Title :
Prognostics of crack propagation in structures using time delay neural network
Author :
Khan, Faisal ; Eker, Omer.F. ; Jennions, Ian K. ; Tsourdos, Antonios
Author_Institution :
Integrated Vehicle Health Management Centre Cranfield University, MK43 0AL, UK
Abstract :
In today´s IVHM system, diagnostics and prognostic play a crucial part in the system safety while reducing the operating and maintenance costs. Structural health management is a vital part of IVHM as arguably structures are the biggest and most costly part of the system, thus the failure of the structure could lead to catastrophic results. The failure of a structure is usually caused by cracks or fractures, to identify the cracks and their growth would be desirable for the SHM. While detection of cracks and the prediction of crack growth is a daunting task, demarcation of the crack is essential to prevent failures. This article presents a technique for the prognostic of crack propagation through aluminium by utilising a time delay neural network algorithm. The Virkler dataset has been used and the remaining useful life has been calculated.
Keywords :
Accuracy; Degradation; Hidden Markov models; Maintenance engineering; Mathematical model; Measurement; Neural networks; Integrated vehicle health management (IVHM); condition based maintenance (CBM); structure health management (SHM); time delay neural network (TDNN);
Conference_Titel :
Prognostics and Health Management (PHM), 2015 IEEE Conference on
Conference_Location :
Austin, TX, USA
DOI :
10.1109/ICPHM.2015.7245040