Access to master’s theses is restricted to current ERAU students, faculty, and staff.
Date of Award
Thesis - Open Access
Master of Aerospace Engineering
Dr. Eric v. K. Hill
Dr. Yi Zhao
Dr. Ilteris Demirkiran
This purpose of this research was to identify fatigue crack growth and predict failure for 7075-T6 aluminum notched bars under uniaxial tensile loading using acoustic emission (AE) data. The experiments performed in this study extend the results obtained by previous researchers who used maximum cyclic loads of 4,000, 3,000, and 2,000 pounds at a stress ratio of R = 0.0 and a frequency of 1 Hz to perform the fatigue tests. For this research the cyclic load remained at 2,000 pounds, but an additional ten specimens were tested in order to increase the amount of AE data available to the backpropagation neural network (BPNN) for prediction of cyclic life to failure. In addition, the AE data obtained from cyclic testing were filtered and successfully classified using a Kohonen self-organizing map (SOM) to identify the plane stress and plane strain failure mode data. Furthermore, the early cycle (< 25% of fatigue life) AE amplitude distribution data from the test samples were used to predict fatigue lives using the BPNN. The increased AE data from the ten new specimens allowed the neural network to predict fatigue lives on ten total samples with a worst case error of -9.39%. The prediction results are presented along with comparisons to the previous research. Thus, neural network analysis of acoustic emission data provided both accurate fatigue life prediction and classification of the failure mechanisms involved.
Scholarly Commons Citation
Okur, Muhammed Arif, "Neural Network Fatigue Life Prediction in Notched Aluminum Specimens from Acoustic Emission Data" (2010). Theses - Daytona Beach. 246.