CAD and Spatial Data Mining Framework for Petro-Chemical Pipeline Industry
Keywords:
Petro-Chemical Pipeline Industry, , Data Mining, Computer Aided Design (CAD), GIS (Geographic Information System), Decision MakingAbstract
Decision making within industry is a crucial process that needs great deal of attention, breadth of knowledge and experience in multiple domains, intellectual abilities and comprehensive understanding of process flow. The ability of decision makers is constrained by the complexity of the matter, accuracy of data and the circumstances in which the decision is to be made. The planning & development panel in Petro-Chemical pipeline industry utilizes substantial resources for making decisions about pipeline infrastructure installations, emergency management and hazard prediction. The technical scenarios in pipeline industry are visualized on the grid of spatial data and analyzed under certain engineering codes and rules. The decision made after such an analysis is not immune to human interventional error, lack of expertise, complexity of computer aided design, over-utilization of time and proximity of error.
This paper is aimed to build a framework for authentic interpretation of geo-spatial and cartographic data and to make decision for pipeline installation by extracting the hidden patterns and technical knowledge from this data. This framework will read and extract data from GIS and other cartographic systems and use data mining and machine learning techniques to identify influencing factors in decision making. The framework will focus on minimizing human interaction and try to automate the complex decision-making process by searching the solution in the complex hypothesis space. An optimized model of decision making is proposed which will minimize revenue loss, time consumption, consumer’s dissatisfaction and environmental hazards, which are apparently destined in existing decision-making mechanism. Historical data about several decisions in case of new installation as well as standardized rules from the industry will be used to train the system. New rules would evolve on the successful training which will be helpful to find solution.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).