Forecasting wear characteristics of rail vehicles

Abstract

A method for determining time-dependent wear characteristics (VV) of a technical component of a rail vehicle is described. The method involves determining and storing a digital twin (ZW) of the technical component with a current wear status (VS) and a distance-dependent wear profile (V) of the technical component. Furthermore, the future time-dependent wear characteristics (VV) of the technical component of the rail vehicle are estimated according to a future timetable (FP) of the rail vehicle and on the basis of the digital twin (ZW). A method for scheduling rail vehicles is also described. Additionally, an estimating device (50) is described. Moreover, a planning device (60) is described.

Description

[0001] The invention relates to a method for determining the time-dependent wear behavior of a technical component of a rail vehicle. Furthermore, the invention relates to a method for planning the deployment of rail vehicles. In addition, the invention relates to an estimation device. Finally, the invention relates to a planning device, a computer program product, and a computer-readable medium.

[0002] The wear and tear of functional units in rail vehicles must be regularly monitored by maintenance personnel to prevent breakdowns and accidents caused by technical failures. Regular visual inspections of wear-prone technical components are time-consuming and also cost valuable operating time. In contrast, automated prediction of material wear in the railway environment would enable improved and predictable maintenance intervals, thus saving costs in the optimal operation of rail vehicles, especially locomotives. Savings potential is particularly evident in components with high wear, such as pantograph contact strips or wheels. Individual wear patterns usually result from local conditions. These conditions include, for example, the type and level of the mains voltage used, the degree of wear on the overhead line, and so on.

[0003] Traditionally, maintenance or replacement of components is carried out after a defined number of kilometers driven or after measuring the thickness of the contact strips at the depot. However, the former approach does not take into account the individual wear patterns of technical components, meaning that material resources cannot be used optimally. The latter approach, on the other hand, involves a high maintenance effort for checking the wear condition of each technical component, resulting in comparatively high personnel costs.

[0004] Document DE 10 2009 024 506 A1 describes a method for determining maintenance information regarding an object to be maintained by determining a deterioration model of the object to be maintained based on at least one influencing factor characterizing the deterioration and the maintenance information depending on the deterioration model.

[0005] The task, therefore, is to enable more effective prediction of the future wear and tear of a rail vehicle and more effective maintenance of a rail vehicle.

[0006] This problem is solved by a method for determining a time-dependent wear behavior of a technical component of a rail vehicle according to claim 1, a method for the deployment planning of rail vehicles according to claim 7, an estimation device according to claim 11, a planning device according to claim 12, a computer program product according to claim 13 and a computer-readable medium according to claim 14.

[0007] In the inventive method for determining the time-dependent wear behavior of a technical component of a rail vehicle, a digital twin of the technical component, comprising a current wear status and a route-dependent wear profile of the technical component of the rail vehicle, is determined and stored. A technical component is understood to be a functional unit of the rail vehicle used in its operation, which is subject to usage-dependent, and in particular route-dependent, wear. In everyday language, such a technical component is also referred to as a wear part. If the technical component reaches a maximum tolerable level of wear, it must either be replaced or overhauled / repaired as part of a maintenance measure.A digital twin is understood to be a digital representation of a technical component that includes information about the physical or technical condition of the component. In this specific case, the digital twin represents the current wear status and location-dependent wear behavior of a technical component of a rail vehicle.

[0008] The current wear status indicates the most recently determined measurement of wear of the technical component.

[0009] A wear profile is understood to be a location-dependent measure of the wear of a technical component. This location dependency is preferably implemented by dividing the rail network into track sections and determining the degree of wear of the technical component associated with each section. Since the wear of the technical component is generally very low during a single journey over a track section, the cumulative wear of a rail vehicle is measured after numerous journeys on that section. Based on this cumulative wear, an average wear of the rail vehicle for a single journey over the track section is calculated.The average wear of a technical component during a journey over a specific section of track ultimately yields the value of the rail vehicle's wear profile, also known as the track-related wear profile component, for that specific section. A track section is defined as a section of track between two stations. Preferably, the track section is defined as a section of track between two adjacent stations.

