Completion of ABS design review helps demonstrate feasibility of the University of Maine's semisubmersible foundation concept for offshore wind facilities.
ABS and its industry and university partners are expediting innovation through collaboration and knowledge-sharing. Research conducted through joint industry projects and university partnerships targets technologies to support the future of classification, which will be continuous and more condition-risk-based. Among the critical technologies under study are sensors and autonomous inspection, materials innovation and nanotechnology.
ABS has supported endowed academic chairs at eight campuses worldwide:
ABS is collaborating with Singapore Polytechnic in the development of a vision-based coating inspection and assessment system which utilizes a deep learning technique to automate coating breakdown and corrosion (CBC) assessment. This project is funded by Singapore Maritime Institute.
Based on machine learning (ML) technology, this system can automatically assess images so as to identify and classify defects such as coating failures, corrosion, and structural damage. A database of thousands of images, which is ever expanding with more images collected from inspections, has been compiled to train and verify the system. This offers the potential for improvements in performance and efficiency over the current industry approach of visual inspection. This methodology can also be extended to identify other defects such as fractures and buckling.
ABS is working with the University of Michigan, Stevens Institute of Technology and Vanderbilt University to study cross-industry processes and best practices for data sourcing, management and analytics supporting risk-informed decision making. The study will explore methods to optimize data use – to improve the client’s classification experience, and drive improved operations and performance for owners and operators.
The studies will focus on several key areas including advanced data analytics, emerging inspection and monitoring technologies, data architecture, application of smart technologies, as well as the overarching data framework. Each university brings a unique perspective and has assigned a team of distinguished researchers to focus on one or more aspects of the study, and contribute to the summary document. Additionally, the university will peer review of other universities’ recommendations.
ABS and National University of Singapore are jointly developing efficient computational techniques for ship analysis and design to improve ship performance by reducing vibration and noise. The project is funded by Singapore Maritime Institute (SMI). The main goal is tackling the added mass effect on ship vibration in sea water, evaluating the magnitude and direction of vibrational energy flow in the ship structure.
Analysis tools developed will facilitate calculation of the added mass associated with ship vibration modes and will be integrated into current workflows for ship design and performance assessment.