Horizon 2020 Marie Skłodowska-Curie Innovative Training Network

Matteo Vagnoli

BSc, MSc
Home/Matteo Vagnoli
Matteo Vagnoli 2018-10-31T16:15:32+00:00
Early Stage Researcher
University of Nottingham (United Kingdom)

Project 9: Railway bridge condition monitoring and fault diagnostics

Click on the icons for Matteo’s email, blog and Linkedin profile

Research Interests:

System reliability; Fault diagnostics; Risk assessment; Health monitoring; Nuclear safety; Sensitivity analysis; Dynamic reliability

Biography:

Matteo Vagnoli gained a BSc in Energy Engineering from Politecnico di Milano in Italy. After graduating with honors in his MSc in Nuclear Engineering, he worked as a research fellow and teaching assistant in collaboration with the Laboratory of Signal and Risk Analysis (LASAR), under the supervision of Dott. Francesco Di Maio and Prof. Enrico Zio. His work was centered on developing innovative methods of risk-based post-processing and on-line clustering methods, computational methods for dynamic reliability analysis of industrial systems, as well as Mathematical and Statistical models within the Integrated Deterministic and Probabilistic Safety Analysis (IDPSA) framework, and evaluating the impact of climate change in the Energy supply system.

Before joining TRUSS ITN in September 2015, he had been the referee of scientific journals and conferences and participated in International conferences. A summary of his research highlights and training, dissemination and outreach activities in TRUSS  other than network-wide events, is provided in the pdf below, followed by more detailed info on his research outputs.

ESR9_Summary

Research Outputs:

  • Di Maio, F., Vagnoli, M. and Zio, E. (2015), “Risk-Based Clustering for Near Misses Identification in Integrated Deterministic and Probabilistic Safety Analysis”, Science and Technology of Nuclear Installations, vol. 2015, Article ID 693891, 29 pages, 2015. [DOI]
  • Sahlin, U., Di Maio, F., Vagnoli, M. and Zio, E. (2015), “Evaluating the impact of climate change on the risk assessment of nuclear power plants”, Safety and Reliability of Complex Engineered Systems, Taylor & Francis Group, London, ISBN 978-1-138-02879-1.
  • Di Maio, F., Vagnoli, M. and Zio, E. (2016), “Transient identification by clustering based on Integrated Deterministic and Probabilistic Safety Analysis outcomes, Annals of Nuclear Energy, 87: 217-227.
  • Di Maio, F., Baronchelli, S., Vagnoli, M. and Zio, E. (2017), “Prime Implicants Determination by Differential Evolution for Dynamic Reliability Analysis of Non-Coherent Systems”, Annals of Nuclear Energy, 102: 91-105.
  • Vagnoli, M., Di Maio, F. and Zio, E. (2017), “Ensembles of climate change models for robust risk assessment of nuclear power plants”, Special Issue of Part O: Journal of Risk and Reliability. [DOI].

Publications in TRUSS

Journal papers
A large amount of data is generated by Structural Health Monitoring (SHM) systems and, as a consequence, processing and interpreting this data can be difficult and time consuming. Particularly, if work activities such as maintenance or modernization are carried out on a bridge or tunnel infrastructure, a robust data analysis is needed, in order to accurately and quickly process the data and provide reliable information to decision makers. In this way the service disruption can be minimized and the safety of the asset and the workforce guaranteed. In this paper a data mining method for detecting critical behaviour of a railway tunnel is presented. The method starts with a pre-processing step that aims to remove the noise in the recorded data. A feature definition and selection step is then performed to identify the most critical area of the tunnel. An ensemble of change-point detection algorithms is proposed, in order to analyse the critical area of the tunnel and point out the time when unexpected behaviour occurs, as well as its duration and location. The work activities, which are carried out at the time of occurrence of the critical behaviour and have caused this behaviour, are finally identified from a database of the work schedule and used for the validation of the results. Using the proposed method, fast and reliable information about infrastructure condition is provided to decision makers. [DOI]

