METHOD AND APPARATUS FOR IDENTIFYING FAULTS FOR A TECHNICAL SYSTEM

Abstract

A method and an apparatus for identifying faults in a computer-aided manner for a technical system including a switch and a switch drive is provided. A fault or a disruption in the switch and/or in the switch drive is detected by capturing a temporal profile of a measurement variable of the switch drive. A simulation model is provided for the technical system and a fault situation is set by means of setting values of the simulation model, wherein the setting values are assigned to the fault situation. The technical system is simulated by means of the simulation model, wherein a simulated temporal profile of the measurement variable is captured. The simulated temporal profile is compared with the temporal profile of the measurement variable of the switch drive, wherein the fault situation is assigned to the detected fault on the basis of the comparison.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to European application No. 18164710.8, having a filing date of Mar. 28, 2018, the entire contents of which are hereby incorporated by reference.

FIELD OF TECHNOLOGY

The following relates to a method and an apparatus for identifying faults in a computer-aided manner for a technical system comprising a switch and a switch drive.

BACKGROUND

Switches and switch drives are central elements of the route in rail traffic. To ensure an operating procedure as permanently as possible, requirements imposed on the functionality of the switch/switch drive system are generally high. Disruptions or faults in the switch and/or the switch drive can greatly restrict the operation of the rail traffic.

It is known practice to monitor a rail infrastructure and to check the functionality of a switch and its drive using sensors, for example. In particular, diagnostic systems which can detect a fault in the system and/or in the operation of the system by means of sensors, an evaluation unit and a computer are known. For this purpose, a power consumption of the switch drive, that is to say a temporal profile of the power consumed during an actuating operation for example, can be monitored. A fault, for example a blockage on account of an obstacle in a switch, can be detected, for example, if the power consumption exceeds or undershoots a predefined threshold value. A fault can generally be rectified only after an inspection and a search for the cause of the fault, for example by a service engineer. This can often be very time-consuming and may result in an interruption in operation. In addition, the identification of individual causes of faults is often not practical since only the result state of the faulty system may be available.

SUMMARY

An aspect relates to the identification of causes of faults for a system comprising a switch and a switch drive assigned to the switch.

The aspect is achieved by means of a method, an apparatus, a computer program product (non-transitory computer readable storage medium having instructions, which when executed by a processor, perform actions), and a computer-readable storage medium

A first aspect relates to a method for identifying faults in a computer-aided manner for a technical system comprising a switch and a switch drive, having the method steps of:

• • detecting a fault in the switch and/or in the switch drive by capturing a temporal profile of a measurement variable of the switch drive,
  • providing a simulation model for the technical system and setting a fault situation by means of the setting values of the simulation model, wherein the setting values are assigned to the fault situation,
  • simulating the technical system by means of the simulation model, wherein a simulated temporal profile of the measurement variable is captured,
  • comparing the simulated temporal profile of the measurement variable with the temporal profile of the measurement variable of the switch drive, wherein the fault situation is assigned to the detected fault on the basis of the comparison result,
  • identifying a cause of the detected fault on the basis of the setting values of the simulation model and on the basis of the comparison result,
  • outputting the identified cause of the fault.

An advantage of the method according to embodiments of the invention is that the cause of a detected fault in the technical system can be identified by simulating the technical system which comprises a switch and at least one switch drive. The embodiments are directed, in particular, to rail systems, for example railroad switches and switch drives. A fault can be identified, in particular, remotely, that is to say without locally examining the technical system. This enables, for example, faster maintenance of the switch and of the switch drive in the event of a disruption and can prevent a relatively long operational interruption, in particular.

The technical system can be simulated, in particular, under a known fault condition. A simulated fault situation can be assigned to the detected fault on the basis of the comparison result, in particular if the simulated temporal profile corresponds to the measured temporal profile of the measurement variable within a tolerance range, for example.

In connection with embodiments of the invention, “computer-aided” can be understood as meaning, for example, an implementation of the method in which a processor, in particular, carries out at least one step of the method.

A fault or a disruption in the switch/switch drive system can be detected by monitoring a temporal profile of a measurement variable of the switch drive. For example, the power consumption of the switch drive can be monitored, and a fault can be detected if the power consumption exceeds or undershoots a threshold value. A quick analysis of the cause of the fault, for example an analysis in real time, can be carried out by simulating the system.

