Method for ordering vehicles in a fleet of vehicles according to a maintenance need; Computer program and associated computer system.

A method for analyzing vehicle fleet data to detect maintenance bursts and prioritize vehicles based on duration and intensity, addressing the inefficiencies in current systems by automating maintenance scheduling.

FR3141259B1Active Publication Date: 2024-11-01ALSTOM HOLDINGS SA
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
FR2022010996
Authority / Receiving Office
FR · FR
Patent Type
Patents
Current Assignee / Owner
Filing Date
2022-10-24
Publication Date
2024-11-01
Estimated Expiration
2042-10-24

AI Technical Summary

Technical Problem

Current maintenance systems for vehicle fleets, particularly railway vehicles, generate a vast amount of data that is difficult to analyze, requiring significant time and resources, and lack efficient methods to prioritize maintenance based on urgent needs across vehicles.

Method used

A method that analyzes time series data from vehicle monitoring systems to detect bursts in maintenance needs, using a likelihood and transition function to determine optimal maintenance sequences and prioritize vehicles based on burst duration and intensity.

Benefits of technology

Automatically identifies vehicles with high maintenance needs, optimizing maintenance scheduling by reducing manual effort and improving operational efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000012_0000
    Figure 00000012_0000
  • Figure 00000013_0000
    Figure 00000013_0000
Patent Text Reader

Abstract

Method for ordering vehicles in a fleet of vehicles according to a maintenance need; Computer program and associated computer system.This process (100) comprises the steps of: for each vehicle in the fleet, determining (110) a time series comprising, for each time step, an instantaneous value of at least one quantity of interest obtained from monitoring events acquired by means of a fleet vehicle monitoring system; analyzing (120), over a predetermined time interval, the time series, taking into account the time series determined for all vehicles in the fleet, considering that at each time step, the state of a vehicle is either a "normal" or an "abnormal" state, to obtain an optimal sequence of states over the predetermined time interval; and detecting (130) the possible presence of one or more bursts in the optimal sequence of states, then ordering (140) a list of the vehicles in the fleet according to the properties of the bursts detected for each vehicle. Figure for the abstract: Figure 2.
Need to check novelty before this filing date? Find Prior Art

Description

Title of the invention: Method for ordering the vehicles of a fleet of vehicles according to a maintenance need; Associated computer program and computer system.

[0001] The present invention relates to the field of maintenance of a fleet of vehicles, in particular railway vehicles, such as trains, metros, trams, etc.

[0002] Systems are known for monitoring potential failures of a railway vehicle based on the generation of events during the operation of this vehicle. More precisely, the monitored vehicle is equipped with a plurality of sensors capable of acquiring data which, once processed, make it possible to generate characteristic events. An event constitutes a new entry in a monitoring database. It is defined by a plurality of attributes, such as for example a vehicle identifier, an event identifier, a time of occurrence of the event, the type to which the event belongs, and different values ​​characterizing it (which may depend on the type to which the event belongs).

[0003] Currently, the events generated for a vehicle are analyzed by maintenance operators in order to carry out a diagnosis on the state of the vehicle and determine whether it is necessary to carry out a maintenance operation on this vehicle and the nature of this maintenance operation: simple inspection or replacement of such or such faulty component (or about to fail) of the railway vehicle in question.

[0004] However, such monitoring systems generate thousands of events every day and for each vehicle in a fleet.

[0005] Such a mass of information is difficult for an operator to analyze. Such an analysis remains complex, particularly to establish significant correlations between events. It therefore requires a significant investment in terms of working time and costs.

[0006] Furthermore, it is practically impossible for an operator to compare the vehicles in a fleet with each other to determine which of these vehicles has an urgent need for maintenance in order to carry out the required maintenance operations on this vehicle rather than on another. Today, the choice of inspecting one vehicle rather than another is essentially an empirical decision taken by the maintenance operator.

[0007] It would therefore be interesting to be able to quickly and simply identify the vehicle(s) in a fleet which have a priority need for maintenance, even if only to optimize maintenance tasks and limit the time during which equipment cannot be used.

