WO2023152699A1

WO2023152699A1 - Apparatus.and method for monitoring a railway, subway or tramway bogie

Info

Publication number: WO2023152699A1
Application number: PCT/IB2023/051208
Authority: WO
Inventors: Roberto Nappi
Original assignee: Hitachi Rail Sts S.P.A.
Priority date: 2022-02-11
Filing date: 2023-02-10
Publication date: 2023-08-17
Also published as: IT202200002591A1

Abstract

The invention relates to an apparatus (1) and a method for monitoring a railway, subway or tramway bogie (B) comprising a damper (D, WD, VD, YD, LD), wherein said method comprises a) an acquisition phase wherein at least one travel datum is acquired, which represents a quantity concerning at least one behaviour of said bogie (B) in a travelling condition, b) a processing phase, wherein at least one monitoring datum is determined, by means of a neural network and on the basis of said, at least one travel datum, at least one monitoring datum representing an operating state of said damper (D, WD, VD, YD, LD), c) a transmission phase, wherein a signal (SM), in which said at least one monitoring datum is encoded, is transmitted to a supervision computer (3).

Description

TITLE: "APPARATUS AND METHOD FOR MONITORING A RAILWAY, SUBWAY

OR TRAMWAY BOGIE"

DESCRIPTION:

The present invention relates to an apparatus and a method for monitoring a railway, subway or tramway bogie, in particular a bogie of a passenger or freight coach, preferably of the four- axle type.

As is known, railway, subway or tramway bogies are very complex, especially those used for railway coaches travelling on high-speed lines, because they are equipped with a suspension system composed of a plurality of dampers (preferably ten) that must always be fully operational in order to keep the mechanical stress caused by high-speed motion within the design limits. Due to the presence of such a high number of dampers in a railway bogie, the probability is high that some coaches of a train may have one or more malfunctioning dampers, and such defective coaches might easily cause an accident, e.g. derailment or detachment .

In order to prevent such malfunctions from occurring, bogies must be inspected in a workshop, where dynamic tests can be carried out with the utmost safety. Nevertheless, such an approach is unsatisfactory as far as fault prevention is concerned, because too much time often passes between inspections; as a matter of fact, faults are often detected in the workshop, or while the train is travelling (e.g. when the train drivers detect excessive coach vibrations), or after an accident, such as a derailment or a collision (e.g. against a mast of the overhead line) caused by a coach exceeding the loading gauge.

The present invention aims at solving these and other problems by providing an apparatus for monitoring a railway, subway or tramway bogie.

Furthermore, the present invention aims at solving these and other problems by providing also a method for monitoring a railway, subway or tramway bogie.

The basic idea of the present invention is to use a neural network for determining a monitoring datum which represents an operating state of a railway, subway or tramway bogie, in particular of dampers comprised in said railway bogie, wherein said neural network is trained in a manner such that, when inputting to said neural network at least one training datum representing at least one quantity concerning at.least one second behaviour of a second damper in an abnormal operating condition, said neural network will output a second monitoring datum indicating the occurrence of said abnormal operating condition, and wherein said at least one monitoring datum is transmitted to a supervision computer via transmission means. This makes it possible to determine the occurrence of abnormal operating conditions of the bogie as it is travelling, without having to move the bogie to the workshop. It will thus be possible to immediat.ely take the necessary steps (e.g. to detach a coach comprising a faulty bogie from the train) and/or to carry out preventive maintenance, so as to reduce the probability that faults or even accidents (e.g. a derailment, and/or a collision) might occur.

Further advantageous features of the present invention will be set out in the appended claims. These features as well as further advantages of the present invention will become more apparent in the light of the following description of a preferred embodiment thereof as shown in the annexed drawings, which are provided herein merely by way of non-limiting example, wherein: - Fig. 1 shows a railway bogie to which an apparatus for monitoring a railway, subway or tramway bogie according to the invention can be applied;

- Fig. 2 shows a railway, subway or tramway monitoring system comprising the apparatus for monitoring a railway, subway or tramway bogie according to the invention; - Fig. 3 shows a block diagram of the apparatus of Figure 2;

- Fig. 4 shows a flow chart of a method for monitoring a railway, subway or tramway bogie according to the invention.

