FiberEUse: A Funded Project Towards the Reuse of the End-of-Life Fiber Reinforced Composites with Nondestructive Inspection

FiberEUse is a €9.8 million research project funded by the European Union since June 2017 and collaborating with 20 partners from 7 EU countries. It aims at developing different innovative solutions towards enhancing the profitability of glass and carbon fiber reinforced polymer composites (GFRP and CFRP) recycling and reuse in added-value products and high-tech applications. There are three big tasks: (i) mechanical recycling of short GFRP, (ii) thermal recycling of long fibers (both GFRP and CFRP), (iii) inspection, repairing and remanufacturing for the end-of-life (EoL) GFRP/CFRP products. As one of the partners, the main objective of our work is to design a nondestructive testing (NDT) method for recycled/repaired/remanufactured CFRP products based on hyperspectral imagery (HSI). In this paper, we will introduce the use of hyperspectral imaging for erosion detection in different materials. Our previous work on metal corrosion estimation will be discussed first. Then, the idea of this work is carried out. The experimental setup of both works is illustrated and more details of our strategy are provided with future development direction.

[1]  Ginu Rajan,et al.  Overview of Fiber Optic Sensor Technologies for Strain/Temperature Sensing Applications in Composite Materials , 2016, Sensors.

[2]  Stephen Marshall,et al.  Singular spectrum analysis for improving hyperspectral imaging based beef eating quality evaluation , 2015, Comput. Electron. Agric..

[3]  Wenjiang Huang,et al.  Potential of UV and SWIR hyperspectral imaging for determination of levels of phenolic flavour compounds in peated barley malt. , 2019, Food chemistry.

[4]  Stephen Marshall,et al.  Superpixel based Feature Specific Sparse Representation for Spectral-Spatial Classification of Hyperspectral Images , 2019, Remote. Sens..

[5]  Alberto Ferrer,et al.  Comparison of latent variable‐based and artificial intelligence methods for impurity detection in PET recycling from NIR hyperspectral images , 2018 .

[6]  Stephen Marshall,et al.  Segmented Autoencoders for Unsupervised Embedded Hyperspectral Band Selection , 2018, 2018 7th European Workshop on Visual Information Processing (EUVIP).

[7]  Stephen Marshall,et al.  MIMR-DGSA: Unsupervised hyperspectral band selection based on information theory and a modified discrete gravitational search algorithm , 2019, Inf. Fusion.

[8]  Zhijing Yang,et al.  Sparse Representation-Based Augmented Multinomial Logistic Extreme Learning Machine With Weighted Composite Features for Spectral–Spatial Classification of Hyperspectral Images , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Stephen Marshall,et al.  Hyperspectral Image Enhancement and Mixture Deep-Learning Classification of Corneal Epithelium Injuries , 2017, Sensors.

[10]  Stephen Marshall,et al.  Hyperspectral imaging for erosion detection in wind turbine blades , 2016 .

[11]  Marco Balsi,et al.  Hyperspectral characterization of marine plastic litters , 2018, 2018 IEEE International Workshop on Metrology for the Sea; Learning to Measure Sea Health Parameters (MetroSea).

[12]  Jizhou Sun,et al.  What’s Wrong with the Murals at the Mogao Grottoes: A Near-Infrared Hyperspectral Imaging Method , 2015, Scientific Reports.

[13]  A. Lystrup,et al.  Composite materials for wind power turbine blades , 2005 .

[14]  Jaime Zabalza,et al.  Feature extraction and data reduction for hyperspectral remote sensing Earth observation , 2015 .