Prediction of Corrosion in Pipeline by using Deep Learning

The inspection of corrosion in the pipeline need to be implemented and maintained by the oil and gas company in order to transport various type of crude oil or natural gas over short and long distance. This is because, the corrosion rate could give significant impact on inside and outside of t...

Full description

Main Author: BAHARUDIN, NUR FARAHIN
Format: Final Year Project
Language: English
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-utpedia.21765 /
Published: IRC 2020
Subjects:
Q Science (General)
Online Access: http://utpedia.utp.edu.my/21765/1/23227_Nur%20Farahin%20Baharudin.pdf
http://utpedia.utp.edu.my/21765/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-utpedia.21765
recordtype eprints
spelling utp-utpedia.217652021-09-23T23:39:16Z http://utpedia.utp.edu.my/21765/ Prediction of Corrosion in Pipeline by using Deep Learning BAHARUDIN, NUR FARAHIN Q Science (General) The inspection of corrosion in the pipeline need to be implemented and maintained by the oil and gas company in order to transport various type of crude oil or natural gas over short and long distance. This is because, the corrosion rate could give significant impact on inside and outside of the pipeline surfaces which then leads to high cost of damage expenses. Therefore, the purpose of this research paper is to perform the prediction of corrosion in pipeline by using the deep learning method. This paper includes literature review and comparisons technique on the analytical and visualization tools. In addition, the accuracy of data will be validated by using the Cross-Validation technique in order to choose the lowest RMSE and best suited of LSTM model. Hence, the results based on the model prediction of corrosion rate will be visualized in Power BI dashboards so that the results could be shared, analyzed and discussed the solution to a better business decision. IRC 2020-01 Final Year Project NonPeerReviewed application/pdf en http://utpedia.utp.edu.my/21765/1/23227_Nur%20Farahin%20Baharudin.pdf BAHARUDIN, NUR FARAHIN (2020) Prediction of Corrosion in Pipeline by using Deep Learning. IRC, Universiti Teknologi PETRONAS. (Submitted)
institution Universiti Teknologi Petronas
collection UTPedia
language English
topic Q Science (General)
spellingShingle Q Science (General)
BAHARUDIN, NUR FARAHIN
Prediction of Corrosion in Pipeline by using Deep Learning
description The inspection of corrosion in the pipeline need to be implemented and maintained by the oil and gas company in order to transport various type of crude oil or natural gas over short and long distance. This is because, the corrosion rate could give significant impact on inside and outside of the pipeline surfaces which then leads to high cost of damage expenses. Therefore, the purpose of this research paper is to perform the prediction of corrosion in pipeline by using the deep learning method. This paper includes literature review and comparisons technique on the analytical and visualization tools. In addition, the accuracy of data will be validated by using the Cross-Validation technique in order to choose the lowest RMSE and best suited of LSTM model. Hence, the results based on the model prediction of corrosion rate will be visualized in Power BI dashboards so that the results could be shared, analyzed and discussed the solution to a better business decision.
format Final Year Project
author BAHARUDIN, NUR FARAHIN
author_sort BAHARUDIN, NUR FARAHIN
title Prediction of Corrosion in Pipeline by using Deep Learning
title_short Prediction of Corrosion in Pipeline by using Deep Learning
title_full Prediction of Corrosion in Pipeline by using Deep Learning
title_fullStr Prediction of Corrosion in Pipeline by using Deep Learning
title_full_unstemmed Prediction of Corrosion in Pipeline by using Deep Learning
title_sort prediction of corrosion in pipeline by using deep learning
publisher IRC
publishDate 2020
url http://utpedia.utp.edu.my/21765/1/23227_Nur%20Farahin%20Baharudin.pdf
http://utpedia.utp.edu.my/21765/
_version_ 1741195783299923968
score 11.62408

Similar Items