[0010] In this way, a location-dependent wear profile can be determined for different technical components of an individual rail vehicle. The wear profile can also be generalized and parameterized. This means that the wear profile is preferably determined based on wear values ​​observed across a large number of rail vehicles and scenarios with varying parameters or parameter values. As will be explained in detail later, the wear of a pantograph or the wheels of a rail vehicle can depend on weather conditions and the weight of the rail vehicle. Therefore, instead of an average wear value, a wear profile for each track section can also be assigned a function that depends on various variables and / or parameters influencing the wear of a technical component.

[0011] Furthermore, the future time-dependent wear behavior of the rail vehicle is estimated based on a future timetable and the digital twin. As already mentioned, the digital twin includes both the current wear status of the rail vehicle's technical components and a route-dependent wear profile, on the basis of which the future time-dependent wear behavior of the rail vehicle is estimated.

[0012] The timetable allows for the determination of a rail vehicle's future route and track usage. Based on the route, the track sections assigned to it can be identified. Using the wear profile values ​​or wear profile functions assigned to each track section, along with known and predicted values ​​for variables and parameters, predicted wear values ​​for an individual rail vehicle can be calculated for each track section. The total predicted wear, assuming the timetable is adhered to within a predetermined time interval, is then the sum of the predicted wear values ​​for each track section.

[0013] Advantageously, a maintenance interval or the next maintenance date can be determined based on the predicted wear of a technical component of a rail vehicle. Conventionally fixed maintenance intervals can thus be individually adjusted when applying the method according to the invention, so that maintenance effort can be reduced to the necessary minimum. The maintenance of an individual rail vehicle can therefore be planned according to the timetable. Rail vehicles can also be used more optimally for specific driving missions, taking into account their current wear status and their respective predicted next maintenance date.

[0014] Based on the aforementioned considerations and described advantageous effects, a method for the deployment planning of rail vehicles can also be specified. In the inventive method for the deployment planning of rail vehicles, the future wear behavior of a plurality of available rail vehicles for different deployment scenarios is determined using the inventive method for determining the time-dependent wear behavior of a technical component of a rail vehicle. Furthermore, a deployment scenario is selected depending on a constraint related to the future wear behavior or the predicted wear and the necessary maintenance of the rail vehicles. The constraint preferably comprises one or more wear- and maintenance-related criteria to be met.A deployment scenario is understood as a plan according to which specific vehicles are deployed on specific routes according to a timetable in order to fulfill the aforementioned constraint. For example, such a criterion might require minimal maintenance within a predetermined time interval. The deployment of rail vehicles can also be adapted to maintenance capacities. For instance, the wear and tear of the rail vehicles is managed in such a way that, with a minimum number of rail vehicles required and with existing or predetermined maintenance capacities, sufficient maintenance capacity is always available for the rail vehicles, thus preventing timetable disruptions due to maintenance backlogs and similar issues.

[0015] The estimating device according to the invention comprises a database for determining and storing a digital twin of a technical component of a rail vehicle, including a current wear status and a route-dependent wear profile of the technical component. Furthermore, the estimating device according to the invention includes an estimating unit for estimating the future time-dependent wear behavior of the technical component of the rail vehicle, based on a future timetable for the rail vehicle and using the digital twin. As already mentioned, the digital twin includes information on the current wear status of the technical component of the rail vehicle as well as information on a route-dependent wear profile of the technical component of the rail vehicle.The estimating device according to the invention shares the advantages of the inventive method for determining a time-dependent wear behavior of a technical component of a rail vehicle.

[0016] The planning device according to the invention comprises an estimation device according to the invention for estimating the wear of a plurality of available rail vehicles for different operating scenarios of the rail vehicles in order to fulfill a predetermined timetable, and a selection unit for selecting an operating scenario depending on a constraint relating to the wear and the necessary maintenance of the rail vehicles. The planning device according to the invention shares the advantages of the inventive method for the operational planning of rail vehicles.