[0008] The aim of the present invention is in particular to meet this need.

[0009] For this purpose, the invention relates to a method, implemented by computer, for ordering the vehicles of a fleet of vehicles according to a maintenance need, characterized in that it comprises the steps of: for each vehicle of the fleet, determining a time series, the time series comprising, for each time step, an instantaneous value of at least one quantity of interest obtained from monitoring events acquired by means of a system for monitoring the vehicles of the fleet of vehicles; analyzing, over a predetermined time interval, the time series, taking into account the time series determined for all the vehicles of the fleet of vehicles, considering that at each time step, the state of a vehicle is either a "normal" state or an "abnormal" state requiring maintenance, so as to obtain an optimal sequence of states over the predetermined time interval;and, detecting the possible presence of one or more bursts in the optimal sequence of states, then ordering a list of vehicles in the fleet of vehicles according to the properties of the bursts detected for each of the vehicles.;

[0010] According to particular embodiments, this method comprises one or more of the following characteristics, taken in isolation or in all technically possible combinations:

[0011] - the quantity of interest is the total number of events or the total number of events of a particular type affecting the vehicle considered, acquired during a reference time window.

[0012] - analyzing the time series involves optimizing a cost function, combining a likelihood function and, preferably, a transition function, so as to determine an instantaneous probability for each time step.

[0013] - the instantaneous probability for a time step is compared to a probability of reference calculated from the quantities of interest of all vehicles in the vehicle fleet, to determine the optimal state in which the vehicle considered is at the time step considered.

[0014] - the presence of bursts in the optimal sequence of states consists of determining a number of consecutive time steps that the vehicle spends in the “abnormal” state in the optimal sequence of states and, when this number of time steps is greater than a predetermined threshold, consider that it is a burst.

[0015] - a salvo is characterized by a duration and / or an intensity and order the list of vehicles of the vehicle fleet according to the properties of the bursts detected for each vehicle is carried out according to the duration and / or intensity of said bursts.

[0016] - the vehicle is a railway vehicle, such as a train, a subway, or a tram.

[0017] The invention also relates to a computer program product comprising software instructions which, when executed by a computer, implement the preceding method.

[0018] The invention also relates to a computer system, characterized in that it is adapted to implement the preceding method, the computer system being able to access the content of a surveillance database to read the surveillance events acquired by a surveillance system.

[0019] Preferably, the system comprises: a module for determining a time series of a quantity of interest; a module for analyzing the time series of a quantity of interest to determine an optimal sequence of states; a module for detecting bursts in the optimal sequence of states; and, a module for scheduling the vehicles of a fleet of vehicles according to the properties of the detected bursts.

[0020] The invention and its advantages will be better understood on reading the detailed description which follows of a particular embodiment, given solely by way of non-limiting example, this description being made with reference to the appended drawings in which:

[0021] [Fig-1] [Fig.l] is a schematic representation of a computer system for the implementation of the method according to the invention; and,

[0022] [Fig.2] [Fig.2] is a block representation of a mode of realization preferred implementation of the scheduling method according to the invention.

[0023] The method according to the invention makes it possible to automatically order the trains of a fleet of trains according to a maintenance requirement.

[0024] A train fleet groups together a plurality of trains that are similar or even identical to each other and that are put into circulation on a network in an essentially interchangeable manner. In other words, the question of ordering, in relation to each other, the trains of a fleet according to a maintenance need makes sense, since these different trains are comparable in their structure (and therefore their wear and potential failures) and in their use (and therefore in their operating conditions).

[0025] The method according to the invention is based on the detection of bursts or bursts by analyzing a time series of a quantity of interest developed from events generated by a state-of-the-art monitoring system.

[0026] In the context of time series analysis of a quantity, burst detection is a technique for identifying values ​​of that quantity that show a sharp increase over a limited period of time compared to a baseline level.

[0027] Many burst detection algorithms are known, particularly in signal processing applications. Generally, a burst detection algorithm identifies periods of time (or bursts) during which a target value is unusually frequent.

