PACMAN

Challenge

Dealing with corrosion (e.g. rust) on offshore structures such as offshore wind turbines is both expensive and difficult. Much of the work takes place manually in hard-to-reach areas, and it requires both time, money and high security. In addition, there are quite a few regulations and industry standards in the field that must be adhered to, and those things combined make the current process time-consuming, unstructured and not efficient.

Solution

The PACMAN project develops and demonstrates the application of predictive corrosion management – a method that digitizes corrosion monitoring. With the help of machine learning, the program can detect corrosion, assess the extent of the damage and the need for treatment and, not least, predict the need for maintenance in the future.

The tools to be able to perform these automatically predictable corrosion determinations are: automatic position marking, improved corrosion detection through more advanced camera technology, improved machine learning methods for visual detection of corrosion in 2D images, and automatic transfer of 2D image corrosion results to a 3D interpretation for more efficient handling of these corrosion results.

The predictive corrosion identification tool must be able to provide a draft work order and most importantly: drastically reduce time on corrosion management costs.

Effect

Offshore transport reduced by up to 67%

Printed documents reduced by 100%

Time spent on the entire process reduced by up to 85%