Application of Artificial Intelligence and Big data to Decision-making Support for Engineering-Procurement-Construction (EPC) Projects
- Title
- Application of Artificial Intelligence and Big data to Decision-making Support for Engineering-Procurement-Construction (EPC) Projects
- Authors
- 최소원; 최수진; 이승엽; LEE, EUL BUM
- Date Issued
- 2020-12-17
- Publisher
- US-Korea Conference (UKC) 2021
- Abstract
- I. INTRODUCTION
A. Background
The plant Engineering-Procurement-Construction (EPC) project is a complex industry that spans its full cycle from bidding to engineering, construction, and Operations & Maintenance (O&M).
Many EPC companies are facing difficulties in managing the entire project cycle due to a vast amount of systematic decision-making processes based on data such as track records. There are cases of project losses due to insufficient risk management such as schedule delays and cost overrun. It is essential to secure competitive advantages in the high value-added portion of the value chain such as Project Management Consultancy (PMC) and Front-End Engineering Design (FEED) in order to survive in global competition. Innovation-driven engineering and management solutions are in high demand to meet global competitiveness in the plant industry,
This study presents a technology of an “AI-based engineering big data integrated analysis support system” to predict and respond to risks that may occur in the entire project life cycle.
B. Methodology
The model illustrates a knowledge-based system from the bidding to O&M stage to support decision-making for EPC projects. The model utilizes a machine learning platform with various algorithms to analyze Invitation to Bid (ITB) documents at the bidding stage and construct a predictive model of O&M facilities.
Five modules based on machine learning algorithms have been developed, including bidding document analysis, design cost prediction, design error analysis, design change analysis, and predictive maintenance of plant equipment. A prototype system has been developed using the Python programming language to support the implementation of the proposed model.
II. RESULTS
Based on the result of prototype system, this model could help EPC companies manage risks at each stage of the EPC project and minimize project risks.
The engineering ITB analysis module and the design cost prediction module will be introduced in detail among the five main modules.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/107172
- Article Type
- Conference
- Citation
- US-Korea Conference 2021 on Science, Technology, and Entrepreneurship (UKC 2021), 2020-12-17
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.