Inspection Of Offshore Structures Research Articles

General reinforcement learning control for AUV manoeuvring in turbulent flows

Turbulence induces unsteady loads on autonomous underwater vehicles (AUVs) and may present a significant navigation challenge. This leads to elevated risks of mission failure or vehicle damage in proximity to obstacles. A scenario of particular interest is inspection of offshore structures that needs to be carried out at short range inside a turbulent wake. This work presents a control strategy based on reinforcement learning (RL) that has been designed to handle such a complex manoeuvring scenario. Training and evaluation is carried out using computational fluid dynamics (CFD) simulations of a simplified 2D geometry of similar manoeuvring characteristics to that of an AUV moving in the horizontal plane. Due to the high cost of the simulations, substantial emphasis has been placed on improving sampling efficiency of RL training using experience transfer from a computationally less demanding environment and quicker filling of the replay buffer by applying geometric transformations to the observations. The agent can navigate not only in the training environment, but also in a previously unseen flow generated by a large circular cylinder immersed in a current. The developed control strategy has also been interfaced with a path-following algorithm that allowed the controlled vehicle to carry out an inspection task.

Position-based augmented reality platform for aiding construction and inspection of offshore plants

We propose an augmented reality platform to help workers with fabrication and inspection of offshore structures. The platform is designed to work under various constraints that are commonly encountered in an industrial environment and often make the existing AR methods fail to work properly. It consists of modules for tracking, registration, and augmentation. The tracking module estimates the worker’s position in real time. The registration module aligns the actual objects with 3D computer-aided design models to estimate an accurate pose of the worker’s mobile device. The augmentation module correctly augments information on the target objects on the device screen using the pose data. We test several application scenarios to demonstrate the feasibility of the proposed platform for the fabrication and inspection processes of an offshore plant.

Risk assessment based on performantial criterion for inspection of offshore structures in presence of large cracks

Risk assessment based on performantial criterion for inspection of offshore structures in presence of large cracks

Risk assessment based on performantial criterion for inspection of offshore structures in presence of large cracks

When performing risk analysis, it is often uneasy to find the link between limit state and consequences. This paper focuses on efficiency based limit states in case of large cracks on offshore structures. Randomness and uncertainties on loading as well as on crack measurement and detection are introduced.

Underwater inspection of offshore structures

SynopsisUnder the Offshore Installations (Construction and Survey) Regulations 1974 all structures established or maintained in UK waters must possess a valid certificate of fitness. To obtain this certificate annual visual inspections of parts of the structure must be carried out both above and below water. A major survey of the complete structure or platform is required every five years.Underwater inspections may be carried out down to 50 m by divers on surface demand. Below 50 m when divers are involved it is essential to use either a diving bell or lock-out submersible. To avoid saturation diving and reduce diving hazards, the unmanned submersible has been developed as an underwater inspection tool.Various navigation systems have been developed for offshore position fixing. Deepwater navigation and surveying relies on a combination of surface radio stations and seabed underwater acoustic transponders. Platform navigation for underwater inspection and maintenance is a major problem due to poor diving access and few underwater reference points.The inefficiency of the present diver operated navigation and survey systems round platforms is now being investigated by a research team from the University of Strathclyde. Preliminary tests of equipment have already been carried out in a diving tank and at sea.