ABS Tests Artificial Intelligence Tools for Detecting Corrosion

File image

By The Maritime Executive 04-24-2019 06:00:46

ABS, Google Cloud and Ukrainian software company SoftServe have completed a pilot project using artificial intelligence (AI) models to detect corrosion and coating breakdown on ships and offshore structures. The project successfully demonstrated the accuracy of AI in detecting and assessing structural anomalies found during visual inspection. According to ABS, AI techniques could also be used to analyze images over time to understand corrosion and coating breakdown trends.

“Digital innovation in AI will change how surveys and maintenance strategies are executed, driving more condition-based approaches to class and maintenance,” said ABS Chairman, President and CEO Christopher J. Wiernicki in a statement. “We are building a future in which digital tools can remotely assess the condition of a ship or offshore unit, and automatically detect and measure coating breakdown and other structural issues, improving safety and reliability.”

Computerized interpretation of digital imagery pairs well with drone-based inspection, another area that ABS has pioneered for ships and offshore structures. Drone surveys generate extensive digital video footage, which can potentially be "scanned" by AI or computer vision techniques to detect anomolies. In one study from 2016, this combination was tested by Norwegian researchers for the inspection of corrosion on steel highway bridges. In that study, a deep learning model produced accurate identification of rust in 88 percent of the cases it analyzed. 

ABS' technology relies on much more sophisticated AI tools developed by Google Cloud. "We are excited to team with Google Cloud and SoftServe to effectively apply AI technology to the marine and offshore industries," said ABS Deputy Chief Digital Officer, Kashif Mahmood. “By combining our deep domain experience in offshore and marine structures with Google Cloud’s extensive knowledge of AI applications and SoftServe’s development capabilities, we were able to take this idea from concept to reality.”