7/30/2019 Structural Health Monitoring Using Statistical Pattern Recognition
1/15
Structural Health Monitoring Using
Statistical Pattern Recognition
Los Alamos Dynamics Structural Dynamics and Mechanical Vibration Consultants
Presented by
Charles R. Farrar, Ph.D., P.E. and Hoon Sohn, Ph. D.
7/30/2019 Structural Health Monitoring Using Statistical Pattern Recognition
2/15
Los Alamos Dynamics Structural Dynamics and Mechanical Vibration Consultants
Structural Health Monitoring using Statistical Pattern Recognition
Course Demo 2
Overview of the Course
Summarize the rapidly evolving field of structural
health monitoring.
Summarize the historical developments of this technology. Provide overview of current methods.
Show real world application of this technology.
Identify the limitations of the current technology.
Present cutting edge statistical tools for diagnosis.
Discuss current and future research directions.
Course Theme: Structural Health Monitoring is aproblem in statistical pattern recognition.
7/30/2019 Structural Health Monitoring Using Statistical Pattern Recognition
3/15
Los Alamos Dynamics Structural Dynamics and Mechanical Vibration Consultants
Structural Health Monitoring using Statistical Pattern Recognition
Course Demo 3
Actual
loadingand operating
conditions
Usage Monitoring
System
Response
measurement
Inputmeasurement
1. Instrumentation
2. Data management
System
assessment
model
1. Modeling & simulation
2. Data interrogation
Structural Health
MonitoringDamage Prognosis
1. Modeling & simulation
2. Data interrogation
3. Embedded processing
Predictivemodel
Predictive
loading
model
1. Data interrogation
Future Loading Estimation
Where Does Structural Health Monitoring Fit In The Big Picture
7/30/2019 Structural Health Monitoring Using Statistical Pattern Recognition
4/15
Los Alamos Dynamics Structural Dynamics and Mechanical Vibration Consultants
Structural Health Monitoring using Statistical Pattern Recognition
Course Demo 4
Process of Structural Health Monitoring
Vibration-based damage detection is part of the more
general process of Structural Health Monitoring
The Structural Health Monitoring process includes:1. Operational evaluation of the structure
2. Data acquisition and cleansing
3. Feature extraction and information condensation
4. Statistical model development
7/30/2019 Structural Health Monitoring Using Statistical Pattern Recognition
5/15
Los Alamos Dynamics Structural Dynamics and Mechanical Vibration Consultants
Structural Health Monitoring using Statistical Pattern Recognition
Course Demo 5
Rotating Machinery Application
Frequency in Hz
0 1000 2000 3000 4000 5000
0
0
0
0ax Amp.38
20-MAR-96
21-MAR-96
21-MAR-96
21-MAR-96
01-APR
18-
0
Before Bearing ReplacementBefore Bearing Replacement
Engineers at Intels Fab-11 plant
measure vibrations on a vacuum
blower motor
Spectral response of machine
vibrations before (bottom trace)
and after bearing replacement
7/30/2019 Structural Health Monitoring Using Statistical Pattern Recognition
6/15
Los Alamos Dynamics Structural Dynamics and Mechanical Vibration Consultants
Structural Health Monitoring using Statistical Pattern Recognition
Course Demo 6
Early Work on Offshore Structures
Offshore Industry spent millions of
dollars during the 70s and 80s in an
effort to launch practical damage
detection and health monitoring ofoffshore platforms
Numerous examples in the literature of
numerical modeling efforts as well as
scale-model and full-scale experiments Many practical problems were
encountered: Machine noise
Non-uniform inputs Hostile environment for instrumentation
Marine growth
Changes in foundation with time
Modal frequencies can be
insensitive to many of the
damage types the offshore
industry is interested in
7/30/2019 Structural Health Monitoring Using Statistical Pattern Recognition
7/15
Los Alamos Dynamics Structural Dynamics and Mechanical Vibration Consultants
Structural Health Monitoring using Statistical Pattern Recognition
Course Demo 7
Overview of Aerospace Applications
Aging aircraft
Rotorcraft
Reusable launch vehicles:
Space shuttle
X-33
DC-XA
International space station &
related truss test beds
MIR space station
Damage to 1988 Aloha
Airlines flight motivated the
development of an FAA
Aging Aircraft Center at
Sandia National Laboratory
7/30/2019 Structural Health Monitoring Using Statistical Pattern Recognition
8/15
Los Alamos Dynamics Structural Dynamics and Mechanical Vibration Consultants
Structural Health Monitoring using Statistical Pattern Recognition
Course Demo 8
1. Operational Evaluation
Operational evaluation begins to answer questionsregarding implementation issues for a structuralhealth monitoring system.