[0017] A large part of the aforementioned components of the estimating and planning device according to the invention can be implemented wholly or partially as software modules in a processor of a suitable computer system, e.g., a computer in the headquarters of a transport company or in a railway depot. A largely software-based implementation has the advantage that even previously used computer systems can be easily retrofitted by a software update to operate according to the invention. In this respect, the problem is also solved by a corresponding computer program product with a computer program that can be directly loaded into a computer system, containing program sections to execute the steps of the inventive method for determining the time-dependent wear behavior of a technical component of a rail vehicle and the inventive method for the operational planning of rail vehicles.At least the steps executable by a computer, in particular the step to determine and store a digital twin, the step to estimate the future time-dependent wear behavior of the rail vehicle, the step to estimate the wear of a plurality of available rail vehicles, and the step to select an operational scenario depending on a constraint related to the wear and necessary maintenance of the rail vehicles, must be executed when the program is run in the computer system. Such a computer program product may, in addition to the computer program itself, include additional components such as documentation and / or additional components, including hardware components such as hardware keys (dongles, etc.) for using the software.

[0018] For transport to the computer system or control unit and / or for storage on or in the computer system or control unit, a computer-readable medium, such as a memory stick, a hard drive, or other portable or permanently installed data carrier, can be used, on which the program sections of the computer program that can be read and executed by a computer system are stored. The computer system may, for example, include one or more cooperating microprocessors or similar components.

[0019] The dependent claims and the subsequent description each contain particularly advantageous embodiments and further developments of the invention. In particular, the claims of one claim category may also be further developed analogously to the dependent claims of another claim category and their descriptive parts.

[0020] In the inventive method for determining the time-dependent wear behavior of a technical component of a rail vehicle, the technical component preferably comprises a technical component for energy transmission. This energy transmission preferably includes the transmission of electrical and / or mechanical energy. During energy transmission, a multitude of dissipation phenomena occur, causing wear on the energy transmission component(s). The technical component also preferably comprises a component that moves relative to a contact element, which is preferably stationary. The energy transmission can encompass both the energy supply of the rail vehicle and a part of the traction process. During this relative movement, frictional effects occur, leading to wear of the technical component.The contact element is particularly well-suited to being part of the stationary railway infrastructure, with the technical component moving relative to the contact element. Since the wear of a technical component in direct contact with the infrastructure is generally route-dependent, it is particularly effective to estimate the future time-dependent wear behavior of a technical component of a rail vehicle based on a route-dependent wear profile, which is part of a digital twin of the technical component of the rail vehicle, and a future timetable for the rail vehicle.

[0021] Besides energy transfer at an interface between the rail vehicle and the infrastructure, such as an overhead line or the track itself, the technical component can also be part of a technical system installed inside the rail vehicle for electrical or mechanical energy transmission or conversion. Even with an internal technical component of a rail vehicle, varying stresses on the component depending on the route can have an individual impact on the extent of its wear.

[0022] The technical component preferably includes a grinding strip or a wheel profile.

[0023] The current wear status for the slip ring preferably includes information regarding the current wear condition or status of the slip ring. This information preferably includes the current slip ring thickness.

[0024] The current wear status of a wheel profile preferably includes information regarding the current wear condition or status of the wheel profile. Preferably, this information includes quantitative information regarding any deviation of the current wheel profile from the wheel profile of an unused wheel of a rail vehicle of the same type. Advantageously, the maintenance of these particularly wear-prone technical components can be optimized, and the deployment of rail vehicles can be tailored and optimized to the current and predicted wear of individual rail vehicles.

[0025] As already mentioned, the estimation of the future wear-related behavior of the technical components of the rail vehicle is based on the current wear status and the track-dependent wear profile of the rail vehicle, both of which are part of the stored digital twin. Advantageously, no additional investigation is required for the wear prediction; it is sufficient to query the current status data of the digital twin.

