Assessment of Remaining Useful Life of Pipelines Using Different Artificial Neural Networks Models

Zangenehmadar, Zahra; Moselhi, Osama

doi:10.1061/(asce)cf.1943-5509.0000886

Cited by 46 publications

(14 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Motiee and Ghasemnejad [17] used different variables, such as material, age, length, diameter, and hydraulic pressure, for implementing four statistical models (i.e., Linear Regression, Poisson Regression, Exponential Regression, and Logistic Regression) to generate relationships for pipe failure prediction. The results demonstrated that Logistic Regression exhibited the best performance accuracy in comparison to the other regression methods.Machine Learning (ML) methods, such as Artificial Neuronal Networks [18,19], Support Vector Machines [20], Fuzzy Logic [1], and boosting algorithms [21], have recently been used for pipe failure detection due to their ability to produce accurate results and simulate complex relationships between the variables that explain the pipe failure process [6]. Winkler et al [9] proposed an approach to predict pipe failures based on boosted techniques (e.g., RUSboost, Adaboost, Random Forest, and Decision Trees), based on existing pipe attributes and historical failure records in a medium-sized city.…”

mentioning

confidence: 99%

“…Machine Learning (ML) methods, such as Artificial Neuronal Networks [18,19], Support Vector Machines [20], Fuzzy Logic [1], and boosting algorithms [21], have recently been used for pipe failure detection due to their ability to produce accurate results and simulate complex relationships between the variables that explain the pipe failure process [6]. Winkler et al [9] proposed an approach to predict pipe failures based on boosted techniques (e.g., RUSboost, Adaboost, Random Forest, and Decision Trees), based on existing pipe attributes and historical failure records in a medium-sized city.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Comparison of Statistical and Machine Learning Models for Pipe Failure Modeling in Water Distribution Networks

Giraldo-González

Rodríguez

2020

Water

View full text Add to dashboard Cite

The application of statistical and Machine Learning models plays a critical role in planning and decision support processes for efficient and reliable Water Distribution Network (WDN) management. Failure models can provide valuable information for prioritizing system rehabilitation even in data scarcity scenarios, such as developing countries. Few studies have analyzed the performance of more than two models, and examples of case studies in developing countries are insufficient. This study compares various statistical and Machine Learning models to provide useful information to practitioners for the selection of a suitable pipe failure model according to information availability and network characteristics. Three statistical models (i.e., Linear, Poisson, and Evolutionary Polynomial Regressions) were used for failure prediction in groups of pipes. Machine Learning approaches, particularly Gradient-Boosted Tree (GBT), Bayes, Support Vector Machines and Artificial Neuronal Networks (ANNs), were compared in predicting individual pipe failure rates. The proposed approach was applied to a WDN in Bogotá (Colombia). The statistical models showed an acceptable performance (R2 between 0.695 and 0.927), but the Poisson Regression was the most suitable for predicting failures in pipes with lower failure rates. Regarding Machine Learning models, Bayes and ANNs exhibited low performance in the prediction of pipe failure condition. The GBT approach had the best performing classifier.

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%

Comparison of Statistical and Machine Learning Models for Pipe Failure Modeling in Water Distribution Networks

Giraldo-González

Rodríguez

2020

Water

View full text Add to dashboard Cite

show abstract

“…Based on findings from oil and gas major operating companies worldwide, most organizations have pipelines in their inventory that have been in operation for more than 60 years, and still operating, without manifesting significant integrity degradation or any reasonable statistical recorded failures. In the same study, statistics also showed that pipelines that were retired before their economics life span, on basis of reliability failure or constraints, fall below the five percentile worldwide [6], while more than ninety-five percent have operated more than the designed 20-25 years. Paradoxically, the 20-25 year life generally in practice is merely an axiom [7], and grossly at huge variance with historical reality, masking an irregularity that undercuts the total functional values of pipeline assets.…”

Section: Introductionmentioning

confidence: 88%

Valuating hydrocarbon pipeline facility service beyond 20–25 year economic life: Accounting for residual value

Alaneme¹,

Al-Lajam²,

Al-Jaafari³

et al. 2021

Nig. J. Tech.

View full text Add to dashboard Cite

The 20–25 years economic life for hydrocarbon pipelines in the investment decision model is at wide variance with historical statistical records of more than 90-percent world-wide. Opinions diverge, from service type to the product quality, and materials resilience as basis for this premise. While, financial experts consider time to fully depreciate a capital investment, irrespective of the rate of returns, engineers consider operational availability and reliability duration. The risk is that actual residue values of pipelines worldwide are erroneously omitted in every project’s economics Cash-flow computation, thus eroding the investment decision quality. Statistics showed that more than 60-percent of pipelines worldwide have already exceeded the 25 years economic life, while more than 40-percent have operated more than 30-years and above. This theoretical appraisal identified a gap in the economic model in handling multi-criteria risk management uncertainties like hedging, weighting, etc., and highlighted the exigency to craft and assign numeric residue values for pipelines in the investment Cash-flow models.

show abstract

“…This approach has shown promising results proving the robustness of ANN models when it comes to predicting the residual life of pipelines. Zangenehmadar et al [ 51 ] used this approach in their research to determine the useful life of pipelines using the Levenberg-Marquart back-propagation algorithm. Their ANN model was able to predict the useful life of a pipeline with an error percentage of less than 5%.…”

Section: Artificial Neural Network As a Corroded Pipeline Failure Pressure Prediction Toolmentioning

confidence: 99%

A Review of Finite Element Analysis and Artificial Neural Networks as Failure Pressure Prediction Tools for Corroded Pipelines

Kumar

Arumugam

et al. 2021

Materials

View full text Add to dashboard Cite

This paper discusses the capabilities of artificial neural networks (ANNs) when integrated with the finite element method (FEM) and utilized as prediction tools to predict the failure pressure of corroded pipelines. The use of conventional residual strength assessment methods has proven to produce predictions that are conservative, and this, in turn, costs companies by leading to premature maintenance and replacement. ANNs and FEM have proven to be strong failure pressure prediction tools, and they are being utilized to replace the time-consuming methods and conventional codes. FEM is widely used to evaluate the structural integrity of corroded pipelines, and the integration of ANNs into this process greatly reduces the time taken to obtain accurate results.

show abstract

Assessment of Remaining Useful Life of Pipelines Using Different Artificial Neural Networks Models

Cited by 46 publications

References 20 publications

Comparison of Statistical and Machine Learning Models for Pipe Failure Modeling in Water Distribution Networks

Comparison of Statistical and Machine Learning Models for Pipe Failure Modeling in Water Distribution Networks

Valuating hydrocarbon pipeline facility service beyond 20–25 year economic life: Accounting for residual value

A Review of Finite Element Analysis and Artificial Neural Networks as Failure Pressure Prediction Tools for Corroded Pipelines

Contact Info

Product

Resources

About