A Real-Time Back-Analysis Technique to Infer Rheological Parameters from Field Monitoring

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The long-term stress analysis of engineering projects can be significantly expedited if we can determine an appropriate rheological model and its corresponding parameters. In the present contribution, we show that an accurate and real-time estimation of rheological parameters is possible by employing deep learning and metaheuristic algorithms. A real-time back-analysis technique was proposed using a deep long short-term memory neural network (DeepLSTM) as a substitute for numerical modelling and firefly algorithm (FA) to search for the optimum parameter. The performance of the proposed technique, the DeepLSTM-FA, was verified using a tunnel response with the FLAC 2D finite difference program. Furthermore, the application of the DeepLSTM-FA to an engineering instance, namely, the Adriatic Motorway near Draga Valley, was discussed in detail, revealing that the DeepLSTM-FA can provide practitioners with an accurate and real-time estimation of rheological parameters, thereby allowing for timely stress and stability analyses. We found that an accurate estimation of rheological parameters can be made using the first few points of displacement data instead of the whole displacement profile. This technique extends recent efforts to determine rheological parameters in real time and significantly accelerates the application of stress and stability analyses in the future.

Original languageEnglish
Pages (from-to)3029-3043
Number of pages15
JournalRock Mechanics and Rock Engineering
Volume51
Issue number10
DOIs
Publication statusPublished - 1 Oct 2018

Fingerprint

back analysis
Monitoring
Neural networks
monitoring
engineering
FLAC
Stress analysis
stress analysis
motorway
Tunnels
parameter
tunnel
learning
Long short-term memory
valley
modeling

Cite this

@article{06551bff57de4ac09788c72df6f4c883,
title = "A Real-Time Back-Analysis Technique to Infer Rheological Parameters from Field Monitoring",
abstract = "The long-term stress analysis of engineering projects can be significantly expedited if we can determine an appropriate rheological model and its corresponding parameters. In the present contribution, we show that an accurate and real-time estimation of rheological parameters is possible by employing deep learning and metaheuristic algorithms. A real-time back-analysis technique was proposed using a deep long short-term memory neural network (DeepLSTM) as a substitute for numerical modelling and firefly algorithm (FA) to search for the optimum parameter. The performance of the proposed technique, the DeepLSTM-FA, was verified using a tunnel response with the FLAC 2D finite difference program. Furthermore, the application of the DeepLSTM-FA to an engineering instance, namely, the Adriatic Motorway near Draga Valley, was discussed in detail, revealing that the DeepLSTM-FA can provide practitioners with an accurate and real-time estimation of rheological parameters, thereby allowing for timely stress and stability analyses. We found that an accurate estimation of rheological parameters can be made using the first few points of displacement data instead of the whole displacement profile. This technique extends recent efforts to determine rheological parameters in real time and significantly accelerates the application of stress and stability analyses in the future.",
keywords = "Back-analysis, Deep long short-term memory, Firefly algorithm, Rheological parameters",
author = "Chongchong Qi and Andy Fourie",
year = "2018",
month = "10",
day = "1",
doi = "10.1007/s00603-018-1513-2",
language = "English",
volume = "51",
pages = "3029--3043",
journal = "Journal Rock Mechanics and Rock Engineering",
issn = "0723-2632",
publisher = "Springer",
number = "10",

}

A Real-Time Back-Analysis Technique to Infer Rheological Parameters from Field Monitoring. / Qi, Chongchong; Fourie, Andy.

In: Rock Mechanics and Rock Engineering, Vol. 51, No. 10, 01.10.2018, p. 3029-3043.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Real-Time Back-Analysis Technique to Infer Rheological Parameters from Field Monitoring

AU - Qi, Chongchong

AU - Fourie, Andy

PY - 2018/10/1

Y1 - 2018/10/1

N2 - The long-term stress analysis of engineering projects can be significantly expedited if we can determine an appropriate rheological model and its corresponding parameters. In the present contribution, we show that an accurate and real-time estimation of rheological parameters is possible by employing deep learning and metaheuristic algorithms. A real-time back-analysis technique was proposed using a deep long short-term memory neural network (DeepLSTM) as a substitute for numerical modelling and firefly algorithm (FA) to search for the optimum parameter. The performance of the proposed technique, the DeepLSTM-FA, was verified using a tunnel response with the FLAC 2D finite difference program. Furthermore, the application of the DeepLSTM-FA to an engineering instance, namely, the Adriatic Motorway near Draga Valley, was discussed in detail, revealing that the DeepLSTM-FA can provide practitioners with an accurate and real-time estimation of rheological parameters, thereby allowing for timely stress and stability analyses. We found that an accurate estimation of rheological parameters can be made using the first few points of displacement data instead of the whole displacement profile. This technique extends recent efforts to determine rheological parameters in real time and significantly accelerates the application of stress and stability analyses in the future.

AB - The long-term stress analysis of engineering projects can be significantly expedited if we can determine an appropriate rheological model and its corresponding parameters. In the present contribution, we show that an accurate and real-time estimation of rheological parameters is possible by employing deep learning and metaheuristic algorithms. A real-time back-analysis technique was proposed using a deep long short-term memory neural network (DeepLSTM) as a substitute for numerical modelling and firefly algorithm (FA) to search for the optimum parameter. The performance of the proposed technique, the DeepLSTM-FA, was verified using a tunnel response with the FLAC 2D finite difference program. Furthermore, the application of the DeepLSTM-FA to an engineering instance, namely, the Adriatic Motorway near Draga Valley, was discussed in detail, revealing that the DeepLSTM-FA can provide practitioners with an accurate and real-time estimation of rheological parameters, thereby allowing for timely stress and stability analyses. We found that an accurate estimation of rheological parameters can be made using the first few points of displacement data instead of the whole displacement profile. This technique extends recent efforts to determine rheological parameters in real time and significantly accelerates the application of stress and stability analyses in the future.

KW - Back-analysis

KW - Deep long short-term memory

KW - Firefly algorithm

KW - Rheological parameters

UR - http://www.scopus.com/inward/record.url?scp=85047374508&partnerID=8YFLogxK

U2 - 10.1007/s00603-018-1513-2

DO - 10.1007/s00603-018-1513-2

M3 - Article

VL - 51

SP - 3029

EP - 3043

JO - Journal Rock Mechanics and Rock Engineering

JF - Journal Rock Mechanics and Rock Engineering

SN - 0723-2632

IS - 10

ER -