Neural networks deterioration models for serviceability condition of buried stormwater pipes

Tran, Danh; Ng, A. W. M; Perera, B. J. C

doi:10.1016/j.engappai.2007.02.005

Cited by 44 publications

(34 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sampling data of network weights from their posterior distribution were used to compute the condition of pipes which resulted in 95% confidence ranges (or interval prediction). Detailed implementation of the Bayesian MCMC simulation for training the NNM can be found in Kingston et al (2006) and Tran et al (2007).…”

Section: Neural Network Model (Nnm)mentioning

confidence: 99%

“…The second objective is to improve the performance of the neural network model (NNM) developed by Tran et al (2009) for predicting the structural condition of individual pipes, since the Markov model in Micevski et al (2002) and Tran et al (2008) had no link mechanism between pipe factors such as pipe size and age with pipe deterioration and thus failed to predict the structural condition of a particular pipe. The improved predictive performance of NNM was done in this study by using the Bayesian Markov chain Monte Carlo simulation technique which was used for calibrating the NNM for hydraulic deterioration of stormwater pipes in Tran et al (2007). The structural condition for any particular pipe predicted by the NNM can be used for identifying pipes that are in poor condition for repair actions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Markov and Neural Network Models for Prediction of Structural Deterioration of Storm-Water Pipe Assets

Tran

Perera

2010

J. Infrastruct. Syst.

View full text Add to dashboard Cite

Abstract. Stormwater pipe networks in Australia are designed to convey water from rainfall and surface runoff. They do not transport sewerage. Their structural deterioration is progressive with aging and will eventually cause pipe collapse with consequences of service interruption. Predicting structural condition of pipes provides vital information for asset management to prevent unexpected failures and to extend service life. This study focused on predicting the structural condition of stormwater pipes with two objectives. The first objective is the prediction of structural condition changes of the whole network of stormwater pipes by a Markov model at different times during their service life. This information can be used for planning annual budget and estimating the useful life of pipe assets. The second objective is the prediction of structural condition of any particular pipe by a neural network model. This knowledge is valuable in identifying pipes that are in poor condition for repair actions. A case study with CCTV inspection snapshot data was used to demonstrate the applicability of these two models.

show abstract

Section: Neural Network Model (Nnm)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Markov and Neural Network Models for Prediction of Structural Deterioration of Storm-Water Pipe Assets

Tran

Perera

2010

J. Infrastruct. Syst.

View full text Add to dashboard Cite

show abstract

“…It was decided to measure the damage to 50%, as any damage more than 50% will result in near total failure for the storm drainage pipe. Neural Network Deterioration Model (NNDM), developed by Tran et al [7], specializes in identifying and ranking the deterioration factors of storm drainage. NNDM has been determined that there are nine factors that have damaging effects to storm drainage.…”

Section: Event Tree Analysismentioning

confidence: 99%

“…NNDM has been determined that there are nine factors that have damaging effects to storm drainage. The model developed a ranking order for the deterioration factors -the factors are size, trees, climate conditions, slope, soil, depth, location, structure and age -which are ranked from 1 being the most important to 9 being the least important (Tran et al [7]). Moreover, the model stated that two factors (age and structure) had an insignificant effect when comparing them with the other factors.…”

Section: Event Tree Analysismentioning

confidence: 99%

Risk-based assessment of climate change impact on storm drainage system

Alsaqqaf¹,

Zhang²,

Mohamed³

2010

WIT Transactions on Ecology and the Environment

View full text Add to dashboard Cite

Climate change impacts on engineering infrastructures are increasing. The infrastructures are expected to withstand more frequent and severe weather events, more climate variability, and changes in climate norms (average conditions). It is anticipated that many civil infrastructure systems such as storm drainage, will fail to meet the expected environmental pressures. Therefore, it is important to identify current and future risks; to develop strategies for adapting such risks; and to implement an effective maintenance plan. In the study, the climate change impacts on storm drainage were investigated, particularly in Southport, Queensland, Australia. The historical rainfall data for 120 years were analysed to identify the changes in the trends, patterns and frequencies of rainfall. The peak flow in a flooding event was identified. The investigation provides essential information for the vulnerability to risk failure of the existing storm drainage system, such as at a critical pipe failure point. Finally, the research applied a risk-based vulnerability assessment by risk analysis and management quantification tools to quantify the impact that rainfall may induce through storm drainage failure.

show abstract

“…A number of different performance indicators (PIs) for the sewer and water systems have been proposed recently (Alegre et al 2000;Matos et al 2003;Tran et al 2007). …”

Section: Introductionmentioning

confidence: 99%

Asset deterioration analysis using multi-utility data and multi-objective data mining

Savić

Giustolisi

Laucelli

2009

Journal of Hydroinformatics

View full text Add to dashboard Cite

Physically-based models derive from first principles (e.g. physical laws) and rely on known variables and parameters. Because these have physical meaning, they also explain the underlying relationships of the system and are usually transportable from one system to another as a structural entity. They only require model parameters to be updated. Data-driven or regressive techniques involve data mining for modelling and one of the major drawbacks of this is that the functional form describing relationships between variables and the numerical parameters is not transportable to other physical systems as is the case with their classical physically-based counterparts. Aimed at striking a balance, Evolutionary Polynomial Regression (EPR) offers a way to model multi-utility data of asset deterioration in order to render model structures transportable across physical systems. EPR is a recently developed hybrid regression method providing symbolic expressions for models and works with formulae based on pseudo-polynomial expressions, usually in a multi-objective scenario where the best Pareto optimal models (parsimony versus accuracy) are selected from data in a single case study. This article discusses the improvement of EPR in dealing with multi-utility data (multi-case study) where it has been tried to achieve a general model structure for asset deterioration prediction across different water systems.

show abstract

Neural networks deterioration models for serviceability condition of buried stormwater pipes

Cited by 44 publications

References 18 publications

Markov and Neural Network Models for Prediction of Structural Deterioration of Storm-Water Pipe Assets

Markov and Neural Network Models for Prediction of Structural Deterioration of Storm-Water Pipe Assets

Risk-based assessment of climate change impact on storm drainage system

Asset deterioration analysis using multi-utility data and multi-objective data mining

Contact Info

Product

Resources

About