http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Fault detection of composite beam by using the modal parameters and RBFNN technique
Irshad Ahmad Khan,Dayal Ramakrushna Parhi 대한기계학회 2015 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.29 No.4
The detection of transverse cracks in terms of their location and intensity by using the radial basis function neural network (RBFNN)technique is analyzed in the current research and validated with experimental investigation. The glass fiber-reinforced epoxy composite isused in this research because of its valuable features, such as high stiffness and strength-to-weight ratios, good fatigue and wear resistance,and damage tolerance capability compared with isotropic material. The theoretical and numerical investigations are performed toobtain a relationship between the change in natural frequencies and mode shapes for the cracked and noncracked composite beam. Numericalanalysis is performed by using the finite element software ANSYS on cracked and noncracked composite beams to measure themodal parameters, such as natural frequencies and mode shapes. These parameters are used to design an artificial intelligent controllerbased on the RBFNN-type neural network for predicting crack severity and its intensity. The relative natural frequencies and modeshapes (First, second, and third modes) of vibration are used as input data to the RBFNN controller, and the relative crack locations andcrack depths are the output of RBFNN. Results from theoretical and numerical analysis are compared with the experimental results, and agood agreement is observed between them.