eddy current testing · 2013-10-30 · anfis (adaptive-network-based fuzzy inference ... nortec...

30
1 Intelligent Eddy Current Crack Detection System Design Based on Neuro-Fuzzy Logic 1 Data fusion ECT signal processing Oct. 09 th , 2013 Baoguang Xu MASc. Concordia University Montreal

Upload: hoangkhue

Post on 27-Jul-2019

218 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

1

Intelligent Eddy Current Crack

Detection System Design Based on

Neuro-Fuzzy Logic

1

Data fusion – ECT signal processing

Oct. 09th , 2013 Baoguang Xu MASc. Concordia University Montreal

Page 2: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

Outline

Project description and goals

Eddy current signal feature extraction and analysis using fuzzy logic. Signal de-noise

Signal features and feature extraction

Fuzzy logic

Experiments and results

Conclusions and Future work

2

Page 3: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

3

1. Project description and goals

Page 5: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

5

Project description and goals

• In aerospace industry especially in aircraft maintenance, ECT is performed manually.

Time and cost consuming

Result depends on human experience.

• Currently no signal recognition system is able to indicate crack features such as depth and shape etc. automatically

In aircraft maintenance and manufacturing especially for quality control, ECT signal recognition largely relies on the properties of cracks

• The goal of the project--- to provide the aerospace industry with a user friendly, AI aided signal recognition system to obtain the cracks’ information automatically.

Page 6: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

6

Program Design Diagram

Known Signal input Signal de-noiseSignal

processing(feature extraction)

Fuzzy logic training (ANFIS)

Signal from unknown crack

Trained fuzzy logic

Signal de-noiseSignal

processing(feature extraction)

Crack information

output (depth, width shape

etc.)

Training

Page 7: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

7

2. Eddy current signal feature extraction and analysis

Page 8: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

8

Signal de-noise

• Filter choices

High/Low pass filter

Fourier transform.

Wavelet transform. √

Page 9: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

9

Wavelet de-noise

S(signal

)Filter

cA1

Filter

cD1

Filter

cA2

Filter

cD2

Filter

cA3

Filter

cD3

1. Decompose signal into wavelet components (in which case noises are been

separated).

2. Define the right wavelet C coefficient in order to miniature or remove noises.

3. Reconstruct processed signal by defining C coefficient [1]

Page 10: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

10

De-noise Result

Page 11: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

11

Signal features and feature extraction

Impedance of eddy current test Typical crack signal for differential probe

2 2

LZ R X

: ImpedanceZ

: eactanceLX R

: esistanceR R

Page 12: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

12

Signal features and feature extraction

Before After

Page 13: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

13

Approaches to obtain the crack information based on ECT signal

• Theoretical model

Analytical Modeling

Numerical Modeling

Drawbacks: It is hard to establish the theoretical models due to the complexity of crack geometry and the non-accessible detailed coil information of the probe.

• Artificial intelligence

Fuzzy logic

Neural networks

Drawbacks: Artificial intelligence techniques require large set of reliable data to train the system.

Page 14: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

14

Fuzzy logic

• Fuzzy logic is known as an artificial intelligence tool to describe complicated physical phenomena and to anticipate the linear or nonlinear results based on collected input and output data [2].

• Instead of using absolute 1 (true) and 0 (false) to make traditional logical decision, fuzzy logic introduces the concept of membership to describe how the input and output weight (in between 1 and 0) as a member in a certain membership.

Fuzzifier DuzzifierInput OutputFuzzy rules

Membership

FunctionFuzzy logic system

Page 15: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

15

ANFIS (Adaptive-Network-Based Fuzzy Inference System)

• Neuro-based fuzzy logic is inspired by neural network, similar to that of neural network which constitutes input and output mapping via their membership functions and related parameters [3].

Neuro mapping structure, Fuzzy rules samples after training

Page 16: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

16

3. Experiments and Results

Page 17: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

17

Hardware information

Olympus: Nortec 500S Frequency Range 50 Hz -12 MHz Probe: differential reflection probe (PRL/500 kHz - 3 MHz/D) Crack sample: Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil)

Pictures come from:[5][6]

Page 18: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

18

Hardware information

National instruments: NI USB-6009 8 analog inputs (14-bit, 48 kS/s) 2 analog outputs (12-bit, 150 S/s); 12 digital I/O; 32-bit counter Compatible with LabVIEW, LabWindows™/CVI, and Measurement Studio for Visual Studio .NET

Pictures come from:[7]

Page 19: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

19

computer Data Acquisition Card

ECT equipment

Hardware Connection

Page 20: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

20

Testing Sample

Material: Aluminum 7075-T6 notch crack sample

0.008 in. (0.203 mm), 0.020 in. (0.508 mm) and 0.040 in. (1.016 mm) 0.0315in. (0.80mm), 0.0591in. (1.50mm), 0.0787in. (2.0mm)

Page 21: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

21

Experimental results

Page 22: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

22

Experimental results

Page 23: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

23

Experimental results

Page 24: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

24

User interface

ECT user friendly interface

Page 25: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

25

Experimental results (angled crack)

angled crack sample

One important finding: The crack angle

could have relation with the ratio of upper

loop width and down side loop width,

which will be investigated in the future

Page 26: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

26

4. Conclusions and Future work

Page 27: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

27

Conclusions

The feature extraction algorism is able to process differential ECT signal

Trained fuzzy logic possess an accurate result of crack depth predication with proper tuning method

User interface is partial functional and is able to implement the feature extraction as well as the crack definition.

Page 28: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

28

Future work

• More data collection

Smaller cracks

Cracks with complicated crack geometry

Data from robotic scan system

• Theoretical model exploration

Impedance trajectory simulation

Data collection and training using theoretical modeling

• User interface improvement and implementation

Page 29: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

29

References

1. Takagi T., Bowler J.R., Yoshida Y., “Electromagnetic Nondestructive Evaluation”, Volume 1, IOS Press, 1997 .Smaller cracks

2. Wang, L. X. “A Course in Fuzzy systems and Control”, Prentice Hall PTR, 1997.

3. Jang, J.-S. R., “ANFIS: Adaptive-Network-based Fuzzy Inference Systems,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 23, No. 3, pp. 665-685, May 1993.

4. Garcia-Martin, J., Gomez-Gil, J. and Vazquez-Sanchez, E., "Non-Destructive Techniques Based on Eddy Current Testing", Sensors, vol.11, no.3, March 2011, pp. 2525-2565.

5. " Nortec 500Series Portable Eddy Current Flaw Detectors Operation Manual " , PN 7720140.00, Revision B, July 2013

6. " Olympus Eddy Current Probes “catalog

7. National Instruments Product spec. http://sine.ni.com/nips/cds/view/p/lang/en/nid/201987

Page 30: Eddy Current Testing · 2013-10-30 · ANFIS (Adaptive-Network-Based Fuzzy Inference ... Nortec TB-S1 Standard (deep notches: 8mil; 20mil; 40mil) Pictures come from:[5][6] 18 Hardware

30

Thank you!

Q&A