To main content

PRAI: Prediction of Riser-response by Artificial Intelligence

The objective of PRAI is to develop a hybrid VIV response prediction model combined of physics-based numerical models and data-driven machine learning methods.

Contact person

  • Jie Wu

    Jie Wu

    Senior Research Scientist Energy and Transport

The model will be developed for response estimation in the design of deep-water riser systems, but can also be integrated in future on-board riser management systems. This will lead to reduced cost and increased safety of these systems in both design and operation. The methods developed in PRAI are equally applicable to other offshore slender structures, such as risers for deep-sea mining, mooring lines and power cables for floating wind turbines, etc.

Background

Deep-water risers are continuously exposed to complex external loads, e.g., currents, waves and vessel motions. Vortices will be shed periodically around the riser under various flow conditions, which may cause resonance when the shedding frequency is close to the natural frequency of the riser. This so-called Vortex Induced Vibrations (VIV) due to may lead to fast accumulation of fatigue damage to the structure. Consequently, VIV represents a safety risk and is a major design consideration adding notable costs to all stages of the riser system development. Offshore platforms collect data from onboard sensors, but the sensor density along the risers is limited. Consequently, the state-of-the-art models for VIV response prediction cannot provide sufficient precision for on-board monitoring and decision support. The industry standard is to compensate the large uncertainties with expensive safety factors.

The novelty of PRAI is to combine a recently developed time-domain VIV prediction model with concepts from machine learning. The time-domain modelling allows for intuitive interpretation of the underlying physical phenomena, while the machine learning infers connections directly from available sensor data. Methods where we combine physical methods and machine learning are called hybrid analytics.   

 

 

 

Key Factors

Project duration

2020 - 2024

Budget:

NOK 15,2 mill.

 

 

 

 

Explore research areas