Structural Damage Detection by Integrating Data Fusion and Probabilistic Neural Network

Abstract

Over the past two decades, multi-sensor data fusion method has attracted increasing attention to structural health monitoring due to its inherent capabilities in extracting information from different sources and integrating them into a consistent, accurate and intelligible data set. Meanwhile, since the probabilistic neural network (PNN) describes measurement data in a Bayesian probabilistic approach, it has been successfully applied to structural damage detection (Jiang et al. 2004; Klenke et al. 1996; Ko et al. 1999; Ni et al. 2001). In order to make full use of multi-sensor data (or information) from multi-resource and to improve the diagnosis accuracy of the health conditions for complex structures, it is advisable to combine these methods and exploit their individual advantages. In this paper, a 5-phase complex structural damage detection method by integrating data fusion and PNN is developed and implemented. The proposed method is then applied to damage detection and identification of two simulation examples. The result shows that the proposed method is feasible and effective for damage identification.

Keywords

data fusion damage detection wavelet analysis energy feature fusion algorithms probabilistic neural network

Get full access to this article

View all access options for this article.

References

Abidi

M.A.

and Gonzalez

R.C.

(1992). Data Fusion in Robotics and Machine Intelligence, Academic Press, Inc., Boston, USA.

Adeli

and Karim

(2000). “Fuzzy-wavelet RBFNN model for freeway incident detection”, Journal of Transportation Engineering, ASCE, Vol. 126, No. 6, pp. 464–471.

Adeli

(2001). “Neural networks in civil engineering: 1989–2000”, Computer-Aided Civil and Infrastructure Engineering, Vol. 16, pp. 126–142.

Albrecht

Busch

Kloppenburg

Metze

and Tavan

(2000). “Generalized radial basis function networks for classification and novelty detection: Self-organization of optimal Bayesian decision”, Neural Networks, Vol. 13, pp. 1075–1093.

Ding

Y.X.

and Shen

X.Q.

(1997). “Wavelet neural network based on energy density”, China Computer Journal, Vol. 20, No. 9, pp. 832–838.

Doebling

S.W.

and Farrar

C.R.

(1999). The State of the Art in Structural Identification of Constructed Facilities, Los Alamos National Laboratory Report DRAFT, Los Alamos, USA.

Gros

X.E.

Bousigue

and Takahashi

(1999). “NDT data fusion at pixel level”, NDT & E International, vol. 32, pp. 283–292.

Gros

X.E.

(2001). Applications of NDT Data Fusion, Kluwer Academic Publishers, Boston, USA.

Hall

D.L.

(1992). Mathematical Techniques in Multi-Sensor Data Fusion, Artech House, Boston, USA.

10.

Hera

and Hou

(2004). “Application of wavelet approach for ASCE structural health monitoring benchmark studies”, Journal of Engineering Mechanics, ASCE, Vol. 130, No. 1, pp. 96–104.

11.

Jiang

S.F.

(2002). Structural Optimization and Damage Detection Based on Neural Network, Science Press, Peking, China.

12.

Jiang

S.F.

and Wang

L.S.

(2005). “Data fusion technique in the structural health monitoring”, Journal of Shenyang Jianzhu University, Vol. 21, No. 1, pp. 18–22.

13.

Jiang

S.F.

Zhang

and Yang

X.N.

(2004). “Damage identification of steel structures based on wavelet probabilistic neural network”, Proceedings of International. Symposium on the Second International Conference on Steel & Composite Structures, Choi

C.K.

ed., Seoul, Korea, September, pp. 722–732.

14.

Johnson

E. A.

Lam

H. F.

Katafygiotis

L.S.

and Beck

J.L.

(2000). “A benchmark problem for structural health monitoring and damage detection”, Proceedings of International Symposium on EM2000 (CD Rom), Austin, Tex., USA.

15.

Klenke

S. E.

and Paez

T.L.

(1996). “Damage identification with probabilistic neural networks”, Proceedings of the 14^th International Modal Analysis Conference, Dearborn, Michigan, February, pp. 99–104.

16.

J.M.

Y.Q.

and Chan

T.H.T.

(1999). “Dynamic monitoring of structural health in cable-supported bridges”, Proceedings of International Symposium on Smart Systems for Bridges, Structures and Highways, Liu

S.C.

ed., New Port Beach, USA, March, pp. 370–381.

17.

Kozinea

I.O.

and Filimonovb

Y.V.

(2000). “Imprecise reliabilities: Experiences and advances”, Reliability Engineering and System Safety, Vol. 67, pp. 75–83.

18.

S.L.

and Li

(2003). “The method of roller bearing fault monitoring based on wavelet packet energy feature”, Journal of System Simulation, Vol. 15, No. 1, pp. 76–80.

19.

Mallat

(1989). “A theory for multi-resolution signal decomposition: The wavelet representation”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 11, pp. 674–692.

20.

Y.Q.

Jiang

S.F.

and Ko

J.M.

(2001). “Application of the adaptive probabilistic neural network to the damage detection of Tsing Ma Bridge”, Proceedings of the International Conference on Health Monitoring and Management of Civil Infrastructure Systems, Aktan

A.E.

ed., New Port Beach, USA, March, pp. 347–356.

21.

Y.Q.

Wang

B.S.

and Ko

J.M.

(2002). “Constructing input vectors to neural networks for structural damage identification”, Smart Materials and Structures, Vol. 11, pp. 825–833.

22.

Qian

(2005). Introduction to Time-Frequency and Wavelet Analysis, China Machine Press, Peking, China.

23.

Specht

D.F.

(1990). “Probabilistic neural networks”, International Journal of Neural Networks, Vol. 3, pp. 109–118.

24.

Yeung

W.T.

and Smith

J.W.

(2005). “Damage detection in bridges using neural networks for pattern recognition of vibration signatures”, Engineering Structures, Vol. 27, pp. 685–698.