Classification of Micro-Damage in Piezoelectric Ceramics Using Machine Learning of Ultrasound Signals
Open Access
- 27 September 2019
- Vol. 19 (19), 4216
- https://doi.org/10.3390/s19194216
Abstract
Ultrasound based structural health monitoring of piezoelectric material is challenging if a damage changes at a microscale over time. Classifying geometrically similar damages with a difference in diameter as small as 100 m is difficult using conventional sensing and signal analysis approaches. Here, we use an unconventional ultrasound sensing approach that collects information of the entire bulk of the material and investigate the applicability of machine learning approaches for classifying such similar defects. Our results show that appropriate feature design combined with simple k-nearest neighbor classifier can provide up to 98% classification accuracy even though conventional features for time-series data and a variety of classifiers cannot achieve close to 70% accuracy. The newly proposed hybrid feature, which combines frequency domain information in the form of power spectral density and time domain information in the form of sign of slope change, is a suitable feature for achieving the best classification accuracy on this challenging problem.
Keywords
This publication has 45 references indexed in Scilit:
- Ultrasonic sensor based defect detection and characterisation of ceramicsUltrasonics, 2014
- A Bayesian approach for damage localization in plate-like structures using Lamb wavesSmart Materials and Structures, 2013
- Defect Classification in Pipes by Neural Networks Using Multiple Guided Ultrasonic Wave Features Extracted After Wavelet ProcessingJournal of Pressure Vessel Technology, 2005
- Imaging and measurement of local mechanical material properties by atomic force acoustic microscopySurface and Interface Analysis, 2002
- Subsurface defect detection in materials using optical coherence tomographyOptics Express, 1998
- The random subspace method for constructing decision forestsIeee Transactions On Pattern Analysis and Machine Intelligence, 1998
- Subsurface Defect Detection in Ceramics Using an Optical Gated Scatter ReflectometerJournal of the American Ceramic Society, 1996
- Direct imaging of travelling Rayleigh waves by stroboscopic X-ray topographyNature, 1982
- An Algorithm for Finding Best Matches in Logarithmic Expected TimeACM Transactions on Mathematical Software, 1977