[0026] Preferably, the wear profile includes a digital rail network map to which location-dependent attributes are assigned that influence the wear profile. These location-dependent attributes enable the creation of a "wear map" that allows for the prediction of wear on a technical component depending on the chosen route of the rail vehicle. Location-dependent attributes can, for example, include the type of railway power network used, theAb The utilization rate of the overhead line and a location-dependent gradient or incline are included. A digital rail network map makes it possible to assign attributes to points or sections of track that influence the wear profile. Digital maps can be based on map data, for example, detailed map data available on the internet such as "Openrail" or "OpenStreetMap", which each represent routes as graphs.

[0027] The digital rail network map preferably represents the routes as graphs with edges connecting adjacent stations, preferably railway stations. The edges of the graph are preferably assigned track section-specific wear profile components. Advantageously, for a given timetable, the total wear can be calculated by adding the values ​​of track section-specific wear profile components from different track sections.

[0028] Alternatively, wear patterns can also be stored in nodes of a graph if a technical component is not subject to continuous wear, but rather to discrete, "intermittent" wear. Such instantaneous wear is preferably caused by a temporary disruption in the infrastructure, resulting in intermittent wear. This effect can occur, for example, with a defective or worn rail joint, or with the subsidence of sleepers. A worn overhead line can also produce such an effect. Pressure differences generated at tunnel entrances and exits, which create unwanted lateral forces and thus generate their own wear patterns, can also cause instantaneous wear.

[0029] The section-specific wear profile component preferably includes at least one of the following data types or depends on one of the following data types: Statistics on the wear and tear of the technical component, weather data, vehicle data.

[0030] Based on statistics regarding the wear and tear of the technical component that has occurred section by section, an expected value can be formed for the wear and tear of the technical component that will occur when a predetermined timetable is fulfilled.

[0031] Weather data provides information about current and expected weather conditions for adhering to a timetable. These weather conditions influence the wear and tear of a rail vehicle's technical components.

[0032] Vehicle data, or vehicle-specific data, also influences the expected wear of a technical component of a rail vehicle. For example, the wear of a contact strip and a wheel of a rail vehicle depends on the weight of the rail vehicle. Typical vehicle-specific characteristics include the type of pantograph used by a rail vehicle.

[0033] The vehicle data preferably includes at least one of the following data types: Vehicle characteristics, mission data, maintenance data.

[0034] The vehicle characteristics encompass individual properties of a rail vehicle, such as a vehicle version or vehicle type.

[0035] Mission data encompasses all data related to the individual operation of rail vehicles that influence the wear and tear of technical components. This includes, in particular, the routes traveled and their length and condition.

[0036] The maintenance data includes the current wear condition, preferably the sliding strip thickness or wheel tread thickness, and, if applicable, maintenance activities carried out or planned.

[0037] The type of track traveled influences the wear behavior of various technical components of a rail vehicle. For example, wheels and contact strips wear more on gradients than on level tracks. Wear on contact strips and wheels is also significantly increased at higher speeds. Wheel wear also depends on the geometry of the wheels and the track surface.

[0038] In addition to the direct storage of statistical data, functional relationships for calculating wear, either globally or for individual track sections, can also be stored in the digital twin. For example, as briefly mentioned earlier, the wear of a technical component can be represented as a linear or nonlinear function of a plurality of variables and parameters. Such parameters preferably include the length of a track section, the average speed of a rail vehicle on the track, and, specifically for a contact strip, the current density through the contact strip.

[0039] Alternatively or additionally, instead of a rigid model for the wear of a technical component depending on the variables and parameters influencing the wear, an artificial intelligence-based model can also be determined and stored. Typical methods for generating such a model include machine learning. Preferably, such a model is trained individually for a plurality of track segments, and particularly preferably for each track segment of a track network or each edge of a graph associated with the track network. For this purpose, so-called labeled training data is used, which contains both known values ​​of variables and parameters as input data and wear values ​​as labels that can be compared with the result data generated during training. Advantageously, such a model can even be retrained during a train journey.The model is updated when parameter values, variable values, and wear values ​​of the technical components are measured during or after the testing process, thus achieving increased accuracy and timeliness. It should be noted that the wear of a technical component, such as a sliding strip or a wheel tire, is generally less than the measurement tolerance of the instruments used to measure it. Therefore, wear can only be measured with the required accuracy after a number of trips over a section of the route. An artificial intelligence-based model offers the advantage of improved flexibility and scalability, as it automatically adapts to changing conditions and requires less data storage compared to determining expected wear based on statistics.

