Wootton, AJ, Day, CR and Haycock, P (2018) Fault Detection in Steel-Reinforced Concrete Using Echo State Networks. 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, 2018. pp. 1-8. ISSN 2161-4407

[thumbnail of PID5350031.pdf]
PID5350031.pdf - Accepted Version

Download (630kB) | Preview


The cost of maintaining and repairing the world's ageing reinforced concrete infrastructure continues to increase, and is expected to cost the United States economy alone $58 billion by 2020. Consequently, the use of non-destructive testing technologies for the early identification of faults in roads and bridges is becoming increasingly important. One such technology is the Electromagnetic Anomaly Detection (EMAD) technique, which exploits non-destructive magnetic flux leakage to detect defects in steel reinforcing meshes embedded in concrete. Despite the increasing need for such techniques, the data analysis options currently in use are limited. This paper presents an application of Echo State Networks, a recurrent neural network from the field of reservoir computing that features a short-term memory, to data obtained using the EMAD technique. Having been trained to discern real defect signals from other anomalous magnetic features, the performance of the ESNs was then compared to that of an analytical data analysis technique that is currently used to process EMAD data. It was found that average ESN performance was comparable in terms of AUC, while the optimal threshold was more consistent, greatly aiding application in the `real-world'. A qualitative analysis of the output of both methods on an unseen testing dataset also demonstrated the superiority of ESNs for practical use as a real time tool for on-site inspections.

Item Type: Article
Additional Information: © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Uncontrolled Keywords: bridges (structures), condition monitoring, construction industry, data analysis, echo, electromagnetic fields, inspection, magnetic flux, nondestructive testing, real-time systems, recurrent neural nets, reinforced concrete, reservoirs, roads, signal processing, steel, structural engineering, bridges, nondestructive magnetic flux leakage, steel reinforcing meshes, recurrent neural network, short-term memory, defect signals, analytical data analysis technique, United States economy, nondestructive testing technologies, roads, echo state networks, fault detection, steel-reinforced concrete infrastructure, electromagnetic anomaly detection technique, defects detection, ESN performance, reservoir computing, optimal threshold, real-time tool, on-site inspection, repairing cost, Reservoirs, Concrete, Corrosion, Steel, Magnetic flux, Bridges, Electromagnetics, Echo State Networks, Reservoir Computing, spatially varying data, structural health monitoring, steel-reinforced concrete, magnetic flux leakage
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Natural Sciences > School of Computing and Mathematics
Related URLs:
Depositing User: Symplectic
Date Deposited: 21 Mar 2019 11:48
Last Modified: 21 Mar 2019 11:59
URI: https://eprints.keele.ac.uk/id/eprint/6098

Actions (login required)

View Item
View Item