Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

PAIP - Atomized pipe analyses

Reference number
Coordinator TEKNISKA VERKEN I LINKÖPING AB (PUBL) - Tekniska Verken i Linköping
Funding from Vinnova SEK 500 000
Project duration November 2018 - November 2019
Status Completed

Purpose and goal

The aim of the project is to develop and verify an automated pipe analysis service that is as good or better than today´s trained analysts (people). In the project we have completed a service for automated pipe analysis that can do an image analysis of filmed pipelines. In its current form, the service has not achieved better precision than today´s trained analysts.

Expected results and effects

Today, the service has not achieved better precision than today´s trained analysts, but has proven to improve the work process and reduced several manual steps. When the service is launched, we expect a more standardized way of working that reduces dependence on people in the form of simplified work steps. This is achieved mainly through the expert interface developed and saves the operators the work of uploading a file and manually identifying the current defect that needs to be examined. In the expert interface, the operator can click on a specific defect at the right place in the file.

Planned approach and implementation

The project has been carried out by the Technical Works staff and external AI experts from Silo.AI. The work has been done from several places in virtual workspaces and physical meetings. The meetings mainly focused on service design workshops. The development work has been done remotely by Silo.AI and the Technical Works staff in two-week sprints with a subsequent sprint review. After every two sprints, a complete system demonstration has been carried out. It has worked well to run the project in distance form with an English-speaking external supplier.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 16 November 2018

Reference number 2018-04267

Page statistics