Railway importance in the transportation industry is increasing continuously, due to the growing demand of both passenger travel and transportation of goods. However, more than 35% of the 300,000 railway bridges across Europe are over 100-years old, and their reliability directly impacts the reliability of the railway network. This increased demand may lead to higher risk associated with their unexpected failures, resulting safety hazards to passengers and increased whole life cycle cost of the asset. Consequently, one of the most important aspects of evaluation of the reliability of the overall railway transport system is bridge structural health monitoring, which can monitor the health state of the bridge by allowing an early detection of failures. Therefore, a fast, safe and cost-effective recovery of the optimal health state of the bridge, where the levels of element degradation or failure are maintained efficiently, can be achieved. In this article, after an introduction to the desired features of structural health monitoring, a review of the most commonly adopted bridge fault detection methods is presented. Mainly, the analysis focuses on model-based finite element updating strategies, non-model-based (data-driven) fault detection methods, such as artificial neural network, and Bayesian belief network–based structural health monitoring methods. A comparative study, which aims to discuss and compare the performance of the reviewed types of structural health monitoring methods, is then presented by analysing a short-span steel structure of a railway bridge. Opportunities and future challenges of the fault detection methods of railway bridges are highlighted. [DOI] -> Link to full text in repository

Conference contributions
Between February 2016 and April 2017 seven bridges around the world collapsed suddenly, by causing fatali-ties and significant economic losses. Structural Health Monitoring (SHM) techniques can assess the health state of an infrastructure by analysing its behaviour, and point out degraded elements that require to be main-tained. As a consequence, SHM methods can improve the safety of the transportation network, and reduce the life cycle costs of the infrastructure, by optimizing the maintenance schedule. In this paper, a Bayesian Belief Network (BBN) approach is proposed to assess the health state of a beam-and-slab bridge, by relying on the analysis of its vertical acceleration. A procedure to robustly define the Conditional Probabilities Tables (CPTs) of the BBN is proposed, by merging expert judgement with information about the bridge behaviour. The BBN allows to update the health state of the bridge when a new measurement of the bridge acceleration is available, by taking account of the health state of each element of the bridge. In this way, the degradation level of the whole bridge and of its elements is monitored over time, and unexpected behaviour of the bridge are diagnosed.
Structural Health Monitoring (SHM) techniques are able to monitor the behaviour of critical infrastructure over time, by improving the safety and reliability of the asset. A large amount of data is generated by SHM methods continuously. Therefore, machine learning methods can be developed in order to transform the available data into valuable information for decision-makers, by pointing out vulnerabilities of the critical infrastructure. In this paper, a machine learning classifier for condition monitoring and damage detection of bridges is proposed by adopting a Neuro-Fuzzy algorithm. The method allows to assess the health state of the infrastructure automatically, accurately and rapidly, every time when a new measurement of the bridge behaviour is available. The method is validated and tested by monitoring the behaviour of an in-field steel truss bridge, which is subjected to a progressive damage process.
The performance of four methods in establishing whether a bridge has experienced damage or not from the response to the crossing of a vehicle, is assessed within the Marie Skłodowska-Curie Innovative Training Net-work titled TRUSS (Training in Reducing Uncertainty of Structural Safety, http://trussitn.eu, 2015-2019). The first and second methods extract vibration-based damage sensitive features and apply a Bayesian Belief net-work respectively from/to bridge accelerations to determine the occurrence of damage. A third method based on bridge rotations applies bridge weigh-in-motion concepts to detect damage from the estimated vehicle’s weights. Finally, a fourth method derives bridge curvature and damage from the vehicle response. A blind test based on the responses of a complex vehicle-bridge interaction theoretical model is carried out to assess performance. The estimations of damage by each method are collected independently and compared to the exact solution.

