Search

Data-driven analysis for damage assessment has a large potential in structural health monitoring (SHM) systems, where sensors are permanently attached to the structure, enabling continuous and frequent measurements. In this contribution, we propose a machine learning (ML) approach for automated damage detection, based on an ML toolbox for industrial condition monitoring. The toolbox combines multiple complementary algorithms for feature extraction and selection and automatically chooses the best combination of methods for the dataset at hand. Here, this toolbox is applied to a guided wave-based SHM dataset for varying temperatures and damage locations, which is freely available on the Open Guided Waves platform. A classification rate of 96.2% is achieved, demonstrating reliable and automated damage detection. Moreover, the ability of the ML model to identify a damaged structure at untrained damage locations and temperatures is demonstrated.

The scaled boundary finite element method is applied to the simulation of Lamb waves for ultrasonic testing applications. With this method, the general elastodynamic problem is solved, while only the boundary of the domain under consideration has to be discretized. The reflection of the fundamental Lamb wave modes from cracks of different geometry in a steel plate is modeled. A test problem is compared with commercial finite element software, showing the efficiency and convergence of the scaled boundary finite element method. A special formulation of this method is utilized to calculate dispersion relations for plate structures. For the discretization of the boundary, higher-order elements are employed to improve the efficiency of the simulations. The simplicity of mesh generation of a cracked plate for a scaled boundary finite element analysis is illustrated.

The generation of airborne ultrasound is presented using the thermoacoustic principle applied to carbon materials at the micro- and nanoscale. Such materials are shown to be capable of emitting ultrasound when being fed by an alternating current. We tested the acoustic performance of carbon fibers, bucky papers and electrospun polyacrylonitrile-derived carbon nanofibers and determined the sound pressure for frequencies up to 350 kHz. A comparison between the experimental results and the theoretical prediction showed remarkable agreement for frequencies up to 150 kHz. Beyond 150 kHz, we found slight deviations from the expected sound pressure dependence on the square root of the frequency. [ABSTRACT FROM AUTHOR]