基于粗集的改进对向传播网络结构损伤识别-福州大学.pdf

30 6 JOURNAL OF V IBRAT ION AND SHOCK Vol. 30 No. 6 2011 , ( , 350108) : , ( RCPN ) , RCPN, 1 , , , , : ; ; ; : TU31 . 5; TP2 4; TP183 : A Structural dam age identification based on rough set and revised counter-propagation network JIANG Shao-f ei, LIN Jie ( College of C ivil Engineering, Fuzhou Un iversity, Fuzhou 350108, China) Abstract: In order to make full use of redundant, complementary and uncertain information and thus assess the structural health statesw ith a structural health mon itoring system, a new damage identification method by integrating rough setw ith revised counter-propagation network ( RCPN) w asproposed. In themethod, rough setw as used to dealw ith data so as to reduce their uncertainties and spatial dmi ensions, the currentCPN modelw as revised to mi prove the capab ilities of processing uncertainties and carring on classification, and then the RCPN modelw as used for damage identification. To validate the proposed method, single- and mu lt-i damage patterns of a frame w ere identified as an example, and some mi portant factors, such as measurement noise, neural newt ork models and data processing technologies, w ere investigated emphatically. The resu lts show that the proposed method can effectively reduce the spatial dmi ension of data and is of preferable damage identification accuracy and robustness. K ey words: rough set; revised counter-propagation newt ork; damage identification; attributes reduction , [ 1, 2] , , ,