Corrosion Rate Prediction for Underground Gas Pipelines Using A LevenbergMarquardt Artificial Neural Network ANN (original) (raw)
Related papers
An Artificial Neural Network Modeling for Pipeline Corrosion Growth Prediction
Corrosion defect assessment becoming a forte issue in pipeline reliability assessment to accurately predict the severity of its condition. Due to the uncertainties inherit from the pipeline inspection at present, statistical model use to model the corrosion growth apply a correctional methods to reduce the gap (means and variation) between predicted values and the actual data. This study aims to develop a time dependent corrosion growth model for oil and gas pipeline using Artificial Neural Network (ANN) as an alternative to the current method and to evaluate its applicability without enforcing data correctional methods. This model is formulated based on parameters of defect extracted from in-line inspection data (ILI) and quantified by statistical analysis. The develop model gives the prediction of the corrosion depth and length of the defect that can be used to calculate the corrosion rate or growth. The results and outcome of the present study can help pipeline operators to predi...
A Neural Network Predictive Model of Pipeline Internal Corrosion Profile
2014
Internal corrosion is a crucial issue for the safe operation of oil&gas pipelines. This is a phenomenon due to interaction of different mechanisms. Water and electrochemistry, protective scales, flow velocity, steel composition and localized bacteria attacks are relevant. Despite the large number of models proposed in literature, the corrosion process is very complex and rarely reproduced by existing models. For this reason, an artificial neural network (ANN) based model is investigated, with the aim to correctly predict the presence of metal loss and corrosion rate along a pipeline. In this paper, a case study is considered, based on real field data. The model integrates the geometrical profile of a real pipeline, flow simulations and the most important deterministic corrosion models. It is shown that the ANN model outperforms the deterministic ones.
Corrosion Assessment of some Buried Metal Pipes using Neural Network Algorithm
International Journal of Engineering and Manufacturing, 2017
The key aim of this assessment is to characterize the rate of corrosion of buried Nickel plated and non-plated AISI 1015 steel pipes using a Modified Artificial Neural Network on Matlab and taking the oil and gas area of Nigeria as a case study. Ten (10) metal specimens were used. Five (5) were nickel electroplated specimens buried differently in 5 plastic containers containing 5 different soil samples with the other 5 non-plated specimens also buried into the same 5 soil samples but different plastic containers. In carrying out the experiment, the data that was collected for 25 consecutive days were grouped into sets of input and output data. This was required so as to appropriately feed the modelling tool (Artificial Neural Network). The input data were; temperature of the soil sample, temperature of the immediate surroundings, and pH of the soil sample while the output data was weight loss. Conclusively, Modified Artificial Neural Network relationships between the varied selected input parameters that affects corrosion rate (soil sample temperature, immediate environment temperature and pH value) and the output parameter (Corrosion Penetration Rate) were derived. Also, soil sample temperature and the immediate surrounding temperature combined conditions had the strongest effect on corrosion penetration rate while the immediate surrounding temperature and the pH value combined conditions had the weakest effect on corrosion penetration rate.
This work proposes an improved quantitative prediction model for corrosion under insulation (CUI) for oil and gas piping in equatorial climate zone, using real-world data and integrated with experimental work using modified two stages of Artificial Neural Network. Investigation into the effect of single type of data source and different type of fitting line analysis on the final CUI model are also discussed with the goal for Risk Based Inspection (RBI) to be more effective. Results from the CUI prediction model exhibits high R 2 of 0.9919 and Root Mean Squared Error (RMSE) of 0.0087.
ARTIFICIAL NEURAL NETWORK FOR PREDICTING OIL PIPELINE CONDITION
ARTIFICIAL NEURAL NETWORK FOR PREDICTING OIL PIPELINE CONDITION, 2019
A pipeline is the most significant asset for the oil and gas industry as it transports the petroleum product from the beneath of the sea to the oil platform to be processed and distributed around the world. However, the maximum lifetime of the pipelines is only ten (10) years then the pipe must be altered or changed. Today, with the availability of advanced analytics which is predictive analytics, it should be utilized to assist the refinery segment of oil and gas industry to decide whether the pipeline should be changed or not based on its situation. The project proposes predictive modelling to predict the oil pipeline condition due to corrosion. The cause of pipeline corrosion occurring is due to chloride concentration, iron concentration and pH reading in sour water. An artificial neural network is predictive modelling that can predict what could happen with a high success rate by training the historical cause of corrosion data. This model is relied upon to assist pipeline administrators with assessing and anticipate the state of oil pipeline condition.
Modeling of Corrosion Rate Under Two Phase Flow in Horizontal Pipe Using Neural Network
The present study develops an artificial neural network (ANN) to model an analysis and a simulation of the correlation between the average corrosion rate carbon steel and the effective parameter Reynolds number (Re), water concentration (Wc) % temperature (T o ) with constant of PH 7 . The water, produced fom oil in Kirkuk oil field in Iraq from well no. k184-Depth2200ft., has been used as a corrosive media and specimen area (400 mm 2 ) for the materials that were used as low carbon steel pipe. The pipes are supplied by Doura Refinery . The used flow system is all made of Q.V.F glass, and the circulation of the two -phase (liquid -liquid ) is affected using a Q.V.F pump .The input parameters of the model consists of Reynolds number , water concentration and temperature. The output is average corrosion rate .The performance of the two training algorithms, gradient descent with momentum and Levenberg-Marquardt, are compared to select the most suitable training algorithm for corrosion rate model. The model can be used to calculate the average corrosion rate properties of carbon steel alloy as functions of Reynolds number, water concentration and temperature. Accordingly, the combined influence of these effective parameters and the average corrosion rate is simulated. The results show that the corrosion rate increases with the increase of temperature, Reynolds number and the increase of water concentration.
