In the early phases of a pipeline project, the lack of data available for routing results in multiple routes being considered and interactions with land owners with only a general route. As a consequence, multiple survey programs are undertaken only to collect data that often is not being used, or site revisits are required to collect additional survey data. Repeated visits by survey crews to the field results in considerable cost and schedule delay to the project. A project was undertaken to reduce these costs and schedule impacts by replacing the need for survey work during FEED by utilizing remote sensing data and Artificial Intelligence (AI). This paper outlines the methods for collection of High Density (HD) LiDAR and high resolution imagery and then using AI to automatically identify all above ground features. This technique has proven to provide data of sufficient accuracy and completeness to conduct Pre-FEED and FEED level routing and engineering of a pipeline project. When survey is required, it is only to collect below ground features and to collect or verify data in very specific detail. Additionally, when required for legal or engineering reasons, survey work can be conducted more efficiently by providing the crews with a field database of the features already captured and means for updating the database with the data they collect or verify.
- Pipeline Division
Use of Advanced Processing Techniques of High Density LiDAR in Place of Survey for Cost and Schedule Reductions on Early Phase Pipeline Projects: Capital Project Results
Hlady, JT, & Parker, D. "Use of Advanced Processing Techniques of High Density LiDAR in Place of Survey for Cost and Schedule Reductions on Early Phase Pipeline Projects: Capital Project Results." Proceedings of the 2016 11th International Pipeline Conference. Volume 2: Pipeline Safety Management Systems; Project Management, Design, Construction and Environmental Issues; Strain Based Design; Risk and Reliability; Northern Offshore and Production Pipelines. Calgary, Alberta, Canada. September 26–30, 2016. V002T02A013. ASME. https://doi.org/10.1115/IPC2016-64235
Download citation file: