Remaining useful life prediction of a piping system using artificial neural networks: A case study

Shaik, Nagoor Basha; Pedapati, Srinivasa Rao; Dzubir, Faizul Azly

doi:10.1016/j.asej.2021.06.021

Cited by 24 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first layer consists of input neurons; these neurons transmit data to the second hidden layer, which transmits the data to the final output layer. The hidden layers units seek to learn about the collected information by measuring it in compliance with the internal structure of the ANN 32 . These rules allow changing their output, which is subsequently passed to the next layer.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Experimental investigation and ANN modelling on CO2 hydrate kinetics in multiphase pipeline systems

Shaik

Sayani

Benjapolakul

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

Gas hydrates are progressively becoming a key concern when determining the economics of a reservoir due to flow interruptions, as offshore reserves are produced in ever deeper and colder waters. The creation of a hydrate plug poses equipment and safety risks. No current existing models have the feature of accurately predicting the kinetics of gas hydrates when a multiphase system is encountered. In this work, Artificial Neural Networks (ANN) are developed to study and predict the effect of the multiphase system on the kinetics of gas hydrates formation. Primarily, a pure system and multiphase system containing crude oil are used to conduct experiments. The details of the rate of formation for both systems are found. Then, these results are used to develop an A.I. model that can be helpful in predicting the rate of hydrate formation in both pure and multiphase systems. To forecast the kinetics of gas hydrate formation, two ANN models with single layer perceptron are presented for the two combinations of gas hydrates. The results indicated that the prediction models developed are satisfactory as R2 values are close to 1 and M.S.E. values are close to 0. This study serves as a framework to examine hydrate formation in multiphase systems.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

Experimental investigation and ANN modelling on CO2 hydrate kinetics in multiphase pipeline systems

Shaik

Sayani

Benjapolakul

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Bias term is usually considered as one for all the neurons. Finally,

g

is a sigmoid activation function that can be written as Equation (), 42

g ((), x) goodbreak= \frac{1}{1 + e^{- x}}

The parameters from the first layer are then transferred into the second layer. Each of the 7 neurons in the second layer received some weighted input from the 20 neurons of layer one.…”

Section: Pipeline Safety Management System Using Neural Networkmentioning

confidence: 99%

Gas pipeline safety management system based on neural network

Mujtaba

Lemma

Vandrangi

2022

Process Safety Progress

View full text Add to dashboard Cite

The risk of leakage poses a grave threat to natural gas pipeline safety. The high compressibility of gases combined with unsteady boundary conditions makes detecting leaks in pipelines a challenging endeavor. To date, in the literature, only a limited number of studies have focused on leak detection and diagnostics in gas mixture pipelines. The present study provides a system for detecting, locating, and estimating the size of small gas leaks from a compressible and dynamic natural gas flow in pipelines with improved accuracy. As a case study, a long natural gas pipeline of 80 km is simulated with leak sizes of 0%, 2%, and 5%. The safety system is developed using mass flow rate, temperature, and pressure measurements. Six classes for faulty cases and one class for no fault case were considered for the study. A shallow neural network classifier (SNNC) is trained to identify a specific fault class. The SNNC is based on a two-layered network with 20 and 7 neurons. An input vector of 15 variables is provided to the system, and the output is one of the seven possible classes. Leakage as low as 2% at various locations are correctly diagnosed with more than 99% correct classification rate.

show abstract

“…2). Learning is the most important ability of a neural network, and a neural network will be able to generalize, classify and foresee [4], [12]. In other words, because of having experienced, neural networks will have recognition ability.…”

Section: Definition Of Artificial Neural Networkmentioning

confidence: 99%

“…The Data sets and the previously proxy algorithms are considered as the most important factors for qualifying a proxy model. To make sure that all aspects of the model are dealt with, an infinite size dataset is required, which is practically impossible [3], [9], [12]. Some techniques of experimental design are enlisted to extract the utmost information with the least simulations.…”

Section: Creating Proxy Modelmentioning

confidence: 99%

See 1 more Smart Citation

Oil Production Forecasting with Uncertainty Description Using Data Driven Proxy Model

Tavakolifaradonbe¹,

Moradi²,

Moldestad³

2022

Linköping Electronic Conference Proceedings

View full text Add to dashboard Cite

The petroleum industry operates under great uncertainty. Achieving an efficient approach to quantify uncertainty in oil production models is of key importance in supporting decision-makers to find suitable strategies for mitigating risks and maximizing profit. Uncertainty quantification is commonly performed based on the Monte Carlo approach and this is a very time-consuming process by using the physics-based models developed by reservoir simulators. To solve this challenge, data-driven proxy models which are less complex and computationally efficient can be used as an alternative. This paper aims to investigate the functionality of the ANN method in developing proxy models for uncertainty quantification of oil production from advanced wells. The investigation is conducted through a case study for uncertainty assessment of cumulative oil and water productions from a long horizontal well with ICD completion and zonal isolation in a synthetic reservoir for 10 years. In this study, the Eclipse® reservoir simulator is used for developing the base case model and it is coupled with MATLAB® for generating the required data sets to train and test the ANN proxy model. According to the obtained results, the trained and developed ANN proxy model can predict the production of oil and water from advanced wells accurately with a mean error of less than 4%. Besides, the proxy model is 150 times faster than the Eclipse model and can solve the challenge of the time-consuming process of uncertainty quantification.

show abstract

Remaining useful life prediction of a piping system using artificial neural networks: A case study

Cited by 24 publications

References 19 publications

Experimental investigation and ANN modelling on CO2 hydrate kinetics in multiphase pipeline systems

Experimental investigation and ANN modelling on CO2 hydrate kinetics in multiphase pipeline systems

Gas pipeline safety management system based on neural network

Oil Production Forecasting with Uncertainty Description Using Data Driven Proxy Model

Contact Info

Product

Resources

About