Accurate characterization of fragment fly-out properties from high-speed warhead detonations is essential for estimation of collateral damage and lethality for a given weapon. Real warhead dynamic detonation tests are rare, costly, and often unrealizable with current technology, leaving fragmentation experiments limited to static arena tests and numerical simulations. Stereoscopic imaging techniques can now provide static arena tests with time-dependent tracks of individual fragments, each with characteristics such as fragment IDs and their respective position vector. Simulation methods can account for the dynamic case but can exclude relevant dynamics experienced in real-life warhead detonations. This research leverages machine learning methodologies to predict fragmentation characteristics using data from this imaging technique and simulation data combined. Gaussian mixture models (GMMs), fit via expectation maximization (EM), are used to model fragment track intersections on a defined surface of intersection. After modeling the fragment distributions, k-nearest neighbor (K-NN) regressors are used to predict the desired fragmentation characteristics. Using Monte Carlo simulations, the K-NN regression is shown to predict the distributions for the total number of fragments intersecting a given surface and the total fragment velocity and mass associated with that surface. An ability to predict fragment fly-out characteristics accurately and quickly would provide information which can then be used to evaluate the collateral damage and lethality of a given weapon.
","abstract_html":"<p>Accurate characterization of fragment fly-out properties from high-speed warhead detonations is essential for estimation of collateral damage and lethality for a given weapon. Real warhead dynamic detonation tests are rare, costly, and often unrealizable with current technology, leaving fragmentation experiments limited to static arena tests and numerical simulations. Stereoscopic imaging techniques can now provide static arena tests with time-dependent tracks of individual fragments, each with characteristics such as fragment IDs and their respective position vector. Simulation methods can account for the dynamic case but can exclude relevant dynamics experienced in real-life warhead detonations. This research leverages machine learning methodologies to predict fragmentation characteristics using data from this imaging technique and simulation data combined. Gaussian mixture models (GMMs), fit via expectation maximization (EM), are used to model fragment track intersections on a defined surface of intersection. After modeling the fragment distributions, k-nearest neighbor (K-NN) regressors are used to predict the desired fragmentation characteristics. Using Monte Carlo simulations, the K-NN regression is shown to predict the distributions for the total number of fragments intersecting a given surface and the total fragment velocity and mass associated with that surface. An ability to predict fragment fly-out characteristics accurately and quickly would provide information which can then be used to evaluate the collateral damage and lethality of a given weapon.</p>","abstract_has_math":false,"creators":["Larsen, Katharine"],"institution":null,"degree_name":"Master of Science in Aerospace Engineering","degree_level":"Thesis - Open Access","degree_discipline":"Aerospace Engineering","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-10-01T07:00:00Z","date_published":"2022-10-01T07:00:00Z","updated_at":"2026-07-27T19:25:10Z","subjects":["Machine Learning","Fragmentation","Gaussian Mixture Models","K-Nearest Neighbor Regression","Regression Learning","Artificial Intelligence and Robotics","Dynamical Systems","Navigation, Guidance, Control, and Dynamics","Numerical Analysis and Scientific Computing","Other Aerospace Engineering","Probability"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://commons.erau.edu/edt/708","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Larsen, Katharine"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"thesis:degree_discipline","label":"Discipline","values":["Aerospace Engineering"]},{"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":["Machine Learning","Fragmentation","Gaussian Mixture Models","K-Nearest Neighbor Regression","Regression Learning","Artificial Intelligence and Robotics","Dynamical Systems","Navigation, Guidance, Control, and Dynamics","Numerical Analysis and Scientific Computing","Other Aerospace Engineering","Probability"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://commons.erau.edu/edt/708"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Accurate characterization of fragment fly-out properties from high-speed warhead detonations is essential for estimation of collateral damage and lethality for a given weapon. Real warhead dynamic detonation tests are rare, costly, and often unrealizable with current technology, leaving fragmentation experiments limited to static arena tests and numerical simulations. Stereoscopic imaging techniques can now provide static arena tests with time-dependent tracks of individual fragments, each with characteristics such as fragment IDs and their respective position vector. Simulation methods can account for the dynamic case but can exclude relevant dynamics experienced in real-life warhead detonations. This research leverages machine learning methodologies to predict fragmentation characteristics using data from this imaging technique and simulation data combined. Gaussian mixture models (GMMs), fit via expectation maximization (EM), are used to model fragment track intersections on a defined surface of intersection. After modeling the fragment distributions, k-nearest neighbor (K-NN) regressors are used to predict the desired fragmentation characteristics. Using Monte Carlo simulations, the K-NN regression is shown to predict the distributions for the total number of fragments intersecting a given surface and the total fragment velocity and mass associated with that surface. An ability to predict fragment fly-out characteristics accurately and quickly would provide information which can then be used to evaluate the collateral damage and lethality of a given weapon.
"]},{"key":"dc:title","label":"Title","values":["Machine Learning to Predict Warhead Fragmentation In-Flight Behavior from Static Data"]}]}],"canonical_facts":{"dc:creator":["Larsen, Katharine"],"dc:description.abstract":["Accurate characterization of fragment fly-out properties from high-speed warhead detonations is essential for estimation of collateral damage and lethality for a given weapon. Real warhead dynamic detonation tests are rare, costly, and often unrealizable with current technology, leaving fragmentation experiments limited to static arena tests and numerical simulations. Stereoscopic imaging techniques can now provide static arena tests with time-dependent tracks of individual fragments, each with characteristics such as fragment IDs and their respective position vector. Simulation methods can account for the dynamic case but can exclude relevant dynamics experienced in real-life warhead detonations. This research leverages machine learning methodologies to predict fragmentation characteristics using data from this imaging technique and simulation data combined. Gaussian mixture models (GMMs), fit via expectation maximization (EM), are used to model fragment track intersections on a defined surface of intersection. After modeling the fragment distributions, k-nearest neighbor (K-NN) regressors are used to predict the desired fragmentation characteristics. Using Monte Carlo simulations, the K-NN regression is shown to predict the distributions for the total number of fragments intersecting a given surface and the total fragment velocity and mass associated with that surface. An ability to predict fragment fly-out characteristics accurately and quickly would provide information which can then be used to evaluate the collateral damage and lethality of a given weapon.
"],"dc:identifier":["https://commons.erau.edu/edt/708"],"dc:subject":["Machine Learning","Fragmentation","Gaussian Mixture Models","K-Nearest Neighbor Regression","Regression Learning","Artificial Intelligence and Robotics","Dynamical Systems","Navigation, Guidance, Control, and Dynamics","Numerical Analysis and Scientific Computing","Other Aerospace Engineering","Probability"],"dc:title":["Machine Learning to Predict Warhead Fragmentation In-Flight Behavior from Static Data"],"thesis:degree_discipline":["Aerospace Engineering"],"thesis:degree_level":["Thesis - Open Access"],"thesis:degree_name":["Master of Science in Aerospace Engineering"]},"updated_at":"2026-07-27T19:25:10Z"}