[0040] Such a model preferably includes a regressor. A regressor allows a functional relationship to be determined using statistical data.

[0041] In the inventive method for deployment planning, the constraint preferably includes the maximum maintenance capacities for the rail vehicles. Advantageously, by taking the maintenance capacities into account, a timetable-compliant train operation can be maintained.

[0042] Preferably, the constraint includes minimal maintenance requirements for the rail vehicles. This would be advantageous as it allows for savings in rail vehicle maintenance resources.

[0043] The secondary condition also preferably includes adherence to the timetable without maintenance. This approach aims to avoid the need to temporarily take vehicles out of service for maintenance. This method can be advantageous when very few rail vehicles are available and downtime due to maintenance needs to be avoided.

[0044] The constraint can also include adhering to the timetable with as few rail vehicles as possible. Simultaneous maintenance work on different vehicles should be kept to a minimum in order to keep as many vehicles as possible in service at the same time.

[0045] Preferably, the creation of the digital twin involves an automated determination of the extent of wear on the technical component. Advantageously, the creation of a wear twin can be done without any personnel effort.

[0046] The invention is explained in more detail below with reference to the accompanying figures and exemplary embodiments. The figures show: FIG 1 a graph representation of a train connection, illustrating the wear behavior of a contact strip of a rail vehicle, FIG 2 a diagram illustrating the dependence of wear behavior on a number of parameters, FIG 3 a flowchart illustrating an estimation of wear behavior based on an AI-based model, FIG 4 a flowchart illustrating a planning procedure according to an embodiment of the invention, FIG 5 a schematic representation of an estimating device according to an embodiment of the invention, FIG 6 a schematic representation of a planning device according to an embodiment of the invention.

[0047] In FIG 1 Figure 1 is a graph representing a section of a digital network map showing a train connection. Graph 1 illustrates the wear behavior of a contact strip on a rail vehicle. The train connection runs between Berlin (abbreviated B) via Leipzig (abbreviated L), Nuremberg (abbreviated N) to Munich (abbreviated M). Along the edges of the graph, wear profile components VK, VBL, VLN, and VNM, representing sections between the individual cities, are shown or arranged for a contact strip on a rail vehicle. Naturally, such wear data can also include information on the wear of multiple contact strips from different rail vehicles. The wear data can also include statistics on the wear of a contact strip for multiple rail vehicles. Furthermore, the Ab The usage profile represents a dependency of wear on current weather data or characteristic vehicle data. Therefore, based on the statistical data stored for each edge of the graph and, if applicable, functional relationships, and given knowledge of the vehicle type and the predicted weather, a statistically expected wear or a statistically expected wear profile of a specific rail vehicle intended to travel a predetermined route can be calculated. Is the ak If the specific thickness of a contact strip on a particular rail vehicle is known, it is possible to estimate, based on the aforementioned data, when the rail vehicle will require maintenance according to a predetermined timetable. The thickness of the contact strip is determined by the following factors: FIG 1 The graph representation shown represents the data collection, which is also referred to as the digital twin (DT) or the wear twin.

[0048] In FIG 2 Figure 200 shows a model representation, or nonlinear function, of wear A (in micrometers µm per kilometer km) as a function of variables and parameters, such as the speed v (in kilometers per hour h) and the electric current density J (in amperes A per square centimeter cm²) through the contact strip. This approach allows for the prediction of wear during a train journey on a predetermined track without having to directly access a database containing extensive statistics.