A simulation model of the switch and of the at least one switch drive is provided. To identify the cause of the fault, the simulation model can be used to simulate a predefined fault situation, for example a blockage of the operation of actuating the switch by an obstacle. A “fault situation” can be understood as meaning, for example, a combination of one or more individual causes of faults, wherein setting values of the simulation model are assigned to the fault situation. In other words, the fault situation can be based on individual causes of faults. A cause of a fault can be derived from the setting values.

The technical system can be simulated taking into account the fault situation and a simulated temporal profile of a measurement variable can be captured. A measurement variable, for which there is a measurement or a temporal profile of the actual temporal system, is investigated in the simulation. The fault situation can be predefined and can be set by means of setting values for the simulation model. In particular, the setting values can be assigned to the fault situation and a cause of a fault, for example an obstacle in the switch or sluggish movement of individual moving parts, can be represented thereby. The setting values of the simulation model can therefore be selected to reproduce this fault situation.

The operations of actuating the switch can be simulated by means of the simulation model and the temporal profile of a measurement variable can be determined from the simulation. A cause of a fault can be identified on the basis of the comparison with the temporal profile of the measurement variable of the actual switch drive. For example, a measured load curve and a simulated load curve can be compared with one another. For example, the comparison may reveal a correspondence of the two temporal profiles within a predefined range of values and the fault situation can be determined as the cause of the detected fault or can be assigned to the latter. A plurality of causes of faults can be determined and output on the basis of the setting values of the simulation model. It is possible to assign a probability value to the comparison, on the basis of which value the cause of the fault can be identified.

In an advantageous embodiment of the method, the simulation model can represent an electronic and/or a mechanical component of the switch and of the switch drive.

The simulation model of the technical system comprising a switch and at least one switch drive may comprise, in particular, detailed modeling of the mechanics and/or electronics of the system. The physics and the operating principles of the technical system can be represented by means of the simulation model and fault situations can thus be analyzed. Operations of actuating the switch can be simulated and the temporal profile of a measurement variable can be determined therefrom.

In one advantageous embodiment, more than one fault situation can be set, and the simulated temporal profile of the measurement variable can be respectively captured and, on the basis of the comparison with the temporal profile of the measurement variable of the switch drive in each case, that simulated temporal profile with the smallest deviation can be selected.

More than one fault situation can be provided and can be set in the simulation model by means of assigned setting values. A plurality of fault situations of the technical system can be set and simulated in succession. In other words, the technical system can be repeatedly simulated under different known fault conditions. For each simulation with a set fault situation, a simulated temporal profile of the measurement variable can accordingly be determined in each case. That simulated fault situation whose associated simulated temporal profile exhibits the smallest deviation from the measured temporal profile, that is to say exhibits the best correspondence in the comparison for example, can be determined on the basis of a comparison with the measured temporal profile of the measurement variable of the switch drive. For example, the deviation can be used to determine a probability value which indicates the probability of a cause of a fault being able to be assigned to the detected fault. This embodiment of the method can be used to determine the cause of the fault on which the detected fault is based with a high degree of probability.

In an advantageous embodiment, a faulty component of the technical system can be determined on the basis of the simulated temporal profile of the measurement variable and the identified cause of the fault.

The simulation model can represent individual software and/or hardware components of the technical system. A component of the technical system in which the fault occurs, for example, or which is faulty can be identified on the basis of the setting values assigned to the fault situation.

In one advantageous embodiment, sensor data can be captured and evaluated as measurement variables of the technical system by means of a detection module.

The technical system comprises sensors for monitoring measurement variables of the individual components, for example of the switch drive. A detection module can capture and evaluate the sensor data, for example, and can determine a fault in the technical system from the evaluation. The technical system is monitored continuously and the sensor data are evaluated promptly or in real time.

In one advantageous embodiment, the simulation model can be created and/or calibrated on the basis of a configuration and/or on the basis of conditions of use and/or environmental data and/or sensor data of the technical system.