[0028] The burst detection algorithms can be adapted for discrete data streams, as is the case for events generated by a train fleet monitoring system. In the following, the embodiment that is presented in detail implements a burst detection algorithm based on logarithmic maximum likelihood.

[0029] According to the invention, burst detection for a particular train is performed by determining the baseline level from the events generated by the monitoring system for all trains in the fleet.

[0030] [Fig. 1] represents a computer system 10 for implementing the method according to the invention.

[0031] It comprises a monitoring database 12 collecting the events generated by a monitoring system 20 of the trains in the fleet.

[0032] The computer system 10 comprises a computer 14 comprising calculation means, such as a processor, and storage means, such as a memory. The memory stores in particular the instructions of computer programs, in particular a program 30 whose execution allows the implementation of the method according to the invention.

[0033] The program 30 can be broken down into modules, in particular a module 32 for determining a time series of a quantity of interest, a module 34 for analyzing the time series, a module 36 for detecting bursts, and a module 38 for scheduling the trains of the fleet.

[0034] The computer system 10 advantageously comprises a human-machine interface 16, for example a tablet, making it possible to display the results of the implementation of the method according to the invention for the benefit of a maintenance operator.

[0035] Referring to [Fig.2], a preferred embodiment of a method for ordering trains of a train fleet according to a maintenance need is presented.

[0036] The method 100 is implemented independently of a prior step 90 of acquiring events.

[0037] The method 100 as such comprises a step 110 of determining a time series of a quantity of interest or characteristic (this step corresponding to the execution of the module 32), a step 120 of analyzing a time series (this step corresponding to the execution of the module 34), a step 130 of burst detection (this step corresponding to the execution of the module 36) and a step 140 of scheduling the trains of the fleet (this step corresponding to the execution of the module 38). Acquisition step 90

[0038] This step, prior to the implementation of the method according to the invention, is carried out in accordance with the prior art.

[0039] It is carried out by the monitoring system 20.

[0040] It consists of acquiring, for each train in the fleet, monitoring data and creating events from the acquired data.

[0041] The data is delivered by sensors fitted to each train.

[0042] Events are associated with a particular train. They are dated. For example, the time step chosen for dating events is that of the day.

[0043] The events are recorded in the monitoring database 12.

[0044] It should be noted that a high number of occurrences of an event may be due to an actual failure of the monitored equipment (the monitoring system may then continue to report this failure until it is repaired). But, a high number of occurrences may also be due to an error in the design of the monitoring system itself, in particular the modeling of the failure that this system uses to generate monitoring events (and then the monitoring system reports the event several times over time).

[0045] Step 110 of determining a time series of a quantity of interest

[0046] The purpose of step 110 is to construct, for each train, a time series of a quantity of interest from the events contained in the monitoring database 12.

[0047] The quantity of interest is any time variable developed from all or part of the monitoring events associated with a train and allowing, by aggregating these monitoring events, to quantify a maintenance requirement at each time step.

[0048] For example, we first define a time window corresponding, for example, to a week of operation of a train.

[0049] The quantity of interest is then, for example, the total number of monitoring events generated for the train considered within the time window. The quantity of interest thus calculated is dated, for example, with the last day of the time window used.

[0050] It is sufficient to repeat this operation by sliding the time window of the chosen time step (here the day), to calculate a quantity of interest for each day of operation of a train.

[0051] The time series for a train is then made up of the sequence of values ​​of the quantity of interest for this train.

[0052] Such a time series is obtained for each of the trains in the fleet.

[0053] Alternatively, instead of the cumulative number of events, the quantity of interest could correspond to the cumulative number of events of a particular type (i.e. associated with a specific failure or a specific component of the train). Alternatively, instead of analyzing only a time series of one quantity of interest, it could be chosen to calculate different quantities of interest and to follow each of these quantities over time. Step 120 of analyzing a time series

[0054] For each train in the fleet, this step consists of analyzing the time series of the quantity of interest obtained in step 110 by applying a burst detection algorithm, then quantifying the maintenance requirement of the train considered as a function of the bursts detected.