In this description, any reference to "an embodiment" will indicate that a particular configuration, structure or feature is comprised in at least one embodiment of the invention. Therefore, expressions such as "in an embodiment" and the like, which may be found in different parts of this description, will not necessarily refer to the same embodiment. Moreover, any particular configuration, structure or feature may be combined as deemed appropriate in one or more embodiments. The references below are therefore used only for simplicity's sake, and shall not limit the protection scope or extension of the various embodiments.

With reference to Fig. 1, the following will describe a two- axle railway bogie B of the type which is used for travelling on high-speed lines; said bogie B comprises the following elements:

- a frame C supporting part of the weight of a coach (not shown in the drawing) and comprising a primary suspension system comprising elastic members (e.g. coil springs) and dampers (which will be further described below) capable of damping vibrations coming from the wheels while travelling, and a secondary system comprising elastic members, preferably mechanical ones (e.g. coil springs) or pneumatic ones (also known as "air springs") and dampers (which will be further described below) capable of damping oscillations (e.g. dangerous zigzagging) caused by forces acting upon the coach and due, for example, to dynamic effects (e.g. centrifugal forces) and/or aerodynamic effects (e.g. lift and/or downforce) and/or discontinuities and/or irregularities encountered along the line;

- four railway wheels W mounted to two distinct axles and attached to the frame C via the primary suspension system.

The primary suspension system comprises a wheel damper WD for each railway wheel W, wherein said wheel damper WD comprises a first portion integral with a rotation axle of said wheel W and a second portion integral with the frame C, and wherein said wheel damper WD is configured (e.g. through suitable orientation) in such a way as to damp any oscillations occurring along an axis parallel to a vertical axis Y and caused by irregularities encountered by the wheel W while the bogie B is travelling.

The secondary suspension system comprises the following elements: - a pair of vertical dampers VD, each one comprising a first portion constrained to the frame C and a second portion constrained to the coach (not shown), wherein said vertical damper VD is configured (e.g. through suitable orientation) in such a way as to damp any oscillations along the vertical axis Y or along an axis parallel to the vertical axis Y;

- a pair of yaw dampers YD (also known as "anti-zigzag dampers"), each one comprising a first portion constrained to the frame C and a second portion constrained to the coach (not shown), wherein said yaw damper YD is configured (e.g. through suitable orientation) in such a way as to damp any oscillations about the vertical axis Y or about an axis parallel to the vertical axis Y;

- at least one lateral damper LD, preferably two of them (also known as "horizontal dampers"), comprising a first portion constrained to the frame C and a second portion constrained to the coach (not shown), wherein said lateral damper LD is configured (e.g. through suitable orientation) in such a way as to damp any oscillations along a horizontal axis X (which is substantially parallel to the axis of rotation of the wheels W) or along an axis parallel to said horizontal axis X.

Also with reference to Fig. 2, the following will describe a system S for monitoring the bogie B, which can travel on a railway, subway or tramway network.

The system S preferably comprises the following elements: --- an apparatus 1 for monitoring said bogie B (e.g. an embedded device, an industrial PC, a development board, or the like), preferably positioned on a damper D, which may be either equal or similar to one of the dampers WD,VD,YD,LD described above)

— sensor means (which will be further described below) configured for detecting at least one travel datum which represents a quantity concerning at least one behaviour of said bogie B in a travelling condition, i.e. when the dampers WD,VD,YD,LD are being stressed;