Before simulating the system, the simulation model can be adapted to actual conditions and can be accordingly calibrated. For example, sensor data may provide current information relating to the technical system to be simulated which can be set by means of setting values of the simulation model. The simulation can therefore represent, in particular, the actual system, for example special properties. The search for the cause of the fault can therefore be improved.

In one advantageous embodiment, measures for rectifying the fault in the switch and/or in the switch drive can be determined and initiated by outputting the identified cause of the fault.

The output of the identified cause of the fault can be used to initiate measures for rectifying the fault. For example, a suitable measure can be determined, and/or a faulty component can be identified on the basis of the cause of the fault. Fast maintenance can therefore be achieved. In particular, efficient remote maintenance can therefore be carried out for a switch system which is difficult to access.

In one advantageous embodiment, the identified cause of the fault can be stored in a database and/or in a storage unit.

The identified cause of the fault can be recorded in a list or a catalog. The stored cause of the fault can be used, for example, to search for a cause of a fault in the event of future disruptions in the same system or in a similar technical system. For example, a description of the identified cause of the fault, for example the environmental information, can be additionally stored. It is also possible to use stored causes of faults as an input for subsequent fault identification, in the form of a fault situation, for the simulation model. The identification of faults can be accelerated with known inputs by means of simulation.

Another aspect of embodiments of the invention relates to an apparatus for identifying faults in a computer-aided manner for a technical system comprising a switch and a switch drive, comprising:

• • a detection module for detecting a fault in the switch and/or in the switch drive by capturing a temporal profile of a measurement variable of the switch drive,
  • a simulation module for providing a simulation model for the technical system and for setting a fault situation by means of setting values of the simulation model, wherein the setting values are assigned to the fault situation, and for simulating the technical system by means of the simulation model, wherein a simulated temporal profile of the measurement variable is captured,
  • a comparison module for comparing the simulated temporal profile of the measurement variable with the temporal profile of the measurement variable of the switch drive, wherein the fault situation is assigned to the detected fault on the basis of the comparison result,
  • an identification module for identifying a cause of the detected fault on the basis of the setting values of the simulation model and on the basis of the comparison result,
  • an output module for outputting the identified cause of the fault.

An apparatus according to embodiments of the invention may be in the form of a software and/or hardware module.

In one advantageous embodiment, the apparatus comprises sensors for capturing sensor data of the technical system.

Sensors capture temporal profiles of measurement variables of the technical system continuously and/or regularly. For example, a power consumption can be captured over time by means of a sensor on the switch drive.

In one advantageous embodiment, the simulation module can be set up to create and/or calibrate the simulation model on the basis of a configuration and/or on the basis of conditions of use and/or environmental data and/or sensor data of the technical system.

In one advantageous embodiment, the apparatus comprises a storage unit and/or a database for storing an identified cause of the fault.

Another aspect of embodiments of the invention relates to a computer program product which can be directly loaded into a programmable computer, comprising program code parts which are suitable for carrying out the steps of the method according to embodiments of the invention, and to a computer-readable storage medium.

BRIEF DESCRIPTION

Some of the embodiments will be described in detail, with references to the following Figures, wherein like designations denote like members, wherein:

FIG. 1 shows, in the form of a flowchart, one exemplary embodiment of the method according to embodiments of the invention for identifying faults in a computer-aided manner for a technical system;

FIG. 2 shows, in the form of a flowchart, another exemplary embodiment of the method according to embodiments of the invention for identifying faults in a computer-aided manner for a technical system; and

FIG. 3 shows a block diagram of an exemplary embodiment of the apparatus according to embodiments of the invention for identifying faults in a computer-aided manner for a technical system.

Mutually corresponding objects are provided with the same reference signs in all figures.

DETAILED DESCRIPTION

FIG. 1 shows, in the form of a flowchart, one exemplary embodiment of the steps of the method according to embodiments of the invention. The exemplary embodiment relates to a rail system comprising a switch and a switch drive. In step S1, a fault or a disruption in the system is captured by means of a detection module. For example, the fault may cause a failure of the switch controller, with the result that sensors on the switch drive detect a fall in the temporal profile of the power consumption. The detected fault comprises the failure of the switch system, for example. The sensors can also capture, for example, temperature, pressure, acceleration or voltage.

