Identification of Damping and Dynamic Young’ s Modulus of a Structural Adhesive Using Radial Basis Function Neural Networks and Modal Data K. Jahani & A.S. Nobari Received: 14 July 2009 / Accepted: 18 September 2009 / Published online: 18 November 2009 # Society for Experimental Mechanics 2009 Abstract In this paper, the radial basis function neural networks (RBFNN) was applied to the problem of identifying dynamic Young’ s modulus and damping char- acteristic of a structural adhesive, using modal data. To identify Young’ s modulus from undamped model, an appropriate RBFNN using modal data (mode shape and natural frequency) in each mode is developed. Based on a previous work, in order to identify loss factor, two approaches adopted in the identification process. In the first one, a two stage RBFNN is developed. In stage I, Young’ s modulus is identified from undamped model and in stage II using the results of stage I an appropriate RBFNN is developed in each mode for identification of loss factor by implementing real parts of eigenvalues of damped model. In the second approach, a one stage RBFNN is developed using real and imaginary parts of eigenvalues of damped model to identify Young’ s moduli and loss factors simultaneously. The repeatability and consistency of the method is proved by repeating the identification process for several times. The validity of results is proved by comparing the results with those identified in a previous work. Keywords Radial basis function neural networks . Adhesive . Young’ s Modulus . Damping . Loss factor Introduction Identification of dynamic characteristics of adhesives has been a subject of extensive research and many valuable publications can be cited in this respect [1–7]. All of the techniques used in identification process are prone to some sort of numerical ill-condition if the joint under investiga- tion is very stiff. This is due to the fact that the system characteristics (such as eigenvalues and/or eigenvectors) which are used in identification become insensitive to variation of joint stiffness when this stiffness goes beyond a certain limit set by the relative stiffness of the parent structures and the joint. Here an alternative method for determination of properties of a structural adhesive using artificial neural network (ANN) is presented. Identification process using model updating techniques is confronted with more complex formula and mathematical difficulties. In other words, ANN method requires less complicated calculations, though knowledge regarding the ranges of changes of real operating parameters of the structure under investigation is necessary. The use of neural network in finite element model updating [8, 9] and joint identification [10] has shown that a multilayer perceptron(MLP) or a radial basis function (RBF) network can provide a good mapping between frequency (or modal) domain and physical parameters of the system being studied. The comparison of these two types of networks, show that there always exists an RBF network capable of accurately mimicking a specified MLP, and vice versa [10]. In this paper, the radial basis function neural networks (RBFNN) is used to identify the dynamic properties of a structural adhesive. The main advantage of an RBFNN is that it has single global minima whose weight-space co-ordinates can be calculated by the least square technique. Also, an RBFNN may be trained K. Jahani (*) Faculty of Mechanical Engineering, University of Tabriz, Tabriz, Iran e-mail: ka_jahani@tabrizu.ac.ir A.S. Nobari Aerospace Engineering Department, Amirkabir University of Technology, Tehran, Iran Experimental Mechanics (2010) 50:607–619 DOI 10.1007/s11340-009-9302-1