Sei sulla pagina 1di 33

Guided Waves for Stress

Corrosion Crack Detection in


Pipelines Feature Selection
and Classification

Austin Albright, Venugopal K. Varma,


Raymond Tucker, and Philip Bingham

OAK RIDGE NATIONAL LABORATORY


U. S. DEPARTMENT OF ENERGY

Outline

Introduction and System Overview


Current Methodology & Challenges
Features Selection/Manipulation
Our Technique & Features
Results from Synthetic & Real-World
SCC Samples
Lessons Learned & Future Work
OAK RIDGE NATIONAL LABORATORY
U. S. DEPARTMENT OF ENERGY

Stress Corrosion Cracks (SCCs)


are a growing concern for the
Nations aging infrastructure.
Major contributors to creation of SCCs are:
Repeated Stressing and Relaxation of the
System
e.g. Thermal and operating pressure
variations, and other mechanical influences.
Environment
Soil pH, moisture level, coating break down
OAK RIDGE NATIONAL LABORATORY
U. S. DEPARTMENT OF ENERGY

Our Focus is to detect SCCs in


large diameter Natural Gas
Pipelines, specifically 26-inch and
30-inch diameter pipelines.
Corrosion + Cyclical Loading = SCC
SCC generally found in colonies
SCC are very hard to see with the naked eye
The majority of SCCs run along the axial
direction of pipes
We are looking for SCCs on the outside of the
pipes
from inside the pipe
OAK RIDGE NATIONAL LABORATORY
U. S. DEPARTMENT OF ENERGY

Liquid Fluorescent Magnetic Particle


Inspection allows SCCs to be visualized
on pipes that have been removed from
service & cleaned

Suspension of fine metal particles in an aerosol spray can


The suspect area is sprayed, then a strong magnetic field is
applied
This draws the metal particles into any depression in the
surface such as nicks, scratches, and SCCs
The metal particles glow under a blacklight
One or The suspension is white paint and the particles are black
the other
not both
White Paint & Black Particle Version

OAK RIDGE NATIONAL LABORATORY


U. S. DEPARTMENT OF ENERGY

Blacklight Version

Magnetic Flux Leakage (MFL) is


the standard pipeline
inspection technique used today
Used on active, buried natural gas pipelines
MFL creates a magnetic field axially along the
pipe
Unfortunately, the axial orientation of SCCs
combined with their small size result in little to
no flux leakage.

OAK RIDGE NATIONAL LABORATORY


U. S. DEPARTMENT OF ENERGY

As an alternative, we can
inspect buried pipes using
Electromagnetic Acoustic
Transducers
Allows ultrasonic (EMATs)
Inspection without the need
of a liquid coupling agent
EMATs can be designed to fit almost any
diameter pipe
ORNL EMATs

have been designed specifically to create an


ultrasonic guided wave to detect SCC (axial defects)
produce a shear wave traveling circumferentially in
the pipe wall
utilize pitch-catch mode (one is the transmitter, the
other
is the
receiver)
OAK RIDGE
NATIONAL
LABORATORY
U. S. DEPARTMENT OF ENERGY

The ORNL Shear EMAT


S

N
Permanent

Magnet
Magnets

Current
Coils
Current Coils

EMAT for 30
diameter pipes
Pipe
Pipe Wall
Wall

Shear
Wave
Shear

Lorentz Force:

f=JxB

f is body force per unit volume


J is current density [Amp/m2]
B is magnetic flux density [Tesla]
OAK RIDGE NATIONAL LABORATORY
U. S. DEPARTMENT OF ENERGY

Aluminum
Frame
Magnets

EMAT Coil

ORNLs Test Platform


EMATs

Computer

System Carriage

Signal Conditioning
unit
OAK RIDGE NATIONAL LABORATORY
U. S. DEPARTMENT OF ENERGY

Resolver

ORNL Platform Inside a 30 inch


Pipe

OAK RIDGE NATIONAL LABORATORY


U. S. DEPARTMENT OF ENERGY

Discrete Data Points in Time

The received EMAT Signatures are


functions of axial position and
time.
Amplitude
Color Indicates Amplitude

The features are extracted from the data


in this boxed range

Axial Position [inches] can also be in [signatures]


OAK RIDGE NATIONAL LABORATORY
U. S. DEPARTMENT OF ENERGY

Features are numerical quantities


that describe an event, object, or
trait.

Good features should improve the discernability


between classes

There are two categories describing feature sets:

Supervised and Unsupervised


Supervised learning uses known data sets (i.e., a
signature in the set is known to be a SCC signatures or a
non-SCC signatures) and determines what features
discriminate these two classes.
Unsupervised learning assumes nothing about the class
of the signatures making up the data
Supervised Feature Sets are difficult to create for realworld applications.

