Neural Network Fatigue Life Prediction in 7075-T6 Aluminum from Acoustic Emission Data

<p>The objective of this research was to classify acoustic emission (AE) -data associated with fatigue cracks in aluminum fatigue specimens and to use early cycle life AE data to predict failure in such members. An AE data acquisition system coupled with a Kohonen self organizing map and a back propagation neural network were used to perform the analysis. AE waveforms were recorded during fatigue cycling of twenty-four notched 7075-T6 aluminum specimens using broad-band piezoelectric transducers. A Kohonen self organizing map was used to classify the AE flaw growth signals. The signals were classified into three categories based on their AE parameters: plastic deformation, plane strain fracture and mixed mode (plane strain and plane stress) fracture.</p> <p>Acoustic emission amplitude data from the twenty-four low cycle fatigue tests were used to train and test a back propagation neural network for prediction of cycles to failure. The input data consisted of amplitude frequency histograms (30-100 dB) and the actual cycle lives. The output was the predicted cycles to failure or fatigue life. A network capable of predicting cycles to failure with a worst case error of- 9.30% was the final result.</p>

Name thesis:degree_name

Master of Aerospace Engineering

Level thesis:degree_level

Thesis - Open Access

Discipline thesis:degree_discipline

Aerospace Engineering

Year

2004

Author dc:creator

• Ibekwe, Emeka Chigozie

Contributors dc:contributor

• Eric v. K. Hill
• Frank J. Radosta
• Jean-Michel Dhainaut

• neural network
• fatigue
• aluminum
• acoustic emission
• Aerospace Engineering
• Structures and Materials

Repository record dc:identifier

https://commons.erau.edu/db-theses/276

OAI identifier oai:identifier

oai:commons.erau.edu:db-theses-1124