferably both, the transmitter 1 10 and the receiver 120 can comprise a data processor 117 and 127 respectively associated to a data storage unit, e.g. a memory 1 19 and 129, for storing therein for example measured or real time calculated data.

[0032] The controller 101 of the control system 100 according to the disclosure is configured to collect over time, a track circuit waveform signal provided by the at least one track circuit. The track circuit waveform signal originates from the one or more electrical signal(s) transmitted by the transmitter 110 and collected by the receiver 120.

[0033] The controller 101 is further configured to:- compare over time the collected track circuit waveform signal with a predicted waveform signal for the rail section 1 ; and- if at least a portion of the collected waveform signal differs from the predicted waveform signal by at least a predetermined threshold for a predetermined interval of time, determine that a buckling event has occurred on at least one rail 2, 3 of the rail section 1 .

[0034] In one possible embodiment, the controller is configured to collect the track circuit waveform signal provided by the at least one track circuit in real-time.

[0035] In one possible embodiment, the controller is configured to collect continuously over time the track circuit waveform signal provided by the at least one track circuit.

[0036] Hence, the track circuit waveform signal provided by the at least one track circuit can be collected continuously and in real time.

[0037] In one possible embodiment, the predetermined interval of time is selectively adjustable.

[0038] In one possible aspect, the controller is further configured to issue an alert signal for an operator when it is determined that a buckling event has occurred on at leastone rail 2, 3 of the rail section 1. In one possible embodiment, the alert signal may be automated by directly controlling a railway signal or communicating directly with an operator, e.g. a train operator, or train control systems.

[0039] In one possible aspect, the threshold is determined during a training phase, during which the controller is trained. During this one or more track circuit waveform signals, preferably a plurality of track circuit waveform signals, are collected under buckle-free conditions of the rail section 1 .

[0040] In particular, the controller 101 is provided with or is associated to one or more algorithm(s) that, during the training phase, is / are taught to determine the difference between changes of the waveform signal over the time that are expected and changes that are unexpected and usually rare, i.e. due to buckling events occurring on at least one of the rails

[0041] For example, expected changes are due to thermal heating or cooling of the rails and / or contamination / precipitation of the ballast that change the resistance of the ballast.

[0042] For example, in the training phase, different innovative Machine Learning and Al algorithms, such as Autoencoders (AE) and Long-Short Term Memory (LSTM) Neural Networks, but not limited to, can be used to look for these changes in the shapes and time transitions of track circuit data waveform signals for detecting a rail buckle. The algorithms are trained on the ‘good’ track circuit data, namely without presence of rail buckle events, for instance under different conditions.

[0043] In one possible embodiment, the controller 101 is configured to elaborate the predicted waveform signal based on the one or more track circuit waveform signals collected in the training phase.

[0044] In particular, during operations, the controller 101 is configured to compare over the time the collected track circuit waveform signal with the predicted waveform signal for the rail section 1 . For instance, the difference between data points of the currently collected waveform signal and expected data points along the predicted waveform signal is calculated as a reconstruction error between such data. In a buckle-free situation, the reconstruction error should be very small, if any at all, indicating that the algorithm(s) has / have seen similar data points before, thus no rail buckle events have occurred.

[0045] For instance, in FIG. 3, such points, representing output data from the algorithm(s) that appears “normal”, i.e. where no rail buckle has occurred and are below the detection threshold are indicated by the reference number 306 along the waveform 304 which represents the output of the rail buckle detection algorithm(s).

[0046] However, in the case of a rail buckle, the algorithm reports large differences between the current track circuit data and the data deriving from the training set(s). In such a case, if at least a portion of the collected waveform signal differs from the predicted waveform signal by at least a predetermined threshold for a predetermined interval of time.

[0047] For instance, such threshold is indicated in FIG. 3 by the line 303, and as above indicated the points 306 indicate that no buckling events have occurred.

[0048] Accordingly, when during the predetermined interval of time, a certain portion of the collected waveform signal differs from the predicted waveform signal for at least a predetermined threshold, i.e. there are a certain number of points which are positioned above the threshold 303, then the occurrence of a buckling event on at least one of the rail 2, 3 of the rail section 1 is determined.