Wavelet filtering is a useful method


for extracting information from
transient signals, such as our EMAT
signatures.

Wavelet Analysis

Time-Frequency Decomposition
Transients can be resolved
Basis Function can be created or selected to target a
signal
Example Wavelet Decomposition Tree

OAK RIDGE NATIONAL LABORATORY


U. S. DEPARTMENT OF ENERGY

Details of our Wavelet


Decomposition
4-level Decomposition
(yields 5 pieces)
Using semi-custom Basis
Function

We still must distill features


from the wavelet transform
Energy Percentage of Energy in each Wavelet Level.
Entropy Percentage of Entropy in each Wavelet Level.
Difference Measure the mean of each wavelet level is
calculated from the no-defect set and subtracted from
the matching level of the current signature and then
summed.
Point-by-Point Mahalanobis Distance (MD) treat
each discrete point of a wavelet level as an actual feature.
(Point-by-Point MD)2 square each wavelet levels
point-by-point MD value , for each signature.
OAK RIDGE NATIONAL LABORATORY
U. S. DEPARTMENT OF ENERGY

If all the features were good, then


using all the features would produce
the best classification.
Feature Problems
A feature can be noise
Redundant
Misrepresentative

Related Problems
Overfitting
Dimensionality
Poor Classification

Common Techniques to Reduce these


Problems are:
Find Better Features
Linear Discriminant Analysis (LDA)
Principal Component Analysis (PCA)

Principal Component Analysis


(PCA)
also known as

Karhunen-Leve transform

Reduces the feature space

dimensionality
PCA is an Unsupervised
Technique

where,

S is the covariance matrix of the data set

e is an eigenvector(s) of S

Set (matrix) of
eigenvectors being used

is the eigenvalue(s) corresponding to


To project: y eset
x
Projected data

S e e

the eigenvectors
Original data

Linear Discriminant Analysis


(LDA)
also known as

Fisher Discriminant
Analysis

Seeks to minimize the


in-class variance while
at the same time
reducing the betweenclass variance
Projects the data
in to a c 1 n matrix
LDA is a Supervised
Technique

S B w SW w

where,

S B is the between-class scatter matrix

SW is the within-class scatter matrix

w is the eigenvectors of S B

is the eigenvalue of S B , each

corresponds a single eigenvector in w


Set (matrix) of
eigenvectors being used


To project: y wset x
Projected data

Original data

LDA versus PCA


Efficient Discrimination or Efficient
Space

OAK RIDGE NATIONAL LABORATORY


U. S. DEPARTMENT OF ENERGY

PCA+LDA, as a sequential operation


applied to the original feature set
PCA is used to remove stochastic noise
and lower the dimensionality
LDA is used to provide improve
discernability between the classes
Feature
Matrix
(n x m)

1xm

kxm
LDA

PCA

Example:

k<n

n features
m samples
2 classes

OAK RIDGE NATIONAL LABORATORY


U. S. DEPARTMENT OF ENERGY

Classifier

Class
B

Class
A

Which technique should be used? It


depends on what your problem is,
but the basic criteria are
If you have a noise problem and/or have high
dimensionality
at least use PCA.
If you have a class separability issue
use
LDA.
If you have both problems
use PCA+LDA.
If you just plain arent sure what is going on
try each of these techniques.
OAK RIDGE NATIONAL LABORATORY
U. S. DEPARTMENT OF ENERGY

The Mahalanobis Distance (MD)


calculated from a set of non-SCC
signatures is used to classify the
unknown signatures.
Statistically the non-SCC (good) signatures are
well represented, which is why we use MD from
the good signatures for our classifier.
MD returns a scalar value indicating a signatures
distance from the good clusters centroid.
We refer to the MD value as the Flaw Distance,
since the larger the distance the more flaw-like
the signature under test.
OAK RIDGE NATIONAL LABORATORY
U. S. DEPARTMENT OF ENERGY

The feature transformation


techniques presented have improved
our defect detection.

Synthetic SCC Test Bed


Unused (new) 10-foot long, 30 diameter pipe
4 scan lines were machined in to it
2 lines of parabolic cuts
circumferential widths of 8, 12, 16, and 20 mils

2 lines of rectangular cuts


circumferential widths of 8, 12, 16, and 20 mils

Cuts ranged in depth from 10-75% of the wall


thickness (0.375).
OAK RIDGE NATIONAL LABORATORY
U. S. DEPARTMENT OF ENERGY

Comparison of Results from a Parabolic Cuts Scan Line


MD using all of the original features

MD using 2 hand-picked features

MD after using PCA (13 out of 25 eigenvectors)