- a supervision computer 3 (e.g. a remote physical server and/or a remote and/or "in-cloud" virtualized server) in communication with said apparatus 1 and configured for receiving a signal SM generated by said apparatus 1, and for notifying an operator when a monitoring datum is encoded in said signal SM which indicates that the apparatus 1 has detected an abnormal operating condition of the bogie B. Herein, an abnormal operating condition is a condition in which the bogie B is faulty or an operating condition in which the bogie B, while it can still travel along the line, cannot do so optimally (e.g. at a lower speed and/or with less braking power than normal), and such an operating condition may lead over time to failure of said bogie B (e.g. due to strong vibrations while travelling), which might result in accidents such as a derailment, a collision (e.g. against a mast of the overhead line) caused by the coach exceeding the loading gauge, or a separation of the line of coaches, thus preventing traffic on at least a portion of the line.

It must be pointed out that, although the bogie B represented in Fig. 1 is a two-axle railway bogie, the invention is also applicable to any type of railway, subway or tramway bogie, without however departing from the teachings of the present invention.

Also with reference to Fig. 3, the apparatus 1 preferably comprises the following components: - processing means 11, e.g. one or more CPUs, GPUs, DSPs, FPGAs and/or the like, which preferably implement, whether in hardware and/or software form, a neural network trained by inputting to said neural network at least one training datum representing a quantity concerning at least one (second) behaviour of a second damper in an abnormal operating condition, and forced to output a second monitoring datum indicating the occurrence of said abnormal operating condition;

- volatile memory means 12, e.g. a random access memory RAM, in signal communication with the processing means 11. When the apparatus 1 is in an operating condition, said volatile memory means 12 store the travel data acquired by the sensor means;

- non-volatile memory means 13, preferably one or more magnetic disks (hard disks) or a Flash memory or another type of memory, in signal communication with the processing means 11 and with the volatile memory means 12, and wherein said non- volatile memory means 13 contain at least one set of instructions implementing a method for monitoring the bogie B according to the invention. Moreover, said non-volatile memory means 13 may also contain information that makes it possible to configure and/or operate the neural network (e.g. a set of internal weights, numbers of levels in the various layers, or the like);

- input and/or output (I/O) means 14 which can be connected to the sensor means and which are configured for acquiring at least one travel datum which represents a quantity concerning at least one behaviour of the bogie B in a travelling condition, which, as will be described below, may comprise a revolution speed of a wheel W and/or a speed of motion and/or a length (elongation) of the damper D, at least one pressure in a portion of said damper D, an acceleration to which the damper D and/or the bogie B is subjected, a frequency at which the bogie B is vibrating, or the like. These input/output means 14 may comprise, for example, a USB™, IEEE 1394, RS232, RS485, IEEE 1284 adapter or the like;

- transmission means 15, preferably wired and/or wireless ones (,e.g. a network interface sucn as 803.2 (also Known as

Ethernet) or 802.11 (also known as WiFi™) or 802.16 (also known as WiMax™) or a data network interface such as GSM/GPRS/UMTS/LTE/5G, TETRA™, LoRa™, XBee™, ZigBee™ or the like), configured for transmitting a signal SM, in which said at least one monitoring datum is encoded, to the supervision computer 3, wherein said monitoring datum represents an operating state of said bogie B and/or of the damper D, i.e. indicates whether said bogie B is operating correctly or requires maintenance because one of its dampers WD,VD,YD,LD is not working correctly, or the like;

- a communication bus 17 allowing information to be exchanged among the processing means 11, the volatile memory means 12, the non-volatile memory means 13, the input/output means 14, and the transmission means 15. Also with reference to Fig. 4, when the apparatus 1 is in an operating condition, said apparatus 1 executes a set of instructions implementing the method according to the invention, which comprises the following phases: - an acquisition phase P1, wherein at least one travel datum is acquired, via the input means 14, which represents a quantity concerning at least one behaviour of said bogie B in a travelling condition; - a processing phase P2, wherein at least one monitoring datum is determined, by means of a neural network and on the basis of said at least one travel datum, wherein said at least one monitoring datum represents an operating state of said damper D, wherein said neural network is trained in a manner such that, when inputting to said neural network at least one training datum representing at least one quantity concerning at least one second behaviour of a second damper in an abnormal operating condition, it will output a second monitoring datum indicating the occurrence of said abnormal operating condition; - a transmission phase P3, wherein the signal SM, in which said at least one monitoring datum is encoded, is transmitted, via transmission means 15, to the supervision computer 3.

