A Bayesian Estimation Method to Improve Deterioration Prediction for Infrastructure System with Markov Chain Model

Kobayashi, Kiyoshi; Kaito, Kiyoyuki; Lethanh, Nam

doi:10.7492/ijaec.2012.001

Cited by 29 publications

(21 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The t.p.s due to MDPs are first estimated as is normally explained in Tsuda et al (2006), Lethanh (2009) and Kobayashi et al (2012a). As this is a well-established process, this step is not explained here.…”

Section: Estimate Transition Probabilities Due To Mdps Alonementioning

confidence: 99%

“…The probability of passing from one non-failure CS to another in each unit of time, that is a transition probability (t.p. ), is determined using past inspection data and can be estimated as described in Tsuda et al (2006) and Kobayashi et al (2012a).…”

Section: A Model For Manifest Processesmentioning

confidence: 99%

“…In discrete time Markov chain, the deterioration of an object is modelled by determining the probability that the object will pass from one discrete CS to another in a fixed period of time, where the CSs are defined using values of performance indicators (e.g. visual indicators of corrosion, roughness and cracking of the road surface) (Kuhn, 2010;Kobayashi et al 2012aKobayashi et al , 2012b). …”

Section: Introductionmentioning

confidence: 99%

“…The probabilities of passing from each non-failure CS to each failure CS are estimated using normalised fragility curves, and the probabilities of passing from each nonfailure CS to each non-failure CS are initially estimated using the Markov model of Tsuda et al (2006) and Kobayashi et al (2012a) and later adjusted taking into consideration the probabilities of entering the failure CSs.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Optimal intervention strategies for multiple objects affected by manifest and latent deterioration processes

Lethanh¹,

Adey²,

Fernando

2014

Structure and Infrastructure Engineering

Self Cite

View full text Add to dashboard Cite

In the existing infrastructure management systems, optimal interventions strategies (OISs) are determined for objects that deteriorate gradually (manifest deterioration process, MDPs), under the assumption that with appropriate inspection and intervention strategies the probability of failure of object can be neglected. Objects that deteriorate suddenly (latent deterioration process, LDPs), for example, due to scouring during a flood or earth movements during an earthquake are not considered. The determination of OISs for an object that deteriorates due to both MDPs and LDPs requires the consideration of both. The latter, however, means that the probability of failure of the object must be considered. In this article, a Markov model is presented that can be used to determine OISs for multiple objects of multiple types affected by uncorrelated MDPs and LDPs. The model is an extension of the model proposed by Mayet and Madanat (Incorporation of seismic considerations in bridge management systems. Computer-Aided Civil and Infrastructure Engineering, 17:185 -193, 2002). In the model, a set of condition states (CSs) is used to describe the condition of objects of each type, where each set is composed of nonfailure CSs and failure CSs. The probabilities of going from each non-failure CS to each failure CS are estimated using normalised fragility curves, and the probabilities of going from each non-failure CS to each non-failure CS are initially estimated using the Markov deterioration prediction model of Kobayashi, Kaito, and Lethanh (A Bayesian estimation method to improve deterioration prediction for infrastructure system with Markov chain model. International Journal of Architecture, Engineering and Construction, 1:1 -13, 2012a) and later adjusted taking into consideration the probabilities of entering the failure CSs. The use of the model is demonstrated using a road link comprising one road section and one bridge.

show abstract

Section: Estimate Transition Probabilities Due To Mdps Alonementioning

confidence: 99%

Section: A Model For Manifest Processesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimal intervention strategies for multiple objects affected by manifest and latent deterioration processes

Lethanh¹,

Adey²,

Fernando

2014

Structure and Infrastructure Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…The estimation of the transition probabilities for the Markov models is ideally done using available condition state data that have been collected at uniform time intervals over a long period of time (Lee, 1970). Although somewhat more complicated, when data have been collected at non-uniform intervals of time over a long period of time, the transition probabilities can be estimated using statistical methods, such as survival analysis, maximum likelihood estimation, and Bayesian estimation approaches (Hastings, 1970;Lancaster, 1990;Kobayashi et al, 2012a;Mizutani et al, 2013;Lethanh et al, 2015). When little to no condition state data are available, transition probabilities have been estimated using expert opinion or estimated in various ways to obtain a best fit with the condition states predicted using mechanisticempirical models (Golroo and Tighe, 2012;Indiana Department of Transportation, 2013).…”

Section: Finite State Markov Models and Transition Probabilitiesmentioning

confidence: 99%

Improving the Estimation of Markov Transition Probabilities Using Mechanistic-Empirical Models

Mizutani

Lethanh²,

Adey

et al. 2017

Front. Built Environ.

Self Cite

View full text Add to dashboard Cite

In many current state-of-the-art bridge management systems, Markov models are used for both the prediction of deterioration and the determination of optimal intervention strategies. Although transition probabilities of Markov models are generally estimated using inspection data, it is not uncommon that there are situations where there are inadequate data available to estimate the transition probabilities. In this article, a methodology is proposed to estimate the transition probabilities from mechanistic-empirical models for reinforced concrete elements. The proposed methodology includes the estimation of the transition probabilities analytically when possible and when not through the use of Bayesian statistics, which requires the formulation of a likelihood function and the use of Markov Chain Monte Carlo simulations. In an example, the difference between the average condition predicted over a 100-year time period with a Markov model developed using the proposed methodology and the condition predicted using mechanistic-empirical models were found to be 54% of that when the state-of-the-art methodology, i.e., a methodology that estimates the transition probabilities using best fit curves based on yearly condition distributions, was used. The variation in accuracy of the Markov model as a function of the number of deterioration paths generated using the mechanistic-empirical models is also shown.

show abstract

Field-Regularised Factorization Machines for Mining the Maintenance Logs of Equipment

Zhang

et al. 2018

AI 2018: Advances in Artificial Intelligence

View full text Add to dashboard Cite

Failure prediction is very important for railway infrastructure. Traditionally, data from various sensors are collected for this task. Value of maintenance logs is often neglected. Maintenance records of equipment usually indicate equipment status. They could be valuable for prediction of equipment faults. In this paper, we propose Fieldregularised Factorization Machines (FrFMs) to predict failures of railway points with maintenance logs. Factorization Machine (FM) and its variants are state-of-the-art algorithms designed for sparse data. They are widely used in click-through rate prediction and recommendation systems. Categorical variables are converted to binary features through one-hot encoding and then fed into these models. However, field information is ignored in this process. We propose Field-regularised Factorization Machines to incorporate such valuable information. Experiments on data set from railway maintenance logs and another public data set show the effectiveness of our methods.

show abstract

A Bayesian Estimation Method to Improve Deterioration Prediction for Infrastructure System with Markov Chain Model

Cited by 29 publications

References 17 publications

Optimal intervention strategies for multiple objects affected by manifest and latent deterioration processes

Optimal intervention strategies for multiple objects affected by manifest and latent deterioration processes

Improving the Estimation of Markov Transition Probabilities Using Mechanistic-Empirical Models

Field-Regularised Factorization Machines for Mining the Maintenance Logs of Equipment

Contact Info

Product

Resources

About