[0049] In the example of FIG. 3, points of the waveform 304 indicating the occurrence of a buckling are those indicated by the reference number 307. However, sometimes there are some data points above the line of threshold 303, yet there is no determination of a buckling event since the discriminating criteria of at least a portion of the collected waveform signal differing from the predicted waveform signal of a predetermined threshold for a predetermined interval of time is not met (see reference number 308 in FIG. 3). Hence, such data points, despite exceeding the threshold 303, are considered, as outliers and therefore undesired alarms for buckling are prevented.

[0050] FIG. 3 also shows, for the sake of exemplary illustration, the patterns of the actual temperature 301 of the rail provided for example by a thermocouple, and of actual forces in the rail provided by a strain gauge 302. As evident, when there is a buckle event, also the pattern of the force exerted on the rail interested by the buckling events changes substantially (see reference 305), while during buckling free situations their pattern is substantially more regular.

[0051] As above indicated, FIG. 2 schematically illustrates a flow diagram of a method 200 for determining the occurrence of a buckling event on at least one rail of a railway line, which can be carried out for instance with the components of the system 100.

[0052] In particular, the method 200 comprises at least the following steps:210: collecting a track circuit waveform signal provided by at least one track circuit, e.g. the track circuit above described which includes the transmitter 110 and the receiver 120, installed along a track section 1 of the railway line;220: comparing over time the collected track circuit waveform signal with a predicted waveform signal for the track section 1 ;- if at least a portion of the collected waveform signal differs from the predicted waveform signal by at least a predetermined threshold for a predetermined interval of time,then (230) determining that a buckling event has occurred on at least one rail 2, 3 of the track section 1 . As above indicated, the predetermined interval of time can be selectively adjusted.

[0053] In one possible embodiment, in the step 210 the track circuit waveform signal provided by the at least one track circuit is collected in real-time.

[0054] In one possible embodiment, in the step 210 the track circuit waveform signal provided by the at least one track circuit is collected continuously over time.

[0055] Hence, in such step 210 the track circuit waveform signal provided by the at least one track circuit can be collected continuously and in real time.

[0056] In one possible embodiment, the method 200 comprises issuing (step 240) an alert signal for an operator when it is determined that a buckling event has occurred on at least one rail 2, 3 of the track section 1 . In yet another embodiment, the alerting step 240 may be automated by directly controlling a railway signal or communicating directly with an operator, e.g. a train operator, or train control systems.

[0057] In one possible embodiment, the method 200 comprises a pre-training step (205) where one or more track circuit waveform signals are collected under buckle-free conditions of the track section 1 .

[0058] In particular, in the method 200 according to the disclosure, the predicted waveform signal is elaborated based on the one or more track circuit waveform signals collected in the pre-training step 205.

[0059] Further, as those skilled in the art would appreciate and based on the foregoing description, the above described embodiments of the disclosure may be implemented using computer programming including computer software, firmware, hardware or any combination or subset thereof. Any such resulting program, having computer-readable code means, may be embodied or provided within one or more non-transitory computer-readable media, thereby making a computer program product, i.e., an article of manufacture, according to the discussed embodiments of the disclosure. The computer readable media may be, for example, but is not limited to, a fixed (hard) drive, diskette, optical disk, magnetic tape, semiconductor memory such as read-only memory (ROM), and / or any transmitting / receiving medium such as the Internet or other communication network or link. The article of manufacture containing the computer code may be made and / or used by executing the code directly from one medium, by copying the code from one medium to another medium, or by transmitting the code over a network. In practice, the devised code includes software instructions which, once executed by a processor or equivalent device, carry out and / or cause suitable machinery and / or equipment to carry out the various steps / substeps of a method 200 as described in the foregoing description.

[0060] Hence, it is evident that the control system 100 and method 200, as well as the related computer program product and non-transitory computer-readable medium comprising software code stored therein, according to the present disclosure, provide a novel and cost effective solution for effectively determining the occurrence of buckling events.

