A METHOD FOR NONPARAMETRIC DAMAGE DETECTION THROUGH THE USE OF NEURALNETWORKS

A neural network-based approach is presented for the detection of chan ges in the characteristics of structure-unknown systems. The approach relies on the use of vibration measurements from a 'healthy' system to train a neural network for identification purposes. Subsequently, the trained network is fed comparable vibration measurements from the sam e structure under different episodes of response in order to monitor t he health of the structure. The methodology is applied to actual data obtained from ambient vibration measurements on a steel building struc ture that was damaged under strong seismic motion during the Hyogo-Ken Nanbu Earthquake of 17 January 1995. The measurements were done befor e and after repairs to the damaged frame were made. A neural network i s trained with data after the repairs, which represents 'healthy' cond ition of the building. The trained network, which is subsequently fed data before the repairs, successfully identified the difference betwee n the damaged storey and the undamaged storey. Through this study, it is shown that the proposed approach has the potential of being a pract ical tool for a damage detection methodology applied to smart civil st ructures. (C) 1998 John Wiley & Sons, Ltd.