Abstract
This paper uses fuzzy neural network modelling for the identification of structural parameters of multi-storey shear buildings. First the identification has been done using response of the structure subject to ambient vibration with fuzzy initial condition. Then forced vibration with horizontal displacement in fuzzified form has been used to investigate the identification procedure. The model has been developed to handle the data in fuzzified form for multi-storey shear structure, and the procedure is tested for the identification of the stiffness parameters of simple example problems using the prior values of the design parameters.
Similar content being viewed by others
References
Brownjohn JMW (2003) Ambient vibration studies for system identification of tall buildings. Earthq Eng Struct Dyn 32(1):71–96
Chakraverty S, Sharma RK, Singh VP (2003) Soft-computing approach for identification of dynamic systems. J New Build Mater Constr World 9(2):50–56
Chakraverty S (2004) Modelling for identification of stiffness parameters of multi-storey structure from dynamic data. J Sci Ind Res 63(2):142–148
Chakraverty S (2005) Identification of structural parameters of multi-storey shear buildings from modal data. Earthq Eng Struct Dyn 34(6):543–554
Chakraverty S (2007) Identification of structural parameters of two-storey shear buildings by the iterative training of neural networks. J Archit Sci Rev 50(4):380–384
Chakraverty S (2009) Vibration of plates. CRC Press, Taylor and Francis Group, Boca Raton, pp 1–411
Datta AK, Shrikhande M, Paul DK (1998) System identification of buildings: a review. In: Proceedings of eleventh symposium on earthquake engineering. University of Roorkee, Roorkee, India
Hegde G, Sinha R (2008) Parameter identification of torsionally coupled shear buildings from earthquake response records. Earthq Eng Struct Dyn 37(11):313–1331
Hong AL, Betti R, Lin CC (2009) Identification of dynamic models of a building structure using multiple earthquake records. Struct Control Health Monit 16(2):178–199
Huang CS, Hung SL, Wen CM, Tu TT (2003) A neural network approach for structural identification and diagnosis of a building from seismic response data. Earthq Eng Struct Dyn 32(2):187–206
Ibanez P (1979) Review of analytical and experimental techniques for improving structural dynamic models. Weld Res Council Bull 249:1–193
Ishibuchi H, Fujioka R, Tanaka H (1992) An architecture of neural networks for input vectors of fuzzy numbers. In: IEEE international conference on fuzzy systems, pp 1293–1300
Ishibuchi H, Tanaka H, Okada H (1993) Fuzzy neural networks with fuzzy weights and fuzzy biases. In: IEEE international conference on neural networks, vol 3, pp 1650–1655
Ishibuchi H, Morioka K, Tanaka H (1994) A fuzzy neural network with trapezoid fuzzy weights. In: IEEE world congress on computational intelligence proceedings of the third IEEE conference on fuzzy systems, vol 1, pp 228–233
Ishibuchi H, Kwon K, Tanaka H (1995) A learning algorithm of fuzzy neural networks with triangular fuzzy weights. Fuzzy Sets Syst 71:277–293
Ishibuchi H, Morioka K, Turksen IB (1995) Learning by fuzzified neural networks. Int J Approx Reason 13:327–358
Kao CY, Hung SL (2003) Detection of structural damage via free vibration responses generated by approximating artificial neural networks. Comput Struct 81(28–29):2631–2644
Khanmirza E, Khaji N, Majd VJ (2011) Model updating of multistory shear buildings for simultaneous identification of mass, stiffness and damping matrices using two different soft-computing methods. Expert Syst Appl 38(5):5320–5329
Leu VQ, Mwasilu F, Choi HH, Lee J, Jung JW (2013) Robust fuzzy neural network sliding mode control scheme for IPMSM drives. Int J Electron 101(7):919–938
Lu PC (1998) The application of fuzzy neural network techniques in constructing an adaptive car-following indicator. AIEDAM 12(3):231–241
Masri SF, Bekey GA, Sassi H, Caughey TK (1982) Non parametric identification of a class of nonlinear multidegree dynamic systems. Earthq Eng Struct Dyn 10(1):1–30
Masri SF, Smyth AW, Chassiakos AG, Caughey TK, Hunter NF (2000) Application of neural networks for detection of changes in nonlinear systems. J Eng Mech 126(7):666–676