[0055] This step takes into account not only the time series associated with the train considered but also the time series associated with the other trains in the fleet.

[0056] The burst detection algorithm more particularly used in the present embodiment is based on the model that at each time step a train can only be in two possible states, respectively a nominal operating state (“normal state” in the following) and an operating state requiring maintenance (“abnormal state” in the following).

[0057] More precisely, assuming that the events follow a binomial distribution when the train is in the normal state and a binomial distribution (identical to simplify the present description) when the train is in the abnormal state, the burst detection algorithm aims to determine the sequence of states which best corresponds to the observations constituted by the values ​​of the time series of the quantity of interest over the time interval considered.

[0058] Consider for example a time interval of one week, subdivided by time steps of one day. Each time step of the interval is indexed by the integer t between 1 and T, where is the maximum number of time steps of the interval of interest (here T is equal to 7).

[0059] Consider a fleet composed of N trains. Each train is indexed by an integer j between 1 and N

[0060] The daily value of the characteristic quantity for train j on day t is noted: H /

[0061] The daily value of the total characteristic quantity for all trains in the fleet on day t is given by: a

[0062] The integrated value of the characteristic quantity for train j over the time interval is given by: _ V! THERE 7

[0063] The integrated value of the total characteristic quantity for all trains in the fleet on the time interval is given by

[0064] We define the probability of the base level for train j, or reference probability, by G / GF

[0065] This reference probability is associated with the normal state for train j. It corresponds to the events affecting train j in relation to all the events affecting the trains in the fleet, over the time interval considered.

[0066] The associated burst probability for train j is then defined by: pburst — q pref, where a is a proportionality constant.

[0067] This burst probability is associated with the abnormal state for train j.

[0068] It is then a matter of calculating a sequence of states 5(t) over the time interval considered which is compatible with the characteristic values ​​g. ( t ) and g ( t ) for the train j.

[0069] To do this, a statistical criterion is chosen. For example, in the present embodiment, the statistical criterion chosen is based on a cost function associating a logarithmic likelihood function, advantageously combined with a transition function.

[0070] The instantaneous likelihood function associated with state s(t) at time t (also noted s) for train j is the binomial likelihood function L^j ( t ):

[0072] For numerical reasons, we seek to minimize the logarithm of L^jf t) over the time interval considered. In order to evaluate the likelihood of the normal state (s = "normal"), the probability P- is taken equal to p'A . The likelihood of the abnormal state (s = "abnormal") is evaluated by taking P- equal to pbursî.

[0073] The transition function / fL(y) from state J at time t to state s' at the following time t+1 makes it possible to associate a cost with a change of state.

[0074] Preferably, since, by definition, the normal state is the expected state of the train and the abnormal state is an "exceptional" state, the transition function is non-zero only if there is a change of state and the transition is from the normal state to the abnormal state.

[0075] It is conceivable that the transition function is proportional to T, to make it comparable to the likelihood term in the optimization process when T increases (i.e. when the time interval increases).

[0076] Thus, the instantaneous criterion to minimize is the following:

[0077] fj(t) -

[0078] Over the time interval, the criterion to be minimized becomes:

[0080] The optimal sequence of states s(t) of train j, that is to say the sequence of states (“normal” or “abnormal”) of train j which best explains the observation according to the binomial model, is therefore the one which minimizes the cost function for all the time steps of the time interval considered.

[0081] The optimal sequence is determined for example using optimization by a “greedy” algorithm, known to those skilled in the art. Step 130 of burst detection

[0082] The optimal sequence of states is finally analyzed to isolate possible bursts. A burst is then characterized by a minimum number of consecutive time steps in the abnormal state. This threshold number is predefined. It can be chosen equal to one, a burst then being detected as soon as the train is in the abnormal state.

[0083] In addition to its duration, a burst can be characterized by an intensity. The intensity of a burst is for example given by the sum of the values ​​of the cost function fj(t ) over the time step(s) associated with the burst. Scheduling Step 140

[0084] Once the previous steps have been carried out for each train, the way of ordering the trains in the fleet among themselves depends on the quantity of interest.

