AUTHOR=Mohamadi Sara , Lattanzi David , Azari Hoda TITLE=Fusion and Visualization of Bridge Deck Nondestructive Evaluation Data via Machine Learning JOURNAL=Frontiers in Materials VOLUME=7 YEAR=2020 URL=https://www.frontiersin.org/journals/materials/articles/10.3389/fmats.2020.576918 DOI=10.3389/fmats.2020.576918 ISSN=2296-8016 ABSTRACT=

To maintain infrastructure safety and integrity, nondestructive evaluation (NDE) technologies are often used for detection of subsurface defects and for holistic condition assessment of structures. While the rapid advances in data collection and the diversity of available sensing technologies provide new opportunities, the ability to efficiently process data and combine heterogeneous data sources to make robust decisions remains a challenge. Heterogeneous NDE measurements often conflict with one another and methods to visualize integrated results are usually developed ad hoc. In this work, a framework is presented to support fusion of multiple NDE techniques in order to improve both detection and quantification accuracy while also improving the visualization of NDE results. For data sources with waveform representations, the discrete wavelet transform (DWT) is used to extract salient features and facilitate fusion with scalar-valued NDE measurements. The description of a signal in terms of its salient features using a wavelet transform allows for capturing the significance of the original data, while suppressing measurement noise. The complete set of measurements is then fused using nonparametric machine learning so as to relax the need for Bayesian assumptions regarding statistical distributions. A novel visualization schema based on classifier confidence intervals is then employed to support holistic visualization and decision making. To validate the capabilities of the proposed methodology, an experimental prototype system was created and tested from NDE measurements of laboratory-scale bridge decks at Turner-Fairbank highway research center (TFHRC). The laboratory decks exhibit various types of artificial defects and several non-destructive tests were previously carried out by research center technicians to characterize the existing damages. The results suggest that the chosen feature extraction process, in this case the DWT, plays a critical role in classifier performance. The experimental evaluation also indicates a need for nonlinear machine learning algorithms for optimal fusion performance. In particular, support vector machines provided the most robust and consistent data fusion and defect detection capabilities. Overall, data fusion combinations are shown to provide more accurate and consistent detection results when compared to single NDE detection approaches, particularly for the detection of subsurface delamination.