Title :
Crack Fault Diagnosis Based on MEP Based Neural Network
Author :
Liu, Mingjun ; Xiu, Liming ; Jia, Guangfeng ; Chen, Yuehui
Author_Institution :
Sch. of Electr. Eng. & Autom., Harbin Inst. of Technol., Harbin, China
Abstract :
The Multi Expression Programming (MEP) and Neural Network (NN) is applied to the crack fault diagnosis of structure. The inherent frequency and the position of the crack obtained by ANSYS are used as parameters of the neural network. This approach employs MEP to evolve the architecture and the parameters encoded in the NN. This framework allows input variables selection, over-layer connections for the various nodes involved. It is showed that the proposed method is feasible to diagnose the crack fault of structure.
Keywords :
cracks; fault diagnosis; mathematical programming; mechanical engineering computing; neural nets; ANSYS; MEP based neural network; crack fault diagnosis; input variables selection; multi expression programming; overlayer connections; Algorithm design and analysis; Artificial neural networks; Bridges; Fault diagnosis; Feedforward neural networks; Feedforward systems; Input variables; Inspection; Neural networks; Safety;
Conference_Titel :
Computer Science and Computational Technology, 2008. ISCSCT '08. International Symposium on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-3746-7
DOI :
10.1109/ISCSCT.2008.274
