Artificial neural networks for impact force reconstruction on composite plates and relevant uncertainty propagation

Recent challenges in structural health monitoring have been arising from new safety requirements and the increasing use of composite materials for aerospace structures. The behavior of composite materials is much more complex than that of metallic alloys [1], [2]. For composite materials, impacts are one of the main causes of damage and it becomes crucial to correctly determine if an impact has occurred, and therefore if damage is present, especially because composites are subjected to the so called barely visible impact damage which can eventually lead to the catastrophic failure of the system [3].