Multi-sensor data fusion using geometric transformations for the nondestructive evaluation of gas transmission pipelines

1
Multi-sensor data fusion using geometric
transformations for the nondestructive evaluation
of gas transmission pipelines

• by
• PJ Kulick
• Graduate Advisor Dr. Shreekanth Mandayam
• MS Final Oral Presentation
• August 29, 2003, 300 PM

2
Outline

• Introduction
• Objectives and Scope of Thesis
• Background
• Approach
• Implementation Results
• Conclusions

3
Gas Transmission Pipelines
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions

• 280,000 miles
• 24 - 36 inch dia.

4
In-Line Inspection
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
5
Nondestructive Evaluation (NDE)
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
6
Gas Transmission Pipeline Indications

• Benign
• T-sections
• Welds
• Valves
• Taps
• Straps
• Sleeves
• Transitions

• Anomalies
• Stress Corrosion Cracking
• Pitting
• Arching
• Mechanical Damage

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
7
NDE using Multiple Inspection Modalities
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
8
Data Fusion
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
9
Data Fusion
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
10
Objectives of This Thesis

• Develop data fusion techniques for the extraction
  of redundant and complementary information
• Validate techniques using simulated canonical
  images
• Validate techniques using laboratory NDE signals

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
11
Expected Contributions
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions

• A data fusion algorithm with the ability to
  identify redundant and complementary information
  present in multiple combinations of pairs of NDE
  data sets.
• i. e. (MFL-UT, MFL-Thermal, UT-Thermal)

12
Nondestructive Evaluation of Gas Pipelines
0.2
0.0
0.6
0.4
Ultrasonic Testing
Magnetic Imaging
Virtual Reality
Data Fusion
Advanced Visualization
Acoustic Emission

• This research work is sponsored by
• US Department of Energy
• National Science Foundation
• ExxonMobil

Thermal Imaging
Digital Signal/Image Processing
Test Platforms
13
Previous Work in Data Fusion

• Mathematical Theory
• Probability Theory
• Bayes Theorum
• Possibility Theory
• Fuzzy logic
• Belief Theory
• Dempster Shafer
• Improved DS Theories
• Transferable Belief Model

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
14
Previous Work in Data Fusion

• Mathematical Transforms
• Discrete Fourier Transform (DFT)
• Discrete Cosine Transform (DCT)
• Wavelet based transforms

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
15
Geometric Transformations

• Spatial Transformation

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
16
Geometric Transformations

• Gray-level Interpolation

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
17
Approach
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
Feature x1
Geometric Transformation
Redundant/ Complementary Information
OBJECT
Feature x2
g2(x2) T g1-1(x1, x2) h
homomorphic operator
18
Approach

• Redundant Data Extraction
• ? Train RBF (homomorphic operator ? )
• g1(x1, x2) g2(x2) h1

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
19
Approach

• Redundant Data Extraction
• ? Test RBF
• h1 x2 g1(x1, x2)

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
20
Canonical Image Results

• Simulation 1

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
x2
x1

• 6 Images
• 4 Training
• 2 Test
• 20 x 20 pixels
• 20 x 20 DCT sent into network in vector form

Complementary
Redundant
21
Canonical Image Results

• Simulation 1 Training Data Results

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
22
Canonical Image Results

• Simulation 1 Test Data Results

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
23
Canonical Image Results

• Simulation 2

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
x2
x1

• 6 Images
• 4 Training
• 2 Test
• 20 x 20 pixels
• 20 x 20 DCT fed into network in vector form

Complementary
Redundant
24
Canonical Image Results

• Simulation 2 Training Data Results

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
25
Canonical Image Results

• Simulation 2 Training Data Results

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
26
Canonical Image Results

• Simulation 2 Test Data Results

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
27
Experimental Setup

• Test Specimen Suite

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
28
Experimental Setup MFL
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
Pipe section
Hall probe
Probe mount
Current leads
Clamp
29
Experimental SetupTangential MFL Images
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
30
Experimental Setup UT
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
31
Experimental SetupUT Time of Flight (TOF) Images
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
32
Experimental Setup Thermal
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
33
Experimental SetupThermal Phase Images
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
34
What is Redundant and Complementary Information?

