摘要
A nonparametric structural damage detection methodology based on neural networks method ispresented for health monitoring of structure-unknown systems.In this approach appropriate neural networksare trained by use of the modal test data from a ‘healthy’structure.The trained networks which are subse-quently fed with vibration measurements from the same structure in different stages have the capability of rec-ognizing the location and the content of structural damage and thereby can monitor the health of the structure.A modified back-propagation neural network is proposed to solve the two practical problems encountered bythe traditional back-propagation method,i.e.,slow learning progress and convergence to a false local mini-mum.Various training algorithms,types of the input layer and numbers of the nodes in the input layer areconsidered.Numerical example results from a 5-degree-of-freedom spring-mass structure and analyses on theexperimental data of an actual 5-storey-steel-frame demonstrate that neural-networks-based method is a robustprocedure and a practical tool for the detection of structural damage,and that the modified back-propagationalgorithm could improve the computational efficiency as well as the accuracy of detection.
A nonparametric structural damage detection methodology based on neuralnetworks method is presented for health monitoring of structure-unknown systems. In this approachappropriate neural networks are trained by use of the modal test data from a 'healthy' structure.The trained networks which are subsequently fed with vibration measurements from the same structurein different stages have the capability of recognizing the location and the content of structuraldamage and thereby can monitor the health of the structure. A modified back-propagation neuralnetwork is proposed to solve the two practical problems encountered by the traditionalback-propagation method, i.e., slow learning progress and convergence to a false local minimum.Various training algorithms, types of the input layer and numbers of the nodes in the input layerare considered. Numerical example results from a 5-degree-of-freedom spring-mass structure andanalyses on the experimental data of an actual 5-storey-steel-frame demonstrate thatneural-networks-based method is a robust procedure and a practical tool for the detection ofstructural damage, and that the modified back-propagation algorithm could improve the computationalefficiency as well as the accuracy of detection.
基金
the National Natural Science Foundation of China (No.59908003)
the Natural Science Foundation of Hubei Province (No.99J035)
