eprintid: 7712
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/00/77/12
datestamp: 2023-11-09 16:19:31
lastmod: 2023-11-09 16:19:31
status_changed: 2023-11-09 16:10:13
type: article
metadata_visibility: show
creators_name: Khan, M.M.
creators_name: Mokhtar, A.
creators_name: Hussin, H.
title: Prediction for corrosion under insulation subject to carbon steel pipes using ANFIS
ispublished: pub
note: cited By 1
abstract: Failures due to corrosion under insulation (CUI) are one of the most common external corrosion failures in petroleum and power industry. A small and inadequate amount of CUI corrosion rate data is available from literature and original plants. American Petroleum Institute (API) in its version API 581 has also given confined data for CUI which limits the use of the data for quantitative risk based inspection (RBI) analysis for both stainless steels and carbon steels. The aim of this paper is to construct and then checking the accuracy of an adaptive neuro fuzzy inference system (ANFIS) model along with predicting CUI corrosion rate of carbon steel based on, API data. The simulation shows that the model effectively predict the corrosion rates against the CUI corrosion rates given by API 581 with a mean absolute deviation ( MAD ) of 0.0006. The model is also giving CUI corrosion rates where API 581 is showing no value for it. The results from this model would provide the inspection engineers a satisfactory amount of CUI corrosion rate data which will be good enough for the quantitative approach of RBI. © 2006-2016 Asian Research Publishing Network (ARPN).
date: 2016
publisher: Asian Research Publishing Network
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85000642909&partnerID=40&md5=b15f15c6e1c0ff7b1db07b04178f76be
full_text_status: none
publication: ARPN Journal of Engineering and Applied Sciences
volume: 11
number: 1
pagerange: 268-276
refereed: TRUE
issn: 18196608
citation:   Khan, M.M. and Mokhtar, A. and Hussin, H.  (2016) Prediction for corrosion under insulation subject to carbon steel pipes using ANFIS.  ARPN Journal of Engineering and Applied Sciences, 11 (1).  pp. 268-276.  ISSN 18196608