• We have defined this as follows

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
Defect Profile
Method 1 NDE Signature
Method 2 NDE Signature
Redundant Information
Complementary Information
35
Experimental SetupTangential MFL Images
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
36
Experimental SetupUT Time of Flight (TOF) Images
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
37
Experimental SetupThermal Phase Images
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
38
Data Fusion Trials
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
Trial 1 UT-MFL UT-Thermal MFL-Thermal
Trial 2 UT-MFL UT-Thermal MFL-Thermal
Trial 3 UT-MFL UT-Thermal MFL-Thermal
39
Data Fusion Trials

• Trial 1

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
40
UT and MFL Data Fusion Results
Trial 1
41
UT and MFL Data Fusion Results
Trial 1
42
Data Fusion Trials

• Trial 2

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
43
UT and MFL Data Fusion Results
Trial 2
44
UT and MFL Data Fusion Results
Trial 2
45
Data Fusion Trials

• Trial 3

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
46
UT and MFL Data Fusion Results
Trial 3
47
UT and MFL Data Fusion Results
Trial 3
48
Data Fusion Trials
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
Trial 1 UT-MFL UT-Thermal MFL-Thermal
Trial 2 UT-MFL UT-Thermal MFL-Thermal
Trial 3 UT-MFL UT-Thermal MFL-Thermal
49
Data Fusion Trials

• Trial 1

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
50
UT and Thermal Data Fusion Results
Trial 1
51
UT and Thermal Data Fusion Results
Trial 1
52
Data Fusion Trials

• Trial 2

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
53
UT and Thermal Data Fusion Results
Trial 2
54
UT and Thermal Data Fusion Results
Trial 2
55
Data Fusion Trials

• Trial 3

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
56
UT and Thermal Data Fusion Results
Trial 3
57
UT and Thermal Data Fusion Results
Trial 3
58
Data Fusion Trials
OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
Trial 1 UT-MFL UT-Thermal MFL-Thermal
Trial 2 UT-MFL UT-Thermal MFL-Thermal
Trial 3 UT-MFL UT-Thermal MFL-Thermal
59
Data Fusion Trials

• Trial 1

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
60
MFL and Thermal Data Fusion Results
Trial 1
61
MFL and Thermal Data Fusion Results
Trial 1
62
Data Fusion Trials

• Trial 2

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
63
MFL and Thermal Data Fusion Results
Trial 2
64
MFL and Thermal Data Fusion Results
Trial 2
65
Data Fusion Trials

• Trial 3

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
66
MFL and Thermal Data Fusion Results
Trial 3
67
MFL and Thermal Data Fusion Results
Trial 3
68
Accomplishments

• Development of a generalized technique for fusing
  data from two distinct observations of the same
  object
• Design of an algorithm that can extract redundant
  and complementary information from two distinct
  observations of the same object
• Validation using simulated canonical images
• Validation using lab data representative of the
  NDE of gas transmission pipelines

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
69
Conclusions

• Algorithm is sufficiently general does not
  specify which features are redundant or
  complementary
• Efficacy has been demonstrated by defining the
  redundancy and complementarity of two NDE images
  by correlating defect signature pixels with the
  location, size and shape of the defect
• Definition and approach are extremely accurate in
  all instances of training data and sufficiently
  accurate in all instances of test data
• Information presented to the neural network is
  distinct the matrices manipulated are
  non-singular
• The errors that occur during certain instances of
  training and testing illustrate the need for a
  large, more diverse data set
• Data fusion of UT/MFL proved better then data
  fusion of UT/Thermal or MFL/Thermal

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
70
Directions for Future Work

• Enhancement of training and test data
• Explore variety of image preprocessing techniques
• Investigate various definitions of redundant and
  complementary information
• Test techniques robustness with noisy real-world
  NDE signals
• Adapt algorithm for heterogenous datasets

OUTLINE Introduction Objectives/
Scope Background Approach Implementation
Results Conclusions
71
Acknowledgements

• U.S. Department of Energy, "A Data Fusion System
  for the NondestructiveEvaluation of Non-Piggable
  Pipes," DE-FC26-02NT41648
• ExxonMobil, "Development of an Acoustic Emission
  Test Platform with a Biaxial Stress Loading
  System," PERF 95-11
• Joseph Oagaro