Systems and methods for identifying damage in a structure

• US 20070260427A1
• Filed: 07/10/2007
• Published: 11/08/2007
• Est. Priority Date: 09/22/2003
• Status: Active Grant

• Current Assignee: Advanced Structure Monitoring, Inc.
• Original Assignee: Advanced Monitoring Systems, Inc.
• Inventors: Kim, Hyeung-Yun
• Granted Patent: US 7,590,510 B2
• Time in Patent Office: Days
• US Class Current: 702/185
• CPC Class Codes: G01H 11/00 Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by detecting changes in electric or magnetic properties
• CPC Class Codes: G01H 11/08 using piezoelectric devices
• CPC Class Codes: G01H 9/004 using fibre optic sensors light guides per se G02B6/00, acousto-optical devices specially adapted for gating or modulating in optical wave guides G02F1/125
• CPC Class Codes: G01M 11/086 Details about the embedment of the optical fiber within the DUT
• CPC Class Codes: G01M 5/0033 by determining damage, crack or wear
• CPC Class Codes: G01M 5/0066 by exciting or detecting vibration or acceleration vibration testing of structures G01M7/00
• CPC Class Codes: G01M 5/0091 by using electromagnetic excitation or detection
• CPC Class Codes: G01N 2291/011 Velocity or travel time
• CPC Class Codes: G01N 2291/015 Attenuation, scattering
• CPC Class Codes: G01N 2291/02491 Materials with nonlinear acoustic properties
• CPC Class Codes: G01N 2291/0258 Structural degradation, e.g. fatigue of composites, ageing of oils
• CPC Class Codes: G01N 2291/0422 Shear waves, transverse waves, horizontally polarised waves
• CPC Class Codes: G01N 2291/0423 Surface waves, e.g. Rayleigh waves, Love waves
• CPC Class Codes: G01N 2291/0427 Flexural waves, plate waves, e.g. Lamb waves, tuning fork, cantilever
• CPC Class Codes: G01N 2291/106 one or more transducer arrays
• CPC Class Codes: G01N 29/043 in the interior, e.g. by shear waves
• CPC Class Codes: G01N 29/0609 Display arrangements, e.g. colour displays indicating or recording in connection with measuring in general G01D
• CPC Class Codes: G01N 29/0672 by acoustic tomography medical tomography A61B8/13
• CPC Class Codes: G01N 29/07 by measuring propagation velocity or propagation time of acoustic waves
• CPC Class Codes: G01N 29/223 Supports, positioning or alignment in fixed situation mounting transducers per se G10K11/004
• CPC Class Codes: G01N 29/245 : Ceramic probes, e.g. lead zirconate titanate [PZT] probes
• CPC Class Codes: G01N 29/2475 : Embedded probes, i.e. probes incorporated in objects to be inspected
• CPC Class Codes: G01N 29/2493 : Wheel shaped probes
• CPC Class Codes: G01N 29/28 : providing acoustic coupling , e.g. water impedance matching G10K11/02
• CPC Class Codes: G01N 29/4418 : with a model, e.g. best-fit, regression analysis
• CPC Class Codes: G01N 29/4463 : Signal correction, e.g. distance amplitude correction [DAC], distance gain size [DGS], noise filtering

Abstract

Systems, methods and recordable media for identifying damage in a structure. A method includes the steps of: obtaining a plurality of damage index values for a network coupled to the structure, wherein each of the damage index values is a quantity to be affected by damage in the structure; generating a distribution of damage index value over a surface using the obtained damage index values; and identifying the damage by analyzing the distribution.

Claims

1. A computer-implemented method of identifying damage in a structure, comprising:

obtaining a plurality of damage index values for a network coupled to a structure, each of the damage index values being a quantity to be affected by damage in the structure;

generating, by use of a computer process, a distribution of damage index value over a surface using the obtained damage index values; and

identifying the damage by analyzing the distribution.

2. The method of claim 1, wherein the step of identifying the damage includes:

building a damage classifier; and

classifying the damage by use of the damage classifier.

3. The method of claim 2, wherein the step of building a damage classifier includes:

training the damage classifier with at least one input data associated with at least one predetermined damage.

4. The method of claim 3, wherein the input data includes a hot-spot region in a distribution of damage index value.

5. The method of claim 3, wherein the input data is generated by wavelet-transforming a hot-spot region in a distribution of damage index value.

6. The method of claim 5, wherein the input data includes wavelets of the wavelet-transformed hot-spot region.

7. The method of claim 3, wherein the damage classifier includes one or more multilayer perceptions (MLPs), each of the MLPs being operative to classify a damage type of the input data.

8. The method of claim 7, wherein the damage classifier further includes a modular network classifier for performing nonlinear transformation and mixing of outputs from the MLPs.

