Quantitative nondestructive evaluation with ultrasonic method using neural networks and computational mechanics

Oishi, Atsuya; Yamada, Kanji; Yoshimura, Shinobu; Yagawa, Genki

doi:10.1007/bf00350265

Cited by 42 publications

(12 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For a general discussion of various applications in structural mechanics see, e.g., Berke and Hajela (1992). Damage identi®cation problems by means of static data have been treated among others in Wu et al (1992) and by means of dynamic data among others in Rhim and Lee (1995), Oishi et al (1995).…”

Section: Neural Network Solution Methodsmentioning

confidence: 99%

“…Recall here that the main idea behind the back propagation neural network model is that (e.g., Oishi et al 1995) a speci®c norm between the network's output z H j , for inputs equal torz j Y p l , respectively, and the known outputs z j for j 1Y F F F Y k, is iteratively minimized during the learning phase. In this sense, a neural network identi®-cation procedure is classi®ed as a nonparametric structural identi®cation method, because no parametric model is assumed for the solution of the identi®cation problem itself (Natke 1993).…”

Section: Neural Network Solution Methodsmentioning

confidence: 99%

“…Haslinger et al 1986;Outrata andZowe 1992, Stavroulakis 1995a, b). In fact, nonsmooth optimization techniques Outrata and Zowe (1992), Stravroulakis (1995a, b), genetic algorithms Chen and Ou (1995), Kalman ®ltering iterations Tosaka et al (1995), and neural networks Oishi et al (1995) have been applied for the solution of related problems or problems with comparable complexity. The simultaneous consideration of more than one loading cases is expected to be necessary as well, since then, it is more feasible that the nonlinear crack is activated and manifests itself in the measurements.…”

Section: Introductionmentioning

confidence: 99%

“…Among others, elastodynamic identi®cation problems are considered in Tanaka et al (1991) and Oishi et al (1995). In Tanaka et al (1991), the elastodynamic inverse analysis problem for time-harmonic excitations is solved by the boundary element method.…”

Section: Introductionmentioning

confidence: 99%

“…This effect of including noisy information in this procedure is mainly reported in Tanaka et al (1991) while the method of it is described in previous publications of the same authors. In Oishi et al (1995) an ultrasonic, nondestructive evaluation technique is simulated by elastodynamic boundary element calculations. The length or both the length and the position of a given vertical crack in a rectangular plate is identi®ed.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Nondestructive elastostatic identification of unilateral cracks through BEM and neural networks

Stavroulakis¹,

Antes²

1997

Computational Mechanics

View full text Add to dashboard Cite

An inverse problem in nonlinear elastostatics is considered which concerns the identi®cation of unilateral contact cracks by means of boundary measurements for given static loadings. Highly nonlinear structural behaviour like closed cracks can hardly be identi®ed. In this case, the analysis of more than one loading cases is proposed and tested in this paper. The direct problem is modelled by using a direct multiregion boundary element formulation. The arising linear complementarity problem is solved explicitly by a pivoting (Lemke) technique. In view of the complexity of the inverse problem, a neural network based identi®cation approach is adopted which uses feed-forward multilayer neural networks trained by back-propagation, error-driven supervised training. The applicability of the method is demonstrated by some numerical examples.

show abstract

Section: Neural Network Solution Methodsmentioning

confidence: 99%

Section: Neural Network Solution Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Nondestructive elastostatic identification of unilateral cracks through BEM and neural networks

Stavroulakis¹,

Antes²

1997

Computational Mechanics

View full text Add to dashboard Cite

show abstract

New Regularization by Transformation for Neural Network Based Inverse Analyses and Its Application to Structure Identification

Yoshimura

Matsuda

Yagawa

1996

Int. J. Numer. Meth. Engng.

Self Cite

View full text Add to dashboard Cite

SUMMARYThe present authors have been developing an inverse analysis approach using the multilayer neural network and the computational mechanics. This approach basically consists of the following three subprocesses. First, parametrically varying model parameters of a system, their corresponding responses of the system are calculated through computational mechanics simulations such as the finite element analyses, each of which is an ordinary direct analysis. Each data pair of model parameters vs. system responses is called training pattern. Second, a neural network is iteratively trained using a number of training patterns. Here the system responses are given to the input units of the network, while the model parameters to be identified are shown to the network as teacher data. Finally, some system responses measured are given to the well-trained network, which immediately outputs appropriate model parameters even for untrained patterns. This is an inverse analysis. This paper proposes a new regularization method suitable for the inverse analysis approach mentioned above. This method named the Generalized-Space-Lattice (GSL) transformation transforms original input and/or output data points of all training patterns onto uniformly spaced lattice points over a multi-dimensional space. The topological relationships among all the data points are maintained through this transformation. The neural network is then trained using the GSL-transformed training patterns. Since this method significantly remedies localization of training patterns caused due to strong nonlinearity of problem, the neural network can learn the training patterns efficiently as well as accurately. Fundamental performances of the present inverse analysis approach combined with the GSL transformation are examined in detail through the identification of a vibrating non-uniform beam in Young's modulus based on the observation of its multiple eigenfrequencies and eigenmodes.

show abstract

Crack and Flaw Identification in Statics and Dynamics, using Filter Algorithms and Soft Computing

Stavroulakis

Engelhardt

Antes

Parameter Identification of Materials and Structures

View full text Add to dashboard Cite

Quantitative nondestructive evaluation with ultrasonic method using neural networks and computational mechanics

Cited by 42 publications

References 23 publications

Nondestructive elastostatic identification of unilateral cracks through BEM and neural networks

Nondestructive elastostatic identification of unilateral cracks through BEM and neural networks

New Regularization by Transformation for Neural Network Based Inverse Analyses and Its Application to Structure Identification

Crack and Flaw Identification in Statics and Dynamics, using Filter Algorithms and Soft Computing

Contact Info

Product

Resources

About