Autonomous Inspection of Subsea Facilities-Gulf of Mexico Trials
Bibliographic record
Abstract
Abstract Lockheed Martin Corporation is conducting a multi-year technology developmentprogram to advance the state of the art of Autonomous Underwater Vehicle (AUV)inspection technologies for the offshore oil & gas industry. The scope ofthis project is to develop and demonstrate AUV technologies for conductingautonomous structural survey and inspection of subsea facilities for a widerange of applications, including pre/post-hurricane inspection of offshoreplatforms, pre/post-decommissioning structural survey, and deepwater facility /riser inspection. This paper will describe the results of Lockheed Martin'srecently completed technology demonstration project, Autonomous Inspection ofSubsea Facilities, including laboratory simulation, local offshore trials, andtechnology validation trials in the Gulf of Mexico against offshore productionplatforms. This project was jointly funded by the Research Partnership toSecure Energy for America (RPSEA), Lockheed Martin and sea trials weresupported by Chevron Energy Technology Company Capabilities demonstrated duringoffshore trials included (1) autonomous real-time three-dimensional (3D)imaging and modeling of an underwater facility, (2) detection and highlightingof changes to the facility in real time, and (3) feature-based navigation, theaiding of the AUV's navigation along its path based on feature detection andrecognition. The paper will describe the results achieved, and will highlightthe performance improvements over current platform inspection methods, including significant improvements in operating efficiencies, and thedevelopment of highly accurate 3D models for use in structural integritymanagement. Finally, the paper will outline the potential benefits of evolvingAUV and sensor technologies for applications such as structural survey, pipeline inspection, subsea facility inspection, and light intervention, including potentially game changing improvements in cost, performance, safetyand reliability that will enable more cost-effective operations in deepwaterand/or remote subsea fields. Introduction Subsea Integrity Management is defined by the Energy Institute Guidelines forthe Management of Integrity of Subsea Facilities as " the management of a subseasystem or asset to ensure that it delivers the design requirements, and doesnot harm life, health or the environment, through the required life." A keyelement in any integrity management program is regular in-service inspections. As the industry moves into deeper and harsher environments, challenges faced byoperators include the high cost of subsea inspection and the limited inspectionintervals available. Inspections provide a snapshot of the structural health ofthe system. Integrity management practices in deepwater fields rely heavily ongeneral visual inspection of subsea equipment. Remotely operated vehicles(ROVs) and divers are the primary means used today to conduct inspections -ROVs exclusively in deepwater (greater than 100-meter water depth) and diversgenerally limited to less than100-meter water depth. In both cases supportvessels larger than 70 to 100 meters with support crews numbering more than 30and with 100+ tons of equipment are required to collect the simplest visualinspection record. The quality and usefulness of the records are highlydependent on the seawater's visual clarity, illumination, camera and recordingequipment, and ROV or diver stability. An ROV inspection of a deepwaterfacility can provide visual evidence of structural degradation, impact damage, corrosion, valve damage, leaks, vibration, and other structural damage (Figure 1). Benchmarking the condition of subsea equipment following installation andtracking its status over time can provide a history of the deterioration rate. Video inspections include: well heads, valve positions, pipeline endterminations (PLETs), pipeline end manifolds (PLEMs), underwater terminationmanifolds (UTMs), flowlines, jumpers, moorings, risers, and associated cablingand equipment on the sea bed. This equipment is often spread over many squarekilometers requiring the support vessel to maneuver in DP mode for days. Inspection speed is totally dependent on the coordinated movement of the ROVand support vessel and the skill of the ROV pilot.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".