The Design of Pressure Vessel Failure Risk Estimation Program Due to Uniform Corrosion Based on Machine Learning with Artificial Neural Networks

Helya Chafshoh Nafisah, Fernanda Hartoyo, Jaka Fajar Fatriansyah, Donanta Dhaneswara, Harry Joni Varia

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Pressure vessels are a tool for storing liquid and gas fluids. The temperature difference between the pressure vessel and the surrounding environment causes failure to occur. One of the causes of that failure is uniform corrosion that can be avoided by conducting a risk-based inspection (RBI) by calculating the probability and consequence of failure. Deep learning is a subfield of machine learning, which is prominent in recent years due to its capability to handle high dimensional data. Among the deep learning models for analyzing risk in pressure vessels is artificial neural networks (ANNs). This model can shorten the time, increase accuracy and efficiency, and lower the cost. This article discusses the design of a pressure vessel dataset based on the API 581 standard and the calculation of failure predictions using ANNs. High accuracy 93% for the classification of the probability of failure and 100% for the consequences of failure have been obtained. The classification determination of those failure categories was also continued by calculating precision and recall parameters. The results obtained confirmed the accuracy of the classification, and hence indicated the succeeding of the ANNs model to classify the data.

Original languageEnglish
Title of host publication2023 International Seminar on Intelligent Technology and Its Applications
Subtitle of host publicationLeveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages170-174
Number of pages5
ISBN (Electronic)9798350313956
DOIs
Publication statusPublished - 2023
Event24th International Seminar on Intelligent Technology and Its Applications, ISITIA 2023 - Hybrid, Surabaya, Indonesia
Duration: 26 Jul 202327 Jul 2023

Publication series

Name2023 International Seminar on Intelligent Technology and Its Applications: Leveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding

Conference

Conference24th International Seminar on Intelligent Technology and Its Applications, ISITIA 2023
Country/TerritoryIndonesia
CityHybrid, Surabaya
Period26/07/2327/07/23

Keywords

  • API 581
  • artificial neural networks
  • machine learning
  • pressure vessel
  • risk-based inspection
  • uniform corrosion

Fingerprint

Dive into the research topics of 'The Design of Pressure Vessel Failure Risk Estimation Program Due to Uniform Corrosion Based on Machine Learning with Artificial Neural Networks'. Together they form a unique fingerprint.

Cite this