Acoustic emission monitoring and failure behavior discrimination of 8YSZ thermal barrier coatings under Vickers indentation testing

Towards a Diagnostic Tool for Diagnosing Joint Pathologies: Supervised Learning of Acoustic Emission Signals

“…The feature selection method used is described in [29]. First, the ten most common features used in previous studies were selected [18,30,31] and then normalised to give a weighting using X = X−µ σ with µ the mean value of the descriptor and σ the standard deviation. Next, the correlation matrix was calculated and subjected to complete link hierarchical clustering.…”

“…The classification accuracy obtained in this study is comparable with other studies that have utilised machine learning algorithms to analyse AE signals. Qiao et al [18] obtained a 93% average classification accuracy when using a BP neural network to classify 8YSZ thermal barrier coatings according to the indentation failure experienced. In using KNN to classify AE signals acquired during the fatigue testing of carbon fibre composites, Momon et al [29] obtained an above 90% classification accuracy.…”

“…SOM-k was the most effective at classifying AE responses to failures. Qiao et al [18] also used k-means clustering to classify AE signals from ceramic thermal barrier coatings during indentation testing into three distinct categories associated with different failure modes. Using back propagation (BP) neural networks to further identify failure types of the coatings after thermal exposure, the results showed that AE measurements could distinguish between the mechanisms of high-temperature oxidation that accelerated thermal barrier degradation.…”

Added Cutting Teeth to Promote Surface Crack Incisions for Cutting Sandstone

“…However, the method to promote surface crack incision lacks su cient study. Fortunately, the recent study by Xiao et al (2019) may shed some light on how to promote surface crack incisions. They applied the Vickers indenter (Fig.…”