Improved Reconstruction and Anomaly Detection in JET using LIDAR-Vision fusion

Improved Reconstruction and Anomaly Detection in JET using LIDAR-Vision fusion

Improved Reconstruction and Anomaly Detection in JET using LIDAR-Vision fusion 150 150 UKAEA Opendata
UKAEA-RACE-CP(21)04

Improved Reconstruction and Anomaly Detection in JET using LIDAR-Vision fusion

Just like most industrial or scientific installations, future fusion reactors will require more or less frequent maintenance. The expected environmental conditions, as well as the necessity of carrying out many maintenance tasks in parallel in result in remote robotic maintenance becoming a necessity in order to minimize the maintenance shutdown durations. Advanced technologies will be required to carry out the automated inspection and maintenance tasks. LIDAR is a promising technology which is only just starting to be applied in Fusion contexts. Though it is presently not radiation tolerant enough to be utilized in future reactor designs such as ITER or DEMO without further development, the low radiation levels in JET have presented an opportunity to evaluate the technology for use in fusion environments. In a previous publication, we have presented initial results using data captured in JET in the form of a coloured 3D-pointcloud created by LIDAR-Vision sensor fusion. In this paper, we will present further results obtained by processing and utilising this data. This will include details on the improvement of model quality using recorded JET RH Boom kinematics data, updated pointcloud-CAD data comparisons using numerical methods, as well as the segmentation of the vessel interior into tiles and the detection of discrepancies between the CAD model and the dataset. Finally, the results will be discussed and the relevance of this technology for future remote maintenance system inspection / navigation tasks will be discussed.

Collection:
Conference
Journal:
Publisher:
Conference:
14th International Symposium on Fusion Nuclear Technology (ISFNT-14) Budapest,Hungary, 22-27 September 2019
Published date:
25/11/2020
The published version of this paper is currently under embargo and will be available on 25/11/2022