Provide economic and/or life-safety justifications forperforming the monitoring.
Define system-specific damage including types of damageand expected locations.
Define the operational and environmental conditions underwhich the system functions.
Define the limitations on data acquisition in the operationalenvironment.
Operational evaluation will require input from manydifferent sources (designers, operators, maintenancepeople, financial analysts, regulatory officials)
7/30/2019 Structural Health Monitoring Using Statistical Pattern Recognition
9/15
Los Alamos Dynamics Structural Dynamics and Mechanical Vibration Consultants
Structural Health Monitoring using Statistical Pattern Recognition
Course Demo 9
2. Data Acquisition: Conventional Monitoring vs. WiMMS
Centralized
Data Acquisition
SensorsCabling
Micro-
Processor
Wireless
Modem
SensorsA-to-D
Batteries
Wireless
Modem PC
Centralized
Data Storage
SU
SU
SUSU
Sensor Units
SU
WirelessCommunication
SU
SM
Sensors
Cables
Data Acq. Unix Box
Bus
Sensors
Sensors
From Straser, 1998
7/30/2019 Structural Health Monitoring Using Statistical Pattern Recognition
10/15
Los Alamos Dynamics Structural Dynamics and Mechanical Vibration Consultants
Structural Health Monitoring using Statistical Pattern Recognition
Course Demo 10
2. Data Acquisition: Commercial Wireless Monitoring Systems
Developed at UCBerkeley EE Dept.
Marketed through
Crossbow, SanJose
See
www.xbow.com
2.5cm
Analog Devices
two axis accelerometer
Local processor
and transmitter Photo Detector
and thermalsensor
7/30/2019 Structural Health Monitoring Using Statistical Pattern Recognition
11/15
Los Alamos Dynamics Structural Dynamics and Mechanical Vibration Consultants
Structural Health Monitoring using Statistical Pattern Recognition
Course Demo 11
2. Data Acquisition: Demonstration of the Mote System
A portal test structureThe preload in the bolt is varied
by a PZT actuator
The loosening of the bolt is detected and
reported by the LDE lights in the sensor Correlation reading between two sensors
7/30/2019 Structural Health Monitoring Using Statistical Pattern Recognition
12/15
Los Alamos Dynamics Structural Dynamics and Mechanical Vibration Consultants
Structural Health Monitoring using Statistical Pattern Recognition
Course Demo 12
3. Feature Extraction: Flowchart of Model Update-Based Damage
Identification
FEM Correlated with
Undamaged Data
Modal Frequencies and
Mode Shapes from Test
of Damaged Structure
FEM Correlated with
Damaged Data
Damage is identified by
comparing two finite element
models: one correlated with
undamaged data; one
correlated with damaged data
DAMAGE?
Update
FEMwith
Data
7/30/2019 Structural Health Monitoring Using Statistical Pattern Recognition
13/15
Los Alamos Dynamics Structural Dynamics and Mechanical Vibration Consultants
Structural Health Monitoring using Statistical Pattern Recognition
Course Demo 13
3. Feature Extraction: Uncracked vs. Cracked Beam Response:
Wigner-Ville Transform
Uncracked Cracked
7/30/2019 Structural Health Monitoring Using Statistical Pattern Recognition
14/15
Los Alamos Dynamics Structural Dynamics and Mechanical Vibration Consultants
Structural Health Monitoring using Statistical Pattern Recognition
Course Demo 14
4. Statistical Modeling: Outline of the Statistical Process
3. FEATURE EXTRACTION
AR Coefficients
Residual Error
Modal Parameters
Flexibility Matrices
2. PREDICTION MODELING
AR
CVA
Kalman Filter
Neural Network
( )tx
time
( )tx
1. DATA ACQUISITION
From healthy structure
From damaged structure
time
*
**
*
* ** * *
*
* *
*
*
**
**
CL
UCL
LCL
ei
or
4. CONTROL CHART CONSTRUCTION
S Chart
CUSUM
X-bar Chart
5. MONITORING 6. DECISION MAKING
7/30/2019 Structural Health Monitoring Using Statistical Pattern Recognition
15/15
Los Alamos Dynamics Structural Dynamics and Mechanical Vibration Consultants
Structural Health Monitoring using Statistical Pattern Recognition
Course Demo 15
How to Get Started in Structural Health Monitoring
We will be happy to help you get your program going: Consult for you on various aspects of your project:
Program and resource planning
Experiment design
Feature selection and identification
Statistical methods
Conduct an in-house short course tailored to your application Please contact us for any further information:
Email Hoon or Chuck directly:
http://www.la-dynamics.com
(435) 603-0375