[0085] If we consider, as in the previous example, the cumulative number of daily events, we can classify the trains in decreasing order of duration of the bursts detected for each train over the time interval considered. If two bursts have the same duration, then the trains are classified by decreasing intensity of these bursts.

[0086] If, on the contrary, we consider the number of daily events of a particular type, then the bursts are classified by intensity (knowing that the intensity takes into account in a certain way the duration of the burst).

[0087] Once the trains in the fleet have been ordered by priority, only the identifiers of the first X trains (for example, X=3) are displayed on the interface 16.

[0088] Advantageously, by selecting the identifier of a train, the operator accesses the Y most recurring events (for example, Y=5) affecting this train Advantages

[0089] The present method helps maintenance operators to select the priority train for maintenance quickly and rationally.

[0090] What is relevant for ranking trains relative to each other is not the number of occurrences of events as such, but rather a change significant in the proportion of events generated by a train compared to the rest of the fleet, in a certain period of time and possibly for a certain type of events.

[0091] If an unusual and abrupt increase occurs for a particular train (in the total number of events, or only for a single type of event), then it can be considered that, for some reason, the behavior of this train is altered. It is important to flag this automatically because it may be symptomatic of something abnormal that should be rectified as quickly as possible.

Claims

Claims

1. A computer-implemented method (100) for ordering the vehicles of a fleet of vehicles according to a maintenance need, characterized in that it comprises the steps of: - for each vehicle of the fleet, - determining (110) a time series, the time series comprising, for each time step, an instantaneous value of at least one quantity of interest obtained from monitoring events acquired by means of a system for monitoring the vehicles of the fleet of vehicles; - analyzing (120), over a predetermined time interval, the time series, taking into account the time series determined for all the vehicles of the fleet of vehicles, considering that at each time step, the state of a vehicle is either a "normal" state or an "abnormal" state requiring maintenance, so as to obtain an optimal sequence of states over the predetermined time interval;and, - detecting (130) the possible presence of one or more bursts in the optimal sequence of states, then - ordering (140) a list of vehicles in the fleet of vehicles according to the properties of the bursts detected for each of the vehicles.;

2. Method according to claim 1, in which the quantity of interest is the total number of events or the total number of events of a particular type affecting the vehicle considered, acquired during a reference time window.

3. A method according to any preceding claim, wherein analyzing the time series comprises optimizing a cost function, combining a likelihood function and, preferably, a transition function, so as to determine an instantaneous probability for each time step.

4. Method according to claim 3, in which the instantaneous probability for a time step is compared to a reference probability calculated from the quantities of interest of all the vehicles in the fleet of vehicles, to determine the optimal state in which the vehicle considered is at the time step considered.

5. A method according to any preceding claim, wherein detecting the presence of bursts in the optimal sequence of states comprises determining a number of consecutive time steps that the vehicle enters the “abnormal” state in the optimal sequence of states and, when this number of time steps is greater than a predetermined threshold, consider that it is a salvo.

6. Method according to any one of the preceding claims, in which a burst is characterized by a duration and / or an intensity and ordering the list of vehicles in the fleet of vehicles according to the properties of the bursts detected for each vehicle is carried out according to the duration and / or the intensity of said bursts.

7. A method according to any preceding claim, wherein the vehicle is a rail vehicle, such as a train, a subway, or a tram.

8. A computer program comprising software instructions which, when executed by a computer, implement a method according to any one of the preceding claims.

9. Computer system (10), characterized in that it is adapted to implement a method (100) according to any one of claims 1 to 6, the computer system being able to access the content of a monitoring database (23) to read the monitoring events acquired by a monitoring system (20).

10. System according to claim 9, comprising: - a module (32) for determining a time series of a quantity of interest; - a module (34) for analyzing the time series of a quantity of interest to determine an optimal sequence of states; - a module (36) for detecting bursts in the optimal sequence of states; and, - a module (38) for scheduling the vehicles of a fleet of vehicles according to the properties of the detected bursts.