This makes it possible to determine the occurrence of abnormal operating conditions of the bogie B as it is travelling, without having to move said bogie B to the workshop. It will thus be possible to immediately take the necessary steps (e.g. to detach a coach comprising a faulty bogie from the train) and/or to carry out preventive maintenance, so as to reduce the probability that faults or even accidents (e.g. a derailment and/or a collision) might occur.

The neural network is preferably of the feed-forward type, e.g. a Convolutional Neural Network (CNN), a Fully Connected Deep Neural Network (FC DNN), or a Hierarchical Temporal Memory (HTM); such neural network preferably has a number of inputs equalling the quantity of operating data that have been acquired by the input means 14 and that must undergo the categorization process. Also, said neural network must, be trained beforehand by means of a training process, which is preferably carried out by using a workstation comprising a CPU having more computational capacity than the processing means 11, wherein said CPU is preferably configured for executing a set of instructions implementing a training algorithm, preferably a Stochastic Gradient Descent (SGD) algorithm.

This makes it possible to determine the occurrence of abnormal operating conditions while the bogie B is travelling, without having to move the bogie B to the workshop. It will thus be possible to immediately take the necessary steps and/or to carry out preventive maintenance in order to reduce the probability that faults or even accidents might occur.

In more detail, the method according to the invention preferably comprises also a training phase, wherein, prior to executing the processing phase P2, said neural network is trained in a manner such that, when inputting to said neural network said at least one training datum, the latter will output the desired (second) monitoring datum. This will allow the monitoring system S to be flexibly adapted in the course of its service life, e.g. by increasing the number of abnormal operating conditions that said monitoring system S will be able to autonomously recognise.

It will thus be possible to immediately take the necessary steps and/or to carry out preventive maintenance in order to reduce the probability that faults or even accidents might occur.

In addition to the above, the travel data may preferably be transmitted to remote entities (e.g. one or more servers) located in a data processing centre (i.e. to the supervision computer 3), as well as to entities close to the bogie B, such as portable data processing and displaying systems used by service personnel (e.g. smartphones, tablets or laptops), or to data collection devices (e.g. microcontrollers comprising communication means such as a LoRa™ communication interface or the like) positioned on travelling vehicles (e.g. train carriages circulating along the line) and/or flying vehicles (e.g. remotely controlled vehicles performing surveillance tasks over the line).

In more detail, the apparatus 1 is preferably configured for transmitting (during the transmission phase P3), via the transmission means 15, said at least one travel datum to said supervision computer 3, wherein said supervision computer 3 is configured for executing the following steps: - receiving, via communication means comprised in said supervision computer 3 (and compatible with the transmission means 15 of the apparatus 1), said at least one travel datum;

-- generating a predictive maintenance plan for said bogie B on the basis of a historic model (e.g. generated by means of laboratory stress tests, so that said historic model can numerically model the ageing of the parts making up the bogie B) and said at least one travel datum, e.g. by calculating a probability of a failure of at least one of the dampers WD,VD,YD,LD on the basis of a travel datum and using, as a model, a historic sequence of travel data of another bogie similar to (e.g. of the same type as) the bogie B. It must be pointed out that "predictive maintenance plan" refers to the definitions contained in the UNI 133062018, UNI 10147 2003 and UNI 9910 specifications, i.e. a maintenance plan developed by predicting at least one instant of time when the life cycle of a component will end (e.g. when it will fail) on the basis of a historic model and data concerning said component, and/or a similar one.