[0049] In FIG 3 A flowchart 300 is shown, which is a Ab An estimate of the wear behavior of a pantograph based on an AI-based model is illustrated.

[0050] In step 3.I, data regarding the wear profile A(P) of a pantograph type are collected for each section or edge of a graph representing a track map. A specific pantograph type is defined for each edge, depending on the power system used for the associated track. Therefore, if a pantograph of a first pantograph type must be used on a track section, it is not meaningful to also display values ​​for a second pantograph type that differs technically. Similarly, the type of railway power is defined for each track section, i.e., whether DC (direct current) or AC (alternating current) is used and at what voltage, e.g., 1.5 kV, 3 kV, 16.7 kV, or 25 kV, the railway power network operates in that section.However, for a longer planned route, different pantograph types and different types of traction current can be used by one and the same rail vehicle. Further parameters P that influence pantograph wear include the speed of the rail vehicle, weather data, and the train weight. The train weight affects the electrical current density J of the current flowing through the pantograph. Furthermore, pantograph wear depends on the length of the route and the electrical current density J across the pantograph's contact strip.

[0051] Instead of simply saving the aforementioned parameters and wear values, the following occurs in the FIG 3 In the illustrated embodiment, an artificial neural network KN is trained in step 3.II. The parameters P mentioned, such as the electrical current density J through the contact strip, the speed of the rail vehicle, the pantograph type, the train weight, weather data, the length of the track, etc., are used as input data and labeled with the measured output data, i.e., the associated wear values ​​of the wear profile A(P). The artificial neural network is trained to determine the associated output data based on the input data.

[0052] In step 3.III, the trained artificial neural network KN is used to predict the future wear behavior VV of a contact strip of a pantograph of a rail vehicle with a defined timetable FP.

[0053] In FIG 4 A flowchart 400 is shown, which illustrates a method for the deployment planning of rail vehicles according to an embodiment of the invention.

[0054] In step 4.I, this is already done in FIG 1 bis FIG 3 Illustrated procedures for estimating the future wear behavior VV of a plurality of available rail vehicles for different application scenarios of the rail vehicles to fulfill a predetermined timetable FP were carried out.

[0055] In step 4.II, an operational scenario ES is selected based on a constraint NB related to the expected future wear and tear VV and the necessary maintenance of the rail vehicles. Such a constraint could, for example, require minimal maintenance for the rail vehicles and adherence to the timetable.

[0056] In FIG 5 An estimation device 50 according to an embodiment of the invention is shown. The estimation device 50 comprises a database 51 for determining and storing a digital twin ZW of a technical component. The digital twin ZW comprises a current wear status VS and a route-dependent wear profile V for a technical component, in particular a contact strip, of a rail vehicle.

[0057] Furthermore, the estimating device 50 includes an estimating unit 52 for estimating the future time-dependent wear behavior VV of the rail vehicle depending on a future timetable FP of the rail vehicle, the current wear status VS and the route-dependent wear profile V of the rail vehicle in question.

[0058] In FIG 6 A planning device 60 according to an embodiment of the invention is illustrated. The planning device 60 comprises the following: FIG 5The estimating device 50 shown is part of the planning device 60 and also includes a selection unit 61 for selecting an operational scenario ES depending on a constraint NB related to the wear and tear and necessary maintenance of the available rail vehicles. The selection unit 61 queries the estimating device 50 for the digital twins ZW of the individual rail vehicles in an available fleet FUP. The digital twins ZW comprise a current wear status VS of one or more technical components of the individual rail vehicles in the fleet FUP and the respective wear profile V of each rail vehicle.Based on the digital twins ZW of the individual rail vehicles 1 of the fleet FUP, a timetable FP, and a predefined constraint NB, which, in addition to the main condition that no rail vehicle may be used beyond its wear limit, specifies a further optimization goal, selection unit 61 determines an operational plan or operational scenario ES for the optimal use of the fleet FUP. The constraint NB could, for example, state that minimal maintenance effort should be required.

