Remote diagnosis modelling

• US 8,543,282 B2
• Filed: 05/12/2008
• Issued: 09/24/2013
• Est. Priority Date: 05/14/2007
• Status: Active Grant

• Current Assignee: Volvo Truck Corporation (AB Volvo)
• Original Assignee: Volvo Technology Corporation
• Inventors: Byttner, Stefan, Hansson, Jrgen, Svensson, Magnus, Rgnvaldsson, Thorsteinn
• Primary Examiner(s): FRISBY, KEITH J
• Application Number:
  US12/600,260
• Publication Number:
  US 20100174444A1
• Time in Patent Office: 1,961 Days
• Field of Search: 701/29.3, 701/29.1, 701/29.4, 701/30.2, 701/30.5, 701/30.6, 701/30.7, 701/31.4, 701/32.1, 701/32.9, 701/33.4, 701/33.7, 701/31.9, 702/34
• US Class Current: 701/29.3
• CPC Class Codes: G06F 11/0751 Error or fault detection not based on redundancy power supply failures G06F1/30; network fault management H04L41/06
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling

Abstract

A diagnosis and maintenance method, a diagnosis and maintenance assembly comprising a central server and a system, and a computer program for diagnosis and maintenance for a plurality of systems, particularly for a plurality of vehicles, wherein each system provides at least one system-related signal which provides the basis for the diagnosis and/or maintenance of/for the system are provided. The basis for diagnosis and/or maintenance is determined by determining for each system at least one relation between the system-related signals, comparing the compatible determined relations, determining for the plurality of systems based on the result of the comparison which relations are significant relations and providing a diagnosis and/or maintenance decision based on the determined significant relations.

Claims

1. A method for providing diagnosis and/or maintenance for a plurality of systems, each system providing a plurality of system-related signals, the method comprising:

determining, for the plurality of system-related signals for the plurality of systems, relations between a plurality of the plurality of system-related signals;

comparing the plurality of determined relations between the plurality of the system-related signals;

determining, based on the comparison, which of the determined relation are significant relations; and

providing a diagnosis and/or maintenance decision based on the determined significant relations.

2. The method according to claim 1, wherein the step of determining the plurality of relations is performed

between the same system-related signals at different points in time and/or

between different system-related signals at the same point in time and/or at different points in time.

3. The method according to claim 1, wherein at least one of the plurality of relations is a linear or non-linear correlation, and/or at least one of the plurality of relations is particularly expressed by histogramming or clustering with or without topological information.

4. The method according to claim 1, further comprising at least one of the additional steps of:

defining a norm for the determined significant relations, particularly by comparing the significant relations for the plurality of systems,

detecting a deviation from the norm, and

determining a significance of the deviation from the norm, wherein the steps of detecting a deviation and determining its significance are performed by statistical methods, wherein the step of determining a significance of the deviation is performed by a statistical confidence test.

5. The method according to claim 4, wherein the diagnosis and/or maintenance decision is provided for an individual system from the plurality of systems, wherein the diagnosis and/or maintenance decision is provided based on the detected deviation of a significant relation from its norm.

6. The method according to claim 1, wherein the determination of the plurality of relations is performed by fitting a model to the signals, wherein the model, associated model parameters, a model output and a fitting quality are defined.

7. The method according to claim 6, further comprising at least one of the additional steps of

performing a cross-validation for the fitted models

determining a variance of the fitted models within the plurality of systems, wherein the determination of the significant relation preferably takes into account the fitting quality of the model and/or the variance of the models.

8. The method according to claim 6, wherein the step of defining, the norm comprises:

defining norm values for the model parameters and/or the model output, wherein said norm values are determined from the model parameters and/or model outputs of all systems.

9. The method according to claim 8, wherein the norm values for the model parameter and/or model outputs are defined by statistical methods, particularly calculating average values M, wherein M=[a b c] and a, b, c =model parameters/outputs, and/or covariance matrices for the model parameter/outputs of all systems, and wherein the significant deviation from the norm is defined if the model parameters and/or outputs are outside an allowed range defined by a suitable parameterised distribution.

10. The method according to claim 6, wherein the determination of the plurality of relations and/or the fitting, of the model is performed by each system itself, and the other steps are performed by a service centre, wherein the service centre sends a request for the determination of the relation to each system.

11. The method according to claim 1, wherein the significant relations are monitored for detecting a deviation from the norm, wherein the monitoring is performed by constantly fitting different models, selecting a suitable model from the fitted models and comparing the model parameters of the suitable fitted model to norm values.

12. The method according to claim 1, wherein the plurality of system-related signals for which relations are determined are randomly and/or deterministically selected.

13. The method according to claim 1, wherein the system is a mechatronic or electronic system.

14. An assembly for performing diagnosis and maintenance, comprising:

at least two systems for which diagnosis and/or maintenance are performed, wherein each system of the at least two systems provides a plurality of system-related signals, the at least two systems being adapted to determine a plurality of relations between the system-related signals, and

a central server including

a comparison unit for comparing the plurality of determined relations;

a determination unit for determining based on the result of the comparison which of the determined relations are significant relations;

a diagnosis/maintenance unit for providing a diagnosis and/or maintenance decision based on the determined significant relations.

15. The assembly according to claim 14, wherein both the central server and each system of the at least two systems further each include a communication device, wherein the communication device of the central server is adapted to transmit to each system of the at least two systems a request for a plurality of relations between system-related signals, the communication device of each system of the at least two systems is adapted to receive the request and to transmit the requested plurality of relations, and the communication device of the central server is further adapted to receive the transmitted requested plurality of relations.

16. The assembly according to claim 14, wherein each system of the at least two systems is adapted to determine the plurality of relations between the same system-related signals at different time points and/or between different system-related signals at the same and/or different time points.

17. The assembly according to claim 14, wherein each of the systems of the at least two systems is further adapted to perform a fitting of a model to the signals, wherein the model, associated model parameters, a model output and a fitting quality are defined.

18. The assembly according, to claim 14, wherein the central server is adapted to perform a selection of the system-related signals for which the plurality of relations are determined, wherein said selection is performed by using, random and/or deterministic search methods.

19. A central server which is adapted to be part of an assembly according to claim 14.

20. A non-transitory storage medium comprising a computer program to be executed by a central processing unit (CPU) that is part of a central server according to claim 19 for providing diagnosis and/or maintenance for a plurality of systems.

21. A computer readable medium comprising a computer program according to claim 20.

22. A system providing at least one system-related signal which is adapted to be part of an assembly according to claim 14, wherein the system is a mechatronic or electronic system.

23. A method for providing diagnosis and/or maintenance for a plurality of systems, each system providing a first and a second system-related signal, the method comprising:

determining for each system relations between the first and second system-related signals to provide a plurality of determined relations;

comparing the plurality of determined relations;

determining, based on the results of the comparison, which of the plurality of determined relations are significant relations; and

providing a diagnosis and/or maintenance decision based on the determined significant relations.

24. An assembly for performing diagnosis and maintenance, comprising:

at least two systems for which diagnosis and/or maintenance are performed, wherein each system provides a first and a second system-related signal and each system is adapted to determine relations between the first and second system-related signals to provide a plurality of determined relations; and

a central server including

a comparison unit for comparing the plurality of determined relations,

a determination unit for determining based on the result of the comparison which of the plurality of determined relations are significant relations, and

a diagnosis/maintenance unit for providing a diagnosis and/or maintenance decision base on the determined significant elations.