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.
Highlights
Damage detection is an important aspect for characterization of any material in structural health monitoring
We show that simple k-nearest neighbor (KNN) architectures are generally sufficient for classifying the damages with differences in dimension as small as 100 μm
The numbers of time and frequency samples, which serve as the size of feature vectors in the raw signal and power spectral densities (PSDs), respectively, are significantly larger than the number of features generated in Higher order crossings (HOC) and Discrete cosine transform (DCT)
Summary
Damage detection is an important aspect for characterization of any material in structural health monitoring. Detection of change in micro-damages is important for sensor technology for structural health monitoring. It is important to detect, localize and quantify the defect in the piezo- ceramic in order to avoid false alarm in structural health monitoring applications. We propose a methodology to quantify the precursor to damages in the PZT ceramic sensors that can provide sufficient warning time for early retrofitting of the structure. The precursor to damages is defined as any hidden feature resulting from early degradation of the structure or the sensor, leading to microscale defects or microstructural and morphological changes. Ultrasonic inspection is used extensively for quality assessment of the structures and microscale damage detection in a wide range of materials in the present time.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