[0059] Finally, it should be noted once again that the methods and devices described above are merely preferred embodiments of the invention and that the invention can be varied by a person skilled in the art without departing from the scope of the invention, insofar as it is defined by the claims. For the sake of completeness, it should also be noted that the use of the indefinite articles "a" or "an" does not preclude the possibility that the features in question may be present multiple times. Likewise, the term "unit" does not preclude the possibility that it consists of several components, which may also be spatially distributed.

Claims

1. Method for determining a time-dependent wear behaviour (VV) of a technical component of a rail vehicle, said method comprising the following steps: - determining and storing a digital twin (ZW) of the technical component with a current wear state (VS) and a line-dependent wear profile (V) of the technical component, said profile indicating a location-dependent measure of the wear of the technical component, - estimating the future time-dependent wear behaviour (VV) of the technical component of the rail vehicle depending on a future timetable (FP) of the rail vehicle, according to which the rail vehicle is used on particular lines, and based on the digital twin (ZW).

2. Method according to Claim 1, wherein the technical component includes a contact strip or a wheel profile.

3. Method according to either one of the preceding claims, wherein the wear profile (V) is determined using a digital rail network map with which location-dependent attributes which influence the wear behaviour of the technical component are associated.

4. Method according to Claim 3, wherein the digital rail network map depicts lines as a graph with edges as the connection between adjacent stations.

5. Method according to Claim 4, wherein a line-related wear profile component (VK), which indicates the average wear of a technical component during a journey over a specific line section, is associated with each of the edges of the graph.

6. Method according to Claim 5, wherein the line-related wear profile component (VK) includes at least one of the following data types or is dependent on one of the follow data types: - a statistic about the wear of the technical component, - weather data, - vehicle data.

7. Method for planning the use of rail vehicles, said method comprising the following steps: - estimating a future wear behaviour (VV) of a plurality of available rail vehicles for different use scenarios (ES) of the rail vehicles in order to observe a predetermined timetable (FP) using the method according to any one of Claims 1 to 6, - selecting a use scenario (ES) depending on a secondary condition (NB) related to the wear behaviour (VV) and the required maintenance of the rail vehicles.

8. Method according to Claim 7, wherein the secondary condition (NB) includes the maximum maintenance capacities for the rail vehicles.

9. Method according to Claim 7 or 8, wherein the secondary condition (NB) includes observing the timetable (FP) with minimal maintenance outlay.

10. Method according to any one of Claims 7 to 9, wherein the secondary condition (NB) includes observing the timetable (FP) with the lowest possible number of rail vehicles.

11. Estimation device (50), comprising: - a database (51) for determining and storing a digital twin (ZW) of a technical component of a rail vehicle with a current wear state (VS) and a line-dependent wear profile (V) of the technical component, said profile indicating a location-dependent measure of the wear of the technical component, - an estimation unit (52) for estimating the future time-dependent wear behaviour (VV) of the rail vehicle depending on a future timetable (FP) of the rail vehicle, according to which the rail vehicle is used on particular lines, and based on the digital twin (ZW).

12. Planning device (60), comprising: - an estimation device (50) according to Claim 11 for estimating a future wear behaviour (VV) of a plurality of available rail vehicles for different use scenarios (ES) of the rail vehicles in order to observe a predetermined timetable (FP), - a selection unit (61) for selecting a use scenario (ES) depending on a secondary condition (NB) related to the wear behaviour (VV) and the required maintenance.

13. Computer program product having a computer program which can be loaded directly into a memory unit, having program sections to execute the steps of a method according to any one of Claims 1 to 6 in an estimation device according to Claim 11 or to execute the steps of a method according to any one of Claims 7-10 in a planning device according to Claim 12 when the computer program is executed.

14. Computer-readable medium on which program sections which can be executed by a computation unit are stored to execute the steps of a method according to any one of Claims 1 to 6 in an estimation device according to Claim 11 or to execute the steps of a method according to any one of Claims 7-10 in a planning device according to Claim 12 when the program sections are executed by the computation unit.

Images