A two-time-scale point process model of water main breaks for infrastructure asset management

Lin, Peiyuan; Yuan, Xian‐Xun

doi:10.1016/j.watres.2018.11.066

Cited by 23 publications

(45 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, as will be shown later in the Case Study section, predictions based on the means and the full distributions of are very different. This is consistent with the finding by Lin and Yuan (2019) who proposed a two-time-scale model for predicting water main breaks. Scholten, Scheidegger, Reichert, Mauer, and Lienert (2014) also suggested the use of full distributions for model prediction to account for the parameter uncertainty.…”

Section: Accuracy In Terms Of Predictionsupporting

confidence: 93%

“…Figures and clearly demonstrate the importance of selecting appropriate parameter estimates, in terms of decision‐making for pipe‐flushing prioritizations within the evidence‐based risk‐informed asset management framework. We showed in another paper (Lin & Yuan, ) for modeling water main breaks that when the data are complete and abundant, the means of the model parameters can be used to correctly predict the cumulative number of breaks; whereas the full distributions must be used when the data are incomplete and/or small of volume. In this paper, we advocate the same for predictions of sewer pipe grade probabilities.…”

Section: Case Studymentioning

confidence: 99%

“…In particular, the Metropolis-Hasting algorithm is used. Readers can refer to, for example, Gelman et al (2014), H. Wang, Yajima, Liang, and Castaneda (2015), Yuan, Mao, and Pandey (2009), and Lin and Yuan (2019) for more technical details of the MCMC simulation approach.…”

Section: Scenario 3: Multiple Mrr Eventsmentioning

confidence: 99%

“…The scarcity of data has resulted in great difficulties in modeling the natural physical deterioration, let alone the measurement and modeling of maintenance effectiveness, which many people would think requires data immediately before and after the maintenance activities. Therefore, although there have been degradation models for water and sewer pipes in the literature (e.g., Baik, Jeong, & Abraham, 2006;Duchesne, Beardsell, Villeneuve, Toumbou, & Bouchard, 2013;Kleiner, 2001;Lin & Yuan, 2019;Tran, Perera, & Ng, 2009;Wirahadikusumah, Abraham, & Iseley, 2001), researchers have been busy dealing with the issues arising from lack of data and left the maintenance effectiveness untouched.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Integrative modeling of performance deterioration and maintenance effectiveness for infrastructure assets with missing condition data

Lin

Yuan

Tovilla

2019

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

Deterioration modeling is an important analytical component in infrastructure asset management. It concerns the prediction of performance and remaining service life of assets of different designs under omnifarious working environments. For long‐term prediction, it also requires to characterize maintenance effectiveness because maintenance activities do not necessarily bring an asset to a completely renewed status. Deterioration modeling research has for decades been largely focusing on the modeling of the natural deterioration process per se, whereas the modeling of maintenance effectiveness is only a recent focus of investigation, mainly in pavement research. In practice, the asset conditions immediately before and after a given maintenance treatment both are not often known. This has made the modeling of maintenance effectiveness and long‐term deterioration prediction a challenging task. To bridge the gap, this paper presents a novel approach that integrates the modeling of deterioration and maintenance effectiveness into one process. The natural deterioration of asset performance is modeled as a continuous‐time Markov chain, whereas the effectiveness of a maintenance measure is modeled as a discrete‐time Markov chain. To account for missing condition data before and after the maintenance event, the paper also develops a robust statistical method based on Markov chain Monte Carlo simulation. A real‐life case study on a municipal sewer pipe system is carried out for demonstration of the proposed integrated modeling approach. The functional deterioration of sewer pipes and the effectiveness of flushing operations that target to bring flow capacity to intact state are modeled. Influences of pipe length, diameter, slope, and sewershed area are examined. The present work is a valuable step toward development of evidence‐based risk‐informed asset management framework.

show abstract

Section: Accuracy In Terms Of Predictionsupporting

confidence: 93%

Section: Case Studymentioning

confidence: 99%

Section: Scenario 3: Multiple Mrr Eventsmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Integrative modeling of performance deterioration and maintenance effectiveness for infrastructure assets with missing condition data

Lin

Yuan

Tovilla

2019

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

show abstract

“…These data samples may include performance data, operational conditions data, management data, maintenance historical data, location information, financial data, etc. [4], [5], [10], [47], [67], [68]. Specific examples of missing data could include: a) Missing asset ID (or tag), where the data collected cannot be assigned to an asset for asset condition assessment purposes [69].…”

Section: E Examples Of Types Of Missing Data Within Asset Managementmentioning

confidence: 99%

Approaches to Dealing With Missing Data in Railway Asset Management

2020

View full text Add to dashboard Cite

The collection of reliable and high-quality data is seen as a prerequisite for effective and efficient rail infrastructure and rolling stock asset management to meet the requirements of asset owners and service providers. In this paper, the importance of recovering missing information in railway asset management is highlighted, and the advanced models and algorithms that have been applied to recovering the missed data are analyzed and discussed. Through making comparisons among these models and algorithms, a procedure is proposed to guide selecting the appropriate models based on different data missing scenarios. Using the newly developed framework with one dataset from each scenario, new models with different structures are trained and finally, the most suitable model is selected and utilized to recover the missing data and the selected model's performance is evaluated using the data with known or clearly identified missing data mechanisms. Challenges via application of advanced algorithms for recovering missing data are discussed.

show abstract

An evolutionary fuzzy system to support the replacement policy in water supply networks: The ranking of pipes according to their failure risk

Robles-Velasco

Muñuzuri

Onieva

et al. 2021

Applied Soft Computing

View full text Add to dashboard Cite

A two-time-scale point process model of water main breaks for infrastructure asset management

Cited by 23 publications

References 21 publications

Integrative modeling of performance deterioration and maintenance effectiveness for infrastructure assets with missing condition data

Integrative modeling of performance deterioration and maintenance effectiveness for infrastructure assets with missing condition data

Approaches to Dealing With Missing Data in Railway Asset Management

An evolutionary fuzzy system to support the replacement policy in water supply networks: The ranking of pipes according to their failure risk

Contact Info

Product

Resources

About