Session: 01-08-02 Digitalization, AI/ML, Digital Twins - II

Submission Number: 157554

Advanced Sensors and Digital Twin Technology for Reliable Mooring Integrity
Assessment Through Physics Based Models 

Offshore mooring systems primarily use chains, wire ropes, and polyester segments to connect floaters to anchors, providing seakeeping in harsh marine environments. These systems are subjected to dynamic loads and are vulnerable to degradation and failure due to corrosion, fatigue etc. The current state of mooring monitoring includes direct and indirect line load measurement systems, as well as developments in artificial neural networks (ANNs) for detecting mooring line failures. Direct load measurement systems (e.g., load cells) interfere with mooring line action, are expensive, difficult to maintain, and are often unreliable. Indirect load measurement systems, such as inclinometers, which measure the shape of mooring lines, overcome these shortcomings and are generally more reliable. ANN-based monitoring systems are useful for detecting line failures after the fact but require considerable training with simulated inputs to be effective. As the offshore renewable energy sector expands, particularly with floating offshore wind turbines (FOWTs), there is an increasing demand for more reliable, cost-effective, and proactive monitoring solutions.

To address these challenges, this paper presents the latest advances in a physics-based Mooring Condition Monitoring System (MCMS) that offers a scalable and cost-effective solution for real-time mooring integrity assessment. The system utilizes reliable sensors, including Global Positioning System (GPS) units and Motion Reference Unit (MRU), which continuously collect data without interfering with mooring operations. The system also implements advanced analytics by processing the collected data through the BMT DEEP analytics platform, incorporating Digital Twin Technology to create a dynamic, real-time digital replica of the mooring system. By synthesizing data from multiple sources into a common time reference, the MCMS enables comprehensive, remote monitoring and proactive maintenance of mooring systems, reducing reliance on costly inspections and improving overall safety and operational efficiency. At the core of the MCMS is a solver engine that integrates both quasi-static and dynamic mooring models, incorporating component weights, elastic properties, and segment cross-sectional areas. Material properties are periodically updated to account for the effects of corrosion and creep. In this study, the proposed MCMS is applied to the operational data collected from the world’s first commercial floating-wind farm (Hywind Scotland Pilot Park) to predict mooring line responses. The challenges encountered in this process are highlighted, along with the steps taken to overcome them.

Presenting Author: Suvabrata Das BMT Commercial USA Inc.

Presenting Author Biography: Suvabrata Das is currently working as a Principal Data Analyst with BMT Commercial USA Inc.
The focus of his present work is asset monitoring and digital twin development. He has over 15
years of industry experience as a Naval Architect, in the field of hydrodynamic and structural
analysis. He has earlier obtained his Ph.D. and M.S. in Ocean Engineering from the University
of Hawaii at Manoa, and his bachelor's degree in Naval Architecture from the Indian Institute of
Technology at Kharagpur.