Apparatus and methods for evaluating a dynamic system

• US 20060155734A1
• Filed: 01/07/2005
• Published: 07/13/2006
• Est. Priority Date: 01/07/2005
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Grimes, Michael R.
• Granted Patent: US 7,937,197 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G07C 5/0808 Diagnosing performance data testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005

Abstract

A method of evaluating whether a vehicle under test is operating as intended. Parameters of the vehicle are sampled at a plurality of sample times to obtain a plurality of data samples. Data samples from more than one of the sample times are included in a sample set. The sample set is input to an artificial neural network (ANN). Many time-varying parameters, e.g., response times in motor vehicle systems, can be detected and evaluated.

Claims

1. A method of evaluating whether a vehicle under test is operating as intended, said method comprising:

sampling parameters of the vehicle at a plurality of sample times to obtain a plurality of data samples;

including data samples from more than one of the sample times in a sample set; and

inputting the sample set to an artificial neural network (ANN).

2. The method of claim 1 further comprising separating two of the sample times by a predetermined interval.

3. The method of claim 1 further comprising:

including the data samples in a plurality of sample sets; and

inputting the sample sets to the ANN.

4. The method of claim 3 wherein the ANN includes a self-organizing map (SOM), said method further comprising training the SOM to evaluate parameters of the vehicle based on the sample sets.

5. The method of claim 1 wherein sampling parameters of the vehicle comprises sampling data relating to a motor of the vehicle.

6. A method of evaluating whether a response over time of a vehicle under test is within an expected range, said method comprising:

sampling parameters of the vehicle to obtain a plurality of sets of data samples;

inputting a first of the sample sets to an artificial neural network (ANN);

including a data sample from the first sample set in a second of the sample sets; and

inputting the second sample set to the ANN.

7. The method of claim 6 further comprising:

sampling parameters of the vehicle at a plurality of sample times to obtain the data samples; and

including a data sample obtained at one of the sample times in a sample set that includes a data sample obtained at another of the sample times.

8. The method of claim 6 wherein said inputting is performed to train the ANN.

9. The method of claim 6 further comprising training the ANN to evaluate parameters of the vehicle based on data samples obtained at different sample times.

10. The method of claim 6 wherein the ANN comprises a self-organizing map (SOM).

11. The method of claim 6 wherein sampling parameters of the vehicle to obtain a plurality of sets of data samples comprises sampling parameters of the vehicle at predetermined time intervals.

12. An evaluating apparatus for evaluating responses over time by a subject vehicle, said apparatus comprising:

a sampling apparatus that obtains a plurality of data samples from the vehicle; and

a processor that inputs the data samples as a plurality of sample sets to a self-organizing map (SOM);

wherein said processor includes one of the data samples in more than one of the sample sets.

13. The evaluating apparatus of claim 12 wherein said processor includes the one of the data samples in more than one of the sample sets based on a sample time associated with the one of the data samples.

14. The evaluating apparatus of claim 12 wherein one of the sample sets comprises data samples obtained by said sampling apparatus at more than one sample time.

15. The evaluating apparatus of claim 12 wherein said processor trains the SOM using the plurality of sample sets.

16. The evaluating apparatus of claim 12 wherein the subject vehicle includes a motor and said sampling apparatus obtains a plurality of data samples relating to operation of the motor.

17. An evaluating apparatus for evaluating one or more time-varying parameters in a system under test, said apparatus comprising:

a sampling apparatus that obtains from the system a plurality of data samples describing the parameters at a plurality of sample times; and

a processor that;

includes a time series of the data samples in a sample set; and

inputs the sample set to a self-organizing map (SOM).

18. The apparatus of claim 17, wherein said processor trains said SOM to evaluate an input to the system at one time relative to an output of the system at another time.