[vc_empty_space][vc_empty_space]
Artificial neural networks for corrosion rate prediction in gas pipelines
Supriyatman D.a, Sumarnib, Sidarto K.A.b, Suratman R.b
a Total E and P Indonesie, Indonesia
b Institut Teknologi Bandung, Indonesia
[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]Artificial Neural Network (ANN) is adopted from the human neural network systems and is among many tools to understand complex model including corrosion. Such predictive model can be developed through corrosion rate. By ANN application, one may update its model iteratively, hence it will be adaptable for all decisions. It can be learned from the previous data and recognize patterns of data always changing and dynamic, like the ones in oil and gas fields. Based on the characteristics of ANN methods, corrosion rate model will update iteratively during the training phase leading to the best (more accurate) model target. Using a number of data input and output characteristics of the fluid, the result of corrosion rate model will be able to predict the corrosion rate in the range of the entered input data. With models that are adaptive and can adjust to changes in the dynamic data, one will be able to obtain predictions with a great degree of accuracy. Research methodology on the subject using crude oil was developed by Hernandez and Nesic (2005). Some crude oil characteristic associated with the corrosion rate are, among others, sulfur, vanadium, nickel contents, total acid number and API. A correlation analysis between the crude oil characteristics vs corrosion rate, then a regression model of percentage of inhibiton which is a function of characteristics of crude oil were obtained. Percentage of inhibition in this regard is the number of ratio between the corrosion rate of the fluid-carrying pipe and corrosion rate in the blank pipe. This paper will describe ANN that creates a program to determine the corrosion rates of the carbon-steel materials containing flowing fluid (gas). The characteristics evaluated are gas composition, temperature and pressure then regression equation of inhibition percentage will be made in the characteristics function of earlier inputs. Only data having a high level of significance will be used, and the ones of very low level of significances will be excluded in the equation. The next step is building models with ANN for which significant data based on the regression test will be used as input data to the corrosion prediction program in gas pipelines. The deliverable of this study is getting the prediction program of gas pipeline corrosion of carbon steel using MATLAB software. The program accuracy of the program is compared with the actual data. Copyright 2012, Society of Petroleum Engineers.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Characteristics functions,Correlation analysis,Corrosion prediction,Corrosion rate models,Gas pipeline corrosion,Neural network systems,Research methodologies,Temperature and pressures[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Artificial neural network,Corrosion rate,Prediction[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]