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...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.展开更多
The authors regret corrections in the Figure captions as below.1.Fig.1 Caption Current version:Fig.1.The content of substances in Sour tea solu-tions at different stages of digestion(A-C)1.0 mg/mL solution:(A)TP,(B)TF...The authors regret corrections in the Figure captions as below.1.Fig.1 Caption Current version:Fig.1.The content of substances in Sour tea solu-tions at different stages of digestion(A-C)1.0 mg/mL solution:(A)TP,(B)TF,(C)FAA.(D-H)1.5 mg/mL solution:(D)CAF,(E)GA,(F)quercetin,(G)myricetin,(H)catechins.Different letters(a-c)indicate significant differences among digestion stages as determined by one-way ANOVA followed by Duncan's test.Data are presented as mean±SD(n=X).Different lowercase letters above the bars/points indicate signifi-cant differences among groups according to one-way ANOVA followed by Duncan's multiple range test(p<0.05).展开更多
基金the National Natural Science Foundation of China (No.59908003)the Natural Science Foundation of Hubei Province (No.99J035)
文摘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.
文摘The authors regret corrections in the Figure captions as below.1.Fig.1 Caption Current version:Fig.1.The content of substances in Sour tea solu-tions at different stages of digestion(A-C)1.0 mg/mL solution:(A)TP,(B)TF,(C)FAA.(D-H)1.5 mg/mL solution:(D)CAF,(E)GA,(F)quercetin,(G)myricetin,(H)catechins.Different letters(a-c)indicate significant differences among digestion stages as determined by one-way ANOVA followed by Duncan's test.Data are presented as mean±SD(n=X).Different lowercase letters above the bars/points indicate signifi-cant differences among groups according to one-way ANOVA followed by Duncan's multiple range test(p<0.05).