It will thus be possible to carry out predictive maintenance in order to reduce the probability that faults or even accidents might occur. As shown in Fig. 2, the damper D has an elongate shape and comprises a first portion D1 and a second portion D2, both comprising a body having a cylindrical cross-section, wherein the body of the first section D1 has a larger diameter than that of said second section, and comprises a chamber which is preferably filled with oil (not shown in the annexed drawings), and wherein the body of said first section DI is penetrated by the body of said second section D2, which comprises a rod and a piston connected to said rod (not shown in the annexed drawings), wherein said piston has a diameter slightly smaller than that of said chamber, within which it is so positioned that said second portion D2 can slide along a longitudinal axis A of said damper D, thus varying the length of said damper D. Preferably, the oil in the chamber of the first section D1 has a viscosity that is suitable to brake the motion of the piston, and hence of the entire second portion D2; in addition, said piston comprises holes which are properly sized to generate a resistant force of adequate intensity to provide a desired damping effect, and wherein said piston preferably also comprises reed valves positioned inside said holes, so that it is advantageously possible, by adjusting the orientation of said valves, to differentiate the intensity of the generated resistant force depending on the direction of movement of the piston. As an alternative to or in combination with the above, the system S preferably comprises also a supporting frame 4 so shaped as to allow the device 1 and the sensor means to be coupled to the damper D; such supporting frame 4 comprises the following elements: - a first ring 41 shaped in such a way that it. can be coupled to the body of said first portion D1 of the damper D;

- a second ring 42 shaped in such a way that it can be coupled to the body of said second portion D2 of the damper D; - a telescopic rod 43 that mutually connects the first ring 41 and the second ring 42;

- a boxed body 44 shaped to house the apparatus 1.

This supporting frame 4 makes it possible to easily install the apparatus 1 on a damper of a railway, subway or tramway bogie already in use, permitting the detection of abnormal operating conditions of a bogie already circulating in a transportation network. It will thus be possible to immediately take the necessary steps and/or to carry out preventive maintenance on the bogies, so as to reduce the probability that faults or even accidents might occur.

The sensor means that detect the travel data may comprise one or more of the following elements:

- a first pressure sensor 5, preferably a differential sensor with a piezoelectric transducer, so positioned as to be able to detect a pressure difference between the outside environment and a first end of the chamber of the first portion DI of the damper D, and wherein said first pressure sensor 5 is preferably coupled to the first ring 41; - a second pressure sensor 6, preferably a differential sensor with a piezoelectric transducer, so positioned as to be able to detect a pressure difference between the outside environment and a second end of said chamber of the damper D, wherein said second end is opposite to the first end, so that said ends are separated by the piston of the second portion D2, and wherein said second pressure sensor 6 is preferably coupled to the second ring 42;

- a temperature sensor 7 (e.g. a PT100 or PT1000 thermistor, a thermocouple, or the like), so positioned as to be able to detect the temperature of the damper D, particularly in proximity to said chamber of the first portion DI of the damper D, so as to sense any heat produced by the damper D while the bogie B is travelling, and wherein said temperature sensor is preferably coupled to the body of the first portion D1;

- an elongation sensor 8 (e.g. an absolute linear encoder), so positioned as to be able to detect the distance between two points respectively comprised on the body of the first portion D1 and on the body of the second portion D2 of the damper D, wherein said elongation sensor is preferably coupled to the telescopic rod 43;

- a microphone 9 (e.g. a piezoelectric microphone) so positioned as to be able to detect a sound produced by at least one element of the damper D while the bogie B is travelling.

Therefore, the operating data preferably represent at least a pressure developed within the chamber of the damper D and/or a temperature of said damper D and/or an extension of said damper D and/or a sound emitted by the damper D while the bogie B is travelling.

The following will describe a number of technical characteristics that permit detecting a set of abnormal operating conditions of the bogie B. This set of conditions should however be considered as a non-limiting example.

