Interest in damage source detection and localization of engineering structures by non-destructive techniques has been increasingly growing. As a non-destructive technique, acoustic emission (AE) has developed rapidly to detect dynamic defects and their evolution behaviors of composite structures, based on the transient elastic waves produced by rapid energy release due to the geometry change of structures. Damage source localization attracts relatively less attention compared to damage pattern recognition. In this paper, acoustic emission (AE) technology is utilized to monitor the real-time condition of the composite scarf joint under tensile loading. A new framework is proposed for damage source localization as following. First, AE feature selection is accomplished by employing the principal component analysis to avoid the Curse of Dimensionality. Second, a plurality of low-dimensional vectors corresponding to AE source events detected by two AE sensors are combined into a matrix, which is subsequently decomposed into a product of two matrices. Third, the AE signal is correlated with the position information by using a characteristic matrix of the distance between the damage source and sensors while another matrix contains the relationships between the source and damage modes. Finally, a novel framework for source localization is constructed based on supervised learning model. The positioning method proposed in this paper can be further generalized to damage source localization of various structures and materials in engineering practice.

*Keywords:* Non-destructive detection, Damage source localization, Acoustic emission (AE), Adhesively bonded joint, Supervised learning


A New Framework for Damage Source Localization in Composite Scarf Joints Based on Acoustic Emission and Supervised Learning

Division / Sponsors: 
Pressure Vessels & Piping (PVP)


Paper Proceedings: https://asmedigitalcollection.asme.org/PVP/PVP2020/volume/83815

PVP2020 - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.