<p>Recent advances in instrumentation, sensing, data management and processing provides greater capability to develop intelligent systems capable of automated diagnostics and prognostics that relate to complex engineering applications. In this context, crack initiation and growth is of primary consideration both for material performance evaluation as well as for damage assessment at the structural level. While several monitoring and evaluation methods related to cracking have been proposed and a number of them have been standardized and transitioned to commercial devices, recent needs for real-time assessment have created the challenge to connect data acquisition with information extraction that can be leveraged in modeling and predictions, including both statistical/probabilistic and physics-based approaches. This investigation presents a novel approach to leverage multi-physics Nondestructive Evaluation (NDE) datasets in an Internet of Things (IoT) framework capable of creating a novel intelligent monitoring system capable of providing near real-time diagnostics and prognostics. To demonstrate the approach a laboratory demonstration was used to obtain data using compact-tension specimens of an aerospace-grade aluminum alloy subjected to both monotonic and cyclic loading in accordance with ASTM standards. Acoustic Emission and Digital Image Correlation datasets were acquired and used to produce cross-validated sets of multi-physics NDE information that were processed using an in-house built IoT system capable of edge and cloud computing. The main innovation of this approach is the fact that a combination of edge and fog hardware and software proves to be advantageous in implementing a data structure that can be used in unsupervised and supervised machine learning operations that can successfully flag the initiation and subsequent crack growth. Such information is then used to form inputs to modeling to further illustrate the value of adopting this framework in fracture and fatigue investigations. A discussion will also follow on how this approach can benefit verification and validation methods as well as how it relates to the recent advances in dynamic and data-driven digital twin applications.</p>

An Intelligent System for Crack Growth Monitoring

Paper Proceedings: https://asmedigitalcollection.asme.org/SMASIS/SMASIS2021/volume/85499

ASME 2021 Smart Materials, Adaptive Structures and Intelligent Systems (SMASIS2021)

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.