Heterogeneous data fusion for the improved non-destructive detection of steel-reinforcement defects using echo state networks

Abstract

The degradation of roads is an expensive problem: in the United Kingdom alone, £27 billion was spent on road repairs between 2013 and 2019. One potential cost-saver is the early, non-destructive detection of faults. There are many available techniques, each with its own benefits and drawbacks. This paper builds upon the successful processing of magnetic flux leakage (MFL) data by echo state networks (ESNs) for damage diagnostics, by augmenting ESNs with the depth of concrete cover as part of a data fusion approach. This fusion-based ESN outperformed a number of non-fusion ESN comparators and a previously used analytical technique. Additionally, the fusion ESN had an optimal threshold value whose standard deviation was three times smaller than that of the nearest alternative technique, potentially prompting a move towards automated defect detection in ‘real-world’ applications.