NEURAL-NETWORK-BASED SELECTION OF DYNAMIC SYSTEM PARAMETERS

The present paper explores the use of a global response technique util izing a neurocomputing paradigm to the solution of an inverse eigenval ue problem. For a given vibratory system, the problem is one of determ ining a set of physical construction parameters such as mass, stiffnes s, and damping, to yield a desired set of eigenvalues and eigenvectors , In absence of an exact analytical solution to the problem, approxima tions yielded by the backpropagation and an improved counterpropagatio n neural networks are examined. While estimates from both network arch itectures are acceptable for technical implementation, the CPN network is much simpler to train, Improvements to the CPN network include a d ynamic adjustment of the network size, the use of averaging operators for training, and an increased accuracy of approximations based on a n onlinear blend of interconnection weights. A state matrix representati on of a truck suspension system is used as an illustrative problem to demonstrate the effectiveness of the neurocomputing approach in such i nverse eigenvalue problems.