Abstract
As the offshore energy sector moves towards renewable energy solutions and sustainable practices in oil and gas, the need for safe, efficient, and environmentally responsible operations are more critical than ever. Sophisticated marine operations, involving advanced vessels and technologies, are key to achieving these objectives.
Historically, decisions to proceed with or stop offshore operations have relied on the well-established metrics significant wave height (Hs) and peak wave period (Tp). While these parameters provide practical assessments due to their direct measurability and accessibility from wave forecasts by weather service providers, they often oversimplify the complex interactions between environmental factors and product responses. This can lead to unnecessary weather-related delays and increased vessel emissions, or worse, unsafe conditions.
Our objective is to further develop and promote alternative approaches with real-world applicability that enables the offshore energy sector to move towards safer, and more efficient and environmentally responsible operations.
The Vessel Motion Based Criteria (VMBC) methodology has been proposed in two previous studies as an advanced approach to improve the accuracy of operability assessments by linking the vessels motion with product response parameters. However, its effectiveness has relied on engineers' ability to capture potentially complex and non-linear relationships between these parameters. Therefore, VMBC is often applied in scenarios where apparent linear relationships are observed, leaving much of its potential untapped.
This paper introduces an enhanced interpretation of VMBC that utilizes mature machine learning classification techniques to capture the relationship between vessel motion and product response parameters. The enhancement aims to extend VMBC's applicability to scenarios characterized by non-linear interactions involving multiple parameters. By leveraging machine learning, the revised VMBC approach not only addresses scenarios with less obvious relationships but also streamlines the process of setting operational limits. The automation of this process significantly reduces the engineering effort required, resulting in greater accuracy and efficiency of operability determinations.
A real-world offshore case study is presented comparing this enhanced VMBC methodology with the previous interpretations and traditional operability assessment methods, focusing on accuracy and operational efficiency gains. The present work marks a significant step forward in integrating digital tools with advanced operability determination methodologies.
Digital decision-support tools are revolutionizing the field by automating much of the weather assessment process and enabling the use of more advanced operability determination methods. The enhanced VMBC method is well-suited for integration into these tools, leveraging rich weather datasets to offer a transformative approach to operability analysis.