Natke HG (1982) Identification of vibrating structures. Springer, Berlin, pp 1–510
Quek ST, Wang W, Koh CG (1999) System identification of linear MDOF structures under ambient excitation. Earthq Eng Struct Dyn 28(1):61–77
Wu ZS, Xu B, Yokoyama K (2002) Decentralized parametric damage based on neural networks. Comput Aided Civ Infrastruct Eng 17(3):175–184
Xu B, Wu Z, Yokoyama K (2002) A localized identification strategy with neural networks and its application to structural health monitoring. J Struct Eng 48A:419–427
Xu B, Wu Z, Chen G, Yokoyama K (2004) Direct identification of structural parameters from dynamic responses with neural networks. Eng Appl Artif Intell 17(8):931–943
Yang JN, Lei Y, Pan S, Huang N (2003) System identification of linear structures based on Hilbert-Huang spectral analysis, part 1: normal modes. Earthq Eng Struct Dyn 32(9):1443–1467
Yu W, Li X (2004) Fuzzy identification using fuzzy neural networks with stable learning algorithms. IEEE Trans Fuzzy Syst 12(3):411–420
Yuan P, Wu Z, Ma X (1998) Estimated mass and stiffness matrices of shear building from modal test data. Earthq Eng Struct Dyn 27(5):415–421
Yun CB, Bahng EY (2000) Substructural identification using neural networks. Comput Struct 77(1):41–52
Zhang H, Dai X (2012) The application of fuzzy neural network in medicine—a survey. In: International conference on biology and biomedical sciences, vol 9, pp 111–116
Acknowledgments
The authors would like to acknowledge funding from the Ministry of Earth Sciences, New Delhi, to carry out this investigation. The authors also thank the anonymous reviewers for their suggestions which have helped in improving the contents of this paper.
Author information
Authors and Affiliations
Corresponding author
Appendix: Fuzzy set theory and preliminaries
Appendix: Fuzzy set theory and preliminaries
The following Fuzzy arithmetic operations are used in this paper for defining fuzzified neural network.
-
(A)
Let X be an universal set. Then the fuzzy subset A of X is defined by its membership function
$$\mu_{A} :\;X \to \left[ {0,1} \right]$$which assign a real number μ A (x) in the interval [0, 1], to each element x ∊ X, where the value of μ A (x) at x shows the grade of membership of x in A.
-
(B)
Given a fuzzy set A in X and any real number α ∊ [0, 1], then the α- cut or α-level or cut worthy set of A, denoted by A α is the crisp set
$$A_{\alpha } = \left\{ {x \in X\left| {\mu_{A} (x) \ge \alpha } \right.} \right\}$$ -
(C)
A triangular fuzzy number (TFN) A can be defined as a triplet \(\left[ {\underline{a} ,ac,\bar{a}} \right]\). Its member ship function is defined as
$$\mu_{A} (x) = \left\{ {\begin{array}{*{20}l} {0,} \hfill & {x < \underline{a} } \hfill \\ {\frac{{x - \underline{a} }}{{ac - \bar{a}}},} \hfill & {\underline{a} \le x \le ac} \hfill \\ {\frac{{\bar{a} - x}}{{\bar{a} - ac}},} \hfill & {ac \le x \le \bar{a}} \hfill \\ {0,} \hfill & {x > \bar{a}} \hfill \\ \end{array} } \right.$$Above TFN may be transformed to an interval form A α by α- cut as
$$A_{\alpha } = \left[ {\underline{a}^{\left( \alpha \right)} ,\bar{a}^{(\alpha )} } \right] = \left[ {(ac - \underline{a} )\alpha + \underline{a} , - (\bar{a} - ac)\alpha + \bar{a}} \right]$$where a (α) and \(\overline{a}^{\left( \alpha \right)}\) are the lower and upper limits of the α-level set A α .
1.1 Operation of fuzzy numbers
We introduce arithmetic operations on fuzzy numbers and the results are expressed in terms of membership functions ∀x, y, z ∊ R as below
-
1.
Addition: \(\mu_{A( + )B} (z) = \hbox{max} \{ \mu_{A} (x) \wedge \mu_{B} (y)|z = x + y\} .\)
-
2.
Multiplication: \(\mu_{A( \cdot )B} (z) = \hbox{max} \{ \mu_{A} (x) \wedge \mu_{B} (y)|z = x \cdot y\} .\)
-
3.
Nonlinear mapping: \(\mu_{f(Net)} (z) = \hbox{max} \left\{ {\mu_{Net} (x)|z = f(x)} \right\} .\)
Rights and permissions
About this article
Cite this article
Chakraverty, S., Sahoo, D.M. Fuzzy neural network-based system identification of multi-storey shear buildings. Neural Comput & Applic 28, 597–612 (2017). https://doi.org/10.1007/s00521-015-2101-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-015-2101-y