MD after using LDA

MD after using PCA+LDA


OAK RIDGE NATIONAL LABORATORY
U. S. DEPARTMENT OF ENERGY

Blind Test of a Decommissioned


Natural Gas Pipeline Section (known
to contain SCCs)

Conducted at the Battelle Pipeline Simulation


Facility (PSF) in Columbus, OH.
Given a pipe and specific areas from which we
were to report our findings (from those areas only.)
Allowed to make multiple scans of the pipe to
collect data.
Given 2 weeks to submit our findings.
Then the PSF staff distributed the answer keys.
OAK RIDGE NATIONAL LABORATORY
U. S. DEPARTMENT OF ENERGY

January 2006, Blind Test Results

OAK RIDGE NATIONAL LABORATORY


U. S. DEPARTMENT OF ENERGY

Every defect response in the MD plot corresponds to a


defect and/or combination of defects
B

Corrosion &
SCC

SCC

NOT SCCs
Superficial
Manufacturing
Handling Marks

Corrosion
SCCs

OAK RIDGE NATIONAL LABORATORY


U. S. DEPARTMENT OF ENERGY

Conclusion/Summary

We can detect SCCs in any orientation e.g. axial


We also can detect pitting and corrosion patches
Our detection threshold is tied to the volume of
the defect, not merely depth of penetration
PCA+LDA significantly improved the
discernability of both synthetic and real SCC
Mostly by suppressing the responses generated by
metallurgic variations and small changes in gap
between the EMAT and the pipe wall.

Most Important is, when the projection matrices


calculated from the synthetic SCC data are used
on REAL SCC data, the same improvements are
achieved.
OAK RIDGE NATIONAL LABORATORY
U. S. DEPARTMENT OF ENERGY

Future Work
Automate identification of real defect
Develop a method for differentiating
between corrosion patches and SCCs, and
possible SCCs in a corrosion patch as well.
Investigate the benefits of normalizing
the energy across an entire scan data set,
in hopes of removing the false positives
due to changes in the air gap (coupling)
between the EMATs and the pipe wall.

OAK RIDGE NATIONAL LABORATORY


U. S. DEPARTMENT OF ENERGY

Questions ?

THE
END

OAK RIDGE NATIONAL LABORATORY


U. S. DEPARTMENT OF ENERGY

ORNL Sensor System


Hardware
Electromagnetic
Acoustic Transducers
(EMATs) the sensors
Resolver for position
Signal Conditioning
Devices amps & matching
networks

Software
Online
O/S Windows 2000
LabVIEW (National Instruments)
All Data Acquisition is
handled via LabVIEW

Offline

Matlab (Mathworks)

Computer dual Xeon


Data Acquisition
Tone Burst Generator

Data Processing,
Flaw Identification,
Visualization, etc

We still must distill features from


the wavelet transform.
Energy Percentage of Energy in each Wavelet Level
n
S 2
ijk
k

1
F
, for j 1, 2, 3, 4 and 5
ij
5 n
S2
p 1 k 1 ijkp

Entropy Percentage of Entropy in each Wavelet Level


n
F S
ln(S
) , for j 6, 7, 8, 9 and 10
ij k 1 i ( j 5)k
i ( j 5)k

Difference Measure the mean of each wavelet level


is calculated from the good set and subtracted from the
matching level of the current signature and then summed
n
F (S
SM
) 2 , for j 11, 12, 13, 14 and 15
ij k 1 i ( j 10)k
( j 10)k

We still must distill features from the


wavelet transform, Continued.
Point-by-Point MD treat each discrete point of a wavelet level
as an actual feature.
( Si ( j 15)1 GM ( j 15)1)
M i [( S

i ( j 15)1

GM

( j 15)1

) (S

i ( j 15)k

GM

( j 15)k

)] 1

( Si ( j 15)k GM ( j 15)k )

, for j 16, 17, 18, 19 and 20

(Point-by-Point MD)2 square each wavelet levels point-bypoint MD value , for each signature.
Notation
j the wavelet level
i signature number
k number of discrete points in each
wavelet level e.g. detail-4 k = 32
p number of wavelet levels
S signature data vector

GM mean of level j of the good set


-1 the good sets inverse covariance
matrix
NOTE: j is formed so that all the features
can be calculated in one pass. GM is
accessible as a whole level or point-by-point

PCA can

reduce stochastic noise


lower dimensionality by representing the
information in the most efficient space

LDA can

improve classification by better separating the


classes
lower dimensionality, returns feature matrix as
a (Num. Classes 1) x (Num. Samples) matrix

PCA+LDA can

remove stochastic noise


lower the dimensionality
Improve discernability between classes

OAK RIDGE NATIONAL LABORATORY


U. S. DEPARTMENT OF ENERGY

Potrebbero piacerti anche