Maintenance system and method for analyzing functional failures of a system

• US 10,198,303 B2
• Filed: 08/29/2016
• Issued: 02/05/2019
• Est. Priority Date: 10/15/2015
• Status: Active Grant

• Current Assignee: Siemens AG
• Original Assignee: Siemens AG
• Inventors: Hofig, Kai, Joanni, Andreas, Montrone, Francesco
• Primary Examiner(s): Patel, Kamini B
• Application Number:
  US15/249,729
• Publication Number:
  US 20170109223A1
• Time in Patent Office: 890 Days
• Field of Search: 714 473
• CPC Class Codes: G05B 23/0283 Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06
• CPC Class Codes: G06F 11/0721 within a central processing unit [CPU]
• CPC Class Codes: G06F 11/079 Root cause analysis, i.e. error or fault diagnosis in a hardware test environment G06F11/22; in a software test environment G06F11/36
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

A method for analyzing functional failures of a technical system using a processor to compute a meta data model, including the following steps is provided. A first step of gathering at least one failure mode for each component of a system dataset describing the technical system. A second step of associating at least one effect and at least one related maintenance task with each failure mode to mitigate and/or to dissolve the effect in the meta data model. A third step of computing failure probabilities of said technical system based on the meta data model, while the technical system is in the specific situation.

Claims

1. A method for analyzing functional failures of a technical system, wherein a processor computes a meta data model by executing the following steps:

gathering at least one failure mode for each component of a system dataset describing said technical system;

associating at least one effect and at least one related maintenance task with each failure mode to mitigate and/or to dissolve said effect;

at least one situation dataset with said system dataset reflecting conditions of a specific situation while said technical system is operating;

a design reliability dataset indicating a first probability with each failure mode defined during a design time of the technical system;

a situation reliability dataset indicating a second probability with a failure mode defined by the at least one situation dataset in the meta data model; and

computing failure probabilities of said technical system based on said meta data model, while the technical system is in the specific situation; and

wherein said technical system comprises at least one sensor to acquire the at least one situation dataset or to create a new situation dataset and updating the meta data model with the at least one situation dataset or the new situation dataset.

2. The method according to claim 1, wherein said system dataset comprises at least one subsystem and each component is a part of the at least one subsystem.

3. The method according to claim 1, wherein the at least one situation dataset defines at least one situation task to mitigate and/or to dissolve a failure mode caused by the specific situation.

4. The method according to claim 1, wherein the at least one effect is associated with at least one design task to mitigate said effect.

5. The method according to claim 4, wherein the at least one maintenance task comprises of the at least one design task and/or the at least one situation task.

7. The method according to claim 1, wherein the situation dataset includes weather conditions, vibration, noise, radiation, and/or a combination thereof.

8. The method according to claim 1, wherein the method is a failure mode and effects analysis.

10. The method according to claim 1, wherein if a situation reliability dataset is available for a failure mode it replaces a design reliability dataset for that failure mode;

and a situation reliability dataset is unavailable for a failure mode preferably the design reliability dataset is used for that failure mode to compute the failure probabilities of said technical system.

11. The method according to claim 3, wherein if a situation task is available to mitigate and/or to dissolve a failure mode it replaces the design task for that failure mode;

and a situation task is unavailable to mitigate and/or to dissolve a failure mode preferably the design task is used to mitigate and/or to dissolve that failure mode and/or an effect associated with that failure mode.

16. 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 according claim 1.

17. A providing device for the computer program product according to claim 16, wherein the providing device provides and/or saves the computer program product.

6. A method for analyzing functional failures of a technical system, wherein a processor computes a meta data model by executing the following steps:

gathering at least one failure mode for each component of a system dataset describing said technical system;

associating at least one effect and at least one related maintenance task with each failure mode to mitigate and/or to dissolve said effect;

at least one situation dataset with said system dataset reflecting conditions of a specific situation while said technical system is operating;

a design reliability dataset indicating a first probability with each failure mode defined during a design time of the technical system;

a situation reliability dataset indicating a second probability with a failure mode defined by the at least one situation dataset in the meta data model;

computing failure probabilities of said technical system based on said meta data model, while the technical system is in the specific situation; and

wherein said technical system comprises at least one sensor to acquire the at least one situation dataset or to create a new situation dataset, the at least one situation dataset or the new situation dataset is preferably transmitted to a centralized maintenance station, the centralized maintenance station updates the meta data model with the at least one situation dataset or the new situation dataset, the centralized maintenance station computes the failure probabilities of said technical system, while the technical system is in the specific situation, and the centralized maintenance station preferably computes the failure probabilities of at least one other technical system, while the at least one other technical system is in a specific situation.

9. The method according to claim 6, wherein the analysis is conducted for at least one other technical system, and for each analysis a separate meta data model is computed.

12. A maintenance system for analyzing the functional failures of at least one technical system, comprising:

a processor to compute a meta data model;

a database unit to store the meta data model;

a gathering unit to gather at least one failure mode for each component of a system dataset describing said technical system;

an association unit to associate in the meta data model at least one effect and at least one related maintenance task with each failure mode to mitigate and/or to dissolve said effect;

at least one situation dataset with said system dataset reflecting conditions of a specific situation while said technical system is operating;

a design reliability dataset indicating a first probability with each failure mode defined during a design time of the technical system;

a situation reliability dataset indicating a second probability with a failure mode defined by the specific situation;

a computation unit to compute by the processor failure probabilities of said technical system based on said meta data model while said technical system is in the specific situation; and

updating the meta data model with the at least one specific situation or a new situation dataset while said technical system is in the specific situation.

13. The maintenance system according to claim 12, wherein said system dataset comprises at least one subsystem and each component is a part of the at least one subsystem, wherein the at least one situation dataset preferably defines at least one situation task to mitigate and/or to dissolve a failure mode caused by the specific situation, the at least one effect is associated with at least one design task to mitigate said effect.

14. The maintenance system according to claim 12, wherein the maintenance system is connected by means of a network with said technical system, the maintenance system is connected by means of the network with at least one other technical system to analyze the functional failures of the at least one other technical system.

15. The maintenance system according to claim 14, wherein the functional failures are analyzed for at least one another technical system, and for the analyzed at least one other technical system a separate meta data model is computed.