Development and application of a deep learning–based sparse autoencoder framework for structural damage identification

Abstract

This article proposes a deep sparse autoencoder framework for structural damage identification. This framework can be employed to obtain the optimal solutions for some pattern recognition problems with highly nonlinear nature, such as learning a mapping between the vibration characteristics and structural damage. Three main components are defined in the proposed framework, namely, the pre-processing component with a data whitening process, the sparse dimensionality reduction component where the dimensionality of the original input vector is reduced while preserving the required necessary information, and the relationship learning component where the mapping between the compressed dimensional feature and the stiffness reduction parameters of the structure is built. The proposed framework utilizes the sparse autoencoders based deep neural network structure to enhance the capability and performance of the dimensionality reduction and relationship learning components with a pre-training scheme. In the final stage of training, both components are jointly optimized to fine-tune the network towards achieving a better accuracy in structural damage identification. Since structural damages usually occur only at a small number of elements that exhibit stiffness reduction out of the large total number of elements in the entire structure, sparse regularization is adopted in this framework. Numerical studies on a steel frame structure are conducted to investigate the accuracy and robustness of the proposed framework in structural damage identification, taking into consideration the effects of noise in the measurement data and uncertainties in the finite element modelling. Experimental studies on a prestressed concrete bridge in the laboratory are conducted to further validate the performance of using the proposed framework for structural damage identification.

Keywords

Deep learning neural networks sparse autoencoders structural damage identification pre-training

Get full access to this article

View all access options for this article.

References

Padil

Bakhary

Hao

The use of a non-probabilistic artificial neural network to consider uncertainties in vibration-based-damage detection. Mech Syst Signal Pr 2017; 83: 194–209.

Schmidhuber

Deep learning in neural networks: an overview. Neural Networks 2015; 61: 85–117.

Hochreiter

Bengio

Frasconi

et al . Gradient flow in recurrent nets: the difficulty of learning longterm dependencies. In: Kolen

Kremer

(eds) A field guide to dynamical recurrent neural networks. New York: IEEE Press, 2001, pp. 2–8.

Bengio

Simard

Frasconi

Learning long-term dependencies with gradient descent is difficult. IEEE T Neural Networ 1994; 5(2): 157–166.

Hinton

Salakhutdinov

RR.

Reducing the dimensionality of data with neural networks. Science 2006; 313(5786): 504–507.

Vincent

Larochelle

Bengio

et al . Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on machine learning, Helsinki, 5–9 July 2008, pp. 1096–1103. New York: ACM.

Ranzato

Boureau

Le Cun

Sparse feature learning for deep belief networks. Adv Neur In 2008; 20: 1185–1192.

Vincent

Larochelle

Lajoie

et al . Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J Mach Learn Res 2010; 11: 3371–3408.

Srivastava

Improving neural networks with dropout. Master’s Thesis, University of Toronto, Toronto, ON, Canada, 2013.

10.

Goodfellow

Warde-Farley

Mirza

et al . Maxout networks. JMLR WCP 2013; 28(3): 1319–1327.

11.

Arel

Rose

Karnowski

TP.

Deep machine learning – a new frontier in artificial intelligence research. IEEE Comput Intell Mag 2010; 5(4): 13–18.

12.

Jia

Lei

Lin

et al . Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mech Syst Signal Pr 2016; 72: 303–315.

13.

Bao

Tang

et al . Computer vision and deep learning–based data anomaly detection method for structural health monitoring. Struct Health Monit. Epub ahead of print 19 February 2018. DOI: 10.1177/1475921718757405.

14.

Lin

Nie

HW.

Structural damage detection with automatic feature-extraction through deep learning. Comput-Aided Civ Inf 2017; 32: 1025–1046.

15.

Cha

Choi

Büyüköztürk

Deep learning-based crack damage detection using convolutional neural networks. Comput-Aided Civ Inf 2017; 32(5): 361–378.

16.

Pathirage

CSN

et al . Structural damage identification based on autoencoder neural networks and deep learning. Eng Struct 2018; 172: 13–28.

17.

Glorot

Bordes

Bengio

Deep sparse rectifier neural networks. PMLR 2011; 15: 315–323.

18.

Martinez

AM.

Recognizing imprecisely localized, partially occluded, and expression variant faces from a single sample per class. IEEE T Pattern Anal 2002; 24(6): 748–763.

19.

Fidler

Skocaj

Leonardis

Combining reconstructive and discriminative subspace methods for robust classification and regression by subsampling. IEEE T Pattern Anal 2006; 28(3): 337–350.

20.

Doi

Balcan

Lewicki

. A theoretical analysis of robust coding over noisy overcomplete channels. In: Proceedings of the 18th international conference on neural information processing systems, Vancouver, BC, Canada, 5–8 December 2005, pp. 307–314. New York: ACM.

21.

Olshausen

Field

DJ.

Sparse coding with an overcomplete basis set: a strategy employed by V1?

Vision Res 1997; 37(23): 3311–3325.

22.

Ranzato

Poultney

Chopra

et al . Efficient learning of sparse representations with an energy-based model. In: Proceedings of the 19th international conference on neural information processing systems, Vancouver, BC, Canada, 4–7 December 2006, pp. 1137–1144. New York: ACM.

23.

Bengio

Learning deep architectures for AI. Found Trends Mach Learn 2009; 2(1): 1–127.

24.

Kessy

Agnan

Lewin

Alex

Strimmer

Korbinian

. Optimal whitening and decorrelation. Am Stat 2018; pp. 1–6.

25.

Bengio

Practical recommendations for gradient-based training of deep architectures. In: Montavon

Orr

Müller

(eds) Neural networks: tricks of the trade (Lecture Notes in Computer Science). New York: Springer, 2012, pp. 437–478.

26.

Joyce

JM.

Kullback-Leibler divergence. In: Lovric

(ed.) International encyclopedia of statistical science. New York: Springer, 2011, pp. 720–722.

27.

Møller

MF.

A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks 1993; 6(4): 525–533.

28.

Hao

Substructure damage identification based on wavelet domain response reconstruction. Struct Health Monit 2014; 13(4): 389–405.

29.

Xia

Hao

Brownjohn

JMW

et al . Damage identification of structures with uncertain frequency and mode shape data. Earthq Eng Struct D 2002; 31(5): 1053–1066.

30.

Lam

CT.

The selection of pattern features for structural damage detection using an extended Bayesian ANN algorithm. Eng Struct 2008; 30(10): 2762–2770.

31.

CT.

Application of Bayesian-designed artificial neural networks in phase II structural health monitoring benchmark studies. Aust J Struct Eng 2014; 15(1): 27–36.

32.

Law

Hao

. Improved damage identification in a bridge structure subject to moving vehicular loads: numerical and experimental studies. Int J Mech Sci 2013; 74: 99–111.