Damage mechanism identification has scientific and practical ramifications for the structural health monitoring, design, and application of composite systems. Recent advances in machine learning uncover pathways to identify the waveform-damage mechanism relationship in higher-dimensional spaces for a comprehensive understanding of damage evolution. This review evaluates the state of the field, beginning with a physics-based understanding of acoustic emission waveform feature extraction, followed by a detailed overview of waveform clustering, labeling, and error analysis strategies. Fundamental requirements for damage mechanism identification in any machine learning framework, including those currently in use, under development, and yet to be explored, are discussed.
The diffusion of arsenic in polycrystalline silicon films has been studied over the temperature range 750–950 °C and for grain sizes 210–510 nm. Rutherford backscattering spectrometry was used to measure the concentration profiles of arsenic, initially introduced into the polysilicon by ion implantation, after various annealing steps. The concentration profiles were found to be determined by a combination of two factors—the low diffusivity in the bulk of the rains and the much higher diffusivity in the grain boundaries. The diffusivity of arsenic in the grain boundaries was independent of concentration, with an activation energy of 3.9 eV, very close to that of the low-concentration arsenic diffusivity in single-crystal silicon. However, the value of the diffusivity was 8.6×104 exp(−3.9/kT)cm2/s, four orders of magnitude higher than the single-crystal value. The diffusivity in the interior of the grains was the same as that in single-crystal silicon.
In this work, we demonstrate that damage mechanism identification from acoustic emission (AE) signals generated in minicomposites with elastically similar constituents is possible. AE waveforms were generated by SiC/SiC ceramic matrix minicomposites (CMCs) loaded under uniaxial tension and recorded by four sensors (two models with each model placed at two ends). Signals were encoded with a modified partial power scheme and subsequently partitioned through spectral clustering. Matrix cracking and fiber failure were identified based on the frequency information contained in the AE event they produced, despite the similar constituent elastic properties of the matrix and fiber. Importantly, the resultant identification of AE events closely followed CMC damage chronology, wherein early matrix cracking is later followed by fiber breaks, even though the approach is fully domain-knowledge agnostic. Additionally, the partitions were highly precise across both the model and location of the sensors, and the partitioning was repeatable. The presented approach is promising for CMCs and other composite systems with elastically similar constituents.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.