During the training phase, said at least one training datum preferably represents at least one (first) pressure developed at a first internal end of a chamber of a second damper (i.e. a pressure difference between atmospheric pressure and said first end of the chamber) and a plurality of extensions of said second damper when said chamber is emptied (even only partially) of a viscous fluid (e.g. an oil), wherein said damper is preferably similar to the damper D, and wherein said second monitoring datum indicates that the damper has run out of oil.

This makes it possible to automatically detect an abnormal operating condition due to an insufficient oil level within the chamber of the damper D, without having to measure the level of said oil either directly or indirectly (e.g. by means of bench tests); in fact, the pressure will remain lower than normal even after a very quick variation of the elongation of said damper D. It will thus be possible to immediately take the necessary steps and/or to carry out preventive maintenance in order to reduce the probability that faults or even accidents might occur. In addition to the above, during the training phase, said at. least one training datum may represent also a second pressure developed at a second end within the chamber of said second damper (i.e. a pressure difference between atmospheric pressure and said second end of the chamber) when said chamber is emptied (even only partially) of the viscous fluid, wherein said second end is opposite to the first end, so that said ends are separated by the piston of the second portion D2.

This makes it possible to automatically detect, in an even more precise manner, an abnormal operating condition due to an insufficient oil level within the chamber of the damper D, without having to measure the level of said oil either directly or indirectly (e.g. by means of bench tests); in fact, the pressure at both ends of the chamber will remain at very similar values even after a very quick variation of the elongation of said damper D, because the oil will be replaced by a certain amount of air, which, since its viscosity is much lower than that of said oil, will flow through the piston holes much faster than the oil. It will thus be possible to immediately take the necessary steps and/or to carry out preventive maintenance in order to reduce the probability that faults or even accidents might occur.

In combination with or as an alternative to the above, during the training phase, said at least one training datum represents a temperature of a portion (preferably, the first portion D1) of said second damper when said second damper is suffering a mechanical problem (e.g. a broken piston ring, a bent piston rod, etc.), and said second monitoring datum indicates that said piston of said second damper is moving with difficulty. This makes it possible to automatically detect an abnormal operating condition caused by excessive friction undergone by the piston of the damper D, e.g. because of a broken piston ring; in fact, the amount of heat dissipated while the bogie B is travelling will be greater than normal because of increased friction. It will thus be possible to immediately take the necessary steps and/or to carry out preventive maintenance in order to reduce the probability that faults or even accidents might occur. In combination with or as an alternative to the above, during the training phase, said at least one training datum represents a sound emitted into the environment by said second damper when said second damper is suffering a mechanical problem (e.g. a broken piston ring, a bent rod, etc.), and said second monitoring datum indicates that said piston of said damper D is moving with difficulty.

This makes it possible to automatically detect an abnormal operating condition caused by excessive friction undergone by the piston and/or the rod of the damper D, e.g. because of a broken piston ring, a bent rod, or the like; in fact, the noise produced by the friction between the two portions DI and D2 while the bogie B is travelling will be greater than normal because of such mechanical problems. It will thus be possible to immediately take the necessary steps and/or to carry out preventive maintenance in order to reduce the probability that faults or even accidents might occur.

In combination with the above, the apparatus 1 may comprise, or be connected to, at least one of the following elements: - an inertial sensor (e.g. a gyroscope/accelerometer , preferably of the solid-state type, and/or an inclinometer, and/or the like) so positioned as to detect at least a speed and/or an acceleration and/or an inclination of a portion of the bogie B, e.g. the frame C, the rotation axles of the wheels W, etc.; - a satellite positioning signal receiver (also known as "GNSS receiver") configured for determining the position and/or the speed of the bogie B.

