Time

Topic

09:00-10:00

1. Introduction

- Motivation for SHM, (NDE vs SHM)
- Fundamental Axioms
- Statistical pattern recognition paradigm
- Historical Overview: Aerospace /Civil/Mechanical Application
- Operational evaluation

10:00-11:00

2. Data Acquisition I

- Sensor network components
- Sensor performance metrics
- Signal conditioning issues
- Sensor network paradigms
- Sensor Fusion
- Excitation

11:00-11:15

Break

11:15-12:15

3. Data Acquisition II

- Piezoelectric Active sensing
- Guided Wave Propagation
- Fiber Optics
- MEMS
- Emerging Sensing Technologies
- Energy Harvesting

12:15-13:15

4. Damage Sensitive Features

- Feature selection criteria
- Summary of features reported in the literature
- Waveform Comparisons
- Physical model parameters
- Data-Based model parameters

13:15-14:30

Lunch

14:30-15:30

5. Data Normalization

-Environmental/ operational effects on SHM
-Parametric modeling environmental effects
-Look-up table technique
-Machine learning techniques
-Experimental design

15:30-15:45

Break

15:45-16:45

6. Statistical Classification: Supervised and Unsupervised learning Techniques

- Supervised and unsupervised learning techniques
- Hypothesis testing
- Group Classification
- Outlier Detection
- Regression modeling
- Machine learning approaches

16:45-17:00

Break

17:00-17:45

7. Examples

- Aerospace Applications
- Rotor craft application
- Civil Engineering Applications (bridges)
- Mechanical Systems Applications (telescope)
- Reliability approaches to prognosis

17:45-18:00

8. Closing Remarks and Survey

- Recap the statistical pattern recognition paradigm
- Fundamental Axioms of SHM
- Getting Started
- Other sources of  information
- Course Survey