Probabilistic infrastructure performance models: An iterative-methods approach

Yehia, Ayatollah; Swei, Omar

doi:10.1016/j.trc.2019.12.019

Cited by 14 publications

(4 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…9 demonstrates that probabilistic models are not commonly used in road engineering. Although it is a powerful tool to cope with uncertainty, several authors indicate that it is a complex method which is data intensive [99,[103][104][105][106]. Because large datasets are often not available, researchers prefer to use deterministic models.…”

Section: Probabilistic Modelsmentioning

confidence: 99%

Implementing life cycle cost analysis in road engineering: A critical review on methodological framework choices

Moins

Bergh

Audenaert

2020

Renewable and Sustainable Energy Reviews

View full text Add to dashboard Cite

Section: Probabilistic Modelsmentioning

confidence: 99%

Implementing life cycle cost analysis in road engineering: A critical review on methodological framework choices

Moins

Bergh

Audenaert

2020

Renewable and Sustainable Energy Reviews

View full text Add to dashboard Cite

“…2. Literature review QC/QA performance specification as described in this section is contrasted with performance evaluation more generally, which involves the application of methods to assess the condition of infrastructure over time, typically to optimize maintenance and rehabilitation (Yehia and Swei, 2020). A review of construction PS studies in general leads to studies that are focused on prescriptive specifications, with a component of laboratory testing that leads to the prescriptive ingredients for, say, asphalt mixtures (Mills-Beale and You, 2010).…”

Section: Introductionmentioning

confidence: 99%

A new quality measure for acceptance and payment with a QC/QA performance specification using Bayesian updating

Sullivan

Novak

Hernández

et al. 2023

IJQRM

View full text Add to dashboard Cite

PurposeThis paper introduces a novel quality measure, the percent-within-distribution, or PWD, for acceptance and payment in a quality control/quality assurance (QC/QA) performance specification (PS).Design/methodology/approachThe new quality measure takes any sample size or distribution and uses a Bayesian updating process to re-estimate parameters of a design distribution as sample observations are fed through the algorithm. This methodology can be employed in a wide range of applications, but the authors demonstrate the use of the measure for a QC/QA PS with upper and lower bounds on 28-day compressive strength of in-place concrete for bridge decks.FindingsThe authors demonstrate the use of this new quality measure to illustrate how it addresses the shortcomings of the percent-within-limits (PWL), which is the current industry standard quality measure. The authors then use the PWD to develop initial pay factors through simulation regimes. The PWD is shown to function better than the PWL with realistic sample lots simulated to represent a variety of industry responses to a new QC/QA PS.Originality/valueThe analytical contribution of this work is the introduction of the new quality measure. However, the practical and managerial contributions of this work are of equal significance.

show abstract

“…The available pavement performance models can be commonly classified into three types, namely empirical, mechanistic, and mechanistic-empirical models (Yehia and Swei, 2020). Mechanistic models rely heavily on the expected theoretical behaviour of the materials.…”

Section: Introductionmentioning

confidence: 99%

“…Secondly, pavement deterioration has inherent uncertainty due to measurement error, data processing, and other possible reasons (Yehia and Swei, 2020;Amin and Amador-Jimé nez, 2017). This motivates many researchers to incorporate uncertainty consideration into their modelling framework, which helps evaluate the reliability of prediction results.…”

Section: Introductionmentioning

confidence: 99%

Modelling of pavement performance evolution considering uncertainty and interpretability: a machine learning based framework

Yao

Leng

Jiang

et al. 2021

International Journal of Pavement Engineering

View full text Add to dashboard Cite

Machine learning (ML) based pavement performance models have gained increasing popularity in recent years due to their strong power in modelling complex relationships.However, the insufficiency of a feature selection process prior to model construction, the difficulty in explaining the black box models, and the lack of uncertainty consideration all impeded the application of the produced models in real world. To fill these gaps, this study aims to develop a new framework to model the pavement performance evolution based on the state-of-the-art ML techniques, including the BorutaShap method for feature selection, the Bayesian neural network (BNN) for model development and uncertainty quantification, and the SHapley Additive exPlanations (SHAP) approach for model interpretation. A case study of predicting the pavement transverse cracking was conducted. The two generated BNN models yielded relatively accurate predictions with the R-square of 0.86 and 0.79 for unmaintained and maintained segments, respectively. Poor data quality was found to be the dominant source of uncertainty. The model interpretation also provided some insight into the underlying influential mechanism of various factors. The framework was expected to enable the decision-makers to build more reliable and informative pavement performance models that could be integrated into the pavement management tools.

show abstract

Probabilistic infrastructure performance models: An iterative-methods approach

Cited by 14 publications

References 50 publications

Implementing life cycle cost analysis in road engineering: A critical review on methodological framework choices

Implementing life cycle cost analysis in road engineering: A critical review on methodological framework choices

A new quality measure for acceptance and payment with a QC/QA performance specification using Bayesian updating

Modelling of pavement performance evolution considering uncertainty and interpretability: a machine learning based framework

Contact Info

Product

Resources

About