In order to improve the recognition of abnormal operating conditions of the damper D, the input means 14 of the apparatus 1 are preferably configured for acquiring (during the acquisition phase P1) at least one motion datum (preferably generated by the inertial sensor or by the GNSS receiver), which represents a quantity describing a travelling condition of the bogie B (e.g. a speed and/or a direction of travel and/or a longitudinal and/or lateral acceleration, and/or the like), and wherein the processing means 11 are also configured for determining (during the processing phase P2) whether said bogie B is in a travelling condition on the basis of said at least one motion datum (e.g. by estimating the revolution speed of the wheels on the basis of the frequency of a harraonic with greater energy which is present in the signal produced by the inertial sensor, by calculating the distance between two points determined by the GNSS receiver with reference to a known time interval, or the like), and for determining said at least one monitoring datum only if said bogie B is in a travelling condition.

This makes it possible to reduce the number of false positives, making the system S more robust and reliable and advantageously reducing the probability that faults or even accidents might occur.

It should also be highlighted that said at least one travel datum may also comprise a speed and/or a direction of travel and/or a longitudinal and/or lateral acceleration and/or a position of said bogie B, preferably determined by means of the inertial sensor and/or the satellite positioning signal receiver.

This makes it possible to further reduce the number of false positives because the neural network can thus be trained by taking also into account the characteristics of the route being followed by the bogie B and the travelling conditions of said bogie B, so as to make the system S more robust and reliable and hence advantageously reduce the probability that faults or even accidents might occur.

In combination with or as an alternative to the above, the apparatus 1 preferably comprises also the following elements:

- electric accumulator means (e.g. a lithium-ion battery, a supercapacitor, or the like) configured for supplying power to said apparatus 1 or part thereof;

- generator means (e.g. a photovoltaic panel and/or an aeolian and/or piezoelectric and/or thermoelectric and/or electromagnetic and/or vibrational generator, and/or the like) connected to said accumulator means and configured for converting luminous, mechanical or thermal energy into electric energy.

In particular, the generator means preferably comprise the following elements: - at least one winding coupled to the electric accumulator means and positioned on the first portion DI of the damper D;

- at least one permanent magnet (e.g. a neodymium magnet) positioned on the second portion D2 of said damper D and capable of inducing an electromotive force in said at least one winding.

The presence of the electric accumulator means and generator means makes said apparatus 1 suitable for installation on any railway, subway or tramway bogie, in that said apparatus 1 does not need a low-voltage power supply. The increased positioning capability of the apparatus 1 further reduces the risk of accidents.

Of course, the example described so far may be subject to many variations . Some of the possible variants of the invention have been described above, but it will be clear to those skilled in the art that other embodiments may also be implemented in practice, wherein several elements may be replaced with other technically equivalent elements. The present invention is not, therefore, limited to the above-described illustrative examples, but may be subject to various modifications, improvements, or replacements of equivalent parts and elements without however departing from the basic inventive idea, as specified in the following claims.

Claims

CLAIMS :

1. Method for monitoring a railway, subway or tramway bogie (B) comprising a damper (D, WD, VD, YD, LD), characterized in that it comprises

- an acquisition phase (Pl), wherein at least one travel datum is acquired, via input means (14), which represents a quantity concerning at least one behaviour of said bogie (B) in a trave11ing condition,

- a processing phase (P2), wherein at least one monitoring datum is determined, by means of a neural network, on the basis of said at least one travel datum, wherein said at least one monitoring datum represents an operating state of said damper (D, WD, VD, YD, LD), wherein said neural network is trained in a manner such that, when inputting to said neural network at least one training datum representing at least one quantity concerning at least one second behaviour of a second damper in an abnormal operating condition, it will output a second monitoring datum indicating the occurrence of said abnormal operating condition,

- a transmission phase (P3), wherein a signal (SM), in which said at least one monitoring datum is encoded, is transmitted, via transmission means (15), to a supervision computer (3).

