HHLA Container Terminal Burchardkai
Hamburg Port Consulting (HPC) is set to implement a machine learning solution for predicted dwell time at the Hamburger Hafun und Logistik AG (HHLA)’s Container Terminal Burchardkai (CTB).
Currently, no specific information is available on the pick-up time by truck upon stack-in slot selection for import containers which can lead to inefficient container storage location in the yard.
Additionally, it results in a high risk for additional shuffle moves requiring extra resources, maintenance and energy.
In order to mitigate this operational efficiency HPC, jointly with software specialist INFORM and HHLA, has utilised machine learning technology to predict the individual container dwell time aiming to reduce the container rehandling for import containers at terminals.
HPC has identified hidden patterns from the historical data of container moves at HHLA CTB over a period of two years and processed this information into high quality data sets.
Alexis Pangalos, head of software engineering at HPC, said: “Data availability and data processing is an important key when it comes to utilising AI technology.
“A detailed analysis, and a smooth interconnectivity between all different gas systems enable the value of the improved safety while reducing costs and greenhouse gas emissions.”
Assessed by the Syncrotess Machine Learning module from INFORM and validated by the HPC simulation tool, the results have shown a significant reduction of shuffle moves which has resulted in a reduced truck turn time.
Jens Hansen, executive board member responsible for IT at HHLA, said: “Utilising machine learning and artificial intelligence and integrating these technologies in existing IT infrastructure are the success factors for reaching the next level of optimisations.
“A detailed analysis, and a smooth interconnectivity between all different systems enable the value of the improved safety while reducing costs and greenhouse gas emissions.”
It is integrated into the existing terminal operating system (TOS) and the algorithm works in the background, further optimising its prediction based on the running operational data.
The TOS-add on solution Dwell Time Prediction is terminal-specific and can be adopted to other terminals as well.
Source: https://container-mag.com/2020/07/13/hamburg-port-consulting-to-implement-machine-learning-solution-for-container-dwell-time-prediction/
