Search

Abstract: The availability of a model to prepare, supervise and analyse vibration tests of complex non-linear mechanical systems is vital. Analytical models, however, have some limitations when it comes to integrate the complex mathematical and physical parameters of non-linear mechanical systems. In this paper, an original approach based on multilayer perceptron neural network with a time regression input vector is proposed as an alternative solution. An experimental set is designed for this purpose: a non-linear mechanical system is subjected to random, shock and swept sine excitations on a vibrating platform. Its mechanical response is measured with accelerometers. The model is trained and validated based on the raw experimental data. Finally, simulation results from the analysis are presented and discussed. [Copyright &y& Elsevier]

Abstract: In recent years, significant activity has been directed toward active control of mechanical structures. In particular, this is the case of structures subjected to random vibrations where the vibratory environment can deteriorate their performance or cause faulty operation. Development of the regulator, which defines the commands to the actuators, is done by the implementation of a small model of the system to be integrated in real time. This paper presents the active control of a generic mechanical structure and analyzes the influence of the uncertain parameters on the stability and the performance of the system by using the artificial neural network methodology. [Copyright &y& Elsevier]