2. Method according to claim wherein said neural network is a feed-forward convolutional neural network.

3. Method according to claims 1 or further comprising

- a training phase, wherein, prior to executing the processing phase (P2), said neural network is trained in a manner such that, when inputting to said neural network said at least one training datum, said neural network will output said second monitoring datum.

4. Method according to claim 3, wherein, during the training phase, said at least one training datum comprises a plurality of extensions of said second damper and a first pressure developed at a first end within a chamber comprised in a second damper when said chamber is emptied of a viscous fluid, and wherein said second monitoring datum indicates that the damper has run out of oil.

5. Method according to claim 4, wherein, during the training phase, said at least one training datum comprises also a second pressure developed at a second end, opposite to the first end, within the chamber of said second damper when said chamber is empty.

6. Method according to any one of claims 3 to 5, wherein, during the training phase, said at least one training datum comprises a temperature of a portion of the said second damper when said second damper is suffering a mechanical problem, and said second monitoring datum indicates that a piston comprised in said second damper is moving with difficulty.

7. Method according to any one of claims 1 to 6, wherein, during the acquisition phase (P1), at least one motion datum is acquired 'which comprises a quantity describing a travelling condition of tne bogie (B), and wherein during the processing phase (P2) it is determined, on the basis of said at. least one motion datum, whether said bogie (B) is in a travelling condition, and said ar. least one monitoring datum will only be determined if said bogie (B) is in a travelling condition.

8. Computer program product which can be loaded into the memory of an electronic computer anc which comprises portions of software code for executing the phases of the method according to any one of claims 1 to 7.

9. Apparatus (1) for monitoring a railway, subway or tramway bogie (B) comprising a damper (D, WD, VD, YD, LD), characterized in that it. comprises

- input means (14) configured for acquiring at least one travel datum which represents a quantity concerning at least one behaviour of said bogie (B) in a travelling condition,

- processing means (11) configured for determining, by means or a neural network and on tne oasis or sard at least one travel datum, at least one monitoring datum which represents an operating state of said damper (D, WD, VD, YD, LD), wherein said neural network is trained in a manner such that, when inputting to said neural network at least one training datum representing at least one quantity concerning at least one second behaviour of a second damper in an abnormal operating condition, it will output a second monitoring datum indicating the occurrence of said abnormal operating condition,

- transmission means (15) configured for transmitting a signal (SM), in which said at least one monitoring datum is encoded, to a supervision computer (3).

Apparatus (1) according to claim wnerern sard neural network is a feed-forward convolutional neural network.

11. Apparatus (1) according to any one of claims 9 to 10, wherein said at least one travel datum comprises a plurality of extensions of said damper (D, WD, VD, YD, LD) and at least one pressure developed within a chamber comprised in said damper (D, WD, VD, YD, LD).

12. Apparatus (1) according to any one of claims 9 to 11 wherein said at least one travel,datum comprises a sound emitted by said damper (D, WD, VD, YD, LD) as the bogie (B) is travelling.

13. Apparatus (1) according to any one of claims 9 to 12, wherein said at least one travel datum comprises a temperature of said damper (D, WD, VD, YD, LD).

14. Apparatus (1) according to any one of claims 9 to 13, wherein said at least one travel datum comprises a speed and/or a direction of travel and/or a longitudinal and/or lateral acceleration and/or a position of said bogie (B).

15. Apparatus (1) according to any one of claims 9 to 14, further comprising

- electric accumulator means configured for supplying power to said apparatus (1), and - generator means connected to said accumulator means and configured for converting luminous, mechanical or thermal energy into electric energy.

16. System (S) for monitoring a railway, subway or tramway bogie (B), comprising

- an apparatus (1) according to any one of claims 9 to 15, and

- a supervision computer (3) in communication with said apparatus (1), wherein said apparatus (1) is configured for transmitting said at least one travel datum to said supervision computer (3), and wherein said supervision computer (3) is configured for receiving said at least one travel datum and generating a predictive maintenance plan for said bogie (B) on the basis of a historic model and said at least one travel datum.