In step S2, a simulation model of the technical system comprising the switch and the associated switch drive is provided. The simulation model can be set on the basis of a configuration and/or on the basis of conditions of use and/or environmental data and/or sensor data of the technical system. In other words, setting values of the simulation model can be adapted to the system to be simulated. In particular, a simulation model can be adapted to a particular switch/switch drive system, for example with special environmental conditions or a particular maintenance state.

A fault situation is predefined and is set up by setting the setting values of the simulation model. The technical system is simulated by means of the simulation model in which the fault situation has been set. For example, an operation of actuating a switch can be simulated, wherein the fault situation comprises an obstacle in the switch. Consequently, the simulation is carried out in step S3 taking into account the obstacle and a simulated temporal profile of a measurement variable, for example power consumption, is captured.

In step S4, the simulated temporal profile of the measurement variable is compared with the measured temporal profile which is continuously provided by a sensor, for example. A fault situation can be assigned to a detected fault if a deviation between the two temporal profiles falls within a predefined tolerance range. In other words, in the case of a particular similarity of the temporal profiles, the detected fault can be declared with a particular degree of probability with the simulated fault situation.

If the comparison reveals that the predefined fault situation results in a simulated temporal profile which can reproduce the measured temporal profile, at least one cause of a fault can be determined from the fault situation. For this purpose, it is determined in step S5, on the basis of the comparison, that the fault situation is the cause of the detected fault, for example with a statement of the probability, and the at least one cause of the fault can be identified on the basis of the setting values.

The identified cause of the fault is output in step S6. Measures for rectifying the fault can then be initiated. In particular, individual faulty components of the technical system can be determined on the basis of the comparison, with the result that measures can be derived and implemented only for this component.

The method according to embodiments of the invention can also be used, for example, for early fault detection if, for example, an abnormal temporal profile of a measurement variable is captured by a sensor, but a fault is not detected in this case. For example, a change in the temporal profile of a measurement variable can already indicate a future fault. Causes of faults can be determined by means of comparison with a simulated temporal profile according to a predefined fault situation before serious disruptions, for example operational failures, occur.

FIG. 2 shows, in the form of a flowchart, another exemplary embodiment of the method according to embodiments of the invention. The individual method steps are similar to the steps described in FIG. 1. After comparing the simulated temporal profile with the measured temporal profile of a measurement variable, see step S4, a fault situation can be predefined again and the simulation can be carried out, see steps S2 and S3. For example, the comparison may reveal that the selected fault situation results in a simulated temporal profile which cannot reproduce the measured temporal profile within a tolerance range. To optimize the identification of faults, steps S2 to S4 can be repeated as often as desired with different fault situations. It is therefore possible to determine that fault situation whose simulation can reproduce the detected fault in such a manner that the deviation between the simulated temporal profile and the measured temporal profile of the measurement variable is smallest.

In other words, that fault situation for which the simulated temporal profile exhibits the smallest deviation from the measured temporal profile of the corresponding measurement variable is selected.

For example, determined fault situations can be stored in a database and/or a storage unit and can be used for an analysis, in particular a subsequent analysis, of a detected fault.

FIG. 3 shows a block diagram of an exemplary embodiment of the apparatus (100) according to embodiments of the invention. The apparatus (100) comprises a detection module (101), a simulation module (102), a comparison module (103), an identification module (104), an output module (105) and a storage unit (106) or a database (107). The apparatus comprises a processor (108) for carrying out at least one step of the method according to embodiments of the invention. The individual modules are connected to one another in a wired or wireless manner. The apparatus is connected to the actual switch/switch drive system and/or to sensors of the system via a communication connection C.

The apparatus may comprise, in particular, sensors for monitoring measurement variables in the technical system. A fault can be detected on the basis of a measured temporal profile of a measurement variable by means of the detection module (101).

The simulation module (102) is set up to provide a simulation model of the mechanics of the technical system, in particular of the components of the switch and of the switch drive, and therefore to simulate the system. A simulated temporal profile of a measurement variable can be determined on the basis of the simulation.

The comparison module (103) determines the deviation of the simulated temporal profile from the measured temporal profile of a measurement variable and outputs a degree of correspondence or a probability value, for example. The deviation of the two temporal profiles can be investigated using statistical methods, for example.

