Autoregressive Deep Learning Models for Bridge Strain Prediction

Psathas, Anastasios Panagiotis; Iliadis, Lazaros; Achillopoulou, Dimitra V.; Papaleonidas, Antonios; Stamataki, Nikoleta K.; Bountas, Dimitris; Dokas, Ioannis M.

doi:10.1007/978-3-031-08223-8_13

Cited by 4 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…InfraWatch (2008) [98] closely investigates monitoring data from Hollandse bridge and publishes records of measurements and reports. Based on those public data (strains), as well as estimations of future traffic loads [96] derived from the CV-based installed monitoring system, studies have indicated the most appropriate ML algorithm is vanilla long-short term memory (LSTM) [100] to predict the future trend of the bridge's response, resilience, and sustainability [53]. The extension of the existing CV-based system to include those algorithms and consider scenarios of natural hazards or catastrophic events aims to build up the defense of the asset and expand its life cycle using the most efficient decision through its adaptive pathway.…”

Section: Deteriorationmentioning

confidence: 99%

Adaptive Pathways Using Emerging Technologies: Applications for Critical Transportation Infrastructure

Makhoul,

Achillopoulou,

Stamataki

et al. 2023

Sustainability

Self Cite

View full text Add to dashboard Cite

Hazards are becoming more frequent and disturbing the built environment; this issue underpins the emergence of resilience-based engineering. Adaptive pathways (APs) were recently introduced to help flexible and dynamic decision making and adaptive management. Especially under the climate change challenge, APs can account for stressors occurring incrementally or cumulatively and for amplified-hazard scenarios. Continuous records from structural health monitoring (SHM) paired with emerging technologies such as machine learning and artificial intelligence can increase the reliability of measurements and predictions. Thus, emerging technologies can play a crucial role in developing APs through the lifetimes of critical infrastructure. This article contributes to the state of the art by the following four ameliorations. First, the APs are applied to the critical transportation infrastructure (CTI) for the first time. Second, an enhanced and smart AP framework for CTI is proposed; this benefits from the resilience and sustainability of emerging technologies to reduce uncertainties. Third, this innovative framework is assisted by continuous infrastructure performance assessment, which relies on continuous monitoring and mitigation measures that are implemented when needed. Next, it explores the impact of emerging technologies on structural health monitoring (SHM) and their role in enhancing resilience and adaptation by providing updated information. It also demonstrates the flexibility of monitoring systems in evolving conditions and the employment of AI techniques to manage pathways. Finally, the framework is applied to the Hollandse bridge, considering climate-change risks. The study delves into the performance, mitigation measures, and lessons learned during the life cycle of the asset.

show abstract

Section: Deteriorationmentioning

confidence: 99%

Adaptive Pathways Using Emerging Technologies: Applications for Critical Transportation Infrastructure

Makhoul,

Achillopoulou,

Stamataki

et al. 2023

Sustainability

Self Cite

View full text Add to dashboard Cite

show abstract

Strain Prediction of a Bridge Deploying Autoregressive Models with ARIMA and Machine Learning Algorithms

Psathas

Iliadis

Papaleonidas

2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

A brief introductory review to deep generative models for civil structural health monitoring

Luleci,

Catbas

2023

AI Civ. Eng.

View full text Add to dashboard Cite

The use of deep generative models (DGMs) such as variational autoencoders, autoregressive models, flow-based models, energy-based models, generative adversarial networks, and diffusion models has been advantageous in various disciplines due to their high data generative skills. Using DGMs has become one of the most trending research topics in Artificial Intelligence in recent years. On the other hand, the research and development endeavors in the civil structural health monitoring (SHM) area have also been very progressive owing to the increasing use of Machine Learning techniques. As such, some of the DGMs have also been used in the civil SHM field lately. This short review communication paper aims to assist researchers in the civil SHM field in understanding the fundamentals of DGMs and, consequently, to help initiate their use for current and possible future engineering applications. On this basis, this study briefly introduces the concept and mechanism of different DGMs in a comparative fashion. While preparing this short review communication, it was observed that some DGMs had not been utilized or exploited fully in the SHM area. Accordingly, some representative studies presented in the civil SHM field that use DGMs are briefly overviewed. The study also presents a short comparative discussion on DGMs, their link to the SHM, and research directions.

show abstract

Autoregressive Deep Learning Models for Bridge Strain Prediction

Cited by 4 publications

References 34 publications

Adaptive Pathways Using Emerging Technologies: Applications for Critical Transportation Infrastructure

Adaptive Pathways Using Emerging Technologies: Applications for Critical Transportation Infrastructure

Strain Prediction of a Bridge Deploying Autoregressive Models with ARIMA and Machine Learning Algorithms

A brief introductory review to deep generative models for civil structural health monitoring

Contact Info

Product

Resources

About