PILOT : DUISPORT INLAND PORT AS INTELLIGENT LOGISTICS HUB

The duisport pilot will demonstrate the use of big data solutions for the proactive management of terminal operations as well as for predictive maintenance of terminal equipment. The port is situated in Duisburg, a city with close to ½ million inhabitants. The port lies at the center of Germany’s largest metropolitan area, the Rhine-Ruhr metropolitan region, with close to 12 million inhabitants. duisport is connected to all modes of transport (road, rail, inland waterways). The different transport modes serve as entry and exit points for containers to and from the different terminals in the port.

With a total handling of 4.1 million TEU (= Twenty-foot equivalent unit, a measure used for capacity in container transportation, based on the volume of a 20-foot-long intermodal container), duisport is the world’s largest inland port. The approximately 300 logistics-oriented enterprises located at the Port of Duisburg generate value of about 3 billion euros per year. Eight multi-modal container terminals, over 400 weekly combined transports to over 80 direct destinations in Europe and Asia as well as comprehensive warehousing and storage capacities are tied in locally with market- and customer-oriented services.

This pilot utilizes the sheer amount of data generated by all the different actors on the port to make sure the resources are used in the most effective way, by predicting the future outcome of running processes and enabling port operators to proactively adapt those. This is done with the help of cutting edge deep learning prediction models and big data technology. In general, the pilot pursues two objectives:

1. Improve port operations by predicting the future outcome of ongoing business processes, enabling proactive process adaptations.
2. Reduce maintenance cost and waste by predicting breakdowns of port equipment, to make sure maintenance is performed before any major damage happens.

Pilot objectives:

• Predict problems in port operations before they happen
  • Improve the train unloading and loading processes
  • Optimize maintenance lifecycles

Expected Results:

• More trains leaving the terminal on time
• Reduced maintenance cost by optimizing maintenance lifecycles
• Increase of container throughput of port equipment by increasing productive time

The main KPIs of the pilot are:

• Number of trains leaving the terminal on time
• Proportion of productive time of operational time
• Number of container handlings before an equipment failure occurs