TY - GEN
T1 - Integration of Decision Support Modules to Identify the Priority of Risk of Failure in Topside Piping Equipment
T2 - IFIP WG 5.7 International Conference on Advances in Production Management Systems, APMS 2014
AU - Seneviratne, A. M.N.D.B.
AU - Ratnayake, R. M.Chandima
PY - 2014
Y1 - 2014
N2 - The identification and prioritization of locations that have potential for failure (also referred to as thickness measurement locations (TMLs)) in the in-service inspection planning of offshore topside piping equipment requires a significant amount of data analysis together with relevant information. In this context, planning personnel analyze data and information retrieved from piping inspection databases through enterprise resource planning (ERP) software to investigate possible degradation trends in order to recognize the TMLs that have reached a critical level. It is observed that suboptimal prioritization occurs due to time restriction vs. amount of data and/or information that has to be evaluated. The suboptimal prioritization omits some of the critical TMLs, increasing the risk of failures whilst also increasing cost due to taking non-critical TMLs into inspection. Therefore, this manuscript illustrates an approach to integrate the decision support modules (DSMs) via an artificial neural network model for the optimum prioritization.
AB - The identification and prioritization of locations that have potential for failure (also referred to as thickness measurement locations (TMLs)) in the in-service inspection planning of offshore topside piping equipment requires a significant amount of data analysis together with relevant information. In this context, planning personnel analyze data and information retrieved from piping inspection databases through enterprise resource planning (ERP) software to investigate possible degradation trends in order to recognize the TMLs that have reached a critical level. It is observed that suboptimal prioritization occurs due to time restriction vs. amount of data and/or information that has to be evaluated. The suboptimal prioritization omits some of the critical TMLs, increasing the risk of failures whilst also increasing cost due to taking non-critical TMLs into inspection. Therefore, this manuscript illustrates an approach to integrate the decision support modules (DSMs) via an artificial neural network model for the optimum prioritization.
KW - ERP software
KW - In-service inspection planning
KW - artificial neural networks
KW - decision support modules
KW - thickness measurement locations
KW - topside piping equipment
UR - https://www.scopus.com/pages/publications/84906931443
U2 - 10.1007/978-3-662-44733-8_65
DO - 10.1007/978-3-662-44733-8_65
M3 - Conference contribution
AN - SCOPUS:84906931443
SN - 9783662447321
T3 - IFIP Advances in Information and Communication Technology
SP - 521
EP - 529
BT - Advances in Production Management Systems
PB - Springer New York LLC
Y2 - 20 September 2014 through 24 September 2014
ER -