The purpose of this research was to demonstrate the capability of neural networks to discriminate between individual acoustic emission (AE) signals originating from crack growth and rivet rubbing (fretting) in aluminum lap joints. AE waveforms were recorded during tensile fatigue cycling of six notched and riveted 7075-T6 specimens using a broadband piezoelectric transducer and a computer interfaced oscilloscope. The source of 1,311 signals was identified based on triggering logic, amplitude relationships, and time of arrival data collected from the broad-band transducer and three additional 300 Hz resonant transducers bonded to the specimens. The power spectrum of each waveform was calculated and normalized to correct for variable specimen geometry and wave propagation effects. In order to determine the variation between individual signals of the same class, the normalized spectra were clustered onto a two-dimensional feature space using a Kohonen self organizing map (SOM). Then 132 crack growth and 137 rivet rubbing spectra were used to train a back-propagation neural network to provide automatic pattern classification. Although there was some overlap between the clusters mapped in the Kohonen feature space, the trained back-propagation neural network was able to classify the remaining 463 crack growth signals with a 94% accuracy and the 367 rivet rubbing signals with a 99% accuracy.
","abstract_html":"<p>The purpose of this research was to demonstrate the capability of neural networks to discriminate between individual acoustic emission (AE) signals originating from crack growth and rivet rubbing (fretting) in aluminum lap joints. AE waveforms were recorded during tensile fatigue cycling of six notched and riveted 7075-T6 specimens using a broadband piezoelectric transducer and a computer interfaced oscilloscope. The source of 1,311 signals was identified based on triggering logic, amplitude relationships, and time of arrival data collected from the broad-band transducer and three additional 300 Hz resonant transducers bonded to the specimens. The power spectrum of each waveform was calculated and normalized to correct for variable specimen geometry and wave propagation effects. In order to determine the variation between individual signals of the same class, the normalized spectra were clustered onto a two-dimensional feature space using a Kohonen self organizing map (SOM). Then 132 crack growth and 137 rivet rubbing spectra were used to train a back-propagation neural network to provide automatic pattern classification. Although there was some overlap between the clusters mapped in the Kohonen feature space, the trained back-propagation neural network was able to classify the remaining 463 crack growth signals with a 94% accuracy and the 367 rivet rubbing signals with a 99% accuracy.</p>","abstract_has_math":false,"creators":["Almeida, Adriano F. de"],"institution":null,"degree_name":"Master of Science in Aerospace Engineering","degree_level":"Thesis - Open Access","degree_discipline":"Graduate Studies","degree_department":null,"school":null,"contributors":["Eric v. K. Hill","Frank J. Radosta","John R. Novy"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":1994,"date_issued":"1994-05-01T07:00:00Z","date_published":"1994-05-01T07:00:00Z","updated_at":"2026-07-27T19:25:16Z","subjects":["neural networks","acoustic emission","aluminum lap joints","Aerospace Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://commons.erau.edu/db-theses/305","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Eric v. K. Hill","Frank J. Radosta","John R. Novy"]},{"key":"dc:creator","label":"Author","values":["Almeida, Adriano F. de"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"thesis:degree_discipline","label":"Discipline","values":["Graduate Studies"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis - Open Access"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Aerospace Engineering"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["neural networks","acoustic emission","aluminum lap joints","Aerospace Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://commons.erau.edu/db-theses/305"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The purpose of this research was to demonstrate the capability of neural networks to discriminate between individual acoustic emission (AE) signals originating from crack growth and rivet rubbing (fretting) in aluminum lap joints. AE waveforms were recorded during tensile fatigue cycling of six notched and riveted 7075-T6 specimens using a broadband piezoelectric transducer and a computer interfaced oscilloscope. The source of 1,311 signals was identified based on triggering logic, amplitude relationships, and time of arrival data collected from the broad-band transducer and three additional 300 Hz resonant transducers bonded to the specimens. The power spectrum of each waveform was calculated and normalized to correct for variable specimen geometry and wave propagation effects. In order to determine the variation between individual signals of the same class, the normalized spectra were clustered onto a two-dimensional feature space using a Kohonen self organizing map (SOM). Then 132 crack growth and 137 rivet rubbing spectra were used to train a back-propagation neural network to provide automatic pattern classification. Although there was some overlap between the clusters mapped in the Kohonen feature space, the trained back-propagation neural network was able to classify the remaining 463 crack growth signals with a 94% accuracy and the 367 rivet rubbing signals with a 99% accuracy.
"]},{"key":"dc:title","label":"Title","values":["Neural Network Detection of Fatigue Crack Growth in Riveted Joints Using Acoustic Emission"]}]}],"canonical_facts":{"dc:contributor":["Eric v. K. Hill","Frank J. Radosta","John R. Novy"],"dc:creator":["Almeida, Adriano F. de"],"dc:description.abstract":["The purpose of this research was to demonstrate the capability of neural networks to discriminate between individual acoustic emission (AE) signals originating from crack growth and rivet rubbing (fretting) in aluminum lap joints. AE waveforms were recorded during tensile fatigue cycling of six notched and riveted 7075-T6 specimens using a broadband piezoelectric transducer and a computer interfaced oscilloscope. The source of 1,311 signals was identified based on triggering logic, amplitude relationships, and time of arrival data collected from the broad-band transducer and three additional 300 Hz resonant transducers bonded to the specimens. The power spectrum of each waveform was calculated and normalized to correct for variable specimen geometry and wave propagation effects. In order to determine the variation between individual signals of the same class, the normalized spectra were clustered onto a two-dimensional feature space using a Kohonen self organizing map (SOM). Then 132 crack growth and 137 rivet rubbing spectra were used to train a back-propagation neural network to provide automatic pattern classification. Although there was some overlap between the clusters mapped in the Kohonen feature space, the trained back-propagation neural network was able to classify the remaining 463 crack growth signals with a 94% accuracy and the 367 rivet rubbing signals with a 99% accuracy.
"],"dc:identifier":["https://commons.erau.edu/db-theses/305"],"dc:subject":["neural networks","acoustic emission","aluminum lap joints","Aerospace Engineering"],"dc:title":["Neural Network Detection of Fatigue Crack Growth in Riveted Joints Using Acoustic Emission"],"thesis:degree_discipline":["Graduate Studies"],"thesis:degree_level":["Thesis - Open Access"],"thesis:degree_name":["Master of Science in Aerospace Engineering"]},"updated_at":"2026-07-27T19:25:16Z"}