AUTONOMOUS DAMAGE DETECTION IN DOUBLE TRACK STEEL RAILWAY BRIDGES - - PowerPoint PPT Presentation

▶
autonomous damage detection in double track steel railway
SMART_READER_LITE
LIVE PREVIEW

AUTONOMOUS DAMAGE DETECTION IN DOUBLE TRACK STEEL RAILWAY BRIDGES - - PowerPoint PPT Presentation

Jan 04, 2024 262 likes •595 views

AUTONOMOUS DAMAGE DETECTION IN DOUBLE TRACK STEEL RAILWAY BRIDGES Ahmed Rageh Ph.D. Student, Civil Engineering, University of Nebraska-Lincoln Saeed Eftekhar Azam, Ph.D. Postdoctoral Scholar, Civil Engineering, University of Nebraska-Lincoln

slide-1
SLIDE 1

AUTONOMOUS DAMAGE DETECTION IN DOUBLE TRACK STEEL RAILWAY BRIDGES

Ahmed Rageh

Ph.D. Student, Civil Engineering, University of Nebraska-Lincoln

Saeed Eftekhar Azam, Ph.D.

Postdoctoral Scholar, Civil Engineering, University of Nebraska-Lincoln

Daniel Linzell, Ph.D., P.E.

Voelte-Keegan Professor and Department Chair, Civil Engineering, University of Nebraska-Lincoln

1

slide-2
SLIDE 2
  • Outline

Damage detection under nonstationary, unknown inputs Why Proper Orthogonal Modes as damage feature? Why ANNs for damage detection? Bridge description Train loads measured by Weigh in Motion sensors Stringer-to-floor beam connection damage detection

2

slide-3
SLIDE 3
  • Conventional approach to vibration based damage

identification:

1. Model construction: intact baseline model 2. Modal identification: typically OMA 3. Model updating 4. Damage identification

  • Challenges:

1. Modal identification: unknown, non-stationary excitations: train load 2. Model updating: curse of dimensionality for high number

  • f unknowns

3. Modal identification and model updating: Measurement noise

3

slide-4
SLIDE 4
  • Our approach:

1. Construct a model 2. Measure a set of non-stationary loads 3. Find features in response that has correlation to non- stationary loads 4. Use proper orthogonal modes of measured response as damage features 5. Train an ANN:

I. use few train loads and the model to train the network; and II. the trained network will generalize for response to unknown future loads

  • Work done:

1. Detailed FE model of the bridge was constructed 2. Axles loads were measured for 81 trains 3. ANNs were trained 4. ANNs were tested for generalization to unknown loads

4

slide-5
SLIDE 5
  • Why proper orthogonal modes?

1. Could be calculated automatically 2. Robust to measurement noises 3. Easy to interpret

  • Why ANNs:

1. Extract subtle changes from changes in damage features 2. Robust to curse of dimensionality 3. Need for minimal user training 4. Generalize well for unknown inputs

5

slide-6
SLIDE 6
  • Bridge description [Owner plans,

reports]

 Double track  Riveted construction  Pin and eyebar

6

  • Stringer-to-floor beam connection damage

detection – Analytical based

  • MATLAB code
  • Reads train loading excel files
  • Model trains in SAP2000
  • Extracts and stores strains
  • 81 trains to the west, one track, 50

axles/train

slide-7
SLIDE 7
  • Stringer-to-floor beam connection damage detection –

Analytical based

Stress time-history @ marked locations

One sensor capture damage on both sides

7

  • 250
  • 200
  • 150
  • 100
  • 50

50 100 200 300 400 500 Time Step

  • 50

50 100 150 100 200 300 400 500 Time Step

1 20

slide-8
SLIDE 8
  • POMs of 4 train loads for various noise to signal ratio levels:

8

slide-9
SLIDE 9
  • How to treat unknown

inputs?