This paper reports on recent contributions by the Marie Skłodowska-Curie Innovative Training Network titled TRUSS (Training in Reducing Uncertainty of Structural Safety) to the field of structural safety in rail and road bridges (http://trussitn.eu). In TRUSS, uncertainty in bridge safety is addressed via cost-efficient structural performance monitoring and fault diagnostics methods including: (1) the use of the rotation response due to the traffic traversing a bridge and weigh-in-motion concepts as damage indicator, (2) the combination of design parameters in probabilistic context for geometrical and material properties, traffic data and assumption on level of deterioration to evaluate bridge safety (via Bayesian updating and a damage indicator based on real-time measurement), (3) the application of a fuzzy classification technique via feature selection extracted using empirical mode decomposition to detect failure, and (4) the testing of alternative vibration-based damage sensitive features other than modal parameters. Progress has also been made in improving modern technologies based on optical fiber distributed sensing, and sensors mounted on instrumented terrestrial and on aerial vehicles, in order to gather more accurate and efficient info about the structure. More specifically, the following aspects have been covered: (a) the spatial resolution and strain accuracy obtained with optical distributed fiber when applied to concrete elements as well as the ideal adhesive, and the potential for detecting crack or abnormal deflections without failure or debonding, (b) the possibility of using the high-resolution measurement capabilities of the Traffic Speed Deflectometer for bridge monitoring purposes and, (c) the acquisition of bridge details and defects via unmanned aerial vehicles. -> Link to full text in repository

The UK railway network is subjected to an electrification process that aims to electrify most of the network by 2020. This upgrade will improve the capacity, reliability and efficiency of the transportation system by providing cleaner, quicker and more comfortable trains. During this process, railway infrastructures, such as tunnels, require to be adapted in order to provide the necessary clearance for the overhead line equipment, and consequently, a rigorous real-time health monitoring programme is needed to assure safety of workforce. Large amounts of data are generated by the real-time monitoring system, and automated data mining tools are then required to process this data accurately and quickly. Particularly, if an unexpected behaviour of the tunnel is identified, decision makers need to know: i) activities at the worksite at the time of movement occurring; ii) the predicted behaviour of the tunnel in the next few hours.

In this paper, we propose a data mining method which is able to automatically analyse the database of the real-time recorded displacements of the tunnel by detecting the unexpected tunnel behaviour. The proposed tool, first of all, relies on a step of data pre-processing, which is used to remove the measurement noise, followed by a feature definition and selection process, which aims to identify the unexpected critical behaviours of the tunnel. The most critical behaviours are then analysed by developing a change-point detection method, which detects precisely when the tunnel started to deviate from the predicted safe behaviour. Finally, an Artificial Neural Network (ANN) method is used to predict the future displacements of the tunnel by providing fast information to decision makers that can optimize the working schedule accordingly. -> Link to full text in repository

More than 35% of the European railway bridges are over 100 years old and the increasing traffic loads are pushing the railway infrastructure to its limits. Bridge condition-monitoring strategies can help the railway industry to improve safety, availability and reliability of the network. In this paper, a Bayesian Belief Network method for condition monitoring and fault detection of a truss steel railway bridge is proposed by relying on a fuzzy analytical hierarchy process of expert knowledge. The BBN method is proposed for obtaining the bridge health state and identifying the most degraded bridge elements. A Finite Element model is developed for simulating the bridge behaviour and studying a degradation mechanism. The proposed approach originally captures the interactions existing between the health state of different bridge elements and, furthermore, when the evidence about the displacement is introduced in the BBN, the health state of the bridge is updated. -> Link to full text in repository

More than 350,000 railway bridges are present on the European railway network, making them a key infrastructure of the whole railway network. Railway bridges are continuously exposed to changing environmental threats, such as wind, floods and traffic load, which can affect safety and reliability of the bridge. Furthermore, a problem on a bridge can affect the whole railway network by increasing the vulnerability of the geographic area, served by the railway network. In this paper a Bayesian Belief Network (BBN) method is presented in order to move from visual inspection towards a real time Structural Health Monitoring (SHM) of the bridge. It is proposed that the health state of a steel truss bridge is continuously monitored by taking account of the health state of each bridge element. In this way, levels of bridge deterioration can be identified before they become critical, the risk of direct and indirect economic losses can be reduced by defining optimal bridge maintenance works, and the reliability of the bridge can be improved by identifying possible hidden vulnerabilities among different bridge elements. -> Link to full text in repository

Bridges are one of the most critical structures of the railway system. External loads may affect the bridge health state, and consequently their safety, availability and reliability can be improved by monitoring their condition and planning maintenance accordingly. In this paper, a Bayesian Belief Network (BBN) fault detection methodology for a truss steel railway bridge is proposed. The BBN is developed to assess the health state of the whole bridge using evidence about the behaviour of the bridge. In this initial study, the evidence is provided in terms of the values of displacement computed by a Finite Element model. -> Link to full text in repository