Comparison between a Linear Regression and an Artificial Neural Network Model to Detect and Localize Damage in the Powder Mill Bridge

Abstract

This paper evaluates the ability of two different data-driven models to detect and localize simulated structural damage in an in-service bridge for long-term structural health monitoring (SHM). Strain gauge data collected over 4 years is used to characterize the undamaged state of the bridge. The Powder Mill Bridge in Barre, Massachusetts, U.S., which has been instrumented with strain gauges since its opening in 2009, is used as a case study, and the strain gauges used in this study are located at 26 different stations throughout the bridge superstructure. A linear regression (LR) model and an artificial neural network (ANN) model are evaluated based on the following criteria: (a) the ability to accurately predict the strain at each location in the undamaged state of the bridge; (b) the ability to detect simulated structural damage to the bridge superstructure; and (c) the ability to localize simulated structural damage. Both the LR and the ANN models were able to predict the strain at the 26 stations with an average error of less than 5%, indicating that both methodologies were effective in characterizing the undamaged state of the bridge. A calibrated finite element model was then used to simulate damage to the Powder Mill Bridge for three damage scenarios: fascia girder corrosion, girder fracture, and deck delamination. The LR model proved to be just as effective as the ANN model at detecting and localizing damage. A recommended protocol is thus presented for integrating data-driven models into bridge asset management systems.

Get full access to this article

View all access options for this article.

References

Santini-Bell

Lefebvre

P. J.

Sanayei

Brenner

B. R.

Sipple

J. D.

Peddle

Objective Load Rating of a Steel-Girder Bridge using Structural Modeling and Health Monitoring. Journal of Structural Engineering, Vol. 139, No. 10, 2013, pp. 1771–1779. http://doi.org/10.1061/(ASCE)ST.1943-541X.0000599.

Weinstein

J. C.

Sanayei

Brenner

B. R.

Bridge Damage Identification using Artificial Neural Networks. Journal of Bridge Engineering, Vol. 23, No. 11, 2018, p. 04018084. https://doi.org/10.1061/(ASCE)BE.1943-5592.0001302.

Kakadiaris

I. A.

Physics-Based Modeling, Analysis and Animation. Technical Report No. MS-CIS-93-45. University of Pennsylvania Department of Computer and Information Science, 1993.

Toksoy

Aktan

A. E.

Bridge-Condition Assessment by Modal Flexibility. Experimental Mechanics, Vol. 34, No. 3, 1994, pp. 271–278. https://doi.org/10.1007/BF02319765.

Sanayei

Phelps

J. E.

Sipple

J. D.

Santini-Bell

Brenner

B. R.

Instrumentation, Nondestructive Testing, and Finite-Element Model Updating for Bridge Evaluation using Strain Measurements. Journal of Bridge Engineering, Vol. 17, No. 1, 2012, pp. 130–138. http://doi.org/10.1061/(ASCE)BE.1943-5592.0000228.

Sanayei

Reiff

A. J.

Brenner

B. R.

Imbaro

G. R.

Load Rating of a Fully Instrumented Bridge: Comparison of LRFR Approaches. Journal of Performance of Constructed Facilities, Vol. 30, No. 2, 2016, p. 04015019. http://doi.org/10.1061/(ASCE)CF.1943-5509.0000752.

Garcia-Palencia

A. J.

Santini-Bell

Sipple

J. D.

Sanayei

Structural Model Updating of an In-Service Bridge using Dynamic Data. Structural Control and Health Monitoring, Vol. 22, No. 10, 2015, pp. 1265–1281. http://doi.org/10.1002/stc.1742.

Kim

Kawatani

Pseudo-Static Approach for Damage Identification of Bridges Based on Coupling Vibration with a Moving Vehicle. Structure and Infrastructure Engineering – Maintenance, Management, Life-Cycle Design and Performance, Vol. 4, No. 5, 2008, pp. 371–379. https://doi.org/10.1080/15732470701270082.

Shahidi

Physics-Based and Data-Driven Methods with Compact Computing Emphasis for Structural Health Monitoring. Doctoral dissertation. Lehigh University, 2016.

10.

Weber

Paultre

Damage Identification in a Truss Tower by Regularized Model Updating. Journal of Structural Engineering, Vol. 136, No. 3, 2010, pp. 307–316.

11.

James

Witten

Hastie

Tibshirani

An Introduction to Statistical Learning: With Applications in R. Springer, New York, N.Y., 2013.

12.

Seo

Czaplewski

T. M.

Kimn

Hatfield

Integrated Structural Health Monitoring System and Multi-Regression Models for Determining Load Ratings for Complex Steel Bridges. Measurement, Vol. 75, 2015, pp. 308–319. https://dx-doi-org.web.bisu.edu.cn/10.1016/j.measurement.2015.07.043.

13.

Bishop

C. M.

Pattern Recognition and Machine Learning. Springer, Cambridge, 2006.

14.

Hornik

K. M.

Stinchcombe

White

Multilayer Feedforward Networks Are Universal Approximators. Neural Networks, Vol. 2, 1989, pp. 359–366.

15.

Smarsly

Dragos

Wiggenbrock

Machine Learning Techniques for Structural Health Monitoring. Proc., 8th European Workshop on Structural Health Monitoring (EWSHM), Bilbao, Spain, 2016.

16.

Kudva

J. N.

Munir

Tan

P. W.

Damage Detection in Smart Structures Using Neural Networks and Finite-Element Analyses. Smart Materials and Structures, Vol. 1, 1992, pp. 106–112.

17.

Reiff

A. J.

Sanayei

Vogel

R. M.

Statistical Bridge Damage Detection using Girder Distribution Factors. Engineering Structures, Vol. 109, 2016, pp. 139–151.

18.

Lee

S. K.

Current State of Bridge Deterioration in the U.S. – Part 2. Materials Performance, Vol. 51, 2012, pp. 2–7.

19.

Mann

H. B.

Whitney

D. R.

On a Test of Whether One of Two Random Variables Is Stochastically Larger than the Other. The Annals of Mathematical Statistics, Vol. 18, 1947, pp. 50–60.

20.

Sugiyama

Introduction to Statistical Machine Learning. Morgan Kaufmann, Cambridge, Mass., 2016.

21.

New Hampshire Department of Transportation. Bridge Program Recommended Investment Strategy. New Hampshire Department of Transportation, 2018.

22.

University of New Hampshire. The Living Bridge Portsmouth Memorial Bridge: Project Overview. https://livingbridge.unh.edu/. Accessed June 21, 2018.