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. Eric R. Perrell
Dr. Yi Zhao
Composites have grown in importance in the aerospace industry where high specific strength is a priority. Weight reduction in space vehicles is critical because of the exorbitant cost associated with placing objects into space. Major weight savings have been obtained by switching from all metal pressure vessels to composite overwrapped pressure vessels (COPVs). Due to the nature of composites, current nondestructive analysis procedures for COPVs are not adequate for assessing structural integrity. As such, new methods must be developed. Presented herein is one such method.
A method for burst pressure prediction using parametric filtering of acoustic emission (AE) data along with the specification of a categorical variable defining damage type has yielded accurate results for COPVs. The process, while accurate - 5.85 % worst case prediction error — required that the inflicted damage type of the bottle be known in order to make accurate predictions.
The newly developed method relied heavily upon filtering of the parametric data recorded by an acoustic emission detection system. This edited data set was then used to make burst pressure predictions using a three layer backpropagation neural network given the AE amplitude distributions as input.
Scholarly Commons Citation
Dion, Seth-Andrew T., "Neural Network Burst Pressure Prediction in Composite Overwrapped Pressure Vessels from Acoustic Emission Data" (2006). Theses - Daytona Beach. 43.