In the COOKIE project, the CML is working with project partners to develop software for image-based damage detection in empty container inspection based on artificial intelligence. This will not only comply with applicable safety standards, but also make inspection processes at the terminal gate more efficient.
Furthermore, the CML is developing an AI-based concept for digitizing and optimizing tank container washing systems, which are currently largely controlled manually and require large quantities of water and chemical additives to clean stubborn contaminants in the tanks.
Overall, the plan is to improve the plannability of maintenance and availability of empty containers in the Port of Hamburg. As part of "Maintenance & Repair" (maintenance and repairs of empty containers), AI-based image recognition is to support inspectors in damage identification and assessment, thereby increasing the uniformity of damage assessment. This leads to a better probing of healed and damaged containers as well as to a better planning of the reuse of empty containers.
In the "tank container cleaning" application field, an optimal cleaning program is to be learned independently by an AI system and cleaning procedures are to be documented in order to achieve the greatest possible automation of the systems while simultaneously increasing resource efficiency. Modern algorithms from the field of reinforcement learning will be used for this purpose.
Role of the CML in COOKIE:
The CML uses its knowledge and experience in the field of machine learning in the COOKIE project. The focus here is on self-learning reinforcement learning and computer vision as a key technology for automated status recording and the detection of changes.
HCCR Hamburger Container- und Chassis-Repair GmbH (coordinator), Fraunhofer Center for Maritime Logistics and Services CML.
COOKIE is funded by the research program IHATEC - Innovative Port Technologies of the Federal Ministry of Transport and Digital Infrastructure in the period from November 2019 to April 2022.