9. The method of claim 1, wherein the step of identifying the damage includes:

building a codebook; and

classifying the damage by use of the codebook.

10. The method of claim 9, wherein the step of building a codebook includes:

providing a distribution of damage index value that includes at least one hot-spot region;

clustering the hot-spot region to determine cluster centers of the hot-spot;

forming a codevector that includes cluster centers; and

storing the codevector into the codebook.

11. The method of claim 10, wherein the step of clustering the hot spot region is performed by use of a K-mean clustering algorithm.

12. The method of claim 10, wherein the step of building a codebook further includes:

fine-tuning the cluster centers.

13. The method of claim 12, wherein the step of fine-tuning the cluster centers is performed by use of a learning vector quantization (LVQ) algorithm.

14. The method of claim 10, wherein the step of clustering the hot-spot region includes:

utilizing a principal component analysis.

15. The method of claim 14, wherein the step of utilizing principal component analysis includes:

incorporating a Fisher linear discriminant analysis or eigenspace separation transformation.

16. The method of claim 1, wherein the step of identifying the damage includes:

providing a distribution of damage index value that includes at least one hot-spot region;

clustering the hot-spot region to determine cluster centers of the hot-spot;

forming a codevector that includes cluster centers;

training a frequency multilayer perception (FMP) using the codevector; and

causing the trained FMP to classify the damage.

17. The method of claim 1, wherein the network includes a plurality of diagnostic network patches (DNP), each of the patches being able to operate as at least one of a transmitter patch and a sensor patch.

18. A computer readable medium carrying one or more sequences of instructions for identifying damage in a structure, wherein execution of one or more sequences of instructions by one or more processors causes the one or more processors to perform the steps of:

obtaining a plurality of damage index values for a network coupled to a structure, each of the damage index values being a quantity to be affected by damage in the structure;

generating, by use of a computer process, a distribution of damage index value over a surface using the obtained damage index values; and

identifying the damage by analyzing the distribution.

19. The computer readable medium of claim 18, wherein the step of identifying the damage includes:

building a damage classifier; and

classifying the damage by use of the damage classifier.

20. The computer readable medium of claim 19, wherein the step of building a damage classifier includes:

training the damage classifier with at least one input data associated with at least one predetermined damage.

21. The computer readable medium of claim 18, wherein the step of identifying the damage includes:

building a codebook; and

classifying the damage by use of the codebook.

22. The computer readable medium of claim 21, wherein the step of building a codebook includes:

providing a distribution of damage index value that includes at least one hot-spot region;

clustering the hot-spot region to determine cluster centers of the hot-spot;

forming a codevector that includes cluster centers; and

storing the codevector into the codebook.

23. The computer readable medium of claim 18, wherein the step of identifying the damage includes:

providing a distribution of damage index value that includes at least one hot-spot region;

clustering the hot-spot region to determine cluster centers of the hot-spot;

forming a codevector that includes cluster centers;

training a frequency multilayer perception (FMP) using the codevector; and

causing the trained FMP to classify the damage.

24. The computer readable medium of claim 18, wherein the one or more sequences of instructions implement a wireless communication method of Wireless Application Protocol (WAP) or Wireless Markup Language (WML) for the Internet Web Access of a WAP-enable cell phone, Pocket PC with a HTML browser, or other HTML enable devices.

25. A system for identifying damage in a structure, comprising:

means for obtaining a plurality of damage index values for a network coupled to the structure, each of the damage index values being a quantity to be affected by damage in the structure;

means for generating, by use of a computer process, a distribution of damage index value over a surface using the obtained damage index values; and

means for identifying the damage by analyzing the distribution.

26. The system of claim 25, wherein the means for identifying the damage includes:

means for building a damage classifier; and

means for classifying the damage by use of the damage classifier.

27. The system of claim 26, wherein the means for building a damage classifier includes:

means for training the damage classifier with at least one input data associated with at least one predetermined damage.

28. The system of claim 25, wherein the means for identifying the damage includes:

means for building a codebook; and

means for classifying the damage by use of the codebook.

29. The system of claim 28, wherein the means for building a codebook includes:

means for providing a distribution of damage index value that includes at least one hot-spot region;

means for clustering the hot-spot region to determine cluster centers of the hot-spot;

means for forming a codevector that includes cluster centers; and

means for storing the codevector into the codebook.

30. The system of claim 25, wherein the means for identifying the damage includes:

s means for providing a distribution of damage index value that includes at least one hot-spot region;

means for clustering the hot-spot region to determine cluster centers of the hot-spot;

means for forming a codevector that includes cluster centers;

means for training a frequency multilayer perception (FMP) using the codevector; and

means for causing the trained FMP to classify the damage.