On the basis of the comparison result, the identification module (104) outputs a fault situation as the cause of the detected fault. One or more causes of faults can be identified on the basis of the setting values of the simulation model which are assigned to the fault situation.

The output module (105) outputs the one or more identified causes of faults. For example, the causes of faults are stored in the storage unit (106) and/or the database (107). Measures for rectifying faults can be derived on the basis of the causes of faults.

Although the present invention has been disclosed in the form of preferred embodiments and variations thereon, it will be understood that numerous additional modifications and variations could be made thereto without departing from the scope of the invention.

For the sake of clarity, it is to be understood that the use of ‘a’ or ‘an’ throughout this application does not exclude a plurality, and ‘comprising’ does not exclude other steps or elements.

Claims

1. A method for identifying faults in a computer-aided manner for a technical system comprising a switch and a switch drive, the method comprising:

detecting a fault in the switch and/or in the switch drive by capturing a temporal profile of a measurement variable of the switch drive;

providing a simulation model for the technical system and setting a fault situation by means of setting values of the simulation model, wherein the setting values are assigned to the fault situation;

simulating the technical system by means of the simulation model, wherein a simulated temporal profile of the measurement variable is captured;

comparing the simulated temporal profile of the measurement variable with the temporal profile of the measurement variable of the switch drive, wherein the fault situation is assigned to the detected fault on a basis of a comparison result;

identifying a cause of the detected fault on the basis of the setting values of the simulation model and on the basis of the comparison result; and

outputting the identified cause of the fault.

2. The method as claimed in claim 1, wherein the simulation model represents an electronic and/or a mechanical component of the switch and of the switch drive.

3. The method as claimed in claim 1, wherein more than one fault situation is set and the simulated temporal profile of the measurement variable is respectively captured and, on the basis of the comparison with the temporal profile of the measurement variable of the switch drive in each case, that simulated temporal profile with the smallest deviation is selected.

4. The method as claimed in claim 1, wherein a faulty component of the technical system is determined on the basis of the simulated temporal profile of the measurement variable and the identified cause of the fault.

5. The method as claimed in claim 1, wherein sensor data are captured and evaluated as measurement variables of the technical system by means of a detection module.

6. The method as claimed in claim 1, wherein the simulation model is created and/or calibrated on the basis of a configuration and/or on the basis of conditions of use and/or environmental data and/or sensor data of the technical system.

7. The method as claimed in claim 1, wherein measures for rectifying the fault in the switch and/or in the switch drive are determined and initiated by outputting the identified cause of the fault.

8. The method as claimed in claim 1, wherein the identified cause of the fault is stored in a database and/or in a storage unit.

9. An apparatus for identifying faults in a computer-aided manner for a technical system comprising a switch and a switch drive, the apparatus comprising:

a detection module for detecting a fault in the switch and/or in the switch drive by capturing a temporal profile of a measurement variable of the switch drive;

a simulation module for providing a simulation model for the technical system and for setting a fault situation by means of setting values of the simulation model, wherein the setting values are assigned to the fault situation, and for simulating the technical system by means of the simulation model, wherein a simulated temporal profile of the measurement variable is captured;

a comparison module for comparing the simulated temporal profile of the measurement variable with the temporal profile of the measurement variable of the switch drive, wherein the fault situation is assigned to the detected fault on the basis of the comparison result;

an identification module for identifying a cause of the detected fault on the basis of the setting values of the simulation model and on the basis of the comparison result; and

an output module for outputting the identified cause of the fault.

10. The apparatus as claimed in claim 9, comprising sensors for capturing sensor data of the technical system.

11. The apparatus as claimed in claim 9, wherein the simulation module is set up to create and/or calibrate the simulation model on the basis of a configuration and/or on the basis of conditions of use and/or environmental data and/or sensor data of the technical system.

12. The apparatus as claimed in claim 8, further comprising a storage unit and/or a database for storing an identified cause of the fault.

13. A computer program product, comprising a computer readable hardware storage device having computer readable program code stored therein, said program code executable by a processor of a computer system to implement a method as claimed in claim 1.

14. A computer-readable storage medium having a computer program product as claimed in claim 13.