Class society ABS reports that tests of a new Artificial Intelligence (AI) powered Corrosion Detection system have returned results showing 98.9% accuracy in identifying corrosion in vessel tank coatings.
A structural-focused digital system, the ABS AI Corrosion Detection tool utilises an AI algorithm that analyses images and video files to deliver prediction scores and percentages for tank coating breakdown and corrosion. The results allow operators to benchmark and monitor coating changes over time to assist with vessel maintenance between surveys.
Using machine learning automated pattern identification, clients can be provided with proactive alerts of structural defects such as coating failures, fractures and deformations without the need for traditional structural inspections.
The system tests were carried out during examinations of two vessels to develop an accurate assessment of their coating conditions and the presence of corrosion. The reported 98.9% accurate results are based on the AI tool’s analysis of more than 600 images of ballast water tanks.
ABS says that these baseline results should also continue to improve in the future as the system is given more images to analyse to further train the algorithm.
“Corrosion is one of the biggest maintenance challenges in the maritime industry with the total cost estimated at between $50 billion and $80 billion annually,” said Kash Mahmood, ABS Senior Vice President, Digital Solutions.
“This application of advanced machine learning technology to assist with tank coating and corrosion management is unique to ABS, and now we are able to demonstrate that it is highly effective in real world applications.”