Neural network modelling of high pressure CO2 corrosion in pipeline steels
Process Safety and Environmental Protection
The effect of carbon dioxide (CO2) corrosion on pipelines is of great relevance to the petroleum as well as the Carbon Capture and Storage (CCS) industries. CO2 corrosion is responsible for lost production as it brings about the gradual degradation of pipe internals with time. The cost of general corrosion is said to be between 3to 5% of an industrialised nation's gross domestic product (Schmitt et al., 2009; Popoola et al., 2013). In the U.S., the cost of corrosion in the production and manufacturing sector was $34.4 billion in 2014, with the oil and gas industry accounting for more than half (Abbas, 2016). The use of neural networks (NN) as an analytic tool for corrosion data has been established however the aim of this paper is to characterise selected Matlab transfer and training functions, and assess their degree of suitability for CO2 corrosion rate prediction. Assessments of the training functions include the evaluation of the correlation coefficient (R 2-value) and determination of a cumulative absolute error to indicate the level of precision and the extent of model accuracy. A NN model is developed for predicting CO2 corrosion at high partial pressures by considering the results of the various tests and analyses on the given Matlab functions. The results showed that the model is reliable with all test results falling within the 95% confidence limits. Leave-One-Out Cross-Validation (LOOCV) was implemented as a means for carrying out an additional assessment on model performance as well as for model selection from possible alternatives.
Processes, 2020
Pipelines are like a lifeline that is vital to a nation's economic sustainability; as such, pipelines need to be monitored to optimize their performance as well as reduce the product losses incurred in the transportation of petroleum chemicals. A significant number of pipes would be underground; it is of immediate concern to identify and analyse the level of corrosion and assess the quality of a pipe. Therefore, this study intends to present the development of an intelligent model that predicts the condition of crude oil pipeline cantered on specific factors such as metal loss anomalies (over length, width and depth), wall thickness, weld anomalies and pressure flow. The model is developed using Feed-Forward Back Propagation Network (FFBPN) based on historical inspection data from oil and gas fields. The model was trained using the Levenberg-Marquardt algorithm by changing the number of hidden neurons to achieve promising results in terms of maximum Coefficient of determination (R 2) value and minimum Mean Squared Error (MSE). It was identified that a strong R 2 value depends on the number of hidden neurons. The model developed with 16 hidden neurons accurately predicted the Estimated Repair Factor (ERF) value with an R 2 value of 0.9998. The remaining useful life (RUL) of a pipeline is estimated based on the metal loss growth rate calculations. The deterioration profiles of considered factors are generated to identify the individual impact on pipeline condition. The proposed FFBPN was validated with other published models for its robustness and it was found that FFBPN performed better than the previous approaches. The deterioration curves were generated and it was found that pressure has major negative affect on pipeline condition and weld girth has a minor negative affect on pipeline condition. This study can help petroleum and natural gas industrial operators assess the life condition of existing pipelines and thus enhances their inspection and rehabilitation forecasting.
Machine Learning and Knowledge Extraction
Today, the chemical corrosion of metals is one of the main problems of large productions, especially in the oil and gas industries. Due to massive downtime connected to corrosion failures, pipeline corrosion is a central issue in many oil and gas industries. Therefore, the determination of the corrosion progress of oil and gas pipelines is crucial for monitoring the reliability and alleviation of failures that can positively impact health, safety, and the environment. Gas transmission and distribution pipes and other structures buried (or immersed) in an electrolyte, by the existing conditions and due to the metallurgical structure, are corroded. After some time, this disrupts an active system and process by causing damage. The worst corrosion for metals implanted in the soil is in areas where electrical currents are lost. Therefore, cathodic protection (CP) is the most effective method to prevent the corrosion of structures buried in the soil. Our aim in this paper is first to inve...
Artificial neural network for the evaluation of CO2 corrosion in a pipeline steel
Journal of Solid State Electrochemistry, 2009
This paper presents a predictive model for the determination of different types of corrosion by using electrochemical impedance spectroscopy curves and artificial neural network. This proposed model obtains predictions for three different types of corrosion by using Nyquist impedance curves from four input variables: inhibitor concentration, time of exposure, and the real and imaginary experimental component of these curves. The model takes into account the variations of inhibitor concentration over steel to decrease the corrosion rate. For the network, the Levenberg-Marquardt learning algorithm, the hyperbolic tangent sigmoid transfer function and the linear transfer function were used. The best fitting training data set was obtained with five neurons in the hidden layer, which made possible to predict satisfactory efficiency (R>0.99). On the validation of the data set, simulations and theoretical data tests were in good agreement (R>0.9905). The developed model can be used for the determination of the type of curves related to the nature phenomena and rate of corrosion at the metal surface.