[0061] The method 200, system 100, computer program product and non-transitory computer-readable medium thus conceived are susceptible of modifications and variations, all of which are within the scope of the inventive concept as defined in particular by the appended claims. For example, what described in connection with the track or rail section 1 can be replicated for all track sections of the railway line, and there can be one controller 101 for each rail section or one controller can be associated to more than one rail section. The or each controller 101 can comprise or be constituted by any processor-based device, e.g. a microprocessor, microcontroller, a microcomputer, a programmable logic controller, an application specific integrated circuit, or any other programmable circuit, schematically indicated in FIG. 1 by the reference number 102. Therefore, the term processor, as used herein, is not limited to just those integrated circuits referred to in the art as computers, but broadly refers to microprocessors, microcontrollers, microcomputers, programmable logic controllers, application specific integrated circuits, and other programmable circuits, and these terms are used interchangeably herein. Further, the controller 101 can comprise a storage unit or repository 104, e. g. a memory, for storing data or algorithms therein, a communication module 106 for communicating outside, for example with the receiver 120 and / or the transmitter 110, an own source of energy 108. Some parts of the control system 100 and or of the controller 101 and / or of the transmitter 1 10 / receiver 120 may reside on the same electronic unit, or they can even be realized as subparts of a same component or circuit of an electronic unit, or they can be placed remotely from each other and in operative communication there between. All the details may furthermore be replaced with technically equivalent elements.

Claims

CLAIMS1 . A method for determining the occurrence of a buckling event on at least one rail of a railway line, the method comprising:- collecting a track circuit waveform signal provided by at least one track circuit installed along a track section of the railway line;- comparing over time the collected track circuit waveform signal with a predicted waveform signal for the track section;- if at least a portion of the collected waveform signal differs from the predicted waveform signal by at least a predetermined threshold for a predetermined interval of time, then- determining that a buckling event has occurred on at least one rail of the track section.

2. The method according to claim 1 , comprising issuing an alert signal for an operator when it is determined that a buckling event has occurred on at least one rail of the railway section.

3. The method according to any one of claim 1 or 2, wherein it comprises a pre-training where one or more track circuit waveform signals are collected under buckle-free conditions of the rail section.

4. The method according to claim 3, wherein the predicted waveform signal is elaborated based on the one or more track circuit waveform signals collected in the pre-training phase.

5. The method according to any one of the previous claim, wherein said predetermined interval of time is selectively adjustable.

6. The method according to any one of the previous claim, wherein said track circuit waveform signal is collected in real time.

7. The method according to any one of the previous claim, wherein said track circuit waveform signal is collected continuously.

8. A control system for determining the occurrence of a buckling event on at least one rail of a railway line, the system comprising:- at least one track circuit installed along a rail section of the railway line, the track circuit comprising a transmitter adapted to transmit along at least one rail of the track section one or more electrical signals, and a receiver positioned spaced apart from the transmitter along the at least one rail and configured to receive the one or more electrical signals transmitted by the transmitter;- a controller comprised in the track circuit or in operative communication with the track circuit and configured to:- collect a track circuit waveform signal provided by the at least one track circuit;- compare over time the collected track circuit waveform signal with a predicted waveform signal for the rail section; and- if at least a portion of the collected waveform signal differs from the predicted waveform signal by at least a predetermined threshold for a predetermined interval of time, determine that a buckling event has occurred on at least one rail of the railway section.

9. The control system of claim 8, wherein the controller is configured to issue an alert signal for an operator when it is determined that a buckling event has occurred on at least one rail of the railway section.

10. The control system of any one of claims 8 and 9, wherein the controller is pre-trained during a training phase where one or more track circuit waveform signals are collected under buckle-free conditions of the rail section.1 1. The control system of claim 10, wherein the controller is configured to elaborate the predicted waveform signal based on the one or more track circuit waveform signals collected in the training phase.

12. The control system of any one of claims 8 to 1 1 , wherein the controller is configured to collect in real-time said track circuit waveform signal provided by the at least one track circuit.

13. The control system of any one of claims 8 to 12, wherein the controller is configured to collect continuously said track circuit waveform signal provided by the at least one track circuit.

14. A non-transitory computer-readable medium comprising coded instructions stored therein which, when executed by a processor or processing circuitry, cause the processor or processing circuitry to execute or to initiate the execution of a method for determining the occurrence of a buckling event on at least one rail of a railway line of any of claims 1 to 7.

15. A computer program product comprising program code for performing, when executed by a processor or processing circuitry, the method of any of claims 1 to 7.

Images