1. Find features of response which are correlated with loads 2. Train a clustering/classification algorithm

9

  • What we did:

1. Measured train axle loads using Weigh in Motion (WIM) 2. Used the measured axles loads to calculated the structural response 3. Compared response from the model to find a correlation between response features and axle loads 4. Mean RMS of channels is the feature

slide-10
SLIDE 10
  • POMs of each of 4

groups vs all POMs together:

1. You notice categorizing POMS based on RMS values reduces variability 2. We used POMs of Group 4 for ANN training

10

slide-11
SLIDE 11
  • POMs of Group 4 and various damage levels:

1. The higher the damage level, the more pronounced the variation in POM 2. Smaller damage levels not detectable: there is still discrepancy stemming from load variations 3. We used ANNs to detect small damage levels

11

slide-12
SLIDE 12
  • Stringer-to-floor beam connection damage detection –

Analytical based

12

 POMs influenced by:

  • Loads
  • Environmental effects (future work)
  • Damage

 ANNs:

  • Half of trains in Group 4 were used for training
  • Half of trains in Group 4 were used for testing (successful)
  • Trains from Group 1, 2, and 3 yielded bad results
slide-13
SLIDE 13
  • Stringer-to-floor beam connection damage detection –

Analytical based

13

POMs Damage/load scenarios Damage location/intensity

Bending stiffness reduction of: 10:10:100% 200 damage scenarios/train

slide-14
SLIDE 14

14

 In total we measured 81 train loads

  • The trains were categorized, and divided into 4 groups
  • We trained ANN using 6 train loads, all from Group 4
  • We test ANN using 4 trains, from Group 4
slide-15
SLIDE 15
  • Stringer-to-floor beam connection damage detection
  • 6 trains used in ANN training
  • The testing trains were not used in ANN training

15

slide-16
SLIDE 16

16

  • Stringer-to-floor beam connection damage detection
  • 8 trains used in ANN training
  • The testing trains were not used in ANN training
slide-17
SLIDE 17

17

  • Stringer-to-floor beam connection damage detection
  • 6 trains used in ANN training
  • The testing trains were not used in ANN training
slide-18
SLIDE 18

18

  • Stringer-to-floor beam connection damage detection
  • 6 trains used in ANN training
  • The testing trains were not used in ANN training
slide-19
SLIDE 19
  • Stringer-to-floor beam connection damage detection
  • The testing trains were not used in ANN training

19

slide-20
SLIDE 20
  • What if the testing trains are selected from other groups?
  • The testing trains were not used in ANN training

20

slide-21
SLIDE 21
  • What if the testing trains are selected from other groups?
  • The testing trains were not used in ANN training

21

slide-22
SLIDE 22
  • What if the testing trains are selected from other groups?
  • The testing trains were not used in ANN training

22

slide-23
SLIDE 23
  • What if the testing trains are selected from other groups?
  • The testing trains were not used in ANN training

23

slide-24
SLIDE 24
  • Stringer-to-floor beam connection damage detection – Field

based

24

slide-25
SLIDE 25
  • Stringer-to-floor beam connection damage detection –

Field based

25

 POMs/loading effects:

  • Data cleansing
slide-26
SLIDE 26
  • Stringer-to-floor beam connection damage detection –

Field based

26

 POMs/loading effects:

  • Data classifying and peak-picking
slide-27
SLIDE 27
  • Stringer-to-floor beam connection damage detection –

Field based

27

 ANNs:

  • Damage scenarios via reduced strains
  • ANNs trained using healthy and damaged POMs
  • ANNs tested using signal POMs
slide-28
SLIDE 28
  • Stringer-to-floor beam connection damage detection –

Field based

28

All Testing Trains Location 13 DI = 60%

slide-29
SLIDE 29
  • Stringer-to-floor beam connection damage detection –

Field based

29

Train 29 Location 8 All DIs

slide-30
SLIDE 30
  • Conclusions

Damage detected via strains induced by unknown, nonstationary external inputs Proper orthogonal modes are robust damage features Artificial Neural Network is required for identification of large number of damage indices Features for classification of unknown input from the response matrix were found

30

slide-31
SLIDE 31

Questions?

31